diff --git a/.circleci/config.yml b/.circleci/config.yml index 8cf200b826..96b38cff44 100644 --- a/.circleci/config.yml +++ b/.circleci/config.yml @@ -7,10 +7,10 @@ executors: # should also be updated. golang: docker: - - image: cimg/go:1.22 + - image: cimg/go:1.23 arm: - machine: - image: ubuntu-2204:current + docker: + - image: cimg/go:1.23 resource_class: arm.medium jobs: @@ -25,7 +25,7 @@ jobs: test-arm: executor: arm steps: - - checkout + - prometheus/setup_environment - run: uname -a - run: make test-e2e test_mixins: @@ -70,7 +70,7 @@ jobs: machine: image: ubuntu-2204:current environment: - DOCKER_TEST_IMAGE_NAME: quay.io/prometheus/golang-builder:1.22-base + DOCKER_TEST_IMAGE_NAME: quay.io/prometheus/golang-builder:1.23-base REPO_PATH: github.com/prometheus/node_exporter steps: - prometheus/setup_environment diff --git a/.github/workflows/bsd.yml b/.github/workflows/bsd.yml new file mode 100644 index 0000000000..09aa1b5c90 --- /dev/null +++ b/.github/workflows/bsd.yml @@ -0,0 +1,313 @@ +name: bsd + +on: + push: + branches: + - master + pull_request: + branches: + - master + +permissions: + contents: read + +env: + GNU_TAR_VERSION: "1.35" + GO_VERSION_DRAGONFLY: "1.23.3" + GO_VERSION_FREEBSD: "123" + GO_VERSION_NETBSD: "1.23.3" + GO_VERSION_OPENBSD: "1.23.1" + GO_VERSION_SOLARIS: "1.23.3" + +# To spin up one of the VMs below, see the "Debug Shell" section here: https://github.com/vmactions +jobs: + test_freebsd: + name: Run end-to-end tests on FreeBSD + runs-on: ubuntu-latest + steps: + - name: Checkout the repository + uses: actions/checkout@v4 + - name: test-e2e + uses: vmactions/freebsd-vm@v1 + with: + copyback: false + envs: 'GO_VERSION_FREEBSD GNU_TAR_VERSION' + usesh: true + prepare: | + pkg update -f + pkg install -y \ + bash \ + git \ + gmake \ + gnugrep \ + go${GO_VERSION_FREEBSD} \ + gsed \ + gtar \ + python \ + wget + run: | + echo "::group::Setup prerequisites" + set -eu + mkdir bin + ln -s $(which go${GO_VERSION_FREEBSD}) $(pwd)/bin/go + ln -s $(which ggrep) $(pwd)/bin/grep + ln -s $(which gmake) $(pwd)/bin/make + ln -s $(which gsed) $(pwd)/bin/sed + ln -s $(which gtar) $(pwd)/bin/tar + export PATH=$(pwd)/bin:$PATH + echo "::endgroup::" + + echo "::group::Print environment information" + uname -a + echo "GOOS: $(go env GOOS)" + echo "GOARCH: $(go env GOARCH)" + echo "::endgroup::" + + echo "::group::Run End-to-End Tests" + git config --global --add safe.directory $(pwd) + gmake test-e2e + echo "::endgroup::" + + test_openbsd: + name: Run end-to-end tests on OpenBSD + runs-on: ubuntu-latest + steps: + - name: Checkout the repository + uses: actions/checkout@v4 + - name: test-e2e + uses: vmactions/openbsd-vm@v1 + with: + copyback: false + envs: 'GO_VERSION_OPENBSD GNU_TAR_VERSION' + usesh: true + prepare: | + pkg_add -u + pkg_add \ + bash \ + ggrep \ + git \ + gmake \ + go-${GO_VERSION_OPENBSD} \ + gsed \ + gtar-${GNU_TAR_VERSION}p0-static \ + python \ + wget + run: | + echo "::group::Setup prerequisites" + set -eu + mkdir bin + ln -s $(which ggrep) $(pwd)/bin/grep + ln -s $(which gmake) $(pwd)/bin/make + ln -s $(which gsed) $(pwd)/bin/sed + ln -s $(which gtar) $(pwd)/bin/tar + export PATH=$(pwd)/bin:$PATH + echo "::endgroup::" + + echo "::group::Print environment information" + uname -a + echo "GOOS: $(go env GOOS)" + echo "GOARCH: $(go env GOARCH)" + echo "::endgroup::" + + echo "::group::Run End-to-End Tests" + git config --global --add safe.directory $(pwd) + make test-e2e + echo "::endgroup::" + + test_netbsd: + name: Run end-to-end tests on NetBSD + runs-on: ubuntu-latest + steps: + - name: Checkout the repository + uses: actions/checkout@v4 + - name: test-e2e + uses: vmactions/netbsd-vm@v1 + with: + copyback: false + envs: 'GO_VERSION_NETBSD GNU_TAR_VERSION' + usesh: true + prepare: | + /usr/sbin/pkg_add -u + /usr/sbin/pkg_add \ + git \ + gmake \ + grep \ + gsed \ + gtar-base-${GNU_TAR_VERSION}\ + python312 \ + wget + run: | + echo "::group::Setup prerequisites" + set -eu + mkdir bin + GOGZ="go${GO_VERSION_NETBSD}.netbsd-amd64.tar.gz" + wget https://go.dev/dl/${GOGZ} + gtar xzf ${GOGZ} + ln -s $(pwd)/go/bin/go $(pwd)/bin/go + ln -s $(which ggrep) $(pwd)/bin/grep + ln -s $(which gmake) $(pwd)/bin/make + ln -s $(which gsed) $(pwd)/bin/sed + ln -s $(which gtar) $(pwd)/bin/tar + export PATH=$(pwd)/bin:$PATH + echo "::endgroup::" + + echo "::group::Print environment information" + uname -a + echo "GOOS: $(go env GOOS)" + echo "GOARCH: $(go env GOARCH)" + echo "::endgroup::" + + echo "::group::Run End-to-End Tests" + git config --global --add safe.directory $(pwd) + make test-e2e + echo "::endgroup::" + + test_dragonfly: + name: Run end-to-end tests on DragonFly + runs-on: ubuntu-latest + steps: + - name: Checkout the repository + uses: actions/checkout@v4 + - name: test-e2e + uses: vmactions/dragonflybsd-vm@v1 + with: + copyback: false + envs: 'GO_VERSION_DRAGONFLY' + usesh: true + prepare: | + pkg update && pkg upgrade -y + pkg install -y \ + bash \ + git \ + gmake \ + gnugrep \ + gsed \ + gtar \ + python3 \ + wget + run: | + echo "::group::Setup prerequisites" + set -eu + mkdir bin + GOGZ="go${GO_VERSION_DRAGONFLY}.dragonfly-amd64.tar.gz" + wget https://go.dev/dl/${GOGZ} + gtar xzf ${GOGZ} + ln -s $(pwd)/go/bin/go $(pwd)/bin/go + ln -s $(which ggrep) $(pwd)/bin/grep + ln -s $(which gmake) $(pwd)/bin/make + ln -s $(which gsed) $(pwd)/bin/sed + ln -s $(which gtar) $(pwd)/bin/tar + ln -s $(which python3) $(pwd)/bin/python + export PATH=$(pwd)/bin:$PATH + echo "::endgroup::" + + echo "::group::Print environment information" + uname -a + echo "GOOS: $(go env GOOS)" + echo "GOARCH: $(go env GOARCH)" + echo "::endgroup::" + + echo "::group::Run End-to-End Tests" + git config --global --add safe.directory $(pwd) + gmake test-e2e + echo "::endgroup::" + + test_solaris: + name: Run end-to-end tests on Solaris + runs-on: ubuntu-latest + steps: + - name: Checkout the repository + uses: actions/checkout@v4 + - name: test-e2e + uses: vmactions/solaris-vm@v1 + with: + copyback: false + envs: 'GO_VERSION_SOLARIS' + usesh: true + prepare: | + pkg update + pkg install \ + bash \ + curl \ + gcc \ + git \ + gnu-grep \ + gnu-make \ + gnu-sed \ + gnu-tar + run: | + echo "::group::Setup prerequisites" + set -eu + mkdir bin + GOGZ="go${GO_VERSION_SOLARIS}.solaris-amd64.tar.gz" + wget https://go.dev/dl/${GOGZ} + gtar xzf ${GOGZ} + ln -s $(pwd)/go/bin/go $(pwd)/bin/go + ln -s $(which ggrep) $(pwd)/bin/grep + ln -s $(which gmake) $(pwd)/bin/make + ln -s $(which gsed) $(pwd)/bin/sed + ln -s $(which gtar) $(pwd)/bin/tar + export PATH=$(pwd)/bin:$PATH + + echo ">> building promu as it is not shipped for Solaris" + git clone https://github.com/prometheus/promu.git + cd promu + go build . + cd - + + mkdir -p $(go env GOPATH)/bin + ln -s $(pwd)/promu/promu $(go env GOPATH)/bin/promu + export PATH=$(go env GOPATH)/bin:$PATH + echo "::endgroup::" + + echo "::group::Print environment information" + uname -a + echo "GOOS: $(go env GOOS)" + echo "GOARCH: $(go env GOARCH)" + echo "::endgroup::" + + echo "::group::Run End-to-End Tests" + git config --global --add safe.directory $(pwd) + make test-e2e + echo "::endgroup::" + + test_macos: + name: Run end-to-end tests on macOS + runs-on: macos-latest + steps: + - name: Checkout the repository + uses: actions/checkout@v4 + - name: Install dependencies + run: | + brew install \ + bash \ + curl \ + git \ + grep \ + make \ + gnu-sed \ + gnu-tar \ + go \ + python3 + - name: test-e2e + run: | + echo "::group::Setup prerequisites" + set -eu + mkdir bin + ln -s $(which ggrep) $(pwd)/bin/grep + ln -s $(which gmake) $(pwd)/bin/make + ln -s $(which gsed) $(pwd)/bin/sed + ln -s $(which gtar) $(pwd)/bin/tar + export PATH=$(pwd)/bin:$PATH + echo "::endgroup::" + + echo "::group::Print environment information" + uname -a + echo "GOOS: $(go env GOOS)" + echo "GOARCH: $(go env GOARCH)" + echo "::endgroup::" + + echo "::group::Run End-to-End Tests" + git config --global --add safe.directory $(pwd) + make test-e2e + echo "::endgroup::" diff --git a/.github/workflows/container_description.yml b/.github/workflows/container_description.yml index a7d7e150c0..dcca16ff34 100644 --- a/.github/workflows/container_description.yml +++ b/.github/workflows/container_description.yml @@ -4,6 +4,7 @@ on: push: paths: - "README.md" + - "README-containers.md" - ".github/workflows/container_description.yml" branches: [ main, master ] @@ -17,7 +18,7 @@ jobs: if: github.repository_owner == 'prometheus' || github.repository_owner == 'prometheus-community' # Don't run this workflow on forks. steps: - name: git checkout - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4.1.4 + uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 - name: Set docker hub repo name run: echo "DOCKER_REPO_NAME=$(make docker-repo-name)" >> $GITHUB_ENV - name: Push README to Dockerhub @@ -29,7 +30,9 @@ jobs: destination_container_repo: ${{ env.DOCKER_REPO_NAME }} provider: dockerhub short_description: ${{ env.DOCKER_REPO_NAME }} - readme_file: 'README.md' + # Empty string results in README-containers.md being pushed if it + # exists. Otherwise, README.md is pushed. + readme_file: '' PushQuayIoReadme: runs-on: ubuntu-latest @@ -37,7 +40,7 @@ jobs: if: github.repository_owner == 'prometheus' || github.repository_owner == 'prometheus-community' # Don't run this workflow on forks. steps: - name: git checkout - uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4.1.4 + uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 - name: Set quay.io org name run: echo "DOCKER_REPO=$(echo quay.io/${GITHUB_REPOSITORY_OWNER} | tr -d '-')" >> $GITHUB_ENV - name: Set quay.io repo name @@ -49,4 +52,6 @@ jobs: with: destination_container_repo: ${{ env.DOCKER_REPO_NAME }} provider: quay - readme_file: 'README.md' + # Empty string results in README-containers.md being pushed if it + # exists. Otherwise, README.md is pushed. + readme_file: '' diff --git a/.github/workflows/golangci-lint.yml b/.github/workflows/golangci-lint.yml index dde726dea5..d07f38e593 100644 --- a/.github/workflows/golangci-lint.yml +++ b/.github/workflows/golangci-lint.yml @@ -24,11 +24,11 @@ jobs: runs-on: ubuntu-latest steps: - name: Checkout repository - uses: actions/checkout@9bb56186c3b09b4f86b1c65136769dd318469633 # v4.1.2 - - name: install Go - uses: actions/setup-go@0c52d547c9bc32b1aa3301fd7a9cb496313a4491 # v5.0.0 + uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 + - name: Install Go + uses: actions/setup-go@f111f3307d8850f501ac008e886eec1fd1932a34 # v5.3.0 with: - go-version: 1.22.x + go-version: 1.23.x - name: Install snmp_exporter/generator dependencies run: sudo apt-get update && sudo apt-get -y install libsnmp-dev if: github.repository == 'prometheus/snmp_exporter' diff --git a/.gitignore b/.gitignore index a2e66eb96b..988b39cdcc 100644 --- a/.gitignore +++ b/.gitignore @@ -27,6 +27,8 @@ dependencies-stamp /.release /.tarballs +tools/tools + # Intellij /.idea diff --git a/.golangci.yml b/.golangci.yml index 472b3a5e13..8731aefdf1 100644 --- a/.golangci.yml +++ b/.golangci.yml @@ -1,17 +1,9 @@ linters: enable: - depguard + - goimports - misspell - revive - disable: - # Disable soon to deprecated[1] linters that lead to false - # positives when build tags disable certain files[2] - # 1: https://github.com/golangci/golangci-lint/issues/1841 - # 2: https://github.com/prometheus/node_exporter/issues/1545 - - deadcode - - unused - - structcheck - - varcheck issues: exclude-rules: @@ -32,8 +24,6 @@ linters-settings: exclude-functions: # Used in HTTP handlers, any error is handled by the server itself. - (net/http.ResponseWriter).Write - # Never check for logger errors. - - (github.com/go-kit/log.Logger).Log revive: rules: # https://github.com/mgechev/revive/blob/master/RULES_DESCRIPTIONS.md#unused-parameter diff --git a/.promu-cgo.yml b/.promu-cgo.yml index f270f78a29..542f51e25b 100644 --- a/.promu-cgo.yml +++ b/.promu-cgo.yml @@ -1,7 +1,7 @@ go: # Whenever the Go version is updated here, .circle/config.yml and # .promu.yml should also be updated. - version: 1.22 + version: 1.23 cgo: true repository: path: github.com/prometheus/node_exporter diff --git a/.promu.yml b/.promu.yml index 8f883591a1..fcba92d081 100644 --- a/.promu.yml +++ b/.promu.yml @@ -1,7 +1,7 @@ go: # Whenever the Go version is updated here, .circle/config.yml and # .promu-cgo.yml should also be updated. - version: 1.22 + version: 1.23 repository: path: github.com/prometheus/node_exporter build: diff --git a/.yamllint b/.yamllint index 1859cb624b..8d09c375fd 100644 --- a/.yamllint +++ b/.yamllint @@ -1,7 +1,7 @@ --- extends: default ignore: | - ui/react-app/node_modules + **/node_modules rules: braces: diff --git a/CHANGELOG.md b/CHANGELOG.md index ee248324cc..2360e8578b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,9 +5,42 @@ * [ENHANCEMENT] * [BUGFIX] -## 1.8.2 / 2024-06-19 - -* [BUGFIX] Fix CPU pressure metric collection #3054 +## 1.9.1 / 2025-04-01 + +* [BUGFIX] pressure: Fix missing IRQ on older kernels #3263 +* [BUGFIX] Fix Darwin memory leak #3277 + +## 1.9.0 / 2025-02-17 + +* [CHANGE] meminfo: Convert linux implementation to use procfs lib #3049 +* [CHANGE] Update logging to use Go log/slog #3097 +* [FEATURE] filesystem: Add `node_filesystem_mount_info` metric #2970 +* [FEATURE] btrfs: Add metrics for commit statistics #3010 +* [FEATURE] interrupts: Add collector include/exclude filtering #3028 +* [FEATURE] interrupts: Add "exclude zeros" filtering #3028 +* [FEATURE] slabinfo: Add filters for slab name. #3041 +* [FEATURE] pressure: add IRQ PSI metrics #3048 +* [FEATURE] hwmon: Add include and exclude filter for sensors #3072 +* [FEATURE] filesystem: Add NetBSD support #3082 +* [FEATURE] netdev: Add ifAlias label #3087 +* [FEATURE] hwmon: Add Support for GPU Clock Frequencies #3093 +* [FEATURE] Add `exclude[]` URL parameter #3116 +* [FEATURE] Add AIX support #3136 +* [FEATURE] filesystem: Add fs-types/mount-points include flags #3171 +* [FEATURE] netstat: Add collector for tcp packet counters for FreeBSD. #3177 +* [ENHANCEMENT] ethtool: Add logging for filtering flags #2979 +* [ENHANCEMENT] netstat: Add TCPRcvQDrop to default metrics #3021 +* [ENHANCEMENT] diskstats: Add block device rotational #3022 +* [ENHANCEMENT] cpu: Support CPU online status #3032 +* [ENHANCEMENT] arp: optimize interface name resolution #3133 +* [ENHANCEMENT] textfile: Allow specifiying multiple directory globs #3135 +* [ENHANCEMENT] filesystem: Add reporting of purgeable space on MacOS #3206 +* [ENHANCEMENT] ethtool: Skip full scan of NetClass directories #3239 +* [BUGFIX] zfs: Prevent `procfs` integer underflow #2961 +* [BUGFIX] pressure: Fix collection on systems that do not expose a full CPU stat #3054 +* [BUGFIX] cpu: Fix FreeBSD 32-bit host support and plug memory leak #3083 +* [BUGFIX] hwmon: Add safety check to hwmon read #3134 +* [BUGFIX] zfs: Allow space in dataset name #3186 ## 1.8.1 / 2024-05-16 diff --git a/Makefile b/Makefile index b19480e667..4cea420129 100644 --- a/Makefile +++ b/Makefile @@ -117,9 +117,13 @@ update_fixtures: rm -vf collector/fixtures/udev/.unpacked ./ttar -C collector/fixtures -c -f collector/fixtures/udev.ttar udev +.PHONY: tools +tools: + @rm ./tools/tools >/dev/null 2>&1 || true + @$(GO) build -o tools ./tools/... .PHONY: test-e2e -test-e2e: build collector/fixtures/sys/.unpacked collector/fixtures/udev/.unpacked +test-e2e: build collector/fixtures/sys/.unpacked collector/fixtures/udev/.unpacked tools @echo ">> running end-to-end tests" ./end-to-end-test.sh diff --git a/Makefile.common b/Makefile.common index 0e9ace29b4..d1576bb313 100644 --- a/Makefile.common +++ b/Makefile.common @@ -61,7 +61,7 @@ PROMU_URL := https://github.com/prometheus/promu/releases/download/v$(PROMU_ SKIP_GOLANGCI_LINT := GOLANGCI_LINT := GOLANGCI_LINT_OPTS ?= -GOLANGCI_LINT_VERSION ?= v1.56.2 +GOLANGCI_LINT_VERSION ?= v1.63.4 # golangci-lint only supports linux, darwin and windows platforms on i386/amd64/arm64. # windows isn't included here because of the path separator being different. ifeq ($(GOHOSTOS),$(filter $(GOHOSTOS),linux darwin)) @@ -275,3 +275,9 @@ $(1)_precheck: exit 1; \ fi endef + +govulncheck: install-govulncheck + govulncheck ./... + +install-govulncheck: + command -v govulncheck > /dev/null || go install golang.org/x/vuln/cmd/govulncheck@latest diff --git a/README.md b/README.md index ad385650a4..ff5d27ead0 100644 --- a/README.md +++ b/README.md @@ -99,11 +99,14 @@ cpu | flags | --collector.cpu.info.flags-include | N/A diskstats | device | --collector.diskstats.device-include | --collector.diskstats.device-exclude ethtool | device | --collector.ethtool.device-include | --collector.ethtool.device-exclude ethtool | metrics | --collector.ethtool.metrics-include | N/A -filesystem | fs-types | N/A | --collector.filesystem.fs-types-exclude -filesystem | mount-points | N/A | --collector.filesystem.mount-points-exclude +filesystem | fs-types | --collector.filesystem.fs-types-include | --collector.filesystem.fs-types-exclude +filesystem | mount-points | --collector.filesystem.mount-points-include | --collector.filesystem.mount-points-exclude hwmon | chip | --collector.hwmon.chip-include | --collector.hwmon.chip-exclude +hwmon | sensor | --collector.hwmon.sensor-include | --collector.hwmon.sensor-exclude +interrupts | name | --collector.interrupts.name-include | --collector.interrupts.name-exclude netdev | device | --collector.netdev.device-include | --collector.netdev.device-exclude qdisk | device | --collector.qdisk.device-include | --collector.qdisk.device-exclude +slabinfo | slab-names | --collector.slabinfo.slabs-include | --collector.slabinfo.slabs-exclude sysctl | all | --collector.sysctl.include | N/A systemd | unit | --collector.systemd.unit-include | --collector.systemd.unit-exclude @@ -336,13 +339,21 @@ mv /path/to/directory/role.prom.$$ /path/to/directory/role.prom The `node_exporter` will expose all metrics from enabled collectors by default. This is the recommended way to collect metrics to avoid errors when comparing metrics of different families. -For advanced use the `node_exporter` can be passed an optional list of collectors to filter metrics. The `collect[]` parameter may be used multiple times. In Prometheus configuration you can use this syntax under the [scrape config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#). +For advanced use the `node_exporter` can be passed an optional list of collectors to filter metrics. The parameters `collect[]` and `exclude[]` can be used multiple times (but cannot be combined). In Prometheus configuration you can use this syntax under the [scrape config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#). +Collect only `cpu` and `meminfo` collector metrics: ``` params: collect[]: - - foo - - bar + - cpu + - meminfo +``` + +Collect all enabled collector metrics but exclude `netdev`: +``` + params: + exclude[]: + - netdev ``` This can be useful for having different Prometheus servers collect specific metrics from nodes. @@ -371,7 +382,7 @@ To see all available configuration flags: ## TLS endpoint -** EXPERIMENTAL ** +**EXPERIMENTAL** The exporter supports TLS via a new web configuration file. diff --git a/VERSION b/VERSION index 53adb84c82..9ab8337f39 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.8.2 +1.9.1 diff --git a/collector/arp_linux.go b/collector/arp_linux.go index c7861156f3..e1ba52c8c2 100644 --- a/collector/arp_linux.go +++ b/collector/arp_linux.go @@ -17,13 +17,11 @@ package collector import ( - "errors" "fmt" - "net" + "log/slog" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/jsimonetti/rtnetlink" + "github.com/jsimonetti/rtnetlink/v2/rtnl" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" "golang.org/x/sys/unix" @@ -39,7 +37,7 @@ type arpCollector struct { fs procfs.FS deviceFilter deviceFilter entries *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -47,7 +45,7 @@ func init() { } // NewARPCollector returns a new Collector exposing ARP stats. -func NewARPCollector(logger log.Logger) (Collector, error) { +func NewARPCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -76,44 +74,30 @@ func getTotalArpEntries(deviceEntries []procfs.ARPEntry) map[string]uint32 { } func getTotalArpEntriesRTNL() (map[string]uint32, error) { - conn, err := rtnetlink.Dial(nil) + conn, err := rtnl.Dial(nil) if err != nil { return nil, err } defer conn.Close() - neighbors, err := conn.Neigh.List() + // Neighbors will also contain IPv6 neighbors, but since this is purely an ARP collector, + // restrict to AF_INET. + neighbors, err := conn.Neighbours(nil, unix.AF_INET) if err != nil { return nil, err } - ifIndexEntries := make(map[uint32]uint32) + // Map of interface name to ARP neighbor count. + entries := make(map[string]uint32) for _, n := range neighbors { - // Neighbors will also contain IPv6 neighbors, but since this is purely an ARP collector, - // restrict to AF_INET. Also skip entries which have state NUD_NOARP to conform to output - // of /proc/net/arp. - if n.Family == unix.AF_INET && n.State&unix.NUD_NOARP == 0 { - ifIndexEntries[n.Index]++ + // Skip entries which have state NUD_NOARP to conform to output of /proc/net/arp. + if n.State&unix.NUD_NOARP == 0 { + entries[n.Interface.Name]++ } } - enumEntries := make(map[string]uint32) - - // Convert interface indexes to names. - for ifIndex, entryCount := range ifIndexEntries { - iface, err := net.InterfaceByIndex(int(ifIndex)) - if err != nil { - if errors.Unwrap(err).Error() == "no such network interface" { - continue - } - return nil, err - } - - enumEntries[iface.Name] = entryCount - } - - return enumEntries, nil + return entries, nil } func (c *arpCollector) Update(ch chan<- prometheus.Metric) error { diff --git a/collector/bcache_linux.go b/collector/bcache_linux.go index 1d402d3ff5..97064e2197 100644 --- a/collector/bcache_linux.go +++ b/collector/bcache_linux.go @@ -18,9 +18,9 @@ package collector import ( "fmt" + "log/slog" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/bcache" ) @@ -36,12 +36,12 @@ func init() { // A bcacheCollector is a Collector which gathers metrics from Linux bcache. type bcacheCollector struct { fs bcache.FS - logger log.Logger + logger *slog.Logger } // NewBcacheCollector returns a newly allocated bcacheCollector. // It exposes a number of Linux bcache statistics. -func NewBcacheCollector(logger log.Logger) (Collector, error) { +func NewBcacheCollector(logger *slog.Logger) (Collector, error) { fs, err := bcache.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) diff --git a/collector/bonding_linux.go b/collector/bonding_linux.go index d9d04e222c..bfec32fd70 100644 --- a/collector/bonding_linux.go +++ b/collector/bonding_linux.go @@ -19,18 +19,17 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "path/filepath" "strings" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) type bondingCollector struct { slaves, active typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -39,7 +38,7 @@ func init() { // NewBondingCollector returns a newly allocated bondingCollector. // It exposes the number of configured and active slave of linux bonding interfaces. -func NewBondingCollector(logger log.Logger) (Collector, error) { +func NewBondingCollector(logger *slog.Logger) (Collector, error) { return &bondingCollector{ slaves: typedDesc{prometheus.NewDesc( prometheus.BuildFQName(namespace, "bonding", "slaves"), @@ -61,7 +60,7 @@ func (c *bondingCollector) Update(ch chan<- prometheus.Metric) error { bondingStats, err := readBondingStats(statusfile) if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "Not collecting bonding, file does not exist", "file", statusfile) + c.logger.Debug("Not collecting bonding, file does not exist", "file", statusfile) return ErrNoData } return err diff --git a/collector/boot_time_bsd.go b/collector/boot_time_bsd.go index 8a9c17b31a..d632fef094 100644 --- a/collector/boot_time_bsd.go +++ b/collector/boot_time_bsd.go @@ -18,13 +18,13 @@ package collector import ( - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" + "log/slog" ) type bootTimeCollector struct { - logger log.Logger + logger *slog.Logger } func init() { @@ -32,7 +32,7 @@ func init() { } // newBootTimeCollector returns a new Collector exposing system boot time on BSD systems. -func newBootTimeCollector(logger log.Logger) (Collector, error) { +func newBootTimeCollector(logger *slog.Logger) (Collector, error) { return &bootTimeCollector{ logger: logger, }, nil diff --git a/collector/boot_time_solaris.go b/collector/boot_time_solaris.go index 15955121f7..4c336fb3c9 100644 --- a/collector/boot_time_solaris.go +++ b/collector/boot_time_solaris.go @@ -17,21 +17,21 @@ package collector import ( - "github.com/go-kit/log" "github.com/illumos/go-kstat" "github.com/prometheus/client_golang/prometheus" + "log/slog" ) type bootTimeCollector struct { boottime typedDesc - logger log.Logger + logger *slog.Logger } func init() { registerCollector("boottime", defaultEnabled, newBootTimeCollector) } -func newBootTimeCollector(logger log.Logger) (Collector, error) { +func newBootTimeCollector(logger *slog.Logger) (Collector, error) { return &bootTimeCollector{ boottime: typedDesc{ prometheus.NewDesc( diff --git a/collector/btrfs_linux.go b/collector/btrfs_linux.go index 33c88d01e7..831abe659f 100644 --- a/collector/btrfs_linux.go +++ b/collector/btrfs_linux.go @@ -18,13 +18,12 @@ package collector import ( "fmt" + "log/slog" "path" "strings" "syscall" dennwc "github.com/dennwc/btrfs" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/btrfs" ) @@ -32,7 +31,7 @@ import ( // A btrfsCollector is a Collector which gathers metrics from Btrfs filesystems. type btrfsCollector struct { fs btrfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -40,7 +39,7 @@ func init() { } // NewBtrfsCollector returns a new Collector exposing Btrfs statistics. -func NewBtrfsCollector(logger log.Logger) (Collector, error) { +func NewBtrfsCollector(logger *slog.Logger) (Collector, error) { fs, err := btrfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) @@ -62,8 +61,8 @@ func (c *btrfsCollector) Update(ch chan<- prometheus.Metric) error { ioctlStatsMap, err := c.getIoctlStats() if err != nil { - level.Debug(c.logger).Log( - "msg", "Error querying btrfs device stats with ioctl", + c.logger.Debug( + "Error querying btrfs device stats with ioctl", "err", err) ioctlStatsMap = make(map[string]*btrfsIoctlFsStats) } @@ -129,8 +128,8 @@ func (c *btrfsCollector) getIoctlStats() (map[string]*btrfsIoctlFsStats, error) if err != nil { // Failed to open this mount point, maybe we didn't have permission // maybe we'll find another mount point for this FS later. - level.Debug(c.logger).Log( - "msg", "Error inspecting btrfs mountpoint", + c.logger.Debug( + "Error inspecting btrfs mountpoint", "mountPoint", mountPath, "err", err) continue @@ -141,8 +140,8 @@ func (c *btrfsCollector) getIoctlStats() (map[string]*btrfsIoctlFsStats, error) if err != nil { // Failed to get the FS info for some reason, // perhaps it'll work with a different mount point - level.Debug(c.logger).Log( - "msg", "Error querying btrfs filesystem", + c.logger.Debug( + "Error querying btrfs filesystem", "mountPoint", mountPath, "err", err) continue @@ -156,8 +155,8 @@ func (c *btrfsCollector) getIoctlStats() (map[string]*btrfsIoctlFsStats, error) deviceStats, err := c.getIoctlDeviceStats(fs, &fsInfo) if err != nil { - level.Debug(c.logger).Log( - "msg", "Error querying btrfs device stats", + c.logger.Debug( + "Error querying btrfs device stats", "mountPoint", mountPath, "err", err) continue @@ -275,6 +274,30 @@ func (c *btrfsCollector) getMetrics(s *btrfs.Stats, ioctlStats *btrfsIoctlFsStat metricType: prometheus.GaugeValue, value: float64(s.Allocation.GlobalRsvSize), }, + { + name: "commits_total", + desc: "The total number of commits that have occurred.", + metricType: prometheus.CounterValue, + value: float64(s.CommitStats.Commits), + }, + { + name: "last_commit_seconds", + desc: "Duration of the most recent commit, in seconds.", + metricType: prometheus.GaugeValue, + value: float64(s.CommitStats.LastCommitMs) / 1000, + }, + { + name: "max_commit_seconds", + desc: "Duration of the slowest commit, in seconds.", + metricType: prometheus.GaugeValue, + value: float64(s.CommitStats.MaxCommitMs) / 1000, + }, + { + name: "commit_seconds_total", + desc: "Sum of the duration of all commits, in seconds.", + metricType: prometheus.CounterValue, + value: float64(s.CommitStats.TotalCommitMs) / 1000, + }, } // Information about data, metadata and system data. diff --git a/collector/btrfs_linux_test.go b/collector/btrfs_linux_test.go index fcd6f9f995..c2ed57e5de 100644 --- a/collector/btrfs_linux_test.go +++ b/collector/btrfs_linux_test.go @@ -27,6 +27,10 @@ var expectedBtrfsMetrics = [][]btrfsMetric{ { {name: "info", value: 1, extraLabel: []string{"label"}, extraLabelValue: []string{"fixture"}}, {name: "global_rsv_size_bytes", value: 1.6777216e+07}, + {name: "commits_total", value: 258051, metricType: 1}, + {name: "last_commit_seconds", value: 1.0}, + {name: "max_commit_seconds", value: 51.462}, + {name: "commit_seconds_total", value: 47836.090, metricType: 1}, {name: "reserved_bytes", value: 0, extraLabel: []string{"block_group_type"}, extraLabelValue: []string{"data"}}, {name: "used_bytes", value: 8.08189952e+08, extraLabel: []string{"block_group_type", "mode"}, extraLabelValue: []string{"data", "raid0"}}, {name: "size_bytes", value: 2.147483648e+09, extraLabel: []string{"block_group_type", "mode"}, extraLabelValue: []string{"data", "raid0"}}, @@ -45,6 +49,10 @@ var expectedBtrfsMetrics = [][]btrfsMetric{ { {name: "info", value: 1, extraLabel: []string{"label"}, extraLabelValue: []string{""}}, {name: "global_rsv_size_bytes", value: 1.6777216e+07}, + {name: "commits_total", value: 0, metricType: 1}, + {name: "last_commit_seconds", value: 0}, + {name: "max_commit_seconds", value: 0}, + {name: "commit_seconds_total", value: 0, metricType: 1}, {name: "reserved_bytes", value: 0, extraLabel: []string{"block_group_type"}, extraLabelValue: []string{"data"}}, {name: "used_bytes", value: 0, extraLabel: []string{"block_group_type", "mode"}, extraLabelValue: []string{"data", "raid5"}}, {name: "size_bytes", value: 6.44087808e+08, extraLabel: []string{"block_group_type", "mode"}, extraLabelValue: []string{"data", "raid5"}}, @@ -92,7 +100,10 @@ func checkMetric(exp, got *btrfsMetric) bool { } func TestBtrfs(t *testing.T) { - fs, _ := btrfs.NewFS("fixtures/sys") + fs, err := btrfs.NewFS("fixtures/sys") + if err != nil { + t.Fatal(err) + } collector := &btrfsCollector{fs: fs} stats, err := collector.fs.Stats() diff --git a/collector/buddyinfo.go b/collector/buddyinfo.go index c3cc5e046d..62392b9624 100644 --- a/collector/buddyinfo.go +++ b/collector/buddyinfo.go @@ -18,10 +18,9 @@ package collector import ( "fmt" + "log/slog" "strconv" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -33,7 +32,7 @@ const ( type buddyinfoCollector struct { fs procfs.FS desc *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -41,7 +40,7 @@ func init() { } // NewBuddyinfoCollector returns a new Collector exposing buddyinfo stats. -func NewBuddyinfoCollector(logger log.Logger) (Collector, error) { +func NewBuddyinfoCollector(logger *slog.Logger) (Collector, error) { desc := prometheus.NewDesc( prometheus.BuildFQName(namespace, buddyInfoSubsystem, "blocks"), "Count of free blocks according to size.", @@ -62,7 +61,7 @@ func (c *buddyinfoCollector) Update(ch chan<- prometheus.Metric) error { return fmt.Errorf("couldn't get buddyinfo: %w", err) } - level.Debug(c.logger).Log("msg", "Set node_buddy", "buddyInfo", buddyInfo) + c.logger.Debug("Set node_buddy", "buddyInfo", buddyInfo) for _, entry := range buddyInfo { for size, value := range entry.Sizes { ch <- prometheus.MustNewConstMetric( diff --git a/collector/cgroups_linux.go b/collector/cgroups_linux.go index 9f6d01a465..2a4e288e18 100644 --- a/collector/cgroups_linux.go +++ b/collector/cgroups_linux.go @@ -18,8 +18,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -30,7 +30,7 @@ type cgroupSummaryCollector struct { fs procfs.FS cgroups *prometheus.Desc enabled *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -38,7 +38,7 @@ func init() { } // NewCgroupSummaryCollector returns a new Collector exposing a summary of cgroups. -func NewCgroupSummaryCollector(logger log.Logger) (Collector, error) { +func NewCgroupSummaryCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) diff --git a/collector/collector.go b/collector/collector.go index 3112c78970..9768fb6a1c 100644 --- a/collector/collector.go +++ b/collector/collector.go @@ -17,12 +17,11 @@ package collector import ( "errors" "fmt" + "log/slog" "sync" "time" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -50,14 +49,14 @@ const ( ) var ( - factories = make(map[string]func(logger log.Logger) (Collector, error)) + factories = make(map[string]func(logger *slog.Logger) (Collector, error)) initiatedCollectorsMtx = sync.Mutex{} initiatedCollectors = make(map[string]Collector) collectorState = make(map[string]*bool) forcedCollectors = map[string]bool{} // collectors which have been explicitly enabled or disabled ) -func registerCollector(collector string, isDefaultEnabled bool, factory func(logger log.Logger) (Collector, error)) { +func registerCollector(collector string, isDefaultEnabled bool, factory func(logger *slog.Logger) (Collector, error)) { var helpDefaultState string if isDefaultEnabled { helpDefaultState = "enabled" @@ -78,7 +77,7 @@ func registerCollector(collector string, isDefaultEnabled bool, factory func(log // NodeCollector implements the prometheus.Collector interface. type NodeCollector struct { Collectors map[string]Collector - logger log.Logger + logger *slog.Logger } // DisableDefaultCollectors sets the collector state to false for all collectors which @@ -104,7 +103,7 @@ func collectorFlagAction(collector string) func(ctx *kingpin.ParseContext) error } // NewNodeCollector creates a new NodeCollector. -func NewNodeCollector(logger log.Logger, filters ...string) (*NodeCollector, error) { +func NewNodeCollector(logger *slog.Logger, filters ...string) (*NodeCollector, error) { f := make(map[string]bool) for _, filter := range filters { enabled, exist := collectorState[filter] @@ -126,7 +125,7 @@ func NewNodeCollector(logger log.Logger, filters ...string) (*NodeCollector, err if collector, ok := initiatedCollectors[key]; ok { collectors[key] = collector } else { - collector, err := factories[key](log.With(logger, "collector", key)) + collector, err := factories[key](logger.With("collector", key)) if err != nil { return nil, err } @@ -156,7 +155,7 @@ func (n NodeCollector) Collect(ch chan<- prometheus.Metric) { wg.Wait() } -func execute(name string, c Collector, ch chan<- prometheus.Metric, logger log.Logger) { +func execute(name string, c Collector, ch chan<- prometheus.Metric, logger *slog.Logger) { begin := time.Now() err := c.Update(ch) duration := time.Since(begin) @@ -164,13 +163,13 @@ func execute(name string, c Collector, ch chan<- prometheus.Metric, logger log.L if err != nil { if IsNoDataError(err) { - level.Debug(logger).Log("msg", "collector returned no data", "name", name, "duration_seconds", duration.Seconds(), "err", err) + logger.Debug("collector returned no data", "name", name, "duration_seconds", duration.Seconds(), "err", err) } else { - level.Error(logger).Log("msg", "collector failed", "name", name, "duration_seconds", duration.Seconds(), "err", err) + logger.Error("collector failed", "name", name, "duration_seconds", duration.Seconds(), "err", err) } success = 0 } else { - level.Debug(logger).Log("msg", "collector succeeded", "name", name, "duration_seconds", duration.Seconds()) + logger.Debug("collector succeeded", "name", name, "duration_seconds", duration.Seconds()) success = 1 } ch <- prometheus.MustNewConstMetric(scrapeDurationDesc, prometheus.GaugeValue, duration.Seconds(), name) diff --git a/collector/collectorPerconaExtensions.go b/collector/collectorPerconaExtensions.go index ace605e666..f862491eeb 100644 --- a/collector/collectorPerconaExtensions.go +++ b/collector/collectorPerconaExtensions.go @@ -16,16 +16,16 @@ package collector import ( "fmt" + "log/slog" kingpin "github.com/alecthomas/kingpin/v2" - log "github.com/go-kit/log" ) -func RegisterCollectorPublic(collector string, isDefaultEnabled bool, factory func(logger log.Logger) (Collector, error)) { +func RegisterCollectorPublic(collector string, isDefaultEnabled bool, factory func(logger *slog.Logger) (Collector, error)) { registerCollector(collector, isDefaultEnabled, factory) } -func ReplaceCollector(collector string, isDefaultEnabled bool, factory func(logger log.Logger) (Collector, error)) { +func ReplaceCollector(collector string, isDefaultEnabled bool, factory func(logger *slog.Logger) (Collector, error)) { delete(factories, collector) /*var helpDefaultState string if isDefaultEnabled { diff --git a/collector/conntrack_linux.go b/collector/conntrack_linux.go index e4ea954900..309857c767 100644 --- a/collector/conntrack_linux.go +++ b/collector/conntrack_linux.go @@ -19,10 +19,9 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -38,7 +37,7 @@ type conntrackCollector struct { drop *prometheus.Desc earlyDrop *prometheus.Desc searchRestart *prometheus.Desc - logger log.Logger + logger *slog.Logger } type conntrackStatistics struct { @@ -57,7 +56,7 @@ func init() { } // NewConntrackCollector returns a new Collector exposing conntrack stats. -func NewConntrackCollector(logger log.Logger) (Collector, error) { +func NewConntrackCollector(logger *slog.Logger) (Collector, error) { return &conntrackCollector{ current: prometheus.NewDesc( prometheus.BuildFQName(namespace, "", "nf_conntrack_entries"), @@ -154,7 +153,7 @@ func (c *conntrackCollector) Update(ch chan<- prometheus.Metric) error { func (c *conntrackCollector) handleErr(err error) error { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "conntrack probably not loaded") + c.logger.Debug("conntrack probably not loaded") return ErrNoData } return fmt.Errorf("failed to retrieve conntrack stats: %w", err) diff --git a/collector/cpu_aix.go b/collector/cpu_aix.go new file mode 100644 index 0000000000..9d896e2ded --- /dev/null +++ b/collector/cpu_aix.go @@ -0,0 +1,76 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !nocpu +// +build !nocpu + +package collector + +/* +#include // Include the standard Unix header +#include // For errno +*/ +import "C" +import ( + "fmt" + "log/slog" + "strconv" + + "github.com/power-devops/perfstat" + "github.com/prometheus/client_golang/prometheus" +) + +type cpuCollector struct { + cpu typedDesc + logger *slog.Logger + tickPerSecond int64 +} + +func init() { + registerCollector("cpu", defaultEnabled, NewCpuCollector) +} + +func tickPerSecond() (int64, error) { + ticks, err := C.sysconf(C._SC_CLK_TCK) + if ticks == -1 || err != nil { + return 0, fmt.Errorf("failed to get clock ticks per second: %v", err) + } + return int64(ticks), nil +} + +func NewCpuCollector(logger *slog.Logger) (Collector, error) { + ticks, err := tickPerSecond() + if err != nil { + return nil, err + } + return &cpuCollector{ + cpu: typedDesc{nodeCPUSecondsDesc, prometheus.CounterValue}, + logger: logger, + tickPerSecond: ticks, + }, nil +} + +func (c *cpuCollector) Update(ch chan<- prometheus.Metric) error { + stats, err := perfstat.CpuStat() + if err != nil { + return err + } + + for n, stat := range stats { + ch <- c.cpu.mustNewConstMetric(float64(stat.User/c.tickPerSecond), strconv.Itoa(n), "user") + ch <- c.cpu.mustNewConstMetric(float64(stat.Sys/c.tickPerSecond), strconv.Itoa(n), "system") + ch <- c.cpu.mustNewConstMetric(float64(stat.Idle/c.tickPerSecond), strconv.Itoa(n), "idle") + ch <- c.cpu.mustNewConstMetric(float64(stat.Wait/c.tickPerSecond), strconv.Itoa(n), "wait") + } + return nil +} diff --git a/collector/cpu_darwin.go b/collector/cpu_darwin.go index 6c461cc348..31b11702b0 100644 --- a/collector/cpu_darwin.go +++ b/collector/cpu_darwin.go @@ -23,10 +23,10 @@ import ( "bytes" "encoding/binary" "fmt" + "log/slog" "strconv" "unsafe" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -53,7 +53,7 @@ const ClocksPerSec = float64(C.CLK_TCK) type statCollector struct { cpu *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -61,7 +61,7 @@ func init() { } // NewCPUCollector returns a new Collector exposing CPU stats. -func NewCPUCollector(logger log.Logger) (Collector, error) { +func NewCPUCollector(logger *slog.Logger) (Collector, error) { return &statCollector{ cpu: nodeCPUSecondsDesc, logger: logger, diff --git a/collector/cpu_dragonfly.go b/collector/cpu_dragonfly.go index 61cba1eee4..c53aaef00a 100644 --- a/collector/cpu_dragonfly.go +++ b/collector/cpu_dragonfly.go @@ -18,10 +18,10 @@ package collector import ( "errors" + "log/slog" "strconv" "unsafe" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -78,7 +78,7 @@ const maxCPUTimesLen = C.MAXCPU * C.CPUSTATES type statCollector struct { cpu *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -86,7 +86,7 @@ func init() { } // NewStatCollector returns a new Collector exposing CPU stats. -func NewStatCollector(logger log.Logger) (Collector, error) { +func NewStatCollector(logger *slog.Logger) (Collector, error) { return &statCollector{ cpu: nodeCPUSecondsDesc, logger: logger, diff --git a/collector/cpu_freebsd.go b/collector/cpu_freebsd.go index 96b0f033cb..39b0118567 100644 --- a/collector/cpu_freebsd.go +++ b/collector/cpu_freebsd.go @@ -18,12 +18,11 @@ package collector import ( "fmt" + "log/slog" "math" "strconv" "unsafe" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" ) @@ -85,7 +84,7 @@ func getCPUTimes() ([]cputime, error) { type statCollector struct { cpu typedDesc temp typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -93,7 +92,7 @@ func init() { } // NewStatCollector returns a new Collector exposing CPU stats. -func NewStatCollector(logger log.Logger) (Collector, error) { +func NewStatCollector(logger *slog.Logger) (Collector, error) { return &statCollector{ cpu: typedDesc{nodeCPUSecondsDesc, prometheus.CounterValue}, temp: typedDesc{prometheus.NewDesc( @@ -134,11 +133,11 @@ func (c *statCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { if err == unix.ENOENT { // No temperature information for this CPU - level.Debug(c.logger).Log("msg", "no temperature information for CPU", "cpu", cpu) + c.logger.Debug("no temperature information for CPU", "cpu", cpu) } else { // Unexpected error ch <- c.temp.mustNewConstMetric(math.NaN(), lcpu) - level.Error(c.logger).Log("msg", "failed to query CPU temperature for CPU", "cpu", cpu, "err", err) + c.logger.Error("failed to query CPU temperature for CPU", "cpu", cpu, "err", err) } continue } diff --git a/collector/cpu_linux.go b/collector/cpu_linux.go index 75d2a795b2..8ca703657b 100644 --- a/collector/cpu_linux.go +++ b/collector/cpu_linux.go @@ -17,7 +17,9 @@ package collector import ( + "errors" "fmt" + "log/slog" "os" "path/filepath" "regexp" @@ -25,17 +27,17 @@ import ( "strconv" "sync" + "golang.org/x/exp/maps" + "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" "github.com/prometheus/procfs/sysfs" - "golang.org/x/exp/maps" ) type cpuCollector struct { - fs procfs.FS + procfs procfs.FS + sysfs sysfs.FS cpu *prometheus.Desc cpuInfo *prometheus.Desc cpuFrequencyHz *prometheus.Desc @@ -45,7 +47,8 @@ type cpuCollector struct { cpuCoreThrottle *prometheus.Desc cpuPackageThrottle *prometheus.Desc cpuIsolated *prometheus.Desc - logger log.Logger + logger *slog.Logger + cpuOnline *prometheus.Desc cpuStats map[int64]procfs.CPUStat cpuStatsMutex sync.Mutex isolatedCpus []uint16 @@ -70,28 +73,29 @@ func init() { } // NewCPUCollector returns a new Collector exposing kernel/system statistics. -func NewCPUCollector(logger log.Logger) (Collector, error) { - fs, err := procfs.NewFS(*procPath) +func NewCPUCollector(logger *slog.Logger) (Collector, error) { + pfs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) } - sysfs, err := sysfs.NewFS(*sysPath) + sfs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) } - isolcpus, err := sysfs.IsolatedCPUs() + isolcpus, err := sfs.IsolatedCPUs() if err != nil { if !os.IsNotExist(err) { return nil, fmt.Errorf("Unable to get isolated cpus: %w", err) } - level.Debug(logger).Log("msg", "Could not open isolated file", "error", err) + logger.Debug("Could not open isolated file", "error", err) } c := &cpuCollector{ - fs: fs, - cpu: nodeCPUSecondsDesc, + procfs: pfs, + sysfs: sfs, + cpu: nodeCPUSecondsDesc, cpuInfo: prometheus.NewDesc( prometheus.BuildFQName(namespace, cpuCollectorSubsystem, "info"), "CPU information from /proc/cpuinfo.", @@ -132,6 +136,11 @@ func NewCPUCollector(logger log.Logger) (Collector, error) { "Whether each core is isolated, information from /sys/devices/system/cpu/isolated.", []string{"cpu"}, nil, ), + cpuOnline: prometheus.NewDesc( + prometheus.BuildFQName(namespace, cpuCollectorSubsystem, "online"), + "CPUs that are online and being scheduled.", + []string{"cpu"}, nil, + ), logger: logger, isolatedCpus: isolcpus, cpuStats: make(map[int64]procfs.CPUStat), @@ -146,7 +155,7 @@ func NewCPUCollector(logger log.Logger) (Collector, error) { func (c *cpuCollector) compileIncludeFlags(flagsIncludeFlag, bugsIncludeFlag *string) error { if (*flagsIncludeFlag != "" || *bugsIncludeFlag != "") && !*enableCPUInfo { *enableCPUInfo = true - level.Info(c.logger).Log("msg", "--collector.cpu.info has been set to `true` because you set the following flags, like --collector.cpu.info.flags-include and --collector.cpu.info.bugs-include") + c.logger.Info("--collector.cpu.info has been set to `true` because you set the following flags, like --collector.cpu.info.flags-include and --collector.cpu.info.bugs-include") } var err error @@ -178,12 +187,21 @@ func (c *cpuCollector) Update(ch chan<- prometheus.Metric) error { if c.isolatedCpus != nil { c.updateIsolated(ch) } - return c.updateThermalThrottle(ch) + err := c.updateThermalThrottle(ch) + if err != nil { + return err + } + err = c.updateOnline(ch) + if err != nil { + return err + } + + return nil } // updateInfo reads /proc/cpuinfo func (c *cpuCollector) updateInfo(ch chan<- prometheus.Metric) error { - info, err := c.fs.CPUInfo() + info, err := c.procfs.CPUInfo() if err != nil { return err } @@ -205,7 +223,7 @@ func (c *cpuCollector) updateInfo(ch chan<- prometheus.Metric) error { cpuFreqEnabled, ok := collectorState["cpufreq"] if !ok || cpuFreqEnabled == nil { - level.Debug(c.logger).Log("msg", "cpufreq key missing or nil value in collectorState map") + c.logger.Debug("cpufreq key missing or nil value in collectorState map") } else if !*cpuFreqEnabled { for _, cpu := range info { ch <- prometheus.MustNewConstMetric(c.cpuFrequencyHz, @@ -269,12 +287,12 @@ func (c *cpuCollector) updateThermalThrottle(ch chan<- prometheus.Metric) error // topology/physical_package_id if physicalPackageID, err = readUintFromFile(filepath.Join(cpu, "topology", "physical_package_id")); err != nil { - level.Debug(c.logger).Log("msg", "CPU is missing physical_package_id", "cpu", cpu) + c.logger.Debug("CPU is missing physical_package_id", "cpu", cpu) continue } // topology/core_id if coreID, err = readUintFromFile(filepath.Join(cpu, "topology", "core_id")); err != nil { - level.Debug(c.logger).Log("msg", "CPU is missing core_id", "cpu", cpu) + c.logger.Debug("CPU is missing core_id", "cpu", cpu) continue } @@ -292,7 +310,7 @@ func (c *cpuCollector) updateThermalThrottle(ch chan<- prometheus.Metric) error if coreThrottleCount, err := readUintFromFile(filepath.Join(cpu, "thermal_throttle", "core_throttle_count")); err == nil { packageCoreThrottles[physicalPackageID][coreID] = coreThrottleCount } else { - level.Debug(c.logger).Log("msg", "CPU is missing core_throttle_count", "cpu", cpu) + c.logger.Debug("CPU is missing core_throttle_count", "cpu", cpu) } } @@ -302,7 +320,7 @@ func (c *cpuCollector) updateThermalThrottle(ch chan<- prometheus.Metric) error if packageThrottleCount, err := readUintFromFile(filepath.Join(cpu, "thermal_throttle", "package_throttle_count")); err == nil { packageThrottles[physicalPackageID] = packageThrottleCount } else { - level.Debug(c.logger).Log("msg", "CPU is missing package_throttle_count", "cpu", cpu) + c.logger.Debug("CPU is missing package_throttle_count", "cpu", cpu) } } } @@ -334,9 +352,31 @@ func (c *cpuCollector) updateIsolated(ch chan<- prometheus.Metric) { } } +// updateOnline reads /sys/devices/system/cpu/cpu*/online through sysfs and exports online status metrics. +func (c *cpuCollector) updateOnline(ch chan<- prometheus.Metric) error { + cpus, err := c.sysfs.CPUs() + if err != nil { + return err + } + // No-op if the system does not support CPU online stats. + cpu0 := cpus[0] + if _, err := cpu0.Online(); err != nil && errors.Is(err, os.ErrNotExist) { + return nil + } + for _, cpu := range cpus { + setOnline := float64(0) + if online, _ := cpu.Online(); online { + setOnline = 1 + } + ch <- prometheus.MustNewConstMetric(c.cpuOnline, prometheus.GaugeValue, setOnline, cpu.Number()) + } + + return nil +} + // updateStat reads /proc/stat through procfs and exports CPU-related metrics. func (c *cpuCollector) updateStat(ch chan<- prometheus.Metric) error { - stats, err := c.fs.Stat() + stats, err := c.procfs.Stat() if err != nil { return err } @@ -380,68 +420,68 @@ func (c *cpuCollector) updateCPUStats(newStats map[int64]procfs.CPUStat) { // If idle jumps backwards by more than X seconds, assume we had a hotplug event and reset the stats for this CPU. if (cpuStats.Idle - n.Idle) >= jumpBackSeconds { - level.Debug(c.logger).Log("msg", jumpBackDebugMessage, "cpu", i, "old_value", cpuStats.Idle, "new_value", n.Idle) + c.logger.Debug(jumpBackDebugMessage, "cpu", i, "old_value", cpuStats.Idle, "new_value", n.Idle) cpuStats = procfs.CPUStat{} } if n.Idle >= cpuStats.Idle { cpuStats.Idle = n.Idle } else { - level.Debug(c.logger).Log("msg", "CPU Idle counter jumped backwards", "cpu", i, "old_value", cpuStats.Idle, "new_value", n.Idle) + c.logger.Debug("CPU Idle counter jumped backwards", "cpu", i, "old_value", cpuStats.Idle, "new_value", n.Idle) } if n.User >= cpuStats.User { cpuStats.User = n.User } else { - level.Debug(c.logger).Log("msg", "CPU User counter jumped backwards", "cpu", i, "old_value", cpuStats.User, "new_value", n.User) + c.logger.Debug("CPU User counter jumped backwards", "cpu", i, "old_value", cpuStats.User, "new_value", n.User) } if n.Nice >= cpuStats.Nice { cpuStats.Nice = n.Nice } else { - level.Debug(c.logger).Log("msg", "CPU Nice counter jumped backwards", "cpu", i, "old_value", cpuStats.Nice, "new_value", n.Nice) + c.logger.Debug("CPU Nice counter jumped backwards", "cpu", i, "old_value", cpuStats.Nice, "new_value", n.Nice) } if n.System >= cpuStats.System { cpuStats.System = n.System } else { - level.Debug(c.logger).Log("msg", "CPU System counter jumped backwards", "cpu", i, "old_value", cpuStats.System, "new_value", n.System) + c.logger.Debug("CPU System counter jumped backwards", "cpu", i, "old_value", cpuStats.System, "new_value", n.System) } if n.Iowait >= cpuStats.Iowait { cpuStats.Iowait = n.Iowait } else { - level.Debug(c.logger).Log("msg", "CPU Iowait counter jumped backwards", "cpu", i, "old_value", cpuStats.Iowait, "new_value", n.Iowait) + c.logger.Debug("CPU Iowait counter jumped backwards", "cpu", i, "old_value", cpuStats.Iowait, "new_value", n.Iowait) } if n.IRQ >= cpuStats.IRQ { cpuStats.IRQ = n.IRQ } else { - level.Debug(c.logger).Log("msg", "CPU IRQ counter jumped backwards", "cpu", i, "old_value", cpuStats.IRQ, "new_value", n.IRQ) + c.logger.Debug("CPU IRQ counter jumped backwards", "cpu", i, "old_value", cpuStats.IRQ, "new_value", n.IRQ) } if n.SoftIRQ >= cpuStats.SoftIRQ { cpuStats.SoftIRQ = n.SoftIRQ } else { - level.Debug(c.logger).Log("msg", "CPU SoftIRQ counter jumped backwards", "cpu", i, "old_value", cpuStats.SoftIRQ, "new_value", n.SoftIRQ) + c.logger.Debug("CPU SoftIRQ counter jumped backwards", "cpu", i, "old_value", cpuStats.SoftIRQ, "new_value", n.SoftIRQ) } if n.Steal >= cpuStats.Steal { cpuStats.Steal = n.Steal } else { - level.Debug(c.logger).Log("msg", "CPU Steal counter jumped backwards", "cpu", i, "old_value", cpuStats.Steal, "new_value", n.Steal) + c.logger.Debug("CPU Steal counter jumped backwards", "cpu", i, "old_value", cpuStats.Steal, "new_value", n.Steal) } if n.Guest >= cpuStats.Guest { cpuStats.Guest = n.Guest } else { - level.Debug(c.logger).Log("msg", "CPU Guest counter jumped backwards", "cpu", i, "old_value", cpuStats.Guest, "new_value", n.Guest) + c.logger.Debug("CPU Guest counter jumped backwards", "cpu", i, "old_value", cpuStats.Guest, "new_value", n.Guest) } if n.GuestNice >= cpuStats.GuestNice { cpuStats.GuestNice = n.GuestNice } else { - level.Debug(c.logger).Log("msg", "CPU GuestNice counter jumped backwards", "cpu", i, "old_value", cpuStats.GuestNice, "new_value", n.GuestNice) + c.logger.Debug("CPU GuestNice counter jumped backwards", "cpu", i, "old_value", cpuStats.GuestNice, "new_value", n.GuestNice) } c.cpuStats[i] = cpuStats diff --git a/collector/cpu_linux_test.go b/collector/cpu_linux_test.go index b148ffcd93..158ae8ff40 100644 --- a/collector/cpu_linux_test.go +++ b/collector/cpu_linux_test.go @@ -17,10 +17,11 @@ package collector import ( + "io" + "log/slog" "reflect" "testing" - "github.com/go-kit/log" "github.com/prometheus/procfs" ) @@ -35,7 +36,7 @@ func makeTestCPUCollector(s map[int64]procfs.CPUStat) *cpuCollector { dup := make(map[int64]procfs.CPUStat, len(s)) copyStats(dup, s) return &cpuCollector{ - logger: log.NewNopLogger(), + logger: slog.New(slog.NewTextHandler(io.Discard, nil)), cpuStats: dup, } } diff --git a/collector/cpu_netbsd.go b/collector/cpu_netbsd.go index 7fc95c8081..ae1235eb74 100644 --- a/collector/cpu_netbsd.go +++ b/collector/cpu_netbsd.go @@ -18,6 +18,7 @@ package collector import ( "errors" + "log/slog" "math" "regexp" "sort" @@ -25,14 +26,21 @@ import ( "strings" "unsafe" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" "howett.net/plist" ) +const ( + _IOC_OUT = uint(0x40000000) + _IOC_IN = uint(0x80000000) + _IOC_INOUT = (_IOC_IN | _IOC_OUT) + _IOCPARM_MASK = uint(0x1fff) + _IOCPARM_SHIFT = uint(16) + _IOCGROUP_SHIFT = uint(8) +) + type clockinfo struct { hz int32 // clock frequency tick int32 // micro-seconds per hz tick @@ -51,7 +59,7 @@ type cputime struct { type plistref struct { pref_plist unsafe.Pointer - pref_len uint64 + pref_len uint } type sysmonValues struct { @@ -65,25 +73,19 @@ type sysmonProperty []sysmonValues type sysmonProperties map[string]sysmonProperty -func readBytes(ptr unsafe.Pointer, length uint64) []byte { - buf := make([]byte, length-1) - var i uint64 - for ; i < length-1; i++ { - buf[i] = *(*byte)(unsafe.Pointer(uintptr(ptr) + uintptr(i))) - } - return buf +func _IOC(inout uint, group byte, num uint, len uintptr) uint { + return ((inout) | ((uint(len) & _IOCPARM_MASK) << _IOCPARM_SHIFT) | (uint(group) << _IOCGROUP_SHIFT) | (num)) } -func ioctl(fd int, nr int64, typ byte, size uintptr, retptr unsafe.Pointer) error { +func _IOWR(group byte, num uint, len uintptr) uint { + return _IOC(_IOC_INOUT, group, num, len) +} + +func ioctl(fd int, nr uint, typ byte, size uintptr, retptr unsafe.Pointer) error { _, _, errno := unix.Syscall( unix.SYS_IOCTL, uintptr(fd), - // Some magicks derived from sys/ioccom.h. - uintptr((0x40000000|0x80000000)| - ((int64(size)&(1<<13-1))<<16)| - (int64(typ)<<8)| - nr, - ), + uintptr(_IOWR(typ, nr, size)), uintptr(retptr), ) if errno != 0 { @@ -93,7 +95,7 @@ func ioctl(fd int, nr int64, typ byte, size uintptr, retptr unsafe.Pointer) erro } func readSysmonProperties() (sysmonProperties, error) { - fd, err := unix.Open(rootfsFilePath("/dev/sysmon"), unix.O_RDONLY, 0777) + fd, err := unix.Open(rootfsFilePath("/dev/sysmon"), unix.O_RDONLY, 0) if err != nil { return nil, err } @@ -104,8 +106,8 @@ func readSysmonProperties() (sysmonProperties, error) { if err = ioctl(fd, 0, 'E', unsafe.Sizeof(retptr), unsafe.Pointer(&retptr)); err != nil { return nil, err } - - bytes := readBytes(retptr.pref_plist, retptr.pref_len) + defer unix.Syscall(unix.SYS_MUNMAP, uintptr(retptr.pref_plist), uintptr(retptr.pref_len), uintptr(0)) + bytes := unsafe.Slice((*byte)(unsafe.Pointer(retptr.pref_plist)), retptr.pref_len-1) var props sysmonProperties if _, err = plist.Unmarshal(bytes, &props); err != nil { @@ -180,7 +182,7 @@ func getCPUTimes() ([]cputime, error) { if err != nil { return nil, err } - ncpus := *(*int)(unsafe.Pointer(&ncpusb[0])) + ncpus := int(*(*uint32)(unsafe.Pointer(&ncpusb[0]))) if ncpus < 1 { return nil, errors.New("Invalid cpu number") @@ -192,10 +194,10 @@ func getCPUTimes() ([]cputime, error) { if err != nil { return nil, err } - for len(cpb) >= int(unsafe.Sizeof(int(0))) { - t := *(*int)(unsafe.Pointer(&cpb[0])) + for len(cpb) >= int(unsafe.Sizeof(uint64(0))) { + t := *(*uint64)(unsafe.Pointer(&cpb[0])) times = append(times, float64(t)/cpufreq) - cpb = cpb[unsafe.Sizeof(int(0)):] + cpb = cpb[unsafe.Sizeof(uint64(0)):] } } @@ -214,7 +216,7 @@ func getCPUTimes() ([]cputime, error) { type statCollector struct { cpu typedDesc temp typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -222,7 +224,7 @@ func init() { } // NewStatCollector returns a new Collector exposing CPU stats. -func NewStatCollector(logger log.Logger) (Collector, error) { +func NewStatCollector(logger *slog.Logger) (Collector, error) { return &statCollector{ cpu: typedDesc{nodeCPUSecondsDesc, prometheus.CounterValue}, temp: typedDesc{prometheus.NewDesc( @@ -269,7 +271,7 @@ func (c *statCollector) Update(ch chan<- prometheus.Metric) error { if temp, ok := cpuTemperatures[cpu]; ok { ch <- c.temp.mustNewConstMetric(temp, lcpu) } else { - level.Debug(c.logger).Log("msg", "no temperature information for CPU", "cpu", cpu) + c.logger.Debug("no temperature information for CPU", "cpu", cpu) ch <- c.temp.mustNewConstMetric(math.NaN(), lcpu) } } diff --git a/collector/cpu_openbsd.go b/collector/cpu_openbsd.go index 8715ff9885..2d59f5476c 100644 --- a/collector/cpu_openbsd.go +++ b/collector/cpu_openbsd.go @@ -17,10 +17,10 @@ package collector import ( + "log/slog" "strconv" "unsafe" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" ) @@ -45,14 +45,14 @@ const ( type cpuCollector struct { cpu typedDesc - logger log.Logger + logger *slog.Logger } func init() { registerCollector("cpu", defaultEnabled, NewCPUCollector) } -func NewCPUCollector(logger log.Logger) (Collector, error) { +func NewCPUCollector(logger *slog.Logger) (Collector, error) { return &cpuCollector{ cpu: typedDesc{nodeCPUSecondsDesc, prometheus.CounterValue}, logger: logger, diff --git a/collector/cpu_solaris.go b/collector/cpu_solaris.go index c78845423f..550ba37462 100644 --- a/collector/cpu_solaris.go +++ b/collector/cpu_solaris.go @@ -17,9 +17,9 @@ package collector import ( + "log/slog" "strconv" - "github.com/go-kit/log" "github.com/illumos/go-kstat" "github.com/prometheus/client_golang/prometheus" ) @@ -29,14 +29,14 @@ import "C" type cpuCollector struct { cpu typedDesc - logger log.Logger + logger *slog.Logger } func init() { registerCollector("cpu", defaultEnabled, NewCpuCollector) } -func NewCpuCollector(logger log.Logger) (Collector, error) { +func NewCpuCollector(logger *slog.Logger) (Collector, error) { return &cpuCollector{ cpu: typedDesc{nodeCPUSecondsDesc, prometheus.CounterValue}, logger: logger, diff --git a/collector/cpu_vulnerabilities_linux.go b/collector/cpu_vulnerabilities_linux.go index 69a2c587e3..180d56d6c3 100644 --- a/collector/cpu_vulnerabilities_linux.go +++ b/collector/cpu_vulnerabilities_linux.go @@ -15,8 +15,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -40,7 +40,7 @@ func init() { registerCollector(cpuVulerabilitiesCollector, defaultDisabled, NewVulnerabilitySysfsCollector) } -func NewVulnerabilitySysfsCollector(logger log.Logger) (Collector, error) { +func NewVulnerabilitySysfsCollector(logger *slog.Logger) (Collector, error) { return &cpuVulnerabilitiesCollector{}, nil } diff --git a/collector/cpufreq_linux.go b/collector/cpufreq_linux.go index 3372be1ab6..79e2308c0f 100644 --- a/collector/cpufreq_linux.go +++ b/collector/cpufreq_linux.go @@ -18,15 +18,16 @@ package collector import ( "fmt" - "github.com/go-kit/log" + "log/slog" + "strings" + "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" - "strings" ) type cpuFreqCollector struct { fs sysfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -34,7 +35,7 @@ func init() { } // NewCPUFreqCollector returns a new Collector exposing kernel/system statistics. -func NewCPUFreqCollector(logger log.Logger) (Collector, error) { +func NewCPUFreqCollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) diff --git a/collector/cpufreq_solaris.go b/collector/cpufreq_solaris.go index c3fb9ee687..c13703e14f 100644 --- a/collector/cpufreq_solaris.go +++ b/collector/cpufreq_solaris.go @@ -18,9 +18,9 @@ package collector import ( "fmt" + "log/slog" "strconv" - "github.com/go-kit/log" "github.com/illumos/go-kstat" "github.com/prometheus/client_golang/prometheus" ) @@ -29,14 +29,14 @@ import ( import "C" type cpuFreqCollector struct { - logger log.Logger + logger *slog.Logger } func init() { registerCollector("cpufreq", defaultEnabled, NewCpuFreqCollector) } -func NewCpuFreqCollector(logger log.Logger) (Collector, error) { +func NewCpuFreqCollector(logger *slog.Logger) (Collector, error) { return &cpuFreqCollector{ logger: logger, }, nil diff --git a/collector/devstat_dragonfly.go b/collector/devstat_dragonfly.go index 11678054f7..b1796860fa 100644 --- a/collector/devstat_dragonfly.go +++ b/collector/devstat_dragonfly.go @@ -19,8 +19,8 @@ package collector import ( "errors" "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -98,7 +98,7 @@ type devstatCollector struct { bytesDesc *prometheus.Desc transfersDesc *prometheus.Desc blocksDesc *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -106,7 +106,7 @@ func init() { } // NewDevstatCollector returns a new Collector exposing Device stats. -func NewDevstatCollector(logger log.Logger) (Collector, error) { +func NewDevstatCollector(logger *slog.Logger) (Collector, error) { return &devstatCollector{ bytesDesc: prometheus.NewDesc( prometheus.BuildFQName(namespace, devstatSubsystem, "bytes_total"), diff --git a/collector/devstat_freebsd.go b/collector/devstat_freebsd.go index 20cdc27674..a9d4272003 100644 --- a/collector/devstat_freebsd.go +++ b/collector/devstat_freebsd.go @@ -19,10 +19,10 @@ package collector import ( "errors" "fmt" + "log/slog" "sync" "unsafe" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -43,7 +43,7 @@ type devstatCollector struct { duration typedDesc busyTime typedDesc blocks typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -51,7 +51,7 @@ func init() { } // NewDevstatCollector returns a new Collector exposing Device stats. -func NewDevstatCollector(logger log.Logger) (Collector, error) { +func NewDevstatCollector(logger *slog.Logger) (Collector, error) { return &devstatCollector{ devinfo: &C.struct_devinfo{}, bytes: typedDesc{prometheus.NewDesc( diff --git a/collector/diskstats_aix.go b/collector/diskstats_aix.go new file mode 100644 index 0000000000..c6619fd9bd --- /dev/null +++ b/collector/diskstats_aix.go @@ -0,0 +1,82 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !nodiskstats +// +build !nodiskstats + +package collector + +import ( + "fmt" + "log/slog" + + "github.com/power-devops/perfstat" + "github.com/prometheus/client_golang/prometheus" +) + +const diskstatsDefaultIgnoredDevices = "" + +type diskstatsCollector struct { + rbytes typedDesc + wbytes typedDesc + time typedDesc + + deviceFilter deviceFilter + logger *slog.Logger + + tickPerSecond int64 +} + +func init() { + registerCollector("diskstats", defaultEnabled, NewDiskstatsCollector) +} + +// NewDiskstatsCollector returns a new Collector exposing disk device stats. +func NewDiskstatsCollector(logger *slog.Logger) (Collector, error) { + ticks, err := tickPerSecond() + if err != nil { + return nil, err + } + deviceFilter, err := newDiskstatsDeviceFilter(logger) + if err != nil { + return nil, fmt.Errorf("failed to parse device filter flags: %w", err) + } + + return &diskstatsCollector{ + rbytes: typedDesc{readBytesDesc, prometheus.CounterValue}, + wbytes: typedDesc{writtenBytesDesc, prometheus.CounterValue}, + time: typedDesc{ioTimeSecondsDesc, prometheus.CounterValue}, + + deviceFilter: deviceFilter, + logger: logger, + + tickPerSecond: ticks, + }, nil +} + +func (c *diskstatsCollector) Update(ch chan<- prometheus.Metric) error { + stats, err := perfstat.DiskStat() + if err != nil { + return err + } + + for _, stat := range stats { + if c.deviceFilter.ignored(stat.Name) { + continue + } + ch <- c.rbytes.mustNewConstMetric(float64(stat.Rblks*512), stat.Name) + ch <- c.wbytes.mustNewConstMetric(float64(stat.Wblks*512), stat.Name) + ch <- c.time.mustNewConstMetric(float64(stat.Time/c.tickPerSecond), stat.Name) + } + return nil +} diff --git a/collector/diskstats_common.go b/collector/diskstats_common.go index 2ab84438e7..593d055847 100644 --- a/collector/diskstats_common.go +++ b/collector/diskstats_common.go @@ -11,18 +11,17 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build !nodiskstats && (openbsd || linux || darwin) +//go:build !nodiskstats && (openbsd || linux || darwin || aix) // +build !nodiskstats -// +build openbsd linux darwin +// +build openbsd linux darwin aix package collector import ( "errors" + "log/slog" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -93,10 +92,10 @@ var ( ) ) -func newDiskstatsDeviceFilter(logger log.Logger) (deviceFilter, error) { +func newDiskstatsDeviceFilter(logger *slog.Logger) (deviceFilter, error) { if *oldDiskstatsDeviceExclude != "" { if !diskstatsDeviceExcludeSet { - level.Warn(logger).Log("msg", "--collector.diskstats.ignored-devices is DEPRECATED and will be removed in 2.0.0, use --collector.diskstats.device-exclude") + logger.Warn("--collector.diskstats.ignored-devices is DEPRECATED and will be removed in 2.0.0, use --collector.diskstats.device-exclude") *diskstatsDeviceExclude = *oldDiskstatsDeviceExclude } else { return deviceFilter{}, errors.New("--collector.diskstats.ignored-devices and --collector.diskstats.device-exclude are mutually exclusive") @@ -108,11 +107,11 @@ func newDiskstatsDeviceFilter(logger log.Logger) (deviceFilter, error) { } if *diskstatsDeviceExclude != "" { - level.Info(logger).Log("msg", "Parsed flag --collector.diskstats.device-exclude", "flag", *diskstatsDeviceExclude) + logger.Info("Parsed flag --collector.diskstats.device-exclude", "flag", *diskstatsDeviceExclude) } if *diskstatsDeviceInclude != "" { - level.Info(logger).Log("msg", "Parsed Flag --collector.diskstats.device-include", "flag", *diskstatsDeviceInclude) + logger.Info("Parsed Flag --collector.diskstats.device-include", "flag", *diskstatsDeviceInclude) } return newDeviceFilter(*diskstatsDeviceExclude, *diskstatsDeviceInclude), nil diff --git a/collector/diskstats_darwin.go b/collector/diskstats_darwin.go index b5f6c53844..98052fe7db 100644 --- a/collector/diskstats_darwin.go +++ b/collector/diskstats_darwin.go @@ -18,8 +18,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/lufia/iostat" "github.com/prometheus/client_golang/prometheus" ) @@ -35,7 +35,7 @@ type diskstatsCollector struct { descs []typedDescFunc deviceFilter deviceFilter - logger log.Logger + logger *slog.Logger } func init() { @@ -43,7 +43,7 @@ func init() { } // NewDiskstatsCollector returns a new Collector exposing disk device stats. -func NewDiskstatsCollector(logger log.Logger) (Collector, error) { +func NewDiskstatsCollector(logger *slog.Logger) (Collector, error) { var diskLabelNames = []string{"device"} deviceFilter, err := newDiskstatsDeviceFilter(logger) diff --git a/collector/diskstats_linux.go b/collector/diskstats_linux.go index ed5d044a61..c083a3f0e8 100644 --- a/collector/diskstats_linux.go +++ b/collector/diskstats_linux.go @@ -19,12 +19,11 @@ package collector import ( "bufio" "fmt" + "log/slog" "os" "strconv" "strings" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/blockdevice" ) @@ -85,7 +84,7 @@ type diskstatsCollector struct { filesystemInfoDesc typedFactorDesc deviceMapperInfoDesc typedFactorDesc ataDescs map[string]typedFactorDesc - logger log.Logger + logger *slog.Logger getUdevDeviceProperties func(uint32, uint32) (udevInfo, error) } @@ -95,7 +94,7 @@ func init() { // NewDiskstatsCollector returns a new Collector exposing disk device stats. // Docs from https://www.kernel.org/doc/Documentation/iostats.txt -func NewDiskstatsCollector(logger log.Logger) (Collector, error) { +func NewDiskstatsCollector(logger *slog.Logger) (Collector, error) { var diskLabelNames = []string{"device"} fs, err := blockdevice.NewFS(*procPath, *sysPath) if err != nil { @@ -113,7 +112,7 @@ func NewDiskstatsCollector(logger log.Logger) (Collector, error) { infoDesc: typedFactorDesc{ desc: prometheus.NewDesc(prometheus.BuildFQName(namespace, diskSubsystem, "info"), "Info of /sys/block/.", - []string{"device", "major", "minor", "path", "wwn", "model", "serial", "revision"}, + []string{"device", "major", "minor", "path", "wwn", "model", "serial", "revision", "rotational"}, nil, ), valueType: prometheus.GaugeValue, }, @@ -262,7 +261,7 @@ func NewDiskstatsCollector(logger log.Logger) (Collector, error) { // Only enable getting device properties from udev if the directory is readable. if stat, err := os.Stat(*udevDataPath); err != nil || !stat.IsDir() { - level.Error(logger).Log("msg", "Failed to open directory, disabling udev device properties", "path", *udevDataPath) + logger.Error("Failed to open directory, disabling udev device properties", "path", *udevDataPath) } else { collector.getUdevDeviceProperties = getUdevDeviceProperties } @@ -284,7 +283,7 @@ func (c *diskstatsCollector) Update(ch chan<- prometheus.Metric) error { info, err := getUdevDeviceProperties(stats.MajorNumber, stats.MinorNumber) if err != nil { - level.Debug(c.logger).Log("msg", "Failed to parse udev info", "err", err) + c.logger.Debug("Failed to parse udev info", "err", err) } // This is usually the serial printed on the disk label. @@ -295,6 +294,12 @@ func (c *diskstatsCollector) Update(ch chan<- prometheus.Metric) error { serial = info[udevIDSerialShort] } + queueStats, err := c.fs.SysBlockDeviceQueueStats(dev) + // Block Device Queue stats may not exist for all devices. + if err != nil && !os.IsNotExist(err) { + c.logger.Debug("Failed to get block device queue stats", "device", dev, "err", err) + } + ch <- c.infoDesc.mustNewConstMetric(1.0, dev, fmt.Sprint(stats.MajorNumber), fmt.Sprint(stats.MinorNumber), @@ -303,6 +308,7 @@ func (c *diskstatsCollector) Update(ch chan<- prometheus.Metric) error { info[udevIDModel], serial, info[udevIDRevision], + strconv.FormatUint(queueStats.Rotational, 2), ) statCount := stats.IoStatsCount - 3 // Total diskstats record count, less MajorNumber, MinorNumber and DeviceName @@ -355,14 +361,14 @@ func (c *diskstatsCollector) Update(ch chan<- prometheus.Metric) error { for attr, desc := range c.ataDescs { str, ok := info[attr] if !ok { - level.Debug(c.logger).Log("msg", "Udev attribute does not exist", "attribute", attr) + c.logger.Debug("Udev attribute does not exist", "attribute", attr) continue } if value, err := strconv.ParseFloat(str, 64); err == nil { ch <- desc.mustNewConstMetric(value, dev) } else { - level.Error(c.logger).Log("msg", "Failed to parse ATA value", "err", err) + c.logger.Error("Failed to parse ATA value", "err", err) } } } diff --git a/collector/diskstats_linux_test.go b/collector/diskstats_linux_test.go index 8e969c3e3a..fd90353f08 100644 --- a/collector/diskstats_linux_test.go +++ b/collector/diskstats_linux_test.go @@ -18,11 +18,11 @@ package collector import ( "fmt" - "os" + "io" + "log/slog" "strings" "testing" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/testutil" ) @@ -39,7 +39,7 @@ func (c testDiskStatsCollector) Describe(ch chan<- *prometheus.Desc) { prometheus.DescribeByCollect(c, ch) } -func NewTestDiskStatsCollector(logger log.Logger) (prometheus.Collector, error) { +func NewTestDiskStatsCollector(logger *slog.Logger) (prometheus.Collector, error) { dsc, err := NewDiskstatsCollector(logger) if err != nil { return testDiskStatsCollector{}, err @@ -113,21 +113,21 @@ node_disk_flush_requests_time_seconds_total{device="sdc"} 1.944 node_disk_flush_requests_total{device="sdc"} 1555 # HELP node_disk_info Info of /sys/block/. # TYPE node_disk_info gauge -node_disk_info{device="dm-0",major="252",minor="0",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-1",major="252",minor="1",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-2",major="252",minor="2",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-3",major="252",minor="3",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-4",major="252",minor="4",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-5",major="252",minor="5",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0",major="179",minor="0",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0p1",major="179",minor="1",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0p2",major="179",minor="2",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="nvme0n1",major="259",minor="0",model="SAMSUNG EHFTF55LURSY-000Y9",path="pci-0000:02:00.0-nvme-1",revision="4NBTUY95",serial="S252B6CU1HG3M1",wwn="eui.p3vbbiejx5aae2r3"} 1 -node_disk_info{device="sda",major="8",minor="0",model="TOSHIBA_KSDB4U86",path="pci-0000:3b:00.0-sas-phy7-lun-0",revision="0102",serial="2160A0D5FVGG",wwn="0x7c72382b8de36a64"} 1 -node_disk_info{device="sdb",major="8",minor="16",model="SuperMicro_SSD",path="pci-0000:00:1f.2-ata-1",revision="0R",serial="SMC0E1B87ABBB16BD84E",wwn="0xe1b87abbb16bd84e"} 1 -node_disk_info{device="sdc",major="8",minor="32",model="INTEL_SSDS9X9SI0",path="pci-0000:00:1f.2-ata-4",revision="0100",serial="3EWB5Y25CWQWA7EH1U",wwn="0x58907ddc573a5de"} 1 -node_disk_info{device="sr0",major="11",minor="0",model="Virtual_CDROM0",path="pci-0000:00:14.0-usb-0:1.1:1.0-scsi-0:0:0:0",revision="1.00",serial="AAAABBBBCCCC1",wwn=""} 1 -node_disk_info{device="vda",major="254",minor="0",model="",path="pci-0000:00:06.0",revision="",serial="",wwn=""} 1 +node_disk_info{device="dm-0",major="252",minor="0",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-1",major="252",minor="1",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-2",major="252",minor="2",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-3",major="252",minor="3",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-4",major="252",minor="4",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-5",major="252",minor="5",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0",major="179",minor="0",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0p1",major="179",minor="1",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0p2",major="179",minor="2",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="nvme0n1",major="259",minor="0",model="SAMSUNG EHFTF55LURSY-000Y9",path="pci-0000:02:00.0-nvme-1",revision="4NBTUY95",rotational="0",serial="S252B6CU1HG3M1",wwn="eui.p3vbbiejx5aae2r3"} 1 +node_disk_info{device="sda",major="8",minor="0",model="TOSHIBA_KSDB4U86",path="pci-0000:3b:00.0-sas-phy7-lun-0",revision="0102",rotational="1",serial="2160A0D5FVGG",wwn="0x7c72382b8de36a64"} 1 +node_disk_info{device="sdb",major="8",minor="16",model="SuperMicro_SSD",path="pci-0000:00:1f.2-ata-1",revision="0R",rotational="0",serial="SMC0E1B87ABBB16BD84E",wwn="0xe1b87abbb16bd84e"} 1 +node_disk_info{device="sdc",major="8",minor="32",model="INTEL_SSDS9X9SI0",path="pci-0000:00:1f.2-ata-4",revision="0100",rotational="0",serial="3EWB5Y25CWQWA7EH1U",wwn="0x58907ddc573a5de"} 1 +node_disk_info{device="sr0",major="11",minor="0",model="Virtual_CDROM0",path="pci-0000:00:14.0-usb-0:1.1:1.0-scsi-0:0:0:0",revision="1.00",rotational="0",serial="AAAABBBBCCCC1",wwn=""} 1 +node_disk_info{device="vda",major="254",minor="0",model="",path="pci-0000:00:06.0",revision="",rotational="0",serial="",wwn=""} 1 # HELP node_disk_io_now The number of I/Os currently in progress. # TYPE node_disk_io_now gauge node_disk_io_now{device="dm-0"} 0 @@ -317,10 +317,10 @@ node_disk_written_bytes_total{device="sr0"} 0 node_disk_written_bytes_total{device="vda"} 1.0938236928e+11 ` - logger := log.NewLogfmtLogger(os.Stderr) + logger := slog.New(slog.NewTextHandler(io.Discard, nil)) collector, err := NewDiskstatsCollector(logger) if err != nil { - panic(err) + t.Fatal(err) } c, err := NewTestDiskStatsCollector(logger) if err != nil { diff --git a/collector/diskstats_openbsd.go b/collector/diskstats_openbsd.go index 2a69042aac..49415c17f4 100644 --- a/collector/diskstats_openbsd.go +++ b/collector/diskstats_openbsd.go @@ -18,9 +18,9 @@ package collector import ( "fmt" + "log/slog" "unsafe" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" ) @@ -41,7 +41,7 @@ type diskstatsCollector struct { time typedDesc deviceFilter deviceFilter - logger log.Logger + logger *slog.Logger } func init() { @@ -49,7 +49,7 @@ func init() { } // NewDiskstatsCollector returns a new Collector exposing disk device stats. -func NewDiskstatsCollector(logger log.Logger) (Collector, error) { +func NewDiskstatsCollector(logger *slog.Logger) (Collector, error) { deviceFilter, err := newDiskstatsDeviceFilter(logger) if err != nil { return nil, fmt.Errorf("failed to parse device filter flags: %w", err) diff --git a/collector/diskstats_openbsd_amd64.go b/collector/diskstats_openbsd_amd64.go index a39cabb538..b290d88920 100644 --- a/collector/diskstats_openbsd_amd64.go +++ b/collector/diskstats_openbsd_amd64.go @@ -18,9 +18,9 @@ package collector import ( "fmt" + "log/slog" "unsafe" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" ) @@ -52,7 +52,7 @@ type diskstatsCollector struct { time typedDesc deviceFilter deviceFilter - logger log.Logger + logger *slog.Logger } func init() { @@ -60,7 +60,7 @@ func init() { } // NewDiskstatsCollector returns a new Collector exposing disk device stats. -func NewDiskstatsCollector(logger log.Logger) (Collector, error) { +func NewDiskstatsCollector(logger *slog.Logger) (Collector, error) { deviceFilter, err := newDiskstatsDeviceFilter(logger) if err != nil { return nil, fmt.Errorf("failed to parse device filter flags: %w", err) diff --git a/collector/dmi.go b/collector/dmi.go index 794755076a..2282d7bd00 100644 --- a/collector/dmi.go +++ b/collector/dmi.go @@ -19,11 +19,10 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "strings" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -38,7 +37,7 @@ func init() { } // NewDMICollector returns a new Collector exposing DMI information. -func NewDMICollector(logger log.Logger) (Collector, error) { +func NewDMICollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) @@ -47,7 +46,7 @@ func NewDMICollector(logger log.Logger) (Collector, error) { dmi, err := fs.DMIClass() if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(logger).Log("msg", "Platform does not support Desktop Management Interface (DMI) information", "err", err) + logger.Debug("Platform does not support Desktop Management Interface (DMI) information", "err", err) dmi = &sysfs.DMIClass{} } else { return nil, fmt.Errorf("failed to read Desktop Management Interface (DMI) information: %w", err) diff --git a/collector/drbd_linux.go b/collector/drbd_linux.go index f192a24c6f..cbaf816193 100644 --- a/collector/drbd_linux.go +++ b/collector/drbd_linux.go @@ -20,12 +20,11 @@ import ( "bufio" "errors" "fmt" + "log/slog" "os" "strconv" "strings" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -79,14 +78,14 @@ type drbdCollector struct { numerical map[string]drbdNumericalMetric stringPair map[string]drbdStringPairMetric connected *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { registerCollector("drbd", defaultDisabled, newDRBDCollector) } -func newDRBDCollector(logger log.Logger) (Collector, error) { +func newDRBDCollector(logger *slog.Logger) (Collector, error) { return &drbdCollector{ numerical: map[string]drbdNumericalMetric{ "ns": newDRBDNumericalMetric( @@ -191,7 +190,7 @@ func (c *drbdCollector) Update(ch chan<- prometheus.Metric) error { file, err := os.Open(statsFile) if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "stats file does not exist, skipping", "file", statsFile, "err", err) + c.logger.Debug("stats file does not exist, skipping", "file", statsFile, "err", err) return ErrNoData } @@ -208,7 +207,7 @@ func (c *drbdCollector) Update(ch chan<- prometheus.Metric) error { kv := strings.Split(field, ":") if len(kv) != 2 { - level.Debug(c.logger).Log("msg", "skipping invalid key:value pair", "field", field) + c.logger.Debug("skipping invalid key:value pair", "field", field) continue } @@ -274,7 +273,7 @@ func (c *drbdCollector) Update(ch chan<- prometheus.Metric) error { continue } - level.Debug(c.logger).Log("msg", "unhandled key-value pair", "key", kv[0], "value", kv[1]) + c.logger.Debug("unhandled key-value pair", "key", kv[0], "value", kv[1]) } return scanner.Err() diff --git a/collector/drm_linux.go b/collector/drm_linux.go index 11b8c6283b..61bb59ac77 100644 --- a/collector/drm_linux.go +++ b/collector/drm_linux.go @@ -18,8 +18,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -30,7 +30,7 @@ const ( type drmCollector struct { fs sysfs.FS - logger log.Logger + logger *slog.Logger CardInfo *prometheus.Desc GPUBusyPercent *prometheus.Desc MemoryGTTSize *prometheus.Desc @@ -46,7 +46,7 @@ func init() { } // NewDrmCollector returns a new Collector exposing /sys/class/drm/card?/device stats. -func NewDrmCollector(logger log.Logger) (Collector, error) { +func NewDrmCollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) diff --git a/collector/edac_linux.go b/collector/edac_linux.go index c7719b7a64..c14c96c36e 100644 --- a/collector/edac_linux.go +++ b/collector/edac_linux.go @@ -18,10 +18,10 @@ package collector import ( "fmt" + "log/slog" "path/filepath" "regexp" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -39,7 +39,7 @@ type edacCollector struct { ueCount *prometheus.Desc csRowCECount *prometheus.Desc csRowUECount *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -47,7 +47,7 @@ func init() { } // NewEdacCollector returns a new Collector exposing edac stats. -func NewEdacCollector(logger log.Logger) (Collector, error) { +func NewEdacCollector(logger *slog.Logger) (Collector, error) { return &edacCollector{ ceCount: prometheus.NewDesc( prometheus.BuildFQName(namespace, edacSubsystem, "correctable_errors_total"), diff --git a/collector/entropy_linux.go b/collector/entropy_linux.go index 909d2ff4c2..6da61125c6 100644 --- a/collector/entropy_linux.go +++ b/collector/entropy_linux.go @@ -18,8 +18,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -28,7 +28,7 @@ type entropyCollector struct { fs procfs.FS entropyAvail *prometheus.Desc entropyPoolSize *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -36,7 +36,7 @@ func init() { } // NewEntropyCollector returns a new Collector exposing entropy stats. -func NewEntropyCollector(logger log.Logger) (Collector, error) { +func NewEntropyCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) diff --git a/collector/ethtool_linux.go b/collector/ethtool_linux.go index 7412c27c37..78f7afe2da 100644 --- a/collector/ethtool_linux.go +++ b/collector/ethtool_linux.go @@ -23,6 +23,7 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "regexp" "sort" @@ -31,8 +32,6 @@ import ( "syscall" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" "github.com/safchain/ethtool" @@ -79,13 +78,13 @@ type ethtoolCollector struct { deviceFilter deviceFilter infoDesc *prometheus.Desc metricsPattern *regexp.Regexp - logger log.Logger + logger *slog.Logger } // makeEthtoolCollector is the internal constructor for EthtoolCollector. // This allows NewEthtoolTestCollector to override its .ethtool interface // for testing. -func makeEthtoolCollector(logger log.Logger) (*ethtoolCollector, error) { +func makeEthtoolCollector(logger *slog.Logger) (*ethtoolCollector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) @@ -96,6 +95,16 @@ func makeEthtoolCollector(logger log.Logger) (*ethtoolCollector, error) { return nil, fmt.Errorf("failed to initialize ethtool library: %w", err) } + if *ethtoolDeviceInclude != "" { + logger.Info("Parsed flag --collector.ethtool.device-include", "flag", *ethtoolDeviceInclude) + } + if *ethtoolDeviceExclude != "" { + logger.Info("Parsed flag --collector.ethtool.device-exclude", "flag", *ethtoolDeviceExclude) + } + if *ethtoolIncludedMetrics != "" { + logger.Info("Parsed flag --collector.ethtool.metrics-include", "flag", *ethtoolIncludedMetrics) + } + // Pre-populate some common ethtool metrics. return ðtoolCollector{ fs: fs, @@ -213,7 +222,7 @@ func buildEthtoolFQName(metric string) string { } // NewEthtoolCollector returns a new Collector exposing ethtool stats. -func NewEthtoolCollector(logger log.Logger) (Collector, error) { +func NewEthtoolCollector(logger *slog.Logger) (Collector, error) { return makeEthtoolCollector(logger) } @@ -363,10 +372,10 @@ func (c *ethtoolCollector) updateSpeeds(ch chan<- prometheus.Metric, prefix stri } func (c *ethtoolCollector) Update(ch chan<- prometheus.Metric) error { - netClass, err := c.fs.NetClass() + netClass, err := c.fs.NetClassDevices() if err != nil { if errors.Is(err, os.ErrNotExist) || errors.Is(err, os.ErrPermission) { - level.Debug(c.logger).Log("msg", "Could not read netclass file", "err", err) + c.logger.Debug("Could not read netclass file", "err", err) return ErrNoData } return fmt.Errorf("could not get net class info: %w", err) @@ -376,7 +385,7 @@ func (c *ethtoolCollector) Update(ch chan<- prometheus.Metric) error { return fmt.Errorf("no network devices found") } - for device := range netClass { + for _, device := range netClass { var stats map[string]uint64 var err error @@ -395,12 +404,12 @@ func (c *ethtoolCollector) Update(ch chan<- prometheus.Metric) error { } else { if errno, ok := err.(syscall.Errno); ok { if err == unix.EOPNOTSUPP { - level.Debug(c.logger).Log("msg", "ethtool link info error", "err", err, "device", device, "errno", uint(errno)) + c.logger.Debug("ethtool link info error", "err", err, "device", device, "errno", uint(errno)) } else if errno != 0 { - level.Error(c.logger).Log("msg", "ethtool link info error", "err", err, "device", device, "errno", uint(errno)) + c.logger.Error("ethtool link info error", "err", err, "device", device, "errno", uint(errno)) } } else { - level.Error(c.logger).Log("msg", "ethtool link info error", "err", err, "device", device) + c.logger.Error("ethtool link info error", "err", err, "device", device) } } @@ -412,12 +421,12 @@ func (c *ethtoolCollector) Update(ch chan<- prometheus.Metric) error { } else { if errno, ok := err.(syscall.Errno); ok { if err == unix.EOPNOTSUPP { - level.Debug(c.logger).Log("msg", "ethtool driver info error", "err", err, "device", device, "errno", uint(errno)) + c.logger.Debug("ethtool driver info error", "err", err, "device", device, "errno", uint(errno)) } else if errno != 0 { - level.Error(c.logger).Log("msg", "ethtool driver info error", "err", err, "device", device, "errno", uint(errno)) + c.logger.Error("ethtool driver info error", "err", err, "device", device, "errno", uint(errno)) } } else { - level.Error(c.logger).Log("msg", "ethtool driver info error", "err", err, "device", device) + c.logger.Error("ethtool driver info error", "err", err, "device", device) } } @@ -428,12 +437,12 @@ func (c *ethtoolCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { if errno, ok := err.(syscall.Errno); ok { if err == unix.EOPNOTSUPP { - level.Debug(c.logger).Log("msg", "ethtool stats error", "err", err, "device", device, "errno", uint(errno)) + c.logger.Debug("ethtool stats error", "err", err, "device", device, "errno", uint(errno)) } else if errno != 0 { - level.Error(c.logger).Log("msg", "ethtool stats error", "err", err, "device", device, "errno", uint(errno)) + c.logger.Error("ethtool stats error", "err", err, "device", device, "errno", uint(errno)) } } else { - level.Error(c.logger).Log("msg", "ethtool stats error", "err", err, "device", device) + c.logger.Error("ethtool stats error", "err", err, "device", device) } } @@ -452,7 +461,7 @@ func (c *ethtoolCollector) Update(ch chan<- prometheus.Metric) error { metricFQName := buildEthtoolFQName(metricName) existingMetric, exists := metricFQNames[metricFQName] if exists { - level.Debug(c.logger).Log("msg", "dropping duplicate metric name", "device", device, + c.logger.Debug("dropping duplicate metric name", "device", device, "metricFQName", metricFQName, "metric1", existingMetric, "metric2", metricName) // Keep the metricName as "deleted" in the dict in case there are 3 duplicates. metricFQNames[metricFQName] = "" diff --git a/collector/ethtool_linux_test.go b/collector/ethtool_linux_test.go index cf55c6b1f5..98e66dbc20 100644 --- a/collector/ethtool_linux_test.go +++ b/collector/ethtool_linux_test.go @@ -19,6 +19,8 @@ package collector import ( "bufio" "fmt" + "io" + "log/slog" "os" "path/filepath" "strconv" @@ -26,7 +28,6 @@ import ( "syscall" "testing" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/testutil" "github.com/safchain/ethtool" @@ -49,7 +50,7 @@ func (c testEthtoolCollector) Describe(ch chan<- *prometheus.Desc) { prometheus.DescribeByCollect(c, ch) } -func NewTestEthtoolCollector(logger log.Logger) (prometheus.Collector, error) { +func NewTestEthtoolCollector(logger *slog.Logger) (prometheus.Collector, error) { dsc, err := NewEthtoolTestCollector(logger) if err != nil { return testEthtoolCollector{}, err @@ -255,14 +256,14 @@ func (e *EthtoolFixture) LinkInfo(intf string) (ethtool.EthtoolCmd, error) { return res, err } -func NewEthtoolTestCollector(logger log.Logger) (Collector, error) { +func NewEthtoolTestCollector(logger *slog.Logger) (Collector, error) { collector, err := makeEthtoolCollector(logger) - collector.ethtool = &EthtoolFixture{ - fixturePath: "fixtures/ethtool/", - } if err != nil { return nil, err } + collector.ethtool = &EthtoolFixture{ + fixturePath: "fixtures/ethtool/", + } return collector, nil } @@ -370,10 +371,10 @@ node_network_supported_speed_bytes{device="eth0",duplex="half",mode="10baseT"} 1 ` *sysPath = "fixtures/sys" - logger := log.NewLogfmtLogger(os.Stderr) + logger := slog.New(slog.NewTextHandler(io.Discard, nil)) collector, err := NewEthtoolTestCollector(logger) if err != nil { - panic(err) + t.Fatal(err) } c, err := NewTestEthtoolCollector(logger) if err != nil { diff --git a/collector/exec_bsd.go b/collector/exec_bsd.go index 87cb3ceeb4..07de879ee0 100644 --- a/collector/exec_bsd.go +++ b/collector/exec_bsd.go @@ -18,13 +18,13 @@ package collector import ( - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" + "log/slog" ) type execCollector struct { sysctls []bsdSysctl - logger log.Logger + logger *slog.Logger } func init() { @@ -32,7 +32,7 @@ func init() { } // NewExecCollector returns a new Collector exposing system execution statistics. -func NewExecCollector(logger log.Logger) (Collector, error) { +func NewExecCollector(logger *slog.Logger) (Collector, error) { // From sys/vm/vm_meter.c: // All are of type CTLTYPE_UINT. // diff --git a/collector/fibrechannel_linux.go b/collector/fibrechannel_linux.go index 13a3b5dc16..cb8be9db1d 100644 --- a/collector/fibrechannel_linux.go +++ b/collector/fibrechannel_linux.go @@ -18,11 +18,11 @@ package collector import ( "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" + "github.com/prometheus/node_exporter/collector/utils" "github.com/prometheus/procfs/sysfs" ) @@ -31,7 +31,7 @@ const maxUint64 = ^uint64(0) type fibrechannelCollector struct { fs sysfs.FS metricDescs map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger subsystem string } @@ -40,7 +40,7 @@ func init() { } // NewFibreChannelCollector returns a new Collector exposing FibreChannel stats. -func NewFibreChannelCollector(logger log.Logger) (Collector, error) { +func NewFibreChannelCollector(logger *slog.Logger) (Collector, error) { var i fibrechannelCollector var err error @@ -98,7 +98,7 @@ func (c *fibrechannelCollector) Update(ch chan<- prometheus.Metric) error { hosts, err := c.fs.FibreChannelClass() if err != nil { if os.IsNotExist(err) { - level.Debug(c.logger).Log("msg", "fibrechannel statistics not found, skipping") + c.logger.Debug("fibrechannel statistics not found, skipping") return ErrNoData } return fmt.Errorf("error obtaining FibreChannel class info: %s", err) @@ -114,23 +114,36 @@ func (c *fibrechannelCollector) Update(ch chan<- prometheus.Metric) error { infoValue := 1.0 // First push the Host values - ch <- prometheus.MustNewConstMetric(infoDesc, prometheus.GaugeValue, infoValue, host.Name, host.Speed, host.PortState, host.PortType, host.PortID, host.PortName, host.FabricName, host.SymbolicName, host.SupportedClasses, host.SupportedSpeeds, host.DevLossTMO) + ch <- prometheus.MustNewConstMetric(infoDesc, prometheus.GaugeValue, infoValue, utils.SafeDereference( + host.Name, + host.Speed, + host.PortState, + host.PortType, + host.PortID, + host.PortName, + host.FabricName, + host.SymbolicName, + host.SupportedClasses, + host.SupportedSpeeds, + host.DevLossTMO, + )...) // Then the counters - c.pushCounter(ch, "dumped_frames_total", host.Counters.DumpedFrames, host.Name) - c.pushCounter(ch, "error_frames_total", host.Counters.ErrorFrames, host.Name) - c.pushCounter(ch, "invalid_crc_total", host.Counters.InvalidCRCCount, host.Name) - c.pushCounter(ch, "rx_frames_total", host.Counters.RXFrames, host.Name) - c.pushCounter(ch, "rx_words_total", host.Counters.RXWords, host.Name) - c.pushCounter(ch, "tx_frames_total", host.Counters.TXFrames, host.Name) - c.pushCounter(ch, "tx_words_total", host.Counters.TXWords, host.Name) - c.pushCounter(ch, "seconds_since_last_reset_total", host.Counters.SecondsSinceLastReset, host.Name) - c.pushCounter(ch, "invalid_tx_words_total", host.Counters.InvalidTXWordCount, host.Name) - c.pushCounter(ch, "link_failure_total", host.Counters.LinkFailureCount, host.Name) - c.pushCounter(ch, "loss_of_sync_total", host.Counters.LossOfSyncCount, host.Name) - c.pushCounter(ch, "loss_of_signal_total", host.Counters.LossOfSignalCount, host.Name) - c.pushCounter(ch, "nos_total", host.Counters.NosCount, host.Name) - c.pushCounter(ch, "fcp_packet_aborts_total", host.Counters.FCPPacketAborts, host.Name) + // Note: `procfs` guarantees these a safe dereference for these counters. + c.pushCounter(ch, "dumped_frames_total", *host.Counters.DumpedFrames, *host.Name) + c.pushCounter(ch, "error_frames_total", *host.Counters.ErrorFrames, *host.Name) + c.pushCounter(ch, "invalid_crc_total", *host.Counters.InvalidCRCCount, *host.Name) + c.pushCounter(ch, "rx_frames_total", *host.Counters.RXFrames, *host.Name) + c.pushCounter(ch, "rx_words_total", *host.Counters.RXWords, *host.Name) + c.pushCounter(ch, "tx_frames_total", *host.Counters.TXFrames, *host.Name) + c.pushCounter(ch, "tx_words_total", *host.Counters.TXWords, *host.Name) + c.pushCounter(ch, "seconds_since_last_reset_total", *host.Counters.SecondsSinceLastReset, *host.Name) + c.pushCounter(ch, "invalid_tx_words_total", *host.Counters.InvalidTXWordCount, *host.Name) + c.pushCounter(ch, "link_failure_total", *host.Counters.LinkFailureCount, *host.Name) + c.pushCounter(ch, "loss_of_sync_total", *host.Counters.LossOfSyncCount, *host.Name) + c.pushCounter(ch, "loss_of_signal_total", *host.Counters.LossOfSignalCount, *host.Name) + c.pushCounter(ch, "nos_total", *host.Counters.NosCount, *host.Name) + c.pushCounter(ch, "fcp_packet_aborts_total", *host.Counters.FCPPacketAborts, *host.Name) } return nil diff --git a/collector/filefd_linux.go b/collector/filefd_linux.go index 55069d6c5d..39a72fcd43 100644 --- a/collector/filefd_linux.go +++ b/collector/filefd_linux.go @@ -20,10 +20,10 @@ import ( "bytes" "fmt" "io" + "log/slog" "os" "strconv" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -32,7 +32,7 @@ const ( ) type fileFDStatCollector struct { - logger log.Logger + logger *slog.Logger } func init() { @@ -40,7 +40,7 @@ func init() { } // NewFileFDStatCollector returns a new Collector exposing file-nr stats. -func NewFileFDStatCollector(logger log.Logger) (Collector, error) { +func NewFileFDStatCollector(logger *slog.Logger) (Collector, error) { return &fileFDStatCollector{logger}, nil } diff --git a/collector/filesystem_aix.go b/collector/filesystem_aix.go new file mode 100644 index 0000000000..a1314a0f01 --- /dev/null +++ b/collector/filesystem_aix.go @@ -0,0 +1,65 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !nofilesystem +// +build !nofilesystem + +package collector + +import ( + "github.com/power-devops/perfstat" +) + +const ( + defMountPointsExcluded = "^/(dev|aha)($|/)" + defFSTypesExcluded = "^procfs$" +) + +// Expose filesystem fullness. +func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) { + fsStat, err := perfstat.FileSystemStat() + if err != nil { + return nil, err + } + for _, stat := range fsStat { + if c.mountPointFilter.ignored(stat.MountPoint) { + c.logger.Debug("Ignoring mount point", "mountpoint", stat.MountPoint) + continue + } + fstype := stat.TypeString() + if c.fsTypeFilter.ignored(fstype) { + c.logger.Debug("Ignoring fs type", "type", fstype) + continue + } + + ro := 0.0 + if stat.Flags&perfstat.VFS_READONLY != 0 { + ro = 1.0 + } + + stats = append(stats, filesystemStats{ + labels: filesystemLabels{ + device: stat.Device, + mountPoint: stat.MountPoint, + fsType: fstype, + }, + size: float64(stat.TotalBlocks / 512.0), + free: float64(stat.FreeBlocks / 512.0), + avail: float64(stat.FreeBlocks / 512.0), // AIX doesn't distinguish between free and available blocks. + files: float64(stat.TotalInodes), + filesFree: float64(stat.FreeInodes), + ro: ro, + }) + } + return stats, nil +} diff --git a/collector/filesystem_bsd.go b/collector/filesystem_bsd.go index d3025a0171..2810a5a3d5 100644 --- a/collector/filesystem_bsd.go +++ b/collector/filesystem_bsd.go @@ -11,17 +11,14 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build (darwin || dragonfly) && !nofilesystem -// +build darwin dragonfly -// +build !nofilesystem +//go:build dragonfly && !nofilesystem +// +build dragonfly,!nofilesystem package collector import ( "errors" "unsafe" - - "github.com/go-kit/log/level" ) /* @@ -50,15 +47,15 @@ func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) { stats = []filesystemStats{} for i := 0; i < int(count); i++ { mountpoint := C.GoString(&mnt[i].f_mntonname[0]) - if c.excludedMountPointsPattern.MatchString(mountpoint) { - level.Debug(c.logger).Log("msg", "Ignoring mount point", "mountpoint", mountpoint) + if c.mountPointFilter.ignored(mountpoint) { + c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint) continue } device := C.GoString(&mnt[i].f_mntfromname[0]) fstype := C.GoString(&mnt[i].f_fstypename[0]) - if c.excludedFSTypesPattern.MatchString(fstype) { - level.Debug(c.logger).Log("msg", "Ignoring fs type", "type", fstype) + if c.fsTypeFilter.ignored(fstype) { + c.logger.Debug("Ignoring fs type", "type", fstype) continue } diff --git a/collector/filesystem_common.go b/collector/filesystem_common.go index f5d5135241..4161b3fe57 100644 --- a/collector/filesystem_common.go +++ b/collector/filesystem_common.go @@ -11,19 +11,18 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build !nofilesystem && (linux || freebsd || openbsd || darwin || dragonfly) +//go:build !nofilesystem && (linux || freebsd || netbsd || openbsd || darwin || dragonfly || aix) // +build !nofilesystem -// +build linux freebsd openbsd darwin dragonfly +// +build linux freebsd netbsd openbsd darwin dragonfly aix package collector import ( "errors" - "regexp" + "fmt" + "log/slog" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -37,7 +36,7 @@ var ( mountPointsExcludeSet bool mountPointsExclude = kingpin.Flag( "collector.filesystem.mount-points-exclude", - "Regexp of mount points to exclude for filesystem collector.", + "Regexp of mount points to exclude for filesystem collector. (mutually exclusive to mount-points-include)", ).Default(defMountPointsExcluded).PreAction(func(c *kingpin.ParseContext) error { mountPointsExcludeSet = true return nil @@ -46,11 +45,15 @@ var ( "collector.filesystem.ignored-mount-points", "Regexp of mount points to ignore for filesystem collector.", ).Hidden().String() + mountPointsInclude = kingpin.Flag( + "collector.filesystem.mount-points-include", + "Regexp of mount points to include for filesystem collector. (mutually exclusive to mount-points-exclude)", + ).String() fsTypesExcludeSet bool fsTypesExclude = kingpin.Flag( "collector.filesystem.fs-types-exclude", - "Regexp of filesystem types to exclude for filesystem collector.", + "Regexp of filesystem types to exclude for filesystem collector. (mutually exclusive to fs-types-include)", ).Default(defFSTypesExcluded).PreAction(func(c *kingpin.ParseContext) error { fsTypesExcludeSet = true return nil @@ -59,27 +62,34 @@ var ( "collector.filesystem.ignored-fs-types", "Regexp of filesystem types to ignore for filesystem collector.", ).Hidden().String() + fsTypesInclude = kingpin.Flag( + "collector.filesystem.fs-types-include", + "Regexp of filesystem types to exclude for filesystem collector. (mutually exclusive to fs-types-exclude)", + ).String() filesystemLabelNames = []string{"device", "mountpoint", "fstype", "device_error"} ) type filesystemCollector struct { - excludedMountPointsPattern *regexp.Regexp - excludedFSTypesPattern *regexp.Regexp + mountPointFilter deviceFilter + fsTypeFilter deviceFilter sizeDesc, freeDesc, availDesc *prometheus.Desc filesDesc, filesFreeDesc *prometheus.Desc + purgeableDesc *prometheus.Desc roDesc, deviceErrorDesc *prometheus.Desc - logger log.Logger + mountInfoDesc *prometheus.Desc + logger *slog.Logger } type filesystemLabels struct { - device, mountPoint, fsType, options, deviceError string + device, mountPoint, fsType, options, deviceError, major, minor string } type filesystemStats struct { labels filesystemLabels size, free, avail float64 files, filesFree float64 + purgeable float64 ro, deviceError float64 } @@ -88,30 +98,8 @@ func init() { } // NewFilesystemCollector returns a new Collector exposing filesystems stats. -func NewFilesystemCollector(logger log.Logger) (Collector, error) { - if *oldMountPointsExcluded != "" { - if !mountPointsExcludeSet { - level.Warn(logger).Log("msg", "--collector.filesystem.ignored-mount-points is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.mount-points-exclude") - *mountPointsExclude = *oldMountPointsExcluded - } else { - return nil, errors.New("--collector.filesystem.ignored-mount-points and --collector.filesystem.mount-points-exclude are mutually exclusive") - } - } - - if *oldFSTypesExcluded != "" { - if !fsTypesExcludeSet { - level.Warn(logger).Log("msg", "--collector.filesystem.ignored-fs-types is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.fs-types-exclude") - *fsTypesExclude = *oldFSTypesExcluded - } else { - return nil, errors.New("--collector.filesystem.ignored-fs-types and --collector.filesystem.fs-types-exclude are mutually exclusive") - } - } - - subsystem := "filesystem" - level.Info(logger).Log("msg", "Parsed flag --collector.filesystem.mount-points-exclude", "flag", *mountPointsExclude) - mountPointPattern := regexp.MustCompile(*mountPointsExclude) - level.Info(logger).Log("msg", "Parsed flag --collector.filesystem.fs-types-exclude", "flag", *fsTypesExclude) - filesystemsTypesPattern := regexp.MustCompile(*fsTypesExclude) +func NewFilesystemCollector(logger *slog.Logger) (Collector, error) { + const subsystem = "filesystem" sizeDesc := prometheus.NewDesc( prometheus.BuildFQName(namespace, subsystem, "size_bytes"), @@ -143,6 +131,12 @@ func NewFilesystemCollector(logger log.Logger) (Collector, error) { filesystemLabelNames, nil, ) + purgeableDesc := prometheus.NewDesc( + prometheus.BuildFQName(namespace, subsystem, "purgeable_bytes"), + "Filesystem space available including purgeable space (MacOS specific).", + filesystemLabelNames, nil, + ) + roDesc := prometheus.NewDesc( prometheus.BuildFQName(namespace, subsystem, "readonly"), "Filesystem read-only status.", @@ -155,17 +149,36 @@ func NewFilesystemCollector(logger log.Logger) (Collector, error) { filesystemLabelNames, nil, ) + mountInfoDesc := prometheus.NewDesc( + prometheus.BuildFQName(namespace, subsystem, "mount_info"), + "Filesystem mount information.", + []string{"device", "major", "minor", "mountpoint"}, + nil, + ) + + mountPointFilter, err := newMountPointsFilter(logger) + if err != nil { + return nil, fmt.Errorf("unable to parse mount points filter flags: %w", err) + } + + fsTypeFilter, err := newFSTypeFilter(logger) + if err != nil { + return nil, fmt.Errorf("unable to parse fs types filter flags: %w", err) + } + return &filesystemCollector{ - excludedMountPointsPattern: mountPointPattern, - excludedFSTypesPattern: filesystemsTypesPattern, - sizeDesc: sizeDesc, - freeDesc: freeDesc, - availDesc: availDesc, - filesDesc: filesDesc, - filesFreeDesc: filesFreeDesc, - roDesc: roDesc, - deviceErrorDesc: deviceErrorDesc, - logger: logger, + mountPointFilter: mountPointFilter, + fsTypeFilter: fsTypeFilter, + sizeDesc: sizeDesc, + freeDesc: freeDesc, + availDesc: availDesc, + filesDesc: filesDesc, + filesFreeDesc: filesFreeDesc, + purgeableDesc: purgeableDesc, + roDesc: roDesc, + deviceErrorDesc: deviceErrorDesc, + mountInfoDesc: mountInfoDesc, + logger: logger, }, nil } @@ -215,6 +228,74 @@ func (c *filesystemCollector) Update(ch chan<- prometheus.Metric) error { c.filesFreeDesc, prometheus.GaugeValue, s.filesFree, s.labels.device, s.labels.mountPoint, s.labels.fsType, s.labels.deviceError, ) + ch <- prometheus.MustNewConstMetric( + c.mountInfoDesc, prometheus.GaugeValue, + 1.0, s.labels.device, s.labels.major, s.labels.minor, s.labels.mountPoint, + ) + if s.purgeable >= 0 { + ch <- prometheus.MustNewConstMetric( + c.purgeableDesc, prometheus.GaugeValue, + s.purgeable, s.labels.device, s.labels.mountPoint, s.labels.fsType, s.labels.deviceError, + ) + } } return nil } + +func newMountPointsFilter(logger *slog.Logger) (deviceFilter, error) { + if *oldMountPointsExcluded != "" { + if !mountPointsExcludeSet { + logger.Warn("--collector.filesystem.ignored-mount-points is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.mount-points-exclude") + *mountPointsExclude = *oldMountPointsExcluded + } else { + return deviceFilter{}, errors.New("--collector.filesystem.ignored-mount-points and --collector.filesystem.mount-points-exclude are mutually exclusive") + } + } + + if *mountPointsInclude != "" && !mountPointsExcludeSet { + logger.Debug("mount-points-exclude flag not set when mount-points-include flag is set, assuming include is desired") + *mountPointsExclude = "" + } + + if *mountPointsExclude != "" && *mountPointsInclude != "" { + return deviceFilter{}, errors.New("--collector.filesystem.mount-points-exclude and --collector.filesystem.mount-points-include are mutually exclusive") + } + + if *mountPointsExclude != "" { + logger.Info("Parsed flag --collector.filesystem.mount-points-exclude", "flag", *mountPointsExclude) + } + if *mountPointsInclude != "" { + logger.Info("Parsed flag --collector.filesystem.mount-points-include", "flag", *mountPointsInclude) + } + + return newDeviceFilter(*mountPointsExclude, *mountPointsInclude), nil +} + +func newFSTypeFilter(logger *slog.Logger) (deviceFilter, error) { + if *oldFSTypesExcluded != "" { + if !fsTypesExcludeSet { + logger.Warn("--collector.filesystem.ignored-fs-types is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.fs-types-exclude") + *fsTypesExclude = *oldFSTypesExcluded + } else { + return deviceFilter{}, errors.New("--collector.filesystem.ignored-fs-types and --collector.filesystem.fs-types-exclude are mutually exclusive") + } + } + + if *fsTypesInclude != "" && !fsTypesExcludeSet { + logger.Debug("fs-types-exclude flag not set when fs-types-include flag is set, assuming include is desired") + *fsTypesExclude = "" + } + + if *fsTypesExclude != "" && *fsTypesInclude != "" { + return deviceFilter{}, errors.New("--collector.filesystem.fs-types-exclude and --collector.filesystem.fs-types-include are mutually exclusive") + } + + if *fsTypesExclude != "" { + logger.Info("Parsed flag --collector.filesystem.fs-types-exclude", "flag", *fsTypesExclude) + } + if *fsTypesInclude != "" { + logger.Info("Parsed flag --collector.filesystem.fs-types-include", "flag", *fsTypesInclude) + } + + return newDeviceFilter(*fsTypesExclude, *fsTypesInclude), nil +} diff --git a/collector/filesystem_freebsd.go b/collector/filesystem_freebsd.go index f05702d14f..502ae0a850 100644 --- a/collector/filesystem_freebsd.go +++ b/collector/filesystem_freebsd.go @@ -17,7 +17,6 @@ package collector import ( - "github.com/go-kit/log/level" "golang.org/x/sys/unix" ) @@ -40,20 +39,20 @@ func (c *filesystemCollector) GetStats() ([]filesystemStats, error) { stats := []filesystemStats{} for _, fs := range buf { mountpoint := unix.ByteSliceToString(fs.Mntonname[:]) - if c.excludedMountPointsPattern.MatchString(mountpoint) { - level.Debug(c.logger).Log("msg", "Ignoring mount point", "mountpoint", mountpoint) + if c.mountPointFilter.ignored(mountpoint) { + c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint) continue } device := unix.ByteSliceToString(fs.Mntfromname[:]) fstype := unix.ByteSliceToString(fs.Fstypename[:]) - if c.excludedFSTypesPattern.MatchString(fstype) { - level.Debug(c.logger).Log("msg", "Ignoring fs type", "type", fstype) + if c.fsTypeFilter.ignored(fstype) { + c.logger.Debug("Ignoring fs type", "type", fstype) continue } if (fs.Flags & unix.MNT_IGNORE) != 0 { - level.Debug(c.logger).Log("msg", "Ignoring mount flagged as ignore", "mountpoint", mountpoint) + c.logger.Debug("Ignoring mount flagged as ignore", "mountpoint", mountpoint) continue } diff --git a/collector/filesystem_linux.go b/collector/filesystem_linux.go index 1d0c8493b9..3a7bda4d24 100644 --- a/collector/filesystem_linux.go +++ b/collector/filesystem_linux.go @@ -21,14 +21,13 @@ import ( "errors" "fmt" "io" + "log/slog" "os" "strings" "sync" "time" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "golang.org/x/sys/unix" ) @@ -74,12 +73,12 @@ func (c *filesystemCollector) GetStats() ([]filesystemStats, error) { go func() { for _, labels := range mps { - if c.excludedMountPointsPattern.MatchString(labels.mountPoint) { - level.Debug(c.logger).Log("msg", "Ignoring mount point", "mountpoint", labels.mountPoint) + if c.mountPointFilter.ignored(labels.mountPoint) { + c.logger.Debug("Ignoring mount point", "mountpoint", labels.mountPoint) continue } - if c.excludedFSTypesPattern.MatchString(labels.fsType) { - level.Debug(c.logger).Log("msg", "Ignoring fs", "type", labels.fsType) + if c.fsTypeFilter.ignored(labels.fsType) { + c.logger.Debug("Ignoring fs type", "type", labels.fsType) continue } @@ -90,7 +89,7 @@ func (c *filesystemCollector) GetStats() ([]filesystemStats, error) { labels: labels, deviceError: 1, }) - level.Debug(c.logger).Log("msg", "Mount point is in an unresponsive state", "mountpoint", labels.mountPoint) + c.logger.Debug("Mount point is in an unresponsive state", "mountpoint", labels.mountPoint) stuckMountsMtx.Unlock() continue } @@ -128,14 +127,14 @@ func (c *filesystemCollector) processStat(labels filesystemLabels) filesystemSta // If the mount has been marked as stuck, unmark it and log it's recovery. if _, ok := stuckMounts[labels.mountPoint]; ok { - level.Debug(c.logger).Log("msg", "Mount point has recovered, monitoring will resume", "mountpoint", labels.mountPoint) + c.logger.Debug("Mount point has recovered, monitoring will resume", "mountpoint", labels.mountPoint) delete(stuckMounts, labels.mountPoint) } stuckMountsMtx.Unlock() if err != nil { labels.deviceError = err.Error() - level.Debug(c.logger).Log("msg", "Error on statfs() system call", "rootfs", rootfsFilePath(labels.mountPoint), "err", err) + c.logger.Debug("Error on statfs() system call", "rootfs", rootfsFilePath(labels.mountPoint), "err", err) return filesystemStats{ labels: labels, deviceError: 1, @@ -157,7 +156,7 @@ func (c *filesystemCollector) processStat(labels filesystemLabels) filesystemSta // stuckMountWatcher listens on the given success channel and if the channel closes // then the watcher does nothing. If instead the timeout is reached, the // mount point that is being watched is marked as stuck. -func stuckMountWatcher(mountPoint string, success chan struct{}, logger log.Logger) { +func stuckMountWatcher(mountPoint string, success chan struct{}, logger *slog.Logger) { mountCheckTimer := time.NewTimer(*mountTimeout) defer mountCheckTimer.Stop() select { @@ -170,19 +169,19 @@ func stuckMountWatcher(mountPoint string, success chan struct{}, logger log.Logg case <-success: // Success came in just after the timeout was reached, don't label the mount as stuck default: - level.Debug(logger).Log("msg", "Mount point timed out, it is being labeled as stuck and will not be monitored", "mountpoint", mountPoint) + logger.Debug("Mount point timed out, it is being labeled as stuck and will not be monitored", "mountpoint", mountPoint) stuckMounts[mountPoint] = struct{}{} } stuckMountsMtx.Unlock() } } -func mountPointDetails(logger log.Logger) ([]filesystemLabels, error) { - file, err := os.Open(procFilePath("1/mounts")) +func mountPointDetails(logger *slog.Logger) ([]filesystemLabels, error) { + file, err := os.Open(procFilePath("1/mountinfo")) if errors.Is(err, os.ErrNotExist) { - // Fallback to `/proc/mounts` if `/proc/1/mounts` is missing due hidepid. - level.Debug(logger).Log("msg", "Reading root mounts failed, falling back to system mounts", "err", err) - file, err = os.Open(procFilePath("mounts")) + // Fallback to `/proc/self/mountinfo` if `/proc/1/mountinfo` is missing due hidepid. + logger.Debug("Reading root mounts failed, falling back to self mounts", "err", err) + file, err = os.Open(procFilePath("self/mountinfo")) } if err != nil { return nil, err @@ -199,20 +198,33 @@ func parseFilesystemLabels(r io.Reader) ([]filesystemLabels, error) { for scanner.Scan() { parts := strings.Fields(scanner.Text()) - if len(parts) < 4 { + if len(parts) < 10 { return nil, fmt.Errorf("malformed mount point information: %q", scanner.Text()) } + major, minor := 0, 0 + _, err := fmt.Sscanf(parts[2], "%d:%d", &major, &minor) + if err != nil { + return nil, fmt.Errorf("malformed mount point information: %q", scanner.Text()) + } + + m := 5 + for parts[m+1] != "-" { + m++ + } + // Ensure we handle the translation of \040 and \011 // as per fstab(5). - parts[1] = strings.Replace(parts[1], "\\040", " ", -1) - parts[1] = strings.Replace(parts[1], "\\011", "\t", -1) + parts[4] = strings.Replace(parts[4], "\\040", " ", -1) + parts[4] = strings.Replace(parts[4], "\\011", "\t", -1) filesystems = append(filesystems, filesystemLabels{ - device: parts[0], - mountPoint: rootfsStripPrefix(parts[1]), - fsType: parts[2], - options: parts[3], + device: parts[m+3], + mountPoint: rootfsStripPrefix(parts[4]), + fsType: parts[m+2], + options: parts[5], + major: fmt.Sprint(major), + minor: fmt.Sprint(minor), deviceError: "", }) } diff --git a/collector/filesystem_linux_test.go b/collector/filesystem_linux_test.go index 325ffc87b2..d088598f3c 100644 --- a/collector/filesystem_linux_test.go +++ b/collector/filesystem_linux_test.go @@ -17,11 +17,12 @@ package collector import ( + "io" + "log/slog" "strings" "testing" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" ) func Test_parseFilesystemLabelsError(t *testing.T) { @@ -82,15 +83,23 @@ func TestMountPointDetails(t *testing.T) { "/var/lib/kubelet/plugins/kubernetes.io/vsphere-volume/mounts/[vsanDatastore] bafb9e5a-8856-7e6c-699c-801844e77a4a/kubernetes-dynamic-pvc-3eba5bba-48a3-11e8-89ab-005056b92113.vmdk": "", } - filesystems, err := mountPointDetails(log.NewNopLogger()) + filesystems, err := mountPointDetails(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { t.Log(err) } + foundSet := map[string]bool{} for _, fs := range filesystems { if _, ok := expected[fs.mountPoint]; !ok { t.Errorf("Got unexpected %s", fs.mountPoint) } + foundSet[fs.mountPoint] = true + } + + for mountPoint := range expected { + if _, ok := foundSet[mountPoint]; !ok { + t.Errorf("Expected %s, got nothing", mountPoint) + } } } @@ -103,7 +112,7 @@ func TestMountsFallback(t *testing.T) { "/": "", } - filesystems, err := mountPointDetails(log.NewNopLogger()) + filesystems, err := mountPointDetails(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { t.Log(err) } @@ -131,7 +140,7 @@ func TestPathRootfs(t *testing.T) { "/sys/fs/cgroup": "", } - filesystems, err := mountPointDetails(log.NewNopLogger()) + filesystems, err := mountPointDetails(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { t.Log(err) } diff --git a/collector/filesystem_macos.go b/collector/filesystem_macos.go new file mode 100644 index 0000000000..26b3064428 --- /dev/null +++ b/collector/filesystem_macos.go @@ -0,0 +1,107 @@ +// Copyright 2015 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build darwin && !nofilesystem +// +build darwin,!nofilesystem + +package collector + +/* +#cgo CFLAGS: -x objective-c +#cgo LDFLAGS: -framework Foundation +#import +Float64 purgeable(char *path) { + CFNumberRef tmp; + NSError *error = nil; + NSString *str = [NSString stringWithUTF8String:path]; + NSURL *fileURL = [[NSURL alloc] initFileURLWithPath:str]; + NSDictionary *results = [fileURL resourceValuesForKeys:@[NSURLVolumeAvailableCapacityForImportantUsageKey] error:&error]; + if (results) { + if ((tmp = CFDictionaryGetValue((CFDictionaryRef)results, NSURLVolumeAvailableCapacityForImportantUsageKey)) == NULL) { + return -1.0f; + } + Float64 value; + if (CFNumberGetValue(tmp, kCFNumberFloat64Type, &value)) { + return value; + } + } + return -1.0f; +} +*/ +import "C" + +import ( + "errors" + "unsafe" +) + +/* +#include +#include +#include +#include +*/ +import "C" + +const ( + defMountPointsExcluded = "^/(dev)($|/)" + defFSTypesExcluded = "^devfs$" + readOnly = 0x1 // MNT_RDONLY +) + +// Expose filesystem fullness. +func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) { + var mntbuf *C.struct_statfs + count := C.getmntinfo(&mntbuf, C.MNT_NOWAIT) + if count == 0 { + return nil, errors.New("getmntinfo() failed") + } + + mnt := (*[1 << 20]C.struct_statfs)(unsafe.Pointer(mntbuf)) + stats = []filesystemStats{} + for i := 0; i < int(count); i++ { + mountpoint := C.GoString(&mnt[i].f_mntonname[0]) + if c.mountPointFilter.ignored(mountpoint) { + c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint) + continue + } + + device := C.GoString(&mnt[i].f_mntfromname[0]) + fstype := C.GoString(&mnt[i].f_fstypename[0]) + if c.fsTypeFilter.ignored(fstype) { + c.logger.Debug("Ignoring fs type", "type", fstype) + continue + } + + var ro float64 + if (mnt[i].f_flags & readOnly) != 0 { + ro = 1 + } + + stats = append(stats, filesystemStats{ + labels: filesystemLabels{ + device: device, + mountPoint: rootfsStripPrefix(mountpoint), + fsType: fstype, + }, + size: float64(mnt[i].f_blocks) * float64(mnt[i].f_bsize), + free: float64(mnt[i].f_bfree) * float64(mnt[i].f_bsize), + avail: float64(mnt[i].f_bavail) * float64(mnt[i].f_bsize), + files: float64(mnt[i].f_files), + filesFree: float64(mnt[i].f_ffree), + purgeable: float64(C.purgeable(C.CString(mountpoint))), + ro: ro, + }) + } + return stats, nil +} diff --git a/collector/filesystem_netbsd.go b/collector/filesystem_netbsd.go new file mode 100644 index 0000000000..c7395893a7 --- /dev/null +++ b/collector/filesystem_netbsd.go @@ -0,0 +1,132 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !nofilesystem +// +build !nofilesystem + +package collector + +import ( + "fmt" + "syscall" + "unsafe" + + "golang.org/x/sys/unix" +) + +const ( + defMountPointsExcluded = "^/(dev)($|/)" + defFSTypesExcluded = "^(kernfs|procfs|ptyfs|fdesc)$" + _VFS_NAMELEN = 32 + _VFS_MNAMELEN = 1024 +) + +/* + * Go uses the NetBSD 9 ABI and thus syscall.SYS_GETVFSSTAT is compat_90_getvfsstat. + * We have to declare struct statvfs90 because it is not included in the unix package. + * See NetBSD/src/sys/compat/sys/statvfs.h. + */ +type statvfs90 struct { + F_flag uint + F_bsize uint + F_frsize uint + F_iosize uint + + F_blocks uint64 + F_bfree uint64 + F_bavail uint64 + F_bresvd uint64 + + F_files uint64 + F_ffree uint64 + F_favail uint64 + F_fresvd uint64 + + F_syncreads uint64 + F_syncwrites uint64 + + F_asyncreads uint64 + F_asyncwrites uint64 + + F_fsidx [2]uint32 + F_fsid uint32 + F_namemax uint + F_owner uint32 + F_spare [4]uint32 + + F_fstypename [_VFS_NAMELEN]byte + F_mntonname [_VFS_MNAMELEN]byte + F_mntfromname [_VFS_MNAMELEN]byte + + cgo_pad [4]byte +} + +func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) { + var mnt []statvfs90 + if syscall.SYS_GETVFSSTAT != 356 /* compat_90_getvfsstat */ { + /* + * Catch if golang ever updates to newer ABI and bail. + */ + return nil, fmt.Errorf("getvfsstat: ABI mismatch") + } + for { + r1, _, errno := syscall.Syscall(syscall.SYS_GETVFSSTAT, uintptr(0), 0, unix.ST_NOWAIT) + if errno != 0 { + return nil, fmt.Errorf("getvfsstat: %s", string(errno)) + } + mnt = make([]statvfs90, r1, r1) + r2, _, errno := syscall.Syscall(syscall.SYS_GETVFSSTAT, uintptr(unsafe.Pointer(&mnt[0])), unsafe.Sizeof(mnt[0])*r1, unix.ST_NOWAIT /* ST_NOWAIT */) + if errno != 0 { + return nil, fmt.Errorf("getvfsstat: %s", string(errno)) + } + if r1 == r2 { + break + } + } + + stats = []filesystemStats{} + for _, v := range mnt { + mountpoint := unix.ByteSliceToString(v.F_mntonname[:]) + if c.mountPointFilter.ignored(mountpoint) { + c.logger.Debug("msg", "Ignoring mount point", "mountpoint", mountpoint) + continue + } + + device := unix.ByteSliceToString(v.F_mntfromname[:]) + fstype := unix.ByteSliceToString(v.F_fstypename[:]) + if c.fsTypeFilter.ignored(fstype) { + c.logger.Debug("msg", "Ignoring fs type", "type", fstype) + continue + } + + var ro float64 + if (v.F_flag & unix.MNT_RDONLY) != 0 { + ro = 1 + } + + stats = append(stats, filesystemStats{ + labels: filesystemLabels{ + device: device, + mountPoint: mountpoint, + fsType: fstype, + }, + size: float64(v.F_blocks) * float64(v.F_bsize), + free: float64(v.F_bfree) * float64(v.F_bsize), + avail: float64(v.F_bavail) * float64(v.F_bsize), + files: float64(v.F_files), + filesFree: float64(v.F_ffree), + ro: ro, + }) + } + return stats, nil +} diff --git a/collector/filesystem_openbsd.go b/collector/filesystem_openbsd.go index 1c1e479e1f..fa9f8eb871 100644 --- a/collector/filesystem_openbsd.go +++ b/collector/filesystem_openbsd.go @@ -17,7 +17,6 @@ package collector import ( - "github.com/go-kit/log/level" "golang.org/x/sys/unix" ) @@ -42,15 +41,15 @@ func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) { stats = []filesystemStats{} for _, v := range mnt { mountpoint := unix.ByteSliceToString(v.F_mntonname[:]) - if c.excludedMountPointsPattern.MatchString(mountpoint) { - level.Debug(c.logger).Log("msg", "Ignoring mount point", "mountpoint", mountpoint) + if c.mountPointFilter.ignored(mountpoint) { + c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint) continue } device := unix.ByteSliceToString(v.F_mntfromname[:]) fstype := unix.ByteSliceToString(v.F_fstypename[:]) - if c.excludedFSTypesPattern.MatchString(fstype) { - level.Debug(c.logger).Log("msg", "Ignoring fs type", "type", fstype) + if c.fsTypeFilter.ignored(fstype) { + c.logger.Debug("Ignoring fs type", "type", fstype) continue } diff --git a/collector/fixtures/e2e-64k-page-output.txt b/collector/fixtures/e2e-64k-page-output.txt index 99c58abaf7..030fa88e8a 100644 --- a/collector/fixtures/e2e-64k-page-output.txt +++ b/collector/fixtures/e2e-64k-page-output.txt @@ -1,55 +1,59 @@ -# HELP go_gc_duration_seconds A summary of the pause duration of garbage collection cycles. +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. # TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge # HELP go_goroutines Number of goroutines that currently exist. # TYPE go_goroutines gauge # HELP go_info Information about the Go environment. # TYPE go_info gauge -# HELP go_memstats_alloc_bytes Number of bytes allocated and still in use. +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. # TYPE go_memstats_alloc_bytes gauge -# HELP go_memstats_alloc_bytes_total Total number of bytes allocated, even if freed. +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. # TYPE go_memstats_alloc_bytes_total counter -# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. # TYPE go_memstats_buck_hash_sys_bytes gauge -# HELP go_memstats_frees_total Total number of frees. +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. # TYPE go_memstats_frees_total counter -# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. # TYPE go_memstats_gc_sys_bytes gauge -# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and still in use. +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. # TYPE go_memstats_heap_alloc_bytes gauge -# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. # TYPE go_memstats_heap_idle_bytes gauge -# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes # TYPE go_memstats_heap_inuse_bytes gauge -# HELP go_memstats_heap_objects Number of allocated objects. +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. # TYPE go_memstats_heap_objects gauge -# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. # TYPE go_memstats_heap_released_bytes gauge -# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. # TYPE go_memstats_heap_sys_bytes gauge # HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. # TYPE go_memstats_last_gc_time_seconds gauge -# HELP go_memstats_lookups_total Total number of pointer lookups. -# TYPE go_memstats_lookups_total counter -# HELP go_memstats_mallocs_total Total number of mallocs. +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. # TYPE go_memstats_mallocs_total counter -# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. # TYPE go_memstats_mcache_inuse_bytes gauge -# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. # TYPE go_memstats_mcache_sys_bytes gauge -# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. # TYPE go_memstats_mspan_inuse_bytes gauge -# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. # TYPE go_memstats_mspan_sys_bytes gauge -# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. # TYPE go_memstats_next_gc_bytes gauge -# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. # TYPE go_memstats_other_sys_bytes gauge -# HELP go_memstats_stack_inuse_bytes Number of bytes in use by the stack allocator. +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. # TYPE go_memstats_stack_inuse_bytes gauge -# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. # TYPE go_memstats_stack_sys_bytes gauge -# HELP go_memstats_sys_bytes Number of bytes obtained from system. +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. # TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge # HELP go_threads Number of OS threads created. # TYPE go_threads gauge # HELP node_arp_entries ARP entries by device @@ -161,6 +165,14 @@ node_btrfs_allocation_ratio{block_group_type="metadata",mode="raid1",uuid="0abb2 node_btrfs_allocation_ratio{block_group_type="metadata",mode="raid6",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 2 node_btrfs_allocation_ratio{block_group_type="system",mode="raid1",uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 2 node_btrfs_allocation_ratio{block_group_type="system",mode="raid6",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 2 +# HELP node_btrfs_commit_seconds_total Sum of the duration of all commits, in seconds. +# TYPE node_btrfs_commit_seconds_total counter +node_btrfs_commit_seconds_total{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 47836.09 +node_btrfs_commit_seconds_total{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 +# HELP node_btrfs_commits_total The total number of commits that have occurred. +# TYPE node_btrfs_commits_total counter +node_btrfs_commits_total{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 258051 +node_btrfs_commits_total{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 # HELP node_btrfs_device_size_bytes Size of a device that is part of the filesystem. # TYPE node_btrfs_device_size_bytes gauge node_btrfs_device_size_bytes{device="loop22",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 1.073741824e+10 @@ -177,6 +189,14 @@ node_btrfs_global_rsv_size_bytes{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 1. # TYPE node_btrfs_info gauge node_btrfs_info{label="",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 1 node_btrfs_info{label="fixture",uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 1 +# HELP node_btrfs_last_commit_seconds Duration of the most recent commit, in seconds. +# TYPE node_btrfs_last_commit_seconds gauge +node_btrfs_last_commit_seconds{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 1 +node_btrfs_last_commit_seconds{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 +# HELP node_btrfs_max_commit_seconds Duration of the slowest commit, in seconds. +# TYPE node_btrfs_max_commit_seconds gauge +node_btrfs_max_commit_seconds{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 51.462 +node_btrfs_max_commit_seconds{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 # HELP node_btrfs_reserved_bytes Amount of space reserved for a data type # TYPE node_btrfs_reserved_bytes gauge node_btrfs_reserved_bytes{block_group_type="data",uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 0 @@ -468,21 +488,21 @@ node_disk_flush_requests_time_seconds_total{device="sdc"} 1.944 node_disk_flush_requests_total{device="sdc"} 1555 # HELP node_disk_info Info of /sys/block/. # TYPE node_disk_info gauge -node_disk_info{device="dm-0",major="252",minor="0",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-1",major="252",minor="1",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-2",major="252",minor="2",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-3",major="252",minor="3",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-4",major="252",minor="4",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-5",major="252",minor="5",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0",major="179",minor="0",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0p1",major="179",minor="1",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0p2",major="179",minor="2",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="nvme0n1",major="259",minor="0",model="SAMSUNG EHFTF55LURSY-000Y9",path="pci-0000:02:00.0-nvme-1",revision="4NBTUY95",serial="S252B6CU1HG3M1",wwn="eui.p3vbbiejx5aae2r3"} 1 -node_disk_info{device="sda",major="8",minor="0",model="TOSHIBA_KSDB4U86",path="pci-0000:3b:00.0-sas-phy7-lun-0",revision="0102",serial="2160A0D5FVGG",wwn="0x7c72382b8de36a64"} 1 -node_disk_info{device="sdb",major="8",minor="16",model="SuperMicro_SSD",path="pci-0000:00:1f.2-ata-1",revision="0R",serial="SMC0E1B87ABBB16BD84E",wwn="0xe1b87abbb16bd84e"} 1 -node_disk_info{device="sdc",major="8",minor="32",model="INTEL_SSDS9X9SI0",path="pci-0000:00:1f.2-ata-4",revision="0100",serial="3EWB5Y25CWQWA7EH1U",wwn="0x58907ddc573a5de"} 1 -node_disk_info{device="sr0",major="11",minor="0",model="Virtual_CDROM0",path="pci-0000:00:14.0-usb-0:1.1:1.0-scsi-0:0:0:0",revision="1.00",serial="AAAABBBBCCCC1",wwn=""} 1 -node_disk_info{device="vda",major="254",minor="0",model="",path="pci-0000:00:06.0",revision="",serial="",wwn=""} 1 +node_disk_info{device="dm-0",major="252",minor="0",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-1",major="252",minor="1",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-2",major="252",minor="2",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-3",major="252",minor="3",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-4",major="252",minor="4",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-5",major="252",minor="5",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0",major="179",minor="0",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0p1",major="179",minor="1",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0p2",major="179",minor="2",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="nvme0n1",major="259",minor="0",model="SAMSUNG EHFTF55LURSY-000Y9",path="pci-0000:02:00.0-nvme-1",revision="4NBTUY95",rotational="0",serial="S252B6CU1HG3M1",wwn="eui.p3vbbiejx5aae2r3"} 1 +node_disk_info{device="sda",major="8",minor="0",model="TOSHIBA_KSDB4U86",path="pci-0000:3b:00.0-sas-phy7-lun-0",revision="0102",rotational="1",serial="2160A0D5FVGG",wwn="0x7c72382b8de36a64"} 1 +node_disk_info{device="sdb",major="8",minor="16",model="SuperMicro_SSD",path="pci-0000:00:1f.2-ata-1",revision="0R",rotational="0",serial="SMC0E1B87ABBB16BD84E",wwn="0xe1b87abbb16bd84e"} 1 +node_disk_info{device="sdc",major="8",minor="32",model="INTEL_SSDS9X9SI0",path="pci-0000:00:1f.2-ata-4",revision="0100",rotational="0",serial="3EWB5Y25CWQWA7EH1U",wwn="0x58907ddc573a5de"} 1 +node_disk_info{device="sr0",major="11",minor="0",model="Virtual_CDROM0",path="pci-0000:00:14.0-usb-0:1.1:1.0-scsi-0:0:0:0",revision="1.00",rotational="0",serial="AAAABBBBCCCC1",wwn=""} 1 +node_disk_info{device="vda",major="254",minor="0",model="",path="pci-0000:00:06.0",revision="",rotational="0",serial="",wwn=""} 1 # HELP node_disk_io_now The number of I/Os currently in progress. # TYPE node_disk_io_now gauge node_disk_io_now{device="dm-0"} 0 @@ -851,6 +871,10 @@ node_hwmon_fan_target_rpm{chip="nct6779",sensor="fan2"} 27000 # HELP node_hwmon_fan_tolerance Hardware monitor fan element tolerance # TYPE node_hwmon_fan_tolerance gauge node_hwmon_fan_tolerance{chip="nct6779",sensor="fan2"} 0 +# HELP node_hwmon_freq_freq_mhz Hardware monitor for GPU frequency in MHz +# TYPE node_hwmon_freq_freq_mhz gauge +node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="mclk"} 300 +node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="sclk"} 214 # HELP node_hwmon_in_alarm Hardware sensor alarm status (in) # TYPE node_hwmon_in_alarm gauge node_hwmon_in_alarm{chip="nct6779",sensor="in0"} 0 @@ -964,8 +988,10 @@ node_hwmon_pwm_weight_temp_step_tol{chip="nct6779",sensor="pwm1"} 0 # TYPE node_hwmon_sensor_label gauge node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp1"} 1 node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp2"} 1 -node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side ",sensor="fan1"} 1 -node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side ",sensor="fan2"} 1 +node_hwmon_sensor_label{chip="hwmon4",label="mclk",sensor="freq2"} 1 +node_hwmon_sensor_label{chip="hwmon4",label="sclk",sensor="freq1"} 1 +node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side",sensor="fan1"} 1 +node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side",sensor="fan2"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 0",sensor="temp2"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 1",sensor="temp3"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 2",sensor="temp4"} 1 @@ -2322,6 +2348,9 @@ node_netstat_TcpExt_SyncookiesSent 0 # HELP node_netstat_TcpExt_TCPOFOQueue Statistic TcpExtTCPOFOQueue. # TYPE node_netstat_TcpExt_TCPOFOQueue untyped node_netstat_TcpExt_TCPOFOQueue 42 +# HELP node_netstat_TcpExt_TCPRcvQDrop Statistic TcpExtTCPRcvQDrop. +# TYPE node_netstat_TcpExt_TCPRcvQDrop untyped +node_netstat_TcpExt_TCPRcvQDrop 131 # HELP node_netstat_TcpExt_TCPTimeouts Statistic TcpExtTCPTimeouts. # TYPE node_netstat_TcpExt_TCPTimeouts untyped node_netstat_TcpExt_TCPTimeouts 115 @@ -2830,6 +2859,9 @@ node_pressure_io_stalled_seconds_total 159.229614 # HELP node_pressure_io_waiting_seconds_total Total time in seconds that processes have waited due to IO congestion # TYPE node_pressure_io_waiting_seconds_total counter node_pressure_io_waiting_seconds_total 159.886802 +# HELP node_pressure_irq_stalled_seconds_total Total time in seconds no process could make progress due to IRQ congestion +# TYPE node_pressure_irq_stalled_seconds_total counter +node_pressure_irq_stalled_seconds_total 0.008494 # HELP node_pressure_memory_stalled_seconds_total Total time in seconds no process could make progress due to memory congestion # TYPE node_pressure_memory_stalled_seconds_total counter node_pressure_memory_stalled_seconds_total 0 @@ -3757,6 +3789,9 @@ node_zfs_arc_l2_writes_lock_retry 0 # HELP node_zfs_arc_l2_writes_sent kstat.zfs.misc.arcstats.l2_writes_sent # TYPE node_zfs_arc_l2_writes_sent untyped node_zfs_arc_l2_writes_sent 0 +# HELP node_zfs_arc_memory_available_bytes kstat.zfs.misc.arcstats.memory_available_bytes +# TYPE node_zfs_arc_memory_available_bytes untyped +node_zfs_arc_memory_available_bytes -9.223372036854776e+17 # HELP node_zfs_arc_memory_direct_count kstat.zfs.misc.arcstats.memory_direct_count # TYPE node_zfs_arc_memory_direct_count untyped node_zfs_arc_memory_direct_count 542 @@ -4286,108 +4321,139 @@ node_zfs_zil_zil_itx_needcopy_count 0 # TYPE node_zfs_zpool_dataset_nread untyped node_zfs_zpool_dataset_nread{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nread{dataset="pool1/dataset1",zpool="pool1"} 28 +node_zfs_zpool_dataset_nread{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nread{dataset="pool3/dataset with space",zpool="pool3"} 28 node_zfs_zpool_dataset_nread{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nread{dataset="poolz1/dataset1",zpool="poolz1"} 28 # HELP node_zfs_zpool_dataset_nunlinked kstat.zfs.misc.objset.nunlinked # TYPE node_zfs_zpool_dataset_nunlinked untyped node_zfs_zpool_dataset_nunlinked{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nunlinked{dataset="pool1/dataset1",zpool="pool1"} 3 +node_zfs_zpool_dataset_nunlinked{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nunlinked{dataset="pool3/dataset with space",zpool="pool3"} 3 node_zfs_zpool_dataset_nunlinked{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nunlinked{dataset="poolz1/dataset1",zpool="poolz1"} 14 # HELP node_zfs_zpool_dataset_nunlinks kstat.zfs.misc.objset.nunlinks # TYPE node_zfs_zpool_dataset_nunlinks untyped node_zfs_zpool_dataset_nunlinks{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nunlinks{dataset="pool1/dataset1",zpool="pool1"} 3 +node_zfs_zpool_dataset_nunlinks{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nunlinks{dataset="pool3/dataset with space",zpool="pool3"} 3 node_zfs_zpool_dataset_nunlinks{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nunlinks{dataset="poolz1/dataset1",zpool="poolz1"} 14 # HELP node_zfs_zpool_dataset_nwritten kstat.zfs.misc.objset.nwritten # TYPE node_zfs_zpool_dataset_nwritten untyped node_zfs_zpool_dataset_nwritten{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nwritten{dataset="pool1/dataset1",zpool="pool1"} 12302 +node_zfs_zpool_dataset_nwritten{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nwritten{dataset="pool3/dataset with space",zpool="pool3"} 12302 node_zfs_zpool_dataset_nwritten{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nwritten{dataset="poolz1/dataset1",zpool="poolz1"} 32806 # HELP node_zfs_zpool_dataset_reads kstat.zfs.misc.objset.reads # TYPE node_zfs_zpool_dataset_reads untyped node_zfs_zpool_dataset_reads{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_reads{dataset="pool1/dataset1",zpool="pool1"} 2 +node_zfs_zpool_dataset_reads{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_reads{dataset="pool3/dataset with space",zpool="pool3"} 2 node_zfs_zpool_dataset_reads{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_reads{dataset="poolz1/dataset1",zpool="poolz1"} 2 # HELP node_zfs_zpool_dataset_writes kstat.zfs.misc.objset.writes # TYPE node_zfs_zpool_dataset_writes untyped node_zfs_zpool_dataset_writes{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_writes{dataset="pool1/dataset1",zpool="pool1"} 4 +node_zfs_zpool_dataset_writes{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_writes{dataset="pool3/dataset with space",zpool="pool3"} 4 node_zfs_zpool_dataset_writes{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_writes{dataset="poolz1/dataset1",zpool="poolz1"} 10 # HELP node_zfs_zpool_nread kstat.zfs.misc.io.nread # TYPE node_zfs_zpool_nread untyped node_zfs_zpool_nread{zpool="pool1"} 1.88416e+06 +node_zfs_zpool_nread{zpool="pool3"} 1.88416e+06 node_zfs_zpool_nread{zpool="poolz1"} 2.82624e+06 # HELP node_zfs_zpool_nwritten kstat.zfs.misc.io.nwritten # TYPE node_zfs_zpool_nwritten untyped node_zfs_zpool_nwritten{zpool="pool1"} 3.206144e+06 +node_zfs_zpool_nwritten{zpool="pool3"} 3.206144e+06 node_zfs_zpool_nwritten{zpool="poolz1"} 2.680501248e+09 # HELP node_zfs_zpool_rcnt kstat.zfs.misc.io.rcnt # TYPE node_zfs_zpool_rcnt untyped node_zfs_zpool_rcnt{zpool="pool1"} 0 +node_zfs_zpool_rcnt{zpool="pool3"} 0 node_zfs_zpool_rcnt{zpool="poolz1"} 0 # HELP node_zfs_zpool_reads kstat.zfs.misc.io.reads # TYPE node_zfs_zpool_reads untyped node_zfs_zpool_reads{zpool="pool1"} 22 +node_zfs_zpool_reads{zpool="pool3"} 22 node_zfs_zpool_reads{zpool="poolz1"} 33 # HELP node_zfs_zpool_rlentime kstat.zfs.misc.io.rlentime # TYPE node_zfs_zpool_rlentime untyped node_zfs_zpool_rlentime{zpool="pool1"} 1.04112268e+08 +node_zfs_zpool_rlentime{zpool="pool3"} 1.04112268e+08 node_zfs_zpool_rlentime{zpool="poolz1"} 6.472105124093e+12 # HELP node_zfs_zpool_rtime kstat.zfs.misc.io.rtime # TYPE node_zfs_zpool_rtime untyped node_zfs_zpool_rtime{zpool="pool1"} 2.4168078e+07 +node_zfs_zpool_rtime{zpool="pool3"} 2.4168078e+07 node_zfs_zpool_rtime{zpool="poolz1"} 9.82909164e+09 # HELP node_zfs_zpool_rupdate kstat.zfs.misc.io.rupdate # TYPE node_zfs_zpool_rupdate untyped node_zfs_zpool_rupdate{zpool="pool1"} 7.921048984922e+13 +node_zfs_zpool_rupdate{zpool="pool3"} 7.921048984922e+13 node_zfs_zpool_rupdate{zpool="poolz1"} 1.10734831944501e+14 # HELP node_zfs_zpool_state kstat.zfs.misc.state # TYPE node_zfs_zpool_state gauge node_zfs_zpool_state{state="degraded",zpool="pool1"} 0 node_zfs_zpool_state{state="degraded",zpool="pool2"} 0 +node_zfs_zpool_state{state="degraded",zpool="pool3"} 0 node_zfs_zpool_state{state="degraded",zpool="poolz1"} 1 node_zfs_zpool_state{state="faulted",zpool="pool1"} 0 node_zfs_zpool_state{state="faulted",zpool="pool2"} 0 +node_zfs_zpool_state{state="faulted",zpool="pool3"} 0 node_zfs_zpool_state{state="faulted",zpool="poolz1"} 0 node_zfs_zpool_state{state="offline",zpool="pool1"} 0 node_zfs_zpool_state{state="offline",zpool="pool2"} 0 +node_zfs_zpool_state{state="offline",zpool="pool3"} 0 node_zfs_zpool_state{state="offline",zpool="poolz1"} 0 node_zfs_zpool_state{state="online",zpool="pool1"} 1 node_zfs_zpool_state{state="online",zpool="pool2"} 0 +node_zfs_zpool_state{state="online",zpool="pool3"} 1 node_zfs_zpool_state{state="online",zpool="poolz1"} 0 node_zfs_zpool_state{state="removed",zpool="pool1"} 0 node_zfs_zpool_state{state="removed",zpool="pool2"} 0 +node_zfs_zpool_state{state="removed",zpool="pool3"} 0 node_zfs_zpool_state{state="removed",zpool="poolz1"} 0 node_zfs_zpool_state{state="suspended",zpool="pool1"} 0 node_zfs_zpool_state{state="suspended",zpool="pool2"} 1 +node_zfs_zpool_state{state="suspended",zpool="pool3"} 0 node_zfs_zpool_state{state="suspended",zpool="poolz1"} 0 node_zfs_zpool_state{state="unavail",zpool="pool1"} 0 node_zfs_zpool_state{state="unavail",zpool="pool2"} 0 +node_zfs_zpool_state{state="unavail",zpool="pool3"} 0 node_zfs_zpool_state{state="unavail",zpool="poolz1"} 0 # HELP node_zfs_zpool_wcnt kstat.zfs.misc.io.wcnt # TYPE node_zfs_zpool_wcnt untyped node_zfs_zpool_wcnt{zpool="pool1"} 0 +node_zfs_zpool_wcnt{zpool="pool3"} 0 node_zfs_zpool_wcnt{zpool="poolz1"} 0 # HELP node_zfs_zpool_wlentime kstat.zfs.misc.io.wlentime # TYPE node_zfs_zpool_wlentime untyped node_zfs_zpool_wlentime{zpool="pool1"} 1.04112268e+08 +node_zfs_zpool_wlentime{zpool="pool3"} 1.04112268e+08 node_zfs_zpool_wlentime{zpool="poolz1"} 6.472105124093e+12 # HELP node_zfs_zpool_writes kstat.zfs.misc.io.writes # TYPE node_zfs_zpool_writes untyped node_zfs_zpool_writes{zpool="pool1"} 132 +node_zfs_zpool_writes{zpool="pool3"} 132 node_zfs_zpool_writes{zpool="poolz1"} 25294 # HELP node_zfs_zpool_wtime kstat.zfs.misc.io.wtime # TYPE node_zfs_zpool_wtime untyped node_zfs_zpool_wtime{zpool="pool1"} 7.155162e+06 +node_zfs_zpool_wtime{zpool="pool3"} 7.155162e+06 node_zfs_zpool_wtime{zpool="poolz1"} 9.673715628e+09 # HELP node_zfs_zpool_wupdate kstat.zfs.misc.io.wupdate # TYPE node_zfs_zpool_wupdate untyped node_zfs_zpool_wupdate{zpool="pool1"} 7.9210489694949e+13 +node_zfs_zpool_wupdate{zpool="pool3"} 7.9210489694949e+13 node_zfs_zpool_wupdate{zpool="poolz1"} 1.10734831833266e+14 # HELP node_zoneinfo_high_pages Zone watermark pages_high # TYPE node_zoneinfo_high_pages gauge @@ -4564,6 +4630,10 @@ node_zoneinfo_spanned_pages{node="0",zone="Normal"} 7.806976e+06 # TYPE process_cpu_seconds_total counter # HELP process_max_fds Maximum number of open file descriptors. # TYPE process_max_fds gauge +# HELP process_network_receive_bytes_total Number of bytes received by the process over the network. +# TYPE process_network_receive_bytes_total counter +# HELP process_network_transmit_bytes_total Number of bytes sent by the process over the network. +# TYPE process_network_transmit_bytes_total counter # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge # HELP process_resident_memory_bytes Resident memory size in bytes. diff --git a/collector/fixtures/e2e-output-darwin.txt b/collector/fixtures/e2e-output-darwin.txt new file mode 100644 index 0000000000..77eb45cbb7 --- /dev/null +++ b/collector/fixtures/e2e-output-darwin.txt @@ -0,0 +1,277 @@ +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. +# TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge +# HELP go_goroutines Number of goroutines that currently exist. +# TYPE go_goroutines gauge +# HELP go_info Information about the Go environment. +# TYPE go_info gauge +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_alloc_bytes gauge +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. +# TYPE go_memstats_alloc_bytes_total counter +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. +# TYPE go_memstats_buck_hash_sys_bytes gauge +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_frees_total counter +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. +# TYPE go_memstats_gc_sys_bytes gauge +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_heap_alloc_bytes gauge +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_idle_bytes gauge +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes +# TYPE go_memstats_heap_inuse_bytes gauge +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. +# TYPE go_memstats_heap_objects gauge +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. +# TYPE go_memstats_heap_released_bytes gauge +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_sys_bytes gauge +# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. +# TYPE go_memstats_last_gc_time_seconds gauge +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_mallocs_total counter +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. +# TYPE go_memstats_mcache_inuse_bytes gauge +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. +# TYPE go_memstats_mcache_sys_bytes gauge +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. +# TYPE go_memstats_mspan_inuse_bytes gauge +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. +# TYPE go_memstats_mspan_sys_bytes gauge +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. +# TYPE go_memstats_next_gc_bytes gauge +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. +# TYPE go_memstats_other_sys_bytes gauge +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. +# TYPE go_memstats_stack_inuse_bytes gauge +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. +# TYPE go_memstats_stack_sys_bytes gauge +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. +# TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge +# HELP go_threads Number of OS threads created. +# TYPE go_threads gauge +# HELP node_buddyinfo_blocks Count of free blocks according to size. +# TYPE node_buddyinfo_blocks gauge +node_buddyinfo_blocks{node="0",size="0",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="0",zone="DMA32"} 759 +node_buddyinfo_blocks{node="0",size="0",zone="Normal"} 4381 +node_buddyinfo_blocks{node="0",size="1",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="1",zone="DMA32"} 572 +node_buddyinfo_blocks{node="0",size="1",zone="Normal"} 1093 +node_buddyinfo_blocks{node="0",size="10",zone="DMA"} 3 +node_buddyinfo_blocks{node="0",size="10",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="10",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="2",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="2",zone="DMA32"} 791 +node_buddyinfo_blocks{node="0",size="2",zone="Normal"} 185 +node_buddyinfo_blocks{node="0",size="3",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="3",zone="DMA32"} 475 +node_buddyinfo_blocks{node="0",size="3",zone="Normal"} 1530 +node_buddyinfo_blocks{node="0",size="4",zone="DMA"} 2 +node_buddyinfo_blocks{node="0",size="4",zone="DMA32"} 194 +node_buddyinfo_blocks{node="0",size="4",zone="Normal"} 567 +node_buddyinfo_blocks{node="0",size="5",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="5",zone="DMA32"} 45 +node_buddyinfo_blocks{node="0",size="5",zone="Normal"} 102 +node_buddyinfo_blocks{node="0",size="6",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="6",zone="DMA32"} 12 +node_buddyinfo_blocks{node="0",size="6",zone="Normal"} 4 +node_buddyinfo_blocks{node="0",size="7",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="8",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="9",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="Normal"} 0 +# HELP node_disk_read_errors_total The total number of read errors. +# TYPE node_disk_read_errors_total counter +node_disk_read_errors_total{device="disk0"} 0 +# HELP node_disk_read_retries_total The total number of read retries. +# TYPE node_disk_read_retries_total counter +node_disk_read_retries_total{device="disk0"} 0 +# HELP node_disk_write_errors_total The total number of write errors. +# TYPE node_disk_write_errors_total counter +node_disk_write_errors_total{device="disk0"} 0 +# HELP node_disk_write_retries_total The total number of write retries. +# TYPE node_disk_write_retries_total counter +node_disk_write_retries_total{device="disk0"} 0 +# HELP node_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which node_exporter was built, and the goos and goarch for the build. +# TYPE node_exporter_build_info gauge +# HELP node_memory_swap_total_bytes Memory information field swap_total_bytes. +# TYPE node_memory_swap_total_bytes gauge +node_memory_swap_total_bytes 0 +# HELP node_memory_swap_used_bytes Memory information field swap_used_bytes. +# TYPE node_memory_swap_used_bytes gauge +node_memory_swap_used_bytes 0 +# HELP node_memory_total_bytes Memory information field total_bytes. +# TYPE node_memory_total_bytes gauge +node_memory_total_bytes 7.516192768e+09 +# HELP node_network_noproto_total Network device statistic noproto. +# TYPE node_network_noproto_total counter +node_network_noproto_total{device="lo0"} 0 +# HELP node_network_receive_drop_total Network device statistic receive_drop. +# TYPE node_network_receive_drop_total counter +node_network_receive_drop_total{device="lo0"} 0 +# HELP node_network_receive_errs_total Network device statistic receive_errs. +# TYPE node_network_receive_errs_total counter +node_network_receive_errs_total{device="lo0"} 0 +# HELP node_network_receive_packets_total Network device statistic receive_packets. +# TYPE node_network_receive_packets_total counter +# HELP node_network_transmit_bytes_total Network device statistic transmit_bytes. +# TYPE node_network_transmit_bytes_total counter +# HELP node_network_transmit_colls_total Network device statistic transmit_colls. +# TYPE node_network_transmit_colls_total counter +node_network_transmit_colls_total{device="lo0"} 0 +# HELP node_network_transmit_errs_total Network device statistic transmit_errs. +# TYPE node_network_transmit_errs_total counter +node_network_transmit_errs_total{device="lo0"} 0 +# HELP node_network_transmit_packets_total Network device statistic transmit_packets. +# TYPE node_network_transmit_packets_total counter +# HELP node_os_info A metric with a constant '1' value labeled by build_id, id, id_like, image_id, image_version, name, pretty_name, variant, variant_id, version, version_codename, version_id. +# TYPE node_os_info gauge +node_os_info{build_id="",id="ubuntu",id_like="debian",image_id="",image_version="",name="Ubuntu",pretty_name="Ubuntu 20.04.2 LTS",variant="",variant_id="",version="20.04.2 LTS (Focal Fossa)",version_codename="focal",version_id="20.04"} 1 +# HELP node_os_version Metric containing the major.minor part of the OS version. +# TYPE node_os_version gauge +node_os_version{id="ubuntu",id_like="debian",name="Ubuntu"} 20.04 +# HELP node_scrape_collector_duration_seconds node_exporter: Duration of a collector scrape. +# TYPE node_scrape_collector_duration_seconds gauge +# HELP node_scrape_collector_success node_exporter: Whether a collector succeeded. +# TYPE node_scrape_collector_success gauge +node_scrape_collector_success{collector="boottime"} 1 +node_scrape_collector_success{collector="buddyinfo"} 1 +node_scrape_collector_success{collector="cpu"} 1 +node_scrape_collector_success{collector="diskstats"} 1 +node_scrape_collector_success{collector="loadavg"} 1 +node_scrape_collector_success{collector="meminfo"} 1 +node_scrape_collector_success{collector="netdev"} 1 +node_scrape_collector_success{collector="os"} 1 +node_scrape_collector_success{collector="powersupplyclass"} 1 +node_scrape_collector_success{collector="textfile"} 1 +node_scrape_collector_success{collector="thermal"} 0 +node_scrape_collector_success{collector="time"} 1 +node_scrape_collector_success{collector="xfrm"} 1 +# HELP node_textfile_mtime_seconds Unixtime mtime of textfiles successfully read. +# TYPE node_textfile_mtime_seconds gauge +# HELP node_textfile_scrape_error 1 if there was an error opening or reading a file, 0 otherwise +# TYPE node_textfile_scrape_error gauge +node_textfile_scrape_error 0 +# HELP node_time_seconds System time in seconds since epoch (1970). +# TYPE node_time_seconds gauge +# HELP node_time_zone_offset_seconds System time zone offset in seconds. +# TYPE node_time_zone_offset_seconds gauge +# HELP node_xfrm_acquire_error_packets_total State hasn’t been fully acquired before use +# TYPE node_xfrm_acquire_error_packets_total counter +node_xfrm_acquire_error_packets_total 24532 +# HELP node_xfrm_fwd_hdr_error_packets_total Forward routing of a packet is not allowed +# TYPE node_xfrm_fwd_hdr_error_packets_total counter +node_xfrm_fwd_hdr_error_packets_total 6654 +# HELP node_xfrm_in_buffer_error_packets_total No buffer is left +# TYPE node_xfrm_in_buffer_error_packets_total counter +node_xfrm_in_buffer_error_packets_total 2 +# HELP node_xfrm_in_error_packets_total All errors not matched by other +# TYPE node_xfrm_in_error_packets_total counter +node_xfrm_in_error_packets_total 1 +# HELP node_xfrm_in_hdr_error_packets_total Header error +# TYPE node_xfrm_in_hdr_error_packets_total counter +node_xfrm_in_hdr_error_packets_total 4 +# HELP node_xfrm_in_no_pols_packets_total No policy is found for states e.g. Inbound SAs are correct but no SP is found +# TYPE node_xfrm_in_no_pols_packets_total counter +node_xfrm_in_no_pols_packets_total 65432 +# HELP node_xfrm_in_no_states_packets_total No state is found i.e. Either inbound SPI, address, or IPsec protocol at SA is wrong +# TYPE node_xfrm_in_no_states_packets_total counter +node_xfrm_in_no_states_packets_total 3 +# HELP node_xfrm_in_pol_block_packets_total Policy discards +# TYPE node_xfrm_in_pol_block_packets_total counter +node_xfrm_in_pol_block_packets_total 100 +# HELP node_xfrm_in_pol_error_packets_total Policy error +# TYPE node_xfrm_in_pol_error_packets_total counter +node_xfrm_in_pol_error_packets_total 10000 +# HELP node_xfrm_in_state_expired_packets_total State is expired +# TYPE node_xfrm_in_state_expired_packets_total counter +node_xfrm_in_state_expired_packets_total 7 +# HELP node_xfrm_in_state_invalid_packets_total State is invalid +# TYPE node_xfrm_in_state_invalid_packets_total counter +node_xfrm_in_state_invalid_packets_total 55555 +# HELP node_xfrm_in_state_mismatch_packets_total State has mismatch option e.g. UDP encapsulation type is mismatch +# TYPE node_xfrm_in_state_mismatch_packets_total counter +node_xfrm_in_state_mismatch_packets_total 23451 +# HELP node_xfrm_in_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_in_state_mode_error_packets_total counter +node_xfrm_in_state_mode_error_packets_total 100 +# HELP node_xfrm_in_state_proto_error_packets_total Transformation protocol specific error e.g. SA key is wrong +# TYPE node_xfrm_in_state_proto_error_packets_total counter +node_xfrm_in_state_proto_error_packets_total 40 +# HELP node_xfrm_in_state_seq_error_packets_total Sequence error i.e. Sequence number is out of window +# TYPE node_xfrm_in_state_seq_error_packets_total counter +node_xfrm_in_state_seq_error_packets_total 6000 +# HELP node_xfrm_in_tmpl_mismatch_packets_total No matching template for states e.g. Inbound SAs are correct but SP rule is wrong +# TYPE node_xfrm_in_tmpl_mismatch_packets_total counter +node_xfrm_in_tmpl_mismatch_packets_total 51 +# HELP node_xfrm_out_bundle_check_error_packets_total Bundle check error +# TYPE node_xfrm_out_bundle_check_error_packets_total counter +node_xfrm_out_bundle_check_error_packets_total 555 +# HELP node_xfrm_out_bundle_gen_error_packets_total Bundle generation error +# TYPE node_xfrm_out_bundle_gen_error_packets_total counter +node_xfrm_out_bundle_gen_error_packets_total 43321 +# HELP node_xfrm_out_error_packets_total All errors which is not matched others +# TYPE node_xfrm_out_error_packets_total counter +node_xfrm_out_error_packets_total 1e+06 +# HELP node_xfrm_out_no_states_packets_total No state is found +# TYPE node_xfrm_out_no_states_packets_total counter +node_xfrm_out_no_states_packets_total 869 +# HELP node_xfrm_out_pol_block_packets_total Policy discards +# TYPE node_xfrm_out_pol_block_packets_total counter +node_xfrm_out_pol_block_packets_total 43456 +# HELP node_xfrm_out_pol_dead_packets_total Policy is dead +# TYPE node_xfrm_out_pol_dead_packets_total counter +node_xfrm_out_pol_dead_packets_total 7656 +# HELP node_xfrm_out_pol_error_packets_total Policy error +# TYPE node_xfrm_out_pol_error_packets_total counter +node_xfrm_out_pol_error_packets_total 1454 +# HELP node_xfrm_out_state_expired_packets_total State is expired +# TYPE node_xfrm_out_state_expired_packets_total counter +node_xfrm_out_state_expired_packets_total 565 +# HELP node_xfrm_out_state_invalid_packets_total State is invalid, perhaps expired +# TYPE node_xfrm_out_state_invalid_packets_total counter +node_xfrm_out_state_invalid_packets_total 28765 +# HELP node_xfrm_out_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_out_state_mode_error_packets_total counter +node_xfrm_out_state_mode_error_packets_total 8 +# HELP node_xfrm_out_state_proto_error_packets_total Transformation protocol specific error +# TYPE node_xfrm_out_state_proto_error_packets_total counter +node_xfrm_out_state_proto_error_packets_total 4542 +# HELP node_xfrm_out_state_seq_error_packets_total Sequence error i.e. Sequence number overflow +# TYPE node_xfrm_out_state_seq_error_packets_total counter +node_xfrm_out_state_seq_error_packets_total 543 +# HELP promhttp_metric_handler_errors_total Total number of internal errors encountered by the promhttp metric handler. +# TYPE promhttp_metric_handler_errors_total counter +promhttp_metric_handler_errors_total{cause="encoding"} 0 +promhttp_metric_handler_errors_total{cause="gathering"} 0 +# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served. +# TYPE promhttp_metric_handler_requests_in_flight gauge +promhttp_metric_handler_requests_in_flight 1 +# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code. +# TYPE promhttp_metric_handler_requests_total counter +promhttp_metric_handler_requests_total{code="200"} 0 +promhttp_metric_handler_requests_total{code="500"} 0 +promhttp_metric_handler_requests_total{code="503"} 0 +# HELP testmetric1_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_1 untyped +testmetric1_1{foo="bar"} 10 +# HELP testmetric1_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_2 untyped +testmetric1_2{foo="baz"} 20 +# HELP testmetric2_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_1 untyped +testmetric2_1{foo="bar"} 30 +# HELP testmetric2_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_2 untyped +testmetric2_2{foo="baz"} 40 diff --git a/collector/fixtures/e2e-output-dragonfly.txt b/collector/fixtures/e2e-output-dragonfly.txt new file mode 100644 index 0000000000..b6a828ad0e --- /dev/null +++ b/collector/fixtures/e2e-output-dragonfly.txt @@ -0,0 +1,251 @@ +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. +# TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge +# HELP go_goroutines Number of goroutines that currently exist. +# TYPE go_goroutines gauge +# HELP go_info Information about the Go environment. +# TYPE go_info gauge +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_alloc_bytes gauge +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. +# TYPE go_memstats_alloc_bytes_total counter +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. +# TYPE go_memstats_buck_hash_sys_bytes gauge +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_frees_total counter +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. +# TYPE go_memstats_gc_sys_bytes gauge +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_heap_alloc_bytes gauge +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_idle_bytes gauge +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes +# TYPE go_memstats_heap_inuse_bytes gauge +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. +# TYPE go_memstats_heap_objects gauge +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. +# TYPE go_memstats_heap_released_bytes gauge +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_sys_bytes gauge +# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. +# TYPE go_memstats_last_gc_time_seconds gauge +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_mallocs_total counter +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. +# TYPE go_memstats_mcache_inuse_bytes gauge +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. +# TYPE go_memstats_mcache_sys_bytes gauge +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. +# TYPE go_memstats_mspan_inuse_bytes gauge +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. +# TYPE go_memstats_mspan_sys_bytes gauge +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. +# TYPE go_memstats_next_gc_bytes gauge +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. +# TYPE go_memstats_other_sys_bytes gauge +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. +# TYPE go_memstats_stack_inuse_bytes gauge +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. +# TYPE go_memstats_stack_sys_bytes gauge +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. +# TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge +# HELP go_threads Number of OS threads created. +# TYPE go_threads gauge +# HELP node_buddyinfo_blocks Count of free blocks according to size. +# TYPE node_buddyinfo_blocks gauge +node_buddyinfo_blocks{node="0",size="0",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="0",zone="DMA32"} 759 +node_buddyinfo_blocks{node="0",size="0",zone="Normal"} 4381 +node_buddyinfo_blocks{node="0",size="1",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="1",zone="DMA32"} 572 +node_buddyinfo_blocks{node="0",size="1",zone="Normal"} 1093 +node_buddyinfo_blocks{node="0",size="10",zone="DMA"} 3 +node_buddyinfo_blocks{node="0",size="10",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="10",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="2",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="2",zone="DMA32"} 791 +node_buddyinfo_blocks{node="0",size="2",zone="Normal"} 185 +node_buddyinfo_blocks{node="0",size="3",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="3",zone="DMA32"} 475 +node_buddyinfo_blocks{node="0",size="3",zone="Normal"} 1530 +node_buddyinfo_blocks{node="0",size="4",zone="DMA"} 2 +node_buddyinfo_blocks{node="0",size="4",zone="DMA32"} 194 +node_buddyinfo_blocks{node="0",size="4",zone="Normal"} 567 +node_buddyinfo_blocks{node="0",size="5",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="5",zone="DMA32"} 45 +node_buddyinfo_blocks{node="0",size="5",zone="Normal"} 102 +node_buddyinfo_blocks{node="0",size="6",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="6",zone="DMA32"} 12 +node_buddyinfo_blocks{node="0",size="6",zone="Normal"} 4 +node_buddyinfo_blocks{node="0",size="7",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="8",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="9",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="Normal"} 0 +# HELP node_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which node_exporter was built, and the goos and goarch for the build. +# TYPE node_exporter_build_info gauge +# HELP node_network_receive_drop_total Network device statistic receive_drop. +# TYPE node_network_receive_drop_total counter +node_network_receive_drop_total{device="lo0"} 0 +# HELP node_network_receive_errs_total Network device statistic receive_errs. +# TYPE node_network_receive_errs_total counter +node_network_receive_errs_total{device="lo0"} 0 +# HELP node_network_receive_packets_total Network device statistic receive_packets. +# TYPE node_network_receive_packets_total counter +# HELP node_network_transmit_bytes_total Network device statistic transmit_bytes. +# TYPE node_network_transmit_bytes_total counter +# HELP node_network_transmit_drop_total Network device statistic transmit_drop. +# TYPE node_network_transmit_drop_total counter +node_network_transmit_drop_total{device="lo0"} 0 +# HELP node_network_transmit_errs_total Network device statistic transmit_errs. +# TYPE node_network_transmit_errs_total counter +node_network_transmit_errs_total{device="lo0"} 0 +# HELP node_network_transmit_packets_total Network device statistic transmit_packets. +# TYPE node_network_transmit_packets_total counter +# HELP node_os_info A metric with a constant '1' value labeled by build_id, id, id_like, image_id, image_version, name, pretty_name, variant, variant_id, version, version_codename, version_id. +# TYPE node_os_info gauge +node_os_info{build_id="",id="ubuntu",id_like="debian",image_id="",image_version="",name="Ubuntu",pretty_name="Ubuntu 20.04.2 LTS",variant="",variant_id="",version="20.04.2 LTS (Focal Fossa)",version_codename="focal",version_id="20.04"} 1 +# HELP node_os_version Metric containing the major.minor part of the OS version. +# TYPE node_os_version gauge +node_os_version{id="ubuntu",id_like="debian",name="Ubuntu"} 20.04 +# HELP node_scrape_collector_duration_seconds node_exporter: Duration of a collector scrape. +# TYPE node_scrape_collector_duration_seconds gauge +# HELP node_scrape_collector_success node_exporter: Whether a collector succeeded. +# TYPE node_scrape_collector_success gauge +node_scrape_collector_success{collector="boottime"} 1 +node_scrape_collector_success{collector="buddyinfo"} 1 +node_scrape_collector_success{collector="cpu"} 1 +node_scrape_collector_success{collector="exec"} 1 +node_scrape_collector_success{collector="loadavg"} 1 +node_scrape_collector_success{collector="meminfo"} 0 +node_scrape_collector_success{collector="netdev"} 1 +node_scrape_collector_success{collector="os"} 1 +node_scrape_collector_success{collector="textfile"} 1 +node_scrape_collector_success{collector="time"} 1 +node_scrape_collector_success{collector="xfrm"} 1 +# HELP node_textfile_mtime_seconds Unixtime mtime of textfiles successfully read. +# TYPE node_textfile_mtime_seconds gauge +# HELP node_textfile_scrape_error 1 if there was an error opening or reading a file, 0 otherwise +# TYPE node_textfile_scrape_error gauge +node_textfile_scrape_error 0 +# HELP node_time_seconds System time in seconds since epoch (1970). +# TYPE node_time_seconds gauge +# HELP node_time_zone_offset_seconds System time zone offset in seconds. +# TYPE node_time_zone_offset_seconds gauge +# HELP node_xfrm_acquire_error_packets_total State hasn’t been fully acquired before use +# TYPE node_xfrm_acquire_error_packets_total counter +node_xfrm_acquire_error_packets_total 24532 +# HELP node_xfrm_fwd_hdr_error_packets_total Forward routing of a packet is not allowed +# TYPE node_xfrm_fwd_hdr_error_packets_total counter +node_xfrm_fwd_hdr_error_packets_total 6654 +# HELP node_xfrm_in_buffer_error_packets_total No buffer is left +# TYPE node_xfrm_in_buffer_error_packets_total counter +node_xfrm_in_buffer_error_packets_total 2 +# HELP node_xfrm_in_error_packets_total All errors not matched by other +# TYPE node_xfrm_in_error_packets_total counter +node_xfrm_in_error_packets_total 1 +# HELP node_xfrm_in_hdr_error_packets_total Header error +# TYPE node_xfrm_in_hdr_error_packets_total counter +node_xfrm_in_hdr_error_packets_total 4 +# HELP node_xfrm_in_no_pols_packets_total No policy is found for states e.g. Inbound SAs are correct but no SP is found +# TYPE node_xfrm_in_no_pols_packets_total counter +node_xfrm_in_no_pols_packets_total 65432 +# HELP node_xfrm_in_no_states_packets_total No state is found i.e. Either inbound SPI, address, or IPsec protocol at SA is wrong +# TYPE node_xfrm_in_no_states_packets_total counter +node_xfrm_in_no_states_packets_total 3 +# HELP node_xfrm_in_pol_block_packets_total Policy discards +# TYPE node_xfrm_in_pol_block_packets_total counter +node_xfrm_in_pol_block_packets_total 100 +# HELP node_xfrm_in_pol_error_packets_total Policy error +# TYPE node_xfrm_in_pol_error_packets_total counter +node_xfrm_in_pol_error_packets_total 10000 +# HELP node_xfrm_in_state_expired_packets_total State is expired +# TYPE node_xfrm_in_state_expired_packets_total counter +node_xfrm_in_state_expired_packets_total 7 +# HELP node_xfrm_in_state_invalid_packets_total State is invalid +# TYPE node_xfrm_in_state_invalid_packets_total counter +node_xfrm_in_state_invalid_packets_total 55555 +# HELP node_xfrm_in_state_mismatch_packets_total State has mismatch option e.g. UDP encapsulation type is mismatch +# TYPE node_xfrm_in_state_mismatch_packets_total counter +node_xfrm_in_state_mismatch_packets_total 23451 +# HELP node_xfrm_in_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_in_state_mode_error_packets_total counter +node_xfrm_in_state_mode_error_packets_total 100 +# HELP node_xfrm_in_state_proto_error_packets_total Transformation protocol specific error e.g. SA key is wrong +# TYPE node_xfrm_in_state_proto_error_packets_total counter +node_xfrm_in_state_proto_error_packets_total 40 +# HELP node_xfrm_in_state_seq_error_packets_total Sequence error i.e. Sequence number is out of window +# TYPE node_xfrm_in_state_seq_error_packets_total counter +node_xfrm_in_state_seq_error_packets_total 6000 +# HELP node_xfrm_in_tmpl_mismatch_packets_total No matching template for states e.g. Inbound SAs are correct but SP rule is wrong +# TYPE node_xfrm_in_tmpl_mismatch_packets_total counter +node_xfrm_in_tmpl_mismatch_packets_total 51 +# HELP node_xfrm_out_bundle_check_error_packets_total Bundle check error +# TYPE node_xfrm_out_bundle_check_error_packets_total counter +node_xfrm_out_bundle_check_error_packets_total 555 +# HELP node_xfrm_out_bundle_gen_error_packets_total Bundle generation error +# TYPE node_xfrm_out_bundle_gen_error_packets_total counter +node_xfrm_out_bundle_gen_error_packets_total 43321 +# HELP node_xfrm_out_error_packets_total All errors which is not matched others +# TYPE node_xfrm_out_error_packets_total counter +node_xfrm_out_error_packets_total 1e+06 +# HELP node_xfrm_out_no_states_packets_total No state is found +# TYPE node_xfrm_out_no_states_packets_total counter +node_xfrm_out_no_states_packets_total 869 +# HELP node_xfrm_out_pol_block_packets_total Policy discards +# TYPE node_xfrm_out_pol_block_packets_total counter +node_xfrm_out_pol_block_packets_total 43456 +# HELP node_xfrm_out_pol_dead_packets_total Policy is dead +# TYPE node_xfrm_out_pol_dead_packets_total counter +node_xfrm_out_pol_dead_packets_total 7656 +# HELP node_xfrm_out_pol_error_packets_total Policy error +# TYPE node_xfrm_out_pol_error_packets_total counter +node_xfrm_out_pol_error_packets_total 1454 +# HELP node_xfrm_out_state_expired_packets_total State is expired +# TYPE node_xfrm_out_state_expired_packets_total counter +node_xfrm_out_state_expired_packets_total 565 +# HELP node_xfrm_out_state_invalid_packets_total State is invalid, perhaps expired +# TYPE node_xfrm_out_state_invalid_packets_total counter +node_xfrm_out_state_invalid_packets_total 28765 +# HELP node_xfrm_out_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_out_state_mode_error_packets_total counter +node_xfrm_out_state_mode_error_packets_total 8 +# HELP node_xfrm_out_state_proto_error_packets_total Transformation protocol specific error +# TYPE node_xfrm_out_state_proto_error_packets_total counter +node_xfrm_out_state_proto_error_packets_total 4542 +# HELP node_xfrm_out_state_seq_error_packets_total Sequence error i.e. Sequence number overflow +# TYPE node_xfrm_out_state_seq_error_packets_total counter +node_xfrm_out_state_seq_error_packets_total 543 +# HELP promhttp_metric_handler_errors_total Total number of internal errors encountered by the promhttp metric handler. +# TYPE promhttp_metric_handler_errors_total counter +promhttp_metric_handler_errors_total{cause="encoding"} 0 +promhttp_metric_handler_errors_total{cause="gathering"} 0 +# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served. +# TYPE promhttp_metric_handler_requests_in_flight gauge +promhttp_metric_handler_requests_in_flight 1 +# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code. +# TYPE promhttp_metric_handler_requests_total counter +promhttp_metric_handler_requests_total{code="200"} 0 +promhttp_metric_handler_requests_total{code="500"} 0 +promhttp_metric_handler_requests_total{code="503"} 0 +# HELP testmetric1_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_1 untyped +testmetric1_1{foo="bar"} 10 +# HELP testmetric1_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_2 untyped +testmetric1_2{foo="baz"} 20 +# HELP testmetric2_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_1 untyped +testmetric2_1{foo="bar"} 30 +# HELP testmetric2_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_2 untyped +testmetric2_2{foo="baz"} 40 diff --git a/collector/fixtures/e2e-output-freebsd.txt b/collector/fixtures/e2e-output-freebsd.txt new file mode 100644 index 0000000000..e7b1dd50f6 --- /dev/null +++ b/collector/fixtures/e2e-output-freebsd.txt @@ -0,0 +1,287 @@ +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. +# TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge +# HELP go_goroutines Number of goroutines that currently exist. +# TYPE go_goroutines gauge +# HELP go_info Information about the Go environment. +# TYPE go_info gauge +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_alloc_bytes gauge +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. +# TYPE go_memstats_alloc_bytes_total counter +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. +# TYPE go_memstats_buck_hash_sys_bytes gauge +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_frees_total counter +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. +# TYPE go_memstats_gc_sys_bytes gauge +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_heap_alloc_bytes gauge +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_idle_bytes gauge +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes +# TYPE go_memstats_heap_inuse_bytes gauge +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. +# TYPE go_memstats_heap_objects gauge +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. +# TYPE go_memstats_heap_released_bytes gauge +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_sys_bytes gauge +# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. +# TYPE go_memstats_last_gc_time_seconds gauge +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_mallocs_total counter +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. +# TYPE go_memstats_mcache_inuse_bytes gauge +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. +# TYPE go_memstats_mcache_sys_bytes gauge +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. +# TYPE go_memstats_mspan_inuse_bytes gauge +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. +# TYPE go_memstats_mspan_sys_bytes gauge +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. +# TYPE go_memstats_next_gc_bytes gauge +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. +# TYPE go_memstats_other_sys_bytes gauge +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. +# TYPE go_memstats_stack_inuse_bytes gauge +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. +# TYPE go_memstats_stack_sys_bytes gauge +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. +# TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge +# HELP go_threads Number of OS threads created. +# TYPE go_threads gauge +# HELP node_buddyinfo_blocks Count of free blocks according to size. +# TYPE node_buddyinfo_blocks gauge +node_buddyinfo_blocks{node="0",size="0",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="0",zone="DMA32"} 759 +node_buddyinfo_blocks{node="0",size="0",zone="Normal"} 4381 +node_buddyinfo_blocks{node="0",size="1",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="1",zone="DMA32"} 572 +node_buddyinfo_blocks{node="0",size="1",zone="Normal"} 1093 +node_buddyinfo_blocks{node="0",size="10",zone="DMA"} 3 +node_buddyinfo_blocks{node="0",size="10",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="10",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="2",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="2",zone="DMA32"} 791 +node_buddyinfo_blocks{node="0",size="2",zone="Normal"} 185 +node_buddyinfo_blocks{node="0",size="3",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="3",zone="DMA32"} 475 +node_buddyinfo_blocks{node="0",size="3",zone="Normal"} 1530 +node_buddyinfo_blocks{node="0",size="4",zone="DMA"} 2 +node_buddyinfo_blocks{node="0",size="4",zone="DMA32"} 194 +node_buddyinfo_blocks{node="0",size="4",zone="Normal"} 567 +node_buddyinfo_blocks{node="0",size="5",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="5",zone="DMA32"} 45 +node_buddyinfo_blocks{node="0",size="5",zone="Normal"} 102 +node_buddyinfo_blocks{node="0",size="6",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="6",zone="DMA32"} 12 +node_buddyinfo_blocks{node="0",size="6",zone="Normal"} 4 +node_buddyinfo_blocks{node="0",size="7",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="8",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="9",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="Normal"} 0 +# HELP node_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which node_exporter was built, and the goos and goarch for the build. +# TYPE node_exporter_build_info gauge +# HELP node_memory_swap_in_bytes_total Bytes paged in from swap devices +# TYPE node_memory_swap_in_bytes_total counter +node_memory_swap_in_bytes_total 0 +# HELP node_memory_swap_out_bytes_total Bytes paged out to swap devices +# TYPE node_memory_swap_out_bytes_total counter +node_memory_swap_out_bytes_total 0 +# HELP node_memory_swap_size_bytes Total swap memory size +# TYPE node_memory_swap_size_bytes gauge +node_memory_swap_size_bytes 1.073741824e+09 +# HELP node_memory_swap_used_bytes Currently allocated swap +# TYPE node_memory_swap_used_bytes gauge +node_memory_swap_used_bytes 0 +# HELP node_memory_user_wired_bytes Locked in memory by user, mlock, etc +# TYPE node_memory_user_wired_bytes gauge +node_memory_user_wired_bytes 0 +# HELP node_netisr_bindthreads netisr threads bound to CPUs +# TYPE node_netisr_bindthreads gauge +node_netisr_bindthreads 0 +# HELP node_netisr_defaultqlimit netisr default queue limit +# TYPE node_netisr_defaultqlimit gauge +node_netisr_defaultqlimit 256 +# HELP node_netisr_maxprot netisr maximum protocols +# TYPE node_netisr_maxprot gauge +node_netisr_maxprot 16 +# HELP node_netisr_maxqlimit netisr maximum queue limit +# TYPE node_netisr_maxqlimit gauge +node_netisr_maxqlimit 10240 +# HELP node_netisr_maxthreads netisr maximum thread count +# TYPE node_netisr_maxthreads gauge +node_netisr_maxthreads 1 +# HELP node_netisr_numthreads netisr current thread count +# TYPE node_netisr_numthreads gauge +node_netisr_numthreads 1 +# HELP node_network_receive_drop_total Network device statistic receive_drop. +# TYPE node_network_receive_drop_total counter +node_network_receive_drop_total{device="lo0"} 0 +# HELP node_network_receive_errs_total Network device statistic receive_errs. +# TYPE node_network_receive_errs_total counter +node_network_receive_errs_total{device="lo0"} 0 +# HELP node_network_receive_packets_total Network device statistic receive_packets. +# TYPE node_network_receive_packets_total counter +# HELP node_network_transmit_bytes_total Network device statistic transmit_bytes. +# TYPE node_network_transmit_bytes_total counter +# HELP node_network_transmit_drop_total Network device statistic transmit_drop. +# TYPE node_network_transmit_drop_total counter +node_network_transmit_drop_total{device="lo0"} 0 +# HELP node_network_transmit_errs_total Network device statistic transmit_errs. +# TYPE node_network_transmit_errs_total counter +node_network_transmit_errs_total{device="lo0"} 0 +# HELP node_network_transmit_packets_total Network device statistic transmit_packets. +# TYPE node_network_transmit_packets_total counter +# HELP node_os_info A metric with a constant '1' value labeled by build_id, id, id_like, image_id, image_version, name, pretty_name, variant, variant_id, version, version_codename, version_id. +# TYPE node_os_info gauge +node_os_info{build_id="",id="ubuntu",id_like="debian",image_id="",image_version="",name="Ubuntu",pretty_name="Ubuntu 20.04.2 LTS",variant="",variant_id="",version="20.04.2 LTS (Focal Fossa)",version_codename="focal",version_id="20.04"} 1 +# HELP node_os_version Metric containing the major.minor part of the OS version. +# TYPE node_os_version gauge +node_os_version{id="ubuntu",id_like="debian",name="Ubuntu"} 20.04 +# HELP node_scrape_collector_duration_seconds node_exporter: Duration of a collector scrape. +# TYPE node_scrape_collector_duration_seconds gauge +# HELP node_scrape_collector_success node_exporter: Whether a collector succeeded. +# TYPE node_scrape_collector_success gauge +node_scrape_collector_success{collector="boottime"} 1 +node_scrape_collector_success{collector="buddyinfo"} 1 +node_scrape_collector_success{collector="cpu"} 1 +node_scrape_collector_success{collector="exec"} 1 +node_scrape_collector_success{collector="loadavg"} 1 +node_scrape_collector_success{collector="meminfo"} 1 +node_scrape_collector_success{collector="netdev"} 1 +node_scrape_collector_success{collector="netisr"} 1 +node_scrape_collector_success{collector="netstat"} 1 +node_scrape_collector_success{collector="os"} 1 +node_scrape_collector_success{collector="textfile"} 1 +node_scrape_collector_success{collector="time"} 1 +node_scrape_collector_success{collector="xfrm"} 1 +node_scrape_collector_success{collector="zfs"} 1 +# HELP node_textfile_mtime_seconds Unixtime mtime of textfiles successfully read. +# TYPE node_textfile_mtime_seconds gauge +# HELP node_textfile_scrape_error 1 if there was an error opening or reading a file, 0 otherwise +# TYPE node_textfile_scrape_error gauge +node_textfile_scrape_error 0 +# HELP node_time_seconds System time in seconds since epoch (1970). +# TYPE node_time_seconds gauge +# HELP node_time_zone_offset_seconds System time zone offset in seconds. +# TYPE node_time_zone_offset_seconds gauge +# HELP node_xfrm_acquire_error_packets_total State hasn’t been fully acquired before use +# TYPE node_xfrm_acquire_error_packets_total counter +node_xfrm_acquire_error_packets_total 24532 +# HELP node_xfrm_fwd_hdr_error_packets_total Forward routing of a packet is not allowed +# TYPE node_xfrm_fwd_hdr_error_packets_total counter +node_xfrm_fwd_hdr_error_packets_total 6654 +# HELP node_xfrm_in_buffer_error_packets_total No buffer is left +# TYPE node_xfrm_in_buffer_error_packets_total counter +node_xfrm_in_buffer_error_packets_total 2 +# HELP node_xfrm_in_error_packets_total All errors not matched by other +# TYPE node_xfrm_in_error_packets_total counter +node_xfrm_in_error_packets_total 1 +# HELP node_xfrm_in_hdr_error_packets_total Header error +# TYPE node_xfrm_in_hdr_error_packets_total counter +node_xfrm_in_hdr_error_packets_total 4 +# HELP node_xfrm_in_no_pols_packets_total No policy is found for states e.g. Inbound SAs are correct but no SP is found +# TYPE node_xfrm_in_no_pols_packets_total counter +node_xfrm_in_no_pols_packets_total 65432 +# HELP node_xfrm_in_no_states_packets_total No state is found i.e. Either inbound SPI, address, or IPsec protocol at SA is wrong +# TYPE node_xfrm_in_no_states_packets_total counter +node_xfrm_in_no_states_packets_total 3 +# HELP node_xfrm_in_pol_block_packets_total Policy discards +# TYPE node_xfrm_in_pol_block_packets_total counter +node_xfrm_in_pol_block_packets_total 100 +# HELP node_xfrm_in_pol_error_packets_total Policy error +# TYPE node_xfrm_in_pol_error_packets_total counter +node_xfrm_in_pol_error_packets_total 10000 +# HELP node_xfrm_in_state_expired_packets_total State is expired +# TYPE node_xfrm_in_state_expired_packets_total counter +node_xfrm_in_state_expired_packets_total 7 +# HELP node_xfrm_in_state_invalid_packets_total State is invalid +# TYPE node_xfrm_in_state_invalid_packets_total counter +node_xfrm_in_state_invalid_packets_total 55555 +# HELP node_xfrm_in_state_mismatch_packets_total State has mismatch option e.g. UDP encapsulation type is mismatch +# TYPE node_xfrm_in_state_mismatch_packets_total counter +node_xfrm_in_state_mismatch_packets_total 23451 +# HELP node_xfrm_in_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_in_state_mode_error_packets_total counter +node_xfrm_in_state_mode_error_packets_total 100 +# HELP node_xfrm_in_state_proto_error_packets_total Transformation protocol specific error e.g. SA key is wrong +# TYPE node_xfrm_in_state_proto_error_packets_total counter +node_xfrm_in_state_proto_error_packets_total 40 +# HELP node_xfrm_in_state_seq_error_packets_total Sequence error i.e. Sequence number is out of window +# TYPE node_xfrm_in_state_seq_error_packets_total counter +node_xfrm_in_state_seq_error_packets_total 6000 +# HELP node_xfrm_in_tmpl_mismatch_packets_total No matching template for states e.g. Inbound SAs are correct but SP rule is wrong +# TYPE node_xfrm_in_tmpl_mismatch_packets_total counter +node_xfrm_in_tmpl_mismatch_packets_total 51 +# HELP node_xfrm_out_bundle_check_error_packets_total Bundle check error +# TYPE node_xfrm_out_bundle_check_error_packets_total counter +node_xfrm_out_bundle_check_error_packets_total 555 +# HELP node_xfrm_out_bundle_gen_error_packets_total Bundle generation error +# TYPE node_xfrm_out_bundle_gen_error_packets_total counter +node_xfrm_out_bundle_gen_error_packets_total 43321 +# HELP node_xfrm_out_error_packets_total All errors which is not matched others +# TYPE node_xfrm_out_error_packets_total counter +node_xfrm_out_error_packets_total 1e+06 +# HELP node_xfrm_out_no_states_packets_total No state is found +# TYPE node_xfrm_out_no_states_packets_total counter +node_xfrm_out_no_states_packets_total 869 +# HELP node_xfrm_out_pol_block_packets_total Policy discards +# TYPE node_xfrm_out_pol_block_packets_total counter +node_xfrm_out_pol_block_packets_total 43456 +# HELP node_xfrm_out_pol_dead_packets_total Policy is dead +# TYPE node_xfrm_out_pol_dead_packets_total counter +node_xfrm_out_pol_dead_packets_total 7656 +# HELP node_xfrm_out_pol_error_packets_total Policy error +# TYPE node_xfrm_out_pol_error_packets_total counter +node_xfrm_out_pol_error_packets_total 1454 +# HELP node_xfrm_out_state_expired_packets_total State is expired +# TYPE node_xfrm_out_state_expired_packets_total counter +node_xfrm_out_state_expired_packets_total 565 +# HELP node_xfrm_out_state_invalid_packets_total State is invalid, perhaps expired +# TYPE node_xfrm_out_state_invalid_packets_total counter +node_xfrm_out_state_invalid_packets_total 28765 +# HELP node_xfrm_out_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_out_state_mode_error_packets_total counter +node_xfrm_out_state_mode_error_packets_total 8 +# HELP node_xfrm_out_state_proto_error_packets_total Transformation protocol specific error +# TYPE node_xfrm_out_state_proto_error_packets_total counter +node_xfrm_out_state_proto_error_packets_total 4542 +# HELP node_xfrm_out_state_seq_error_packets_total Sequence error i.e. Sequence number overflow +# TYPE node_xfrm_out_state_seq_error_packets_total counter +node_xfrm_out_state_seq_error_packets_total 543 +# HELP promhttp_metric_handler_errors_total Total number of internal errors encountered by the promhttp metric handler. +# TYPE promhttp_metric_handler_errors_total counter +promhttp_metric_handler_errors_total{cause="encoding"} 0 +promhttp_metric_handler_errors_total{cause="gathering"} 0 +# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served. +# TYPE promhttp_metric_handler_requests_in_flight gauge +promhttp_metric_handler_requests_in_flight 1 +# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code. +# TYPE promhttp_metric_handler_requests_total counter +promhttp_metric_handler_requests_total{code="200"} 0 +promhttp_metric_handler_requests_total{code="500"} 0 +promhttp_metric_handler_requests_total{code="503"} 0 +# HELP testmetric1_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_1 untyped +testmetric1_1{foo="bar"} 10 +# HELP testmetric1_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_2 untyped +testmetric1_2{foo="baz"} 20 +# HELP testmetric2_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_1 untyped +testmetric2_1{foo="bar"} 30 +# HELP testmetric2_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_2 untyped +testmetric2_2{foo="baz"} 40 diff --git a/collector/fixtures/e2e-output-netbsd.txt b/collector/fixtures/e2e-output-netbsd.txt new file mode 100644 index 0000000000..1a6f140221 --- /dev/null +++ b/collector/fixtures/e2e-output-netbsd.txt @@ -0,0 +1,209 @@ +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. +# TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge +# HELP go_goroutines Number of goroutines that currently exist. +# TYPE go_goroutines gauge +# HELP go_info Information about the Go environment. +# TYPE go_info gauge +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_alloc_bytes gauge +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. +# TYPE go_memstats_alloc_bytes_total counter +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. +# TYPE go_memstats_buck_hash_sys_bytes gauge +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_frees_total counter +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. +# TYPE go_memstats_gc_sys_bytes gauge +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_heap_alloc_bytes gauge +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_idle_bytes gauge +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes +# TYPE go_memstats_heap_inuse_bytes gauge +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. +# TYPE go_memstats_heap_objects gauge +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. +# TYPE go_memstats_heap_released_bytes gauge +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_sys_bytes gauge +# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. +# TYPE go_memstats_last_gc_time_seconds gauge +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_mallocs_total counter +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. +# TYPE go_memstats_mcache_inuse_bytes gauge +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. +# TYPE go_memstats_mcache_sys_bytes gauge +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. +# TYPE go_memstats_mspan_inuse_bytes gauge +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. +# TYPE go_memstats_mspan_sys_bytes gauge +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. +# TYPE go_memstats_next_gc_bytes gauge +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. +# TYPE go_memstats_other_sys_bytes gauge +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. +# TYPE go_memstats_stack_inuse_bytes gauge +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. +# TYPE go_memstats_stack_sys_bytes gauge +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. +# TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge +# HELP go_threads Number of OS threads created. +# TYPE go_threads gauge +# HELP node_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which node_exporter was built, and the goos and goarch for the build. +# TYPE node_exporter_build_info gauge +# HELP node_memory_swap_size_bytes Memory information field swap_size_bytes. +# TYPE node_memory_swap_size_bytes gauge +node_memory_swap_size_bytes 6.442426368e+09 +# HELP node_memory_swap_used_bytes Memory information field swap_used_bytes. +# TYPE node_memory_swap_used_bytes gauge +node_memory_swap_used_bytes 0 +# HELP node_memory_swapped_in_pages_bytes_total Memory information field swapped_in_pages_bytes_total. +# TYPE node_memory_swapped_in_pages_bytes_total counter +node_memory_swapped_in_pages_bytes_total 0 +# HELP node_memory_swapped_out_pages_bytes_total Memory information field swapped_out_pages_bytes_total. +# TYPE node_memory_swapped_out_pages_bytes_total counter +node_memory_swapped_out_pages_bytes_total 0 +# HELP node_os_info A metric with a constant '1' value labeled by build_id, id, id_like, image_id, image_version, name, pretty_name, variant, variant_id, version, version_codename, version_id. +# TYPE node_os_info gauge +node_os_info{build_id="",id="ubuntu",id_like="debian",image_id="",image_version="",name="Ubuntu",pretty_name="Ubuntu 20.04.2 LTS",variant="",variant_id="",version="20.04.2 LTS (Focal Fossa)",version_codename="focal",version_id="20.04"} 1 +# HELP node_os_version Metric containing the major.minor part of the OS version. +# TYPE node_os_version gauge +node_os_version{id="ubuntu",id_like="debian",name="Ubuntu"} 20.04 +# HELP node_scrape_collector_duration_seconds node_exporter: Duration of a collector scrape. +# TYPE node_scrape_collector_duration_seconds gauge +# HELP node_scrape_collector_success node_exporter: Whether a collector succeeded. +# TYPE node_scrape_collector_success gauge +node_scrape_collector_success{collector="boottime"} 1 +node_scrape_collector_success{collector="cpu"} 0 +node_scrape_collector_success{collector="loadavg"} 1 +node_scrape_collector_success{collector="meminfo"} 1 +node_scrape_collector_success{collector="os"} 1 +node_scrape_collector_success{collector="textfile"} 1 +node_scrape_collector_success{collector="time"} 1 +node_scrape_collector_success{collector="xfrm"} 1 +# HELP node_textfile_mtime_seconds Unixtime mtime of textfiles successfully read. +# TYPE node_textfile_mtime_seconds gauge +# HELP node_textfile_scrape_error 1 if there was an error opening or reading a file, 0 otherwise +# TYPE node_textfile_scrape_error gauge +node_textfile_scrape_error 0 +# HELP node_time_seconds System time in seconds since epoch (1970). +# TYPE node_time_seconds gauge +# HELP node_time_zone_offset_seconds System time zone offset in seconds. +# TYPE node_time_zone_offset_seconds gauge +# HELP node_xfrm_acquire_error_packets_total State hasn’t been fully acquired before use +# TYPE node_xfrm_acquire_error_packets_total counter +node_xfrm_acquire_error_packets_total 24532 +# HELP node_xfrm_fwd_hdr_error_packets_total Forward routing of a packet is not allowed +# TYPE node_xfrm_fwd_hdr_error_packets_total counter +node_xfrm_fwd_hdr_error_packets_total 6654 +# HELP node_xfrm_in_buffer_error_packets_total No buffer is left +# TYPE node_xfrm_in_buffer_error_packets_total counter +node_xfrm_in_buffer_error_packets_total 2 +# HELP node_xfrm_in_error_packets_total All errors not matched by other +# TYPE node_xfrm_in_error_packets_total counter +node_xfrm_in_error_packets_total 1 +# HELP node_xfrm_in_hdr_error_packets_total Header error +# TYPE node_xfrm_in_hdr_error_packets_total counter +node_xfrm_in_hdr_error_packets_total 4 +# HELP node_xfrm_in_no_pols_packets_total No policy is found for states e.g. Inbound SAs are correct but no SP is found +# TYPE node_xfrm_in_no_pols_packets_total counter +node_xfrm_in_no_pols_packets_total 65432 +# HELP node_xfrm_in_no_states_packets_total No state is found i.e. Either inbound SPI, address, or IPsec protocol at SA is wrong +# TYPE node_xfrm_in_no_states_packets_total counter +node_xfrm_in_no_states_packets_total 3 +# HELP node_xfrm_in_pol_block_packets_total Policy discards +# TYPE node_xfrm_in_pol_block_packets_total counter +node_xfrm_in_pol_block_packets_total 100 +# HELP node_xfrm_in_pol_error_packets_total Policy error +# TYPE node_xfrm_in_pol_error_packets_total counter +node_xfrm_in_pol_error_packets_total 10000 +# HELP node_xfrm_in_state_expired_packets_total State is expired +# TYPE node_xfrm_in_state_expired_packets_total counter +node_xfrm_in_state_expired_packets_total 7 +# HELP node_xfrm_in_state_invalid_packets_total State is invalid +# TYPE node_xfrm_in_state_invalid_packets_total counter +node_xfrm_in_state_invalid_packets_total 55555 +# HELP node_xfrm_in_state_mismatch_packets_total State has mismatch option e.g. UDP encapsulation type is mismatch +# TYPE node_xfrm_in_state_mismatch_packets_total counter +node_xfrm_in_state_mismatch_packets_total 23451 +# HELP node_xfrm_in_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_in_state_mode_error_packets_total counter +node_xfrm_in_state_mode_error_packets_total 100 +# HELP node_xfrm_in_state_proto_error_packets_total Transformation protocol specific error e.g. SA key is wrong +# TYPE node_xfrm_in_state_proto_error_packets_total counter +node_xfrm_in_state_proto_error_packets_total 40 +# HELP node_xfrm_in_state_seq_error_packets_total Sequence error i.e. Sequence number is out of window +# TYPE node_xfrm_in_state_seq_error_packets_total counter +node_xfrm_in_state_seq_error_packets_total 6000 +# HELP node_xfrm_in_tmpl_mismatch_packets_total No matching template for states e.g. Inbound SAs are correct but SP rule is wrong +# TYPE node_xfrm_in_tmpl_mismatch_packets_total counter +node_xfrm_in_tmpl_mismatch_packets_total 51 +# HELP node_xfrm_out_bundle_check_error_packets_total Bundle check error +# TYPE node_xfrm_out_bundle_check_error_packets_total counter +node_xfrm_out_bundle_check_error_packets_total 555 +# HELP node_xfrm_out_bundle_gen_error_packets_total Bundle generation error +# TYPE node_xfrm_out_bundle_gen_error_packets_total counter +node_xfrm_out_bundle_gen_error_packets_total 43321 +# HELP node_xfrm_out_error_packets_total All errors which is not matched others +# TYPE node_xfrm_out_error_packets_total counter +node_xfrm_out_error_packets_total 1e+06 +# HELP node_xfrm_out_no_states_packets_total No state is found +# TYPE node_xfrm_out_no_states_packets_total counter +node_xfrm_out_no_states_packets_total 869 +# HELP node_xfrm_out_pol_block_packets_total Policy discards +# TYPE node_xfrm_out_pol_block_packets_total counter +node_xfrm_out_pol_block_packets_total 43456 +# HELP node_xfrm_out_pol_dead_packets_total Policy is dead +# TYPE node_xfrm_out_pol_dead_packets_total counter +node_xfrm_out_pol_dead_packets_total 7656 +# HELP node_xfrm_out_pol_error_packets_total Policy error +# TYPE node_xfrm_out_pol_error_packets_total counter +node_xfrm_out_pol_error_packets_total 1454 +# HELP node_xfrm_out_state_expired_packets_total State is expired +# TYPE node_xfrm_out_state_expired_packets_total counter +node_xfrm_out_state_expired_packets_total 565 +# HELP node_xfrm_out_state_invalid_packets_total State is invalid, perhaps expired +# TYPE node_xfrm_out_state_invalid_packets_total counter +node_xfrm_out_state_invalid_packets_total 28765 +# HELP node_xfrm_out_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_out_state_mode_error_packets_total counter +node_xfrm_out_state_mode_error_packets_total 8 +# HELP node_xfrm_out_state_proto_error_packets_total Transformation protocol specific error +# TYPE node_xfrm_out_state_proto_error_packets_total counter +node_xfrm_out_state_proto_error_packets_total 4542 +# HELP node_xfrm_out_state_seq_error_packets_total Sequence error i.e. Sequence number overflow +# TYPE node_xfrm_out_state_seq_error_packets_total counter +node_xfrm_out_state_seq_error_packets_total 543 +# HELP process_open_fds Number of open file descriptors. +# TYPE process_open_fds gauge +# HELP promhttp_metric_handler_errors_total Total number of internal errors encountered by the promhttp metric handler. +# TYPE promhttp_metric_handler_errors_total counter +promhttp_metric_handler_errors_total{cause="encoding"} 0 +promhttp_metric_handler_errors_total{cause="gathering"} 0 +# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served. +# TYPE promhttp_metric_handler_requests_in_flight gauge +promhttp_metric_handler_requests_in_flight 1 +# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code. +# TYPE promhttp_metric_handler_requests_total counter +promhttp_metric_handler_requests_total{code="200"} 0 +promhttp_metric_handler_requests_total{code="500"} 0 +promhttp_metric_handler_requests_total{code="503"} 0 +# HELP testmetric1_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_1 untyped +testmetric1_1{foo="bar"} 10 +# HELP testmetric1_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_2 untyped +testmetric1_2{foo="baz"} 20 +# HELP testmetric2_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_1 untyped +testmetric2_1{foo="bar"} 30 +# HELP testmetric2_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_2 untyped +testmetric2_2{foo="baz"} 40 diff --git a/collector/fixtures/e2e-output-openbsd.txt b/collector/fixtures/e2e-output-openbsd.txt new file mode 100644 index 0000000000..96d2109d52 --- /dev/null +++ b/collector/fixtures/e2e-output-openbsd.txt @@ -0,0 +1,276 @@ +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. +# TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge +# HELP go_goroutines Number of goroutines that currently exist. +# TYPE go_goroutines gauge +# HELP go_info Information about the Go environment. +# TYPE go_info gauge +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_alloc_bytes gauge +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. +# TYPE go_memstats_alloc_bytes_total counter +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. +# TYPE go_memstats_buck_hash_sys_bytes gauge +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_frees_total counter +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. +# TYPE go_memstats_gc_sys_bytes gauge +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_heap_alloc_bytes gauge +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_idle_bytes gauge +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes +# TYPE go_memstats_heap_inuse_bytes gauge +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. +# TYPE go_memstats_heap_objects gauge +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. +# TYPE go_memstats_heap_released_bytes gauge +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_sys_bytes gauge +# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. +# TYPE go_memstats_last_gc_time_seconds gauge +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_mallocs_total counter +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. +# TYPE go_memstats_mcache_inuse_bytes gauge +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. +# TYPE go_memstats_mcache_sys_bytes gauge +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. +# TYPE go_memstats_mspan_inuse_bytes gauge +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. +# TYPE go_memstats_mspan_sys_bytes gauge +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. +# TYPE go_memstats_next_gc_bytes gauge +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. +# TYPE go_memstats_other_sys_bytes gauge +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. +# TYPE go_memstats_stack_inuse_bytes gauge +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. +# TYPE go_memstats_stack_sys_bytes gauge +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. +# TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge +# HELP go_threads Number of OS threads created. +# TYPE go_threads gauge +# HELP node_buddyinfo_blocks Count of free blocks according to size. +# TYPE node_buddyinfo_blocks gauge +node_buddyinfo_blocks{node="0",size="0",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="0",zone="DMA32"} 759 +node_buddyinfo_blocks{node="0",size="0",zone="Normal"} 4381 +node_buddyinfo_blocks{node="0",size="1",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="1",zone="DMA32"} 572 +node_buddyinfo_blocks{node="0",size="1",zone="Normal"} 1093 +node_buddyinfo_blocks{node="0",size="10",zone="DMA"} 3 +node_buddyinfo_blocks{node="0",size="10",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="10",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="2",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="2",zone="DMA32"} 791 +node_buddyinfo_blocks{node="0",size="2",zone="Normal"} 185 +node_buddyinfo_blocks{node="0",size="3",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="3",zone="DMA32"} 475 +node_buddyinfo_blocks{node="0",size="3",zone="Normal"} 1530 +node_buddyinfo_blocks{node="0",size="4",zone="DMA"} 2 +node_buddyinfo_blocks{node="0",size="4",zone="DMA32"} 194 +node_buddyinfo_blocks{node="0",size="4",zone="Normal"} 567 +node_buddyinfo_blocks{node="0",size="5",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="5",zone="DMA32"} 45 +node_buddyinfo_blocks{node="0",size="5",zone="Normal"} 102 +node_buddyinfo_blocks{node="0",size="6",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="6",zone="DMA32"} 12 +node_buddyinfo_blocks{node="0",size="6",zone="Normal"} 4 +node_buddyinfo_blocks{node="0",size="7",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="8",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="9",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="Normal"} 0 +# HELP node_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which node_exporter was built, and the goos and goarch for the build. +# TYPE node_exporter_build_info gauge +# HELP node_memory_swap_size_bytes Memory information field swap_size_bytes. +# TYPE node_memory_swap_size_bytes gauge +node_memory_swap_size_bytes 6.693941248e+09 +# HELP node_memory_swap_used_bytes Memory information field swap_used_bytes. +# TYPE node_memory_swap_used_bytes gauge +node_memory_swap_used_bytes 0 +# HELP node_memory_swapped_in_pages_bytes_total Memory information field swapped_in_pages_bytes_total. +# TYPE node_memory_swapped_in_pages_bytes_total counter +node_memory_swapped_in_pages_bytes_total 0 +# HELP node_memory_swapped_out_pages_bytes_total Memory information field swapped_out_pages_bytes_total. +# TYPE node_memory_swapped_out_pages_bytes_total counter +node_memory_swapped_out_pages_bytes_total 0 +# HELP node_network_noproto_total Network device statistic noproto. +# TYPE node_network_noproto_total counter +node_network_noproto_total{device="lo0"} 0 +node_network_noproto_total{device="pflog0"} 0 +# HELP node_network_receive_drop_total Network device statistic receive_drop. +# TYPE node_network_receive_drop_total counter +node_network_receive_drop_total{device="lo0"} 0 +node_network_receive_drop_total{device="pflog0"} 0 +# HELP node_network_receive_errs_total Network device statistic receive_errs. +# TYPE node_network_receive_errs_total counter +node_network_receive_errs_total{device="lo0"} 0 +node_network_receive_errs_total{device="pflog0"} 0 +# HELP node_network_receive_packets_total Network device statistic receive_packets. +# TYPE node_network_receive_packets_total counter +# HELP node_network_transmit_bytes_total Network device statistic transmit_bytes. +# TYPE node_network_transmit_bytes_total counter +# HELP node_network_transmit_colls_total Network device statistic transmit_colls. +# TYPE node_network_transmit_colls_total counter +node_network_transmit_colls_total{device="lo0"} 0 +node_network_transmit_colls_total{device="pflog0"} 0 +# HELP node_network_transmit_drop_total Network device statistic transmit_drop. +# TYPE node_network_transmit_drop_total counter +node_network_transmit_drop_total{device="lo0"} 0 +node_network_transmit_drop_total{device="pflog0"} 0 +# HELP node_network_transmit_errs_total Network device statistic transmit_errs. +# TYPE node_network_transmit_errs_total counter +node_network_transmit_errs_total{device="lo0"} 0 +node_network_transmit_errs_total{device="pflog0"} 0 +# HELP node_network_transmit_packets_total Network device statistic transmit_packets. +# TYPE node_network_transmit_packets_total counter +# HELP node_os_info A metric with a constant '1' value labeled by build_id, id, id_like, image_id, image_version, name, pretty_name, variant, variant_id, version, version_codename, version_id. +# TYPE node_os_info gauge +node_os_info{build_id="",id="ubuntu",id_like="debian",image_id="",image_version="",name="Ubuntu",pretty_name="Ubuntu 20.04.2 LTS",variant="",variant_id="",version="20.04.2 LTS (Focal Fossa)",version_codename="focal",version_id="20.04"} 1 +# HELP node_os_version Metric containing the major.minor part of the OS version. +# TYPE node_os_version gauge +node_os_version{id="ubuntu",id_like="debian",name="Ubuntu"} 20.04 +# HELP node_scrape_collector_duration_seconds node_exporter: Duration of a collector scrape. +# TYPE node_scrape_collector_duration_seconds gauge +# HELP node_scrape_collector_success node_exporter: Whether a collector succeeded. +# TYPE node_scrape_collector_success gauge +node_scrape_collector_success{collector="boottime"} 1 +node_scrape_collector_success{collector="buddyinfo"} 1 +node_scrape_collector_success{collector="cpu"} 1 +node_scrape_collector_success{collector="diskstats"} 1 +node_scrape_collector_success{collector="interrupts"} 1 +node_scrape_collector_success{collector="loadavg"} 1 +node_scrape_collector_success{collector="meminfo"} 1 +node_scrape_collector_success{collector="netdev"} 1 +node_scrape_collector_success{collector="os"} 1 +node_scrape_collector_success{collector="textfile"} 1 +node_scrape_collector_success{collector="time"} 1 +node_scrape_collector_success{collector="xfrm"} 1 +# HELP node_textfile_mtime_seconds Unixtime mtime of textfiles successfully read. +# TYPE node_textfile_mtime_seconds gauge +# HELP node_textfile_scrape_error 1 if there was an error opening or reading a file, 0 otherwise +# TYPE node_textfile_scrape_error gauge +node_textfile_scrape_error 0 +# HELP node_time_seconds System time in seconds since epoch (1970). +# TYPE node_time_seconds gauge +# HELP node_time_zone_offset_seconds System time zone offset in seconds. +# TYPE node_time_zone_offset_seconds gauge +# HELP node_xfrm_acquire_error_packets_total State hasn’t been fully acquired before use +# TYPE node_xfrm_acquire_error_packets_total counter +node_xfrm_acquire_error_packets_total 24532 +# HELP node_xfrm_fwd_hdr_error_packets_total Forward routing of a packet is not allowed +# TYPE node_xfrm_fwd_hdr_error_packets_total counter +node_xfrm_fwd_hdr_error_packets_total 6654 +# HELP node_xfrm_in_buffer_error_packets_total No buffer is left +# TYPE node_xfrm_in_buffer_error_packets_total counter +node_xfrm_in_buffer_error_packets_total 2 +# HELP node_xfrm_in_error_packets_total All errors not matched by other +# TYPE node_xfrm_in_error_packets_total counter +node_xfrm_in_error_packets_total 1 +# HELP node_xfrm_in_hdr_error_packets_total Header error +# TYPE node_xfrm_in_hdr_error_packets_total counter +node_xfrm_in_hdr_error_packets_total 4 +# HELP node_xfrm_in_no_pols_packets_total No policy is found for states e.g. Inbound SAs are correct but no SP is found +# TYPE node_xfrm_in_no_pols_packets_total counter +node_xfrm_in_no_pols_packets_total 65432 +# HELP node_xfrm_in_no_states_packets_total No state is found i.e. Either inbound SPI, address, or IPsec protocol at SA is wrong +# TYPE node_xfrm_in_no_states_packets_total counter +node_xfrm_in_no_states_packets_total 3 +# HELP node_xfrm_in_pol_block_packets_total Policy discards +# TYPE node_xfrm_in_pol_block_packets_total counter +node_xfrm_in_pol_block_packets_total 100 +# HELP node_xfrm_in_pol_error_packets_total Policy error +# TYPE node_xfrm_in_pol_error_packets_total counter +node_xfrm_in_pol_error_packets_total 10000 +# HELP node_xfrm_in_state_expired_packets_total State is expired +# TYPE node_xfrm_in_state_expired_packets_total counter +node_xfrm_in_state_expired_packets_total 7 +# HELP node_xfrm_in_state_invalid_packets_total State is invalid +# TYPE node_xfrm_in_state_invalid_packets_total counter +node_xfrm_in_state_invalid_packets_total 55555 +# HELP node_xfrm_in_state_mismatch_packets_total State has mismatch option e.g. UDP encapsulation type is mismatch +# TYPE node_xfrm_in_state_mismatch_packets_total counter +node_xfrm_in_state_mismatch_packets_total 23451 +# HELP node_xfrm_in_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_in_state_mode_error_packets_total counter +node_xfrm_in_state_mode_error_packets_total 100 +# HELP node_xfrm_in_state_proto_error_packets_total Transformation protocol specific error e.g. SA key is wrong +# TYPE node_xfrm_in_state_proto_error_packets_total counter +node_xfrm_in_state_proto_error_packets_total 40 +# HELP node_xfrm_in_state_seq_error_packets_total Sequence error i.e. Sequence number is out of window +# TYPE node_xfrm_in_state_seq_error_packets_total counter +node_xfrm_in_state_seq_error_packets_total 6000 +# HELP node_xfrm_in_tmpl_mismatch_packets_total No matching template for states e.g. Inbound SAs are correct but SP rule is wrong +# TYPE node_xfrm_in_tmpl_mismatch_packets_total counter +node_xfrm_in_tmpl_mismatch_packets_total 51 +# HELP node_xfrm_out_bundle_check_error_packets_total Bundle check error +# TYPE node_xfrm_out_bundle_check_error_packets_total counter +node_xfrm_out_bundle_check_error_packets_total 555 +# HELP node_xfrm_out_bundle_gen_error_packets_total Bundle generation error +# TYPE node_xfrm_out_bundle_gen_error_packets_total counter +node_xfrm_out_bundle_gen_error_packets_total 43321 +# HELP node_xfrm_out_error_packets_total All errors which is not matched others +# TYPE node_xfrm_out_error_packets_total counter +node_xfrm_out_error_packets_total 1e+06 +# HELP node_xfrm_out_no_states_packets_total No state is found +# TYPE node_xfrm_out_no_states_packets_total counter +node_xfrm_out_no_states_packets_total 869 +# HELP node_xfrm_out_pol_block_packets_total Policy discards +# TYPE node_xfrm_out_pol_block_packets_total counter +node_xfrm_out_pol_block_packets_total 43456 +# HELP node_xfrm_out_pol_dead_packets_total Policy is dead +# TYPE node_xfrm_out_pol_dead_packets_total counter +node_xfrm_out_pol_dead_packets_total 7656 +# HELP node_xfrm_out_pol_error_packets_total Policy error +# TYPE node_xfrm_out_pol_error_packets_total counter +node_xfrm_out_pol_error_packets_total 1454 +# HELP node_xfrm_out_state_expired_packets_total State is expired +# TYPE node_xfrm_out_state_expired_packets_total counter +node_xfrm_out_state_expired_packets_total 565 +# HELP node_xfrm_out_state_invalid_packets_total State is invalid, perhaps expired +# TYPE node_xfrm_out_state_invalid_packets_total counter +node_xfrm_out_state_invalid_packets_total 28765 +# HELP node_xfrm_out_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_out_state_mode_error_packets_total counter +node_xfrm_out_state_mode_error_packets_total 8 +# HELP node_xfrm_out_state_proto_error_packets_total Transformation protocol specific error +# TYPE node_xfrm_out_state_proto_error_packets_total counter +node_xfrm_out_state_proto_error_packets_total 4542 +# HELP node_xfrm_out_state_seq_error_packets_total Sequence error i.e. Sequence number overflow +# TYPE node_xfrm_out_state_seq_error_packets_total counter +node_xfrm_out_state_seq_error_packets_total 543 +# HELP promhttp_metric_handler_errors_total Total number of internal errors encountered by the promhttp metric handler. +# TYPE promhttp_metric_handler_errors_total counter +promhttp_metric_handler_errors_total{cause="encoding"} 0 +promhttp_metric_handler_errors_total{cause="gathering"} 0 +# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served. +# TYPE promhttp_metric_handler_requests_in_flight gauge +promhttp_metric_handler_requests_in_flight 1 +# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code. +# TYPE promhttp_metric_handler_requests_total counter +promhttp_metric_handler_requests_total{code="200"} 0 +promhttp_metric_handler_requests_total{code="500"} 0 +promhttp_metric_handler_requests_total{code="503"} 0 +# HELP testmetric1_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_1 untyped +testmetric1_1{foo="bar"} 10 +# HELP testmetric1_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_2 untyped +testmetric1_2{foo="baz"} 20 +# HELP testmetric2_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_1 untyped +testmetric2_1{foo="bar"} 30 +# HELP testmetric2_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_2 untyped +testmetric2_2{foo="baz"} 40 diff --git a/collector/fixtures/e2e-output-solaris.txt b/collector/fixtures/e2e-output-solaris.txt new file mode 100644 index 0000000000..2f39a5f6a2 --- /dev/null +++ b/collector/fixtures/e2e-output-solaris.txt @@ -0,0 +1,240 @@ +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. +# TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge +# HELP go_goroutines Number of goroutines that currently exist. +# TYPE go_goroutines gauge +# HELP go_info Information about the Go environment. +# TYPE go_info gauge +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_alloc_bytes gauge +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. +# TYPE go_memstats_alloc_bytes_total counter +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. +# TYPE go_memstats_buck_hash_sys_bytes gauge +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_frees_total counter +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. +# TYPE go_memstats_gc_sys_bytes gauge +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. +# TYPE go_memstats_heap_alloc_bytes gauge +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_idle_bytes gauge +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes +# TYPE go_memstats_heap_inuse_bytes gauge +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. +# TYPE go_memstats_heap_objects gauge +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. +# TYPE go_memstats_heap_released_bytes gauge +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. +# TYPE go_memstats_heap_sys_bytes gauge +# HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. +# TYPE go_memstats_last_gc_time_seconds gauge +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. +# TYPE go_memstats_mallocs_total counter +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. +# TYPE go_memstats_mcache_inuse_bytes gauge +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. +# TYPE go_memstats_mcache_sys_bytes gauge +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. +# TYPE go_memstats_mspan_inuse_bytes gauge +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. +# TYPE go_memstats_mspan_sys_bytes gauge +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. +# TYPE go_memstats_next_gc_bytes gauge +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. +# TYPE go_memstats_other_sys_bytes gauge +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. +# TYPE go_memstats_stack_inuse_bytes gauge +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. +# TYPE go_memstats_stack_sys_bytes gauge +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. +# TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge +# HELP go_threads Number of OS threads created. +# TYPE go_threads gauge +# HELP node_buddyinfo_blocks Count of free blocks according to size. +# TYPE node_buddyinfo_blocks gauge +node_buddyinfo_blocks{node="0",size="0",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="0",zone="DMA32"} 759 +node_buddyinfo_blocks{node="0",size="0",zone="Normal"} 4381 +node_buddyinfo_blocks{node="0",size="1",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="1",zone="DMA32"} 572 +node_buddyinfo_blocks{node="0",size="1",zone="Normal"} 1093 +node_buddyinfo_blocks{node="0",size="10",zone="DMA"} 3 +node_buddyinfo_blocks{node="0",size="10",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="10",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="2",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="2",zone="DMA32"} 791 +node_buddyinfo_blocks{node="0",size="2",zone="Normal"} 185 +node_buddyinfo_blocks{node="0",size="3",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="3",zone="DMA32"} 475 +node_buddyinfo_blocks{node="0",size="3",zone="Normal"} 1530 +node_buddyinfo_blocks{node="0",size="4",zone="DMA"} 2 +node_buddyinfo_blocks{node="0",size="4",zone="DMA32"} 194 +node_buddyinfo_blocks{node="0",size="4",zone="Normal"} 567 +node_buddyinfo_blocks{node="0",size="5",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="5",zone="DMA32"} 45 +node_buddyinfo_blocks{node="0",size="5",zone="Normal"} 102 +node_buddyinfo_blocks{node="0",size="6",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="6",zone="DMA32"} 12 +node_buddyinfo_blocks{node="0",size="6",zone="Normal"} 4 +node_buddyinfo_blocks{node="0",size="7",zone="DMA"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="7",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="8",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="8",zone="Normal"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="DMA"} 1 +node_buddyinfo_blocks{node="0",size="9",zone="DMA32"} 0 +node_buddyinfo_blocks{node="0",size="9",zone="Normal"} 0 +# HELP node_cpu_frequency_max_hertz Maximum CPU thread frequency in hertz. +# TYPE node_cpu_frequency_max_hertz gauge +node_cpu_frequency_max_hertz{cpu="0"} 2.445e+09 +node_cpu_frequency_max_hertz{cpu="1"} 2.445e+09 +node_cpu_frequency_max_hertz{cpu="2"} 2.445e+09 +node_cpu_frequency_max_hertz{cpu="3"} 2.445e+09 +# HELP node_exporter_build_info A metric with a constant '1' value labeled by version, revision, branch, goversion from which node_exporter was built, and the goos and goarch for the build. +# TYPE node_exporter_build_info gauge +# HELP node_os_info A metric with a constant '1' value labeled by build_id, id, id_like, image_id, image_version, name, pretty_name, variant, variant_id, version, version_codename, version_id. +# TYPE node_os_info gauge +node_os_info{build_id="",id="ubuntu",id_like="debian",image_id="",image_version="",name="Ubuntu",pretty_name="Ubuntu 20.04.2 LTS",variant="",variant_id="",version="20.04.2 LTS (Focal Fossa)",version_codename="focal",version_id="20.04"} 1 +# HELP node_os_version Metric containing the major.minor part of the OS version. +# TYPE node_os_version gauge +node_os_version{id="ubuntu",id_like="debian",name="Ubuntu"} 20.04 +# HELP node_scrape_collector_duration_seconds node_exporter: Duration of a collector scrape. +# TYPE node_scrape_collector_duration_seconds gauge +# HELP node_scrape_collector_success node_exporter: Whether a collector succeeded. +# TYPE node_scrape_collector_success gauge +node_scrape_collector_success{collector="boottime"} 1 +node_scrape_collector_success{collector="buddyinfo"} 1 +node_scrape_collector_success{collector="cpu"} 0 +node_scrape_collector_success{collector="cpufreq"} 1 +node_scrape_collector_success{collector="loadavg"} 1 +node_scrape_collector_success{collector="os"} 1 +node_scrape_collector_success{collector="textfile"} 1 +node_scrape_collector_success{collector="time"} 1 +node_scrape_collector_success{collector="xfrm"} 1 +node_scrape_collector_success{collector="zfs"} 0 +# HELP node_textfile_mtime_seconds Unixtime mtime of textfiles successfully read. +# TYPE node_textfile_mtime_seconds gauge +# HELP node_textfile_scrape_error 1 if there was an error opening or reading a file, 0 otherwise +# TYPE node_textfile_scrape_error gauge +node_textfile_scrape_error 0 +# HELP node_time_seconds System time in seconds since epoch (1970). +# TYPE node_time_seconds gauge +# HELP node_time_zone_offset_seconds System time zone offset in seconds. +# TYPE node_time_zone_offset_seconds gauge +# HELP node_xfrm_acquire_error_packets_total State hasn’t been fully acquired before use +# TYPE node_xfrm_acquire_error_packets_total counter +node_xfrm_acquire_error_packets_total 24532 +# HELP node_xfrm_fwd_hdr_error_packets_total Forward routing of a packet is not allowed +# TYPE node_xfrm_fwd_hdr_error_packets_total counter +node_xfrm_fwd_hdr_error_packets_total 6654 +# HELP node_xfrm_in_buffer_error_packets_total No buffer is left +# TYPE node_xfrm_in_buffer_error_packets_total counter +node_xfrm_in_buffer_error_packets_total 2 +# HELP node_xfrm_in_error_packets_total All errors not matched by other +# TYPE node_xfrm_in_error_packets_total counter +node_xfrm_in_error_packets_total 1 +# HELP node_xfrm_in_hdr_error_packets_total Header error +# TYPE node_xfrm_in_hdr_error_packets_total counter +node_xfrm_in_hdr_error_packets_total 4 +# HELP node_xfrm_in_no_pols_packets_total No policy is found for states e.g. Inbound SAs are correct but no SP is found +# TYPE node_xfrm_in_no_pols_packets_total counter +node_xfrm_in_no_pols_packets_total 65432 +# HELP node_xfrm_in_no_states_packets_total No state is found i.e. Either inbound SPI, address, or IPsec protocol at SA is wrong +# TYPE node_xfrm_in_no_states_packets_total counter +node_xfrm_in_no_states_packets_total 3 +# HELP node_xfrm_in_pol_block_packets_total Policy discards +# TYPE node_xfrm_in_pol_block_packets_total counter +node_xfrm_in_pol_block_packets_total 100 +# HELP node_xfrm_in_pol_error_packets_total Policy error +# TYPE node_xfrm_in_pol_error_packets_total counter +node_xfrm_in_pol_error_packets_total 10000 +# HELP node_xfrm_in_state_expired_packets_total State is expired +# TYPE node_xfrm_in_state_expired_packets_total counter +node_xfrm_in_state_expired_packets_total 7 +# HELP node_xfrm_in_state_invalid_packets_total State is invalid +# TYPE node_xfrm_in_state_invalid_packets_total counter +node_xfrm_in_state_invalid_packets_total 55555 +# HELP node_xfrm_in_state_mismatch_packets_total State has mismatch option e.g. UDP encapsulation type is mismatch +# TYPE node_xfrm_in_state_mismatch_packets_total counter +node_xfrm_in_state_mismatch_packets_total 23451 +# HELP node_xfrm_in_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_in_state_mode_error_packets_total counter +node_xfrm_in_state_mode_error_packets_total 100 +# HELP node_xfrm_in_state_proto_error_packets_total Transformation protocol specific error e.g. SA key is wrong +# TYPE node_xfrm_in_state_proto_error_packets_total counter +node_xfrm_in_state_proto_error_packets_total 40 +# HELP node_xfrm_in_state_seq_error_packets_total Sequence error i.e. Sequence number is out of window +# TYPE node_xfrm_in_state_seq_error_packets_total counter +node_xfrm_in_state_seq_error_packets_total 6000 +# HELP node_xfrm_in_tmpl_mismatch_packets_total No matching template for states e.g. Inbound SAs are correct but SP rule is wrong +# TYPE node_xfrm_in_tmpl_mismatch_packets_total counter +node_xfrm_in_tmpl_mismatch_packets_total 51 +# HELP node_xfrm_out_bundle_check_error_packets_total Bundle check error +# TYPE node_xfrm_out_bundle_check_error_packets_total counter +node_xfrm_out_bundle_check_error_packets_total 555 +# HELP node_xfrm_out_bundle_gen_error_packets_total Bundle generation error +# TYPE node_xfrm_out_bundle_gen_error_packets_total counter +node_xfrm_out_bundle_gen_error_packets_total 43321 +# HELP node_xfrm_out_error_packets_total All errors which is not matched others +# TYPE node_xfrm_out_error_packets_total counter +node_xfrm_out_error_packets_total 1e+06 +# HELP node_xfrm_out_no_states_packets_total No state is found +# TYPE node_xfrm_out_no_states_packets_total counter +node_xfrm_out_no_states_packets_total 869 +# HELP node_xfrm_out_pol_block_packets_total Policy discards +# TYPE node_xfrm_out_pol_block_packets_total counter +node_xfrm_out_pol_block_packets_total 43456 +# HELP node_xfrm_out_pol_dead_packets_total Policy is dead +# TYPE node_xfrm_out_pol_dead_packets_total counter +node_xfrm_out_pol_dead_packets_total 7656 +# HELP node_xfrm_out_pol_error_packets_total Policy error +# TYPE node_xfrm_out_pol_error_packets_total counter +node_xfrm_out_pol_error_packets_total 1454 +# HELP node_xfrm_out_state_expired_packets_total State is expired +# TYPE node_xfrm_out_state_expired_packets_total counter +node_xfrm_out_state_expired_packets_total 565 +# HELP node_xfrm_out_state_invalid_packets_total State is invalid, perhaps expired +# TYPE node_xfrm_out_state_invalid_packets_total counter +node_xfrm_out_state_invalid_packets_total 28765 +# HELP node_xfrm_out_state_mode_error_packets_total Transformation mode specific error +# TYPE node_xfrm_out_state_mode_error_packets_total counter +node_xfrm_out_state_mode_error_packets_total 8 +# HELP node_xfrm_out_state_proto_error_packets_total Transformation protocol specific error +# TYPE node_xfrm_out_state_proto_error_packets_total counter +node_xfrm_out_state_proto_error_packets_total 4542 +# HELP node_xfrm_out_state_seq_error_packets_total Sequence error i.e. Sequence number overflow +# TYPE node_xfrm_out_state_seq_error_packets_total counter +node_xfrm_out_state_seq_error_packets_total 543 +# HELP process_open_fds Number of open file descriptors. +# TYPE process_open_fds gauge +# HELP promhttp_metric_handler_errors_total Total number of internal errors encountered by the promhttp metric handler. +# TYPE promhttp_metric_handler_errors_total counter +promhttp_metric_handler_errors_total{cause="encoding"} 0 +promhttp_metric_handler_errors_total{cause="gathering"} 0 +# HELP promhttp_metric_handler_requests_in_flight Current number of scrapes being served. +# TYPE promhttp_metric_handler_requests_in_flight gauge +promhttp_metric_handler_requests_in_flight 1 +# HELP promhttp_metric_handler_requests_total Total number of scrapes by HTTP status code. +# TYPE promhttp_metric_handler_requests_total counter +promhttp_metric_handler_requests_total{code="200"} 0 +promhttp_metric_handler_requests_total{code="500"} 0 +promhttp_metric_handler_requests_total{code="503"} 0 +# HELP testmetric1_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_1 untyped +testmetric1_1{foo="bar"} 10 +# HELP testmetric1_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics1.prom +# TYPE testmetric1_2 untyped +testmetric1_2{foo="baz"} 20 +# HELP testmetric2_1 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_1 untyped +testmetric2_1{foo="bar"} 30 +# HELP testmetric2_2 Metric read from collector/fixtures/textfile/two_metric_files/metrics2.prom +# TYPE testmetric2_2 untyped +testmetric2_2{foo="baz"} 40 diff --git a/collector/fixtures/e2e-output.txt b/collector/fixtures/e2e-output.txt index d52cb99d04..8598f447ca 100644 --- a/collector/fixtures/e2e-output.txt +++ b/collector/fixtures/e2e-output.txt @@ -1,55 +1,59 @@ -# HELP go_gc_duration_seconds A summary of the pause duration of garbage collection cycles. +# HELP go_gc_duration_seconds A summary of the wall-time pause (stop-the-world) duration in garbage collection cycles. # TYPE go_gc_duration_seconds summary +# HELP go_gc_gogc_percent Heap size target percentage configured by the user, otherwise 100. This value is set by the GOGC environment variable, and the runtime/debug.SetGCPercent function. Sourced from /gc/gogc:percent +# TYPE go_gc_gogc_percent gauge +# HELP go_gc_gomemlimit_bytes Go runtime memory limit configured by the user, otherwise math.MaxInt64. This value is set by the GOMEMLIMIT environment variable, and the runtime/debug.SetMemoryLimit function. Sourced from /gc/gomemlimit:bytes +# TYPE go_gc_gomemlimit_bytes gauge # HELP go_goroutines Number of goroutines that currently exist. # TYPE go_goroutines gauge # HELP go_info Information about the Go environment. # TYPE go_info gauge -# HELP go_memstats_alloc_bytes Number of bytes allocated and still in use. +# HELP go_memstats_alloc_bytes Number of bytes allocated in heap and currently in use. Equals to /memory/classes/heap/objects:bytes. # TYPE go_memstats_alloc_bytes gauge -# HELP go_memstats_alloc_bytes_total Total number of bytes allocated, even if freed. +# HELP go_memstats_alloc_bytes_total Total number of bytes allocated in heap until now, even if released already. Equals to /gc/heap/allocs:bytes. # TYPE go_memstats_alloc_bytes_total counter -# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. +# HELP go_memstats_buck_hash_sys_bytes Number of bytes used by the profiling bucket hash table. Equals to /memory/classes/profiling/buckets:bytes. # TYPE go_memstats_buck_hash_sys_bytes gauge -# HELP go_memstats_frees_total Total number of frees. +# HELP go_memstats_frees_total Total number of heap objects frees. Equals to /gc/heap/frees:objects + /gc/heap/tiny/allocs:objects. # TYPE go_memstats_frees_total counter -# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. +# HELP go_memstats_gc_sys_bytes Number of bytes used for garbage collection system metadata. Equals to /memory/classes/metadata/other:bytes. # TYPE go_memstats_gc_sys_bytes gauge -# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and still in use. +# HELP go_memstats_heap_alloc_bytes Number of heap bytes allocated and currently in use, same as go_memstats_alloc_bytes. Equals to /memory/classes/heap/objects:bytes. # TYPE go_memstats_heap_alloc_bytes gauge -# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. +# HELP go_memstats_heap_idle_bytes Number of heap bytes waiting to be used. Equals to /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. # TYPE go_memstats_heap_idle_bytes gauge -# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. +# HELP go_memstats_heap_inuse_bytes Number of heap bytes that are in use. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes # TYPE go_memstats_heap_inuse_bytes gauge -# HELP go_memstats_heap_objects Number of allocated objects. +# HELP go_memstats_heap_objects Number of currently allocated objects. Equals to /gc/heap/objects:objects. # TYPE go_memstats_heap_objects gauge -# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. +# HELP go_memstats_heap_released_bytes Number of heap bytes released to OS. Equals to /memory/classes/heap/released:bytes. # TYPE go_memstats_heap_released_bytes gauge -# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. +# HELP go_memstats_heap_sys_bytes Number of heap bytes obtained from system. Equals to /memory/classes/heap/objects:bytes + /memory/classes/heap/unused:bytes + /memory/classes/heap/released:bytes + /memory/classes/heap/free:bytes. # TYPE go_memstats_heap_sys_bytes gauge # HELP go_memstats_last_gc_time_seconds Number of seconds since 1970 of last garbage collection. # TYPE go_memstats_last_gc_time_seconds gauge -# HELP go_memstats_lookups_total Total number of pointer lookups. -# TYPE go_memstats_lookups_total counter -# HELP go_memstats_mallocs_total Total number of mallocs. +# HELP go_memstats_mallocs_total Total number of heap objects allocated, both live and gc-ed. Semantically a counter version for go_memstats_heap_objects gauge. Equals to /gc/heap/allocs:objects + /gc/heap/tiny/allocs:objects. # TYPE go_memstats_mallocs_total counter -# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. +# HELP go_memstats_mcache_inuse_bytes Number of bytes in use by mcache structures. Equals to /memory/classes/metadata/mcache/inuse:bytes. # TYPE go_memstats_mcache_inuse_bytes gauge -# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. +# HELP go_memstats_mcache_sys_bytes Number of bytes used for mcache structures obtained from system. Equals to /memory/classes/metadata/mcache/inuse:bytes + /memory/classes/metadata/mcache/free:bytes. # TYPE go_memstats_mcache_sys_bytes gauge -# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. +# HELP go_memstats_mspan_inuse_bytes Number of bytes in use by mspan structures. Equals to /memory/classes/metadata/mspan/inuse:bytes. # TYPE go_memstats_mspan_inuse_bytes gauge -# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. +# HELP go_memstats_mspan_sys_bytes Number of bytes used for mspan structures obtained from system. Equals to /memory/classes/metadata/mspan/inuse:bytes + /memory/classes/metadata/mspan/free:bytes. # TYPE go_memstats_mspan_sys_bytes gauge -# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. +# HELP go_memstats_next_gc_bytes Number of heap bytes when next garbage collection will take place. Equals to /gc/heap/goal:bytes. # TYPE go_memstats_next_gc_bytes gauge -# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. +# HELP go_memstats_other_sys_bytes Number of bytes used for other system allocations. Equals to /memory/classes/other:bytes. # TYPE go_memstats_other_sys_bytes gauge -# HELP go_memstats_stack_inuse_bytes Number of bytes in use by the stack allocator. +# HELP go_memstats_stack_inuse_bytes Number of bytes obtained from system for stack allocator in non-CGO environments. Equals to /memory/classes/heap/stacks:bytes. # TYPE go_memstats_stack_inuse_bytes gauge -# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. +# HELP go_memstats_stack_sys_bytes Number of bytes obtained from system for stack allocator. Equals to /memory/classes/heap/stacks:bytes + /memory/classes/os-stacks:bytes. # TYPE go_memstats_stack_sys_bytes gauge -# HELP go_memstats_sys_bytes Number of bytes obtained from system. +# HELP go_memstats_sys_bytes Number of bytes obtained from system. Equals to /memory/classes/total:byte. # TYPE go_memstats_sys_bytes gauge +# HELP go_sched_gomaxprocs_threads The current runtime.GOMAXPROCS setting, or the number of operating system threads that can execute user-level Go code simultaneously. Sourced from /sched/gomaxprocs:threads +# TYPE go_sched_gomaxprocs_threads gauge # HELP go_threads Number of OS threads created. # TYPE go_threads gauge # HELP node_arp_entries ARP entries by device @@ -161,6 +165,14 @@ node_btrfs_allocation_ratio{block_group_type="metadata",mode="raid1",uuid="0abb2 node_btrfs_allocation_ratio{block_group_type="metadata",mode="raid6",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 2 node_btrfs_allocation_ratio{block_group_type="system",mode="raid1",uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 2 node_btrfs_allocation_ratio{block_group_type="system",mode="raid6",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 2 +# HELP node_btrfs_commit_seconds_total Sum of the duration of all commits, in seconds. +# TYPE node_btrfs_commit_seconds_total counter +node_btrfs_commit_seconds_total{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 47836.09 +node_btrfs_commit_seconds_total{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 +# HELP node_btrfs_commits_total The total number of commits that have occurred. +# TYPE node_btrfs_commits_total counter +node_btrfs_commits_total{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 258051 +node_btrfs_commits_total{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 # HELP node_btrfs_device_size_bytes Size of a device that is part of the filesystem. # TYPE node_btrfs_device_size_bytes gauge node_btrfs_device_size_bytes{device="loop22",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 1.073741824e+10 @@ -177,6 +189,14 @@ node_btrfs_global_rsv_size_bytes{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 1. # TYPE node_btrfs_info gauge node_btrfs_info{label="",uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 1 node_btrfs_info{label="fixture",uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 1 +# HELP node_btrfs_last_commit_seconds Duration of the most recent commit, in seconds. +# TYPE node_btrfs_last_commit_seconds gauge +node_btrfs_last_commit_seconds{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 1 +node_btrfs_last_commit_seconds{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 +# HELP node_btrfs_max_commit_seconds Duration of the slowest commit, in seconds. +# TYPE node_btrfs_max_commit_seconds gauge +node_btrfs_max_commit_seconds{uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 51.462 +node_btrfs_max_commit_seconds{uuid="7f07c59f-6136-449c-ab87-e1cf2328731b"} 0 # HELP node_btrfs_reserved_bytes Amount of space reserved for a data type # TYPE node_btrfs_reserved_bytes gauge node_btrfs_reserved_bytes{block_group_type="data",uuid="0abb23a9-579b-43e6-ad30-227ef47fcb9d"} 0 @@ -490,21 +510,21 @@ node_disk_flush_requests_time_seconds_total{device="sdc"} 1.944 node_disk_flush_requests_total{device="sdc"} 1555 # HELP node_disk_info Info of /sys/block/. # TYPE node_disk_info gauge -node_disk_info{device="dm-0",major="252",minor="0",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-1",major="252",minor="1",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-2",major="252",minor="2",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-3",major="252",minor="3",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-4",major="252",minor="4",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="dm-5",major="252",minor="5",model="",path="",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0",major="179",minor="0",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0p1",major="179",minor="1",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="mmcblk0p2",major="179",minor="2",model="",path="platform-df2969f3.mmc",revision="",serial="",wwn=""} 1 -node_disk_info{device="nvme0n1",major="259",minor="0",model="SAMSUNG EHFTF55LURSY-000Y9",path="pci-0000:02:00.0-nvme-1",revision="4NBTUY95",serial="S252B6CU1HG3M1",wwn="eui.p3vbbiejx5aae2r3"} 1 -node_disk_info{device="sda",major="8",minor="0",model="TOSHIBA_KSDB4U86",path="pci-0000:3b:00.0-sas-phy7-lun-0",revision="0102",serial="2160A0D5FVGG",wwn="0x7c72382b8de36a64"} 1 -node_disk_info{device="sdb",major="8",minor="16",model="SuperMicro_SSD",path="pci-0000:00:1f.2-ata-1",revision="0R",serial="SMC0E1B87ABBB16BD84E",wwn="0xe1b87abbb16bd84e"} 1 -node_disk_info{device="sdc",major="8",minor="32",model="INTEL_SSDS9X9SI0",path="pci-0000:00:1f.2-ata-4",revision="0100",serial="3EWB5Y25CWQWA7EH1U",wwn="0x58907ddc573a5de"} 1 -node_disk_info{device="sr0",major="11",minor="0",model="Virtual_CDROM0",path="pci-0000:00:14.0-usb-0:1.1:1.0-scsi-0:0:0:0",revision="1.00",serial="AAAABBBBCCCC1",wwn=""} 1 -node_disk_info{device="vda",major="254",minor="0",model="",path="pci-0000:00:06.0",revision="",serial="",wwn=""} 1 +node_disk_info{device="dm-0",major="252",minor="0",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-1",major="252",minor="1",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-2",major="252",minor="2",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-3",major="252",minor="3",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-4",major="252",minor="4",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="dm-5",major="252",minor="5",model="",path="",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0",major="179",minor="0",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0p1",major="179",minor="1",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="mmcblk0p2",major="179",minor="2",model="",path="platform-df2969f3.mmc",revision="",rotational="0",serial="",wwn=""} 1 +node_disk_info{device="nvme0n1",major="259",minor="0",model="SAMSUNG EHFTF55LURSY-000Y9",path="pci-0000:02:00.0-nvme-1",revision="4NBTUY95",rotational="0",serial="S252B6CU1HG3M1",wwn="eui.p3vbbiejx5aae2r3"} 1 +node_disk_info{device="sda",major="8",minor="0",model="TOSHIBA_KSDB4U86",path="pci-0000:3b:00.0-sas-phy7-lun-0",revision="0102",rotational="1",serial="2160A0D5FVGG",wwn="0x7c72382b8de36a64"} 1 +node_disk_info{device="sdb",major="8",minor="16",model="SuperMicro_SSD",path="pci-0000:00:1f.2-ata-1",revision="0R",rotational="0",serial="SMC0E1B87ABBB16BD84E",wwn="0xe1b87abbb16bd84e"} 1 +node_disk_info{device="sdc",major="8",minor="32",model="INTEL_SSDS9X9SI0",path="pci-0000:00:1f.2-ata-4",revision="0100",rotational="0",serial="3EWB5Y25CWQWA7EH1U",wwn="0x58907ddc573a5de"} 1 +node_disk_info{device="sr0",major="11",minor="0",model="Virtual_CDROM0",path="pci-0000:00:14.0-usb-0:1.1:1.0-scsi-0:0:0:0",revision="1.00",rotational="0",serial="AAAABBBBCCCC1",wwn=""} 1 +node_disk_info{device="vda",major="254",minor="0",model="",path="pci-0000:00:06.0",revision="",rotational="0",serial="",wwn=""} 1 # HELP node_disk_io_now The number of I/Os currently in progress. # TYPE node_disk_io_now gauge node_disk_io_now{device="dm-0"} 0 @@ -873,6 +893,10 @@ node_hwmon_fan_target_rpm{chip="nct6779",sensor="fan2"} 27000 # HELP node_hwmon_fan_tolerance Hardware monitor fan element tolerance # TYPE node_hwmon_fan_tolerance gauge node_hwmon_fan_tolerance{chip="nct6779",sensor="fan2"} 0 +# HELP node_hwmon_freq_freq_mhz Hardware monitor for GPU frequency in MHz +# TYPE node_hwmon_freq_freq_mhz gauge +node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="mclk"} 300 +node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="sclk"} 214 # HELP node_hwmon_in_alarm Hardware sensor alarm status (in) # TYPE node_hwmon_in_alarm gauge node_hwmon_in_alarm{chip="nct6779",sensor="in0"} 0 @@ -986,8 +1010,10 @@ node_hwmon_pwm_weight_temp_step_tol{chip="nct6779",sensor="pwm1"} 0 # TYPE node_hwmon_sensor_label gauge node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp1"} 1 node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp2"} 1 -node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side ",sensor="fan1"} 1 -node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side ",sensor="fan2"} 1 +node_hwmon_sensor_label{chip="hwmon4",label="mclk",sensor="freq2"} 1 +node_hwmon_sensor_label{chip="hwmon4",label="sclk",sensor="freq1"} 1 +node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side",sensor="fan1"} 1 +node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side",sensor="fan2"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 0",sensor="temp2"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 1",sensor="temp3"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 2",sensor="temp4"} 1 @@ -2344,6 +2370,9 @@ node_netstat_TcpExt_SyncookiesSent 0 # HELP node_netstat_TcpExt_TCPOFOQueue Statistic TcpExtTCPOFOQueue. # TYPE node_netstat_TcpExt_TCPOFOQueue untyped node_netstat_TcpExt_TCPOFOQueue 42 +# HELP node_netstat_TcpExt_TCPRcvQDrop Statistic TcpExtTCPRcvQDrop. +# TYPE node_netstat_TcpExt_TCPRcvQDrop untyped +node_netstat_TcpExt_TCPRcvQDrop 131 # HELP node_netstat_TcpExt_TCPTimeouts Statistic TcpExtTCPTimeouts. # TYPE node_netstat_TcpExt_TCPTimeouts untyped node_netstat_TcpExt_TCPTimeouts 115 @@ -2852,6 +2881,9 @@ node_pressure_io_stalled_seconds_total 159.229614 # HELP node_pressure_io_waiting_seconds_total Total time in seconds that processes have waited due to IO congestion # TYPE node_pressure_io_waiting_seconds_total counter node_pressure_io_waiting_seconds_total 159.886802 +# HELP node_pressure_irq_stalled_seconds_total Total time in seconds no process could make progress due to IRQ congestion +# TYPE node_pressure_irq_stalled_seconds_total counter +node_pressure_irq_stalled_seconds_total 0.008494 # HELP node_pressure_memory_stalled_seconds_total Total time in seconds no process could make progress due to memory congestion # TYPE node_pressure_memory_stalled_seconds_total counter node_pressure_memory_stalled_seconds_total 0 @@ -3779,6 +3811,9 @@ node_zfs_arc_l2_writes_lock_retry 0 # HELP node_zfs_arc_l2_writes_sent kstat.zfs.misc.arcstats.l2_writes_sent # TYPE node_zfs_arc_l2_writes_sent untyped node_zfs_arc_l2_writes_sent 0 +# HELP node_zfs_arc_memory_available_bytes kstat.zfs.misc.arcstats.memory_available_bytes +# TYPE node_zfs_arc_memory_available_bytes untyped +node_zfs_arc_memory_available_bytes -9.223372036854776e+17 # HELP node_zfs_arc_memory_direct_count kstat.zfs.misc.arcstats.memory_direct_count # TYPE node_zfs_arc_memory_direct_count untyped node_zfs_arc_memory_direct_count 542 @@ -4308,108 +4343,139 @@ node_zfs_zil_zil_itx_needcopy_count 0 # TYPE node_zfs_zpool_dataset_nread untyped node_zfs_zpool_dataset_nread{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nread{dataset="pool1/dataset1",zpool="pool1"} 28 +node_zfs_zpool_dataset_nread{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nread{dataset="pool3/dataset with space",zpool="pool3"} 28 node_zfs_zpool_dataset_nread{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nread{dataset="poolz1/dataset1",zpool="poolz1"} 28 # HELP node_zfs_zpool_dataset_nunlinked kstat.zfs.misc.objset.nunlinked # TYPE node_zfs_zpool_dataset_nunlinked untyped node_zfs_zpool_dataset_nunlinked{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nunlinked{dataset="pool1/dataset1",zpool="pool1"} 3 +node_zfs_zpool_dataset_nunlinked{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nunlinked{dataset="pool3/dataset with space",zpool="pool3"} 3 node_zfs_zpool_dataset_nunlinked{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nunlinked{dataset="poolz1/dataset1",zpool="poolz1"} 14 # HELP node_zfs_zpool_dataset_nunlinks kstat.zfs.misc.objset.nunlinks # TYPE node_zfs_zpool_dataset_nunlinks untyped node_zfs_zpool_dataset_nunlinks{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nunlinks{dataset="pool1/dataset1",zpool="pool1"} 3 +node_zfs_zpool_dataset_nunlinks{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nunlinks{dataset="pool3/dataset with space",zpool="pool3"} 3 node_zfs_zpool_dataset_nunlinks{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nunlinks{dataset="poolz1/dataset1",zpool="poolz1"} 14 # HELP node_zfs_zpool_dataset_nwritten kstat.zfs.misc.objset.nwritten # TYPE node_zfs_zpool_dataset_nwritten untyped node_zfs_zpool_dataset_nwritten{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_nwritten{dataset="pool1/dataset1",zpool="pool1"} 12302 +node_zfs_zpool_dataset_nwritten{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_nwritten{dataset="pool3/dataset with space",zpool="pool3"} 12302 node_zfs_zpool_dataset_nwritten{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_nwritten{dataset="poolz1/dataset1",zpool="poolz1"} 32806 # HELP node_zfs_zpool_dataset_reads kstat.zfs.misc.objset.reads # TYPE node_zfs_zpool_dataset_reads untyped node_zfs_zpool_dataset_reads{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_reads{dataset="pool1/dataset1",zpool="pool1"} 2 +node_zfs_zpool_dataset_reads{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_reads{dataset="pool3/dataset with space",zpool="pool3"} 2 node_zfs_zpool_dataset_reads{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_reads{dataset="poolz1/dataset1",zpool="poolz1"} 2 # HELP node_zfs_zpool_dataset_writes kstat.zfs.misc.objset.writes # TYPE node_zfs_zpool_dataset_writes untyped node_zfs_zpool_dataset_writes{dataset="pool1",zpool="pool1"} 0 node_zfs_zpool_dataset_writes{dataset="pool1/dataset1",zpool="pool1"} 4 +node_zfs_zpool_dataset_writes{dataset="pool3",zpool="pool3"} 0 +node_zfs_zpool_dataset_writes{dataset="pool3/dataset with space",zpool="pool3"} 4 node_zfs_zpool_dataset_writes{dataset="poolz1",zpool="poolz1"} 0 node_zfs_zpool_dataset_writes{dataset="poolz1/dataset1",zpool="poolz1"} 10 # HELP node_zfs_zpool_nread kstat.zfs.misc.io.nread # TYPE node_zfs_zpool_nread untyped node_zfs_zpool_nread{zpool="pool1"} 1.88416e+06 +node_zfs_zpool_nread{zpool="pool3"} 1.88416e+06 node_zfs_zpool_nread{zpool="poolz1"} 2.82624e+06 # HELP node_zfs_zpool_nwritten kstat.zfs.misc.io.nwritten # TYPE node_zfs_zpool_nwritten untyped node_zfs_zpool_nwritten{zpool="pool1"} 3.206144e+06 +node_zfs_zpool_nwritten{zpool="pool3"} 3.206144e+06 node_zfs_zpool_nwritten{zpool="poolz1"} 2.680501248e+09 # HELP node_zfs_zpool_rcnt kstat.zfs.misc.io.rcnt # TYPE node_zfs_zpool_rcnt untyped node_zfs_zpool_rcnt{zpool="pool1"} 0 +node_zfs_zpool_rcnt{zpool="pool3"} 0 node_zfs_zpool_rcnt{zpool="poolz1"} 0 # HELP node_zfs_zpool_reads kstat.zfs.misc.io.reads # TYPE node_zfs_zpool_reads untyped node_zfs_zpool_reads{zpool="pool1"} 22 +node_zfs_zpool_reads{zpool="pool3"} 22 node_zfs_zpool_reads{zpool="poolz1"} 33 # HELP node_zfs_zpool_rlentime kstat.zfs.misc.io.rlentime # TYPE node_zfs_zpool_rlentime untyped node_zfs_zpool_rlentime{zpool="pool1"} 1.04112268e+08 +node_zfs_zpool_rlentime{zpool="pool3"} 1.04112268e+08 node_zfs_zpool_rlentime{zpool="poolz1"} 6.472105124093e+12 # HELP node_zfs_zpool_rtime kstat.zfs.misc.io.rtime # TYPE node_zfs_zpool_rtime untyped node_zfs_zpool_rtime{zpool="pool1"} 2.4168078e+07 +node_zfs_zpool_rtime{zpool="pool3"} 2.4168078e+07 node_zfs_zpool_rtime{zpool="poolz1"} 9.82909164e+09 # HELP node_zfs_zpool_rupdate kstat.zfs.misc.io.rupdate # TYPE node_zfs_zpool_rupdate untyped node_zfs_zpool_rupdate{zpool="pool1"} 7.921048984922e+13 +node_zfs_zpool_rupdate{zpool="pool3"} 7.921048984922e+13 node_zfs_zpool_rupdate{zpool="poolz1"} 1.10734831944501e+14 # HELP node_zfs_zpool_state kstat.zfs.misc.state # TYPE node_zfs_zpool_state gauge node_zfs_zpool_state{state="degraded",zpool="pool1"} 0 node_zfs_zpool_state{state="degraded",zpool="pool2"} 0 +node_zfs_zpool_state{state="degraded",zpool="pool3"} 0 node_zfs_zpool_state{state="degraded",zpool="poolz1"} 1 node_zfs_zpool_state{state="faulted",zpool="pool1"} 0 node_zfs_zpool_state{state="faulted",zpool="pool2"} 0 +node_zfs_zpool_state{state="faulted",zpool="pool3"} 0 node_zfs_zpool_state{state="faulted",zpool="poolz1"} 0 node_zfs_zpool_state{state="offline",zpool="pool1"} 0 node_zfs_zpool_state{state="offline",zpool="pool2"} 0 +node_zfs_zpool_state{state="offline",zpool="pool3"} 0 node_zfs_zpool_state{state="offline",zpool="poolz1"} 0 node_zfs_zpool_state{state="online",zpool="pool1"} 1 node_zfs_zpool_state{state="online",zpool="pool2"} 0 +node_zfs_zpool_state{state="online",zpool="pool3"} 1 node_zfs_zpool_state{state="online",zpool="poolz1"} 0 node_zfs_zpool_state{state="removed",zpool="pool1"} 0 node_zfs_zpool_state{state="removed",zpool="pool2"} 0 +node_zfs_zpool_state{state="removed",zpool="pool3"} 0 node_zfs_zpool_state{state="removed",zpool="poolz1"} 0 node_zfs_zpool_state{state="suspended",zpool="pool1"} 0 node_zfs_zpool_state{state="suspended",zpool="pool2"} 1 +node_zfs_zpool_state{state="suspended",zpool="pool3"} 0 node_zfs_zpool_state{state="suspended",zpool="poolz1"} 0 node_zfs_zpool_state{state="unavail",zpool="pool1"} 0 node_zfs_zpool_state{state="unavail",zpool="pool2"} 0 +node_zfs_zpool_state{state="unavail",zpool="pool3"} 0 node_zfs_zpool_state{state="unavail",zpool="poolz1"} 0 # HELP node_zfs_zpool_wcnt kstat.zfs.misc.io.wcnt # TYPE node_zfs_zpool_wcnt untyped node_zfs_zpool_wcnt{zpool="pool1"} 0 +node_zfs_zpool_wcnt{zpool="pool3"} 0 node_zfs_zpool_wcnt{zpool="poolz1"} 0 # HELP node_zfs_zpool_wlentime kstat.zfs.misc.io.wlentime # TYPE node_zfs_zpool_wlentime untyped node_zfs_zpool_wlentime{zpool="pool1"} 1.04112268e+08 +node_zfs_zpool_wlentime{zpool="pool3"} 1.04112268e+08 node_zfs_zpool_wlentime{zpool="poolz1"} 6.472105124093e+12 # HELP node_zfs_zpool_writes kstat.zfs.misc.io.writes # TYPE node_zfs_zpool_writes untyped node_zfs_zpool_writes{zpool="pool1"} 132 +node_zfs_zpool_writes{zpool="pool3"} 132 node_zfs_zpool_writes{zpool="poolz1"} 25294 # HELP node_zfs_zpool_wtime kstat.zfs.misc.io.wtime # TYPE node_zfs_zpool_wtime untyped node_zfs_zpool_wtime{zpool="pool1"} 7.155162e+06 +node_zfs_zpool_wtime{zpool="pool3"} 7.155162e+06 node_zfs_zpool_wtime{zpool="poolz1"} 9.673715628e+09 # HELP node_zfs_zpool_wupdate kstat.zfs.misc.io.wupdate # TYPE node_zfs_zpool_wupdate untyped node_zfs_zpool_wupdate{zpool="pool1"} 7.9210489694949e+13 +node_zfs_zpool_wupdate{zpool="pool3"} 7.9210489694949e+13 node_zfs_zpool_wupdate{zpool="poolz1"} 1.10734831833266e+14 # HELP node_zoneinfo_high_pages Zone watermark pages_high # TYPE node_zoneinfo_high_pages gauge @@ -4586,6 +4652,10 @@ node_zoneinfo_spanned_pages{node="0",zone="Normal"} 7.806976e+06 # TYPE process_cpu_seconds_total counter # HELP process_max_fds Maximum number of open file descriptors. # TYPE process_max_fds gauge +# HELP process_network_receive_bytes_total Number of bytes received by the process over the network. +# TYPE process_network_receive_bytes_total counter +# HELP process_network_transmit_bytes_total Number of bytes sent by the process over the network. +# TYPE process_network_transmit_bytes_total counter # HELP process_open_fds Number of open file descriptors. # TYPE process_open_fds gauge # HELP process_resident_memory_bytes Resident memory size in bytes. diff --git a/collector/fixtures/proc/1/mountinfo b/collector/fixtures/proc/1/mountinfo new file mode 100644 index 0000000000..11c50a6fb0 --- /dev/null +++ b/collector/fixtures/proc/1/mountinfo @@ -0,0 +1,31 @@ +24 29 0:22 / /sys rw,nosuid,nodev,noexec,relatime shared:7 - sysfs sysfs rw +25 29 0:23 / /proc rw,nosuid,nodev,noexec,relatime shared:13 - proc proc rw +26 29 0:5 / /dev rw,nosuid,relatime shared:2 - devtmpfs udev rw,size=7978892k,nr_inodes=1994723,mode=755 +27 26 0:24 / /dev/pts rw,nosuid,noexec,relatime shared:3 - devpts devpts rw,gid=5,mode=620,ptmxmode=000 +28 29 0:25 / /run rw,nosuid,relatime shared:5 - tmpfs tmpfs rw,size=1617716k,mode=755 +29 1 259:2 / / rw,relatime shared:1 - ext4 /dev/dm-2 errors=remount-ro,data=ordered +30 24 0:6 / /sys/kernel/security rw,nosuid,nodev,noexec,relatime shared:8 - securityfs securityfs rw +31 26 0:26 / /dev/shm rw,nosuid,nodev shared:4 - tmpfs tmpfs rw,inode64 +32 28 0:27 / /run/lock rw,nosuid,nodev,noexec,relatime shared:6 - tmpfs tmpfs rw,size=5120k +33 24 0:28 / /sys/fs/cgroup ro,nosuid,nodev,noexec shared:9 - tmpfs tmpfs ro,mode=755 +34 31 0:24 / /sys/fs/cgroup/systemd rw,nosuid,nodev,noexec,relatime shared:10 - cgroup cgroup rw,xattr,release_agent=/lib/systemd/systemd-cgroups-agent,name=systemd +35 32 0:25 / /sys/fs/pstore rw,nosuid,nodev,noexec,relatime shared:11 - pstore pstore rw +36 33 0:26 / /sys/fs/cgroup/cpuset rw,nosuid,nodev,noexec,relatime shared:12 - cgroup cgroup rw,cpuset +37 34 0:27 / /sys/fs/cgroup/cpu,cpuacct rw,nosuid,nodev,noexec,relatime shared:14 - cgroup cgroup rw,cpu,cpuacct +38 35 0:28 / /sys/fs/cgroup/devices rw,nosuid,nodev,noexec,relatime shared:16 - cgroup cgroup rw,devices +39 36 0:29 / /sys/fs/cgroup/freezer rw,nosuid,nodev,noexec,relatime shared:17 - cgroup cgroup rw,freezer +40 37 0:30 / /sys/fs/cgroup/net_cls,net_prio rw,nosuid,nodev,noexec,relatime shared:18 - cgroup cgroup rw,net_cls,net_prio +41 38 0:31 / /sys/fs/cgroup/blkio rw,nosuid,nodev,noexec,relatime shared:19 - cgroup cgroup rw,blkio +42 39 0:32 / /sys/fs/cgroup/perf_event rw,nosuid,nodev,noexec,relatime shared:20 - cgroup cgroup rw,perf_event +43 40 0:33 / /proc/sys/fs/binfmt_misc rw,relatime shared:21 - systemd-1 autofs rw,fd=22,pgrp=1,timeout=300,minproto=5,maxproto=5,direct +44 41 0:34 / /dev/mqueue rw,relatime shared:22 - mqueue mqueue rw +45 42 0:35 / /sys/kernel/debug rw,relatime shared:23 - debugfs debugfs rw +46 43 0:36 / /dev/hugepages rw,relatime shared:24 - hugetlbfs hugetlbfs rw +47 44 0:37 / /sys/fs/fuse/connections rw,relatime shared:25 - fusectl fusectl rw +48 45 260:3 / /boot rw,relatime shared:92 - ext2 /dev/sda3 rw +49 46 0:39 / /run/rpc_pipefs rw,relatime shared:27 - rpc_pipefs rpc_pipefs rw +265 37 0:41 / /proc/sys/fs/binfmt_misc rw,nosuid,nodev,noexec,relatime shared:94 - binfmt_misc binfmt_misc rw +3002 28 0:79 / /run/user/1000 rw,nosuid,nodev,relatime shared:1225 - tmpfs tmpfs rw,size=1603436k,nr_inodes=400859,mode=700,uid=1000,gid=1000 +3147 3002 0:81 / /run/user/1000/gvfs rw,nosuid,nodev,relatime shared:1290 - fuse.gvfsd-fuse gvfsd-fuse rw,user_id=1000,group_id=1000 +3148 3003 260:0 / /var/lib/kubelet/plugins/kubernetes.io/vsphere-volume/mounts/[vsanDatastore]\040bafb9e5a-8856-7e6c-699c-801844e77a4a/kubernetes-dynamic-pvc-3eba5bba-48a3-11e8-89ab-005056b92113.vmdk rw,relatime shared:31 - ext4 /dev/sda rw,data=ordered +3149 3004 260:0 / /var/lib/kubelet/plugins/kubernetes.io/vsphere-volume/mounts/[vsanDatastore]\011bafb9e5a-8856-7e6c-699c-801844e77a4a/kubernetes-dynamic-pvc-3eba5bba-48a3-11e8-89ab-005056b92113.vmdk rw,relatime shared:32 - ext4 /dev/sda rw,data=ordered diff --git a/collector/fixtures/proc/1/mounts b/collector/fixtures/proc/1/mounts deleted file mode 100644 index 7452d495a6..0000000000 --- a/collector/fixtures/proc/1/mounts +++ /dev/null @@ -1,32 +0,0 @@ -rootfs / rootfs rw 0 0 -sysfs /sys sysfs rw,nosuid,nodev,noexec,relatime 0 0 -proc /proc proc rw,nosuid,nodev,noexec,relatime 0 0 -udev /dev devtmpfs rw,relatime,size=10240k,nr_inodes=1008585,mode=755 0 0 -devpts /dev/pts devpts rw,nosuid,noexec,relatime,gid=5,mode=620,ptmxmode=000 0 0 -tmpfs /run tmpfs rw,nosuid,relatime,size=1617716k,mode=755 0 0 -/dev/dm-2 / ext4 rw,relatime,errors=remount-ro,data=ordered 0 0 -securityfs /sys/kernel/security securityfs rw,nosuid,nodev,noexec,relatime 0 0 -tmpfs /dev/shm tmpfs rw,nosuid,nodev 0 0 -tmpfs /run/lock tmpfs rw,nosuid,nodev,noexec,relatime,size=5120k 0 0 -tmpfs /sys/fs/cgroup tmpfs ro,nosuid,nodev,noexec,mode=755 0 0 -cgroup /sys/fs/cgroup/systemd cgroup rw,nosuid,nodev,noexec,relatime,xattr,release_agent=/lib/systemd/systemd-cgroups-agent,name=systemd 0 0 -pstore /sys/fs/pstore pstore rw,nosuid,nodev,noexec,relatime 0 0 -cgroup /sys/fs/cgroup/cpuset cgroup rw,nosuid,nodev,noexec,relatime,cpuset 0 0 -cgroup /sys/fs/cgroup/cpu,cpuacct cgroup rw,nosuid,nodev,noexec,relatime,cpu,cpuacct 0 0 -cgroup /sys/fs/cgroup/devices cgroup rw,nosuid,nodev,noexec,relatime,devices 0 0 -cgroup /sys/fs/cgroup/freezer cgroup rw,nosuid,nodev,noexec,relatime,freezer 0 0 -cgroup /sys/fs/cgroup/net_cls,net_prio cgroup rw,nosuid,nodev,noexec,relatime,net_cls,net_prio 0 0 -cgroup /sys/fs/cgroup/blkio cgroup rw,nosuid,nodev,noexec,relatime,blkio 0 0 -cgroup /sys/fs/cgroup/perf_event cgroup rw,nosuid,nodev,noexec,relatime,perf_event 0 0 -systemd-1 /proc/sys/fs/binfmt_misc autofs rw,relatime,fd=22,pgrp=1,timeout=300,minproto=5,maxproto=5,direct 0 0 -mqueue /dev/mqueue mqueue rw,relatime 0 0 -debugfs /sys/kernel/debug debugfs rw,relatime 0 0 -hugetlbfs /dev/hugepages hugetlbfs rw,relatime 0 0 -fusectl /sys/fs/fuse/connections fusectl rw,relatime 0 0 -/dev/sda3 /boot ext2 rw,relatime 0 0 -rpc_pipefs /run/rpc_pipefs rpc_pipefs rw,relatime 0 0 -binfmt_misc /proc/sys/fs/binfmt_misc binfmt_misc rw,relatime 0 0 -tmpfs /run/user/1000 tmpfs rw,nosuid,nodev,relatime,size=808860k,mode=700,uid=1000,gid=1000 0 0 -gvfsd-fuse /run/user/1000/gvfs fuse.gvfsd-fuse rw,nosuid,nodev,relatime,user_id=1000,group_id=1000 0 0 -/dev/sda /var/lib/kubelet/plugins/kubernetes.io/vsphere-volume/mounts/[vsanDatastore]\040bafb9e5a-8856-7e6c-699c-801844e77a4a/kubernetes-dynamic-pvc-3eba5bba-48a3-11e8-89ab-005056b92113.vmdk ext4 rw,relatime,data=ordered 0 0 -/dev/sda /var/lib/kubelet/plugins/kubernetes.io/vsphere-volume/mounts/[vsanDatastore]\011bafb9e5a-8856-7e6c-699c-801844e77a4a/kubernetes-dynamic-pvc-3eba5bba-48a3-11e8-89ab-005056b92113.vmdk ext4 rw,relatime,data=ordered 0 0 diff --git a/collector/fixtures/proc/net/netstat b/collector/fixtures/proc/net/netstat index de88470bdd..a504f800cc 100644 --- a/collector/fixtures/proc/net/netstat +++ b/collector/fixtures/proc/net/netstat @@ -1,4 +1,4 @@ -TcpExt: SyncookiesSent SyncookiesRecv SyncookiesFailed EmbryonicRsts PruneCalled RcvPruned OfoPruned OutOfWindowIcmps LockDroppedIcmps ArpFilter TW TWRecycled TWKilled PAWSPassive PAWSActive PAWSEstab DelayedACKs DelayedACKLocked DelayedACKLost ListenOverflows ListenDrops TCPPrequeued TCPDirectCopyFromBacklog TCPDirectCopyFromPrequeue TCPPrequeueDropped TCPHPHits TCPHPHitsToUser TCPPureAcks TCPHPAcks TCPRenoRecovery TCPSackRecovery TCPSACKReneging TCPFACKReorder TCPSACKReorder TCPRenoReorder TCPTSReorder TCPFullUndo TCPPartialUndo TCPDSACKUndo TCPLossUndo TCPLoss TCPLostRetransmit TCPRenoFailures TCPSackFailures TCPLossFailures TCPFastRetrans TCPForwardRetrans TCPSlowStartRetrans TCPTimeouts TCPRenoRecoveryFail TCPSackRecoveryFail TCPSchedulerFailed TCPRcvCollapsed TCPDSACKOldSent TCPDSACKOfoSent TCPDSACKRecv TCPDSACKOfoRecv TCPAbortOnData TCPAbortOnClose TCPAbortOnMemory TCPAbortOnTimeout TCPAbortOnLinger TCPAbortFailed TCPMemoryPressures TCPSACKDiscard TCPDSACKIgnoredOld TCPDSACKIgnoredNoUndo TCPSpuriousRTOs TCPMD5NotFound TCPMD5Unexpected TCPSackShifted TCPSackMerged TCPSackShiftFallback TCPBacklogDrop TCPMinTTLDrop TCPDeferAcceptDrop IPReversePathFilter TCPTimeWaitOverflow TCPReqQFullDoCookies TCPReqQFullDrop TCPChallengeACK TCPSYNChallenge TCPOFOQueue -TcpExt: 0 0 2 0 0 0 0 0 0 0 388812 0 0 0 0 6 102471 17 9 0 0 80568 0 168808 0 4471289 26 1433940 3744565 0 1 0 0 0 0 0 0 0 0 48 0 0 0 1 0 1 0 1 115 0 0 0 0 9 0 5 0 41 4 0 0 0 0 0 0 0 1 0 0 0 0 2 5 0 0 0 0 0 0 0 2 2 42 +TcpExt: SyncookiesSent SyncookiesRecv SyncookiesFailed EmbryonicRsts PruneCalled RcvPruned OfoPruned OutOfWindowIcmps LockDroppedIcmps ArpFilter TW TWRecycled TWKilled PAWSPassive PAWSActive PAWSEstab DelayedACKs DelayedACKLocked DelayedACKLost ListenOverflows ListenDrops TCPPrequeued TCPDirectCopyFromBacklog TCPDirectCopyFromPrequeue TCPPrequeueDropped TCPHPHits TCPHPHitsToUser TCPPureAcks TCPHPAcks TCPRenoRecovery TCPSackRecovery TCPSACKReneging TCPFACKReorder TCPSACKReorder TCPRenoReorder TCPTSReorder TCPFullUndo TCPPartialUndo TCPDSACKUndo TCPLossUndo TCPLoss TCPLostRetransmit TCPRenoFailures TCPSackFailures TCPLossFailures TCPFastRetrans TCPForwardRetrans TCPSlowStartRetrans TCPTimeouts TCPRenoRecoveryFail TCPSackRecoveryFail TCPSchedulerFailed TCPRcvCollapsed TCPDSACKOldSent TCPDSACKOfoSent TCPDSACKRecv TCPDSACKOfoRecv TCPAbortOnData TCPAbortOnClose TCPAbortOnMemory TCPAbortOnTimeout TCPAbortOnLinger TCPAbortFailed TCPMemoryPressures TCPSACKDiscard TCPDSACKIgnoredOld TCPDSACKIgnoredNoUndo TCPSpuriousRTOs TCPMD5NotFound TCPMD5Unexpected TCPSackShifted TCPSackMerged TCPSackShiftFallback TCPBacklogDrop TCPMinTTLDrop TCPDeferAcceptDrop IPReversePathFilter TCPTimeWaitOverflow TCPReqQFullDoCookies TCPReqQFullDrop TCPChallengeACK TCPSYNChallenge TCPOFOQueue TCPRcvQDrop +TcpExt: 0 0 2 0 0 0 0 0 0 0 388812 0 0 0 0 6 102471 17 9 0 0 80568 0 168808 0 4471289 26 1433940 3744565 0 1 0 0 0 0 0 0 0 0 48 0 0 0 1 0 1 0 1 115 0 0 0 0 9 0 5 0 41 4 0 0 0 0 0 0 0 1 0 0 0 0 2 5 0 0 0 0 0 0 0 2 2 42 131 IpExt: InNoRoutes InTruncatedPkts InMcastPkts OutMcastPkts InBcastPkts OutBcastPkts InOctets OutOctets InMcastOctets OutMcastOctets InBcastOctets OutBcastOctets IpExt: 0 0 0 0 0 0 6286396970 2786264347 0 0 0 0 diff --git a/collector/fixtures/proc/pressure/irq b/collector/fixtures/proc/pressure/irq new file mode 100644 index 0000000000..76059c7572 --- /dev/null +++ b/collector/fixtures/proc/pressure/irq @@ -0,0 +1 @@ +full avg10=0.00 avg60=0.00 avg300=0.00 total=8494 \ No newline at end of file diff --git a/collector/fixtures/proc/spl/kstat/zfs/arcstats b/collector/fixtures/proc/spl/kstat/zfs/arcstats index 48a73a2c5a..1dbeed6f37 100644 --- a/collector/fixtures/proc/spl/kstat/zfs/arcstats +++ b/collector/fixtures/proc/spl/kstat/zfs/arcstats @@ -1,93 +1,94 @@ 6 1 0x01 91 4368 5266997922 97951858082072 name type data -hits 4 8772612 -misses 4 604635 +anon_evictable_data 4 0 +anon_evictable_metadata 4 0 +anon_size 4 1917440 +arc_loaned_bytes 4 0 +arc_meta_limit 4 6275982336 +arc_meta_max 4 449286096 +arc_meta_min 4 16777216 +arc_meta_used 4 308103632 +arc_need_free 4 0 +arc_no_grow 4 0 +arc_prune 4 0 +arc_sys_free 4 261496832 +arc_tempreserve 4 0 +c 4 1643208777 +c_max 4 8367976448 +c_min 4 33554432 +data_size 4 1295836160 +deleted 4 60403 demand_data_hits 4 7221032 demand_data_misses 4 73300 demand_metadata_hits 4 1464353 demand_metadata_misses 4 498170 -prefetch_data_hits 4 3615 -prefetch_data_misses 4 17094 -prefetch_metadata_hits 4 83612 -prefetch_metadata_misses 4 16071 -mru_hits 4 855535 -mru_ghost_hits 4 21100 -mfu_hits 4 7829854 -mfu_ghost_hits 4 821 -deleted 4 60403 -mutex_miss 4 2 -evict_skip 4 2265729 -evict_not_enough 4 680 +duplicate_buffers 4 0 +duplicate_buffers_size 4 0 +duplicate_reads 4 0 evict_l2_cached 4 0 evict_l2_eligible 4 8992514560 evict_l2_ineligible 4 992552448 evict_l2_skip 4 0 +evict_not_enough 4 680 +evict_skip 4 2265729 +hash_chain_max 4 3 +hash_chains 4 412 +hash_collisions 4 50564 hash_elements 4 42359 hash_elements_max 4 88245 -hash_collisions 4 50564 -hash_chains 4 412 -hash_chain_max 4 3 -p 4 516395305 -c 4 1643208777 -c_min 4 33554432 -c_max 4 8367976448 -size 4 1603939792 hdr_size 4 16361080 -data_size 4 1295836160 -metadata_size 4 175298560 -other_size 4 116443992 -anon_size 4 1917440 -anon_evictable_data 4 0 -anon_evictable_metadata 4 0 -mru_size 4 402593792 -mru_evictable_data 4 278091264 -mru_evictable_metadata 4 18606592 -mru_ghost_size 4 999728128 -mru_ghost_evictable_data 4 883765248 -mru_ghost_evictable_metadata 4 115962880 -mfu_size 4 1066623488 -mfu_evictable_data 4 1017613824 -mfu_evictable_metadata 4 9163776 -mfu_ghost_size 4 104936448 -mfu_ghost_evictable_data 4 96731136 -mfu_ghost_evictable_metadata 4 8205312 +hits 4 8772612 +l2_abort_lowmem 4 0 +l2_asize 4 0 +l2_cdata_free_on_write 4 0 +l2_cksum_bad 4 0 +l2_compress_failures 4 0 +l2_compress_successes 4 0 +l2_compress_zeros 4 0 +l2_evict_l1cached 4 0 +l2_evict_lock_retry 4 0 +l2_evict_reading 4 0 +l2_feeds 4 0 +l2_free_on_write 4 0 +l2_hdr_size 4 0 l2_hits 4 0 +l2_io_error 4 0 l2_misses 4 0 -l2_feeds 4 0 -l2_rw_clash 4 0 l2_read_bytes 4 0 +l2_rw_clash 4 0 +l2_size 4 0 l2_write_bytes 4 0 -l2_writes_sent 4 0 l2_writes_done 4 0 l2_writes_error 4 0 l2_writes_lock_retry 4 0 -l2_evict_lock_retry 4 0 -l2_evict_reading 4 0 -l2_evict_l1cached 4 0 -l2_free_on_write 4 0 -l2_cdata_free_on_write 4 0 -l2_abort_lowmem 4 0 -l2_cksum_bad 4 0 -l2_io_error 4 0 -l2_size 4 0 -l2_asize 4 0 -l2_hdr_size 4 0 -l2_compress_successes 4 0 -l2_compress_zeros 4 0 -l2_compress_failures 4 0 -memory_throttle_count 4 0 -duplicate_buffers 4 0 -duplicate_buffers_size 4 0 -duplicate_reads 4 0 +l2_writes_sent 4 0 +memory_available_bytes 3 -922337203685477580 memory_direct_count 4 542 memory_indirect_count 4 3006 -arc_no_grow 4 0 -arc_tempreserve 4 0 -arc_loaned_bytes 4 0 -arc_prune 4 0 -arc_meta_used 4 308103632 -arc_meta_limit 4 6275982336 -arc_meta_max 4 449286096 -arc_meta_min 4 16777216 -arc_need_free 4 0 -arc_sys_free 4 261496832 +memory_throttle_count 4 0 +metadata_size 4 175298560 +mfu_evictable_data 4 1017613824 +mfu_evictable_metadata 4 9163776 +mfu_ghost_evictable_data 4 96731136 +mfu_ghost_evictable_metadata 4 8205312 +mfu_ghost_hits 4 821 +mfu_ghost_size 4 104936448 +mfu_hits 4 7829854 +mfu_size 4 1066623488 +misses 4 604635 +mru_evictable_data 4 278091264 +mru_evictable_metadata 4 18606592 +mru_ghost_evictable_data 4 883765248 +mru_ghost_evictable_metadata 4 115962880 +mru_ghost_hits 4 21100 +mru_ghost_size 4 999728128 +mru_hits 4 855535 +mru_size 4 402593792 +mutex_miss 4 2 +other_size 4 116443992 +p 4 516395305 +prefetch_data_hits 4 3615 +prefetch_data_misses 4 17094 +prefetch_metadata_hits 4 83612 +prefetch_metadata_misses 4 16071 +size 4 1603939792 diff --git a/collector/fixtures/proc/spl/kstat/zfs/pool3/io b/collector/fixtures/proc/spl/kstat/zfs/pool3/io new file mode 100644 index 0000000000..ef2a58fe7f --- /dev/null +++ b/collector/fixtures/proc/spl/kstat/zfs/pool3/io @@ -0,0 +1,3 @@ +12 3 0x00 1 80 79205351707403 395818011156865 +nread nwritten reads writes wtime wlentime wupdate rtime rlentime rupdate wcnt rcnt +1884160 3206144 22 132 7155162 104112268 79210489694949 24168078 104112268 79210489849220 0 0 diff --git a/collector/fixtures/proc/spl/kstat/zfs/pool3/objset-1 b/collector/fixtures/proc/spl/kstat/zfs/pool3/objset-1 new file mode 100644 index 0000000000..9799d262a7 --- /dev/null +++ b/collector/fixtures/proc/spl/kstat/zfs/pool3/objset-1 @@ -0,0 +1,9 @@ +23 1 0x01 7 2160 221578688875 6665999035587 +name type data +dataset_name 7 pool3 +writes 4 0 +nwritten 4 0 +reads 4 0 +nread 4 0 +nunlinks 4 0 +nunlinked 4 0 diff --git a/collector/fixtures/proc/spl/kstat/zfs/pool3/objset-2 b/collector/fixtures/proc/spl/kstat/zfs/pool3/objset-2 new file mode 100644 index 0000000000..e395504b3a --- /dev/null +++ b/collector/fixtures/proc/spl/kstat/zfs/pool3/objset-2 @@ -0,0 +1,9 @@ +24 1 0x01 7 2160 221611904716 7145015038451 +name type data +dataset_name 7 pool3/dataset with space +writes 4 4 +nwritten 4 12302 +reads 4 2 +nread 4 28 +nunlinks 4 3 +nunlinked 4 3 diff --git a/collector/fixtures/proc/spl/kstat/zfs/pool3/state b/collector/fixtures/proc/spl/kstat/zfs/pool3/state new file mode 100644 index 0000000000..1424865cf5 --- /dev/null +++ b/collector/fixtures/proc/spl/kstat/zfs/pool3/state @@ -0,0 +1 @@ +ONLINE diff --git a/collector/fixtures/sys.ttar b/collector/fixtures/sys.ttar index 2cac29e493..5af4626285 100644 --- a/collector/fixtures/sys.ttar +++ b/collector/fixtures/sys.ttar @@ -2,6 +2,243 @@ Directory: sys Mode: 755 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Directory: sys/block +Mode: 755 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Directory: sys/block/sda +Mode: 755 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Directory: sys/block/sda/queue +Mode: 755 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/add_random +Lines: 1 +1 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/chunk_sectors +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/dax +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/discard_granularity +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/discard_max_bytes +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/discard_max_hw_bytes +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/discard_zeroes_data +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/fua +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/hw_sector_size +Lines: 1 +512 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/io_poll +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/io_poll_delay +Lines: 1 +-1 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/io_timeout +Lines: 1 +30000 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Directory: sys/block/sda/queue/iosched +Mode: 755 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/back_seek_max +Lines: 1 +16384 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/back_seek_penalty +Lines: 1 +2 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/fifo_expire_async +Lines: 1 +250 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/fifo_expire_sync +Lines: 1 +125 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/low_latency +Lines: 1 +1 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/max_budget +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/slice_idle +Lines: 1 +8 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/slice_idle_us +Lines: 1 +8000 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/strict_guarantees +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iosched/timeout_sync +Lines: 1 +125 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/iostats +Lines: 1 +1 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/logical_block_size +Lines: 1 +512 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/max_discard_segments +Lines: 1 +1 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/max_hw_sectors_kb +Lines: 1 +32767 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/max_integrity_segments +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/max_sectors_kb +Lines: 1 +1280 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/max_segment_size +Lines: 1 +65536 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/max_segments +Lines: 1 +168 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/minimum_io_size +Lines: 1 +512 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/nomerges +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/nr_requests +Lines: 1 +64 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/nr_zones +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/optimal_io_size +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/physical_block_size +Lines: 1 +512 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/read_ahead_kb +Lines: 1 +128 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/rotational +Lines: 1 +1 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/rq_affinity +Lines: 1 +1 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/scheduler +Lines: 1 +mq-deadline kyber [bfq] none +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/wbt_lat_usec +Lines: 1 +75000 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/write_cache +Lines: 1 +write back +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/write_same_max_bytes +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/write_zeroes_max_bytes +Lines: 1 +0 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/block/sda/queue/zoned +Lines: 1 +none +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Directory: sys/bus Mode: 755 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -437,6 +674,26 @@ Lines: 1 100000 Mode: 644 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/class/hwmon/hwmon4/freq1_input +Lines: 1 +214000000 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/class/hwmon/hwmon4/freq1_label +Lines: 1 +sclk +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/class/hwmon/hwmon4/freq2_input +Lines: 1 +300000000 +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/class/hwmon/hwmon4/freq2_label +Lines: 1 +mclk +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Path: sys/class/hwmon/hwmon5 SymlinkTo: ../../devices/platform/bogus.0/hwmon/hwmon5/ # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -1337,7 +1594,7 @@ Mode: 444 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Path: sys/class/nvme/nvme0/model Lines: 1 -Samsung SSD 970 PRO 512GB +Samsung SSD 970 PRO 512GB Mode: 444 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Path: sys/class/nvme/nvme0/serial @@ -2750,7 +3007,7 @@ Mode: 644 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Path: sys/devices/platform/applesmc.768/fan1_label Lines: 1 -Left side +Left side Mode: 644 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Path: sys/devices/platform/applesmc.768/fan1_manual @@ -2784,7 +3041,7 @@ Mode: 644 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Path: sys/devices/platform/applesmc.768/fan2_label Lines: 1 -Right side +Right side Mode: 644 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Path: sys/devices/platform/applesmc.768/fan2_manual @@ -4489,6 +4746,14 @@ Lines: 1 4096 Mode: 444 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - +Path: sys/fs/btrfs/0abb23a9-579b-43e6-ad30-227ef47fcb9d/commit_stats +Lines: 4 +commits 258051 +last_commit_ms 1000 +max_commit_ms 51462 +total_commit_ms 47836090EOF +Mode: 644 +# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Directory: sys/fs/btrfs/0abb23a9-579b-43e6-ad30-227ef47fcb9d/devices Mode: 755 # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - diff --git a/collector/fixtures_bindmount/proc/1/mountinfo b/collector/fixtures_bindmount/proc/1/mountinfo new file mode 100644 index 0000000000..e4f1bcc549 --- /dev/null +++ b/collector/fixtures_bindmount/proc/1/mountinfo @@ -0,0 +1,6 @@ +29 1 259:0 / /host rw,seclabel,relatime,data=ordered shared:1 - ext4 /dev/nvme1n0 rw +30 1 260:0 / /host/media/volume1 rw,seclabel,relatime,data=ordered shared:1 - ext4 /dev/nvme1n1 rw +31 1 261:0 / /host/media/volume2 rw,seclabel,relatime,data=ordered shared:1 - ext4 /dev/nvme1n2 rw +31 26 0:26 / /dev/shm rw,nosuid,nodev shared:4 - tmpfs tmpfs rw,inode64 +32 28 0:27 / /run/lock rw,nosuid,nodev,noexec,relatime shared:6 - tmpfs tmpfs rw,size=5120k,inode64 +33 24 0:28 / /sys/fs/cgroup rw,nosuid,nodev,noexec,relatime shared:9 - cgroup2 cgroup2 rw diff --git a/collector/fixtures_bindmount/proc/mounts b/collector/fixtures_bindmount/proc/mounts deleted file mode 100644 index 32f9567e98..0000000000 --- a/collector/fixtures_bindmount/proc/mounts +++ /dev/null @@ -1,6 +0,0 @@ -/dev/nvme1n0 /host ext4 rw,seclabel,relatime,data=ordered 0 0 -/dev/nvme1n1 /host/media/volume1 ext4 rw,seclabel,relatime,data=ordered 0 0 -/dev/nvme1n2 /host/media/volume2 ext4 rw,seclabel,relatime,data=ordered 0 0 -tmpfs /dev/shm tmpfs rw,nosuid,nodev 0 0 -tmpfs /run/lock tmpfs rw,nosuid,nodev,noexec,relatime,size=5120k 0 0 -tmpfs /sys/fs/cgroup tmpfs ro,nosuid,nodev,noexec,mode=755 0 0 diff --git a/collector/fixtures_hidepid/proc/mounts b/collector/fixtures_hidepid/proc/mounts deleted file mode 100644 index fb6a96359c..0000000000 --- a/collector/fixtures_hidepid/proc/mounts +++ /dev/null @@ -1 +0,0 @@ -rootfs / rootfs rw 0 0 diff --git a/collector/fixtures_hidepid/proc/self/mountinfo b/collector/fixtures_hidepid/proc/self/mountinfo new file mode 100644 index 0000000000..dde22f67af --- /dev/null +++ b/collector/fixtures_hidepid/proc/self/mountinfo @@ -0,0 +1 @@ +29 1 259:2 / / rw,relatime shared:1 - ext4 /dev/nvme0n1p2 rw,errors=remount-ro diff --git a/collector/hwmon_linux.go b/collector/hwmon_linux.go index a8086d309e..ad8da41b2e 100644 --- a/collector/hwmon_linux.go +++ b/collector/hwmon_linux.go @@ -18,6 +18,8 @@ package collector import ( "errors" + "fmt" + "log/slog" "os" "path/filepath" "regexp" @@ -25,15 +27,15 @@ import ( "strings" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" ) var ( - collectorHWmonChipInclude = kingpin.Flag("collector.hwmon.chip-include", "Regexp of hwmon chip to include (mutually exclusive to device-exclude).").String() - collectorHWmonChipExclude = kingpin.Flag("collector.hwmon.chip-exclude", "Regexp of hwmon chip to exclude (mutually exclusive to device-include).").String() + collectorHWmonChipInclude = kingpin.Flag("collector.hwmon.chip-include", "Regexp of hwmon chip to include (mutually exclusive to device-exclude).").String() + collectorHWmonChipExclude = kingpin.Flag("collector.hwmon.chip-exclude", "Regexp of hwmon chip to exclude (mutually exclusive to device-include).").String() + collectorHWmonSensorInclude = kingpin.Flag("collector.hwmon.sensor-include", "Regexp of hwmon sensor to include (mutually exclusive to sensor-exclude).").String() + collectorHWmonSensorExclude = kingpin.Flag("collector.hwmon.sensor-exclude", "Regexp of hwmon sensor to exclude (mutually exclusive to sensor-include).").String() hwmonInvalidMetricChars = regexp.MustCompile("[^a-z0-9:_]") hwmonFilenameFormat = regexp.MustCompile(`^(?P[^0-9]+)(?P[0-9]*)?(_(?P.+))?$`) @@ -42,7 +44,7 @@ var ( hwmonSensorTypes = []string{ "vrm", "beep_enable", "update_interval", "in", "cpu", "fan", "pwm", "temp", "curr", "power", "energy", "humidity", - "intrusion", + "intrusion", "freq", } ) @@ -52,16 +54,18 @@ func init() { type hwMonCollector struct { deviceFilter deviceFilter - logger log.Logger + sensorFilter deviceFilter + logger *slog.Logger } // NewHwMonCollector returns a new Collector exposing /sys/class/hwmon stats // (similar to lm-sensors). -func NewHwMonCollector(logger log.Logger) (Collector, error) { +func NewHwMonCollector(logger *slog.Logger) (Collector, error) { return &hwMonCollector{ logger: logger, deviceFilter: newDeviceFilter(*collectorHWmonChipExclude, *collectorHWmonChipInclude), + sensorFilter: newDeviceFilter(*collectorHWmonSensorExclude, *collectorHWmonSensorInclude), }, nil } @@ -104,6 +108,9 @@ func sysReadFile(file string) ([]byte, error) { if err != nil { return nil, err } + if n < 0 { + return nil, fmt.Errorf("failed to read file: %q, read returned negative bytes value: %d", file, n) + } return b[:n], nil } @@ -164,7 +171,7 @@ func (c *hwMonCollector) updateHwmon(ch chan<- prometheus.Metric, dir string) er } if c.deviceFilter.ignored(hwmonName) { - level.Debug(c.logger).Log("msg", "ignoring hwmon chip", "chip", hwmonName) + c.logger.Debug("ignoring hwmon chip", "chip", hwmonName) return nil } @@ -202,6 +209,15 @@ func (c *hwMonCollector) updateHwmon(ch chan<- prometheus.Metric, dir string) er // Format all sensors. for sensor, sensorData := range data { + // Filtering for sensors is done on concatenated device name and sensor name + // separated by a semicolon. This allows for excluding or including of specific + // sensors on specific devices. For example, to exclude the sensor "temp3" on + // the device "platform_coretemp_0", use "platform_coretemp_0;temp3" + if c.sensorFilter.ignored(hwmonName + ";" + sensor) { + c.logger.Debug("ignoring sensor", "sensor", sensor) + continue + } + _, sensorType, _, _ := explodeSensorFilename(sensor) labels := []string{hwmonName, sensor} @@ -341,6 +357,15 @@ func (c *hwMonCollector) updateHwmon(ch chan<- prometheus.Metric, dir string) er continue } + if sensorType == "freq" && element == "input" { + if label, ok := sensorData["label"]; ok { + sensorLabel := cleanMetricName(label) + desc := prometheus.NewDesc(name+"_freq_mhz", "Hardware monitor for GPU frequency in MHz", hwmonLabelDesc, nil) + ch <- prometheus.MustNewConstMetric( + desc, prometheus.GaugeValue, parsedValue/1000000.0, append(labels[:len(labels)-1], sensorLabel)...) + } + continue + } // fallback, just dump the metric as is desc := prometheus.NewDesc(name, "Hardware monitor "+sensorType+" element "+element, hwmonLabelDesc, nil) @@ -437,7 +462,7 @@ func (c *hwMonCollector) Update(ch chan<- prometheus.Metric) error { hwmonFiles, err := os.ReadDir(hwmonPathName) if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "hwmon collector metrics are not available for this system") + c.logger.Debug("hwmon collector metrics are not available for this system") return ErrNoData } diff --git a/collector/infiniband_linux.go b/collector/infiniband_linux.go index b0928da3cf..7b1c438157 100644 --- a/collector/infiniband_linux.go +++ b/collector/infiniband_linux.go @@ -19,11 +19,10 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "strconv" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -31,7 +30,7 @@ import ( type infinibandCollector struct { fs sysfs.FS metricDescs map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger subsystem string } @@ -40,7 +39,7 @@ func init() { } // NewInfiniBandCollector returns a new Collector exposing InfiniBand stats. -func NewInfiniBandCollector(logger log.Logger) (Collector, error) { +func NewInfiniBandCollector(logger *slog.Logger) (Collector, error) { var i infinibandCollector var err error @@ -116,7 +115,7 @@ func (c *infinibandCollector) Update(ch chan<- prometheus.Metric) error { devices, err := c.fs.InfiniBandClass() if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "infiniband statistics not found, skipping") + c.logger.Debug("infiniband statistics not found, skipping") return ErrNoData } return fmt.Errorf("error obtaining InfiniBand class info: %w", err) diff --git a/collector/interrupts_common.go b/collector/interrupts_common.go index eea703f97e..80cd71719c 100644 --- a/collector/interrupts_common.go +++ b/collector/interrupts_common.go @@ -18,27 +18,39 @@ package collector import ( - "github.com/go-kit/log" + "log/slog" + + "github.com/alecthomas/kingpin/v2" "github.com/prometheus/client_golang/prometheus" ) type interruptsCollector struct { - desc typedDesc - logger log.Logger + desc typedDesc + logger *slog.Logger + nameFilter deviceFilter + includeZeros bool } func init() { registerCollector("interrupts", defaultDisabled, NewInterruptsCollector) } +var ( + interruptsInclude = kingpin.Flag("collector.interrupts.name-include", "Regexp of interrupts name to include (mutually exclusive to --collector.interrupts.name-exclude).").String() + interruptsExclude = kingpin.Flag("collector.interrupts.name-exclude", "Regexp of interrupts name to exclude (mutually exclusive to --collector.interrupts.name-include).").String() + interruptsIncludeZeros = kingpin.Flag("collector.interrupts.include-zeros", "Include interrupts that have a zero value").Default("true").Bool() +) + // NewInterruptsCollector returns a new Collector exposing interrupts stats. -func NewInterruptsCollector(logger log.Logger) (Collector, error) { +func NewInterruptsCollector(logger *slog.Logger) (Collector, error) { return &interruptsCollector{ desc: typedDesc{prometheus.NewDesc( namespace+"_interrupts_total", "Interrupt details.", interruptLabelNames, nil, ), prometheus.CounterValue}, - logger: logger, + logger: logger, + nameFilter: newDeviceFilter(*interruptsExclude, *interruptsInclude), + includeZeros: *interruptsIncludeZeros, }, nil } diff --git a/collector/interrupts_linux.go b/collector/interrupts_linux.go index ede7819111..77caf423c0 100644 --- a/collector/interrupts_linux.go +++ b/collector/interrupts_linux.go @@ -39,10 +39,19 @@ func (c *interruptsCollector) Update(ch chan<- prometheus.Metric) (err error) { } for name, interrupt := range interrupts { for cpuNo, value := range interrupt.values { + filterName := name + ";" + interrupt.info + ";" + interrupt.devices + if c.nameFilter.ignored(filterName) { + c.logger.Debug("ignoring interrupt name", "filter_name", filterName) + continue + } fv, err := strconv.ParseFloat(value, 64) if err != nil { return fmt.Errorf("invalid value %s in interrupts: %w", value, err) } + if !c.includeZeros && fv == 0.0 { + c.logger.Debug("ignoring interrupt with zero value", "filter_name", filterName, "cpu", cpuNo) + continue + } ch <- c.desc.mustNewConstMetric(fv, strconv.Itoa(cpuNo), name, interrupt.info, interrupt.devices) } } diff --git a/collector/interrupts_openbsd.go b/collector/interrupts_openbsd.go index 9fa5b68d5d..60fcbf1d74 100644 --- a/collector/interrupts_openbsd.go +++ b/collector/interrupts_openbsd.go @@ -106,10 +106,20 @@ func (c *interruptsCollector) Update(ch chan<- prometheus.Metric) error { } for dev, interrupt := range interrupts { for cpuNo, value := range interrupt.values { + interruptType := fmt.Sprintf("%d", interrupt.vector) + filterName := interruptType + ";" + dev + if c.nameFilter.ignored(filterName) { + c.logger.Debug("ignoring interrupt name", "filter_name", filterName) + continue + } + if !c.includeZeros && value == 0.0 { + c.logger.Debug("ignoring interrupt with zero value", "filter_name", filterName, "cpu", cpuNo) + continue + } ch <- c.desc.mustNewConstMetric( value, strconv.Itoa(cpuNo), - strconv.Itoa(interrupt.vector), + interruptType, dev, ) } diff --git a/collector/interrupts_openbsd_amd64.go b/collector/interrupts_openbsd_amd64.go index ba1091c417..69851a222f 100644 --- a/collector/interrupts_openbsd_amd64.go +++ b/collector/interrupts_openbsd_amd64.go @@ -77,10 +77,20 @@ func (c *interruptsCollector) Update(ch chan<- prometheus.Metric) error { } for dev, interrupt := range interrupts { for cpuNo, value := range interrupt.values { + interruptType := fmt.Sprintf("%d", interrupt.vector) + filterName := interruptType + ";" + dev + if c.nameFilter.ignored(filterName) { + c.logger.Debug("ignoring interrupt name", "filter_name", filterName) + continue + } + if !c.includeZeros && value == 0.0 { + c.logger.Debug("ignoring interrupt with zero value", "filter_name", filterName, "cpu", cpuNo) + continue + } ch <- c.desc.mustNewConstMetric( value, strconv.Itoa(cpuNo), - fmt.Sprintf("%d", interrupt.vector), + interruptType, dev, ) } diff --git a/collector/ipvs_linux.go b/collector/ipvs_linux.go index 63a3a1a8a8..7d7bae54a6 100644 --- a/collector/ipvs_linux.go +++ b/collector/ipvs_linux.go @@ -19,14 +19,13 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "sort" "strconv" "strings" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -37,7 +36,7 @@ type ipvsCollector struct { backendLabels []string backendConnectionsActive, backendConnectionsInact, backendWeight typedDesc connections, incomingPackets, outgoingPackets, incomingBytes, outgoingBytes typedDesc - logger log.Logger + logger *slog.Logger } type ipvsBackendStatus struct { @@ -73,11 +72,11 @@ func init() { // NewIPVSCollector sets up a new collector for IPVS metrics. It accepts the // "procfs" config parameter to override the default proc location (/proc). -func NewIPVSCollector(logger log.Logger) (Collector, error) { +func NewIPVSCollector(logger *slog.Logger) (Collector, error) { return newIPVSCollector(logger) } -func newIPVSCollector(logger log.Logger) (*ipvsCollector, error) { +func newIPVSCollector(logger *slog.Logger) (*ipvsCollector, error) { var ( c ipvsCollector err error @@ -143,7 +142,7 @@ func (c *ipvsCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { // Cannot access ipvs metrics, report no error. if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "ipvs collector metrics are not available for this system") + c.logger.Debug("ipvs collector metrics are not available for this system") return ErrNoData } return fmt.Errorf("could not get IPVS stats: %w", err) diff --git a/collector/ipvs_linux_test.go b/collector/ipvs_linux_test.go index 6ee41b299b..bc3e40f975 100644 --- a/collector/ipvs_linux_test.go +++ b/collector/ipvs_linux_test.go @@ -19,14 +19,14 @@ package collector import ( "errors" "fmt" + "io" + "log/slog" "net/http" "net/http/httptest" "os" "strings" "testing" - "github.com/go-kit/log" - "github.com/alecthomas/kingpin/v2" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/promhttp" @@ -114,7 +114,7 @@ func TestIPVSCollector(t *testing.T) { if _, err := kingpin.CommandLine.Parse(args); err != nil { t.Fatal(err) } - collector, err := newIPVSCollector(log.NewNopLogger()) + collector, err := newIPVSCollector(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { if test.err == nil { t.Fatal(err) @@ -182,7 +182,7 @@ func TestIPVSCollectorResponse(t *testing.T) { if _, err := kingpin.CommandLine.Parse(args); err != nil { t.Fatal(err) } - collector, err := NewIPVSCollector(log.NewNopLogger()) + collector, err := NewIPVSCollector(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { t.Fatal(err) } diff --git a/collector/ksmd_linux.go b/collector/ksmd_linux.go index 6d4142ae9a..d504fe300d 100644 --- a/collector/ksmd_linux.go +++ b/collector/ksmd_linux.go @@ -18,9 +18,9 @@ package collector import ( "fmt" + "log/slog" "path/filepath" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -31,7 +31,7 @@ var ( type ksmdCollector struct { metricDescs map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -50,7 +50,7 @@ func getCanonicalMetricName(filename string) string { } // NewKsmdCollector returns a new Collector exposing kernel/system statistics. -func NewKsmdCollector(logger log.Logger) (Collector, error) { +func NewKsmdCollector(logger *slog.Logger) (Collector, error) { subsystem := "ksmd" descs := make(map[string]*prometheus.Desc) diff --git a/collector/lnstat_linux.go b/collector/lnstat_linux.go index b3c90dc06e..43bd7e0590 100644 --- a/collector/lnstat_linux.go +++ b/collector/lnstat_linux.go @@ -18,22 +18,22 @@ package collector import ( "fmt" + "log/slog" "strconv" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) type lnstatCollector struct { - logger log.Logger + logger *slog.Logger } func init() { registerCollector("lnstat", defaultDisabled, NewLnstatCollector) } -func NewLnstatCollector(logger log.Logger) (Collector, error) { +func NewLnstatCollector(logger *slog.Logger) (Collector, error) { return &lnstatCollector{logger}, nil } diff --git a/collector/loadavg.go b/collector/loadavg.go index cb7b2cb142..09b1df3a4b 100644 --- a/collector/loadavg.go +++ b/collector/loadavg.go @@ -11,23 +11,22 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build (darwin || dragonfly || freebsd || linux || netbsd || openbsd || solaris) && !noloadavg -// +build darwin dragonfly freebsd linux netbsd openbsd solaris +//go:build (darwin || dragonfly || freebsd || linux || netbsd || openbsd || solaris || aix) && !noloadavg +// +build darwin dragonfly freebsd linux netbsd openbsd solaris aix // +build !noloadavg package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) type loadavgCollector struct { metric []typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -35,7 +34,7 @@ func init() { } // NewLoadavgCollector returns a new Collector exposing load average stats. -func NewLoadavgCollector(logger log.Logger) (Collector, error) { +func NewLoadavgCollector(logger *slog.Logger) (Collector, error) { return &loadavgCollector{ metric: []typedDesc{ {prometheus.NewDesc(namespace+"_load1", "1m load average.", nil, nil), prometheus.GaugeValue}, @@ -52,7 +51,7 @@ func (c *loadavgCollector) Update(ch chan<- prometheus.Metric) error { return fmt.Errorf("couldn't get load: %w", err) } for i, load := range loads { - level.Debug(c.logger).Log("msg", "return load", "index", i, "load", load) + c.logger.Debug("return load", "index", i, "load", load) ch <- c.metric[i].mustNewConstMetric(load) } return err diff --git a/collector/loadavg_aix.go b/collector/loadavg_aix.go new file mode 100644 index 0000000000..0f3db0d94f --- /dev/null +++ b/collector/loadavg_aix.go @@ -0,0 +1,30 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !noloadavg +// +build !noloadavg + +package collector + +import ( + "github.com/power-devops/perfstat" +) + +func getLoad() ([]float64, error) { + stat, err := perfstat.CpuTotalStat() + if err != nil { + return nil, err + } + + return []float64{float64(stat.LoadAvg1), float64(stat.LoadAvg5), float64(stat.LoadAvg15)}, nil +} diff --git a/collector/logind_linux.go b/collector/logind_linux.go index de5b0d18ad..f5606ee123 100644 --- a/collector/logind_linux.go +++ b/collector/logind_linux.go @@ -18,10 +18,10 @@ package collector import ( "fmt" + "log/slog" "os" "strconv" - "github.com/go-kit/log" "github.com/godbus/dbus/v5" "github.com/prometheus/client_golang/prometheus" ) @@ -46,7 +46,7 @@ var ( ) type logindCollector struct { - logger log.Logger + logger *slog.Logger } type logindDbus struct { @@ -86,7 +86,7 @@ func init() { } // NewLogindCollector returns a new Collector exposing logind statistics. -func NewLogindCollector(logger log.Logger) (Collector, error) { +func NewLogindCollector(logger *slog.Logger) (Collector, error) { return &logindCollector{logger}, nil } diff --git a/collector/mdadm_linux.go b/collector/mdadm_linux.go index 89c56b75d0..5f274ca2a2 100644 --- a/collector/mdadm_linux.go +++ b/collector/mdadm_linux.go @@ -19,16 +19,15 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) type mdadmCollector struct { - logger log.Logger + logger *slog.Logger } func init() { @@ -36,7 +35,7 @@ func init() { } // NewMdadmCollector returns a new Collector exposing raid statistics. -func NewMdadmCollector(logger log.Logger) (Collector, error) { +func NewMdadmCollector(logger *slog.Logger) (Collector, error) { return &mdadmCollector{logger}, nil } @@ -112,7 +111,7 @@ func (c *mdadmCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "Not collecting mdstat, file does not exist", "file", *procPath) + c.logger.Debug("Not collecting mdstat, file does not exist", "file", *procPath) return ErrNoData } @@ -120,7 +119,7 @@ func (c *mdadmCollector) Update(ch chan<- prometheus.Metric) error { } for _, mdStat := range mdStats { - level.Debug(c.logger).Log("msg", "collecting metrics for device", "device", mdStat.Name) + c.logger.Debug("collecting metrics for device", "device", mdStat.Name) stateVals := make(map[string]float64) stateVals[mdStat.ActivityState] = 1 diff --git a/collector/meminfo.go b/collector/meminfo.go index b59337ddbd..4eab27b155 100644 --- a/collector/meminfo.go +++ b/collector/meminfo.go @@ -11,8 +11,8 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build (darwin || linux || openbsd || netbsd) && !nomeminfo -// +build darwin linux openbsd netbsd +//go:build (darwin || linux || openbsd || netbsd || aix) && !nomeminfo +// +build darwin linux openbsd netbsd aix // +build !nomeminfo package collector @@ -21,8 +21,6 @@ import ( "fmt" "strings" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -30,19 +28,10 @@ const ( memInfoSubsystem = "memory" ) -type meminfoCollector struct { - logger log.Logger -} - func init() { registerCollector("meminfo", defaultEnabled, NewMeminfoCollector) } -// NewMeminfoCollector returns a new Collector exposing memory stats. -func NewMeminfoCollector(logger log.Logger) (Collector, error) { - return &meminfoCollector{logger}, nil -} - // Update calls (*meminfoCollector).getMemInfo to get the platform specific // memory metrics. func (c *meminfoCollector) Update(ch chan<- prometheus.Metric) error { @@ -51,7 +40,7 @@ func (c *meminfoCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { return fmt.Errorf("couldn't get meminfo: %w", err) } - level.Debug(c.logger).Log("msg", "Set node_mem", "memInfo", memInfo) + c.logger.Debug("Set node_mem", "memInfo", fmt.Sprintf("%v", memInfo)) for k, v := range memInfo { if strings.HasSuffix(k, "_total") { metricType = prometheus.CounterValue diff --git a/collector/meminfo_aix.go b/collector/meminfo_aix.go new file mode 100644 index 0000000000..ff59105b04 --- /dev/null +++ b/collector/meminfo_aix.go @@ -0,0 +1,47 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !nomeminfo +// +build !nomeminfo + +package collector + +import ( + "log/slog" + + "github.com/power-devops/perfstat" +) + +type meminfoCollector struct { + logger *slog.Logger +} + +// NewMeminfoCollector returns a new Collector exposing memory stats. +func NewMeminfoCollector(logger *slog.Logger) (Collector, error) { + return &meminfoCollector{ + logger: logger, + }, nil +} + +func (c *meminfoCollector) getMemInfo() (map[string]float64, error) { + stats, err := perfstat.MemoryTotalStat() + if err != nil { + return nil, err + } + + return map[string]float64{ + "total_bytes": float64(stats.RealTotal * 4096), + "free_bytes": float64(stats.RealFree * 4096), + "available_bytes": float64(stats.RealAvailable * 4096), + }, nil +} diff --git a/collector/meminfo_darwin.go b/collector/meminfo_darwin.go index bbc969370f..b5b10b4b92 100644 --- a/collector/meminfo_darwin.go +++ b/collector/meminfo_darwin.go @@ -24,11 +24,23 @@ import "C" import ( "encoding/binary" "fmt" + "log/slog" "unsafe" "golang.org/x/sys/unix" ) +type meminfoCollector struct { + logger *slog.Logger +} + +// NewMeminfoCollector returns a new Collector exposing memory stats. +func NewMeminfoCollector(logger *slog.Logger) (Collector, error) { + return &meminfoCollector{ + logger: logger, + }, nil +} + func (c *meminfoCollector) getMemInfo() (map[string]float64, error) { host := C.mach_host_self() infoCount := C.mach_msg_type_number_t(C.HOST_VM_INFO64_COUNT) diff --git a/collector/meminfo_linux.go b/collector/meminfo_linux.go index cee295024f..98d5a5c06b 100644 --- a/collector/meminfo_linux.go +++ b/collector/meminfo_linux.go @@ -17,59 +17,189 @@ package collector import ( - "bufio" "fmt" - "io" - "os" - "regexp" - "strconv" - "strings" -) + "log/slog" -var ( - reParens = regexp.MustCompile(`\((.*)\)`) + "github.com/prometheus/procfs" ) -func (c *meminfoCollector) getMemInfo() (map[string]float64, error) { - file, err := os.Open(procFilePath("meminfo")) +type meminfoCollector struct { + fs procfs.FS + logger *slog.Logger +} + +// NewMeminfoCollector returns a new Collector exposing memory stats. +func NewMeminfoCollector(logger *slog.Logger) (Collector, error) { + fs, err := procfs.NewFS(*procPath) if err != nil { - return nil, err + return nil, fmt.Errorf("failed to open procfs: %w", err) } - defer file.Close() - return parseMemInfo(file) + return &meminfoCollector{ + logger: logger, + fs: fs, + }, nil } -func parseMemInfo(r io.Reader) (map[string]float64, error) { - var ( - memInfo = map[string]float64{} - scanner = bufio.NewScanner(r) - ) +func (c *meminfoCollector) getMemInfo() (map[string]float64, error) { + meminfo, err := c.fs.Meminfo() + if err != nil { + return nil, fmt.Errorf("Failed to get memory info: %s", err) + } + + metrics := make(map[string]float64) - for scanner.Scan() { - line := scanner.Text() - parts := strings.Fields(line) - // Workaround for empty lines occasionally occur in CentOS 6.2 kernel 3.10.90. - if len(parts) == 0 { - continue - } - fv, err := strconv.ParseFloat(parts[1], 64) - if err != nil { - return nil, fmt.Errorf("invalid value in meminfo: %w", err) - } - key := parts[0][:len(parts[0])-1] // remove trailing : from key - // Active(anon) -> Active_anon - key = reParens.ReplaceAllString(key, "_${1}") - switch len(parts) { - case 2: // no unit - case 3: // has unit, we presume kB - fv *= 1024 - key = key + "_bytes" - default: - return nil, fmt.Errorf("invalid line in meminfo: %s", line) - } - memInfo[key] = fv + if meminfo.ActiveBytes != nil { + metrics["Active_bytes"] = float64(*meminfo.ActiveBytes) + } + if meminfo.ActiveAnonBytes != nil { + metrics["Active_anon_bytes"] = float64(*meminfo.ActiveAnonBytes) + } + if meminfo.ActiveFileBytes != nil { + metrics["Active_file_bytes"] = float64(*meminfo.ActiveFileBytes) + } + if meminfo.AnonHugePagesBytes != nil { + metrics["AnonHugePages_bytes"] = float64(*meminfo.AnonHugePagesBytes) + } + if meminfo.AnonPagesBytes != nil { + metrics["AnonPages_bytes"] = float64(*meminfo.AnonPagesBytes) + } + if meminfo.BounceBytes != nil { + metrics["Bounce_bytes"] = float64(*meminfo.BounceBytes) + } + if meminfo.BuffersBytes != nil { + metrics["Buffers_bytes"] = float64(*meminfo.BuffersBytes) + } + if meminfo.CachedBytes != nil { + metrics["Cached_bytes"] = float64(*meminfo.CachedBytes) + } + if meminfo.CmaFreeBytes != nil { + metrics["CmaFree_bytes"] = float64(*meminfo.CmaFreeBytes) + } + if meminfo.CmaTotalBytes != nil { + metrics["CmaTotal_bytes"] = float64(*meminfo.CmaTotalBytes) + } + if meminfo.CommitLimitBytes != nil { + metrics["CommitLimit_bytes"] = float64(*meminfo.CommitLimitBytes) + } + if meminfo.CommittedASBytes != nil { + metrics["Committed_AS_bytes"] = float64(*meminfo.CommittedASBytes) + } + if meminfo.DirectMap1GBytes != nil { + metrics["DirectMap1G_bytes"] = float64(*meminfo.DirectMap1GBytes) + } + if meminfo.DirectMap2MBytes != nil { + metrics["DirectMap2M_bytes"] = float64(*meminfo.DirectMap2MBytes) + } + if meminfo.DirectMap4kBytes != nil { + metrics["DirectMap4k_bytes"] = float64(*meminfo.DirectMap4kBytes) + } + if meminfo.DirtyBytes != nil { + metrics["Dirty_bytes"] = float64(*meminfo.DirtyBytes) + } + if meminfo.HardwareCorruptedBytes != nil { + metrics["HardwareCorrupted_bytes"] = float64(*meminfo.HardwareCorruptedBytes) + } + if meminfo.HugepagesizeBytes != nil { + metrics["Hugepagesize_bytes"] = float64(*meminfo.HugepagesizeBytes) + } + if meminfo.InactiveBytes != nil { + metrics["Inactive_bytes"] = float64(*meminfo.InactiveBytes) + } + if meminfo.InactiveAnonBytes != nil { + metrics["Inactive_anon_bytes"] = float64(*meminfo.InactiveAnonBytes) + } + if meminfo.InactiveFileBytes != nil { + metrics["Inactive_file_bytes"] = float64(*meminfo.InactiveFileBytes) + } + if meminfo.KernelStackBytes != nil { + metrics["KernelStack_bytes"] = float64(*meminfo.KernelStackBytes) + } + if meminfo.MappedBytes != nil { + metrics["Mapped_bytes"] = float64(*meminfo.MappedBytes) + } + if meminfo.MemAvailableBytes != nil { + metrics["MemAvailable_bytes"] = float64(*meminfo.MemAvailableBytes) + } + if meminfo.MemFreeBytes != nil { + metrics["MemFree_bytes"] = float64(*meminfo.MemFreeBytes) + } + if meminfo.MemTotalBytes != nil { + metrics["MemTotal_bytes"] = float64(*meminfo.MemTotalBytes) + } + if meminfo.MlockedBytes != nil { + metrics["Mlocked_bytes"] = float64(*meminfo.MlockedBytes) + } + if meminfo.NFSUnstableBytes != nil { + metrics["NFS_Unstable_bytes"] = float64(*meminfo.NFSUnstableBytes) + } + if meminfo.PageTablesBytes != nil { + metrics["PageTables_bytes"] = float64(*meminfo.PageTablesBytes) + } + if meminfo.PercpuBytes != nil { + metrics["Percpu_bytes"] = float64(*meminfo.PercpuBytes) + } + if meminfo.SReclaimableBytes != nil { + metrics["SReclaimable_bytes"] = float64(*meminfo.SReclaimableBytes) + } + if meminfo.SUnreclaimBytes != nil { + metrics["SUnreclaim_bytes"] = float64(*meminfo.SUnreclaimBytes) + } + if meminfo.ShmemBytes != nil { + metrics["Shmem_bytes"] = float64(*meminfo.ShmemBytes) + } + if meminfo.ShmemHugePagesBytes != nil { + metrics["ShmemHugePages_bytes"] = float64(*meminfo.ShmemHugePagesBytes) + } + if meminfo.ShmemPmdMappedBytes != nil { + metrics["ShmemPmdMapped_bytes"] = float64(*meminfo.ShmemPmdMappedBytes) + } + if meminfo.SlabBytes != nil { + metrics["Slab_bytes"] = float64(*meminfo.SlabBytes) + } + if meminfo.SwapCachedBytes != nil { + metrics["SwapCached_bytes"] = float64(*meminfo.SwapCachedBytes) + } + if meminfo.SwapFreeBytes != nil { + metrics["SwapFree_bytes"] = float64(*meminfo.SwapFreeBytes) + } + if meminfo.SwapTotalBytes != nil { + metrics["SwapTotal_bytes"] = float64(*meminfo.SwapTotalBytes) + } + if meminfo.UnevictableBytes != nil { + metrics["Unevictable_bytes"] = float64(*meminfo.UnevictableBytes) + } + if meminfo.VmallocChunkBytes != nil { + metrics["VmallocChunk_bytes"] = float64(*meminfo.VmallocChunkBytes) + } + if meminfo.VmallocTotalBytes != nil { + metrics["VmallocTotal_bytes"] = float64(*meminfo.VmallocTotalBytes) + } + if meminfo.VmallocUsedBytes != nil { + metrics["VmallocUsed_bytes"] = float64(*meminfo.VmallocUsedBytes) + } + if meminfo.WritebackBytes != nil { + metrics["Writeback_bytes"] = float64(*meminfo.WritebackBytes) + } + if meminfo.WritebackTmpBytes != nil { + metrics["WritebackTmp_bytes"] = float64(*meminfo.WritebackTmpBytes) + } + + // These fields are always in bytes and do not have `Bytes` + // suffixed counterparts in the procfs.Meminfo struct, nor do + // they have `_bytes` suffix on the metric names. + if meminfo.HugePagesFree != nil { + metrics["HugePages_Free"] = float64(*meminfo.HugePagesFree) + } + if meminfo.HugePagesRsvd != nil { + metrics["HugePages_Rsvd"] = float64(*meminfo.HugePagesRsvd) + } + if meminfo.HugePagesSurp != nil { + metrics["HugePages_Surp"] = float64(*meminfo.HugePagesSurp) + } + if meminfo.HugePagesTotal != nil { + metrics["HugePages_Total"] = float64(*meminfo.HugePagesTotal) } - return memInfo, scanner.Err() + return metrics, nil } diff --git a/collector/meminfo_linux_test.go b/collector/meminfo_linux_test.go index a000bea53c..41a0133fe5 100644 --- a/collector/meminfo_linux_test.go +++ b/collector/meminfo_linux_test.go @@ -17,20 +17,23 @@ package collector import ( - "os" + "io" + "log/slog" "testing" ) func TestMemInfo(t *testing.T) { - file, err := os.Open("fixtures/proc/meminfo") + *procPath = "fixtures/proc" + logger := slog.New(slog.NewTextHandler(io.Discard, nil)) + + collector, err := NewMeminfoCollector(logger) if err != nil { - t.Fatal(err) + panic(err) } - defer file.Close() - memInfo, err := parseMemInfo(file) + memInfo, err := collector.(*meminfoCollector).getMemInfo() if err != nil { - t.Fatal(err) + panic(err) } if want, got := 3831959552.0, memInfo["MemTotal_bytes"]; want != got { diff --git a/collector/meminfo_netbsd.go b/collector/meminfo_netbsd.go index a1bd118523..54d23a128e 100644 --- a/collector/meminfo_netbsd.go +++ b/collector/meminfo_netbsd.go @@ -18,8 +18,20 @@ package collector import ( "golang.org/x/sys/unix" + "log/slog" ) +type meminfoCollector struct { + logger *slog.Logger +} + +// NewMeminfoCollector returns a new Collector exposing memory stats. +func NewMeminfoCollector(logger *slog.Logger) (Collector, error) { + return &meminfoCollector{ + logger: logger, + }, nil +} + func (c *meminfoCollector) getMemInfo() (map[string]float64, error) { uvmexp, err := unix.SysctlUvmexp("vm.uvmexp2") if err != nil { diff --git a/collector/meminfo_numa_linux.go b/collector/meminfo_numa_linux.go index 5ce08e99d9..fc26eba499 100644 --- a/collector/meminfo_numa_linux.go +++ b/collector/meminfo_numa_linux.go @@ -20,13 +20,13 @@ import ( "bufio" "fmt" "io" + "log/slog" "os" "path/filepath" "regexp" "strconv" "strings" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -45,7 +45,7 @@ type meminfoMetric struct { type meminfoNumaCollector struct { metricDescs map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -53,7 +53,7 @@ func init() { } // NewMeminfoNumaCollector returns a new Collector exposing memory stats. -func NewMeminfoNumaCollector(logger log.Logger) (Collector, error) { +func NewMeminfoNumaCollector(logger *slog.Logger) (Collector, error) { return &meminfoNumaCollector{ metricDescs: map[string]*prometheus.Desc{}, logger: logger, diff --git a/collector/meminfo_openbsd.go b/collector/meminfo_openbsd.go index c5d2947ec7..ca9f46ad8e 100644 --- a/collector/meminfo_openbsd.go +++ b/collector/meminfo_openbsd.go @@ -18,6 +18,7 @@ package collector import ( "fmt" + "log/slog" ) /* @@ -53,6 +54,17 @@ sysctl_bcstats(struct bcachestats *bcstats) */ import "C" +type meminfoCollector struct { + logger *slog.Logger +} + +// NewMeminfoCollector returns a new Collector exposing memory stats. +func NewMeminfoCollector(logger *slog.Logger) (Collector, error) { + return &meminfoCollector{ + logger: logger, + }, nil +} + func (c *meminfoCollector) getMemInfo() (map[string]float64, error) { var uvmexp C.struct_uvmexp var bcstats C.struct_bcachestats diff --git a/collector/meminfo_openbsd_amd64.go b/collector/meminfo_openbsd_amd64.go index 41adebc3a4..906a36e41f 100644 --- a/collector/meminfo_openbsd_amd64.go +++ b/collector/meminfo_openbsd_amd64.go @@ -17,8 +17,10 @@ package collector import ( - "golang.org/x/sys/unix" + "log/slog" "unsafe" + + "golang.org/x/sys/unix" ) const ( @@ -48,6 +50,17 @@ type bcachestats struct { Dmaflips int64 } +type meminfoCollector struct { + logger *slog.Logger +} + +// NewMeminfoCollector returns a new Collector exposing memory stats. +func NewMeminfoCollector(logger *slog.Logger) (Collector, error) { + return &meminfoCollector{ + logger: logger, + }, nil +} + func (c *meminfoCollector) getMemInfo() (map[string]float64, error) { uvmexpb, err := unix.SysctlRaw("vm.uvmexp") if err != nil { diff --git a/collector/memory_bsd.go b/collector/memory_bsd.go index 6af9d8aaa4..1c3710523d 100644 --- a/collector/memory_bsd.go +++ b/collector/memory_bsd.go @@ -19,8 +19,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" ) @@ -33,7 +33,7 @@ type memoryCollector struct { pageSize uint64 sysctls []bsdSysctl kvm kvm - logger log.Logger + logger *slog.Logger } func init() { @@ -41,7 +41,7 @@ func init() { } // NewMemoryCollector returns a new Collector exposing memory stats. -func NewMemoryCollector(logger log.Logger) (Collector, error) { +func NewMemoryCollector(logger *slog.Logger) (Collector, error) { tmp32, err := unix.SysctlUint32("vm.stats.vm.v_page_size") if err != nil { return nil, fmt.Errorf("sysctl(vm.stats.vm.v_page_size) failed: %w", err) diff --git a/collector/mountstats_linux.go b/collector/mountstats_linux.go index 9dea6fad71..03f1a9b676 100644 --- a/collector/mountstats_linux.go +++ b/collector/mountstats_linux.go @@ -18,9 +18,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -96,7 +95,7 @@ type mountStatsCollector struct { proc procfs.Proc - logger log.Logger + logger *slog.Logger } // used to uniquely identify an NFS mount to prevent duplicates @@ -111,7 +110,7 @@ func init() { } // NewMountStatsCollector returns a new Collector exposing NFS statistics. -func NewMountStatsCollector(logger log.Logger) (Collector, error) { +func NewMountStatsCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -538,15 +537,16 @@ func (c *mountStatsCollector) Update(ch chan<- prometheus.Metric) error { mountAddress = miStats.SuperOptions["addr"] } - deviceIdentifier := nfsDeviceIdentifier{m.Device, stats.Transport.Protocol, mountAddress} - i := deviceList[deviceIdentifier] - if i { - level.Debug(c.logger).Log("msg", "Skipping duplicate device entry", "device", deviceIdentifier) - continue + for k := range stats.Transport { + deviceIdentifier := nfsDeviceIdentifier{m.Device, stats.Transport[k].Protocol, mountAddress} + i := deviceList[deviceIdentifier] + if i { + c.logger.Debug("Skipping duplicate device entry", "device", deviceIdentifier) + break + } + deviceList[deviceIdentifier] = true + c.updateNFSStats(ch, stats, m.Device, stats.Transport[k].Protocol, mountAddress) } - - deviceList[deviceIdentifier] = true - c.updateNFSStats(ch, stats, m.Device, stats.Transport.Protocol, mountAddress) } return nil @@ -617,75 +617,77 @@ func (c *mountStatsCollector) updateNFSStats(ch chan<- prometheus.Metric, s *pro labelValues..., ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportBindTotal, - prometheus.CounterValue, - float64(s.Transport.Bind), - labelValues..., - ) + for i := range s.Transport { + ch <- prometheus.MustNewConstMetric( + c.NFSTransportBindTotal, + prometheus.CounterValue, + float64(s.Transport[i].Bind), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportConnectTotal, - prometheus.CounterValue, - float64(s.Transport.Connect), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportConnectTotal, + prometheus.CounterValue, + float64(s.Transport[i].Connect), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportIdleTimeSeconds, - prometheus.GaugeValue, - float64(s.Transport.IdleTimeSeconds%float64Mantissa), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportIdleTimeSeconds, + prometheus.GaugeValue, + float64(s.Transport[i].IdleTimeSeconds%float64Mantissa), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportSendsTotal, - prometheus.CounterValue, - float64(s.Transport.Sends), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportSendsTotal, + prometheus.CounterValue, + float64(s.Transport[i].Sends), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportReceivesTotal, - prometheus.CounterValue, - float64(s.Transport.Receives), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportReceivesTotal, + prometheus.CounterValue, + float64(s.Transport[i].Receives), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportBadTransactionIDsTotal, - prometheus.CounterValue, - float64(s.Transport.BadTransactionIDs), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportBadTransactionIDsTotal, + prometheus.CounterValue, + float64(s.Transport[i].BadTransactionIDs), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportBacklogQueueTotal, - prometheus.CounterValue, - float64(s.Transport.CumulativeBacklog), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportBacklogQueueTotal, + prometheus.CounterValue, + float64(s.Transport[i].CumulativeBacklog), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportMaximumRPCSlots, - prometheus.GaugeValue, - float64(s.Transport.MaximumRPCSlotsUsed), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportMaximumRPCSlots, + prometheus.GaugeValue, + float64(s.Transport[i].MaximumRPCSlotsUsed), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportSendingQueueTotal, - prometheus.CounterValue, - float64(s.Transport.CumulativeSendingQueue), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportSendingQueueTotal, + prometheus.CounterValue, + float64(s.Transport[i].CumulativeSendingQueue), + labelValues..., + ) - ch <- prometheus.MustNewConstMetric( - c.NFSTransportPendingQueueTotal, - prometheus.CounterValue, - float64(s.Transport.CumulativePendingQueue), - labelValues..., - ) + ch <- prometheus.MustNewConstMetric( + c.NFSTransportPendingQueueTotal, + prometheus.CounterValue, + float64(s.Transport[i].CumulativePendingQueue), + labelValues..., + ) + } for _, op := range s.Operations { opLabelValues := []string{export, protocol, mountAddress, op.Operation} diff --git a/collector/netclass_linux.go b/collector/netclass_linux.go index 327c89aaf4..87763c3b6e 100644 --- a/collector/netclass_linux.go +++ b/collector/netclass_linux.go @@ -19,14 +19,13 @@ package collector import ( "errors" "fmt" + "log/slog" "net" "os" "regexp" "sync" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -43,7 +42,7 @@ type netClassCollector struct { ignoredDevicesPattern *regexp.Regexp metricDescs map[string]*prometheus.Desc metricDescsMu sync.Mutex - logger log.Logger + logger *slog.Logger } func init() { @@ -51,7 +50,7 @@ func init() { } // NewNetClassCollector returns a new Collector exposing network class stats. -func NewNetClassCollector(logger log.Logger) (Collector, error) { +func NewNetClassCollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) @@ -77,7 +76,7 @@ func (c *netClassCollector) netClassSysfsUpdate(ch chan<- prometheus.Metric) err netClass, err := c.getNetClassInfo() if err != nil { if errors.Is(err, os.ErrNotExist) || errors.Is(err, os.ErrPermission) { - level.Debug(c.logger).Log("msg", "Could not read netclass file", "err", err) + c.logger.Debug("Could not read netclass file", "err", err) return ErrNoData } return fmt.Errorf("could not get net class info: %w", err) diff --git a/collector/netclass_rtnl_linux.go b/collector/netclass_rtnl_linux.go index ef963715e5..44d89f8f05 100644 --- a/collector/netclass_rtnl_linux.go +++ b/collector/netclass_rtnl_linux.go @@ -23,8 +23,7 @@ import ( "path/filepath" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log/level" - "github.com/jsimonetti/rtnetlink" + "github.com/jsimonetti/rtnetlink/v2" "github.com/mdlayher/ethtool" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" @@ -45,7 +44,7 @@ func (c *netClassCollector) netClassRTNLUpdate(ch chan<- prometheus.Metric) erro if !errors.Is(errors.Unwrap(err), fs.ErrNotExist) { return fmt.Errorf("could not get link modes: %w", err) } - level.Info(c.logger).Log("msg", "ETHTOOL netlink interface unavailable, duplex and linkspeed are not scraped.") + c.logger.Info("ETHTOOL netlink interface unavailable, duplex and linkspeed are not scraped.") } else { for _, lm := range lms { if c.ignoredDevicesPattern.MatchString(lm.Interface.Name) { diff --git a/collector/netdev_aix.go b/collector/netdev_aix.go new file mode 100644 index 0000000000..ae316443cf --- /dev/null +++ b/collector/netdev_aix.go @@ -0,0 +1,54 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !nonetdev +// +build !nonetdev + +package collector + +import ( + "log/slog" + + "github.com/power-devops/perfstat" +) + +func getNetDevStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { + netDev := netDevStats{} + + stats, err := perfstat.NetAdapterStat() + if err != nil { + return nil, err + } + + for _, stat := range stats { + netDev[stat.Name] = map[string]uint64{ + "receive_packets": uint64(stat.RxPackets), + "transmit_packets": uint64(stat.TxPackets), + "receive_bytes": uint64(stat.RxBytes), + "transmit_bytes": uint64(stat.TxBytes), + "receive_errors": uint64(stat.RxErrors), + "transmit_errors": uint64(stat.TxErrors), + "receive_dropped": uint64(stat.RxPacketsDropped), + "transmit_dropped": uint64(stat.TxPacketsDropped), + "receive_multicast": uint64(stat.RxMulticastPackets), + "transmit_multicast": uint64(stat.TxMulticastPackets), + } + } + + return netDev, nil +} + +func getNetDevLabels() (map[string]map[string]string, error) { + // to be implemented if needed + return nil, nil +} diff --git a/collector/netdev_bsd.go b/collector/netdev_bsd.go index 691bbec4ad..e1a947e7c2 100644 --- a/collector/netdev_bsd.go +++ b/collector/netdev_bsd.go @@ -19,9 +19,7 @@ package collector import ( "errors" - - "github.com/go-kit/log" - "github.com/go-kit/log/level" + "log/slog" ) /* @@ -34,7 +32,7 @@ import ( */ import "C" -func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) { +func getNetDevStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { netDev := netDevStats{} var ifap, ifa *C.struct_ifaddrs @@ -50,7 +48,7 @@ func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error dev := C.GoString(ifa.ifa_name) if filter.ignored(dev) { - level.Debug(logger).Log("msg", "Ignoring device", "device", dev) + logger.Debug("Ignoring device", "device", dev) continue } @@ -72,3 +70,7 @@ func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error return netDev, nil } + +func getNetDevLabels() (map[string]map[string]string, error) { + return nil, nil +} diff --git a/collector/netdev_common.go b/collector/netdev_common.go index 089f1e5870..c19e5df578 100644 --- a/collector/netdev_common.go +++ b/collector/netdev_common.go @@ -11,22 +11,21 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build !nonetdev && (linux || freebsd || openbsd || dragonfly || darwin) +//go:build !nonetdev && (linux || freebsd || openbsd || dragonfly || darwin || aix) // +build !nonetdev -// +build linux freebsd openbsd dragonfly darwin +// +build linux freebsd openbsd dragonfly darwin aix package collector import ( "errors" "fmt" + "log/slog" "net" "strconv" "sync" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -44,7 +43,7 @@ type netDevCollector struct { deviceFilter deviceFilter metricDescsMutex sync.Mutex metricDescs map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger } type netDevStats map[string]map[string]uint64 @@ -54,10 +53,10 @@ func init() { } // NewNetDevCollector returns a new Collector exposing network device stats. -func NewNetDevCollector(logger log.Logger) (Collector, error) { +func NewNetDevCollector(logger *slog.Logger) (Collector, error) { if *oldNetdevDeviceInclude != "" { if *netdevDeviceInclude == "" { - level.Warn(logger).Log("msg", "--collector.netdev.device-whitelist is DEPRECATED and will be removed in 2.0.0, use --collector.netdev.device-include") + logger.Warn("--collector.netdev.device-whitelist is DEPRECATED and will be removed in 2.0.0, use --collector.netdev.device-include") *netdevDeviceInclude = *oldNetdevDeviceInclude } else { return nil, errors.New("--collector.netdev.device-whitelist and --collector.netdev.device-include are mutually exclusive") @@ -66,7 +65,7 @@ func NewNetDevCollector(logger log.Logger) (Collector, error) { if *oldNetdevDeviceExclude != "" { if *netdevDeviceExclude == "" { - level.Warn(logger).Log("msg", "--collector.netdev.device-blacklist is DEPRECATED and will be removed in 2.0.0, use --collector.netdev.device-exclude") + logger.Warn("--collector.netdev.device-blacklist is DEPRECATED and will be removed in 2.0.0, use --collector.netdev.device-exclude") *netdevDeviceExclude = *oldNetdevDeviceExclude } else { return nil, errors.New("--collector.netdev.device-blacklist and --collector.netdev.device-exclude are mutually exclusive") @@ -78,11 +77,11 @@ func NewNetDevCollector(logger log.Logger) (Collector, error) { } if *netdevDeviceExclude != "" { - level.Info(logger).Log("msg", "Parsed flag --collector.netdev.device-exclude", "flag", *netdevDeviceExclude) + logger.Info("Parsed flag --collector.netdev.device-exclude", "flag", *netdevDeviceExclude) } if *netdevDeviceInclude != "" { - level.Info(logger).Log("msg", "Parsed Flag --collector.netdev.device-include", "flag", *netdevDeviceInclude) + logger.Info("Parsed Flag --collector.netdev.device-include", "flag", *netdevDeviceInclude) } return &netDevCollector{ @@ -93,7 +92,7 @@ func NewNetDevCollector(logger log.Logger) (Collector, error) { }, nil } -func (c *netDevCollector) metricDesc(key string) *prometheus.Desc { +func (c *netDevCollector) metricDesc(key string, labels []string) *prometheus.Desc { c.metricDescsMutex.Lock() defer c.metricDescsMutex.Unlock() @@ -101,7 +100,7 @@ func (c *netDevCollector) metricDesc(key string) *prometheus.Desc { c.metricDescs[key] = prometheus.NewDesc( prometheus.BuildFQName(namespace, c.subsystem, key+"_total"), fmt.Sprintf("Network device statistic %s.", key), - []string{"device"}, + labels, nil, ) } @@ -114,13 +113,29 @@ func (c *netDevCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { return fmt.Errorf("couldn't get netstats: %w", err) } + + netDevLabels, err := getNetDevLabels() + if err != nil { + return fmt.Errorf("couldn't get netdev labels: %w", err) + } + for dev, devStats := range netDev { if !*netdevDetailedMetrics { legacy(devStats) } + + labels := []string{"device"} + labelValues := []string{dev} + if devLabels, exists := netDevLabels[dev]; exists { + for labelName, labelValue := range devLabels { + labels = append(labels, labelName) + labelValues = append(labelValues, labelValue) + } + } + for key, value := range devStats { - desc := c.metricDesc(key) - ch <- prometheus.MustNewConstMetric(desc, prometheus.CounterValue, float64(value), dev) + desc := c.metricDesc(key, labels) + ch <- prometheus.MustNewConstMetric(desc, prometheus.CounterValue, float64(value), labelValues...) } } if *netdevAddressInfo { diff --git a/collector/netdev_darwin.go b/collector/netdev_darwin.go index c08f1f8ede..2367ebe5c6 100644 --- a/collector/netdev_darwin.go +++ b/collector/netdev_darwin.go @@ -20,14 +20,13 @@ import ( "bytes" "encoding/binary" "fmt" + "log/slog" "net" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "golang.org/x/sys/unix" ) -func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) { +func getNetDevStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { netDev := netDevStats{} ifs, err := net.Interfaces() @@ -37,13 +36,13 @@ func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error for _, iface := range ifs { if filter.ignored(iface.Name) { - level.Debug(logger).Log("msg", "Ignoring device", "device", iface.Name) + logger.Debug("Ignoring device", "device", iface.Name) continue } ifaceData, err := getIfaceData(iface.Index) if err != nil { - level.Debug(logger).Log("msg", "failed to load data for interface", "device", iface.Name, "err", err) + logger.Debug("failed to load data for interface", "device", iface.Name, "err", err) continue } @@ -118,3 +117,8 @@ type ifData64 struct { Xmittiming uint32 Lastchange unix.Timeval32 } + +func getNetDevLabels() (map[string]map[string]string, error) { + // to be implemented if needed + return nil, nil +} diff --git a/collector/netdev_linux.go b/collector/netdev_linux.go index f3348cda73..58ac4af578 100644 --- a/collector/netdev_linux.go +++ b/collector/netdev_linux.go @@ -18,26 +18,27 @@ package collector import ( "fmt" + "log/slog" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" - "github.com/jsimonetti/rtnetlink" + "github.com/jsimonetti/rtnetlink/v2" "github.com/prometheus/procfs" + "github.com/prometheus/procfs/sysfs" ) var ( - netDevNetlink = kingpin.Flag("collector.netdev.netlink", "Use netlink to gather stats instead of /proc/net/dev.").Default("true").Bool() + netDevNetlink = kingpin.Flag("collector.netdev.netlink", "Use netlink to gather stats instead of /proc/net/dev.").Default("true").Bool() + netdevLabelIfAlias = kingpin.Flag("collector.netdev.label-ifalias", "Add ifAlias label").Default("false").Bool() ) -func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) { +func getNetDevStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { if *netDevNetlink { return netlinkStats(filter, logger) } return procNetDevStats(filter, logger) } -func netlinkStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) { +func netlinkStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { conn, err := rtnetlink.Dial(nil) if err != nil { return nil, err @@ -52,12 +53,12 @@ func netlinkStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) return parseNetlinkStats(links, filter, logger), nil } -func parseNetlinkStats(links []rtnetlink.LinkMessage, filter *deviceFilter, logger log.Logger) netDevStats { +func parseNetlinkStats(links []rtnetlink.LinkMessage, filter *deviceFilter, logger *slog.Logger) netDevStats { metrics := netDevStats{} for _, msg := range links { if msg.Attributes == nil { - level.Debug(logger).Log("msg", "No netlink attributes, skipping") + logger.Debug("No netlink attributes, skipping") continue } name := msg.Attributes.Name @@ -93,13 +94,13 @@ func parseNetlinkStats(links []rtnetlink.LinkMessage, filter *deviceFilter, logg } if filter.ignored(name) { - level.Debug(logger).Log("msg", "Ignoring device", "device", name) + logger.Debug("Ignoring device", "device", name) continue } // Make sure we don't panic when accessing `stats` attributes below. if stats == nil { - level.Debug(logger).Log("msg", "No netlink stats, skipping") + logger.Debug("No netlink stats, skipping") continue } @@ -141,7 +142,7 @@ func parseNetlinkStats(links []rtnetlink.LinkMessage, filter *deviceFilter, logg return metrics } -func procNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) { +func procNetDevStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { metrics := netDevStats{} fs, err := procfs.NewFS(*procPath) @@ -158,7 +159,7 @@ func procNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, erro name := stats.Name if filter.ignored(name) { - level.Debug(logger).Log("msg", "Ignoring device", "device", name) + logger.Debug("Ignoring device", "device", name) continue } @@ -184,3 +185,26 @@ func procNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, erro return metrics, nil } + +func getNetDevLabels() (map[string]map[string]string, error) { + if !*netdevLabelIfAlias { + return nil, nil + } + + fs, err := sysfs.NewFS(*sysPath) + if err != nil { + return nil, err + } + + interfaces, err := fs.NetClass() + if err != nil { + return nil, err + } + + labels := make(map[string]map[string]string) + for iface, params := range interfaces { + labels[iface] = map[string]string{"ifalias": params.IfAlias} + } + + return labels, nil +} diff --git a/collector/netdev_linux_test.go b/collector/netdev_linux_test.go index 7909d01821..06700fd8ed 100644 --- a/collector/netdev_linux_test.go +++ b/collector/netdev_linux_test.go @@ -17,11 +17,11 @@ package collector import ( + "io" + "log/slog" "testing" - "github.com/go-kit/log" - - "github.com/jsimonetti/rtnetlink" + "github.com/jsimonetti/rtnetlink/v2" ) var links = []rtnetlink.LinkMessage{ @@ -166,7 +166,7 @@ var links = []rtnetlink.LinkMessage{ func TestNetDevStatsIgnore(t *testing.T) { filter := newDeviceFilter("^veth", "") - netStats := parseNetlinkStats(links, &filter, log.NewNopLogger()) + netStats := parseNetlinkStats(links, &filter, slog.New(slog.NewTextHandler(io.Discard, nil))) if want, got := uint64(10437182923), netStats["wlan0"]["receive_bytes"]; want != got { t.Errorf("want netstat wlan0 bytes %v, got %v", want, got) @@ -199,7 +199,7 @@ func TestNetDevStatsIgnore(t *testing.T) { func TestNetDevStatsAccept(t *testing.T) { filter := newDeviceFilter("", "^💩0$") - netStats := parseNetlinkStats(links, &filter, log.NewNopLogger()) + netStats := parseNetlinkStats(links, &filter, slog.New(slog.NewTextHandler(io.Discard, nil))) if want, got := 1, len(netStats); want != got { t.Errorf("want count of devices to be %d, got %d", want, got) @@ -230,7 +230,7 @@ func TestNetDevLegacyMetricNames(t *testing.T) { } filter := newDeviceFilter("", "") - netStats := parseNetlinkStats(links, &filter, log.NewNopLogger()) + netStats := parseNetlinkStats(links, &filter, slog.New(slog.NewTextHandler(io.Discard, nil))) for dev, devStats := range netStats { legacy(devStats) @@ -263,7 +263,7 @@ func TestNetDevLegacyMetricValues(t *testing.T) { } filter := newDeviceFilter("", "^enp0s0f0$") - netStats := parseNetlinkStats(links, &filter, log.NewNopLogger()) + netStats := parseNetlinkStats(links, &filter, slog.New(slog.NewTextHandler(io.Discard, nil))) metrics, ok := netStats["enp0s0f0"] if !ok { t.Error("expected stats for interface enp0s0f0") @@ -285,7 +285,7 @@ func TestNetDevLegacyMetricValues(t *testing.T) { func TestNetDevMetricValues(t *testing.T) { filter := newDeviceFilter("", "") - netStats := parseNetlinkStats(links, &filter, log.NewNopLogger()) + netStats := parseNetlinkStats(links, &filter, slog.New(slog.NewTextHandler(io.Discard, nil))) for _, msg := range links { device := msg.Attributes.Name diff --git a/collector/netdev_openbsd.go b/collector/netdev_openbsd.go index b90e3ba7ab..31c2640bb6 100644 --- a/collector/netdev_openbsd.go +++ b/collector/netdev_openbsd.go @@ -18,9 +18,7 @@ package collector import ( "errors" - - "github.com/go-kit/log" - "github.com/go-kit/log/level" + "log/slog" ) /* @@ -31,7 +29,7 @@ import ( */ import "C" -func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) { +func getNetDevStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { netDev := netDevStats{} var ifap, ifa *C.struct_ifaddrs @@ -47,7 +45,7 @@ func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error dev := C.GoString(ifa.ifa_name) if filter.ignored(dev) { - level.Debug(logger).Log("msg", "Ignoring device", "device", dev) + logger.Debug("Ignoring device", "device", dev) continue } @@ -72,3 +70,8 @@ func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error return netDev, nil } + +func getNetDevLabels() (map[string]map[string]string, error) { + // to be implemented if needed + return nil, nil +} diff --git a/collector/netdev_openbsd_amd64.go b/collector/netdev_openbsd_amd64.go index da8a81f34e..e98571648e 100644 --- a/collector/netdev_openbsd_amd64.go +++ b/collector/netdev_openbsd_amd64.go @@ -17,14 +17,14 @@ package collector import ( - "github.com/go-kit/log" - "github.com/go-kit/log/level" + "log/slog" - "golang.org/x/sys/unix" "unsafe" + + "golang.org/x/sys/unix" ) -func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error) { +func getNetDevStats(filter *deviceFilter, logger *slog.Logger) (netDevStats, error) { netDev := netDevStats{} mib := [6]_C_int{unix.CTL_NET, unix.AF_ROUTE, 0, 0, unix.NET_RT_IFLIST, 0} @@ -54,7 +54,7 @@ func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error data := ifm.Data dev := int8ToString(dl.Data[:dl.Nlen]) if filter.ignored(dev) { - level.Debug(logger).Log("msg", "Ignoring device", "device", dev) + logger.Debug("Ignoring device", "device", dev) continue } @@ -76,3 +76,8 @@ func getNetDevStats(filter *deviceFilter, logger log.Logger) (netDevStats, error } return netDev, nil } + +func getNetDevLabels() (map[string]map[string]string, error) { + // to be implemented if needed + return nil, nil +} diff --git a/collector/netisr_freebsd.go b/collector/netisr_freebsd.go index 442bcdc6a7..b3a4451c5c 100644 --- a/collector/netisr_freebsd.go +++ b/collector/netisr_freebsd.go @@ -18,14 +18,14 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) type netisrCollector struct { sysctls []bsdSysctl - logger log.Logger + logger *slog.Logger } const ( @@ -36,7 +36,7 @@ func init() { registerCollector("netisr", defaultEnabled, NewNetisrCollector) } -func NewNetisrCollector(logger log.Logger) (Collector, error) { +func NewNetisrCollector(logger *slog.Logger) (Collector, error) { return &netisrCollector{ sysctls: []bsdSysctl{ { diff --git a/collector/netstat_freebsd.go b/collector/netstat_freebsd.go new file mode 100644 index 0000000000..3c34d8b33c --- /dev/null +++ b/collector/netstat_freebsd.go @@ -0,0 +1,108 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build freebsd +// +build freebsd + +package collector + +import ( + "errors" + "fmt" + "log/slog" + "unsafe" + + "github.com/prometheus/client_golang/prometheus" + "golang.org/x/sys/unix" +) + +/* +#include +#include +#include +#include +#include +#include +*/ +import "C" + +var ( + bsdNetstatTcpSendPacketsTotal = prometheus.NewDesc( + prometheus.BuildFQName(namespace, "netstat", "tcp_transmit_packets_total"), + "TCP packets sent", + nil, nil, + ) + + bsdNetstatTcpRecvPacketsTotal = prometheus.NewDesc( + prometheus.BuildFQName(namespace, "netstat", "tcp_receive_packets_total"), + "TCP packets received", + nil, nil, + ) +) + +type netStatCollector struct { + netStatMetric *prometheus.Desc +} + +func init() { + registerCollector("netstat", defaultEnabled, NewNetStatCollector) +} + +func NewNetStatCollector(logger *slog.Logger) (Collector, error) { + return &netStatCollector{}, nil +} + +func (c *netStatCollector) Describe(ch chan<- *prometheus.Desc) { + ch <- c.netStatMetric +} + +func (c *netStatCollector) Collect(ch chan<- prometheus.Metric) { + _ = c.Update(ch) +} + +func getData(queryString string) ([]byte, error) { + data, err := unix.SysctlRaw(queryString) + if err != nil { + fmt.Println("Error:", err) + return nil, err + } + + if len(data) < int(unsafe.Sizeof(C.struct_tcpstat{})) { + return nil, errors.New("Data Size mismatch") + } + return data, nil +} + +func (c *netStatCollector) Update(ch chan<- prometheus.Metric) error { + + tcpData, err := getData("net.inet.tcp.stats") + if err != nil { + return err + } + + tcpStats := *(*C.struct_tcpstat)(unsafe.Pointer(&tcpData[0])) + + ch <- prometheus.MustNewConstMetric( + bsdNetstatTcpSendPacketsTotal, + prometheus.CounterValue, + float64(tcpStats.tcps_sndtotal), + ) + + ch <- prometheus.MustNewConstMetric( + bsdNetstatTcpRecvPacketsTotal, + prometheus.CounterValue, + float64(tcpStats.tcps_rcvtotal), + ) + + return nil +} diff --git a/collector/netstat_freebsd_test.go b/collector/netstat_freebsd_test.go new file mode 100644 index 0000000000..3b3f852335 --- /dev/null +++ b/collector/netstat_freebsd_test.go @@ -0,0 +1,77 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build freebsd +// +build freebsd + +package collector + +import ( + "github.com/prometheus/client_golang/prometheus" + "golang.org/x/sys/unix" + "testing" + "unsafe" +) + +func TestNetStatCollectorDescribe(t *testing.T) { + ch := make(chan *prometheus.Desc, 1) + collector := &netStatCollector{ + netStatMetric: prometheus.NewDesc("dummy_metric", "dummy", nil, nil), + } + collector.Describe(ch) + desc := <-ch + + if want, got := "dummy_metric", desc.String(); want != got { + t.Errorf("want %s, got %s", want, got) + } +} + +func TestGetData(t *testing.T) { + data, err := getData("net.inet.tcp.stats") + if err != nil { + t.Fatal("unexpected error:", err) + } + + if got, want := len(data), int(unsafe.Sizeof(unix.TCPStats{})); got < want { + t.Errorf("data length too small: want >= %d, got %d", want, got) + } +} + +func TestNetStatCollectorUpdate(t *testing.T) { + ch := make(chan prometheus.Metric, len(metrics)) + collector := &netStatCollector{ + netStatMetric: prometheus.NewDesc("netstat_metric", "NetStat Metric", nil, nil), + } + err := collector.Update(ch) + if err != nil { + t.Fatal("unexpected error:", err) + } + + if got, want := len(ch), len(metrics); got != want { + t.Errorf("metric count mismatch: want %d, got %d", want, got) + } + + for range metrics { + <-ch + } +} + +func TestNewNetStatCollector(t *testing.T) { + collector, err := NewNetStatCollector(nil) + if err != nil { + t.Fatal("unexpected error:", err) + } + if collector == nil { + t.Fatal("collector is nil, want non-nil") + } +} diff --git a/collector/netstat_linux.go b/collector/netstat_linux.go index 8e4c9f4de8..1aa9234004 100644 --- a/collector/netstat_linux.go +++ b/collector/netstat_linux.go @@ -21,13 +21,13 @@ import ( "errors" "fmt" "io" + "log/slog" "os" "regexp" "strconv" "strings" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -36,12 +36,12 @@ const ( ) var ( - netStatFields = kingpin.Flag("collector.netstat.fields", "Regexp of fields to return for netstat collector.").Default("^(.*_(InErrors|InErrs)|Ip_Forwarding|Ip(6|Ext)_(InOctets|OutOctets)|Icmp6?_(InMsgs|OutMsgs)|TcpExt_(Listen.*|Syncookies.*|TCPSynRetrans|TCPTimeouts|TCPOFOQueue)|Tcp_(ActiveOpens|InSegs|OutSegs|OutRsts|PassiveOpens|RetransSegs|CurrEstab)|Udp6?_(InDatagrams|OutDatagrams|NoPorts|RcvbufErrors|SndbufErrors))$").String() + netStatFields = kingpin.Flag("collector.netstat.fields", "Regexp of fields to return for netstat collector.").Default("^(.*_(InErrors|InErrs)|Ip_Forwarding|Ip(6|Ext)_(InOctets|OutOctets)|Icmp6?_(InMsgs|OutMsgs)|TcpExt_(Listen.*|Syncookies.*|TCPSynRetrans|TCPTimeouts|TCPOFOQueue|TCPRcvQDrop)|Tcp_(ActiveOpens|InSegs|OutSegs|OutRsts|PassiveOpens|RetransSegs|CurrEstab)|Udp6?_(InDatagrams|OutDatagrams|NoPorts|RcvbufErrors|SndbufErrors))$").String() ) type netStatCollector struct { fieldPattern *regexp.Regexp - logger log.Logger + logger *slog.Logger } func init() { @@ -50,7 +50,7 @@ func init() { // NewNetStatCollector takes and returns // a new Collector exposing network stats. -func NewNetStatCollector(logger log.Logger) (Collector, error) { +func NewNetStatCollector(logger *slog.Logger) (Collector, error) { pattern := regexp.MustCompile(*netStatFields) return &netStatCollector{ fieldPattern: pattern, diff --git a/collector/network_route_linux.go b/collector/network_route_linux.go index c77e175109..5a5c34d29d 100644 --- a/collector/network_route_linux.go +++ b/collector/network_route_linux.go @@ -18,19 +18,19 @@ package collector import ( "fmt" - "golang.org/x/sys/unix" + "log/slog" "net" "strconv" - "github.com/go-kit/log" - "github.com/jsimonetti/rtnetlink" + "github.com/jsimonetti/rtnetlink/v2" "github.com/prometheus/client_golang/prometheus" + "golang.org/x/sys/unix" ) type networkRouteCollector struct { routeInfoDesc *prometheus.Desc routesDesc *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -38,7 +38,7 @@ func init() { } // NewNetworkRouteCollector returns a new Collector exposing systemd statistics. -func NewNetworkRouteCollector(logger log.Logger) (Collector, error) { +func NewNetworkRouteCollector(logger *slog.Logger) (Collector, error) { const subsystem = "network" routeInfoDesc := prometheus.NewDesc( diff --git a/collector/nfs_linux.go b/collector/nfs_linux.go index e08acdbad7..ea2a1b5259 100644 --- a/collector/nfs_linux.go +++ b/collector/nfs_linux.go @@ -19,11 +19,10 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "reflect" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/nfs" ) @@ -40,7 +39,7 @@ type nfsCollector struct { nfsRPCRetransmissionsDesc *prometheus.Desc nfsRPCAuthenticationRefreshesDesc *prometheus.Desc nfsProceduresDesc *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -48,7 +47,7 @@ func init() { } // NewNfsCollector returns a new Collector exposing NFS statistics. -func NewNfsCollector(logger log.Logger) (Collector, error) { +func NewNfsCollector(logger *slog.Logger) (Collector, error) { fs, err := nfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -100,7 +99,7 @@ func (c *nfsCollector) Update(ch chan<- prometheus.Metric) error { stats, err := c.fs.ClientRPCStats() if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "Not collecting NFS metrics", "err", err) + c.logger.Debug("Not collecting NFS metrics", "err", err) return ErrNoData } return fmt.Errorf("failed to retrieve nfs stats: %w", err) diff --git a/collector/nfsd_linux.go b/collector/nfsd_linux.go index 8b310ea23c..7f1bc24072 100644 --- a/collector/nfsd_linux.go +++ b/collector/nfsd_linux.go @@ -19,10 +19,9 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/nfs" ) @@ -32,7 +31,7 @@ import ( type nfsdCollector struct { fs nfs.FS requestsDesc *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -44,7 +43,7 @@ const ( ) // NewNFSdCollector returns a new Collector exposing /proc/net/rpc/nfsd statistics. -func NewNFSdCollector(logger log.Logger) (Collector, error) { +func NewNFSdCollector(logger *slog.Logger) (Collector, error) { fs, err := nfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -66,7 +65,7 @@ func (c *nfsdCollector) Update(ch chan<- prometheus.Metric) error { stats, err := c.fs.ServerRPCStats() if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "Not collecting NFSd metrics", "err", err) + c.logger.Debug("Not collecting NFSd metrics", "err", err) return ErrNoData } return fmt.Errorf("failed to retrieve nfsd stats: %w", err) diff --git a/collector/ntp.go b/collector/ntp.go index 6cff69cafc..406920e359 100644 --- a/collector/ntp.go +++ b/collector/ntp.go @@ -18,14 +18,13 @@ package collector import ( "fmt" + "log/slog" "net" "sync" "time" "github.com/alecthomas/kingpin/v2" "github.com/beevik/ntp" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -51,7 +50,7 @@ var ( type ntpCollector struct { stratum, leap, rtt, offset, reftime, rootDelay, rootDispersion, sanity typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -62,7 +61,7 @@ func init() { // Default definition of "local" is: // - collector.ntp.server address is a loopback address (or collector.ntp.server-is-mine flag is turned on) // - the server is reachable with outgoing IP_TTL = 1 -func NewNtpCollector(logger log.Logger) (Collector, error) { +func NewNtpCollector(logger *slog.Logger) (Collector, error) { ipaddr := net.ParseIP(*ntpServer) if !*ntpServerIsLocal && (ipaddr == nil || !ipaddr.IsLoopback()) { return nil, fmt.Errorf("only IP address of local NTP server is valid for --collector.ntp.server") @@ -80,7 +79,7 @@ func NewNtpCollector(logger log.Logger) (Collector, error) { return nil, fmt.Errorf("invalid NTP port number %d; must be between 1 and 65535 inclusive", *ntpServerPort) } - level.Warn(logger).Log("msg", "This collector is deprecated and will be removed in the next major version release.") + logger.Warn("This collector is deprecated and will be removed in the next major version release.") return &ntpCollector{ stratum: typedDesc{prometheus.NewDesc( prometheus.BuildFQName(namespace, ntpSubsystem, "stratum"), diff --git a/collector/nvme_linux.go b/collector/nvme_linux.go index 81d4ab2985..d1a9a87b55 100644 --- a/collector/nvme_linux.go +++ b/collector/nvme_linux.go @@ -19,17 +19,16 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) type nvmeCollector struct { fs sysfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -37,7 +36,7 @@ func init() { } // NewNVMeCollector returns a new Collector exposing NVMe stats. -func NewNVMeCollector(logger log.Logger) (Collector, error) { +func NewNVMeCollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) @@ -53,7 +52,7 @@ func (c *nvmeCollector) Update(ch chan<- prometheus.Metric) error { devices, err := c.fs.NVMeClass() if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "nvme statistics not found, skipping") + c.logger.Debug("nvme statistics not found, skipping") return ErrNoData } return fmt.Errorf("error obtaining NVMe class info: %w", err) diff --git a/collector/os_release.go b/collector/os_release.go index 4c86740e61..e589c4ff9e 100644 --- a/collector/os_release.go +++ b/collector/os_release.go @@ -11,12 +11,16 @@ // See the License for the specific language governing permissions and // limitations under the License. +//go:build !noosrelease && !aix +// +build !noosrelease,!aix + package collector import ( "encoding/xml" "errors" "io" + "log/slog" "os" "regexp" "strconv" @@ -24,8 +28,6 @@ import ( "sync" "time" - "github.com/go-kit/log" - "github.com/go-kit/log/level" envparse "github.com/hashicorp/go-envparse" "github.com/prometheus/client_golang/prometheus" ) @@ -58,7 +60,7 @@ type osRelease struct { type osReleaseCollector struct { infoDesc *prometheus.Desc - logger log.Logger + logger *slog.Logger os *osRelease osMutex sync.RWMutex osReleaseFilenames []string // all os-release file names to check @@ -82,7 +84,7 @@ func init() { } // NewOSCollector returns a new Collector exposing os-release information. -func NewOSCollector(logger log.Logger) (Collector, error) { +func NewOSCollector(logger *slog.Logger) (Collector, error) { return &osReleaseCollector{ logger: logger, infoDesc: prometheus.NewDesc( @@ -178,7 +180,7 @@ func (c *osReleaseCollector) Update(ch chan<- prometheus.Metric) error { } if errors.Is(err, os.ErrNotExist) { if i >= (len(c.osReleaseFilenames) - 1) { - level.Debug(c.logger).Log("msg", "no os-release file found", "files", strings.Join(c.osReleaseFilenames, ",")) + c.logger.Debug("no os-release file found", "files", strings.Join(c.osReleaseFilenames, ",")) return ErrNoData } continue diff --git a/collector/os_release_test.go b/collector/os_release_test.go index b45ee0edfa..e5d6b501f0 100644 --- a/collector/os_release_test.go +++ b/collector/os_release_test.go @@ -14,12 +14,12 @@ package collector import ( + "io" + "log/slog" "os" "reflect" "strings" "testing" - - "github.com/go-kit/log" ) const debianBullseye string = `PRETTY_NAME="Debian GNU/Linux 11 (bullseye)" @@ -129,7 +129,7 @@ func TestUpdateStruct(t *testing.T) { } wantedVersion := 20.04 - collector, err := NewOSCollector(log.NewNopLogger()) + collector, err := NewOSCollector(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { t.Fatal(err) } diff --git a/collector/perf_linux.go b/collector/perf_linux.go index 8934371ad0..b62d9b8016 100644 --- a/collector/perf_linux.go +++ b/collector/perf_linux.go @@ -18,13 +18,12 @@ package collector import ( "fmt" + "log/slog" "runtime" "strconv" "strings" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/hodgesds/perf-utils" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" @@ -189,7 +188,7 @@ type perfCollector struct { perfSwProfilers map[int]*perf.SoftwareProfiler perfCacheProfilers map[int]*perf.CacheProfiler desc map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger tracepointCollector *perfTracepointCollector } @@ -199,7 +198,7 @@ type perfTracepointCollector struct { // collection order is the sorted configured collection order of the profiler. collectionOrder []string - logger log.Logger + logger *slog.Logger profilers map[int]perf.GroupProfiler } @@ -218,7 +217,7 @@ func (c *perfTracepointCollector) updateCPU(cpu int, ch chan<- prometheus.Metric profiler := c.profilers[cpu] p := &perf.GroupProfileValue{} if err := profiler.Profile(p); err != nil { - level.Error(c.logger).Log("msg", "Failed to collect tracepoint profile", "err", err) + c.logger.Error("Failed to collect tracepoint profile", "err", err) return err } @@ -240,7 +239,7 @@ func (c *perfTracepointCollector) updateCPU(cpu int, ch chan<- prometheus.Metric // newPerfTracepointCollector returns a configured perfTracepointCollector. func newPerfTracepointCollector( - logger log.Logger, + logger *slog.Logger, tracepointsFlag []string, cpus []int, ) (*perfTracepointCollector, error) { @@ -301,7 +300,7 @@ func newPerfTracepointCollector( // NewPerfCollector returns a new perf based collector, it creates a profiler // per CPU. -func NewPerfCollector(logger log.Logger) (Collector, error) { +func NewPerfCollector(logger *slog.Logger) (Collector, error) { collector := &perfCollector{ perfHwProfilers: map[int]*perf.HardwareProfiler{}, perfSwProfilers: map[int]*perf.SoftwareProfiler{}, diff --git a/collector/perf_linux_test.go b/collector/perf_linux_test.go index fc557ffd32..e385851153 100644 --- a/collector/perf_linux_test.go +++ b/collector/perf_linux_test.go @@ -17,13 +17,14 @@ package collector import ( + "io" + "log/slog" "os" "runtime" "strconv" "strings" "testing" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -44,7 +45,7 @@ func canTestPerf(t *testing.T) { func TestPerfCollector(t *testing.T) { canTestPerf(t) - collector, err := NewPerfCollector(log.NewNopLogger()) + collector, err := NewPerfCollector(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { t.Fatal(err) } @@ -97,7 +98,7 @@ func TestPerfCollectorStride(t *testing.T) { } } perfCPUsFlag = &test.flag - collector, err := NewPerfCollector(log.NewNopLogger()) + collector, err := NewPerfCollector(slog.New(slog.NewTextHandler(io.Discard, nil))) if err != nil { t.Fatal(err) } diff --git a/collector/powersupplyclass.go b/collector/powersupplyclass.go index 7f231dac47..a5e648c098 100644 --- a/collector/powersupplyclass.go +++ b/collector/powersupplyclass.go @@ -18,10 +18,10 @@ package collector import ( + "log/slog" "regexp" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -33,14 +33,14 @@ type powerSupplyClassCollector struct { subsystem string ignoredPattern *regexp.Regexp metricDescs map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { registerCollector("powersupplyclass", defaultEnabled, NewPowerSupplyClassCollector) } -func NewPowerSupplyClassCollector(logger log.Logger) (Collector, error) { +func NewPowerSupplyClassCollector(logger *slog.Logger) (Collector, error) { pattern := regexp.MustCompile(*powerSupplyClassIgnoredPowerSupplies) return &powerSupplyClassCollector{ subsystem: "power_supply", diff --git a/collector/pressure_linux.go b/collector/pressure_linux.go index f64d004fa6..63b32d2a2a 100644 --- a/collector/pressure_linux.go +++ b/collector/pressure_linux.go @@ -19,17 +19,23 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "syscall" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) +const ( + psiResourceCPU = "cpu" + psiResourceIO = "io" + psiResourceMemory = "memory" + psiResourceIRQ = "irq" +) + var ( - psiResources = []string{"cpu", "io", "memory"} + psiResources = []string{psiResourceCPU, psiResourceIO, psiResourceMemory, psiResourceIRQ} ) type pressureStatsCollector struct { @@ -38,10 +44,11 @@ type pressureStatsCollector struct { ioFull *prometheus.Desc mem *prometheus.Desc memFull *prometheus.Desc + irqFull *prometheus.Desc fs procfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -49,7 +56,7 @@ func init() { } // NewPressureStatsCollector returns a Collector exposing pressure stall information -func NewPressureStatsCollector(logger log.Logger) (Collector, error) { +func NewPressureStatsCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -81,6 +88,11 @@ func NewPressureStatsCollector(logger log.Logger) (Collector, error) { "Total time in seconds no process could make progress due to memory congestion", nil, nil, ), + irqFull: prometheus.NewDesc( + prometheus.BuildFQName(namespace, "pressure", "irq_stalled_seconds_total"), + "Total time in seconds no process could make progress due to IRQ congestion", + nil, nil, + ), fs: fs, logger: logger, }, nil @@ -88,40 +100,56 @@ func NewPressureStatsCollector(logger log.Logger) (Collector, error) { // Update calls procfs.NewPSIStatsForResource for the different resources and updates the values func (c *pressureStatsCollector) Update(ch chan<- prometheus.Metric) error { + foundResources := 0 for _, res := range psiResources { - level.Debug(c.logger).Log("msg", "collecting statistics for resource", "resource", res) + c.logger.Debug("collecting statistics for resource", "resource", res) vals, err := c.fs.PSIStatsForResource(res) if err != nil { - if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "pressure information is unavailable, you need a Linux kernel >= 4.20 and/or CONFIG_PSI enabled for your kernel") - return ErrNoData + if errors.Is(err, os.ErrNotExist) && res != psiResourceIRQ { + c.logger.Debug("pressure information is unavailable, you need a Linux kernel >= 4.20 and/or CONFIG_PSI enabled for your kernel", "resource", res) + continue + } + if errors.Is(err, os.ErrNotExist) && res == psiResourceIRQ { + c.logger.Debug("IRQ pressure information is unavailable, you need a Linux kernel >= 6.1 and/or CONFIG_PSI enabled for your kernel", "resource", res) + continue } if errors.Is(err, syscall.ENOTSUP) { - level.Debug(c.logger).Log("msg", "pressure information is disabled, add psi=1 kernel command line to enable it") + c.logger.Debug("pressure information is disabled, add psi=1 kernel command line to enable it") return ErrNoData } return fmt.Errorf("failed to retrieve pressure stats: %w", err) } - if vals.Some == nil { - level.Debug(c.logger).Log("msg", "pressure information returned no 'some' data") + // IRQ pressure does not have 'some' data. + // See https://github.com/torvalds/linux/blob/v6.9/include/linux/psi_types.h#L65 + if vals.Some == nil && res != psiResourceIRQ { + c.logger.Debug("pressure information returned no 'some' data") return ErrNoData } - if vals.Full == nil && res != "cpu" { - level.Debug(c.logger).Log("msg", "pressure information returned no 'full' data") + if vals.Full == nil && res != psiResourceCPU { + c.logger.Debug("pressure information returned no 'full' data") return ErrNoData } switch res { - case "cpu": + case psiResourceCPU: ch <- prometheus.MustNewConstMetric(c.cpu, prometheus.CounterValue, float64(vals.Some.Total)/1000.0/1000.0) - case "io": + case psiResourceIO: ch <- prometheus.MustNewConstMetric(c.io, prometheus.CounterValue, float64(vals.Some.Total)/1000.0/1000.0) ch <- prometheus.MustNewConstMetric(c.ioFull, prometheus.CounterValue, float64(vals.Full.Total)/1000.0/1000.0) - case "memory": + case psiResourceMemory: ch <- prometheus.MustNewConstMetric(c.mem, prometheus.CounterValue, float64(vals.Some.Total)/1000.0/1000.0) ch <- prometheus.MustNewConstMetric(c.memFull, prometheus.CounterValue, float64(vals.Full.Total)/1000.0/1000.0) + case psiResourceIRQ: + ch <- prometheus.MustNewConstMetric(c.irqFull, prometheus.CounterValue, float64(vals.Full.Total)/1000.0/1000.0) default: - level.Debug(c.logger).Log("msg", "did not account for resource", "resource", res) + c.logger.Debug("did not account for resource", "resource", res) + continue } + foundResources++ + } + + if foundResources == 0 { + c.logger.Debug("pressure information is unavailable, you need a Linux kernel >= 4.20 and/or CONFIG_PSI enabled for your kernel") + return ErrNoData } return nil diff --git a/collector/processes_linux.go b/collector/processes_linux.go index 798aeaeb30..653045e553 100644 --- a/collector/processes_linux.go +++ b/collector/processes_linux.go @@ -19,14 +19,13 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "path" "strconv" "strings" "syscall" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -39,7 +38,7 @@ type processCollector struct { procsState *prometheus.Desc pidUsed *prometheus.Desc pidMax *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -47,7 +46,7 @@ func init() { } // NewProcessStatCollector returns a new Collector exposing process data read from the proc filesystem. -func NewProcessStatCollector(logger log.Logger) (Collector, error) { +func NewProcessStatCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -130,10 +129,10 @@ func (c *processCollector) getAllocatedThreads() (int, map[string]int32, int, ma if err != nil { // PIDs can vanish between getting the list and getting stats. if c.isIgnoredError(err) { - level.Debug(c.logger).Log("msg", "file not found when retrieving stats for pid", "pid", pid.PID, "err", err) + c.logger.Debug("file not found when retrieving stats for pid", "pid", pid.PID, "err", err) continue } - level.Debug(c.logger).Log("msg", "error reading stat for pid", "pid", pid.PID, "err", err) + c.logger.Debug("error reading stat for pid", "pid", pid.PID, "err", err) return 0, nil, 0, nil, fmt.Errorf("error reading stat for pid %d: %w", pid.PID, err) } pids++ @@ -151,17 +150,17 @@ func (c *processCollector) getThreadStates(pid int, pidStat procfs.ProcStat, thr fs, err := procfs.NewFS(procFilePath(path.Join(strconv.Itoa(pid), "task"))) if err != nil { if c.isIgnoredError(err) { - level.Debug(c.logger).Log("msg", "file not found when retrieving tasks for pid", "pid", pid, "err", err) + c.logger.Debug("file not found when retrieving tasks for pid", "pid", pid, "err", err) return nil } - level.Debug(c.logger).Log("msg", "error reading tasks for pid", "pid", pid, "err", err) + c.logger.Debug("error reading tasks for pid", "pid", pid, "err", err) return fmt.Errorf("error reading task for pid %d: %w", pid, err) } t, err := fs.AllProcs() if err != nil { if c.isIgnoredError(err) { - level.Debug(c.logger).Log("msg", "file not found when retrieving tasks for pid", "pid", pid, "err", err) + c.logger.Debug("file not found when retrieving tasks for pid", "pid", pid, "err", err) return nil } return fmt.Errorf("unable to list all threads for pid: %d %w", pid, err) @@ -175,10 +174,10 @@ func (c *processCollector) getThreadStates(pid int, pidStat procfs.ProcStat, thr threadStat, err := thread.Stat() if err != nil { if c.isIgnoredError(err) { - level.Debug(c.logger).Log("msg", "file not found when retrieving stats for thread", "pid", pid, "threadId", thread.PID, "err", err) + c.logger.Debug("file not found when retrieving stats for thread", "pid", pid, "threadId", thread.PID, "err", err) continue } - level.Debug(c.logger).Log("msg", "error reading stat for thread", "pid", pid, "threadId", thread.PID, "err", err) + c.logger.Debug("error reading stat for thread", "pid", pid, "threadId", thread.PID, "err", err) return fmt.Errorf("error reading stat for pid:%d thread:%d err:%w", pid, thread.PID, err) } threadStates[threadStat.State]++ diff --git a/collector/processes_linux_test.go b/collector/processes_linux_test.go index e2814a0104..c50d16c8db 100644 --- a/collector/processes_linux_test.go +++ b/collector/processes_linux_test.go @@ -17,10 +17,11 @@ package collector import ( + "io" + "log/slog" "testing" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/procfs" ) @@ -33,7 +34,7 @@ func TestReadProcessStatus(t *testing.T) { if err != nil { t.Errorf("failed to open procfs: %v", err) } - c := processCollector{fs: fs, logger: log.NewNopLogger()} + c := processCollector{fs: fs, logger: slog.New(slog.NewTextHandler(io.Discard, nil))} pids, states, threads, _, err := c.getAllocatedThreads() if err != nil { t.Fatalf("Cannot retrieve data from procfs getAllocatedThreads function: %v ", err) diff --git a/collector/qdisc_linux.go b/collector/qdisc_linux.go index 06ab6a88d6..93a78e3b19 100644 --- a/collector/qdisc_linux.go +++ b/collector/qdisc_linux.go @@ -19,18 +19,17 @@ package collector import ( "encoding/json" "fmt" + "log/slog" "os" "path/filepath" "github.com/alecthomas/kingpin/v2" "github.com/ema/qdisc" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) type qdiscStatCollector struct { - logger log.Logger + logger *slog.Logger deviceFilter deviceFilter bytes typedDesc packets typedDesc @@ -54,10 +53,10 @@ func init() { } // NewQdiscStatCollector returns a new Collector exposing queuing discipline statistics. -func NewQdiscStatCollector(logger log.Logger) (Collector, error) { +func NewQdiscStatCollector(logger *slog.Logger) (Collector, error) { if *oldCollectorQdiskDeviceInclude != "" { if *collectorQdiscDeviceInclude == "" { - level.Warn(logger).Log("msg", "--collector.qdisk.device-include is DEPRECATED and will be removed in 2.0.0, use --collector.qdisc.device-include") + logger.Warn("--collector.qdisk.device-include is DEPRECATED and will be removed in 2.0.0, use --collector.qdisc.device-include") *collectorQdiscDeviceInclude = *oldCollectorQdiskDeviceInclude } else { return nil, fmt.Errorf("--collector.qdisk.device-include and --collector.qdisc.device-include are mutually exclusive") @@ -66,7 +65,7 @@ func NewQdiscStatCollector(logger log.Logger) (Collector, error) { if *oldCollectorQdiskDeviceExclude != "" { if *collectorQdiscDeviceExclude == "" { - level.Warn(logger).Log("msg", "--collector.qdisk.device-exclude is DEPRECATED and will be removed in 2.0.0, use --collector.qdisc.device-exclude") + logger.Warn("--collector.qdisk.device-exclude is DEPRECATED and will be removed in 2.0.0, use --collector.qdisc.device-exclude") *collectorQdiscDeviceExclude = *oldCollectorQdiskDeviceExclude } else { return nil, fmt.Errorf("--collector.qdisk.device-exclude and --collector.qdisc.device-exclude are mutually exclusive") diff --git a/collector/rapl_linux.go b/collector/rapl_linux.go index 642de6c146..25d78f295c 100644 --- a/collector/rapl_linux.go +++ b/collector/rapl_linux.go @@ -19,12 +19,11 @@ package collector import ( "errors" "fmt" + "log/slog" "os" "strconv" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -33,7 +32,7 @@ const raplCollectorSubsystem = "rapl" type raplCollector struct { fs sysfs.FS - logger log.Logger + logger *slog.Logger joulesMetricDesc *prometheus.Desc } @@ -47,7 +46,7 @@ var ( ) // NewRaplCollector returns a new Collector exposing RAPL metrics. -func NewRaplCollector(logger log.Logger) (Collector, error) { +func NewRaplCollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { @@ -74,11 +73,11 @@ func (c *raplCollector) Update(ch chan<- prometheus.Metric) error { zones, err := sysfs.GetRaplZones(c.fs) if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "Platform doesn't have powercap files present", "err", err) + c.logger.Debug("Platform doesn't have powercap files present", "err", err) return ErrNoData } if errors.Is(err, os.ErrPermission) { - level.Debug(c.logger).Log("msg", "Can't access powercap files", "err", err) + c.logger.Debug("Can't access powercap files", "err", err) return ErrNoData } return fmt.Errorf("failed to retrieve rapl stats: %w", err) @@ -88,7 +87,7 @@ func (c *raplCollector) Update(ch chan<- prometheus.Metric) error { microJoules, err := rz.GetEnergyMicrojoules() if err != nil { if errors.Is(err, os.ErrPermission) { - level.Debug(c.logger).Log("msg", "Can't access energy_uj file", "zone", rz, "err", err) + c.logger.Debug("Can't access energy_uj file", "zone", rz, "err", err) return ErrNoData } return err diff --git a/collector/runit.go b/collector/runit.go index 3cae657c33..2813bfd0f3 100644 --- a/collector/runit.go +++ b/collector/runit.go @@ -17,9 +17,9 @@ package collector import ( + "log/slog" + "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus-community/go-runit/runit" "github.com/prometheus/client_golang/prometheus" ) @@ -31,7 +31,7 @@ type runitCollector struct { stateDesired typedDesc stateNormal typedDesc stateTimestamp typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -39,14 +39,14 @@ func init() { } // NewRunitCollector returns a new Collector exposing runit statistics. -func NewRunitCollector(logger log.Logger) (Collector, error) { +func NewRunitCollector(logger *slog.Logger) (Collector, error) { var ( subsystem = "service" constLabels = prometheus.Labels{"supervisor": "runit"} labelNames = []string{"service"} ) - level.Warn(logger).Log("msg", "This collector is deprecated and will be removed in the next major version release.") + logger.Warn("This collector is deprecated and will be removed in the next major version release.") return &runitCollector{ state: typedDesc{prometheus.NewDesc( @@ -82,11 +82,11 @@ func (c *runitCollector) Update(ch chan<- prometheus.Metric) error { for _, service := range services { status, err := service.Status() if err != nil { - level.Debug(c.logger).Log("msg", "Couldn't get status", "service", service.Name, "err", err) + c.logger.Debug("Couldn't get status", "service", service.Name, "err", err) continue } - level.Debug(c.logger).Log("msg", "duration", "service", service.Name, "status", status.State, "pid", status.Pid, "duration_seconds", status.Duration) + c.logger.Debug("duration", "service", service.Name, "status", status.State, "pid", status.Pid, "duration_seconds", status.Duration) ch <- c.state.mustNewConstMetric(float64(status.State), service.Name) ch <- c.stateDesired.mustNewConstMetric(float64(status.Want), service.Name) ch <- c.stateTimestamp.mustNewConstMetric(float64(status.Timestamp.Unix()), service.Name) diff --git a/collector/schedstat_linux.go b/collector/schedstat_linux.go index e5016561da..59b2bd8e1e 100644 --- a/collector/schedstat_linux.go +++ b/collector/schedstat_linux.go @@ -19,10 +19,9 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -53,7 +52,7 @@ var ( ) // NewSchedstatCollector returns a new Collector exposing task scheduler statistics -func NewSchedstatCollector(logger log.Logger) (Collector, error) { +func NewSchedstatCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -64,7 +63,7 @@ func NewSchedstatCollector(logger log.Logger) (Collector, error) { type schedstatCollector struct { fs procfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -75,7 +74,7 @@ func (c *schedstatCollector) Update(ch chan<- prometheus.Metric) error { stats, err := c.fs.Schedstat() if err != nil { if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "schedstat file does not exist") + c.logger.Debug("schedstat file does not exist") return ErrNoData } return err diff --git a/collector/selinux_linux.go b/collector/selinux_linux.go index 79316362fe..f10b43fa54 100644 --- a/collector/selinux_linux.go +++ b/collector/selinux_linux.go @@ -17,7 +17,8 @@ package collector import ( - "github.com/go-kit/log" + "log/slog" + "github.com/opencontainers/selinux/go-selinux" "github.com/prometheus/client_golang/prometheus" ) @@ -26,7 +27,7 @@ type selinuxCollector struct { configMode *prometheus.Desc currentMode *prometheus.Desc enabled *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -34,7 +35,7 @@ func init() { } // NewSelinuxCollector returns a new Collector exposing SELinux statistics. -func NewSelinuxCollector(logger log.Logger) (Collector, error) { +func NewSelinuxCollector(logger *slog.Logger) (Collector, error) { const subsystem = "selinux" return &selinuxCollector{ diff --git a/collector/slabinfo_linux.go b/collector/slabinfo_linux.go index a3c3ebced7..aa871548f0 100644 --- a/collector/slabinfo_linux.go +++ b/collector/slabinfo_linux.go @@ -18,33 +18,41 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" + "github.com/alecthomas/kingpin/v2" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) +var ( + slabNameInclude = kingpin.Flag("collector.slabinfo.slabs-include", "Regexp of slabs to include in slabinfo collector.").Default(".*").String() + slabNameExclude = kingpin.Flag("collector.slabinfo.slabs-exclude", "Regexp of slabs to exclude in slabinfo collector.").Default("").String() +) + type slabinfoCollector struct { - fs procfs.FS - logger log.Logger - subsystem string - labels []string + fs procfs.FS + logger *slog.Logger + subsystem string + labels []string + slabNameFilter deviceFilter } func init() { registerCollector("slabinfo", defaultDisabled, NewSlabinfoCollector) } -func NewSlabinfoCollector(logger log.Logger) (Collector, error) { +func NewSlabinfoCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) } return &slabinfoCollector{logger: logger, - fs: fs, - subsystem: "slabinfo", - labels: []string{"slab"}, + fs: fs, + subsystem: "slabinfo", + labels: []string{"slab"}, + slabNameFilter: newDeviceFilter(*slabNameExclude, *slabNameInclude), }, nil } @@ -55,6 +63,9 @@ func (c *slabinfoCollector) Update(ch chan<- prometheus.Metric) error { } for _, slab := range slabinfo.Slabs { + if c.slabNameFilter.ignored(slab.Name) { + continue + } ch <- c.activeObjects(slab.Name, slab.ObjActive) ch <- c.objects(slab.Name, slab.ObjNum) ch <- c.objectSizeBytes(slab.Name, slab.ObjSize) diff --git a/collector/sockstat_linux.go b/collector/sockstat_linux.go index 480c83b1da..73a3bf6836 100644 --- a/collector/sockstat_linux.go +++ b/collector/sockstat_linux.go @@ -19,10 +19,9 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -35,7 +34,7 @@ const ( var pageSize = os.Getpagesize() type sockStatCollector struct { - logger log.Logger + logger *slog.Logger } func init() { @@ -43,7 +42,7 @@ func init() { } // NewSockStatCollector returns a new Collector exposing socket stats. -func NewSockStatCollector(logger log.Logger) (Collector, error) { +func NewSockStatCollector(logger *slog.Logger) (Collector, error) { return &sockStatCollector{logger}, nil } @@ -58,7 +57,7 @@ func (c *sockStatCollector) Update(ch chan<- prometheus.Metric) error { switch { case err == nil: case errors.Is(err, os.ErrNotExist): - level.Debug(c.logger).Log("msg", "IPv4 sockstat statistics not found, skipping") + c.logger.Debug("IPv4 sockstat statistics not found, skipping") default: return fmt.Errorf("failed to get IPv4 sockstat data: %w", err) } @@ -67,7 +66,7 @@ func (c *sockStatCollector) Update(ch chan<- prometheus.Metric) error { switch { case err == nil: case errors.Is(err, os.ErrNotExist): - level.Debug(c.logger).Log("msg", "IPv6 sockstat statistics not found, skipping") + c.logger.Debug("IPv6 sockstat statistics not found, skipping") default: return fmt.Errorf("failed to get IPv6 sockstat data: %w", err) } diff --git a/collector/softirqs_common.go b/collector/softirqs_common.go index 08ef780f26..73a9f7be82 100644 --- a/collector/softirqs_common.go +++ b/collector/softirqs_common.go @@ -18,7 +18,8 @@ package collector import ( "fmt" - "github.com/go-kit/log" + "log/slog" + "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -26,7 +27,7 @@ import ( type softirqsCollector struct { fs procfs.FS desc typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -34,7 +35,7 @@ func init() { } // NewSoftirqsCollector returns a new Collector exposing softirq stats. -func NewSoftirqsCollector(logger log.Logger) (Collector, error) { +func NewSoftirqsCollector(logger *slog.Logger) (Collector, error) { desc := typedDesc{prometheus.NewDesc( namespace+"_softirqs_functions_total", "Softirq counts per CPU.", diff --git a/collector/softirq_linux.go b/collector/softirqs_linux.go similarity index 100% rename from collector/softirq_linux.go rename to collector/softirqs_linux.go diff --git a/collector/softnet_linux.go b/collector/softnet_linux.go index 42d47780e3..296e587587 100644 --- a/collector/softnet_linux.go +++ b/collector/softnet_linux.go @@ -18,9 +18,9 @@ package collector import ( "fmt" + "log/slog" "strconv" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -34,7 +34,7 @@ type softnetCollector struct { receivedRps *prometheus.Desc flowLimitCount *prometheus.Desc softnetBacklogLen *prometheus.Desc - logger log.Logger + logger *slog.Logger } const ( @@ -46,7 +46,7 @@ func init() { } // NewSoftnetCollector returns a new Collector exposing softnet metrics. -func NewSoftnetCollector(logger log.Logger) (Collector, error) { +func NewSoftnetCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) diff --git a/collector/stat_linux.go b/collector/stat_linux.go index 9974ae7aa7..0b99cc3236 100644 --- a/collector/stat_linux.go +++ b/collector/stat_linux.go @@ -18,9 +18,9 @@ package collector import ( "fmt" + "log/slog" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -34,7 +34,7 @@ type statCollector struct { procsRunning *prometheus.Desc procsBlocked *prometheus.Desc softIRQ *prometheus.Desc - logger log.Logger + logger *slog.Logger } var statSoftirqFlag = kingpin.Flag("collector.stat.softirq", "Export softirq calls per vector").Default("false").Bool() @@ -44,7 +44,7 @@ func init() { } // NewStatCollector returns a new Collector exposing kernel/system statistics. -func NewStatCollector(logger log.Logger) (Collector, error) { +func NewStatCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) diff --git a/collector/supervisord.go b/collector/supervisord.go index 8dc2e78e3c..ae5e2297a0 100644 --- a/collector/supervisord.go +++ b/collector/supervisord.go @@ -19,15 +19,14 @@ package collector import ( "context" "fmt" + "log/slog" "net" "net/http" "net/url" "time" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" - xmlrpc "github.com/mattn/go-xmlrpc" + "github.com/mattn/go-xmlrpc" "github.com/prometheus/client_golang/prometheus" ) @@ -41,7 +40,7 @@ type supervisordCollector struct { stateDesc *prometheus.Desc exitStatusDesc *prometheus.Desc startTimeDesc *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -49,7 +48,7 @@ func init() { } // NewSupervisordCollector returns a new Collector exposing supervisord statistics. -func NewSupervisordCollector(logger log.Logger) (Collector, error) { +func NewSupervisordCollector(logger *slog.Logger) (Collector, error) { var ( subsystem = "supervisord" labelNames = []string{"name", "group"} @@ -69,7 +68,7 @@ func NewSupervisordCollector(logger log.Logger) (Collector, error) { xrpc = xmlrpc.NewClient(*supervisordURL) } - level.Warn(logger).Log("msg", "This collector is deprecated and will be removed in the next major version release.") + logger.Warn("This collector is deprecated and will be removed in the next major version release.") return &supervisordCollector{ upDesc: prometheus.NewDesc( @@ -174,7 +173,7 @@ func (c *supervisordCollector) Update(ch chan<- prometheus.Metric) error { } else { ch <- prometheus.MustNewConstMetric(c.upDesc, prometheus.GaugeValue, 0, labels...) } - level.Debug(c.logger).Log("msg", "process info", "group", info.Group, "name", info.Name, "state", info.StateName, "pid", info.PID) + c.logger.Debug("process info", "group", info.Group, "name", info.Name, "state", info.StateName, "pid", info.PID) } return nil diff --git a/collector/sysctl_linux.go b/collector/sysctl_linux.go index c14341db85..ac7022fbdd 100644 --- a/collector/sysctl_linux.go +++ b/collector/sysctl_linux.go @@ -15,11 +15,11 @@ package collector import ( "fmt" + "log/slog" "strconv" "strings" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -33,7 +33,7 @@ var ( type sysctlCollector struct { fs procfs.FS - logger log.Logger + logger *slog.Logger sysctls []*sysctl } @@ -41,7 +41,7 @@ func init() { registerCollector("sysctl", defaultDisabled, NewSysctlCollector) } -func NewSysctlCollector(logger log.Logger) (Collector, error) { +func NewSysctlCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) diff --git a/collector/systemd_linux.go b/collector/systemd_linux.go index e0d35bcde6..ee2ded8d4a 100644 --- a/collector/systemd_linux.go +++ b/collector/systemd_linux.go @@ -20,6 +20,7 @@ import ( "context" "errors" "fmt" + "log/slog" "math" "regexp" "strconv" @@ -29,8 +30,6 @@ import ( "github.com/alecthomas/kingpin/v2" "github.com/coreos/go-systemd/v22/dbus" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -78,7 +77,7 @@ type systemdCollector struct { // Use regexps for more flexibility than device_filter.go allows systemdUnitIncludePattern *regexp.Regexp systemdUnitExcludePattern *regexp.Regexp - logger log.Logger + logger *slog.Logger } var unitStatesName = []string{"active", "activating", "deactivating", "inactive", "failed"} @@ -88,7 +87,7 @@ func init() { } // NewSystemdCollector returns a new Collector exposing systemd statistics. -func NewSystemdCollector(logger log.Logger) (Collector, error) { +func NewSystemdCollector(logger *slog.Logger) (Collector, error) { const subsystem = "systemd" unitDesc := prometheus.NewDesc( @@ -136,7 +135,7 @@ func NewSystemdCollector(logger log.Logger) (Collector, error) { if *oldSystemdUnitExclude != "" { if !systemdUnitExcludeSet { - level.Warn(logger).Log("msg", "--collector.systemd.unit-blacklist is DEPRECATED and will be removed in 2.0.0, use --collector.systemd.unit-exclude") + logger.Warn("--collector.systemd.unit-blacklist is DEPRECATED and will be removed in 2.0.0, use --collector.systemd.unit-exclude") *systemdUnitExclude = *oldSystemdUnitExclude } else { return nil, errors.New("--collector.systemd.unit-blacklist and --collector.systemd.unit-exclude are mutually exclusive") @@ -144,15 +143,15 @@ func NewSystemdCollector(logger log.Logger) (Collector, error) { } if *oldSystemdUnitInclude != "" { if !systemdUnitIncludeSet { - level.Warn(logger).Log("msg", "--collector.systemd.unit-whitelist is DEPRECATED and will be removed in 2.0.0, use --collector.systemd.unit-include") + logger.Warn("--collector.systemd.unit-whitelist is DEPRECATED and will be removed in 2.0.0, use --collector.systemd.unit-include") *systemdUnitInclude = *oldSystemdUnitInclude } else { return nil, errors.New("--collector.systemd.unit-whitelist and --collector.systemd.unit-include are mutually exclusive") } } - level.Info(logger).Log("msg", "Parsed flag --collector.systemd.unit-include", "flag", *systemdUnitInclude) + logger.Info("Parsed flag --collector.systemd.unit-include", "flag", *systemdUnitInclude) systemdUnitIncludePattern := regexp.MustCompile(fmt.Sprintf("^(?:%s)$", *systemdUnitInclude)) - level.Info(logger).Log("msg", "Parsed flag --collector.systemd.unit-exclude", "flag", *systemdUnitExclude) + logger.Info("Parsed flag --collector.systemd.unit-exclude", "flag", *systemdUnitExclude) systemdUnitExcludePattern := regexp.MustCompile(fmt.Sprintf("^(?:%s)$", *systemdUnitExclude)) return &systemdCollector{ @@ -186,7 +185,7 @@ func (c *systemdCollector) Update(ch chan<- prometheus.Metric) error { systemdVersion, systemdVersionFull := c.getSystemdVersion(conn) if systemdVersion < minSystemdVersionSystemState { - level.Debug(c.logger).Log("msg", "Detected systemd version is lower than minimum, some systemd state and timer metrics will not be available", "current", systemdVersion, "minimum", minSystemdVersionSystemState) + c.logger.Debug("Detected systemd version is lower than minimum, some systemd state and timer metrics will not be available", "current", systemdVersion, "minimum", minSystemdVersionSystemState) } ch <- prometheus.MustNewConstMetric( c.systemdVersionDesc, @@ -199,16 +198,16 @@ func (c *systemdCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { return fmt.Errorf("couldn't get units: %w", err) } - level.Debug(c.logger).Log("msg", "getAllUnits took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("getAllUnits took", "duration_seconds", time.Since(begin).Seconds()) begin = time.Now() summary := summarizeUnits(allUnits) c.collectSummaryMetrics(ch, summary) - level.Debug(c.logger).Log("msg", "collectSummaryMetrics took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("collectSummaryMetrics took", "duration_seconds", time.Since(begin).Seconds()) begin = time.Now() units := filterUnits(allUnits, c.systemdUnitIncludePattern, c.systemdUnitExcludePattern, c.logger) - level.Debug(c.logger).Log("msg", "filterUnits took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("filterUnits took", "duration_seconds", time.Since(begin).Seconds()) var wg sync.WaitGroup defer wg.Wait() @@ -218,7 +217,7 @@ func (c *systemdCollector) Update(ch chan<- prometheus.Metric) error { defer wg.Done() begin = time.Now() c.collectUnitStatusMetrics(conn, ch, units) - level.Debug(c.logger).Log("msg", "collectUnitStatusMetrics took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("collectUnitStatusMetrics took", "duration_seconds", time.Since(begin).Seconds()) }() if *enableStartTimeMetrics { @@ -227,7 +226,7 @@ func (c *systemdCollector) Update(ch chan<- prometheus.Metric) error { defer wg.Done() begin = time.Now() c.collectUnitStartTimeMetrics(conn, ch, units) - level.Debug(c.logger).Log("msg", "collectUnitStartTimeMetrics took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("collectUnitStartTimeMetrics took", "duration_seconds", time.Since(begin).Seconds()) }() } @@ -237,7 +236,7 @@ func (c *systemdCollector) Update(ch chan<- prometheus.Metric) error { defer wg.Done() begin = time.Now() c.collectUnitTasksMetrics(conn, ch, units) - level.Debug(c.logger).Log("msg", "collectUnitTasksMetrics took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("collectUnitTasksMetrics took", "duration_seconds", time.Since(begin).Seconds()) }() } @@ -247,7 +246,7 @@ func (c *systemdCollector) Update(ch chan<- prometheus.Metric) error { defer wg.Done() begin = time.Now() c.collectTimers(conn, ch, units) - level.Debug(c.logger).Log("msg", "collectTimers took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("collectTimers took", "duration_seconds", time.Since(begin).Seconds()) }() } @@ -256,13 +255,13 @@ func (c *systemdCollector) Update(ch chan<- prometheus.Metric) error { defer wg.Done() begin = time.Now() c.collectSockets(conn, ch, units) - level.Debug(c.logger).Log("msg", "collectSockets took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("collectSockets took", "duration_seconds", time.Since(begin).Seconds()) }() if systemdVersion >= minSystemdVersionSystemState { begin = time.Now() err = c.collectSystemState(conn, ch) - level.Debug(c.logger).Log("msg", "collectSystemState took", "duration_seconds", time.Since(begin).Seconds()) + c.logger.Debug("collectSystemState took", "duration_seconds", time.Since(begin).Seconds()) } return err @@ -274,14 +273,14 @@ func (c *systemdCollector) collectUnitStatusMetrics(conn *dbus.Conn, ch chan<- p if strings.HasSuffix(unit.Name, ".service") { serviceTypeProperty, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Service", "Type") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit type", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit type", "unit", unit.Name, "err", err) } else { serviceType = serviceTypeProperty.Value.Value().(string) } } else if strings.HasSuffix(unit.Name, ".mount") { serviceTypeProperty, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Mount", "Type") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit type", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit type", "unit", unit.Name, "err", err) } else { serviceType = serviceTypeProperty.Value.Value().(string) } @@ -299,7 +298,7 @@ func (c *systemdCollector) collectUnitStatusMetrics(conn *dbus.Conn, ch chan<- p // NRestarts wasn't added until systemd 235. restartsCount, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Service", "NRestarts") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit NRestarts", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit NRestarts", "unit", unit.Name, "err", err) } else { ch <- prometheus.MustNewConstMetric( c.nRestartsDesc, prometheus.CounterValue, @@ -317,7 +316,7 @@ func (c *systemdCollector) collectSockets(conn *dbus.Conn, ch chan<- prometheus. acceptedConnectionCount, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Socket", "NAccepted") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit NAccepted", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit NAccepted", "unit", unit.Name, "err", err) continue } ch <- prometheus.MustNewConstMetric( @@ -326,7 +325,7 @@ func (c *systemdCollector) collectSockets(conn *dbus.Conn, ch chan<- prometheus. currentConnectionCount, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Socket", "NConnections") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit NConnections", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit NConnections", "unit", unit.Name, "err", err) continue } ch <- prometheus.MustNewConstMetric( @@ -352,7 +351,7 @@ func (c *systemdCollector) collectUnitStartTimeMetrics(conn *dbus.Conn, ch chan< } else { timestampValue, err := conn.GetUnitPropertyContext(context.TODO(), unit.Name, "ActiveEnterTimestamp") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit StartTimeUsec", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit StartTimeUsec", "unit", unit.Name, "err", err) continue } startTimeUsec = timestampValue.Value.Value().(uint64) @@ -370,7 +369,7 @@ func (c *systemdCollector) collectUnitTasksMetrics(conn *dbus.Conn, ch chan<- pr if strings.HasSuffix(unit.Name, ".service") { tasksCurrentCount, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Service", "TasksCurrent") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit TasksCurrent", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit TasksCurrent", "unit", unit.Name, "err", err) } else { val = tasksCurrentCount.Value.Value().(uint64) // Don't set if tasksCurrent if dbus reports MaxUint64. @@ -382,7 +381,7 @@ func (c *systemdCollector) collectUnitTasksMetrics(conn *dbus.Conn, ch chan<- pr } tasksMaxCount, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Service", "TasksMax") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit TasksMax", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit TasksMax", "unit", unit.Name, "err", err) } else { val = tasksMaxCount.Value.Value().(uint64) // Don't set if tasksMax if dbus reports MaxUint64. @@ -404,7 +403,7 @@ func (c *systemdCollector) collectTimers(conn *dbus.Conn, ch chan<- prometheus.M lastTriggerValue, err := conn.GetUnitTypePropertyContext(context.TODO(), unit.Name, "Timer", "LastTriggerUSec") if err != nil { - level.Debug(c.logger).Log("msg", "couldn't get unit LastTriggerUSec", "unit", unit.Name, "err", err) + c.logger.Debug("couldn't get unit LastTriggerUSec", "unit", unit.Name, "err", err) continue } @@ -476,14 +475,14 @@ func summarizeUnits(units []unit) map[string]float64 { return summarized } -func filterUnits(units []unit, includePattern, excludePattern *regexp.Regexp, logger log.Logger) []unit { +func filterUnits(units []unit, includePattern, excludePattern *regexp.Regexp, logger *slog.Logger) []unit { filtered := make([]unit, 0, len(units)) for _, unit := range units { if includePattern.MatchString(unit.Name) && !excludePattern.MatchString(unit.Name) && unit.LoadState == "loaded" { - level.Debug(logger).Log("msg", "Adding unit", "unit", unit.Name) + logger.Debug("Adding unit", "unit", unit.Name) filtered = append(filtered, unit) } else { - level.Debug(logger).Log("msg", "Ignoring unit", "unit", unit.Name) + logger.Debug("Ignoring unit", "unit", unit.Name) } } @@ -493,15 +492,15 @@ func filterUnits(units []unit, includePattern, excludePattern *regexp.Regexp, lo func (c *systemdCollector) getSystemdVersion(conn *dbus.Conn) (float64, string) { version, err := conn.GetManagerProperty("Version") if err != nil { - level.Debug(c.logger).Log("msg", "Unable to get systemd version property, defaulting to 0") + c.logger.Debug("Unable to get systemd version property, defaulting to 0") return 0, "" } version = strings.TrimPrefix(strings.TrimSuffix(version, `"`), `"`) - level.Debug(c.logger).Log("msg", "Got systemd version", "version", version) + c.logger.Debug("Got systemd version", "version", version) parsedVersion := systemdVersionRE.FindString(version) v, err := strconv.ParseFloat(parsedVersion, 64) if err != nil { - level.Debug(c.logger).Log("msg", "Got invalid systemd version", "version", version) + c.logger.Debug("Got invalid systemd version", "version", version) return 0, "" } return v, version diff --git a/collector/systemd_linux_test.go b/collector/systemd_linux_test.go index d4e300d1d2..1c290377e6 100644 --- a/collector/systemd_linux_test.go +++ b/collector/systemd_linux_test.go @@ -17,11 +17,12 @@ package collector import ( + "io" + "log/slog" "regexp" "testing" "github.com/coreos/go-systemd/v22/dbus" - "github.com/go-kit/log" ) // Creates mock UnitLists @@ -94,7 +95,7 @@ func TestSystemdIgnoreFilter(t *testing.T) { fixtures := getUnitListFixtures() includePattern := regexp.MustCompile("^foo$") excludePattern := regexp.MustCompile("^bar$") - filtered := filterUnits(fixtures[0], includePattern, excludePattern, log.NewNopLogger()) + filtered := filterUnits(fixtures[0], includePattern, excludePattern, slog.New(slog.NewTextHandler(io.Discard, nil))) for _, unit := range filtered { if excludePattern.MatchString(unit.Name) || !includePattern.MatchString(unit.Name) { t.Error(unit.Name, "should not be in the filtered list") @@ -102,7 +103,7 @@ func TestSystemdIgnoreFilter(t *testing.T) { } } func TestSystemdIgnoreFilterDefaultKeepsAll(t *testing.T) { - logger := log.NewNopLogger() + logger := slog.New(slog.NewTextHandler(io.Discard, nil)) c, err := NewSystemdCollector(logger) if err != nil { t.Fatal(err) diff --git a/collector/tapestats_linux.go b/collector/tapestats_linux.go index 264c2210f1..c74c11d04c 100644 --- a/collector/tapestats_linux.go +++ b/collector/tapestats_linux.go @@ -18,12 +18,11 @@ package collector import ( "fmt" + "log/slog" "os" "regexp" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -45,7 +44,7 @@ type tapestatsCollector struct { writeTimeSeconds *prometheus.Desc residualTotal *prometheus.Desc fs sysfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -54,7 +53,7 @@ func init() { // NewTapestatsCollector returns a new Collector exposing tape device stats. // Docs from https://www.kernel.org/doc/html/latest/scsi/st.html#sysfs-and-statistics-for-tape-devices -func NewTapestatsCollector(logger log.Logger) (Collector, error) { +func NewTapestatsCollector(logger *slog.Logger) (Collector, error) { var tapeLabelNames = []string{"device"} fs, err := sysfs.NewFS(*sysPath) @@ -126,7 +125,7 @@ func (c *tapestatsCollector) Update(ch chan<- prometheus.Metric) error { tapes, err := c.fs.SCSITapeClass() if err != nil { if os.IsNotExist(err) { - level.Debug(c.logger).Log("msg", "scsi_tape stats not found, skipping") + c.logger.Debug("scsi_tape stats not found, skipping") return ErrNoData } return fmt.Errorf("error obtaining SCSITape class info: %s", err) @@ -134,7 +133,7 @@ func (c *tapestatsCollector) Update(ch chan<- prometheus.Metric) error { for _, tape := range tapes { if c.ignoredDevicesPattern.MatchString(tape.Name) { - level.Debug(c.logger).Log("msg", "Ignoring device", "device", tape.Name) + c.logger.Debug("Ignoring device", "device", tape.Name) continue } ch <- prometheus.MustNewConstMetric(c.ioNow, prometheus.GaugeValue, float64(tape.Counters.InFlight), tape.Name) diff --git a/collector/tcpstat_linux.go b/collector/tcpstat_linux.go index 99e33bc6a3..476a9b47bf 100644 --- a/collector/tcpstat_linux.go +++ b/collector/tcpstat_linux.go @@ -18,11 +18,11 @@ package collector import ( "fmt" + "log/slog" "os" "syscall" "unsafe" - "github.com/go-kit/log" "github.com/mdlayher/netlink" "github.com/prometheus/client_golang/prometheus" ) @@ -60,7 +60,7 @@ const ( type tcpStatCollector struct { desc typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -68,7 +68,7 @@ func init() { } // NewTCPStatCollector returns a new Collector exposing network stats. -func NewTCPStatCollector(logger log.Logger) (Collector, error) { +func NewTCPStatCollector(logger *slog.Logger) (Collector, error) { return &tcpStatCollector{ desc: typedDesc{prometheus.NewDesc( prometheus.BuildFQName(namespace, "tcp", "connection_states"), diff --git a/collector/textfile.go b/collector/textfile.go index 4f1fd0b8c7..3e0cc4592c 100644 --- a/collector/textfile.go +++ b/collector/textfile.go @@ -18,6 +18,7 @@ package collector import ( "fmt" + "log/slog" "os" "path/filepath" "sort" @@ -25,16 +26,14 @@ import ( "time" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" dto "github.com/prometheus/client_model/go" "github.com/prometheus/common/expfmt" ) var ( - textFileDirectory = kingpin.Flag("collector.textfile.directory", "Directory to read text files with metrics from.").Default("").String() - mtimeDesc = prometheus.NewDesc( + textFileDirectories = kingpin.Flag("collector.textfile.directory", "Directory to read text files with metrics from, supports glob matching. (repeatable)").Default("").Strings() + mtimeDesc = prometheus.NewDesc( "node_textfile_mtime_seconds", "Unixtime mtime of textfiles successfully read.", []string{"file"}, @@ -43,10 +42,10 @@ var ( ) type textFileCollector struct { - path string + paths []string // Only set for testing to get predictable output. mtime *float64 - logger log.Logger + logger *slog.Logger } func init() { @@ -55,15 +54,15 @@ func init() { // NewTextFileCollector returns a new Collector exposing metrics read from files // in the given textfile directory. -func NewTextFileCollector(logger log.Logger) (Collector, error) { +func NewTextFileCollector(logger *slog.Logger) (Collector, error) { c := &textFileCollector{ - path: *textFileDirectory, + paths: *textFileDirectories, logger: logger, } return c, nil } -func convertMetricFamily(metricFamily *dto.MetricFamily, ch chan<- prometheus.Metric, logger log.Logger) { +func convertMetricFamily(metricFamily *dto.MetricFamily, ch chan<- prometheus.Metric, logger *slog.Logger) { var valType prometheus.ValueType var val float64 @@ -79,7 +78,7 @@ func convertMetricFamily(metricFamily *dto.MetricFamily, ch chan<- prometheus.Me for _, metric := range metricFamily.Metric { if metric.TimestampMs != nil { - level.Warn(logger).Log("msg", "Ignoring unsupported custom timestamp on textfile collector metric", "metric", metric) + logger.Warn("Ignoring unsupported custom timestamp on textfile collector metric", "metric", metric) } labels := metric.GetLabel() @@ -195,11 +194,15 @@ func (c *textFileCollector) Update(ch chan<- prometheus.Metric) error { metricsNamesToFiles := map[string][]string{} metricsNamesToHelpTexts := map[string][2]string{} - paths, err := filepath.Glob(c.path) - if err != nil || len(paths) == 0 { - // not glob or not accessible path either way assume single - // directory and let os.ReadDir handle it - paths = []string{c.path} + paths := []string{} + for _, glob := range c.paths { + ps, err := filepath.Glob(glob) + if err != nil || len(ps) == 0 { + // not glob or not accessible path either way assume single + // directory and let os.ReadDir handle it + ps = []string{glob} + } + paths = append(paths, ps...) } mtimes := make(map[string]time.Time) @@ -207,7 +210,7 @@ func (c *textFileCollector) Update(ch chan<- prometheus.Metric) error { files, err := os.ReadDir(path) if err != nil && path != "" { errored = true - level.Error(c.logger).Log("msg", "failed to read textfile collector directory", "path", path, "err", err) + c.logger.Error("failed to read textfile collector directory", "path", path, "err", err) } for _, f := range files { @@ -224,7 +227,7 @@ func (c *textFileCollector) Update(ch chan<- prometheus.Metric) error { if mf.Help != nil && helpTexts[0] != *mf.Help || helpTexts[1] != "" { metricsNamesToHelpTexts[*mf.Name] = [2]string{helpTexts[0], *mf.Help} errored = true - level.Error(c.logger).Log("msg", "inconsistent metric help text", + c.logger.Error("inconsistent metric help text", "metric", *mf.Name, "original_help_text", helpTexts[0], "new_help_text", *mf.Help, @@ -242,7 +245,7 @@ func (c *textFileCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { errored = true - level.Error(c.logger).Log("msg", "failed to collect textfile data", "file", f.Name(), "err", err) + c.logger.Error("failed to collect textfile data", "file", f.Name(), "err", err) continue } @@ -250,10 +253,16 @@ func (c *textFileCollector) Update(ch chan<- prometheus.Metric) error { } } + mfHelp := make(map[string]*string) for _, mf := range parsedFamilies { if mf.Help == nil { + if help, ok := mfHelp[*mf.Name]; ok { + mf.Help = help + continue + } help := fmt.Sprintf("Metric read from %s", strings.Join(metricsNamesToFiles[*mf.Name], ", ")) mf.Help = &help + mfHelp[*mf.Name] = &help } } diff --git a/collector/textfile_test.go b/collector/textfile_test.go index 95e5966f3e..ece70b3a12 100644 --- a/collector/textfile_test.go +++ b/collector/textfile_test.go @@ -18,17 +18,18 @@ package collector import ( "fmt" + "io" + "log/slog" "net/http" "net/http/httptest" "os" "testing" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/promhttp" - "github.com/prometheus/common/promlog" - "github.com/prometheus/common/promlog/flag" + "github.com/prometheus/common/promslog" + "github.com/prometheus/common/promslog/flag" ) type collectorAdapter struct { @@ -51,83 +52,90 @@ func (a collectorAdapter) Collect(ch chan<- prometheus.Metric) { func TestTextfileCollector(t *testing.T) { tests := []struct { - path string - out string + paths []string + out string }{ { - path: "fixtures/textfile/no_metric_files", - out: "fixtures/textfile/no_metric_files.out", + paths: []string{"fixtures/textfile/no_metric_files"}, + out: "fixtures/textfile/no_metric_files.out", }, { - path: "fixtures/textfile/two_metric_files", - out: "fixtures/textfile/two_metric_files.out", + paths: []string{"fixtures/textfile/two_metric_files"}, + out: "fixtures/textfile/two_metric_files.out", }, { - path: "fixtures/textfile/nonexistent_path", - out: "fixtures/textfile/nonexistent_path.out", + paths: []string{"fixtures/textfile/nonexistent_path"}, + out: "fixtures/textfile/nonexistent_path.out", }, { - path: "fixtures/textfile/client_side_timestamp", - out: "fixtures/textfile/client_side_timestamp.out", + paths: []string{"fixtures/textfile/client_side_timestamp"}, + out: "fixtures/textfile/client_side_timestamp.out", }, { - path: "fixtures/textfile/different_metric_types", - out: "fixtures/textfile/different_metric_types.out", + paths: []string{"fixtures/textfile/different_metric_types"}, + out: "fixtures/textfile/different_metric_types.out", }, { - path: "fixtures/textfile/inconsistent_metrics", - out: "fixtures/textfile/inconsistent_metrics.out", + paths: []string{"fixtures/textfile/inconsistent_metrics"}, + out: "fixtures/textfile/inconsistent_metrics.out", }, { - path: "fixtures/textfile/histogram", - out: "fixtures/textfile/histogram.out", + paths: []string{"fixtures/textfile/histogram"}, + out: "fixtures/textfile/histogram.out", }, { - path: "fixtures/textfile/histogram_extra_dimension", - out: "fixtures/textfile/histogram_extra_dimension.out", + paths: []string{"fixtures/textfile/histogram_extra_dimension"}, + out: "fixtures/textfile/histogram_extra_dimension.out", }, { - path: "fixtures/textfile/summary", - out: "fixtures/textfile/summary.out", + paths: []string{"fixtures/textfile/summary"}, + out: "fixtures/textfile/summary.out", }, { - path: "fixtures/textfile/summary_extra_dimension", - out: "fixtures/textfile/summary_extra_dimension.out", + paths: []string{"fixtures/textfile/summary_extra_dimension"}, + out: "fixtures/textfile/summary_extra_dimension.out", }, { - path: "fixtures/textfile/*_extra_dimension", - out: "fixtures/textfile/glob_extra_dimension.out", + paths: []string{ + "fixtures/textfile/histogram_extra_dimension", + "fixtures/textfile/summary_extra_dimension", + }, + out: "fixtures/textfile/glob_extra_dimension.out", }, { - path: "fixtures/textfile/metrics_merge_empty_help", - out: "fixtures/textfile/metrics_merge_empty_help.out", + paths: []string{"fixtures/textfile/*_extra_dimension"}, + out: "fixtures/textfile/glob_extra_dimension.out", }, { - path: "fixtures/textfile/metrics_merge_no_help", - out: "fixtures/textfile/metrics_merge_no_help.out", + paths: []string{"fixtures/textfile/metrics_merge_empty_help"}, + out: "fixtures/textfile/metrics_merge_empty_help.out", }, { - path: "fixtures/textfile/metrics_merge_same_help", - out: "fixtures/textfile/metrics_merge_same_help.out", + paths: []string{"fixtures/textfile/metrics_merge_no_help"}, + out: "fixtures/textfile/metrics_merge_no_help.out", }, { - path: "fixtures/textfile/metrics_merge_different_help", - out: "fixtures/textfile/metrics_merge_different_help.out", + paths: []string{"fixtures/textfile/metrics_merge_same_help"}, + out: "fixtures/textfile/metrics_merge_same_help.out", + }, + { + paths: []string{"fixtures/textfile/metrics_merge_different_help"}, + out: "fixtures/textfile/metrics_merge_different_help.out", }, } for i, test := range tests { mtime := 1.0 c := &textFileCollector{ - path: test.path, + paths: test.paths, mtime: &mtime, - logger: log.NewNopLogger(), + logger: slog.New(slog.NewTextHandler(io.Discard, nil)), } // Suppress a log message about `nonexistent_path` not existing, this is // expected and clutters the test output. - promlogConfig := &promlog.Config{} - flag.AddFlags(kingpin.CommandLine, promlogConfig) + promslogConfig := &promslog.Config{} + flag.AddFlags(kingpin.CommandLine, promslogConfig) if _, err := kingpin.CommandLine.Parse([]string{"--log.level", "debug"}); err != nil { t.Fatal(err) } @@ -145,7 +153,7 @@ func TestTextfileCollector(t *testing.T) { } if string(want) != got { - t.Fatalf("%d.%q want:\n\n%s\n\ngot:\n\n%s", i, test.path, string(want), got) + t.Fatalf("%d.%q want:\n\n%s\n\ngot:\n\n%s", i, test.paths, string(want), got) } } } diff --git a/collector/thermal_darwin.go b/collector/thermal_darwin.go index 25673dcc4d..0a3b8981f4 100644 --- a/collector/thermal_darwin.go +++ b/collector/thermal_darwin.go @@ -47,9 +47,9 @@ import "C" import ( "errors" "fmt" + "log/slog" "unsafe" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -57,7 +57,7 @@ type thermCollector struct { cpuSchedulerLimit typedDesc cpuAvailableCPU typedDesc cpuSpeedLimit typedDesc - logger log.Logger + logger *slog.Logger } const thermal = "thermal" @@ -67,7 +67,7 @@ func init() { } // NewThermCollector returns a new Collector exposing current CPU power levels. -func NewThermCollector(logger log.Logger) (Collector, error) { +func NewThermCollector(logger *slog.Logger) (Collector, error) { return &thermCollector{ cpuSchedulerLimit: typedDesc{ desc: prometheus.NewDesc( diff --git a/collector/thermal_zone_linux.go b/collector/thermal_zone_linux.go index 6eff27321a..95db272340 100644 --- a/collector/thermal_zone_linux.go +++ b/collector/thermal_zone_linux.go @@ -19,10 +19,9 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -35,7 +34,7 @@ type thermalZoneCollector struct { coolingDeviceCurState *prometheus.Desc coolingDeviceMaxState *prometheus.Desc zoneTemp *prometheus.Desc - logger log.Logger + logger *slog.Logger } func init() { @@ -43,7 +42,7 @@ func init() { } // NewThermalZoneCollector returns a new Collector exposing kernel/system statistics. -func NewThermalZoneCollector(logger log.Logger) (Collector, error) { +func NewThermalZoneCollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) @@ -74,7 +73,7 @@ func (c *thermalZoneCollector) Update(ch chan<- prometheus.Metric) error { thermalZones, err := c.fs.ClassThermalZoneStats() if err != nil { if errors.Is(err, os.ErrNotExist) || errors.Is(err, os.ErrPermission) || errors.Is(err, os.ErrInvalid) { - level.Debug(c.logger).Log("msg", "Could not read thermal zone stats", "err", err) + c.logger.Debug("Could not read thermal zone stats", "err", err) return ErrNoData } return err diff --git a/collector/time.go b/collector/time.go index 31a6e74e24..a4a81687b4 100644 --- a/collector/time.go +++ b/collector/time.go @@ -17,10 +17,9 @@ package collector import ( + "log/slog" "time" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -29,7 +28,7 @@ type timeCollector struct { zone typedDesc clocksourcesAvailable typedDesc clocksourceCurrent typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -38,7 +37,7 @@ func init() { // NewTimeCollector returns a new Collector exposing the current system time in // seconds since epoch. -func NewTimeCollector(logger log.Logger) (Collector, error) { +func NewTimeCollector(logger *slog.Logger) (Collector, error) { const subsystem = "time" return &timeCollector{ now: typedDesc{prometheus.NewDesc( @@ -70,9 +69,9 @@ func (c *timeCollector) Update(ch chan<- prometheus.Metric) error { nowSec := float64(now.UnixNano()) / 1e9 zone, zoneOffset := now.Zone() - level.Debug(c.logger).Log("msg", "Return time", "now", nowSec) + c.logger.Debug("Return time", "now", nowSec) ch <- c.now.mustNewConstMetric(nowSec) - level.Debug(c.logger).Log("msg", "Zone offset", "offset", zoneOffset, "time_zone", zone) + c.logger.Debug("Zone offset", "offset", zoneOffset, "time_zone", zone) ch <- c.zone.mustNewConstMetric(float64(zoneOffset), zone) return c.update(ch) } diff --git a/collector/time_linux.go b/collector/time_linux.go index dd4afe7592..212ba2280a 100644 --- a/collector/time_linux.go +++ b/collector/time_linux.go @@ -20,7 +20,6 @@ import ( "fmt" "strconv" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) @@ -35,7 +34,7 @@ func (c *timeCollector) update(ch chan<- prometheus.Metric) error { if err != nil { return fmt.Errorf("couldn't get clocksources: %w", err) } - level.Debug(c.logger).Log("msg", "in Update", "clocksources", fmt.Sprintf("%v", clocksources)) + c.logger.Debug("in Update", "clocksources", fmt.Sprintf("%v", clocksources)) for i, clocksource := range clocksources { is := strconv.Itoa(i) diff --git a/collector/timex.go b/collector/timex.go index 69cbc1a1d0..eb21f7c370 100644 --- a/collector/timex.go +++ b/collector/timex.go @@ -19,10 +19,9 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "golang.org/x/sys/unix" ) @@ -61,7 +60,7 @@ type timexCollector struct { stbcnt, tai, syncStatus typedDesc - logger log.Logger + logger *slog.Logger } func init() { @@ -69,7 +68,7 @@ func init() { } // NewTimexCollector returns a new Collector exposing adjtime(3) stats. -func NewTimexCollector(logger log.Logger) (Collector, error) { +func NewTimexCollector(logger *slog.Logger) (Collector, error) { const subsystem = "timex" return &timexCollector{ @@ -170,7 +169,7 @@ func (c *timexCollector) Update(ch chan<- prometheus.Metric) error { status, err := unix.Adjtimex(timex) if err != nil { if errors.Is(err, os.ErrPermission) { - level.Debug(c.logger).Log("msg", "Not collecting timex metrics", "err", err) + c.logger.Debug("Not collecting timex metrics", "err", err) return ErrNoData } return fmt.Errorf("failed to retrieve adjtimex stats: %w", err) diff --git a/collector/udp_queues_linux.go b/collector/udp_queues_linux.go index 3fac869198..2923936e38 100644 --- a/collector/udp_queues_linux.go +++ b/collector/udp_queues_linux.go @@ -19,10 +19,9 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -31,7 +30,7 @@ type ( udpQueuesCollector struct { fs procfs.FS desc *prometheus.Desc - logger log.Logger + logger *slog.Logger } ) @@ -40,7 +39,7 @@ func init() { } // NewUDPqueuesCollector returns a new Collector exposing network udp queued bytes. -func NewUDPqueuesCollector(logger log.Logger) (Collector, error) { +func NewUDPqueuesCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -64,7 +63,7 @@ func (c *udpQueuesCollector) Update(ch chan<- prometheus.Metric) error { ch <- prometheus.MustNewConstMetric(c.desc, prometheus.GaugeValue, float64(s4.RxQueueLength), "rx", "v4") } else { if errors.Is(errIPv4, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "not collecting ipv4 based metrics") + c.logger.Debug("not collecting ipv4 based metrics") } else { return fmt.Errorf("couldn't get udp queued bytes: %w", errIPv4) } @@ -76,7 +75,7 @@ func (c *udpQueuesCollector) Update(ch chan<- prometheus.Metric) error { ch <- prometheus.MustNewConstMetric(c.desc, prometheus.GaugeValue, float64(s6.RxQueueLength), "rx", "v6") } else { if errors.Is(errIPv6, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "not collecting ipv6 based metrics") + c.logger.Debug("not collecting ipv6 based metrics") } else { return fmt.Errorf("couldn't get udp6 queued bytes: %w", errIPv6) } diff --git a/collector/uname.go b/collector/uname.go index 76e66b7e33..32ca08c406 100644 --- a/collector/uname.go +++ b/collector/uname.go @@ -11,14 +11,15 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build (darwin || freebsd || openbsd || netbsd || linux) && !nouname -// +build darwin freebsd openbsd netbsd linux +//go:build (darwin || freebsd || openbsd || netbsd || linux || aix) && !nouname +// +build darwin freebsd openbsd netbsd linux aix // +build !nouname package collector import ( - "github.com/go-kit/log" + "log/slog" + "github.com/prometheus/client_golang/prometheus" ) @@ -37,7 +38,7 @@ var unameDesc = prometheus.NewDesc( ) type unameCollector struct { - logger log.Logger + logger *slog.Logger } type uname struct { SysName string @@ -49,11 +50,11 @@ type uname struct { } func init() { - registerCollector("uname", defaultEnabled, newUnameCollector) + registerCollector("uname", defaultEnabled, NewUnameCollector) } // NewUnameCollector returns new unameCollector. -func newUnameCollector(logger log.Logger) (Collector, error) { +func NewUnameCollector(logger *slog.Logger) (Collector, error) { return &unameCollector{logger}, nil } diff --git a/collector/uname_bsd.go b/collector/uname_bsd.go index 69bf38e910..fa565a1ccf 100644 --- a/collector/uname_bsd.go +++ b/collector/uname_bsd.go @@ -11,8 +11,8 @@ // See the License for the specific language governing permissions and // limitations under the License. -//go:build (darwin || freebsd || openbsd || netbsd) && !nouname -// +build darwin freebsd openbsd netbsd +//go:build (darwin || freebsd || openbsd || netbsd || aix) && !nouname +// +build darwin freebsd openbsd netbsd aix // +build !nouname package collector diff --git a/collector/utils/utils.go b/collector/utils/utils.go new file mode 100644 index 0000000000..aa5b7540f0 --- /dev/null +++ b/collector/utils/utils.go @@ -0,0 +1,27 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +package utils + +func SafeDereference[T any](s ...*T) []T { + var resolved []T + for _, v := range s { + if v != nil { + resolved = append(resolved, *v) + } else { + var zeroValue T + resolved = append(resolved, zeroValue) + } + } + return resolved +} diff --git a/collector/vmstat_linux.go b/collector/vmstat_linux.go index cde2df5da5..e31be0f7b8 100644 --- a/collector/vmstat_linux.go +++ b/collector/vmstat_linux.go @@ -19,13 +19,13 @@ package collector import ( "bufio" "fmt" + "log/slog" "os" "regexp" "strconv" "strings" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" ) @@ -39,7 +39,7 @@ var ( type vmStatCollector struct { fieldPattern *regexp.Regexp - logger log.Logger + logger *slog.Logger } func init() { @@ -47,7 +47,7 @@ func init() { } // NewvmStatCollector returns a new Collector exposing vmstat stats. -func NewvmStatCollector(logger log.Logger) (Collector, error) { +func NewvmStatCollector(logger *slog.Logger) (Collector, error) { pattern := regexp.MustCompile(*vmStatFields) return &vmStatCollector{ fieldPattern: pattern, diff --git a/collector/watchdog.go b/collector/watchdog.go index 01351be9b5..77fb792ea7 100644 --- a/collector/watchdog.go +++ b/collector/watchdog.go @@ -19,17 +19,16 @@ package collector import ( "errors" "fmt" + "log/slog" "os" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/sysfs" ) type watchdogCollector struct { fs sysfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -37,7 +36,7 @@ func init() { } // NewWatchdogCollector returns a new Collector exposing watchdog stats. -func NewWatchdogCollector(logger log.Logger) (Collector, error) { +func NewWatchdogCollector(logger *slog.Logger) (Collector, error) { fs, err := sysfs.NewFS(*sysPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) @@ -103,7 +102,7 @@ func (c *watchdogCollector) Update(ch chan<- prometheus.Metric) error { watchdogClass, err := c.fs.WatchdogClass() if err != nil { if errors.Is(err, os.ErrNotExist) || errors.Is(err, os.ErrPermission) || errors.Is(err, os.ErrInvalid) { - level.Debug(c.logger).Log("msg", "Could not read watchdog stats", "err", err) + c.logger.Debug("Could not read watchdog stats", "err", err) return ErrNoData } return err diff --git a/collector/watchdog_test.go b/collector/watchdog_test.go index e59382b4c9..baf08995ce 100644 --- a/collector/watchdog_test.go +++ b/collector/watchdog_test.go @@ -18,11 +18,11 @@ package collector import ( "fmt" - "os" + "io" + "log/slog" "strings" "testing" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/testutil" ) @@ -68,7 +68,7 @@ func TestWatchdogStats(t *testing.T) { ` *sysPath = "fixtures/sys" - logger := log.NewLogfmtLogger(os.Stderr) + logger := slog.New(slog.NewTextHandler(io.Discard, nil)) c, err := NewWatchdogCollector(logger) if err != nil { t.Fatal(err) diff --git a/collector/wifi_linux.go b/collector/wifi_linux.go index aff8eb2d36..c84cdd71d4 100644 --- a/collector/wifi_linux.go +++ b/collector/wifi_linux.go @@ -20,12 +20,11 @@ import ( "encoding/json" "errors" "fmt" + "log/slog" "os" "path/filepath" "github.com/alecthomas/kingpin/v2" - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/mdlayher/wifi" "github.com/prometheus/client_golang/prometheus" ) @@ -45,7 +44,7 @@ type wifiCollector struct { stationTransmitFailedTotal *prometheus.Desc stationBeaconLossTotal *prometheus.Desc - logger log.Logger + logger *slog.Logger } var ( @@ -67,7 +66,7 @@ type wifiStater interface { } // NewWifiCollector returns a new Collector exposing Wifi statistics. -func NewWifiCollector(logger log.Logger) (Collector, error) { +func NewWifiCollector(logger *slog.Logger) (Collector, error) { const ( subsystem = "wifi" ) @@ -169,11 +168,11 @@ func (c *wifiCollector) Update(ch chan<- prometheus.Metric) error { if err != nil { // Cannot access wifi metrics, report no error. if errors.Is(err, os.ErrNotExist) { - level.Debug(c.logger).Log("msg", "wifi collector metrics are not available for this system") + c.logger.Debug("wifi collector metrics are not available for this system") return ErrNoData } if errors.Is(err, os.ErrPermission) { - level.Debug(c.logger).Log("msg", "wifi collector got permission denied when accessing metrics") + c.logger.Debug("wifi collector got permission denied when accessing metrics") return ErrNoData } @@ -192,7 +191,7 @@ func (c *wifiCollector) Update(ch chan<- prometheus.Metric) error { continue } - level.Debug(c.logger).Log("msg", "probing wifi device with type", "wifi", ifi.Name, "type", ifi.Type) + c.logger.Debug("probing wifi device with type", "wifi", ifi.Name, "type", ifi.Type) ch <- prometheus.MustNewConstMetric( c.interfaceFrequencyHertz, @@ -210,7 +209,7 @@ func (c *wifiCollector) Update(ch chan<- prometheus.Metric) error { case err == nil: c.updateBSSStats(ch, ifi.Name, bss) case errors.Is(err, os.ErrNotExist): - level.Debug(c.logger).Log("msg", "BSS information not found for wifi device", "name", ifi.Name) + c.logger.Debug("BSS information not found for wifi device", "name", ifi.Name) default: return fmt.Errorf("failed to retrieve BSS for device %s: %v", ifi.Name, err) @@ -223,7 +222,7 @@ func (c *wifiCollector) Update(ch chan<- prometheus.Metric) error { c.updateStationStats(ch, ifi.Name, station) } case errors.Is(err, os.ErrNotExist): - level.Debug(c.logger).Log("msg", "station information not found for wifi device", "name", ifi.Name) + c.logger.Debug("station information not found for wifi device", "name", ifi.Name) default: return fmt.Errorf("failed to retrieve station info for device %q: %v", ifi.Name, err) diff --git a/collector/xfrm.go b/collector/xfrm.go index cbdcc97f1f..d96ee8aa74 100644 --- a/collector/xfrm.go +++ b/collector/xfrm.go @@ -18,15 +18,15 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) type xfrmCollector struct { fs procfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -34,7 +34,7 @@ func init() { } // NewXfrmCollector returns a new Collector exposing XFRM stats. -func NewXfrmCollector(logger log.Logger) (Collector, error) { +func NewXfrmCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) diff --git a/collector/xfrm_test.go b/collector/xfrm_test.go index 2e1ac02899..e009fc40f5 100644 --- a/collector/xfrm_test.go +++ b/collector/xfrm_test.go @@ -18,11 +18,11 @@ package collector import ( "fmt" - "os" + "io" + "log/slog" "strings" "testing" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/testutil" ) @@ -127,7 +127,7 @@ func TestXfrmStats(t *testing.T) { ` *procPath = "fixtures/proc" - logger := log.NewLogfmtLogger(os.Stderr) + logger := slog.New(slog.NewTextHandler(io.Discard, nil)) c, err := NewXfrmCollector(logger) if err != nil { t.Fatal(err) diff --git a/collector/xfs_linux.go b/collector/xfs_linux.go index bb25acab9f..3eac1d0e84 100644 --- a/collector/xfs_linux.go +++ b/collector/xfs_linux.go @@ -18,8 +18,8 @@ package collector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs/xfs" ) @@ -27,7 +27,7 @@ import ( // An xfsCollector is a Collector which gathers metrics from XFS filesystems. type xfsCollector struct { fs xfs.FS - logger log.Logger + logger *slog.Logger } func init() { @@ -35,7 +35,7 @@ func init() { } // NewXFSCollector returns a new Collector exposing XFS statistics. -func NewXFSCollector(logger log.Logger) (Collector, error) { +func NewXFSCollector(logger *slog.Logger) (Collector, error) { fs, err := xfs.NewFS(*procPath, *sysPath) if err != nil { return nil, fmt.Errorf("failed to open sysfs: %w", err) diff --git a/collector/zfs.go b/collector/zfs.go deleted file mode 100644 index df1a97aec3..0000000000 --- a/collector/zfs.go +++ /dev/null @@ -1,159 +0,0 @@ -// Copyright 2016 The Prometheus Authors -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. - -//go:build linux && !nozfs -// +build linux,!nozfs - -package collector - -import ( - "errors" - "strings" - - "github.com/go-kit/log" - "github.com/go-kit/log/level" - "github.com/prometheus/client_golang/prometheus" -) - -var errZFSNotAvailable = errors.New("ZFS / ZFS statistics are not available") - -type zfsSysctl string - -func init() { - registerCollector("zfs", defaultEnabled, NewZFSCollector) -} - -type zfsCollector struct { - linuxProcpathBase string - linuxZpoolIoPath string - linuxZpoolObjsetPath string - linuxZpoolStatePath string - linuxPathMap map[string]string - logger log.Logger -} - -// NewZFSCollector returns a new Collector exposing ZFS statistics. -func NewZFSCollector(logger log.Logger) (Collector, error) { - return &zfsCollector{ - linuxProcpathBase: "spl/kstat/zfs", - linuxZpoolIoPath: "/*/io", - linuxZpoolObjsetPath: "/*/objset-*", - linuxZpoolStatePath: "/*/state", - linuxPathMap: map[string]string{ - "zfs_abd": "abdstats", - "zfs_arc": "arcstats", - "zfs_dbuf": "dbufstats", - "zfs_dmu_tx": "dmu_tx", - "zfs_dnode": "dnodestats", - "zfs_fm": "fm", - "zfs_vdev_cache": "vdev_cache_stats", // vdev_cache is deprecated - "zfs_vdev_mirror": "vdev_mirror_stats", - "zfs_xuio": "xuio_stats", // no known consumers of the XUIO interface on Linux exist - "zfs_zfetch": "zfetchstats", - "zfs_zil": "zil", - }, - logger: logger, - }, nil -} - -func (c *zfsCollector) Update(ch chan<- prometheus.Metric) error { - - if _, err := c.openProcFile(c.linuxProcpathBase); err != nil { - if err == errZFSNotAvailable { - level.Debug(c.logger).Log("err", err) - return ErrNoData - } - } - - for subsystem := range c.linuxPathMap { - if err := c.updateZfsStats(subsystem, ch); err != nil { - if err == errZFSNotAvailable { - level.Debug(c.logger).Log("err", err) - // ZFS /proc files are added as new features to ZFS arrive, it is ok to continue - continue - } - return err - } - } - - // Pool stats - return c.updatePoolStats(ch) -} - -func (s zfsSysctl) metricName() string { - parts := strings.Split(string(s), ".") - return strings.Replace(parts[len(parts)-1], "-", "_", -1) -} - -func (c *zfsCollector) constSysctlMetric(subsystem string, sysctl zfsSysctl, value uint64) prometheus.Metric { - metricName := sysctl.metricName() - - return prometheus.MustNewConstMetric( - prometheus.NewDesc( - prometheus.BuildFQName(namespace, subsystem, metricName), - string(sysctl), - nil, - nil, - ), - prometheus.UntypedValue, - float64(value), - ) -} - -func (c *zfsCollector) constPoolMetric(poolName string, sysctl zfsSysctl, value uint64) prometheus.Metric { - metricName := sysctl.metricName() - - return prometheus.MustNewConstMetric( - prometheus.NewDesc( - prometheus.BuildFQName(namespace, "zfs_zpool", metricName), - string(sysctl), - []string{"zpool"}, - nil, - ), - prometheus.UntypedValue, - float64(value), - poolName, - ) -} - -func (c *zfsCollector) constPoolObjsetMetric(poolName string, datasetName string, sysctl zfsSysctl, value uint64) prometheus.Metric { - metricName := sysctl.metricName() - - return prometheus.MustNewConstMetric( - prometheus.NewDesc( - prometheus.BuildFQName(namespace, "zfs_zpool_dataset", metricName), - string(sysctl), - []string{"zpool", "dataset"}, - nil, - ), - prometheus.UntypedValue, - float64(value), - poolName, - datasetName, - ) -} - -func (c *zfsCollector) constPoolStateMetric(poolName string, stateName string, isActive uint64) prometheus.Metric { - return prometheus.MustNewConstMetric( - prometheus.NewDesc( - prometheus.BuildFQName(namespace, "zfs_zpool", "state"), - "kstat.zfs.misc.state", - []string{"zpool", "state"}, - nil, - ), - prometheus.GaugeValue, - float64(isActive), - poolName, - stateName, - ) -} diff --git a/collector/zfs_common.go b/collector/zfs_common.go new file mode 100644 index 0000000000..7934ec5ad9 --- /dev/null +++ b/collector/zfs_common.go @@ -0,0 +1,22 @@ +// Copyright 2016 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +//go:build !nozfs && (freebsd || linux || solaris) +// +build !nozfs +// +build freebsd linux solaris + +package collector + +func init() { + registerCollector("zfs", defaultEnabled, NewZFSCollector) +} diff --git a/collector/zfs_freebsd.go b/collector/zfs_freebsd.go index 804d4f58a9..d888c3a724 100644 --- a/collector/zfs_freebsd.go +++ b/collector/zfs_freebsd.go @@ -17,25 +17,20 @@ package collector import ( - "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" + "log/slog" ) type zfsCollector struct { sysctls []bsdSysctl - logger log.Logger + logger *slog.Logger } const ( zfsCollectorSubsystem = "zfs" ) -func init() { - registerCollector("zfs", defaultEnabled, NewZfsCollector) -} - -func NewZfsCollector(logger log.Logger) (Collector, error) { +func NewZFSCollector(logger *slog.Logger) (Collector, error) { return &zfsCollector{ sysctls: []bsdSysctl{ { @@ -273,7 +268,7 @@ func (c *zfsCollector) Update(ch chan<- prometheus.Metric) error { v, err := m.Value() if err != nil { // debug logging - level.Debug(c.logger).Log("name", m.name, "mib", m.mib, "couldn't get sysctl:", err) + c.logger.Debug(m.name, "mib", m.mib, "couldn't get sysctl:", err) continue } diff --git a/collector/zfs_linux.go b/collector/zfs_linux.go index ec195b3d62..4baf2b3569 100644 --- a/collector/zfs_linux.go +++ b/collector/zfs_linux.go @@ -18,14 +18,15 @@ package collector import ( "bufio" + "errors" "fmt" "io" + "log/slog" "os" "path/filepath" "strconv" "strings" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" ) @@ -42,7 +43,67 @@ const ( // kstatDataString = "7" ) -var zfsPoolStatesName = []string{"online", "degraded", "faulted", "offline", "removed", "unavail", "suspended"} +var ( + errZFSNotAvailable = errors.New("ZFS / ZFS statistics are not available") + + zfsPoolStatesName = [...]string{"online", "degraded", "faulted", "offline", "removed", "unavail", "suspended"} +) + +type zfsCollector struct { + linuxProcpathBase string + linuxZpoolIoPath string + linuxZpoolObjsetPath string + linuxZpoolStatePath string + linuxPathMap map[string]string + logger *slog.Logger +} + +// NewZFSCollector returns a new Collector exposing ZFS statistics. +func NewZFSCollector(logger *slog.Logger) (Collector, error) { + return &zfsCollector{ + linuxProcpathBase: "spl/kstat/zfs", + linuxZpoolIoPath: "/*/io", + linuxZpoolObjsetPath: "/*/objset-*", + linuxZpoolStatePath: "/*/state", + linuxPathMap: map[string]string{ + "zfs_abd": "abdstats", + "zfs_arc": "arcstats", + "zfs_dbuf": "dbufstats", + "zfs_dmu_tx": "dmu_tx", + "zfs_dnode": "dnodestats", + "zfs_fm": "fm", + "zfs_vdev_cache": "vdev_cache_stats", // vdev_cache is deprecated + "zfs_vdev_mirror": "vdev_mirror_stats", + "zfs_xuio": "xuio_stats", // no known consumers of the XUIO interface on Linux exist + "zfs_zfetch": "zfetchstats", + "zfs_zil": "zil", + }, + logger: logger, + }, nil +} + +func (c *zfsCollector) Update(ch chan<- prometheus.Metric) error { + if _, err := c.openProcFile(c.linuxProcpathBase); err != nil { + if err == errZFSNotAvailable { + c.logger.Debug(err.Error()) + return ErrNoData + } + } + + for subsystem := range c.linuxPathMap { + if err := c.updateZfsStats(subsystem, ch); err != nil { + if err == errZFSNotAvailable { + c.logger.Debug(err.Error()) + // ZFS /proc files are added as new features to ZFS arrive, it is ok to continue + continue + } + return err + } + } + + // Pool stats + return c.updatePoolStats(ch) +} func (c *zfsCollector) openProcFile(path string) (*os.File, error) { file, err := os.Open(procFilePath(path)) @@ -50,7 +111,7 @@ func (c *zfsCollector) openProcFile(path string) (*os.File, error) { // file not found error can occur if: // 1. zfs module is not loaded // 2. zfs version does not have the feature with metrics -- ok to ignore - level.Debug(c.logger).Log("msg", "Cannot open file for reading", "path", procFilePath(path)) + c.logger.Debug("Cannot open file for reading", "path", procFilePath(path)) return nil, errZFSNotAvailable } return file, nil @@ -63,8 +124,15 @@ func (c *zfsCollector) updateZfsStats(subsystem string, ch chan<- prometheus.Met } defer file.Close() - return c.parseProcfsFile(file, c.linuxPathMap[subsystem], func(s zfsSysctl, v uint64) { - ch <- c.constSysctlMetric(subsystem, s, v) + return c.parseProcfsFile(file, c.linuxPathMap[subsystem], func(s zfsSysctl, v interface{}) { + var valueAsFloat64 float64 + switch value := v.(type) { + case int64: + valueAsFloat64 = float64(value) + case uint64: + valueAsFloat64 = float64(value) + } + ch <- c.constSysctlMetric(subsystem, s, valueAsFloat64) }) } @@ -78,7 +146,7 @@ func (c *zfsCollector) updatePoolStats(ch chan<- prometheus.Metric) error { file, err := os.Open(zpoolPath) if err != nil { // this file should exist, but there is a race where an exporting pool can remove the files -- ok to ignore - level.Debug(c.logger).Log("msg", "Cannot open file for reading", "path", zpoolPath) + c.logger.Debug("Cannot open file for reading", "path", zpoolPath) return errZFSNotAvailable } @@ -100,7 +168,7 @@ func (c *zfsCollector) updatePoolStats(ch chan<- prometheus.Metric) error { file, err := os.Open(zpoolPath) if err != nil { // This file should exist, but there is a race where an exporting pool can remove the files. Ok to ignore. - level.Debug(c.logger).Log("msg", "Cannot open file for reading", "path", zpoolPath) + c.logger.Debug("Cannot open file for reading", "path", zpoolPath) return errZFSNotAvailable } @@ -119,7 +187,7 @@ func (c *zfsCollector) updatePoolStats(ch chan<- prometheus.Metric) error { } if zpoolStatePaths == nil { - level.Debug(c.logger).Log("msg", "No pool state files found") + c.logger.Debug("No pool state files found") return nil } @@ -127,7 +195,7 @@ func (c *zfsCollector) updatePoolStats(ch chan<- prometheus.Metric) error { file, err := os.Open(zpoolPath) if err != nil { // This file should exist, but there is a race where an exporting pool can remove the files. Ok to ignore. - level.Debug(c.logger).Log("msg", "Cannot open file for reading", "path", zpoolPath) + c.logger.Debug("Cannot open file for reading", "path", zpoolPath) return errZFSNotAvailable } @@ -144,7 +212,7 @@ func (c *zfsCollector) updatePoolStats(ch chan<- prometheus.Metric) error { return nil } -func (c *zfsCollector) parseProcfsFile(reader io.Reader, fmtExt string, handler func(zfsSysctl, uint64)) error { +func (c *zfsCollector) parseProcfsFile(reader io.Reader, fmtExt string, handler func(zfsSysctl, interface{})) error { scanner := bufio.NewScanner(reader) parseLine := false @@ -163,11 +231,18 @@ func (c *zfsCollector) parseProcfsFile(reader io.Reader, fmtExt string, handler // kstat data type (column 2) should be KSTAT_DATA_UINT64, otherwise ignore // TODO: when other KSTAT_DATA_* types arrive, much of this will need to be restructured - if parts[1] == kstatDataUint64 || parts[1] == kstatDataInt64 { - key := fmt.Sprintf("kstat.zfs.misc.%s.%s", fmtExt, parts[0]) + key := fmt.Sprintf("kstat.zfs.misc.%s.%s", fmtExt, parts[0]) + switch parts[1] { + case kstatDataUint64: value, err := strconv.ParseUint(parts[2], 10, 64) if err != nil { - return fmt.Errorf("could not parse expected integer value for %q", key) + return fmt.Errorf("could not parse expected unsigned integer value for %q: %w", key, err) + } + handler(zfsSysctl(key), value) + case kstatDataInt64: + value, err := strconv.ParseInt(parts[2], 10, 64) + if err != nil { + return fmt.Errorf("could not parse expected signed integer value for %q: %w", key, err) } handler(zfsSysctl(key), value) } @@ -226,7 +301,8 @@ func (c *zfsCollector) parsePoolObjsetFile(reader io.Reader, zpoolPath string, h parseLine := false var zpoolName, datasetName string for scanner.Scan() { - parts := strings.Fields(scanner.Text()) + line := scanner.Text() + parts := strings.Fields(line) if !parseLine && len(parts) == 3 && parts[0] == "name" && parts[1] == "type" && parts[2] == "data" { parseLine = true @@ -240,7 +316,7 @@ func (c *zfsCollector) parsePoolObjsetFile(reader io.Reader, zpoolPath string, h zpoolPathElements := strings.Split(zpoolPath, "/") pathLen := len(zpoolPathElements) zpoolName = zpoolPathElements[pathLen-2] - datasetName = parts[2] + datasetName = line[strings.Index(line, parts[2]):] continue } @@ -291,3 +367,73 @@ func (c *zfsCollector) parsePoolStateFile(reader io.Reader, zpoolPath string, ha return nil } + +func (c *zfsCollector) constSysctlMetric(subsystem string, sysctl zfsSysctl, value float64) prometheus.Metric { + metricName := sysctl.metricName() + + return prometheus.MustNewConstMetric( + prometheus.NewDesc( + prometheus.BuildFQName(namespace, subsystem, metricName), + string(sysctl), + nil, + nil, + ), + prometheus.UntypedValue, + value, + ) +} + +func (c *zfsCollector) constPoolMetric(poolName string, sysctl zfsSysctl, value uint64) prometheus.Metric { + metricName := sysctl.metricName() + + return prometheus.MustNewConstMetric( + prometheus.NewDesc( + prometheus.BuildFQName(namespace, "zfs_zpool", metricName), + string(sysctl), + []string{"zpool"}, + nil, + ), + prometheus.UntypedValue, + float64(value), + poolName, + ) +} + +func (c *zfsCollector) constPoolObjsetMetric(poolName string, datasetName string, sysctl zfsSysctl, value uint64) prometheus.Metric { + metricName := sysctl.metricName() + + return prometheus.MustNewConstMetric( + prometheus.NewDesc( + prometheus.BuildFQName(namespace, "zfs_zpool_dataset", metricName), + string(sysctl), + []string{"zpool", "dataset"}, + nil, + ), + prometheus.UntypedValue, + float64(value), + poolName, + datasetName, + ) +} + +func (c *zfsCollector) constPoolStateMetric(poolName string, stateName string, isActive uint64) prometheus.Metric { + return prometheus.MustNewConstMetric( + prometheus.NewDesc( + prometheus.BuildFQName(namespace, "zfs_zpool", "state"), + "kstat.zfs.misc.state", + []string{"zpool", "state"}, + nil, + ), + prometheus.GaugeValue, + float64(isActive), + poolName, + stateName, + ) +} + +type zfsSysctl string + +func (s zfsSysctl) metricName() string { + parts := strings.Split(string(s), ".") + return strings.Replace(parts[len(parts)-1], "-", "_", -1) +} diff --git a/collector/zfs_linux_test.go b/collector/zfs_linux_test.go index 69e4ed8fc1..7b019e8c6c 100644 --- a/collector/zfs_linux_test.go +++ b/collector/zfs_linux_test.go @@ -35,24 +35,25 @@ func TestArcstatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(arcstatsFile, "arcstats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(arcstatsFile, "arcstats", func(s zfsSysctl, v interface{}) { - if s != zfsSysctl("kstat.zfs.misc.arcstats.hits") { + if s == zfsSysctl("kstat.zfs.misc.arcstats.hits") { + if v.(uint64) != 8772612 { + t.Fatalf("Incorrect value parsed from procfs data") + } + } else if s == zfsSysctl("kstat.zfs.misc.arcstats.memory_available_bytes") { + if v.(int64) != -922337203685477580 { + t.Fatalf("Incorrect value parsed from procfs data") + } + } else { return } handlerCalled = true - - if v != uint64(8772612) { - t.Fatalf("Incorrect value parsed from procfs data") - } - }) - if err != nil { t.Fatal(err) } - if !handlerCalled { t.Fatal("Arcstats parsing handler was not called for some expected sysctls") } @@ -71,7 +72,7 @@ func TestZfetchstatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(zfetchstatsFile, "zfetchstats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(zfetchstatsFile, "zfetchstats", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.zfetchstats.hits") { return @@ -79,7 +80,7 @@ func TestZfetchstatsParsing(t *testing.T) { handlerCalled = true - if v != uint64(7067992) { + if v.(uint64) != 7067992 { t.Fatalf("Incorrect value parsed from procfs data") } @@ -107,7 +108,7 @@ func TestZilParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(zilFile, "zil", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(zilFile, "zil", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.zil.zil_commit_count") { return @@ -115,7 +116,7 @@ func TestZilParsing(t *testing.T) { handlerCalled = true - if v != uint64(10) { + if v.(uint64) != 10 { t.Fatalf("Incorrect value parsed from procfs data") } @@ -143,7 +144,7 @@ func TestVdevCacheStatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(vdevCacheStatsFile, "vdev_cache_stats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(vdevCacheStatsFile, "vdev_cache_stats", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.vdev_cache_stats.delegations") { return @@ -151,7 +152,7 @@ func TestVdevCacheStatsParsing(t *testing.T) { handlerCalled = true - if v != uint64(40) { + if v.(uint64) != 40 { t.Fatalf("Incorrect value parsed from procfs data") } @@ -179,7 +180,7 @@ func TestXuioStatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(xuioStatsFile, "xuio_stats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(xuioStatsFile, "xuio_stats", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.xuio_stats.onloan_read_buf") { return @@ -187,7 +188,7 @@ func TestXuioStatsParsing(t *testing.T) { handlerCalled = true - if v != uint64(32) { + if v.(uint64) != 32 { t.Fatalf("Incorrect value parsed from procfs data") } @@ -215,7 +216,7 @@ func TestFmParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(fmFile, "fm", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(fmFile, "fm", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.fm.erpt-dropped") { return @@ -223,7 +224,7 @@ func TestFmParsing(t *testing.T) { handlerCalled = true - if v != uint64(18) { + if v.(uint64) != 18 { t.Fatalf("Incorrect value parsed from procfs data") } @@ -251,7 +252,7 @@ func TestDmuTxParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(dmuTxFile, "dmu_tx", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(dmuTxFile, "dmu_tx", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.dmu_tx.dmu_tx_assigned") { return @@ -259,7 +260,7 @@ func TestDmuTxParsing(t *testing.T) { handlerCalled = true - if v != uint64(3532844) { + if v.(uint64) != 3532844 { t.Fatalf("Incorrect value parsed from procfs data") } @@ -299,7 +300,7 @@ func TestZpoolParsing(t *testing.T) { handlerCalled = true - if v != uint64(1884160) && v != uint64(2826240) { + if v != 1884160 && v != 2826240 { t.Fatalf("Incorrect value parsed from procfs data %v", v) } @@ -314,6 +315,55 @@ func TestZpoolParsing(t *testing.T) { } } +func TestZpoolObjsetParsingWithSpace(t *testing.T) { + tests := []struct { + path string + expectedDataset string + }{ + { + path: "fixtures/proc/spl/kstat/zfs/pool1/objset-1", + expectedDataset: "pool1", + }, + { + path: "fixtures/proc/spl/kstat/zfs/pool1/objset-2", + expectedDataset: "pool1/dataset1", + }, + { + path: "fixtures/proc/spl/kstat/zfs/pool3/objset-1", + expectedDataset: "pool3", + }, + { + path: "fixtures/proc/spl/kstat/zfs/pool3/objset-2", + expectedDataset: "pool3/dataset with space", + }, + } + + c := zfsCollector{} + + var handlerCalled bool + for _, test := range tests { + file, err := os.Open(test.path) + if err != nil { + t.Fatal(err) + } + + handlerCalled = false + err = c.parsePoolObjsetFile(file, test.path, func(poolName string, datasetName string, s zfsSysctl, v uint64) { + handlerCalled = true + if test.expectedDataset != datasetName { + t.Fatalf("Incorrectly parsed dataset name: expected: '%s', got: '%s'", test.expectedDataset, datasetName) + } + }) + file.Close() + if err != nil { + t.Fatal(err) + } + if !handlerCalled { + t.Fatalf("Zpool parsing handler was not called for '%s'", test.path) + } + } +} + func TestZpoolObjsetParsing(t *testing.T) { zpoolPaths, err := filepath.Glob("fixtures/proc/spl/kstat/zfs/*/objset-*") if err != nil { @@ -339,7 +389,7 @@ func TestZpoolObjsetParsing(t *testing.T) { handlerCalled = true - if v != uint64(0) && v != uint64(4) && v != uint64(10) { + if v != 0 && v != 4 && v != 10 { t.Fatalf("Incorrect value parsed from procfs data %v", v) } @@ -367,7 +417,7 @@ func TestAbdstatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(abdstatsFile, "abdstats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(abdstatsFile, "abdstats", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.abdstats.linear_data_size") { return @@ -375,7 +425,7 @@ func TestAbdstatsParsing(t *testing.T) { handlerCalled = true - if v != uint64(223232) { + if v.(uint64) != 223232 { t.Fatalf("Incorrect value parsed from procfs abdstats data") } @@ -403,7 +453,7 @@ func TestDbufstatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(dbufstatsFile, "dbufstats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(dbufstatsFile, "dbufstats", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.dbufstats.hash_hits") { return @@ -411,7 +461,7 @@ func TestDbufstatsParsing(t *testing.T) { handlerCalled = true - if v != uint64(108807) { + if v.(uint64) != 108807 { t.Fatalf("Incorrect value parsed from procfs dbufstats data") } @@ -439,7 +489,7 @@ func TestDnodestatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(dnodestatsFile, "dnodestats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(dnodestatsFile, "dnodestats", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.dnodestats.dnode_hold_alloc_hits") { return @@ -447,7 +497,7 @@ func TestDnodestatsParsing(t *testing.T) { handlerCalled = true - if v != uint64(37617) { + if v.(uint64) != 37617 { t.Fatalf("Incorrect value parsed from procfs dnodestats data") } @@ -475,7 +525,7 @@ func TestVdevMirrorstatsParsing(t *testing.T) { } handlerCalled := false - err = c.parseProcfsFile(vdevMirrorStatsFile, "vdev_mirror_stats", func(s zfsSysctl, v uint64) { + err = c.parseProcfsFile(vdevMirrorStatsFile, "vdev_mirror_stats", func(s zfsSysctl, v interface{}) { if s != zfsSysctl("kstat.zfs.misc.vdev_mirror_stats.preferred_not_found") { return @@ -483,7 +533,7 @@ func TestVdevMirrorstatsParsing(t *testing.T) { handlerCalled = true - if v != uint64(94) { + if v.(uint64) != 94 { t.Fatalf("Incorrect value parsed from procfs vdev_mirror_stats data") } @@ -520,26 +570,26 @@ func TestPoolStateParsing(t *testing.T) { handlerCalled = true if poolName == "pool1" { - if isActive != uint64(1) && stateName == "online" { + if isActive != 1 && stateName == "online" { t.Fatalf("Incorrect parsed value for online state") } - if isActive != uint64(0) && stateName != "online" { + if isActive != 0 && stateName != "online" { t.Fatalf("Incorrect parsed value for online state") } } if poolName == "poolz1" { - if isActive != uint64(1) && stateName == "degraded" { + if isActive != 1 && stateName == "degraded" { t.Fatalf("Incorrect parsed value for degraded state") } - if isActive != uint64(0) && stateName != "degraded" { + if isActive != 0 && stateName != "degraded" { t.Fatalf("Incorrect parsed value for degraded state") } } if poolName == "pool2" { - if isActive != uint64(1) && stateName == "suspended" { + if isActive != 1 && stateName == "suspended" { t.Fatalf("Incorrect parsed value for suspended state") } - if isActive != uint64(0) && stateName != "suspended" { + if isActive != 0 && stateName != "suspended" { t.Fatalf("Incorrect parsed value for suspended state") } } diff --git a/collector/zfs_solaris.go b/collector/zfs_solaris.go index 52f2500f25..1f10ee0199 100644 --- a/collector/zfs_solaris.go +++ b/collector/zfs_solaris.go @@ -17,9 +17,9 @@ package collector import ( + "log/slog" "strings" - "github.com/go-kit/log" "github.com/illumos/go-kstat" "github.com/prometheus/client_golang/prometheus" ) @@ -54,18 +54,14 @@ type zfsCollector struct { arcstatsSize *prometheus.Desc zfetchstatsHits *prometheus.Desc zfetchstatsMisses *prometheus.Desc - logger log.Logger + logger *slog.Logger } const ( zfsCollectorSubsystem = "zfs" ) -func init() { - registerCollector("zfs", defaultEnabled, NewZfsCollector) -} - -func NewZfsCollector(logger log.Logger) (Collector, error) { +func NewZFSCollector(logger *slog.Logger) (Collector, error) { return &zfsCollector{ abdstatsLinearCount: prometheus.NewDesc( prometheus.BuildFQName(namespace, zfsCollectorSubsystem, "abdstats_linear_count_total"), diff --git a/collector/zoneinfo_linux.go b/collector/zoneinfo_linux.go index 8f7e35d9f1..0b40fd3c59 100644 --- a/collector/zoneinfo_linux.go +++ b/collector/zoneinfo_linux.go @@ -15,10 +15,9 @@ package collector import ( "fmt" + "log/slog" "reflect" - "github.com/go-kit/log" - "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/procfs" ) @@ -28,7 +27,7 @@ const zoneinfoSubsystem = "zoneinfo" type zoneinfoCollector struct { gaugeMetricDescs map[string]*prometheus.Desc counterMetricDescs map[string]*prometheus.Desc - logger log.Logger + logger *slog.Logger fs procfs.FS } @@ -37,7 +36,7 @@ func init() { } // NewZoneinfoCollector returns a new Collector exposing zone stats. -func NewZoneinfoCollector(logger log.Logger) (Collector, error) { +func NewZoneinfoCollector(logger *slog.Logger) (Collector, error) { fs, err := procfs.NewFS(*procPath) if err != nil { return nil, fmt.Errorf("failed to open procfs: %w", err) diff --git a/docs/node-mixin/alerts/alerts.libsonnet b/docs/node-mixin/alerts/alerts.libsonnet index c346480906..61d9dd2d3a 100644 --- a/docs/node-mixin/alerts/alerts.libsonnet +++ b/docs/node-mixin/alerts/alerts.libsonnet @@ -10,7 +10,7 @@ ( node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_size_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < %(fsSpaceFillingUpWarningThreshold)d and - predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[%(fsSpaceFillingUpPredictionWindow)s], 24*60*60) < 0 + predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[%(fsSpaceFillingUpPredictionWindow)s], %(nodeWarningWindowHours)s*60*60) < 0 and node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 ) @@ -20,7 +20,7 @@ severity: 'warning', }, annotations: { - summary: 'Filesystem is predicted to run out of space within the next 24 hours.', + summary: 'Filesystem is predicted to run out of space within the next %(nodeWarningWindowHours)s hours.' % $._config, description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up.', }, }, @@ -30,7 +30,7 @@ ( node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_size_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < %(fsSpaceFillingUpCriticalThreshold)d and - predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], 4*60*60) < 0 + predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], %(nodeCriticalWindowHours)s*60*60) < 0 and node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 ) @@ -40,7 +40,7 @@ severity: '%(nodeCriticalSeverity)s' % $._config, }, annotations: { - summary: 'Filesystem is predicted to run out of space within the next 4 hours.', + summary: 'Filesystem is predicted to run out of space within the next %(nodeCriticalWindowHours)s hours.' % $._config, description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.', }, }, @@ -86,7 +86,7 @@ ( node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_files{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < 40 and - predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], 24*60*60) < 0 + predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], %(nodeWarningWindowHours)s*60*60) < 0 and node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 ) @@ -96,7 +96,7 @@ severity: 'warning', }, annotations: { - summary: 'Filesystem is predicted to run out of inodes within the next 24 hours.', + summary: 'Filesystem is predicted to run out of inodes within the next %(nodeWarningWindowHours)s hours.' % $._config, description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.', }, }, @@ -106,7 +106,7 @@ ( node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_files{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < 20 and - predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], 4*60*60) < 0 + predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], %(nodeCriticalWindowHours)s*60*60) < 0 and node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 ) @@ -116,7 +116,7 @@ severity: '%(nodeCriticalSeverity)s' % $._config, }, annotations: { - summary: 'Filesystem is predicted to run out of inodes within the next 4 hours.', + summary: 'Filesystem is predicted to run out of inodes within the next %(nodeCriticalWindowHours)s hours.' % $._config, description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.', }, }, @@ -191,7 +191,7 @@ ||| % $._config, annotations: { summary: 'Number of conntrack are getting close to the limit.', - description: '{{ $value | humanizePercentage }} of conntrack entries are used.', + description: '{{ $labels.instance }} {{ $value | humanizePercentage }} of conntrack entries are used.', }, labels: { severity: 'warning', @@ -312,7 +312,7 @@ { alert: 'NodeCPUHighUsage', expr: ||| - sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode!="idle"}[2m]))) * 100 > %(cpuHighUsageThreshold)d + sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode!~"idle|iowait"}[2m]))) * 100 > %(cpuHighUsageThreshold)d ||| % $._config, 'for': '15m', labels: { @@ -407,6 +407,20 @@ description: 'Systemd service {{ $labels.name }} has entered failed state at {{ $labels.instance }}', }, }, + { + alert: 'NodeSystemdServiceCrashlooping', + expr: ||| + increase(node_systemd_service_restart_total{%(nodeExporterSelector)s}[5m]) > 2 + ||| % $._config, + 'for': '15m', + labels: { + severity: 'warning', + }, + annotations: { + summary: 'Systemd service keeps restaring, possibly crash looping.', + description: 'Systemd service {{ $labels.name }} has being restarted too many times at {{ $labels.instance }} for the last 15 minutes. Please check if service is crash looping.', + }, + }, { alert: 'NodeBondingDegraded', expr: ||| diff --git a/docs/node-mixin/config.libsonnet b/docs/node-mixin/config.libsonnet index df2af23f92..1a4b3caae4 100644 --- a/docs/node-mixin/config.libsonnet +++ b/docs/node-mixin/config.libsonnet @@ -50,6 +50,16 @@ // 'NodeSystemSaturation' alert. systemSaturationPerCoreThreshold: 2, + // Some of the alerts use predict_linear() to fire alerts ahead of time to + // prevent unrecoverable situations (eg. no more disk space). However, the + // node may have automatic processes (cronjobs) in place to prevent that + // within a certain time window, this may not align with the default time + // window of these alerts. This can cause these alerts to start flapping. + // By reducing the time window, the system gets more time to + // resolve this before problems occur. + nodeWarningWindowHours: '24', + nodeCriticalWindowHours: '4', + // Available disk space (%) thresholds on which to trigger the // 'NodeFilesystemSpaceFillingUp' alerts. These alerts fire if the disk // usage grows in a way that it is predicted to run out in 4h or 1d diff --git a/docs/node-mixin/dashboards/node.libsonnet b/docs/node-mixin/dashboards/node.libsonnet index 898c912d56..41e2903389 100644 --- a/docs/node-mixin/dashboards/node.libsonnet +++ b/docs/node-mixin/dashboards/node.libsonnet @@ -1,7 +1,8 @@ { local nodemixin = import '../lib/prom-mixin.libsonnet', grafanaDashboards+:: { - 'nodes.json': nodemixin.new(config=$._config, platform='Linux').dashboard, - 'nodes-darwin.json': nodemixin.new(config=$._config, platform='Darwin').dashboard, + 'nodes.json': nodemixin.new(config=$._config, platform='Linux', uid=std.md5('nodes.json')).dashboard, + 'nodes-darwin.json': nodemixin.new(config=$._config, platform='Darwin', uid=std.md5('nodes-darwin.json')).dashboard, + 'nodes-aix.json': nodemixin.new(config=$._config, platform='AIX', uid=std.md5('nodes-aix.json')).dashboard, }, } diff --git a/docs/node-mixin/dashboards/use.libsonnet b/docs/node-mixin/dashboards/use.libsonnet index 65e96dd8dc..f9d9e07cf6 100644 --- a/docs/node-mixin/dashboards/use.libsonnet +++ b/docs/node-mixin/dashboards/use.libsonnet @@ -1,466 +1,480 @@ -local grafana = import 'github.com/grafana/grafonnet-lib/grafonnet/grafana.libsonnet'; +local grafana = import 'github.com/grafana/grafonnet/gen/grafonnet-latest/main.libsonnet'; local dashboard = grafana.dashboard; -local row = grafana.row; -local prometheus = grafana.prometheus; -local template = grafana.template; -local graphPanel = grafana.graphPanel; +local variable = dashboard.variable; +local row = grafana.panel.row; +local prometheus = grafana.query.prometheus; + +local timeSeriesPanel = grafana.panel.timeSeries; +local tsOptions = timeSeriesPanel.options; +local tsStandardOptions = timeSeriesPanel.standardOptions; +local tsQueryOptions = timeSeriesPanel.queryOptions; +local tsCustom = timeSeriesPanel.fieldConfig.defaults.custom; +local tsLegend = tsOptions.legend; local c = import '../config.libsonnet'; -local datasourceTemplate = { - current: { - text: 'default', - value: 'default', - }, - hide: 0, - label: 'Data Source', - name: 'datasource', - options: [], - query: 'prometheus', - refresh: 1, - regex: '', - type: 'datasource', -}; +local datasource = variable.datasource.new( + 'datasource', 'prometheus' +); + +local tsCommonPanelOptions = + variable.query.withDatasourceFromVariable(datasource) + + tsCustom.stacking.withMode('normal') + + tsCustom.withFillOpacity(100) + + tsCustom.withShowPoints('never') + + tsLegend.withShowLegend(false) + + tsOptions.tooltip.withMode('multi') + + tsOptions.tooltip.withSort('desc'); local CPUUtilisation = - graphPanel.new( + timeSeriesPanel.new( 'CPU Utilisation', - datasource='$datasource', - span=6, - format='percentunit', - stack=true, - fill=10, - legend_show=false, - ) { tooltip+: { sort: 2 } }; + ) + + tsCommonPanelOptions + + tsStandardOptions.withUnit('percentunit'); local CPUSaturation = // TODO: Is this a useful panel? At least there should be some explanation how load // average relates to the "CPU saturation" in the title. - graphPanel.new( + timeSeriesPanel.new( 'CPU Saturation (Load1 per CPU)', - datasource='$datasource', - span=6, - format='percentunit', - stack=true, - fill=10, - legend_show=false, - ) { tooltip+: { sort: 2 } }; + ) + + tsCommonPanelOptions + + tsStandardOptions.withUnit('percentunit'); local memoryUtilisation = - graphPanel.new( + timeSeriesPanel.new( 'Memory Utilisation', - datasource='$datasource', - span=6, - format='percentunit', - stack=true, - fill=10, - legend_show=false, - ) { tooltip+: { sort: 2 } }; + ) + + tsCommonPanelOptions + + tsStandardOptions.withUnit('percentunit'); local memorySaturation = - graphPanel.new( + timeSeriesPanel.new( 'Memory Saturation (Major Page Faults)', - datasource='$datasource', - span=6, - format='rds', - stack=true, - fill=10, - legend_show=false, - ) { tooltip+: { sort: 2 } }; + ) + + tsCommonPanelOptions + + tsStandardOptions.withUnit('rds'); + +local networkOverrides = tsStandardOptions.withOverrides( + [ + tsStandardOptions.override.byRegexp.new('/Transmit/') + + tsStandardOptions.override.byRegexp.withPropertiesFromOptions( + tsCustom.withTransform('negative-Y') + ), + ] +); local networkUtilisation = - graphPanel.new( + timeSeriesPanel.new( 'Network Utilisation (Bytes Receive/Transmit)', - datasource='$datasource', - span=6, - format='Bps', - stack=true, - fill=10, - legend_show=false, ) - .addSeriesOverride({ alias: '/Receive/', stack: 'A' }) - .addSeriesOverride({ alias: '/Transmit/', stack: 'B', transform: 'negative-Y' }) - { tooltip+: { sort: 2 } }; + + tsCommonPanelOptions + + tsStandardOptions.withUnit('Bps') + + networkOverrides; local networkSaturation = - graphPanel.new( + timeSeriesPanel.new( 'Network Saturation (Drops Receive/Transmit)', - datasource='$datasource', - span=6, - format='Bps', - stack=true, - fill=10, - legend_show=false, ) - .addSeriesOverride({ alias: '/ Receive/', stack: 'A' }) - .addSeriesOverride({ alias: '/ Transmit/', stack: 'B', transform: 'negative-Y' }) - { tooltip+: { sort: 2 } }; + + tsCommonPanelOptions + + tsStandardOptions.withUnit('Bps') + + networkOverrides; local diskIOUtilisation = - graphPanel.new( + timeSeriesPanel.new( 'Disk IO Utilisation', - datasource='$datasource', - span=6, - format='percentunit', - stack=true, - fill=10, - legend_show=false, - ) { tooltip+: { sort: 2 } }; + ) + + tsCommonPanelOptions + + tsStandardOptions.withUnit('percentunit'); local diskIOSaturation = - graphPanel.new( + timeSeriesPanel.new( 'Disk IO Saturation', - datasource='$datasource', - span=6, - format='percentunit', - stack=true, - fill=10, - legend_show=false, - ) { tooltip+: { sort: 2 } }; + ) + + tsCommonPanelOptions + + tsStandardOptions.withUnit('percentunit'); local diskSpaceUtilisation = - graphPanel.new( + timeSeriesPanel.new( 'Disk Space Utilisation', - datasource='$datasource', - span=12, - format='percentunit', - stack=true, - fill=10, - legend_show=false, - ) { tooltip+: { sort: 2 } }; + ) + + tsCommonPanelOptions + + tsStandardOptions.withUnit('percentunit'); { - _clusterTemplate:: template.new( - name='cluster', - datasource='$datasource', - query='label_values(node_time_seconds, %s)' % $._config.clusterLabel, - current='', - hide=if $._config.showMultiCluster then '' else '2', - refresh=2, - includeAll=false, - sort=1 - ), + _clusterVariable:: + variable.query.new('cluster') + + variable.query.withDatasourceFromVariable(datasource) + + variable.query.queryTypes.withLabelValues( + $._config.clusterLabel, + 'node_time_seconds', + ) + + (if $._config.showMultiCluster then variable.query.generalOptions.showOnDashboard.withLabelAndValue() else variable.query.generalOptions.showOnDashboard.withNothing()) + + variable.query.refresh.onTime() + + variable.query.selectionOptions.withIncludeAll(false) + + variable.query.withSort(asc=true), grafanaDashboards+:: { 'node-rsrc-use.json': - dashboard.new( '%sUSE Method / Node' % $._config.dashboardNamePrefix, - time_from='now-1h', - tags=($._config.dashboardTags), - timezone='utc', - refresh='30s', - graphTooltip='shared_crosshair' ) - .addTemplate(datasourceTemplate) - .addTemplate($._clusterTemplate) - .addTemplate( - template.new( + + dashboard.time.withFrom('now-1h') + + dashboard.withTags($._config.dashboardTags) + + dashboard.withTimezone('utc') + + dashboard.withRefresh('30s') + + dashboard.graphTooltip.withSharedCrosshair() + + dashboard.withUid(std.md5('node-rsrc-use.json')) + + dashboard.withVariables([ + datasource, + $._clusterVariable, + variable.query.new('instance') + + variable.query.withDatasourceFromVariable(datasource) + + variable.query.queryTypes.withLabelValues( 'instance', - '$datasource', - 'label_values(node_exporter_build_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}, instance)' % $._config, - refresh='time', - sort=1 - ) - ) - .addRow( - row.new('CPU') - .addPanel(CPUUtilisation.addTarget(prometheus.target('instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Utilisation'))) - .addPanel(CPUSaturation.addTarget(prometheus.target('instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Saturation'))) - ) - .addRow( - row.new('Memory') - .addPanel(memoryUtilisation.addTarget(prometheus.target('instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Utilisation'))) - .addPanel(memorySaturation.addTarget(prometheus.target('instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Major page Faults'))) - ) - .addRow( - row.new('Network') - .addPanel( - networkUtilisation - .addTarget(prometheus.target('instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Receive')) - .addTarget(prometheus.target('instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Transmit')) - ) - .addPanel( - networkSaturation - .addTarget(prometheus.target('instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Receive')) - .addTarget(prometheus.target('instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Transmit')) - ) - ) - .addRow( - row.new('Disk IO') - .addPanel(diskIOUtilisation.addTarget(prometheus.target('instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{device}}'))) - .addPanel(diskIOSaturation.addTarget(prometheus.target('instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{device}}'))) - ) - .addRow( - row.new('Disk Space') - .addPanel( - diskSpaceUtilisation.addTarget(prometheus.target( - ||| - sort_desc(1 - - ( - max without (mountpoint, fstype) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, fstype!="", instance="$instance", %(clusterLabel)s="$cluster"}) - / - max without (mountpoint, fstype) (node_filesystem_size_bytes{%(nodeExporterSelector)s, fstype!="", instance="$instance", %(clusterLabel)s="$cluster"}) - ) != 0 - ) - ||| % $._config, legendFormat='{{device}}' - )) + 'node_exporter_build_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}' % $._config, ) + + variable.query.refresh.onTime() + + variable.query.withSort(asc=true), + ]) + + dashboard.withPanels( + grafana.util.grid.makeGrid([ + row.new('CPU') + + row.withPanels([ + CPUUtilisation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Utilisation')]), + CPUSaturation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Saturation')]), + ]), + row.new('Memory') + + row.withPanels([ + memoryUtilisation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Utilisation')]), + memorySaturation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Major page Faults')]), + ]), + row.new('Network') + + row.withPanels([ + networkUtilisation + tsQueryOptions.withTargets([ + prometheus.new('$datasource', 'instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Receive'), + prometheus.new('$datasource', 'instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Transmit'), + ]), + networkSaturation + tsQueryOptions.withTargets([ + prometheus.new('$datasource', 'instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Receive'), + prometheus.new('$datasource', 'instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Transmit'), + ]), + ]), + row.new('Disk IO') + + row.withPanels([ + diskIOUtilisation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('{{device}}')]), + diskIOSaturation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('{{device}}')]), + ]), + ], panelWidth=12, panelHeight=7) + + grafana.util.grid.makeGrid([ + row.new('Disk Space') + + row.withPanels([ + diskSpaceUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sort_desc(1 - + ( + max without (mountpoint, fstype) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, fstype!="", instance="$instance", %(clusterLabel)s="$cluster"}) + / + max without (mountpoint, fstype) (node_filesystem_size_bytes{%(nodeExporterSelector)s, fstype!="", instance="$instance", %(clusterLabel)s="$cluster"}) + ) != 0 + ) + ||| % $._config + ) + prometheus.withLegendFormat('{{device}}'), + ]), + ]), + ], panelWidth=24, panelHeight=7, startY=34), ), - 'node-cluster-rsrc-use.json': dashboard.new( '%sUSE Method / Cluster' % $._config.dashboardNamePrefix, - time_from='now-1h', - tags=($._config.dashboardTags), - timezone='utc', - refresh='30s', - graphTooltip='shared_crosshair' - ) - .addTemplate(datasourceTemplate) - .addTemplate($._clusterTemplate) - .addRow( - row.new('CPU') - .addPanel( - CPUUtilisation - .addTarget(prometheus.target( - ||| - (( - instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} - * - instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} - ) != 0 ) - / scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) - ||| % $._config, legendFormat='{{ instance }}' - )) - ) - .addPanel( - CPUSaturation - .addTarget(prometheus.target( - ||| - ( - instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} - / scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) - ) != 0 - ||| % $._config, legendFormat='{{instance}}' - )) - ) ) - .addRow( - row.new('Memory') - .addPanel( - memoryUtilisation - .addTarget(prometheus.target( - ||| - ( - instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} - / scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) - ) != 0 - ||| % $._config, legendFormat='{{instance}}', - )) - ) - .addPanel(memorySaturation.addTarget(prometheus.target('instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}' % $._config, legendFormat='{{instance}}'))) - ) - .addRow( - row.new('Network') - .addPanel( - networkUtilisation - .addTarget(prometheus.target('instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Receive')) - .addTarget(prometheus.target('instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Transmit')) - ) - .addPanel( - networkSaturation - .addTarget(prometheus.target('instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Receive')) - .addTarget(prometheus.target('instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Transmit')) - ) - ) - .addRow( - row.new('Disk IO') - .addPanel( - diskIOUtilisation - .addTarget(prometheus.target( - ||| - ( - instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} - / scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) - ) != 0 - ||| % $._config, legendFormat='{{instance}} {{device}}' - )) - ) - .addPanel( - diskIOSaturation - .addTarget(prometheus.target( - ||| - ( + + dashboard.time.withFrom('now-1h') + + dashboard.withTags($._config.dashboardTags) + + dashboard.withTimezone('utc') + + dashboard.withRefresh('30s') + + dashboard.graphTooltip.withSharedCrosshair() + + dashboard.withUid(std.md5('node-cluster-rsrc-use.json')) + + dashboard.withVariables([ + datasource, + $._clusterVariable, + variable.query.withDatasourceFromVariable(datasource) + + variable.query.refresh.onTime() + + variable.query.withSort(asc=true), + ]) + + dashboard.withPanels( + grafana.util.grid.makeGrid([ + row.new('CPU') + + row.withPanels([ + CPUUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + (( + instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} + * + instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} + ) != 0 ) + / scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) + ||| % $._config + ) + prometheus.withLegendFormat('{{ instance }}'), + ]), + CPUSaturation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + ( + instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} + / scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) + ) != 0 + ||| % $._config + ) + prometheus.withLegendFormat('{{ instance }}'), + ]), + ]), + row.new('Memory') + + row.withPanels([ + memoryUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + ( + instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} + / scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) + ) != 0 + ||| % $._config + ) + prometheus.withLegendFormat('{{ instance }}'), + ]), + memorySaturation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + 'instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}' % $._config + ) + prometheus.withLegendFormat('{{ instance }}'), + ]), + ]), + row.new('Network') + + row.withPanels([ + networkUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + 'instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config + ) + prometheus.withLegendFormat('{{ instance }} Receive'), + prometheus.new( + '$datasource', + 'instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config + ) + prometheus.withLegendFormat('{{ instance }} Transmit'), + ]), + networkSaturation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + 'instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config + ) + prometheus.withLegendFormat('{{ instance }} Receive'), + prometheus.new( + '$datasource', + 'instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config + ) + prometheus.withLegendFormat('{{ instance }} Transmit'), + ]), + ]), + row.new('Disk IO') + + row.withPanels([ + diskIOUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} + / scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) + ||| % $._config + ) + prometheus.withLegendFormat('{{ instance }} {{device}}'), + ]), + diskIOSaturation + tsQueryOptions.withTargets([prometheus.new( + '$datasource', + ||| instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) - ) != 0 - ||| % $._config, legendFormat='{{instance}} {{device}}' - )) - ) - ) - .addRow( - row.new('Disk Space') - .addPanel( - diskSpaceUtilisation - .addTarget(prometheus.target( - ||| - sum without (device) ( - max without (fstype, mountpoint) (( - node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"} - - - node_filesystem_avail_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"} - ) != 0) - ) - / scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"}))) - ||| % $._config, legendFormat='{{instance}}' - )) - ) + ||| % $._config + ) + prometheus.withLegendFormat('{{ instance }} {{device}}')]), + ]), + ], panelWidth=12, panelHeight=7) + + grafana.util.grid.makeGrid([ + row.new('Disk Space') + + row.withPanels([ + diskSpaceUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum without (device) ( + max without (fstype, mountpoint) (( + node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"} + - + node_filesystem_avail_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"} + ) != 0) + ) + / scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"}))) + ||| % $._config + ) + prometheus.withLegendFormat('{{ instance }}'), + ]), + ]), + ], panelWidth=24, panelHeight=7, startY=34), ), } + if $._config.showMultiCluster then { 'node-multicluster-rsrc-use.json': dashboard.new( '%sUSE Method / Multi-cluster' % $._config.dashboardNamePrefix, - time_from='now-1h', - tags=($._config.dashboardTags), - timezone='utc', - refresh='30s', - graphTooltip='shared_crosshair' - ) - .addTemplate(datasourceTemplate) - .addRow( - row.new('CPU') - .addPanel( - CPUUtilisation - .addTarget(prometheus.target( - ||| - sum( - (( - instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s} - * - instance:node_num_cpu:sum{%(nodeExporterSelector)s} - ) != 0) - / scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s})) - ) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config - )) - ) - .addPanel( - CPUSaturation - .addTarget(prometheus.target( - ||| - sum(( - instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s} - / scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s})) - ) != 0) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config - )) - ) ) - .addRow( - row.new('Memory') - .addPanel( - memoryUtilisation - .addTarget(prometheus.target( - ||| - sum(( - instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s} - / scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s})) - ) != 0) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config - )) - ) - .addPanel( - memorySaturation - .addTarget(prometheus.target( - ||| - sum(( - instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s} - ) != 0) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config - )) - ) - ) - .addRow( - row.new('Network') - .addPanel( - networkUtilisation - .addTarget(prometheus.target( - ||| - sum(( - instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} - ) != 0) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}} Receive' % $._config - )) - .addTarget(prometheus.target( - ||| - sum(( - instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} - ) != 0) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}} Transmit' % $._config - )) - ) - .addPanel( - networkSaturation - .addTarget(prometheus.target( - ||| - sum(( - instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} - ) != 0) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}} Receive' % $._config - )) - .addTarget(prometheus.target( - ||| - sum(( - instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} - ) != 0) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}} Transmit' % $._config - )) - ) - ) - .addRow( - row.new('Disk IO') - .addPanel( - diskIOUtilisation - .addTarget(prometheus.target( - ||| - sum(( - instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s} - / scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s})) - ) != 0) by (%(clusterLabel)s, device) - ||| % $._config, legendFormat='{{%(clusterLabel)s}} {{device}}' % $._config - )) - ) - .addPanel( - diskIOSaturation - .addTarget(prometheus.target( - ||| - sum(( - instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s} - / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s})) - ) != 0) by (%(clusterLabel)s, device) - ||| % $._config, legendFormat='{{%(clusterLabel)s}} {{device}}' % $._config - )) - ) - ) - .addRow( - row.new('Disk Space') - .addPanel( - diskSpaceUtilisation - .addTarget(prometheus.target( - ||| - sum ( - sum without (device) ( - max without (fstype, mountpoint, instance, pod) (( - node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s} - node_filesystem_avail_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s} - ) != 0) - ) - / scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s}))) - ) by (%(clusterLabel)s) - ||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config - )) - ) + + dashboard.time.withFrom('now-1h') + + dashboard.withTags($._config.dashboardTags) + + dashboard.withTimezone('utc') + + dashboard.withRefresh('30s') + + dashboard.graphTooltip.withSharedCrosshair() + + dashboard.withUid(std.md5('node-multicluster-rsrc-use.json')) + + dashboard.withVariables([ + datasource, + variable.query.withDatasourceFromVariable(datasource) + + variable.query.refresh.onTime() + + variable.query.withSort(asc=true), + ]) + + dashboard.withPanels( + grafana.util.grid.makeGrid([ + row.new('CPU') + + row.withPanels([ + CPUUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum( + (( + instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s} + * + instance:node_num_cpu:sum{%(nodeExporterSelector)s} + ) != 0) + / scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s})) + ) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'), + ]), + CPUSaturation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum(( + instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s} + / scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s})) + ) != 0) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'), + ]), + ]), + row.new('Memory') + + row.withPanels([ + memoryUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum(( + instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s} + / scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s})) + ) != 0) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'), + ]), + memorySaturation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum(( + instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s} + ) != 0) by (%(clusterLabel)s) + ||| + % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'), + ]), + ]), + row.new('Network') + + row.withPanels([ + networkUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum(( + instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} + ) != 0) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Receive'), + prometheus.new( + '$datasource', + ||| + sum(( + instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} + ) != 0) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Transmit'), + ]), + networkSaturation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum(( + instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} + ) != 0) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Receive'), + prometheus.new( + '$datasource', + ||| + sum(( + instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} + ) != 0) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Transmit'), + ]), + ]), + row.new('Disk IO') + + row.withPanels([ + diskIOUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum(( + instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s} + / scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s})) + ) != 0) by (%(clusterLabel)s, device) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} {{device}}'), + ]), + diskIOSaturation + tsQueryOptions.withTargets([prometheus.new( + '$datasource', + ||| + sum(( + instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s} + / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s})) + ) != 0) by (%(clusterLabel)s, device) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} {{device}}')]), + ]), + + ], panelWidth=12, panelHeight=7) + + grafana.util.grid.makeGrid([ + row.new('Disk Space') + + row.withPanels([ + diskSpaceUtilisation + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + sum ( + sum without (device) ( + max without (fstype, mountpoint, instance, pod) (( + node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s} - node_filesystem_avail_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s} + ) != 0) + ) + / scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s}))) + ) by (%(clusterLabel)s) + ||| % $._config + ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'), + ]), + ]), + ], panelWidth=24, panelHeight=7, startY=34), ), } else {}, } diff --git a/docs/node-mixin/jsonnetfile.json b/docs/node-mixin/jsonnetfile.json index 721d4833a0..2d56d91245 100644 --- a/docs/node-mixin/jsonnetfile.json +++ b/docs/node-mixin/jsonnetfile.json @@ -4,20 +4,11 @@ { "source": { "git": { - "remote": "https://github.com/grafana/grafonnet-lib.git", - "subdir": "grafonnet" + "remote": "https://github.com/grafana/grafonnet.git", + "subdir": "gen/grafonnet-latest" } }, - "version": "master" - }, - { - "source": { - "git": { - "remote": "https://github.com/grafana/grafonnet-lib.git", - "subdir": "grafonnet-7.0" - } - }, - "version": "master" + "version": "main" } ], "legacyImports": false diff --git a/docs/node-mixin/lib/prom-mixin.libsonnet b/docs/node-mixin/lib/prom-mixin.libsonnet index 5d2e7bd0ce..f18c273c29 100644 --- a/docs/node-mixin/lib/prom-mixin.libsonnet +++ b/docs/node-mixin/lib/prom-mixin.libsonnet @@ -1,521 +1,535 @@ -local grafana = import 'github.com/grafana/grafonnet-lib/grafonnet/grafana.libsonnet'; +local grafana = import 'github.com/grafana/grafonnet/gen/grafonnet-latest/main.libsonnet'; local dashboard = grafana.dashboard; -local row = grafana.row; -local prometheus = grafana.prometheus; -local template = grafana.template; -local graphPanel = grafana.graphPanel; -local grafana70 = import 'github.com/grafana/grafonnet-lib/grafonnet-7.0/grafana.libsonnet'; -local gaugePanel = grafana70.panel.gauge; -local table = grafana70.panel.table; +local row = grafana.panel.row; +local prometheus = grafana.query.prometheus; +local variable = dashboard.variable; + +local timeSeriesPanel = grafana.panel.timeSeries; +local tsOptions = timeSeriesPanel.options; +local tsStandardOptions = timeSeriesPanel.standardOptions; +local tsQueryOptions = timeSeriesPanel.queryOptions; +local tsCustom = timeSeriesPanel.fieldConfig.defaults.custom; + +local gaugePanel = grafana.panel.gauge; +local gaugeStep = gaugePanel.standardOptions.threshold.step; + +local table = grafana.panel.table; +local tableStep = table.standardOptions.threshold.step; +local tableOverride = table.standardOptions.override; +local tableTransformation = table.queryOptions.transformation; { - new(config=null, platform=null):: { - - local prometheusDatasourceTemplate = { - current: { - text: 'default', - value: 'default', - }, - hide: 0, - label: 'Data Source', - name: 'datasource', - options: [], - query: 'prometheus', - refresh: 1, - regex: '', - type: 'datasource', - }, - - local clusterTemplatePrototype = - template.new( - 'cluster', - '$datasource', - '', - hide=if config.showMultiCluster then '' else '2', - refresh='time', - label='Cluster', - ), - local clusterTemplate = + new(config=null, platform=null, uid=null):: { + + local prometheusDatasourceVariable = variable.datasource.new( + 'datasource', 'prometheus' + ), + + local clusterVariablePrototype = + variable.query.new('cluster') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + (if config.showMultiCluster then variable.query.generalOptions.showOnDashboard.withLabelAndValue() else variable.query.generalOptions.showOnDashboard.withNothing()) + + variable.query.refresh.onTime() + + variable.query.generalOptions.withLabel('Cluster'), + + local clusterVariable = if platform == 'Darwin' then - clusterTemplatePrototype - { query: 'label_values(node_uname_info{%(nodeExporterSelector)s, sysname="Darwin"}, %(clusterLabel)s)' % config } + clusterVariablePrototype + + variable.query.queryTypes.withLabelValues( + ' %(clusterLabel)s' % config, + 'node_uname_info{%(nodeExporterSelector)s, sysname="Darwin"}' % config, + ) else - clusterTemplatePrototype - { query: 'label_values(node_uname_info{%(nodeExporterSelector)s, sysname!="Darwin"}, %(clusterLabel)s)' % config }, - - local instanceTemplatePrototype = - template.new( - 'instance', - '$datasource', - '', - refresh='time', - label='Instance', - ), - local instanceTemplate = + clusterVariablePrototype + + variable.query.queryTypes.withLabelValues( + '%(clusterLabel)s' % config, + 'node_uname_info{%(nodeExporterSelector)s, sysname!="Darwin"}' % config, + ), + + local instanceVariablePrototype = + variable.query.new('instance') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + variable.query.refresh.onTime() + + variable.query.generalOptions.withLabel('Instance'), + + local instanceVariable = if platform == 'Darwin' then - instanceTemplatePrototype - { query: 'label_values(node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname="Darwin"}, instance)' % config } + instanceVariablePrototype + + variable.query.queryTypes.withLabelValues( + 'instance', + 'node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname="Darwin"}' % config, + ) else - instanceTemplatePrototype - { query: 'label_values(node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname!="Darwin"}, instance)' % config }, + instanceVariablePrototype + + variable.query.queryTypes.withLabelValues( + 'instance', + 'node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname!="Darwin"}' % config, + ), local idleCPU = - graphPanel.new( - 'CPU Usage', - datasource='$datasource', - span=6, - format='percentunit', - max=1, - min=0, - stack=true, - ) - .addTarget(prometheus.target( - ||| - ( - (1 - sum without (mode) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode=~"idle|iowait|steal", instance="$instance", %(clusterLabel)s="$cluster"}[$__rate_interval]))) - / ignoring(cpu) group_left - count without (cpu, mode) (node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance", %(clusterLabel)s="$cluster"}) - ) - ||| % config, - legendFormat='{{cpu}}', - intervalFactor=5, - )), + timeSeriesPanel.new('CPU Usage') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + tsStandardOptions.withUnit('percentunit') + + tsCustom.stacking.withMode('normal') + + tsStandardOptions.withMax(1) + + tsStandardOptions.withMin(0) + + tsOptions.tooltip.withMode('multi') + + tsCustom.withFillOpacity(10) + + tsCustom.withShowPoints('never') + + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + ( + (1 - sum without (mode) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode=~"idle|iowait|steal", instance="$instance", %(clusterLabel)s="$cluster"}[$__rate_interval]))) + / ignoring(cpu) group_left + count without (cpu, mode) (node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance", %(clusterLabel)s="$cluster"}) + ) + ||| % config, + ) + + prometheus.withLegendFormat('{{cpu}}') + + prometheus.withIntervalFactor(5), + ]), local systemLoad = - graphPanel.new( - 'Load Average', - datasource='$datasource', - span=6, - format='short', - min=0, - fill=0, - ) - .addTarget(prometheus.target('node_load1{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='1m load average')) - .addTarget(prometheus.target('node_load5{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='5m load average')) - .addTarget(prometheus.target('node_load15{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='15m load average')) - .addTarget(prometheus.target('count(node_cpu_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", mode="idle"})' % config, legendFormat='logical cores')), + timeSeriesPanel.new('Load Average') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + tsStandardOptions.withUnit('short') + + tsStandardOptions.withMin(0) + + tsCustom.withFillOpacity(0) + + tsCustom.withShowPoints('never') + + tsOptions.tooltip.withMode('multi') + + tsQueryOptions.withTargets([ + prometheus.new('$datasource', 'node_load1{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('1m load average'), + prometheus.new('$datasource', 'node_load5{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('5m load average'), + prometheus.new('$datasource', 'node_load15{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('15m load average'), + prometheus.new('$datasource', 'count(node_cpu_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", mode="idle"})' % config) + prometheus.withLegendFormat('logical cores'), + ]), local memoryGraphPanelPrototype = - graphPanel.new( - 'Memory Usage', - datasource='$datasource', - span=9, - format='bytes', - min=0, - ), + timeSeriesPanel.new('Memory Usage') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + tsStandardOptions.withUnit('bytes') + + tsStandardOptions.withMin(0) + + tsOptions.tooltip.withMode('multi') + + tsCustom.withFillOpacity(10) + + tsCustom.withShowPoints('never'), + local memoryGraph = if platform == 'Linux' then - memoryGraphPanelPrototype { stack: true } - .addTarget(prometheus.target( - ||| - ( - node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - - - node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - - - node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - - - node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - ) - ||| % config, - legendFormat='memory used' - )) - .addTarget(prometheus.target('node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='memory buffers')) - .addTarget(prometheus.target('node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='memory cached')) - .addTarget(prometheus.target('node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='memory free')) + memoryGraphPanelPrototype + + tsCustom.stacking.withMode('normal') + + tsQueryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + ( + node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + - + node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + - + node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + - + node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + ) + ||| % config, + ) + prometheus.withLegendFormat('memory used'), + prometheus.new('$datasource', 'node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('memory buffers'), + prometheus.new('$datasource', 'node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('memory cached'), + prometheus.new('$datasource', 'node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('memory free'), + ]) else if platform == 'Darwin' then // not useful to stack - memoryGraphPanelPrototype { stack: false } - .addTarget(prometheus.target('node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='Physical Memory')) - .addTarget(prometheus.target( - ||| - ( - node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - - node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + - node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + - node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - ) - ||| % config, legendFormat='Memory Used' - )) - .addTarget(prometheus.target( - ||| - ( - node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - - node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - ) - ||| % config, legendFormat='App Memory' - )) - .addTarget(prometheus.target('node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='Wired Memory')) - .addTarget(prometheus.target('node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='Compressed')), + memoryGraphPanelPrototype + + tsCustom.stacking.withMode('none') + + tsQueryOptions.withTargets([ + prometheus.new('$datasource', 'node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Physical Memory'), + prometheus.new( + '$datasource', + ||| + ( + node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - + node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + + node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + + node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + ) + ||| % config + ) + prometheus.withLegendFormat( + 'Memory Used' + ), + prometheus.new( + '$datasource', + ||| + ( + node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - + node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + ) + ||| % config + ) + prometheus.withLegendFormat( + 'App Memory' + ), + prometheus.new('$datasource', 'node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Wired Memory'), + prometheus.new('$datasource', 'node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Compressed'), + ]) + + else if platform == 'AIX' then + memoryGraphPanelPrototype + + tsCustom.stacking.withMode('none') + + tsQueryOptions.withTargets([ + prometheus.new('$datasource', 'node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Physical Memory'), + prometheus.new( + '$datasource', + ||| + ( + node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - + node_memory_available_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + ) + ||| % config + ) + prometheus.withLegendFormat('Memory Used'), + ]), + // NOTE: avg() is used to circumvent a label change caused by a node_exporter rollout. local memoryGaugePanelPrototype = - gaugePanel.new( - title='Memory Usage', - datasource='$datasource', - ) - .addThresholdStep('rgba(50, 172, 45, 0.97)') - .addThresholdStep('rgba(237, 129, 40, 0.89)', 80) - .addThresholdStep('rgba(245, 54, 54, 0.9)', 90) - .setFieldConfig(max=100, min=0, unit='percent') - + { - span: 3, - }, + gaugePanel.new('Memory Usage') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + gaugePanel.standardOptions.thresholds.withSteps([ + gaugeStep.withColor('rgba(50, 172, 45, 0.97)'), + gaugeStep.withColor('rgba(237, 129, 40, 0.89)') + gaugeStep.withValue(80), + gaugeStep.withColor('rgba(245, 54, 54, 0.9)') + gaugeStep.withValue(90), + ]) + + gaugePanel.standardOptions.withMax(100) + + gaugePanel.standardOptions.withMin(0) + + gaugePanel.standardOptions.withUnit('percent'), local memoryGauge = if platform == 'Linux' then memoryGaugePanelPrototype - - .addTarget(prometheus.target( - ||| - 100 - - ( - avg(node_memory_MemAvailable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) / - avg(node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) - * 100 - ) - ||| % config, - )) + + gaugePanel.queryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + 100 - + ( + avg(node_memory_MemAvailable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) / + avg(node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) + * 100 + ) + ||| % config, + ), + ]) else if platform == 'Darwin' then memoryGaugePanelPrototype - .addTarget(prometheus.target( - ||| - ( - ( - avg(node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) - - avg(node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) + - avg(node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) + - avg(node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) - ) / + + gaugePanel.queryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + ( + ( + avg(node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) - + avg(node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) + + avg(node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) + + avg(node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) + ) / + avg(node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) + ) + * + 100 + ||| % config + ), + ]) + + else if platform == 'AIX' then + memoryGaugePanelPrototype + + gaugePanel.queryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + 100 - + ( + avg(node_memory_available_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) / avg(node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}) - ) - * - 100 - ||| % config - )), + * 100 + ) + ||| % config + ), + ]), + local diskIO = - graphPanel.new( - 'Disk I/O', - datasource='$datasource', - span=6, - min=0, - fill=0, - ) - // TODO: Does it make sense to have those three in the same panel? - .addTarget(prometheus.target( - 'rate(node_disk_read_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config, - legendFormat='{{device}} read', - intervalFactor=1, - )) - .addTarget(prometheus.target( - 'rate(node_disk_written_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config, - legendFormat='{{device}} written', - intervalFactor=1, - )) - .addTarget(prometheus.target( - 'rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config, - legendFormat='{{device}} io time', - intervalFactor=1, - )) + - { - seriesOverrides: [ - { - alias: '/ read| written/', - yaxis: 1, - }, - { - alias: '/ io time/', - yaxis: 2, - }, - ], - yaxes: [ - self.yaxe(format='Bps'), - self.yaxe(format='percentunit'), - ], - }, + timeSeriesPanel.new('Disk I/O') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + tsStandardOptions.withMin(0) + + tsCustom.withFillOpacity(0) + + tsCustom.withShowPoints('never') + + tsOptions.tooltip.withMode('multi') + + tsQueryOptions.withTargets([ + // TODO: Does it make sense to have those three in the same panel? + prometheus.new('$datasource', 'rate(node_disk_read_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config) + + prometheus.withLegendFormat('{{device}} read') + + prometheus.withIntervalFactor(1), + prometheus.new('$datasource', 'rate(node_disk_written_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config) + + prometheus.withLegendFormat('{{device}} written') + + prometheus.withIntervalFactor(1), + prometheus.new('$datasource', 'rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config) + + prometheus.withLegendFormat('{{device}} io time') + + prometheus.withIntervalFactor(1), + ]) + + tsStandardOptions.withOverrides( + [ + tsStandardOptions.override.byRegexp.new('/ read| written/') + + tsStandardOptions.override.byRegexp.withPropertiesFromOptions( + tsStandardOptions.withUnit('Bps') + ), + tsStandardOptions.override.byRegexp.new('/ io time/') + + tsStandardOptions.override.byRegexp.withPropertiesFromOptions(tsStandardOptions.withUnit('percentunit')), + ] + ), local diskSpaceUsage = - table.new( - title='Disk Space Usage', - datasource='$datasource', - ) - .setFieldConfig(unit='decbytes') - .addThresholdStep(color='green', value=null) - .addThresholdStep(color='yellow', value=0.8) - .addThresholdStep(color='red', value=0.9) - .addTarget(prometheus.target( - ||| - max by (mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s}) - ||| % config, - legendFormat='', - instant=true, - format='table' - )) - .addTarget(prometheus.target( - ||| - max by (mountpoint) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s}) - ||| % config, - legendFormat='', - instant=true, - format='table' - )) - .addOverride( - matcher={ - id: 'byName', - options: 'Mounted on', - }, - properties=[ - { - id: 'custom.width', - value: 260, - }, - ], - ) - .addOverride( - matcher={ - id: 'byName', - options: 'Size', - }, - properties=[ - - { - id: 'custom.width', - value: 93, - }, - - ], - ) - .addOverride( - matcher={ - id: 'byName', - options: 'Used', - }, - properties=[ - { - id: 'custom.width', - value: 72, - }, - ], - ) - .addOverride( - matcher={ - id: 'byName', - options: 'Available', - }, - properties=[ - { - id: 'custom.width', - value: 88, - }, - ], - ) - - .addOverride( - matcher={ - id: 'byName', - options: 'Used, %', - }, - properties=[ - { - id: 'unit', - value: 'percentunit', - }, - { - id: 'custom.displayMode', - value: 'gradient-gauge', - }, - { - id: 'max', - value: 1, - }, - { - id: 'min', - value: 0, - }, + table.new('Disk Space Usage') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + table.standardOptions.withUnit('decbytes') + + table.standardOptions.thresholds.withSteps( + [ + tableStep.withColor('green'), + tableStep.withColor('yellow') + gaugeStep.withValue(0.8), + tableStep.withColor('red') + gaugeStep.withValue(0.9), ] ) - + { span: 6 } - + { - transformations: [ + + table.queryOptions.withTargets([ + prometheus.new( + '$datasource', + ||| + max by (mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s}) + ||| % config + ) + + prometheus.withLegendFormat('') + + prometheus.withInstant() + + prometheus.withFormat('table'), + prometheus.new( + '$datasource', + ||| + max by (mountpoint) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s}) + ||| % config + ) + + prometheus.withLegendFormat('') + + prometheus.withInstant() + + prometheus.withFormat('table'), + ]) + + table.standardOptions.withOverrides([ + tableOverride.byName.new('Mounted on') + + tableOverride.byName.withProperty('custom.width', 260), + tableOverride.byName.new('Size') + + tableOverride.byName.withProperty('custom.width', 93), + tableOverride.byName.new('Used') + + tableOverride.byName.withProperty('custom.width', 72), + tableOverride.byName.new('Available') + + tableOverride.byName.withProperty('custom.width', 88), + tableOverride.byName.new('Used, %') + + tableOverride.byName.withProperty('unit', 'percentunit') + + tableOverride.byName.withPropertiesFromOptions( + table.fieldConfig.defaults.custom.withCellOptions( + { type: 'gauge' }, + ) + ) + + tableOverride.byName.withProperty('max', 1) + + tableOverride.byName.withProperty('min', 0), + ]) + + table.queryOptions.withTransformations([ + tableTransformation.withId('groupBy') + + tableTransformation.withOptions( { - id: 'groupBy', - options: { - fields: { - 'Value #A': { - aggregations: [ - 'lastNotNull', - ], - operation: 'aggregate', - }, - 'Value #B': { - aggregations: [ - 'lastNotNull', - ], - operation: 'aggregate', - }, - mountpoint: { - aggregations: [], - operation: 'groupby', - }, + fields: { + 'Value #A': { + aggregations: [ + 'lastNotNull', + ], + operation: 'aggregate', }, - }, - }, - { - id: 'merge', - options: {}, - }, - { - id: 'calculateField', - options: { - alias: 'Used', - binary: { - left: 'Value #A (lastNotNull)', - operator: '-', - reducer: 'sum', - right: 'Value #B (lastNotNull)', + 'Value #B': { + aggregations: [ + 'lastNotNull', + ], + operation: 'aggregate', }, - mode: 'binary', - reduce: { - reducer: 'sum', + mountpoint: { + aggregations: [], + operation: 'groupby', }, }, - }, + } + ), + tableTransformation.withId('merge'), + tableTransformation.withId('calculateField') + + tableTransformation.withOptions( { - id: 'calculateField', - options: { - alias: 'Used, %', - binary: { - left: 'Used', - operator: '/', - reducer: 'sum', - right: 'Value #A (lastNotNull)', - }, - mode: 'binary', - reduce: { - reducer: 'sum', - }, + alias: 'Used', + binary: { + left: 'Value #A (lastNotNull)', + operator: '-', + reducer: 'sum', + right: 'Value #B (lastNotNull)', }, - }, + mode: 'binary', + reduce: { + reducer: 'sum', + }, + } + ), + tableTransformation.withId('calculateField') + + tableTransformation.withOptions( { - id: 'organize', - options: { - excludeByName: {}, - indexByName: {}, - renameByName: { - 'Value #A (lastNotNull)': 'Size', - 'Value #B (lastNotNull)': 'Available', - mountpoint: 'Mounted on', - }, + alias: 'Used, %', + binary: { + left: 'Used', + operator: '/', + reducer: 'sum', + right: 'Value #A (lastNotNull)', }, - }, + mode: 'binary', + reduce: { + reducer: 'sum', + }, + } + ), + tableTransformation.withId('organize') + + tableTransformation.withOptions( { - id: 'sortBy', - options: { - fields: {}, - sort: [ - { - field: 'Mounted on', - }, - ], + excludeByName: {}, + indexByName: {}, + renameByName: { + 'Value #A (lastNotNull)': 'Size', + 'Value #B (lastNotNull)': 'Available', + mountpoint: 'Mounted on', }, - }, - ], - }, + } + ), + tableTransformation.withId('sortBy') + + tableTransformation.withOptions( + { + fields: {}, + sort: [ + { + field: 'Mounted on', + }, + ], + } + ), + ]), local networkReceived = - graphPanel.new( - 'Network Received', - description='Network received (bits/s)', - datasource='$datasource', - span=6, - format='bps', - min=0, - fill=0, - ) - .addTarget(prometheus.target( - 'rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config, - legendFormat='{{device}}', - intervalFactor=1, - )), + timeSeriesPanel.new('Network Received') + + timeSeriesPanel.panelOptions.withDescription('Network received (bits/s)') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + tsStandardOptions.withUnit('bps') + + tsStandardOptions.withMin(0) + + tsCustom.withFillOpacity(0) + + tsCustom.withShowPoints('never') + + tsOptions.tooltip.withMode('multi') + + tsQueryOptions.withTargets([ + prometheus.new('$datasource', 'rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config) + + prometheus.withLegendFormat('{{device}}') + + prometheus.withIntervalFactor(1), + ]), local networkTransmitted = - graphPanel.new( - 'Network Transmitted', - description='Network transmitted (bits/s)', - datasource='$datasource', - span=6, - format='bps', - min=0, - fill=0, - ) - .addTarget(prometheus.target( - 'rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config, - legendFormat='{{device}}', - intervalFactor=1, - )), + timeSeriesPanel.new('Network Transmitted') + + timeSeriesPanel.panelOptions.withDescription('Network transmitted (bits/s)') + + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable) + + tsStandardOptions.withUnit('bps') + + tsStandardOptions.withMin(0) + + tsCustom.withFillOpacity(0) + + tsOptions.tooltip.withMode('multi') + + tsQueryOptions.withTargets([ + prometheus.new('$datasource', 'rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config) + + prometheus.withLegendFormat('{{device}}') + + prometheus.withIntervalFactor(1), + ]), local cpuRow = row.new('CPU') - .addPanel(idleCPU) - .addPanel(systemLoad), + + row.withPanels([ + idleCPU, + systemLoad, + ]), - local memoryRow = - row.new('Memory') - .addPanel(memoryGraph) - .addPanel(memoryGauge), + local memoryRow = [ + row.new('Memory') + row.gridPos.withY(8), + memoryGraph + row.gridPos.withX(0) + row.gridPos.withY(9) + row.gridPos.withH(7) + row.gridPos.withW(18), + memoryGauge + row.gridPos.withX(18) + row.gridPos.withY(9) + row.gridPos.withH(7) + row.gridPos.withW(6), + ], local diskRow = row.new('Disk') - .addPanel(diskIO) - .addPanel(diskSpaceUsage), + + row.withPanels([ + diskIO, + diskSpaceUsage, + ]), local networkRow = row.new('Network') - .addPanel(networkReceived) - .addPanel(networkTransmitted), + + row.withPanels([ + networkReceived, + networkTransmitted, + ]), - local rows = - [ + local panels = + grafana.util.grid.makeGrid([ cpuRow, - memoryRow, + ], panelWidth=12, panelHeight=7) + + memoryRow + + grafana.util.grid.makeGrid([ diskRow, networkRow, - ], + ], panelWidth=12, panelHeight=7, startY=18), - local templates = + local variables = [ - prometheusDatasourceTemplate, - clusterTemplate, - instanceTemplate, + prometheusDatasourceVariable, + clusterVariable, + instanceVariable, ], - dashboard: if platform == 'Linux' then dashboard.new( '%sNodes' % config.dashboardNamePrefix, - time_from='now-1h', - tags=(config.dashboardTags), - timezone='utc', - refresh='30s', - graphTooltip='shared_crosshair' ) - .addTemplates(templates) - .addRows(rows) + + dashboard.time.withFrom('now-1h') + + dashboard.withTags(config.dashboardTags) + + dashboard.withTimezone('utc') + + dashboard.withRefresh('30s') + + dashboard.withUid(std.md5(uid)) + + dashboard.graphTooltip.withSharedCrosshair() + + dashboard.withVariables(variables) + + dashboard.withPanels(panels) else if platform == 'Darwin' then dashboard.new( '%sMacOS' % config.dashboardNamePrefix, - time_from='now-1h', - tags=(config.dashboardTags), - timezone='utc', - refresh='30s', - graphTooltip='shared_crosshair' ) - .addTemplates(templates) - .addRows(rows), + + dashboard.time.withFrom('now-1h') + + dashboard.withTags(config.dashboardTags) + + dashboard.withTimezone('utc') + + dashboard.withRefresh('30s') + + dashboard.withUid(std.md5(uid)) + + dashboard.graphTooltip.withSharedCrosshair() + + dashboard.withVariables(variables) + + dashboard.withPanels(panels) + else if platform == 'AIX' then + dashboard.new( + '%sAIX' % config.dashboardNamePrefix, + ) + + dashboard.time.withFrom('now-1h') + + dashboard.withTags(config.dashboardTags) + + dashboard.withTimezone('utc') + + dashboard.withRefresh('30s') + + dashboard.withUid(std.md5(uid)) + + dashboard.graphTooltip.withSharedCrosshair() + + dashboard.withVariables(variables) + + dashboard.withPanels(panels), }, } diff --git a/end-to-end-test.sh b/end-to-end-test.sh index 35e4534e6d..944bdc0e26 100755 --- a/end-to-end-test.sh +++ b/end-to-end-test.sh @@ -2,6 +2,38 @@ set -euf -o pipefail +# Allow setting GOHOSTOS for debugging purposes. +GOHOSTOS=${GOHOSTOS:-$(go env GOHOSTOS)} + +# Allow setting arch for debugging purposes. +arch=${arch:-$(uname -m)} + +maybe_flag_search_scope() { + local collector=$1 + os_aux_os="" + if [[ $GOHOSTOS =~ ^(freebsd|openbsd|netbsd|solaris|dragonfly)$ ]]; then + os_aux_os=" ${collector}_bsd.go" + fi + echo "${collector}_common.go ${collector}.go ${collector}_${GOHOSTOS}.go ${collector}_${GOHOSTOS}_${arch}.go${os_aux_os}" +} + +supported_collectors() { + local collectors=$1 + local supported="" + for collector in ${collectors}; do + for filename in $(maybe_flag_search_scope "${collector}"); do + file="collector/${filename}" + if ./tools/tools match ${file} > /dev/null 2>&1; then + if grep -h -E -o -- "registerCollector\(" ${file} > /dev/null 2>&1; then + supported="${supported} ${collector}" + fi + break + fi + done + done + echo "${supported}" | tr ' ' '\n' | sort | uniq +} + enabled_collectors=$(cat << COLLECTORS arp bcache @@ -57,6 +89,8 @@ enabled_collectors=$(cat << COLLECTORS zoneinfo COLLECTORS ) +supported_enabled_collectors=$(supported_collectors "${enabled_collectors}") + disabled_collectors=$(cat << COLLECTORS selinux filesystem @@ -64,6 +98,8 @@ disabled_collectors=$(cat << COLLECTORS uname COLLECTORS ) +supported_disabled_collectors=$(supported_collectors "${disabled_collectors}") + cd "$(dirname $0)" port="$((10000 + (RANDOM % 10000)))" @@ -71,11 +107,9 @@ tmpdir=$(mktemp -d /tmp/node_exporter_e2e_test.XXXXXX) skip_re="^(go_|node_exporter_build_info|node_scrape_collector_duration_seconds|process_|node_textfile_mtime_seconds|node_time_(zone|seconds)|node_network_(receive|transmit)_(bytes|packets)_total)" -arch="$(uname -m)" - case "${arch}" in - aarch64|ppc64le) fixture='collector/fixtures/e2e-64k-page-output.txt' ;; - *) fixture='collector/fixtures/e2e-output.txt' ;; + aarch64|ppc64le) fixture_metrics='collector/fixtures/e2e-64k-page-output.txt' ;; + *) fixture_metrics='collector/fixtures/e2e-output.txt' ;; esac # Only test CPU info collection on x86_64. @@ -109,7 +143,7 @@ do *) echo "Usage: $0 [-k] [-u] [-v]" echo " -k: keep temporary files and leave node_exporter running" - echo " -u: update fixture" + echo " -u: update fixture_metrics" echo " -v: verbose output" exit 1 ;; @@ -122,37 +156,126 @@ then exit 1 fi +collector_flags=$(cat << FLAGS + ${cpu_info_collector} + --collector.arp.device-exclude=nope + --collector.bcache.priorityStats + --collector.cpu.info.bugs-include=${cpu_info_bugs} + --collector.cpu.info.flags-include=${cpu_info_flags} + --collector.hwmon.chip-include=(applesmc|coretemp|hwmon4|nct6779) + --collector.netclass.ignore-invalid-speed + --collector.netclass.ignored-devices=(dmz|int) + --collector.netdev.device-include=lo + --collector.qdisc.device-include=(wlan0|eth0) + --collector.qdisc.fixtures=collector/fixtures/qdisc/ + --collector.stat.softirq + --collector.sysctl.include-info=kernel.seccomp.actions_avail + --collector.sysctl.include=fs.file-nr + --collector.sysctl.include=fs.file-nr:total,current,max + --collector.sysctl.include=kernel.threads-max + --collector.textfile.directory=collector/fixtures/textfile/two_metric_files/ + --collector.wifi.fixtures=collector/fixtures/wifi + --no-collector.arp.netlink +FLAGS +) + +# Handle supported --[no-]collector. flags. These are not hardcoded. +_filtered_collector_flags="" +for flag in ${collector_flags}; do + collector=$(echo "${flag}" | cut -d"." -f2) + # If the flag is associated with an enabled-by-default collector, include it. + enabled_by_default=0 + for filename in $(maybe_flag_search_scope "${collector}") ; do + file="collector/${filename}" + if grep -h -E -o -- "registerCollector\(.*, defaultEnabled" ${file} > /dev/null 2>&1; then + _filtered_collector_flags="${_filtered_collector_flags} ${flag}" + enabled_by_default=1 + break + fi + done + if [ ${enabled_by_default} -eq 1 ]; then + continue + fi + # If the flag is associated with an enabled-list collector, include it. + if echo "${supported_enabled_collectors} ${supported_disabled_collectors}" | grep -q -w "${collector}"; then + _filtered_collector_flags="${_filtered_collector_flags} ${flag}" + fi +done + +# Handle supported --[no-]collector.. flags. These are hardcoded and matched by the expression below. +filtered_collector_flags="" +# Check flags of all supported collectors further down their sub-collectors (beyond the 2nd "."). +for flag in ${_filtered_collector_flags}; do + # Iterate through all possible files where the flag may be defined. + flag_collector="$(echo "${flag}" | cut -d"." -f2)" + for filename in $(maybe_flag_search_scope "${flag_collector}") ; do + file="collector/${filename}" + # Move to next iteration if the current file is not included under the build context. + if ! ./tools/tools match "$file" > /dev/null 2>&1; then + continue + fi + # Flag has the format: --[no-]collector... + if [ -n "$(echo ${flag} | cut -d"." -f3)" ]; then + # Check if the flag is used in the file. + trimmed_flag=$(echo "${flag}" | tr -d "\"' " | cut -d"=" -f1 | cut -c 3-) + if [[ $trimmed_flag =~ ^no- ]]; then + trimmed_flag=$(echo $trimmed_flag | cut -c 4-) + fi + if grep -h -E -o -- "kingpin.Flag\(\"${trimmed_flag}" ${file} > /dev/null 2>&1; then + filtered_collector_flags="${filtered_collector_flags} ${flag}" + else + continue + fi + # Flag has the format: --[no-]collector.. + else + # Flag is supported by the host. + filtered_collector_flags="${filtered_collector_flags} ${flag}" + fi + done +done + +# Check for ignored flags. +ignored_flags="" +for flag in ${collector_flags}; do + flag=$(echo "${flag}" | tr -d " ") + if ! echo "${filtered_collector_flags}" | grep -q -F -- "${flag}" > /dev/null 2>&1; then + ignored_flags="${ignored_flags} ${flag}" + fi +done + +echo "ENABLED COLLECTORS=======" +echo "${supported_enabled_collectors:1}" | tr ' ' '\n' | sort +echo "=========================" + +echo "DISABLED COLLECTORS======" +echo "${supported_disabled_collectors:1}" | tr ' ' '\n' | sort +echo "=========================" + +echo "IGNORED FLAGS============" +echo "${ignored_flags:1}"| tr ' ' '\n' | sort | uniq +echo "=========================" + ./node_exporter \ --path.rootfs="collector/fixtures" \ --path.procfs="collector/fixtures/proc" \ --path.sysfs="collector/fixtures/sys" \ --path.udev.data="collector/fixtures/udev/data" \ - $(for c in ${enabled_collectors}; do echo --collector.${c} ; done) \ - $(for c in ${disabled_collectors}; do echo --no-collector.${c} ; done) \ - --collector.textfile.directory="collector/fixtures/textfile/two_metric_files/" \ - --collector.wifi.fixtures="collector/fixtures/wifi" \ - --collector.qdisc.fixtures="collector/fixtures/qdisc/" \ - --collector.qdisc.device-include="(wlan0|eth0)" \ - --collector.arp.device-exclude="nope" \ - --no-collector.arp.netlink \ - --collector.hwmon.chip-include="(applesmc|coretemp|hwmon4|nct6779)" \ - --collector.netclass.ignored-devices="(dmz|int)" \ - --collector.netclass.ignore-invalid-speed \ - --collector.netdev.device-include="lo" \ - --collector.bcache.priorityStats \ - "${cpu_info_collector}" \ - --collector.cpu.info.bugs-include="${cpu_info_bugs}" \ - --collector.cpu.info.flags-include="${cpu_info_flags}" \ - --collector.stat.softirq \ - --collector.sysctl.include="kernel.threads-max" \ - --collector.sysctl.include="fs.file-nr" \ - --collector.sysctl.include="fs.file-nr:total,current,max" \ - --collector.sysctl.include-info="kernel.seccomp.actions_avail" \ + $(for c in ${supported_enabled_collectors}; do echo --collector.${c} ; done) \ + $(for c in ${supported_disabled_collectors}; do echo --no-collector.${c} ; done) \ + ${filtered_collector_flags} \ --web.listen-address "127.0.0.1:${port}" \ --log.level="debug" > "${tmpdir}/node_exporter.log" 2>&1 & echo $! > "${tmpdir}/node_exporter.pid" +generated_metrics="${tmpdir}/e2e-output.txt" +for os in freebsd openbsd netbsd solaris dragonfly darwin; do + if [ "${GOHOSTOS}" = "${os}" ]; then + generated_metrics="${tmpdir}/e2e-output-${GOHOSTOS}.txt" + fixture_metrics="${fixture_metrics::-4}-${GOHOSTOS}.txt" + fi +done + finish() { if [ $? -ne 0 -o ${verbose} -ne 0 ] then @@ -165,7 +288,7 @@ EOF if [ ${update} -ne 0 ] then - cp "${tmpdir}/e2e-output.txt" "${fixture}" + cp "${generated_metrics}" "${fixture_metrics}" fi if [ ${keep} -eq 0 ] @@ -195,8 +318,63 @@ get() { sleep 1 -get "127.0.0.1:${port}/metrics" | grep -E -v "${skip_re}" > "${tmpdir}/e2e-output.txt" +get "127.0.0.1:${port}/metrics" | grep --text -E -v "${skip_re}" > "${generated_metrics}" + +# The following ignore-list is only applicable to the VMs used to run E2E tests on platforms for which containerized environments are not available. +# However, owing to this, there are some non-deterministic metrics that end up generating samples, unlike their containerized counterparts, for e.g., node_network_receive_bytes_total. +non_deterministic_metrics=$(cat << METRICS + node_boot_time_seconds + node_cpu_frequency_hertz + node_cpu_seconds_total + node_disk_io_time_seconds_total + node_disk_read_bytes_total + node_disk_read_sectors_total + node_disk_read_time_seconds_total + node_disk_reads_completed_total + node_disk_write_time_seconds_total + node_disk_writes_completed_total + node_disk_written_bytes_total + node_disk_written_sectors_total + node_exec_context_switches_total + node_exec_device_interrupts_total + node_exec_forks_total + node_exec_software_interrupts_total + node_exec_system_calls_total + node_exec_traps_total + node_interrupts_total + node_load1 + node_load15 + node_load5 + node_memory_active_bytes + node_memory_buffer_bytes + node_memory_cache_bytes + node_memory_compressed_bytes + node_memory_free_bytes + node_memory_inactive_bytes + node_memory_internal_bytes + node_memory_laundry_bytes + node_memory_purgeable_bytes + node_memory_size_bytes + node_memory_swapped_in_bytes_total + node_memory_swapped_out_bytes_total + node_memory_wired_bytes + node_netstat_tcp_receive_packets_total + node_netstat_tcp_transmit_packets_total + node_network_receive_bytes_total + node_network_receive_multicast_total + node_network_transmit_multicast_total +METRICS +) + +# Remove non-deterministic metrics from the generated metrics file (as we run their workflows in VMs). +for os in freebsd openbsd netbsd solaris dragonfly darwin; do + if [ "${GOHOSTOS}" = "${os}" ]; then + for metric in ${non_deterministic_metrics}; do + sed -i "/${metric}/d" "${generated_metrics}" + done + fi +done diff -u \ - "${fixture}" \ - "${tmpdir}/e2e-output.txt" + "${fixture_metrics}" \ + "${generated_metrics}" diff --git a/examples/systemd/node_exporter.service b/examples/systemd/node_exporter.service index 82553e91ee..1ef24442d2 100644 --- a/examples/systemd/node_exporter.service +++ b/examples/systemd/node_exporter.service @@ -4,7 +4,9 @@ Requires=node_exporter.socket [Service] User=node_exporter -EnvironmentFile=/etc/sysconfig/node_exporter +# Fallback when environment file does not exist +Environment=OPTIONS= +EnvironmentFile=-/etc/sysconfig/node_exporter ExecStart=/usr/sbin/node_exporter --web.systemd-socket $OPTIONS [Install] diff --git a/go.mod b/go.mod index d287b6eea4..3ad96de003 100644 --- a/go.mod +++ b/go.mod @@ -1,6 +1,6 @@ module github.com/prometheus/node_exporter -go 1.23 +go 1.23.0 require ( github.com/alecthomas/kingpin/v2 v2.4.0 @@ -8,60 +8,63 @@ require ( github.com/coreos/go-systemd/v22 v22.5.0 github.com/dennwc/btrfs v0.0.0-20240418142341-0167142bde7a github.com/ema/qdisc v1.0.0 - github.com/go-kit/log v0.2.1 github.com/godbus/dbus/v5 v5.1.0 github.com/hashicorp/go-envparse v0.1.0 github.com/hodgesds/perf-utils v0.7.0 github.com/illumos/go-kstat v0.0.0-20210513183136-173c9b0a9973 github.com/josharian/native v1.1.0 - github.com/jsimonetti/rtnetlink v1.4.2 + github.com/jsimonetti/rtnetlink/v2 v2.0.2 github.com/lufia/iostat v1.2.1 github.com/mattn/go-xmlrpc v0.0.3 - github.com/mdlayher/ethtool v0.1.0 + github.com/mdlayher/ethtool v0.2.0 github.com/mdlayher/netlink v1.7.2 - github.com/mdlayher/wifi v0.3.0 - github.com/montanaflynn/stats v0.7.1 - github.com/opencontainers/selinux v1.11.0 + github.com/mdlayher/wifi v0.3.1 + github.com/opencontainers/selinux v1.11.1 + github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 github.com/prometheus-community/go-runit v0.1.0 - github.com/prometheus/client_golang v1.19.0 + github.com/prometheus/client_golang v1.20.5 github.com/prometheus/client_model v0.6.1 - github.com/prometheus/common v0.53.0 - github.com/prometheus/exporter-toolkit v0.11.0 - github.com/prometheus/procfs v0.14.0 - github.com/safchain/ethtool v0.4.1 - github.com/stretchr/testify v1.9.0 - github.com/tklauser/go-sysconf v0.3.14 - golang.org/x/exp v0.0.0-20240416160154-fe59bbe5cc7f - golang.org/x/sys v0.26.0 + github.com/prometheus/common v0.62.0 + github.com/prometheus/exporter-toolkit v0.14.0 + github.com/prometheus/procfs v0.15.2-0.20240603130017-1754b780536b // == v0.15.1 + https://github.com/prometheus/procfs/commit/1754b780536bb81082baa913e04cc4fff4d2baea + github.com/safchain/ethtool v0.5.10 + golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 + golang.org/x/sys v0.31.0 howett.net/plist v1.0.1 ) require ( github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 // indirect github.com/beorn7/perks v1.0.1 // indirect - github.com/cespare/xxhash/v2 v2.2.0 // indirect + github.com/cespare/xxhash/v2 v2.3.0 // indirect github.com/davecgh/go-spew v1.1.1 // indirect github.com/dennwc/ioctl v1.0.0 // indirect - github.com/go-logfmt/logfmt v0.5.1 // indirect - github.com/golang/protobuf v1.5.3 // indirect github.com/google/go-cmp v0.6.0 // indirect github.com/jpillora/backoff v1.0.0 // indirect + github.com/klauspost/compress v1.17.9 // indirect + github.com/kylelemons/godebug v1.1.0 // indirect github.com/mdlayher/genetlink v1.3.2 // indirect github.com/mdlayher/socket v0.4.1 // indirect + github.com/mdlayher/vsock v1.2.1 // indirect + github.com/montanaflynn/stats v0.7.1 + github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect github.com/pmezard/go-difflib v1.0.0 // indirect github.com/siebenmann/go-kstat v0.0.0-20210513183136-173c9b0a9973 // indirect - github.com/tklauser/numcpus v0.8.0 // indirect + github.com/stretchr/testify v1.10.0 + github.com/tklauser/go-sysconf v0.3.15 + github.com/tklauser/numcpus v0.10.0 // indirect github.com/xhit/go-str2duration/v2 v2.1.0 // indirect go.uber.org/atomic v1.7.0 // indirect go.uber.org/multierr v1.6.0 // indirect - golang.org/x/crypto v0.27.0 // indirect - golang.org/x/net v0.25.0 // indirect - golang.org/x/oauth2 v0.18.0 // indirect - golang.org/x/sync v0.8.0 // indirect - golang.org/x/text v0.18.0 // indirect - google.golang.org/appengine v1.6.7 // indirect - google.golang.org/protobuf v1.33.0 // indirect + golang.org/x/crypto v0.36.0 // indirect + golang.org/x/net v0.37.0 // indirect + golang.org/x/oauth2 v0.28.0 // indirect + golang.org/x/sync v0.12.0 // indirect + golang.org/x/text v0.23.0 // indirect + google.golang.org/protobuf v1.36.1 // indirect gopkg.in/yaml.v2 v2.4.0 // indirect gopkg.in/yaml.v3 v3.0.1 // indirect ) + +//replace github.com/prometheus/procfs => github.com/rexagod/procfs v0.0.0-20241124020414-857c5b813f1b diff --git a/go.sum b/go.sum index eef1ec5435..5893724c4e 100644 --- a/go.sum +++ b/go.sum @@ -6,8 +6,8 @@ github.com/beevik/ntp v1.4.3 h1:PlbTvE5NNy4QHmA4Mg57n7mcFTmr1W1j3gcK7L1lqho= github.com/beevik/ntp v1.4.3/go.mod h1:Unr8Zg+2dRn7d8bHFuehIMSvvUYssHMxW3Q5Nx4RW5Q= github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM= github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw= -github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44= -github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs= +github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs= +github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs= github.com/cilium/ebpf v0.12.3 h1:8ht6F9MquybnY97at+VDZb3eQQr8ev79RueWeVaEcG4= github.com/cilium/ebpf v0.12.3/go.mod h1:TctK1ivibvI3znr66ljgi4hqOT8EYQjz1KWBfb1UVgM= github.com/coreos/go-systemd/v22 v22.5.0 h1:RrqgGjYQKalulkV8NGVIfkXQf6YYmOyiJKk8iXXhfZs= @@ -21,18 +21,9 @@ github.com/dennwc/ioctl v1.0.0 h1:DsWAAjIxRqNcLn9x6mwfuf2pet3iB7aK90K4tF16rLg= github.com/dennwc/ioctl v1.0.0/go.mod h1:ellh2YB5ldny99SBU/VX7Nq0xiZbHphf1DrtHxxjMk0= github.com/ema/qdisc v1.0.0 h1:EHLG08FVRbWLg8uRICa3xzC9Zm0m7HyMHfXobWFnXYg= github.com/ema/qdisc v1.0.0/go.mod h1:FhIc0fLYi7f+lK5maMsesDqwYojIOh3VfRs8EVd5YJQ= -github.com/go-kit/log v0.2.1 h1:MRVx0/zhvdseW+Gza6N9rVzU/IVzaeE1SFI4raAhmBU= -github.com/go-kit/log v0.2.1/go.mod h1:NwTd00d/i8cPZ3xOwwiv2PO5MOcx78fFErGNcVmBjv0= -github.com/go-logfmt/logfmt v0.5.1 h1:otpy5pqBCBZ1ng9RQ0dPu4PN7ba75Y/aA+UpowDyNVA= -github.com/go-logfmt/logfmt v0.5.1/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs= github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA= github.com/godbus/dbus/v5 v5.1.0 h1:4KLkAxT3aOY8Li4FRJe/KvhoNFFxo0m6fNuFUO8QJUk= github.com/godbus/dbus/v5 v5.1.0/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA= -github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= -github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk= -github.com/golang/protobuf v1.5.3 h1:KhyjKVUg7Usr/dYsdSqoFveMYd5ko72D+zANwlG1mmg= -github.com/golang/protobuf v1.5.3/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY= -github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI= github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= github.com/hashicorp/go-envparse v0.1.0 h1:bE++6bhIsNCPLvgDZkYqo3nA+/PFI51pkrHdmPSDFPY= @@ -46,96 +37,96 @@ github.com/josharian/native v1.1.0 h1:uuaP0hAbW7Y4l0ZRQ6C9zfb7Mg1mbFKry/xzDAfmtL github.com/josharian/native v1.1.0/go.mod h1:7X/raswPFr05uY3HiLlYeyQntB6OO7E/d2Cu7qoaN2w= github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2EA= github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4= -github.com/jsimonetti/rtnetlink v1.4.2 h1:Df9w9TZ3npHTyDn0Ev9e1uzmN2odmXd0QX+J5GTEn90= -github.com/jsimonetti/rtnetlink v1.4.2/go.mod h1:92s6LJdE+1iOrw+F2/RO7LYI2Qd8pPpFNNUYW06gcoM= +github.com/jsimonetti/rtnetlink/v2 v2.0.2 h1:ZKlbCujrIpp4/u3V2Ka0oxlf4BCkt6ojkvpy3nZoCBY= +github.com/jsimonetti/rtnetlink/v2 v2.0.2/go.mod h1:7MoNYNbb3UaDHtF8udiJo/RH6VsTKP1pqKLUTVCvToE= +github.com/klauspost/compress v1.17.9 h1:6KIumPrER1LHsvBVuDa0r5xaG0Es51mhhB9BQB2qeMA= +github.com/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw= github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE= github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk= github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY= github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE= +github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc= +github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw= github.com/lufia/iostat v1.2.1 h1:tnCdZBIglgxD47RyD55kfWQcJMGzO+1QBziSQfesf2k= github.com/lufia/iostat v1.2.1/go.mod h1:rEPNA0xXgjHQjuI5Cy05sLlS2oRcSlWHRLrvh/AQ+Pg= github.com/mattn/go-xmlrpc v0.0.3 h1:Y6WEMLEsqs3RviBrAa1/7qmbGB7DVD3brZIbqMbQdGY= github.com/mattn/go-xmlrpc v0.0.3/go.mod h1:mqc2dz7tP5x5BKlCahN/n+hs7OSZKJkS9JsHNBRlrxA= -github.com/mdlayher/ethtool v0.1.0 h1:XAWHsmKhyPOo42qq/yTPb0eFBGUKKTR1rE0dVrWVQ0Y= -github.com/mdlayher/ethtool v0.1.0/go.mod h1:fBMLn2UhfRGtcH5ZFjr+6GUiHEjZsItFD7fSn7jbZVQ= +github.com/mdlayher/ethtool v0.2.0 h1:akcA4WZVWozzirPASeMq8qgLkxpF3ykftVXwnrMKrhY= +github.com/mdlayher/ethtool v0.2.0/go.mod h1:W0pIBrNPK1TslIN4Z9wt1EVbay66Kbvek2z2f29VBfw= github.com/mdlayher/genetlink v1.3.2 h1:KdrNKe+CTu+IbZnm/GVUMXSqBBLqcGpRDa0xkQy56gw= github.com/mdlayher/genetlink v1.3.2/go.mod h1:tcC3pkCrPUGIKKsCsp0B3AdaaKuHtaxoJRz3cc+528o= github.com/mdlayher/netlink v1.7.2 h1:/UtM3ofJap7Vl4QWCPDGXY8d3GIY2UGSDbK+QWmY8/g= github.com/mdlayher/netlink v1.7.2/go.mod h1:xraEF7uJbxLhc5fpHL4cPe221LI2bdttWlU+ZGLfQSw= github.com/mdlayher/socket v0.4.1 h1:eM9y2/jlbs1M615oshPQOHZzj6R6wMT7bX5NPiQvn2U= github.com/mdlayher/socket v0.4.1/go.mod h1:cAqeGjoufqdxWkD7DkpyS+wcefOtmu5OQ8KuoJGIReA= -github.com/mdlayher/wifi v0.3.0 h1:ZfS81w/7xTWBJfhM77K0k6m3sJckwoNOoZUwOW34omo= -github.com/mdlayher/wifi v0.3.0/go.mod h1:/bdkqKYl+lD4recmQM6bTHxMrEUW70reibTyr93CAd0= +github.com/mdlayher/vsock v1.2.1 h1:pC1mTJTvjo1r9n9fbm7S1j04rCgCzhCOS5DY0zqHlnQ= +github.com/mdlayher/vsock v1.2.1/go.mod h1:NRfCibel++DgeMD8z/hP+PPTjlNJsdPOmxcnENvE+SE= +github.com/mdlayher/wifi v0.3.1 h1:bZDuMI1f7z5BtUUO3NgHRdR/R88YtywIe6dsEFI0Txs= +github.com/mdlayher/wifi v0.3.1/go.mod h1:ODQaObvsglghTuNhezD9grkTB4shVNc28aJfTXmvSi8= github.com/montanaflynn/stats v0.7.1 h1:etflOAAHORrCC44V+aR6Ftzort912ZU+YLiSTuV8eaE= github.com/montanaflynn/stats v0.7.1/go.mod h1:etXPPgVO6n31NxCd9KQUMvCM+ve0ruNzt6R8Bnaayow= +github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA= +github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ= github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU= github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U= -github.com/opencontainers/selinux v1.11.0 h1:+5Zbo97w3Lbmb3PeqQtpmTkMwsW5nRI3YaLpt7tQ7oU= -github.com/opencontainers/selinux v1.11.0/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec= +github.com/opencontainers/selinux v1.11.1 h1:nHFvthhM0qY8/m+vfhJylliSshm8G1jJ2jDMcgULaH8= +github.com/opencontainers/selinux v1.11.1/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= +github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 h1:o4JXh1EVt9k/+g42oCprj/FisM4qX9L3sZB3upGN2ZU= +github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE= github.com/prometheus-community/go-runit v0.1.0 h1:uTWEj/Fn2RoLdfg/etSqwzgYNOYPrARx1BHUN052tGA= github.com/prometheus-community/go-runit v0.1.0/go.mod h1:AvJ9Jo3gAFu2lbM4+qfjdpq30FfiLDJZKbQ015u08IQ= -github.com/prometheus/client_golang v1.19.0 h1:ygXvpU1AoN1MhdzckN+PyD9QJOSD4x7kmXYlnfbA6JU= -github.com/prometheus/client_golang v1.19.0/go.mod h1:ZRM9uEAypZakd+q/x7+gmsvXdURP+DABIEIjnmDdp+k= +github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+bR9r+8l63Y= +github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE= github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E= github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY= -github.com/prometheus/common v0.53.0 h1:U2pL9w9nmJwJDa4qqLQ3ZaePJ6ZTwt7cMD3AG3+aLCE= -github.com/prometheus/common v0.53.0/go.mod h1:BrxBKv3FWBIGXw89Mg1AeBq7FSyRzXWI3l3e7W3RN5U= -github.com/prometheus/exporter-toolkit v0.11.0 h1:yNTsuZ0aNCNFQ3aFTD2uhPOvr4iD7fdBvKPAEGkNf+g= -github.com/prometheus/exporter-toolkit v0.11.0/go.mod h1:BVnENhnNecpwoTLiABx7mrPB/OLRIgN74qlQbV+FK1Q= -github.com/prometheus/procfs v0.14.0 h1:Lw4VdGGoKEZilJsayHf0B+9YgLGREba2C6xr+Fdfq6s= -github.com/prometheus/procfs v0.14.0/go.mod h1:XL+Iwz8k8ZabyZfMFHPiilCniixqQarAy5Mu67pHlNQ= +github.com/prometheus/common v0.62.0 h1:xasJaQlnWAeyHdUBeGjXmutelfJHWMRr+Fg4QszZ2Io= +github.com/prometheus/common v0.62.0/go.mod h1:vyBcEuLSvWos9B1+CyL7JZ2up+uFzXhkqml0W5zIY1I= +github.com/prometheus/exporter-toolkit v0.14.0 h1:NMlswfibpcZZ+H0sZBiTjrA3/aBFHkNZqE+iCj5EmRg= +github.com/prometheus/exporter-toolkit v0.14.0/go.mod h1:Gu5LnVvt7Nr/oqTBUC23WILZepW0nffNo10XdhQcwWA= +github.com/prometheus/procfs v0.15.2-0.20240603130017-1754b780536b h1:4EJkx3vycI+n5JY5ht+bnSUGamkmmXkpcNeO/OBT/0A= +github.com/prometheus/procfs v0.15.2-0.20240603130017-1754b780536b/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk= github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ= github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog= -github.com/safchain/ethtool v0.4.1 h1:S6mEleTADqgynileXoiapt/nKnatyR6bmIHoF+h2ADo= -github.com/safchain/ethtool v0.4.1/go.mod h1:XLLnZmy4OCRTkksP/UiMjij96YmIsBfmBQcs7H6tA48= +github.com/safchain/ethtool v0.5.10 h1:Im294gZtuf4pSGJRAOGKaASNi3wMeFaGaWuSaomedpc= +github.com/safchain/ethtool v0.5.10/go.mod h1:w9jh2Lx7YBR4UwzLkzCmWl85UY0W2uZdd7/DckVE5+c= github.com/siebenmann/go-kstat v0.0.0-20210513183136-173c9b0a9973 h1:GfSdC6wKfTGcgCS7BtzF5694Amne1pGCSTY252WhlEY= github.com/siebenmann/go-kstat v0.0.0-20210513183136-173c9b0a9973/go.mod h1:G81aIFAMS9ECrwBYR9YxhlPjWgrItd+Kje78O6+uqm8= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= -github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg= -github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY= -github.com/tklauser/go-sysconf v0.3.14 h1:g5vzr9iPFFz24v2KZXs/pvpvh8/V9Fw6vQK5ZZb78yU= -github.com/tklauser/go-sysconf v0.3.14/go.mod h1:1ym4lWMLUOhuBOPGtRcJm7tEGX4SCYNEEEtghGG/8uY= -github.com/tklauser/numcpus v0.8.0 h1:Mx4Wwe/FjZLeQsK/6kt2EOepwwSl7SmJrK5bV/dXYgY= -github.com/tklauser/numcpus v0.8.0/go.mod h1:ZJZlAY+dmR4eut8epnzf0u/VwodKmryxR8txiloSqBE= +github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA= +github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY= +github.com/tklauser/go-sysconf v0.3.15 h1:VE89k0criAymJ/Os65CSn1IXaol+1wrsFHEB8Ol49K4= +github.com/tklauser/go-sysconf v0.3.15/go.mod h1:Dmjwr6tYFIseJw7a3dRLJfsHAMXZ3nEnL/aZY+0IuI4= +github.com/tklauser/numcpus v0.10.0 h1:18njr6LDBk1zuna922MgdjQuJFjrdppsZG60sHGfjso= +github.com/tklauser/numcpus v0.10.0/go.mod h1:BiTKazU708GQTYF4mB+cmlpT2Is1gLk7XVuEeem8LsQ= github.com/xhit/go-str2duration/v2 v2.1.0 h1:lxklc02Drh6ynqX+DdPyp5pCKLUQpRT8bp8Ydu2Bstc= github.com/xhit/go-str2duration/v2 v2.1.0/go.mod h1:ohY8p+0f07DiV6Em5LKB0s2YpLtXVyJfNt1+BlmyAsU= go.uber.org/atomic v1.7.0 h1:ADUqmZGgLDDfbSL9ZmPxKTybcoEYHgpYfELNoN+7hsw= go.uber.org/atomic v1.7.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc= go.uber.org/multierr v1.6.0 h1:y6IPFStTAIT5Ytl7/XYmHvzXQ7S3g/IeZW9hyZ5thw4= go.uber.org/multierr v1.6.0/go.mod h1:cdWPpRnG4AhwMwsgIHip0KRBQjJy5kYEpYjJxpXp9iU= -golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= -golang.org/x/crypto v0.27.0 h1:GXm2NjJrPaiv/h1tb2UH8QfgC/hOf/+z0p6PT8o1w7A= -golang.org/x/crypto v0.27.0/go.mod h1:1Xngt8kV6Dvbssa53Ziq6Eqn0HqbZi5Z6R0ZpwQzt70= -golang.org/x/exp v0.0.0-20240416160154-fe59bbe5cc7f h1:99ci1mjWVBWwJiEKYY6jWa4d2nTQVIEhZIptnrVb1XY= -golang.org/x/exp v0.0.0-20240416160154-fe59bbe5cc7f/go.mod h1:/lliqkxwWAhPjf5oSOIJup2XcqJaw8RGS6k3TGEc7GI= -golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks= -golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac= -golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM= -golang.org/x/oauth2 v0.18.0 h1:09qnuIAgzdx1XplqJvW6CQqMCtGZykZWcXzPMPUusvI= -golang.org/x/oauth2 v0.18.0/go.mod h1:Wf7knwG0MPoWIMMBgFlEaSUDaKskp0dCfrlJRJXbBi8= -golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ= -golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= -golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= +golang.org/x/crypto v0.36.0 h1:AnAEvhDddvBdpY+uR+MyHmuZzzNqXSe/GvuDeob5L34= +golang.org/x/crypto v0.36.0/go.mod h1:Y4J0ReaxCR1IMaabaSMugxJES1EpwhBHhv2bDHklZvc= +golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 h1:e66Fs6Z+fZTbFBAxKfP3PALWBtpfqks2bwGcexMxgtk= +golang.org/x/exp v0.0.0-20240909161429-701f63a606c0/go.mod h1:2TbTHSBQa924w8M6Xs1QcRcFwyucIwBGpK1p2f1YFFY= +golang.org/x/net v0.37.0 h1:1zLorHbz+LYj7MQlSf1+2tPIIgibq2eL5xkrGk6f+2c= +golang.org/x/net v0.37.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8= +golang.org/x/oauth2 v0.28.0 h1:CrgCKl8PPAVtLnU3c+EDw6x11699EWlsDeWNWKdIOkc= +golang.org/x/oauth2 v0.28.0/go.mod h1:onh5ek6nERTohokkhCD/y2cV4Do3fxFHFuAejCkRWT8= +golang.org/x/sync v0.12.0 h1:MHc5BpPuC30uJk597Ri8TV3CNZcTLu6B6z4lJy+g6Jw= +golang.org/x/sync v0.12.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA= +golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20211031064116-611d5d643895/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= -golang.org/x/sys v0.26.0 h1:KHjCJyddX0LoSTb3J+vWpupP9p0oznkqVk/IfjymZbo= -golang.org/x/sys v0.26.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= -golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= -golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk= -golang.org/x/text v0.18.0 h1:XvMDiNzPAl0jr17s6W9lcaIhGUfUORdGCNsuLmPG224= -golang.org/x/text v0.18.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY= -golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= -golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= -google.golang.org/appengine v1.6.7 h1:FZR1q0exgwxzPzp/aF+VccGrSfxfPpkBqjIIEq3ru6c= -google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc= -google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw= -google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc= -google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI= -google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos= +golang.org/x/sys v0.29.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= +golang.org/x/sys v0.31.0 h1:ioabZlmFYtWhL+TRYpcnNlLwhyxaM9kWTDEmfnprqik= +golang.org/x/sys v0.31.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k= +golang.org/x/text v0.23.0 h1:D71I7dUrlY+VX0gQShAThNGHFxZ13dGLBHQLVl1mJlY= +golang.org/x/text v0.23.0/go.mod h1:/BLNzu4aZCJ1+kcD0DNRotWKage4q2rGVAg4o22unh4= +google.golang.org/protobuf v1.36.1 h1:yBPeRvTftaleIgM3PZ/WBIZ7XM/eEYAaEyCwvyjq/gk= +google.golang.org/protobuf v1.36.1/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= diff --git a/node_exporter.go b/node_exporter.go index a48c3df2bf..69925cd3d1 100644 --- a/node_exporter.go +++ b/node_exporter.go @@ -15,20 +15,19 @@ package main import ( "fmt" - stdlog "log" + "log/slog" "net/http" _ "net/http/pprof" "os" "os/user" "runtime" + "slices" "sort" - "github.com/prometheus/common/promlog" - "github.com/prometheus/common/promlog/flag" + "github.com/prometheus/common/promslog" + "github.com/prometheus/common/promslog/flag" - kingpin "github.com/alecthomas/kingpin/v2" - log "github.com/go-kit/log" - "github.com/go-kit/log/level" + "github.com/alecthomas/kingpin/v2" "github.com/prometheus/client_golang/prometheus" promcollectors "github.com/prometheus/client_golang/prometheus/collectors" versioncollector "github.com/prometheus/client_golang/prometheus/collectors/version" @@ -45,15 +44,17 @@ import ( // newHandler. type handler struct { unfilteredHandler http.Handler + // enabledCollectors list is used for logging and filtering + enabledCollectors []string // exporterMetricsRegistry is a separate registry for the metrics about // the exporter itself. exporterMetricsRegistry *prometheus.Registry includeExporterMetrics bool maxRequests int - logger log.Logger + logger *slog.Logger } -func newHandler(includeExporterMetrics bool, maxRequests int, logger log.Logger) *handler { +func newHandler(includeExporterMetrics bool, maxRequests int, logger *slog.Logger) *handler { h := &handler{ exporterMetricsRegistry: prometheus.NewRegistry(), includeExporterMetrics: includeExporterMetrics, @@ -76,18 +77,41 @@ func newHandler(includeExporterMetrics bool, maxRequests int, logger log.Logger) // ServeHTTP implements http.Handler. func (h *handler) ServeHTTP(w http.ResponseWriter, r *http.Request) { - filters := r.URL.Query()["collect[]"] - level.Debug(h.logger).Log("msg", "collect query:", "filters", filters) + collects := r.URL.Query()["collect[]"] + h.logger.Debug("collect query:", "collects", collects) - if len(filters) == 0 { + excludes := r.URL.Query()["exclude[]"] + h.logger.Debug("exclude query:", "excludes", excludes) + + if len(collects) == 0 && len(excludes) == 0 { // No filters, use the prepared unfiltered handler. h.unfilteredHandler.ServeHTTP(w, r) return } + + if len(collects) > 0 && len(excludes) > 0 { + h.logger.Debug("rejecting combined collect and exclude queries") + w.WriteHeader(http.StatusBadRequest) + w.Write([]byte("Combined collect and exclude queries are not allowed.")) + return + } + + filters := &collects + if len(excludes) > 0 { + // In exclude mode, filtered collectors = enabled - excludeed. + f := []string{} + for _, c := range h.enabledCollectors { + if (slices.Index(excludes, c)) == -1 { + f = append(f, c) + } + } + filters = &f + } + // To serve filtered metrics, we create a filtering handler on the fly. - filteredHandler, err := h.innerHandler(filters...) + filteredHandler, err := h.innerHandler(*filters...) if err != nil { - level.Warn(h.logger).Log("msg", "Couldn't create filtered metrics handler:", "err", err) + h.logger.Warn("Couldn't create filtered metrics handler:", "err", err) w.WriteHeader(http.StatusBadRequest) w.Write([]byte(fmt.Sprintf("Couldn't create filtered metrics handler: %s", err))) return @@ -109,14 +133,13 @@ func (h *handler) innerHandler(filters ...string) (http.Handler, error) { // Only log the creation of an unfiltered handler, which should happen // only once upon startup. if len(filters) == 0 { - level.Info(h.logger).Log("msg", "Enabled collectors") - collectors := []string{} + h.logger.Info("Enabled collectors") for n := range nc.Collectors { - collectors = append(collectors, n) + h.enabledCollectors = append(h.enabledCollectors, n) } - sort.Strings(collectors) - for _, c := range collectors { - level.Info(h.logger).Log("collector", c) + sort.Strings(h.enabledCollectors) + for _, c := range h.enabledCollectors { + h.logger.Info(c) } } @@ -131,7 +154,7 @@ func (h *handler) innerHandler(filters ...string) (http.Handler, error) { handler = promhttp.HandlerFor( prometheus.Gatherers{h.exporterMetricsRegistry, r}, promhttp.HandlerOpts{ - ErrorLog: stdlog.New(log.NewStdlibAdapter(level.Error(h.logger)), "", 0), + ErrorLog: slog.NewLogLogger(h.logger.Handler(), slog.LevelError), ErrorHandling: promhttp.ContinueOnError, MaxRequestsInFlight: h.maxRequests, Registry: h.exporterMetricsRegistry, @@ -146,7 +169,7 @@ func (h *handler) innerHandler(filters ...string) (http.Handler, error) { handler = promhttp.HandlerFor( r, promhttp.HandlerOpts{ - ErrorLog: stdlog.New(log.NewStdlibAdapter(level.Error(h.logger)), "", 0), + ErrorLog: slog.NewLogLogger(h.logger.Handler(), slog.LevelError), ErrorHandling: promhttp.ContinueOnError, MaxRequestsInFlight: h.maxRequests, }, @@ -180,24 +203,24 @@ func main() { toolkitFlags = kingpinflag.AddFlags(kingpin.CommandLine, ":9100") ) - promlogConfig := &promlog.Config{} - flag.AddFlags(kingpin.CommandLine, promlogConfig) + promslogConfig := &promslog.Config{} + flag.AddFlags(kingpin.CommandLine, promslogConfig) kingpin.Version(version.Print("node_exporter")) kingpin.CommandLine.UsageWriter(os.Stdout) kingpin.HelpFlag.Short('h') kingpin.Parse() - logger := promlog.New(promlogConfig) + logger := promslog.New(promslogConfig) if *disableDefaultCollectors { collector.DisableDefaultCollectors() } - level.Info(logger).Log("msg", "Starting node_exporter", "version", version.Info()) - level.Info(logger).Log("msg", "Build context", "build_context", version.BuildContext()) + logger.Info("Starting node_exporter", "version", version.Info()) + logger.Info("Build context", "build_context", version.BuildContext()) if user, err := user.Current(); err == nil && user.Uid == "0" { - level.Warn(logger).Log("msg", "Node Exporter is running as root user. This exporter is designed to run as unprivileged user, root is not required.") + logger.Warn("Node Exporter is running as root user. This exporter is designed to run as unprivileged user, root is not required.") } runtime.GOMAXPROCS(*maxProcs) - level.Debug(logger).Log("msg", "Go MAXPROCS", "procs", runtime.GOMAXPROCS(0)) + logger.Debug("Go MAXPROCS", "procs", runtime.GOMAXPROCS(0)) http.Handle(*metricsPath, newHandler(!*disableExporterMetrics, *maxRequests, logger)) if *metricsPath != "/" { @@ -214,7 +237,7 @@ func main() { } landingPage, err := web.NewLandingPage(landingConfig) if err != nil { - level.Error(logger).Log("err", err) + logger.Error(err.Error()) os.Exit(1) } http.Handle("/", landingPage) @@ -222,7 +245,7 @@ func main() { server := &http.Server{} if err := web.ListenAndServe(server, toolkitFlags, logger); err != nil { - level.Error(logger).Log("err", err) + logger.Error(err.Error()) os.Exit(1) } } diff --git a/percona/perconacollector/standard.go b/percona/perconacollector/standard.go index d41df99361..3f9fed17da 100644 --- a/percona/perconacollector/standard.go +++ b/percona/perconacollector/standard.go @@ -15,8 +15,8 @@ package perconacollector import ( "fmt" + "log/slog" - "github.com/go-kit/log" "github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus/collectors" cl "github.com/prometheus/node_exporter/collector" @@ -30,11 +30,10 @@ func init() { type standardGoCollector struct { origin prometheus.Collector - logger log.Logger } // NewStandardGoCollector creates standard go collector. -func NewStandardGoCollector(logger log.Logger) (cl.Collector, error) { +func NewStandardGoCollector(_ *slog.Logger) (cl.Collector, error) { c := collectors.NewGoCollector() return &standardGoCollector{origin: c}, nil } @@ -49,7 +48,7 @@ type standardProcessCollector struct { } // NewStandardProcessCollector creates standard process collector. -func NewStandardProcessCollector(logger log.Logger) (cl.Collector, error) { +func NewStandardProcessCollector(_ *slog.Logger) (cl.Collector, error) { c := collectors.NewProcessCollector(collectors.ProcessCollectorOpts{}) return &standardProcessCollector{origin: c}, nil } diff --git a/percona/perconacollector/textfile.directory.go b/percona/perconacollector/textfile.directory.go index 4dfddb4a2c..f38a580e53 100644 --- a/percona/perconacollector/textfile.directory.go +++ b/percona/perconacollector/textfile.directory.go @@ -18,6 +18,7 @@ package perconacollector import ( "fmt" + "log/slog" "os" "path/filepath" "sort" @@ -25,8 +26,6 @@ import ( "time" kingpin "github.com/alecthomas/kingpin/v2" - log "github.com/go-kit/log" - "github.com/go-kit/log/level" "github.com/prometheus/client_golang/prometheus" dto "github.com/prometheus/client_model/go" "github.com/prometheus/common/expfmt" @@ -34,7 +33,7 @@ import ( ) var ( - //textFileDirectory = kingpin.Flag("collector.textfile.directory", "Directory to read text files with metrics from.").Default("").String() + // textFileDirectory = kingpin.Flag("collector.textfile.directory", "Directory to read text files with metrics from.").Default("").String() textFileDirectory = kingpin.CommandLine.GetFlag("collector.textfile.directory").Default("").String() textFileDirectoryLr = kingpin.Flag("collector.textfile.directory.lr", "Directory to read text files with low resolution metrics from.").String() textFileDirectoryMr = kingpin.Flag("collector.textfile.directory.mr", "Directory to read text files with medium resolution metrics from.").String() @@ -51,12 +50,12 @@ type textFileCollector struct { path string // Only set for testing to get predictable output. mtime *float64 - logger log.Logger + logger *slog.Logger } func init() { cl.ReplaceCollector("textfile", true, NewTextFileCollector) - //cl.RegisterCollectorPublic("textfile", true, NewTextFileCollector) // Alias for "textfile.mr" for backward compatibility. + // cl.RegisterCollectorPublic("textfile", true, NewTextFileCollector) // Alias for "textfile.mr" for backward compatibility. cl.RegisterCollectorPublic("textfile.lr", false, NewTextFileCollectorLr) cl.RegisterCollectorPublic("textfile.mr", false, NewTextFileCollectorMr) cl.RegisterCollectorPublic("textfile.hr", false, NewTextFileCollectorHr) @@ -64,7 +63,7 @@ func init() { // NewTextFileCollectorLr returns a new Collector exposing metrics read from files // in the given textfile lr directory. -func NewTextFileCollectorLr(logger log.Logger) (cl.Collector, error) { +func NewTextFileCollectorLr(logger *slog.Logger) (cl.Collector, error) { c := &textFileCollector{ path: *textFileDirectoryLr, logger: logger, @@ -74,7 +73,7 @@ func NewTextFileCollectorLr(logger log.Logger) (cl.Collector, error) { // NewTextFileCollectorMr returns a new Collector exposing metrics read from files // in the given textfile mr directory. -func NewTextFileCollectorMr(logger log.Logger) (cl.Collector, error) { +func NewTextFileCollectorMr(logger *slog.Logger) (cl.Collector, error) { c := &textFileCollector{ path: *textFileDirectoryMr, logger: logger, @@ -84,7 +83,7 @@ func NewTextFileCollectorMr(logger log.Logger) (cl.Collector, error) { // NewTextFileCollectorHr returns a new Collector exposing metrics read from files // in the given textfile hr directory. -func NewTextFileCollectorHr(logger log.Logger) (cl.Collector, error) { +func NewTextFileCollectorHr(logger *slog.Logger) (cl.Collector, error) { c := &textFileCollector{ path: *textFileDirectoryHr, logger: logger, @@ -94,7 +93,7 @@ func NewTextFileCollectorHr(logger log.Logger) (cl.Collector, error) { // NewTextFileCollector returns a new Collector exposing metrics read from files // in the given textfile directory. -func NewTextFileCollector(logger log.Logger) (cl.Collector, error) { +func NewTextFileCollector(logger *slog.Logger) (cl.Collector, error) { c := &textFileCollector{ path: *textFileDirectory, logger: logger, @@ -102,7 +101,7 @@ func NewTextFileCollector(logger log.Logger) (cl.Collector, error) { return c, nil } -func convertMetricFamily(metricFamily *dto.MetricFamily, ch chan<- prometheus.Metric, logger log.Logger) { +func convertMetricFamily(metricFamily *dto.MetricFamily, ch chan<- prometheus.Metric, logger *slog.Logger) { var valType prometheus.ValueType var val float64 @@ -118,7 +117,7 @@ func convertMetricFamily(metricFamily *dto.MetricFamily, ch chan<- prometheus.Me for _, metric := range metricFamily.Metric { if metric.TimestampMs != nil { - level.Warn(logger).Log("msg", "Ignoring unsupported custom timestamp on textfile collector metric", "metric", metric) + logger.Warn("Ignoring unsupported custom timestamp on textfile collector metric", "metric", metric) } labels := metric.GetLabel() @@ -243,7 +242,7 @@ func (c *textFileCollector) Update(ch chan<- prometheus.Metric) error { files, err := os.ReadDir(path) if err != nil && path != "" { errored = true - level.Error(c.logger).Log("msg", "failed to read textfile collector directory", "path", path, "err", err) + c.logger.Error("failed to read textfile collector directory", "path", path, "err", err) } for _, f := range files { @@ -254,7 +253,7 @@ func (c *textFileCollector) Update(ch chan<- prometheus.Metric) error { mtime, err := c.processFile(path, f.Name(), ch) if err != nil { errored = true - level.Error(c.logger).Log("msg", "failed to collect textfile data", "file", f.Name(), "err", err) + c.logger.Error("failed to collect textfile data", "file", f.Name(), "err", err) continue } diff --git a/tools/main.go b/tools/main.go new file mode 100644 index 0000000000..cfd4c1135e --- /dev/null +++ b/tools/main.go @@ -0,0 +1,79 @@ +// Copyright 2024 The Prometheus Authors +// Licensed under the Apache License, Version 2.0 (the "License"); +// you may not use this file except in compliance with the License. +// You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, software +// distributed under the License is distributed on an "AS IS" BASIS, +// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +// See the License for the specific language governing permissions and +// limitations under the License. + +package main + +import ( + "flag" + "fmt" + "go/build" + "os" + "path/filepath" + "runtime" +) + +func main() { + printHelpAndDie := func() { + fmt.Println(` +Usage: tools [command]`) + os.Exit(1) + } + if len(os.Args) < 2 { + printHelpAndDie() + } + + // Sub-commands. + matchCmd := flag.NewFlagSet("match", flag.ExitOnError) + switch os.Args[1] { + case "match": + err := matchCmd.Parse(os.Args[2:]) + if err != nil { + fmt.Println("Error parsing flags:", err) + os.Exit(1) + } + if matchCmd.NArg() != 1 { + fmt.Println("Usage: match [file]") + os.Exit(1) + } + file := matchCmd.Arg(0) + + // For debugging purposes, allow overriding these. + goos, found := os.LookupEnv("GOHOSTOS") + if !found { + goos = runtime.GOOS + } + goarch, found := os.LookupEnv("GOARCH") + if !found { + goarch = runtime.GOARCH + } + ctx := build.Context{ + GOOS: goos, + GOARCH: goarch, + } + abs, err := filepath.Abs(file) + if err != nil { + panic(err) + } + match, err := ctx.MatchFile(filepath.Dir(abs), filepath.Base(abs)) + if err != nil { + fmt.Println("Error:", err) + os.Exit(1) + } + if match { + os.Exit(0) + } + os.Exit(1) + default: + printHelpAndDie() + } +}