Compare commits

..

No commits in common. "main" and "v0.6.7" have entirely different histories.
main ... v0.6.7

117 changed files with 6845 additions and 2087 deletions

View File

@ -1,10 +1,8 @@
{ {
"sinks-file": ".github/ci-sinks.json", "sinks": ".github/ci-sinks.json",
"collectors-file" : ".github/ci-collectors.json", "collectors" : ".github/ci-collectors.json",
"receivers-file" : ".github/ci-receivers.json", "receivers" : ".github/ci-receivers.json",
"router-file" : ".github/ci-router.json", "router" : ".github/ci-router.json",
"main" : { "interval": "5s",
"interval": "5s", "duration": "1s"
"duration": "1s"
}
} }

View File

@ -15,7 +15,7 @@ jobs:
# #
# Build on AlmaLinux 8 using go-toolset # Build on AlmaLinux 8 using go-toolset
# #
AlmaLinux8-RPM-build: AlmaLinux-RPM-build:
runs-on: ubuntu-latest runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux # See: https://hub.docker.com/_/almalinux
container: almalinux:8 container: almalinux:8
@ -41,17 +41,14 @@ jobs:
submodules: recursive submodules: recursive
fetch-depth: 0 fetch-depth: 0
# - name: Setup Golang # Use dnf to install build dependencies
# uses: actions/setup-go@v5 - name: Install build dependencies
# with:
# go-version: 'stable'
- name: Setup Golang
run: | run: |
dnf --assumeyes --disableplugin=subscription-manager install \ dnf --assumeyes install \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
- name: RPM build MetricCollector - name: RPM build MetricCollector
id: rpmbuild id: rpmbuild
@ -73,101 +70,20 @@ jobs:
NEW_SRPM=${OLD_SRPM/el8/alma8} NEW_SRPM=${OLD_SRPM/el8/alma8}
mv "${OLD_RPM}" "${NEW_RPM}" mv "${OLD_RPM}" "${NEW_RPM}"
mv "${OLD_SRPM}" "${NEW_SRPM}" mv "${OLD_SRPM}" "${NEW_SRPM}"
echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT echo "::set-output name=SRPM::${NEW_SRPM}"
echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT echo "::set-output name=RPM::${NEW_RPM}"
# See: https://github.com/actions/upload-artifact # See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact - name: Save RPM as artifact
uses: actions/upload-artifact@v4 uses: actions/upload-artifact@v2
with: with:
name: cc-metric-collector RPM for AlmaLinux 8 name: cc-metric-collector RPM for AlmaLinux 8
path: ${{ steps.rpmrename.outputs.RPM }} path: ${{ steps.rpmrename.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact - name: Save SRPM as artifact
uses: actions/upload-artifact@v4 uses: actions/upload-artifact@v2
with: with:
name: cc-metric-collector SRPM for AlmaLinux 8 name: cc-metric-collector SRPM for AlmaLinux 8
path: ${{ steps.rpmrename.outputs.SRPM }} path: ${{ steps.rpmrename.outputs.SRPM }}
overwrite: true
#
# Build on AlmaLinux 9 using go-toolset
#
AlmaLinux9-RPM-build:
runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux
container: almalinux:9
# The job outputs link to the outputs of the 'rpmrename' step
# Only job outputs can be used in child jobs
outputs:
rpm : ${{steps.rpmrename.outputs.RPM}}
srpm : ${{steps.rpmrename.outputs.SRPM}}
steps:
# Use dnf to install development packages
- name: Install development packages
run: |
dnf --assumeyes group install "Development Tools" "RPM Development Tools"
dnf --assumeyes install wget openssl-devel diffutils delve which
# Checkout git repository and submodules
# fetch-depth must be 0 to use git describe
# See: https://github.com/marketplace/actions/checkout
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
fetch-depth: 0
# - name: Setup Golang
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
run: |
dnf --assumeyes --disableplugin=subscription-manager install \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
# AlmaLinux 9 is a derivate of RedHat Enterprise Linux 8 (UBI8),
# so the created RPM both contain the substring 'el9' in the RPM file names
# This step replaces the substring 'el8' to 'alma8'. It uses the move operation
# because it is unclear whether the default AlmaLinux 8 container contains the
# 'rename' command. This way we also get the new names for output.
- name: Rename RPMs (s/el9/alma9/)
id: rpmrename
run: |
OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
NEW_RPM="${OLD_RPM/el9/alma9}"
NEW_SRPM=${OLD_SRPM/el9/alma9}
mv "${OLD_RPM}" "${NEW_RPM}"
mv "${OLD_SRPM}" "${NEW_SRPM}"
echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
# See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector RPM for AlmaLinux 9
path: ${{ steps.rpmrename.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector SRPM for AlmaLinux 9
path: ${{ steps.rpmrename.outputs.SRPM }}
overwrite: true
# #
# Build on UBI 8 using go-toolset # Build on UBI 8 using go-toolset
@ -195,17 +111,14 @@ jobs:
submodules: recursive submodules: recursive
fetch-depth: 0 fetch-depth: 0
# - name: Setup Golang # Use dnf to install build dependencies
# uses: actions/setup-go@v5 - name: Install build dependencies
# with:
# go-version: 'stable'
- name: Setup Golang
run: | run: |
dnf --assumeyes --disableplugin=subscription-manager install \ dnf --assumeyes --disableplugin=subscription-manager install \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
- name: RPM build MetricCollector - name: RPM build MetricCollector
id: rpmbuild id: rpmbuild
@ -215,78 +128,15 @@ jobs:
# See: https://github.com/actions/upload-artifact # See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact - name: Save RPM as artifact
uses: actions/upload-artifact@v4 uses: actions/upload-artifact@v2
with: with:
name: cc-metric-collector RPM for UBI 8 name: cc-metric-collector RPM for UBI 8
path: ${{ steps.rpmbuild.outputs.RPM }} path: ${{ steps.rpmbuild.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact - name: Save SRPM as artifact
uses: actions/upload-artifact@v4 uses: actions/upload-artifact@v2
with: with:
name: cc-metric-collector SRPM for UBI 8 name: cc-metric-collector SRPM for UBI 8
path: ${{ steps.rpmbuild.outputs.SRPM }} path: ${{ steps.rpmbuild.outputs.SRPM }}
overwrite: true
#
# Build on UBI 9 using go-toolset
#
UBI-9-RPM-build:
runs-on: ubuntu-latest
# See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
container: redhat/ubi9
# The job outputs link to the outputs of the 'rpmbuild' step
# The job outputs link to the outputs of the 'rpmbuild' step
outputs:
rpm : ${{steps.rpmbuild.outputs.RPM}}
srpm : ${{steps.rpmbuild.outputs.SRPM}}
steps:
# Use dnf to install development packages
- name: Install development packages
run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros gcc make python39 git wget openssl-devel diffutils delve
# Checkout git repository and submodules
# fetch-depth must be 0 to use git describe
# See: https://github.com/marketplace/actions/checkout
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
fetch-depth: 0
# See: https://github.com/marketplace/actions/setup-go-environment
# - name: Setup Golang
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
run: |
dnf --assumeyes --disableplugin=subscription-manager install \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
# See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector RPM for UBI 9
path: ${{ steps.rpmbuild.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector SRPM for UBI 9
path: ${{ steps.rpmbuild.outputs.SRPM }}
overwrite: true
# #
# Build on Ubuntu 22.04 using official go package # Build on Ubuntu 22.04 using official go package
@ -312,15 +162,17 @@ jobs:
with: with:
submodules: recursive submodules: recursive
fetch-depth: 0 fetch-depth: 0
# Use official golang package
- name: Setup Golang - name: Install Golang
uses: actions/setup-go@v5 run: |
with: wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
go-version: 'stable' tar --directory=/usr/local --extract --gzip
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
go version
- name: DEB build MetricCollector - name: DEB build MetricCollector
id: dpkg-build id: dpkg-build
run: | run: |
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make DEB make DEB
- name: Rename DEB (add '_ubuntu22.04') - name: Rename DEB (add '_ubuntu22.04')
@ -329,65 +181,13 @@ jobs:
OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev) OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu22.04.deb" NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu22.04.deb"
mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}" mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
echo "DEB=${NEW_DEB_FILE}" >> $GITHUB_OUTPUT echo "::set-output name=DEB::${NEW_DEB_FILE}"
# See: https://github.com/actions/upload-artifact # See: https://github.com/actions/upload-artifact
- name: Save DEB as artifact - name: Save DEB as artifact
uses: actions/upload-artifact@v4 uses: actions/upload-artifact@v2
with: with:
name: cc-metric-collector DEB for Ubuntu 22.04 name: cc-metric-collector DEB for Ubuntu 22.04
path: ${{ steps.debrename.outputs.DEB }} path: ${{ steps.debrename.outputs.DEB }}
overwrite: true
#
# Build on Ubuntu 24.04 using official go package
#
Ubuntu-noblenumbat-build:
runs-on: ubuntu-latest
container: ubuntu:24.04
# The job outputs link to the outputs of the 'debrename' step
# Only job outputs can be used in child jobs
outputs:
deb : ${{steps.debrename.outputs.DEB}}
steps:
# Use apt to install development packages
- name: Install development packages
run: |
apt update && apt --assume-yes upgrade
apt --assume-yes install build-essential sed git wget bash
# Checkout git repository and submodules
# fetch-depth must be 0 to use git describe
# See: https://github.com/marketplace/actions/checkout
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
fetch-depth: 0
- name: Setup Golang
uses: actions/setup-go@v5
with:
go-version: 'stable'
- name: DEB build MetricCollector
id: dpkg-build
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make DEB
- name: Rename DEB (add '_ubuntu24.04')
id: debrename
run: |
OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu24.04.deb"
mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
echo "DEB=${NEW_DEB_FILE}" >> $GITHUB_OUTPUT
# See: https://github.com/actions/upload-artifact
- name: Save DEB as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector DEB for Ubuntu 24.04
path: ${{ steps.debrename.outputs.DEB }}
overwrite: true
# #
# Create release with fresh RPMs # Create release with fresh RPMs
@ -395,56 +195,33 @@ jobs:
Release: Release:
runs-on: ubuntu-latest runs-on: ubuntu-latest
# We need the RPMs, so add dependency # We need the RPMs, so add dependency
needs: [AlmaLinux8-RPM-build, AlmaLinux9-RPM-build, UBI-8-RPM-build, UBI-9-RPM-build, Ubuntu-jammy-build, Ubuntu-noblenumbat-build] needs: [AlmaLinux-RPM-build, UBI-8-RPM-build, Ubuntu-jammy-build]
steps: steps:
# See: https://github.com/actions/download-artifact # See: https://github.com/actions/download-artifact
- name: Download AlmaLinux 8 RPM - name: Download AlmaLinux 8 RPM
uses: actions/download-artifact@v4 uses: actions/download-artifact@v2
with: with:
name: cc-metric-collector RPM for AlmaLinux 8 name: cc-metric-collector RPM for AlmaLinux 8
- name: Download AlmaLinux 8 SRPM - name: Download AlmaLinux 8 SRPM
uses: actions/download-artifact@v4 uses: actions/download-artifact@v2
with: with:
name: cc-metric-collector SRPM for AlmaLinux 8 name: cc-metric-collector SRPM for AlmaLinux 8
- name: Download AlmaLinux 9 RPM
uses: actions/download-artifact@v4
with:
name: cc-metric-collector RPM for AlmaLinux 9
- name: Download AlmaLinux 9 SRPM
uses: actions/download-artifact@v4
with:
name: cc-metric-collector SRPM for AlmaLinux 9
- name: Download UBI 8 RPM - name: Download UBI 8 RPM
uses: actions/download-artifact@v4 uses: actions/download-artifact@v2
with: with:
name: cc-metric-collector RPM for UBI 8 name: cc-metric-collector RPM for UBI 8
- name: Download UBI 8 SRPM - name: Download UBI 8 SRPM
uses: actions/download-artifact@v4 uses: actions/download-artifact@v2
with: with:
name: cc-metric-collector SRPM for UBI 8 name: cc-metric-collector SRPM for UBI 8
- name: Download UBI 9 RPM
uses: actions/download-artifact@v4
with:
name: cc-metric-collector RPM for UBI 9
- name: Download UBI 9 SRPM
uses: actions/download-artifact@v4
with:
name: cc-metric-collector SRPM for UBI 9
- name: Download Ubuntu 22.04 DEB - name: Download Ubuntu 22.04 DEB
uses: actions/download-artifact@v4 uses: actions/download-artifact@v2
with: with:
name: cc-metric-collector DEB for Ubuntu 22.04 name: cc-metric-collector DEB for Ubuntu 22.04
- name: Download Ubuntu 24.04 DEB
uses: actions/download-artifact@v4
with:
name: cc-metric-collector DEB for Ubuntu 24.04
# The download actions do not publish the name of the downloaded file, # The download actions do not publish the name of the downloaded file,
# so we re-use the job outputs of the parent jobs. The files are all # so we re-use the job outputs of the parent jobs. The files are all
# downloaded to the current folder. # downloaded to the current folder.
@ -454,51 +231,31 @@ jobs:
- name: Set RPM variables - name: Set RPM variables
id: files id: files
run: | run: |
ALMA_8_RPM=$(basename "${{ needs.AlmaLinux8-RPM-build.outputs.rpm}}") ALMA_8_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux8-RPM-build.outputs.srpm}}") ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
ALMA_9_RPM=$(basename "${{ needs.AlmaLinux9-RPM-build.outputs.rpm}}")
ALMA_9_SRPM=$(basename "${{ needs.AlmaLinux9-RPM-build.outputs.srpm}}")
UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}") UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}") UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
UBI_9_RPM=$(basename "${{ needs.UBI-9-RPM-build.outputs.rpm}}") U_2004_DEB=$(basename "${{ needs.Ubuntu-focal-build.outputs.deb}}")
UBI_9_SRPM=$(basename "${{ needs.UBI-9-RPM-build.outputs.srpm}}")
U_2204_DEB=$(basename "${{ needs.Ubuntu-jammy-build.outputs.deb}}")
U_2404_DEB=$(basename "${{ needs.Ubuntu-noblenumbat-build.outputs.deb}}")
echo "ALMA_8_RPM::${ALMA_8_RPM}" echo "ALMA_8_RPM::${ALMA_8_RPM}"
echo "ALMA_8_SRPM::${ALMA_8_SRPM}" echo "ALMA_8_SRPM::${ALMA_8_SRPM}"
echo "ALMA_9_RPM::${ALMA_9_RPM}"
echo "ALMA_9_SRPM::${ALMA_9_SRPM}"
echo "UBI_8_RPM::${UBI_8_RPM}" echo "UBI_8_RPM::${UBI_8_RPM}"
echo "UBI_8_SRPM::${UBI_8_SRPM}" echo "UBI_8_SRPM::${UBI_8_SRPM}"
echo "UBI_9_RPM::${UBI_9_RPM}" echo "U_2004_DEB::${U_2004_DEB}"
echo "UBI_9_SRPM::${UBI_9_SRPM}" echo "::set-output name=ALMA_8_RPM::${ALMA_8_RPM}"
echo "U_2204_DEB::${U_2204_DEB}" echo "::set-output name=ALMA_8_SRPM::${ALMA_8_SRPM}"
echo "U_2404_DEB::${U_2404_DEB}" echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
echo "ALMA_8_RPM=${ALMA_8_RPM}" >> $GITHUB_OUTPUT echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
echo "ALMA_8_SRPM=${ALMA_8_SRPM}" >> $GITHUB_OUTPUT echo "::set-output name=U_2004_DEB::${U_2004_DEB}"
echo "ALMA_9_RPM=${ALMA_9_RPM}" >> $GITHUB_OUTPUT
echo "ALMA_9_SRPM=${ALMA_9_SRPM}" >> $GITHUB_OUTPUT
echo "UBI_8_RPM=${UBI_8_RPM}" >> $GITHUB_OUTPUT
echo "UBI_8_SRPM=${UBI_8_SRPM}" >> $GITHUB_OUTPUT
echo "UBI_9_RPM=${UBI_9_RPM}" >> $GITHUB_OUTPUT
echo "UBI_9_SRPM=${UBI_9_SRPM}" >> $GITHUB_OUTPUT
echo "U_2204_DEB=${U_2204_DEB}" >> $GITHUB_OUTPUT
echo "U_2404_DEB=${U_2404_DEB}" >> $GITHUB_OUTPUT
# See: https://github.com/softprops/action-gh-release # See: https://github.com/softprops/action-gh-release
- name: Release - name: Release
uses: softprops/action-gh-release@v2 uses: softprops/action-gh-release@v1
if: startsWith(github.ref, 'refs/tags/') if: startsWith(github.ref, 'refs/tags/')
with: with:
name: cc-metric-collector-${{github.ref_name}} name: cc-metric-collector-${{github.ref_name}}
files: | files: |
${{ steps.files.outputs.ALMA_8_RPM }} ${{ steps.files.outputs.ALMA_8_RPM }}
${{ steps.files.outputs.ALMA_8_SRPM }} ${{ steps.files.outputs.ALMA_8_SRPM }}
${{ steps.files.outputs.ALMA_9_RPM }}
${{ steps.files.outputs.ALMA_9_SRPM }}
${{ steps.files.outputs.UBI_8_RPM }} ${{ steps.files.outputs.UBI_8_RPM }}
${{ steps.files.outputs.UBI_8_SRPM }} ${{ steps.files.outputs.UBI_8_SRPM }}
${{ steps.files.outputs.UBI_9_RPM }} ${{ steps.files.outputs.U_2004_DEB }}
${{ steps.files.outputs.UBI_9_SRPM }}
${{ steps.files.outputs.U_2204_DEB }}
${{ steps.files.outputs.U_2404_DEB }}

View File

@ -11,10 +11,10 @@ on:
jobs: jobs:
# #
# Job build-latest # Job build-1-20
# Build on latest Ubuntu using latest golang version # Build on latest Ubuntu using golang version 1.20
# #
build-latest: build-1-20:
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
# See: https://github.com/marketplace/actions/checkout # See: https://github.com/marketplace/actions/checkout
@ -26,10 +26,9 @@ jobs:
# See: https://github.com/marketplace/actions/setup-go-environment # See: https://github.com/marketplace/actions/setup-go-environment
- name: Setup Golang - name: Setup Golang
uses: actions/setup-go@v5 uses: actions/setup-go@v4
with: with:
go-version: '1.21' go-version: '1.20'
check-latest: true
- name: Build MetricCollector - name: Build MetricCollector
run: make run: make
@ -38,9 +37,35 @@ jobs:
run: ./cc-metric-collector --once --config .github/ci-config.json run: ./cc-metric-collector --once --config .github/ci-config.json
# #
# Build on AlmaLinux 8 # Job build-1-21
# Build on latest Ubuntu using golang version 1.21
# #
AlmaLinux8-RPM-build: build-1-21:
runs-on: ubuntu-latest
steps:
# See: https://github.com/marketplace/actions/checkout
# Checkout git repository and submodules
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
# See: https://github.com/marketplace/actions/setup-go-environment
- name: Setup Golang
uses: actions/setup-go@v4
with:
go-version: '1.21'
- name: Build MetricCollector
run: make
- name: Run MetricCollector once
run: ./cc-metric-collector --once --config .github/ci-config.json
#
# Build on AlmaLinux 8 using go-toolset
#
AlmaLinux-RPM-build:
runs-on: ubuntu-latest runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux # See: https://hub.docker.com/_/almalinux
container: almalinux:8 container: almalinux:8
@ -63,18 +88,14 @@ jobs:
submodules: recursive submodules: recursive
fetch-depth: 0 fetch-depth: 0
# See: https://github.com/marketplace/actions/setup-go-environment # Use dnf to install build dependencies
# - name: Setup Golang - name: Install build dependencies
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
run: | run: |
dnf --assumeyes --disableplugin=subscription-manager install \ dnf --assumeyes install \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
- name: RPM build MetricCollector - name: RPM build MetricCollector
id: rpmbuild id: rpmbuild
@ -82,60 +103,13 @@ jobs:
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM make RPM
#
# Build on AlmaLinux 9
#
AlmaLinux9-RPM-build:
runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux
container: almalinux:9
# The job outputs link to the outputs of the 'rpmrename' step
# Only job outputs can be used in child jobs
steps:
# Use dnf to install development packages
- name: Install development packages
run: |
dnf --assumeyes group install "Development Tools" "RPM Development Tools"
dnf --assumeyes install wget openssl-devel diffutils delve which
# Checkout git repository and submodules
# fetch-depth must be 0 to use git describe
# See: https://github.com/marketplace/actions/checkout
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
fetch-depth: 0
# See: https://github.com/marketplace/actions/setup-go-environment
# - name: Setup Golang
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
run: |
dnf --assumeyes --disableplugin=subscription-manager install \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
# #
# Build on UBI 8 using go-toolset # Build on UBI 8 using go-toolset
# #
UBI-8-RPM-build: UBI-8-RPM-build:
runs-on: ubuntu-latest runs-on: ubuntu-latest
# See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
container: redhat/ubi8 container: registry.access.redhat.com/ubi8/ubi:8.8-1032.1692772289
# The job outputs link to the outputs of the 'rpmbuild' step # The job outputs link to the outputs of the 'rpmbuild' step
steps: steps:
@ -152,61 +126,14 @@ jobs:
submodules: recursive submodules: recursive
fetch-depth: 0 fetch-depth: 0
# See: https://github.com/marketplace/actions/setup-go-environment # Use dnf to install build dependencies
# - name: Setup Golang - name: Install build dependencies
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
run: | run: |
dnf --assumeyes --disableplugin=subscription-manager install \ dnf --assumeyes --disableplugin=subscription-manager install \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \ http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
#
# Build on UBI 9 using go-toolset
#
UBI-9-RPM-build:
runs-on: ubuntu-latest
# See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
container: redhat/ubi9
# The job outputs link to the outputs of the 'rpmbuild' step
steps:
# Use dnf to install development packages
- name: Install development packages
run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros gcc make python39 git wget openssl-devel diffutils delve
# Checkout git repository and submodules
# fetch-depth must be 0 to use git describe
# See: https://github.com/marketplace/actions/checkout
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
fetch-depth: 0
# See: https://github.com/marketplace/actions/setup-go-environment
# - name: Setup Golang
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
run: |
dnf --assumeyes --disableplugin=subscription-manager install \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
- name: RPM build MetricCollector - name: RPM build MetricCollector
id: rpmbuild id: rpmbuild
@ -236,48 +163,15 @@ jobs:
submodules: recursive submodules: recursive
fetch-depth: 0 fetch-depth: 0
# Use official golang package # Use official golang package
# See: https://github.com/marketplace/actions/setup-go-environment - name: Install Golang
- name: Setup Golang run: |
uses: actions/setup-go@v5 wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
with: tar --directory=/usr/local --extract --gzip
go-version: 'stable' export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
go version
- name: DEB build MetricCollector - name: DEB build MetricCollector
id: dpkg-build id: dpkg-build
run: | run: |
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
make DEB git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make DEB
#
# Build on Ubuntu 24.04 using official go package
#
Ubuntu-noblenumbat-build:
runs-on: ubuntu-latest
container: ubuntu:24.04
steps:
# Use apt to install development packages
- name: Install development packages
run: |
apt update && apt --assume-yes upgrade
apt --assume-yes install build-essential sed git wget bash
# Checkout git repository and submodules
# fetch-depth must be 0 to use git describe
# See: https://github.com/marketplace/actions/checkout
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
fetch-depth: 0
# Use official golang package
# See: https://github.com/marketplace/actions/setup-go-environment
- name: Setup Golang
uses: actions/setup-go@v5
with:
go-version: 'stable'
- name: DEB build MetricCollector
id: dpkg-build
run: |
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
make DEB

View File

@ -1,17 +1,6 @@
<!--
---
title: cc-metric-collector
description: Metric collecting node agent
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/_index.md
---
-->
# cc-metric-collector # cc-metric-collector
A node agent for measuring, processing and forwarding node level metrics. It is part of the [ClusterCockpit ecosystem](https://clustercockpit.org/docs/overview/). A node agent for measuring, processing and forwarding node level metrics. It is part of the [ClusterCockpit ecosystem](./docs/introduction.md).
The metric collector sends (and receives) metric in the [InfluxDB line protocol](https://docs.influxdata.com/influxdb/cloud/reference/syntax/line-protocol/) as it provides flexibility while providing a separation between tags (like index columns in relational databases) and fields (like data columns). The metric collector sends (and receives) metric in the [InfluxDB line protocol](https://docs.influxdata.com/influxdb/cloud/reference/syntax/line-protocol/) as it provides flexibility while providing a separation between tags (like index columns in relational databases) and fields (like data columns).
@ -46,8 +35,8 @@ The `interval` defines how often the metrics should be read and send to the sink
See the component READMEs for their configuration: See the component READMEs for their configuration:
* [`collectors`](./collectors/README.md) * [`collectors`](./collectors/README.md)
* [`sinks`](https://github.com/ClusterCockpit/cc-lib/blob/main/sinks/README.md) * [`sinks`](./sinks/README.md)
* [`receivers`](https://github.com/ClusterCockpit/cc-lib/blob/main/receivers/README.md) * [`receivers`](./receivers/README.md)
* [`router`](./internal/metricRouter/README.md) * [`router`](./internal/metricRouter/README.md)
# Installation # Installation

View File

@ -7,24 +7,39 @@ import (
"os/signal" "os/signal"
"syscall" "syscall"
"github.com/ClusterCockpit/cc-lib/receivers"
"github.com/ClusterCockpit/cc-lib/sinks"
"github.com/ClusterCockpit/cc-metric-collector/collectors" "github.com/ClusterCockpit/cc-metric-collector/collectors"
"github.com/ClusterCockpit/cc-metric-collector/receivers"
"github.com/ClusterCockpit/cc-metric-collector/sinks"
// "strings" // "strings"
"sync" "sync"
"time" "time"
ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage"
mr "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter" mr "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker" mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
) )
type CentralConfigFile struct { type CentralConfigFile struct {
Interval string `json:"interval"` Interval string `json:"interval"`
Duration string `json:"duration"` Duration string `json:"duration"`
CollectorConfigFile string `json:"collectors"`
RouterConfigFile string `json:"router"`
SinkConfigFile string `json:"sinks"`
ReceiverConfigFile string `json:"receivers,omitempty"`
}
func LoadCentralConfiguration(file string, config *CentralConfigFile) error {
configFile, err := os.Open(file)
if err != nil {
cclog.Error(err.Error())
return err
}
defer configFile.Close()
jsonParser := json.NewDecoder(configFile)
err = jsonParser.Decode(config)
return err
} }
type RuntimeConfig struct { type RuntimeConfig struct {
@ -39,7 +54,7 @@ type RuntimeConfig struct {
ReceiveManager receivers.ReceiveManager ReceiveManager receivers.ReceiveManager
MultiChanTicker mct.MultiChanTicker MultiChanTicker mct.MultiChanTicker
Channels []chan lp.CCMessage Channels []chan lp.CCMetric
Sync sync.WaitGroup Sync sync.WaitGroup
} }
@ -72,7 +87,7 @@ func ReadCli() map[string]string {
cfg := flag.String("config", "./config.json", "Path to configuration file") cfg := flag.String("config", "./config.json", "Path to configuration file")
logfile := flag.String("log", "stderr", "Path for logfile") logfile := flag.String("log", "stderr", "Path for logfile")
once := flag.Bool("once", false, "Run all collectors only once") once := flag.Bool("once", false, "Run all collectors only once")
loglevel := flag.String("loglevel", "info", "Set log level") debug := flag.Bool("debug", false, "Activate debug output")
flag.Parse() flag.Parse()
m = make(map[string]string) m = make(map[string]string)
m["configfile"] = *cfg m["configfile"] = *cfg
@ -82,7 +97,12 @@ func ReadCli() map[string]string {
} else { } else {
m["once"] = "false" m["once"] = "false"
} }
m["loglevel"] = *loglevel if *debug {
m["debug"] = "true"
cclog.SetDebug()
} else {
m["debug"] = "false"
}
return m return m
} }
@ -147,15 +167,8 @@ func mainFunc() int {
CliArgs: ReadCli(), CliArgs: ReadCli(),
} }
// Set loglevel based on command line input.
cclog.Init(rcfg.CliArgs["loglevel"], false)
// Init ccConfig with configuration file
ccconf.Init(rcfg.CliArgs["configfile"])
// Load and check configuration // Load and check configuration
main := ccconf.GetPackageConfig("main") err = LoadCentralConfiguration(rcfg.CliArgs["configfile"], &rcfg.ConfigFile)
err = json.Unmarshal(main, &rcfg.ConfigFile)
if err != nil { if err != nil {
cclog.Error("Error reading configuration file ", rcfg.CliArgs["configfile"], ": ", err.Error()) cclog.Error("Error reading configuration file ", rcfg.CliArgs["configfile"], ": ", err.Error())
return 1 return 1
@ -191,74 +204,70 @@ func mainFunc() int {
return 1 return 1
} }
routerConf := ccconf.GetPackageConfig("router") if len(rcfg.ConfigFile.RouterConfigFile) == 0 {
if len(routerConf) == 0 {
cclog.Error("Metric router configuration file must be set") cclog.Error("Metric router configuration file must be set")
return 1 return 1
} }
sinkConf := ccconf.GetPackageConfig("sinks") if len(rcfg.ConfigFile.SinkConfigFile) == 0 {
if len(sinkConf) == 0 {
cclog.Error("Sink configuration file must be set") cclog.Error("Sink configuration file must be set")
return 1 return 1
} }
collectorConf := ccconf.GetPackageConfig("collectors") if len(rcfg.ConfigFile.CollectorConfigFile) == 0 {
if len(collectorConf) == 0 {
cclog.Error("Metric collector configuration file must be set") cclog.Error("Metric collector configuration file must be set")
return 1 return 1
} }
// Set log file // Set log file
// if logfile := rcfg.CliArgs["logfile"]; logfile != "stderr" { if logfile := rcfg.CliArgs["logfile"]; logfile != "stderr" {
// cclog.SetOutput(logfile) cclog.SetOutput(logfile)
// } }
// Creat new multi channel ticker // Creat new multi channel ticker
rcfg.MultiChanTicker = mct.NewTicker(rcfg.Interval) rcfg.MultiChanTicker = mct.NewTicker(rcfg.Interval)
// Create new metric router // Create new metric router
rcfg.MetricRouter, err = mr.New(rcfg.MultiChanTicker, &rcfg.Sync, routerConf) rcfg.MetricRouter, err = mr.New(rcfg.MultiChanTicker, &rcfg.Sync, rcfg.ConfigFile.RouterConfigFile)
if err != nil { if err != nil {
cclog.Error(err.Error()) cclog.Error(err.Error())
return 1 return 1
} }
// Create new sink // Create new sink
rcfg.SinkManager, err = sinks.New(&rcfg.Sync, sinkConf) rcfg.SinkManager, err = sinks.New(&rcfg.Sync, rcfg.ConfigFile.SinkConfigFile)
if err != nil { if err != nil {
cclog.Error(err.Error()) cclog.Error(err.Error())
return 1 return 1
} }
// Connect metric router to sink manager // Connect metric router to sink manager
RouterToSinksChannel := make(chan lp.CCMessage, 200) RouterToSinksChannel := make(chan lp.CCMetric, 200)
rcfg.SinkManager.AddInput(RouterToSinksChannel) rcfg.SinkManager.AddInput(RouterToSinksChannel)
rcfg.MetricRouter.AddOutput(RouterToSinksChannel) rcfg.MetricRouter.AddOutput(RouterToSinksChannel)
// Create new collector manager // Create new collector manager
rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, collectorConf) rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, rcfg.ConfigFile.CollectorConfigFile)
if err != nil { if err != nil {
cclog.Error(err.Error()) cclog.Error(err.Error())
return 1 return 1
} }
// Connect collector manager to metric router // Connect collector manager to metric router
CollectToRouterChannel := make(chan lp.CCMessage, 200) CollectToRouterChannel := make(chan lp.CCMetric, 200)
rcfg.CollectManager.AddOutput(CollectToRouterChannel) rcfg.CollectManager.AddOutput(CollectToRouterChannel)
rcfg.MetricRouter.AddCollectorInput(CollectToRouterChannel) rcfg.MetricRouter.AddCollectorInput(CollectToRouterChannel)
// Create new receive manager // Create new receive manager
receiveConf := ccconf.GetPackageConfig("receivers") if len(rcfg.ConfigFile.ReceiverConfigFile) > 0 {
if len(receiveConf) > 0 { rcfg.ReceiveManager, err = receivers.New(&rcfg.Sync, rcfg.ConfigFile.ReceiverConfigFile)
rcfg.ReceiveManager, err = receivers.New(&rcfg.Sync, receiveConf)
if err != nil { if err != nil {
cclog.Error(err.Error()) cclog.Error(err.Error())
return 1 return 1
} }
// Connect receive manager to metric router // Connect receive manager to metric router
ReceiveToRouterChannel := make(chan lp.CCMessage, 200) ReceiveToRouterChannel := make(chan lp.CCMetric, 200)
rcfg.ReceiveManager.AddOutput(ReceiveToRouterChannel) rcfg.ReceiveManager.AddOutput(ReceiveToRouterChannel)
rcfg.MetricRouter.AddReceiverInput(ReceiveToRouterChannel) rcfg.MetricRouter.AddReceiverInput(ReceiveToRouterChannel)
use_recv = true use_recv = true

View File

@ -1,5 +1,5 @@
# LIKWID version # LIKWID version
LIKWID_VERSION := 5.4.1 LIKWID_VERSION := 5.2.2
LIKWID_INSTALLED_FOLDER := $(shell dirname $$(which likwid-topology 2>/dev/null) 2>/dev/null) LIKWID_INSTALLED_FOLDER := $(shell dirname $$(which likwid-topology 2>/dev/null) 2>/dev/null)
LIKWID_FOLDER := $(CURDIR)/likwid LIKWID_FOLDER := $(CURDIR)/likwid
@ -23,7 +23,7 @@ likwid:
mkdir --parents --verbose "$${BUILD_FOLDER}" mkdir --parents --verbose "$${BUILD_FOLDER}"
wget --output-document=- http://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz | wget --output-document=- http://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz |
tar --directory="$${BUILD_FOLDER}" --extract --gz tar --directory="$${BUILD_FOLDER}" --extract --gz
install -D --verbose --preserve-timestamps --mode=0644 --target-directory="$(LIKWID_FOLDER)" "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/likwid*.h install -D --verbose --preserve-timestamps --mode=0644 --target-directory="$(LIKWID_FOLDER)" "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/likwid*.h "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/bstrlib.h
rm --recursive "$${BUILD_FOLDER}" rm --recursive "$${BUILD_FOLDER}"
fi fi

View File

@ -1,14 +1,3 @@
<!--
---
title: Metric Collectors
description: Metric collectors for cc-metric-collector
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/_index.md
---
-->
# CCMetric collectors # CCMetric collectors
This folder contains the collectors for the cc-metric-collector. This folder contains the collectors for the cc-metric-collector.
@ -34,6 +23,7 @@ In contrast to the configuration files for sinks and receivers, the collectors c
* [`loadavg`](./loadavgMetric.md) * [`loadavg`](./loadavgMetric.md)
* [`netstat`](./netstatMetric.md) * [`netstat`](./netstatMetric.md)
* [`ibstat`](./infinibandMetric.md) * [`ibstat`](./infinibandMetric.md)
* [`ibstat_perfquery`](./infinibandPerfQueryMetric.md)
* [`tempstat`](./tempMetric.md) * [`tempstat`](./tempMetric.md)
* [`lustrestat`](./lustreMetric.md) * [`lustrestat`](./lustreMetric.md)
* [`likwid`](./likwidMetric.md) * [`likwid`](./likwidMetric.md)
@ -43,10 +33,8 @@ In contrast to the configuration files for sinks and receivers, the collectors c
* [`topprocs`](./topprocsMetric.md) * [`topprocs`](./topprocsMetric.md)
* [`nfs3stat`](./nfs3Metric.md) * [`nfs3stat`](./nfs3Metric.md)
* [`nfs4stat`](./nfs4Metric.md) * [`nfs4stat`](./nfs4Metric.md)
* [`nfsiostat`](./nfsiostatMetric.md)
* [`cpufreq`](./cpufreqMetric.md) * [`cpufreq`](./cpufreqMetric.md)
* [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md) * [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
* [`schedstat`](./schedstatMetric.md)
* [`numastats`](./numastatsMetric.md) * [`numastats`](./numastatsMetric.md)
* [`gpfs`](./gpfsMetric.md) * [`gpfs`](./gpfsMetric.md)
* [`beegfs_meta`](./beegfsmetaMetric.md) * [`beegfs_meta`](./beegfsmetaMetric.md)
@ -63,7 +51,7 @@ A collector reads data from any source, parses it to metrics and submits these m
* `Name() string`: Return the name of the collector * `Name() string`: Return the name of the collector
* `Init(config json.RawMessage) error`: Initializes the collector using the given collector-specific config in JSON. Check if needed files/commands exists, ... * `Init(config json.RawMessage) error`: Initializes the collector using the given collector-specific config in JSON. Check if needed files/commands exists, ...
* `Initialized() bool`: Check if a collector is successfully initialized * `Initialized() bool`: Check if a collector is successfully initialized
* `Read(duration time.Duration, output chan ccMessage.CCMessage)`: Read, parse and submit data to the `output` channel as [`CCMessage`](https://github.com/ClusterCockpit/cc-lib/blob/main/ccMessage/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`. * `Read(duration time.Duration, output chan ccMetric.CCMetric)`: Read, parse and submit data to the `output` channel as [`CCMetric`](../internal/ccMetric/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`.
* `Close()`: Closes down the collector. * `Close()`: Closes down the collector.
It is recommanded to call `setup()` in the `Init()` function. It is recommanded to call `setup()` in the `Init()` function.

View File

@ -14,8 +14,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
const DEFAULT_BEEGFS_CMD = "beegfs-ctl" const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
@ -110,7 +110,7 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -216,7 +216,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
for key, data := range m.matches { for key, data := range m.matches {
value, _ := strconv.ParseFloat(data, 32) value, _ := strconv.ParseFloat(data, 32)
y, err := lp.NewMessage(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now()) y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }

View File

@ -1,17 +1,5 @@
<!--
---
title: BeeGFS metadata metric collector
description: Collect metadata clientstats for `BeeGFS on Demand`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/beegfsmeta.md
---
-->
## `BeeGFS on Demand` collector ## `BeeGFS on Demand` collector
This Collector is to collect `BeeGFS on Demand` (BeeOND) metadata clientstats. This Collector is to collect BeeGFS on Demand (BeeOND) metadata clientstats.
```json ```json
"beegfs_meta": { "beegfs_meta": {
@ -84,4 +72,4 @@ Available Metrics:
* setXA * setXA
* mirror * mirror
The collector adds a `filesystem` tag to all metrics The collector adds a `filesystem` tag to all metrics

View File

@ -14,8 +14,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// Struct for the collector-specific JSON config // Struct for the collector-specific JSON config
@ -103,7 +103,7 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -208,7 +208,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
for key, data := range m.matches { for key, data := range m.matches {
value, _ := strconv.ParseFloat(data, 32) value, _ := strconv.ParseFloat(data, 32)
y, err := lp.NewMessage(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now()) y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }

View File

@ -1,14 +1,3 @@
<!--
---
title: "BeeGFS on Demand metric collector"
description: Collect performance metrics for BeeGFS filesystems
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/beegfsstorage.md
---
-->
## `BeeGFS on Demand` collector ## `BeeGFS on Demand` collector
This Collector is to collect BeeGFS on Demand (BeeOND) storage stats. This Collector is to collect BeeGFS on Demand (BeeOND) storage stats.
@ -63,4 +52,4 @@ Available Metrics:
* "unlnk" * "unlnk"
The collector adds a `filesystem` tag to all metrics The collector adds a `filesystem` tag to all metrics

View File

@ -2,11 +2,12 @@ package collectors
import ( import (
"encoding/json" "encoding/json"
"os"
"sync" "sync"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker" mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
) )
@ -46,7 +47,7 @@ var AvailableCollectors = map[string]MetricCollector{
type collectorManager struct { type collectorManager struct {
collectors []MetricCollector // List of metric collectors to read in parallel collectors []MetricCollector // List of metric collectors to read in parallel
serial []MetricCollector // List of metric collectors to read serially serial []MetricCollector // List of metric collectors to read serially
output chan lp.CCMessage // Output channels output chan lp.CCMetric // Output channels
done chan bool // channel to finish / stop metric collector manager done chan bool // channel to finish / stop metric collector manager
ticker mct.MultiChanTicker // periodically ticking once each interval ticker mct.MultiChanTicker // periodically ticking once each interval
duration time.Duration // duration (for metrics that measure over a given duration) duration time.Duration // duration (for metrics that measure over a given duration)
@ -58,8 +59,8 @@ type collectorManager struct {
// Metric collector manager access functions // Metric collector manager access functions
type CollectorManager interface { type CollectorManager interface {
Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error
AddOutput(output chan lp.CCMessage) AddOutput(output chan lp.CCMetric)
Start() Start()
Close() Close()
} }
@ -71,7 +72,7 @@ type CollectorManager interface {
// * ticker (from variable ticker) // * ticker (from variable ticker)
// * configuration (read from config file in variable collectConfigFile) // * configuration (read from config file in variable collectConfigFile)
// Initialization is done for all configured collectors // Initialization is done for all configured collectors
func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error { func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error {
cm.collectors = make([]MetricCollector, 0) cm.collectors = make([]MetricCollector, 0)
cm.serial = make([]MetricCollector, 0) cm.serial = make([]MetricCollector, 0)
cm.output = nil cm.output = nil
@ -80,7 +81,15 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
cm.ticker = ticker cm.ticker = ticker
cm.duration = duration cm.duration = duration
err := json.Unmarshal(collectConfig, &cm.config) // Read collector config file
configFile, err := os.Open(collectConfigFile)
if err != nil {
cclog.Error(err.Error())
return err
}
defer configFile.Close()
jsonParser := json.NewDecoder(configFile)
err = jsonParser.Decode(&cm.config)
if err != nil { if err != nil {
cclog.Error(err.Error()) cclog.Error(err.Error())
return err return err
@ -178,7 +187,7 @@ func (cm *collectorManager) Start() {
} }
// AddOutput adds the output channel to the metric collector manager // AddOutput adds the output channel to the metric collector manager
func (cm *collectorManager) AddOutput(output chan lp.CCMessage) { func (cm *collectorManager) AddOutput(output chan lp.CCMetric) {
cm.output = output cm.output = output
} }
@ -191,9 +200,9 @@ func (cm *collectorManager) Close() {
} }
// New creates a new initialized metric collector manager // New creates a new initialized metric collector manager
func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) (CollectorManager, error) { func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) (CollectorManager, error) {
cm := new(collectorManager) cm := new(collectorManager)
err := cm.Init(ticker, duration, wg, collectConfig) err := cm.Init(ticker, duration, wg, collectConfigFile)
if err != nil { if err != nil {
return nil, err return nil, err
} }

View File

@ -10,8 +10,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// CPUFreqCollector // CPUFreqCollector
@ -112,14 +112,14 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
// Check if at least one CPU with frequency information was detected // Check if at least one CPU with frequency information was detected
if len(m.topology) == 0 { if len(m.topology) == 0 {
return fmt.Errorf("no CPU frequency info found in %s", cpuInfoFile) return fmt.Errorf("No CPU frequency info found in %s", cpuInfoFile)
} }
m.init = true m.init = true
return nil return nil
} }
func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Check if already initialized // Check if already initialized
if !m.init { if !m.init {
return return
@ -154,7 +154,7 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err)) fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err))
return return
} }
if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil { if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
output <- y output <- y
} }
} }

View File

@ -1,14 +1,3 @@
<!--
---
title: CPU frequency metric collector through cpuinfo
description: Collect the CPU frequency from `/proc/cpuinfo`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/cpufreq_cpuinfo.md
---
-->
## `cpufreq_cpuinfo` collector ## `cpufreq_cpuinfo` collector
```json ```json

View File

@ -9,8 +9,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology" "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
"golang.org/x/sys/unix" "golang.org/x/sys/unix"
) )
@ -91,7 +91,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Check if already initialized // Check if already initialized
if !m.init { if !m.init {
return return
@ -117,7 +117,7 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage
continue continue
} }
if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil { if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
output <- y output <- y
} }
} }

View File

@ -1,14 +1,3 @@
<!--
---
title: CPU frequency metric collector through sysfs
description: Collect the CPU frequency metrics from `/sys/.../cpu/.../cpufreq`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/cpufreq.md
---
-->
## `cpufreq_cpuinfo` collector ## `cpufreq_cpuinfo` collector
```json ```json

View File

@ -9,8 +9,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
sysconf "github.com/tklauser/go-sysconf" sysconf "github.com/tklauser/go-sysconf"
) )
@ -34,7 +34,7 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
m.name = "CpustatCollector" m.name = "CpustatCollector"
m.setup() m.setup()
m.parallel = true m.parallel = true
m.meta = map[string]string{"source": m.name, "group": "CPU"} m.meta = map[string]string{"source": m.name, "group": "CPU", "unit": "Percent"}
m.nodetags = map[string]string{"type": "node"} m.nodetags = map[string]string{"type": "node"}
if len(config) > 0 { if len(config) > 0 {
err := json.Unmarshal(config, &m.config) err := json.Unmarshal(config, &m.config)
@ -105,7 +105,7 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMessage, now time.Time, tsdelta time.Duration) { func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
values := make(map[string]float64) values := make(map[string]float64)
clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK) clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK)
for match, index := range m.matches { for match, index := range m.matches {
@ -122,23 +122,21 @@ func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]st
sum := float64(0) sum := float64(0)
for name, value := range values { for name, value := range values {
sum += value sum += value
y, err := lp.NewMessage(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now) y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now)
if err == nil { if err == nil {
y.AddTag("unit", "Percent")
output <- y output <- y
} }
} }
if v, ok := values["cpu_idle"]; ok { if v, ok := values["cpu_idle"]; ok {
sum -= v sum -= v
y, err := lp.NewMessage("cpu_used", tags, m.meta, map[string]interface{}{"value": sum * 100}, now) y, err := lp.New("cpu_used", tags, m.meta, map[string]interface{}{"value": sum * 100}, now)
if err == nil { if err == nil {
y.AddTag("unit", "Percent")
output <- y output <- y
} }
} }
} }
func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -164,7 +162,7 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage
} }
} }
num_cpus_metric, err := lp.NewMessage("num_cpus", num_cpus_metric, err := lp.New("num_cpus",
m.nodetags, m.nodetags,
m.meta, m.meta,
map[string]interface{}{"value": int(num_cpus)}, map[string]interface{}{"value": int(num_cpus)},

View File

@ -1,14 +1,3 @@
<!--
---
title: CPU usage metric collector
description: Collect CPU metrics from `/proc/stat`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/cpustat.md
---
-->
## `cpustat` collector ## `cpustat` collector
@ -24,15 +13,14 @@ The `cpustat` collector reads data from `/proc/stat` and outputs a handful **nod
Metrics: Metrics:
* `cpu_user` with `unit=Percent` * `cpu_user`
* `cpu_nice` with `unit=Percent` * `cpu_nice`
* `cpu_system` with `unit=Percent` * `cpu_system`
* `cpu_idle` with `unit=Percent` * `cpu_idle`
* `cpu_iowait` with `unit=Percent` * `cpu_iowait`
* `cpu_irq` with `unit=Percent` * `cpu_irq`
* `cpu_softirq` with `unit=Percent` * `cpu_softirq`
* `cpu_steal` with `unit=Percent` * `cpu_steal`
* `cpu_guest` with `unit=Percent` * `cpu_guest`
* `cpu_guest_nice` with `unit=Percent` * `cpu_guest_nice`
* `cpu_used` = `cpu_* - cpu_idle` with `unit=Percent` * `cpu_used` = `cpu_* - cpu_idle`
* `num_cpus`

View File

@ -9,7 +9,7 @@ import (
"strings" "strings"
"time" "time"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol" influx "github.com/influxdata/line-protocol"
) )
@ -75,7 +75,7 @@ var DefaultTime = func() time.Time {
return time.Unix(42, 0) return time.Unix(42, 0)
} }
func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -99,7 +99,10 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMessa
continue continue
} }
output <- lp.FromInfluxMetric(c) y := lp.FromInfluxMetric(c)
if err == nil {
output <- y
}
} }
} }
for _, file := range m.files { for _, file := range m.files {
@ -118,7 +121,10 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMessa
if skip { if skip {
continue continue
} }
output <- lp.FromInfluxMetric(f) y := lp.FromInfluxMetric(f)
if err == nil {
output <- y
}
} }
} }
} }

View File

@ -1,13 +1,3 @@
<!--
---
title: CustomCommand metric collector
description: Collect messages from custom command or files
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/customcmd.md
---
-->
## `customcmd` collector ## `customcmd` collector

View File

@ -8,21 +8,23 @@ import (
"syscall" "syscall"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// "log"
const MOUNTFILE = `/proc/self/mounts` const MOUNTFILE = `/proc/self/mounts`
type DiskstatCollectorConfig struct { type DiskstatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"` ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ExcludeMounts []string `json:"exclude_mounts,omitempty"`
} }
type DiskstatCollector struct { type DiskstatCollector struct {
metricCollector metricCollector
config DiskstatCollectorConfig //matches map[string]int
allowedMetrics map[string]bool config IOstatCollectorConfig
//devices map[string]IOstatCollectorEntry
} }
func (m *DiskstatCollector) Init(config json.RawMessage) error { func (m *DiskstatCollector) Init(config json.RawMessage) error {
@ -31,21 +33,12 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
m.meta = map[string]string{"source": m.name, "group": "Disk"} m.meta = map[string]string{"source": m.name, "group": "Disk"}
m.setup() m.setup()
if len(config) > 0 { if len(config) > 0 {
if err := json.Unmarshal(config, &m.config); err != nil { err := json.Unmarshal(config, &m.config)
if err != nil {
return err return err
} }
} }
m.allowedMetrics = map[string]bool{ file, err := os.Open(string(MOUNTFILE))
"disk_total": true,
"disk_free": true,
"part_max_used": true,
}
for _, excl := range m.config.ExcludeMetrics {
if _, ok := m.allowedMetrics[excl]; ok {
m.allowedMetrics[excl] = false
}
}
file, err := os.Open(MOUNTFILE)
if err != nil { if err != nil {
cclog.ComponentError(m.name, err.Error()) cclog.ComponentError(m.name, err.Error())
return err return err
@ -55,12 +48,12 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
file, err := os.Open(MOUNTFILE) file, err := os.Open(string(MOUNTFILE))
if err != nil { if err != nil {
cclog.ComponentError(m.name, err.Error()) cclog.ComponentError(m.name, err.Error())
return return
@ -69,7 +62,6 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
part_max_used := uint64(0) part_max_used := uint64(0)
scanner := bufio.NewScanner(file) scanner := bufio.NewScanner(file)
mountLoop:
for scanner.Scan() { for scanner.Scan() {
line := scanner.Text() line := scanner.Text()
if len(line) == 0 { if len(line) == 0 {
@ -85,17 +77,13 @@ mountLoop:
if strings.Contains(linefields[1], "boot") { if strings.Contains(linefields[1], "boot") {
continue continue
} }
path := strings.Replace(linefields[1], `\040`, " ", -1)
mountPath := strings.Replace(linefields[1], `\040`, " ", -1) stat := syscall.Statfs_t{
Blocks: 0,
for _, excl := range m.config.ExcludeMounts { Bsize: 0,
if strings.Contains(mountPath, excl) { Bfree: 0,
continue mountLoop
}
} }
err := syscall.Statfs(path, &stat)
stat := syscall.Statfs_t{}
err := syscall.Statfs(mountPath, &stat)
if err != nil { if err != nil {
continue continue
} }
@ -104,20 +92,16 @@ mountLoop:
} }
tags := map[string]string{"type": "node", "device": linefields[0]} tags := map[string]string{"type": "node", "device": linefields[0]}
total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000) total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
if m.allowedMetrics["disk_total"] { y, err := lp.New("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
y, err := lp.NewMessage("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now()) if err == nil {
if err == nil { y.AddMeta("unit", "GBytes")
y.AddMeta("unit", "GBytes") output <- y
output <- y
}
} }
free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000) free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
if m.allowedMetrics["disk_free"] { y, err = lp.New("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
y, err := lp.NewMessage("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now()) if err == nil {
if err == nil { y.AddMeta("unit", "GBytes")
y.AddMeta("unit", "GBytes") output <- y
output <- y
}
} }
if total > 0 { if total > 0 {
perc := (100 * (total - free)) / total perc := (100 * (total - free)) / total
@ -126,12 +110,10 @@ mountLoop:
} }
} }
} }
if m.allowedMetrics["part_max_used"] { y, err := lp.New("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())
y, err := lp.NewMessage("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now()) if err == nil {
if err == nil { y.AddMeta("unit", "percent")
y.AddMeta("unit", "percent") output <- y
output <- y
}
} }
} }

View File

@ -1,13 +1,3 @@
<!--
---
title: Disk usage statistics metric collector
description: Collect metrics for various filesystems from `/proc/self/mounts`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/diskstat.md
---
-->
## `diskstat` collector ## `diskstat` collector
@ -16,13 +6,10 @@ hugo_path: docs/reference/cc-metric-collector/collectors/diskstat.md
"exclude_metrics": [ "exclude_metrics": [
"disk_total" "disk_total"
], ],
"exclude_mounts": [
"slurm-tmpfs"
]
} }
``` ```
The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink. Additionally, any mount point containing one of the strings specified in `exclude_mounts` will be skipped during metric collection. The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
Metrics per device (with `device` tag): Metrics per device (with `device` tag):
* `disk_total` (unit `GBytes`) * `disk_total` (unit `GBytes`)

View File

@ -13,8 +13,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
const DEFAULT_GPFS_CMD = "mmpmon" const DEFAULT_GPFS_CMD = "mmpmon"
@ -94,7 +94,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Check if already initialized // Check if already initialized
if !m.init { if !m.init {
return return
@ -218,7 +218,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue continue
} }
if y, err := if y, err :=
lp.NewMessage( lp.New(
"gpfs_bytes_read", "gpfs_bytes_read",
m.tags, m.tags,
m.meta, m.meta,
@ -234,7 +234,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 { if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 {
bwRead := float64(bytesRead-lastBytesRead) / timeDiff bwRead := float64(bytesRead-lastBytesRead) / timeDiff
if y, err := if y, err :=
lp.NewMessage( lp.New(
"gpfs_bw_read", "gpfs_bw_read",
m.tags, m.tags,
m.meta, m.meta,
@ -258,7 +258,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue continue
} }
if y, err := if y, err :=
lp.NewMessage( lp.New(
"gpfs_bytes_written", "gpfs_bytes_written",
m.tags, m.tags,
m.meta, m.meta,
@ -274,7 +274,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 { if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
if y, err := if y, err :=
lp.NewMessage( lp.New(
"gpfs_bw_write", "gpfs_bw_write",
m.tags, m.tags,
m.meta, m.meta,
@ -304,7 +304,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
fmt.Sprintf("Read(): Failed to convert number of opens '%s' to int64: %v", key_value["_oc_"], err)) fmt.Sprintf("Read(): Failed to convert number of opens '%s' to int64: %v", key_value["_oc_"], err))
continue continue
} }
if y, err := lp.NewMessage("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil { if y, err := lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
output <- y output <- y
} }
@ -316,7 +316,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
fmt.Sprintf("Read(): Failed to convert number of closes: '%s' to int64: %v", key_value["_cc_"], err)) fmt.Sprintf("Read(): Failed to convert number of closes: '%s' to int64: %v", key_value["_cc_"], err))
continue continue
} }
if y, err := lp.NewMessage("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil { if y, err := lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
output <- y output <- y
} }
@ -328,7 +328,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
fmt.Sprintf("Read(): Failed to convert number of reads: '%s' to int64: %v", key_value["_rdc_"], err)) fmt.Sprintf("Read(): Failed to convert number of reads: '%s' to int64: %v", key_value["_rdc_"], err))
continue continue
} }
if y, err := lp.NewMessage("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil { if y, err := lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
output <- y output <- y
} }
@ -340,7 +340,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
fmt.Sprintf("Read(): Failed to convert number of writes: '%s' to int64: %v", key_value["_wc_"], err)) fmt.Sprintf("Read(): Failed to convert number of writes: '%s' to int64: %v", key_value["_wc_"], err))
continue continue
} }
if y, err := lp.NewMessage("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil { if y, err := lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
output <- y output <- y
} }
@ -352,7 +352,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
fmt.Sprintf("Read(): Failed to convert number of read directories: '%s' to int64: %v", key_value["_dir_"], err)) fmt.Sprintf("Read(): Failed to convert number of read directories: '%s' to int64: %v", key_value["_dir_"], err))
continue continue
} }
if y, err := lp.NewMessage("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil { if y, err := lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
output <- y output <- y
} }
@ -364,7 +364,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
fmt.Sprintf("Read(): Failed to convert number of inode updates: '%s' to int: %v", key_value["_iu_"], err)) fmt.Sprintf("Read(): Failed to convert number of inode updates: '%s' to int: %v", key_value["_iu_"], err))
continue continue
} }
if y, err := lp.NewMessage("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil { if y, err := lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
output <- y output <- y
} }
@ -372,7 +372,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
if m.config.SendTotalValues { if m.config.SendTotalValues {
bytesTotal := bytesRead + bytesWritten bytesTotal := bytesRead + bytesWritten
if y, err := if y, err :=
lp.NewMessage("gpfs_bytes_total", lp.New("gpfs_bytes_total",
m.tags, m.tags,
m.meta, m.meta,
map[string]interface{}{ map[string]interface{}{
@ -385,7 +385,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
} }
iops := numReads + numWrites iops := numReads + numWrites
if y, err := if y, err :=
lp.NewMessage("gpfs_iops", lp.New("gpfs_iops",
m.tags, m.tags,
m.meta, m.meta,
map[string]interface{}{ map[string]interface{}{
@ -397,7 +397,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
} }
metaops := numInodeUpdates + numCloses + numOpens + numReaddirs metaops := numInodeUpdates + numCloses + numOpens + numReaddirs
if y, err := if y, err :=
lp.NewMessage("gpfs_metaops", lp.New("gpfs_metaops",
m.tags, m.tags,
m.meta, m.meta,
map[string]interface{}{ map[string]interface{}{

View File

@ -1,14 +1,3 @@
<!--
---
title: GPFS collector
description: Collect infos about GPFS filesystems
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/gpfs.md
---
-->
## `gpfs` collector ## `gpfs` collector
```json ```json

View File

@ -4,8 +4,8 @@ import (
"fmt" "fmt"
"os" "os"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"golang.org/x/sys/unix" "golang.org/x/sys/unix"
"encoding/json" "encoding/json"
@ -182,7 +182,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
} }
// Read reads Infiniband counter files below IB_BASEPATH // Read reads Infiniband counter files below IB_BASEPATH
func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Check if already initialized // Check if already initialized
if !m.init { if !m.init {
@ -230,7 +230,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
// Send absolut values // Send absolut values
if m.config.SendAbsoluteValues { if m.config.SendAbsoluteValues {
if y, err := if y, err :=
lp.NewMessage( lp.New(
counterDef.name, counterDef.name,
info.tagSet, info.tagSet,
m.meta, m.meta,
@ -248,7 +248,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
if counterDef.lastState >= 0 { if counterDef.lastState >= 0 {
rate := float64((counterDef.currentState - counterDef.lastState)) / timeDiff rate := float64((counterDef.currentState - counterDef.lastState)) / timeDiff
if y, err := if y, err :=
lp.NewMessage( lp.New(
counterDef.name+"_bw", counterDef.name+"_bw",
info.tagSet, info.tagSet,
m.meta, m.meta,
@ -278,7 +278,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
// Send total values // Send total values
if m.config.SendTotalValues { if m.config.SendTotalValues {
if y, err := if y, err :=
lp.NewMessage( lp.New(
"ib_total", "ib_total",
info.tagSet, info.tagSet,
m.meta, m.meta,
@ -291,7 +291,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
} }
if y, err := if y, err :=
lp.NewMessage( lp.New(
"ib_total_pkts", "ib_total_pkts",
info.tagSet, info.tagSet,
m.meta, m.meta,

View File

@ -1,13 +1,3 @@
<!--
---
title: InfiniBand Metric collector
description: Collect metrics for InfiniBand devices
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/infiniband.md
---
-->
## `ibstat` collector ## `ibstat` collector

View File

@ -2,24 +2,24 @@ package collectors
import ( import (
"bufio" "bufio"
"os"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
// "log"
"encoding/json" "encoding/json"
"errors" "errors"
"os"
"strconv" "strconv"
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage"
) )
// Konstante für den Pfad zu /proc/diskstats
const IOSTATFILE = `/proc/diskstats` const IOSTATFILE = `/proc/diskstats`
const IOSTAT_SYSFSPATH = `/sys/block`
type IOstatCollectorConfig struct { type IOstatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"` ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
// Neues Feld zum Ausschließen von Devices per JSON-Konfiguration
ExcludeDevices []string `json:"exclude_devices,omitempty"`
} }
type IOstatCollectorEntry struct { type IOstatCollectorEntry struct {
@ -76,7 +76,7 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
if len(m.matches) == 0 { if len(m.matches) == 0 {
return errors.New("no metrics to collect") return errors.New("no metrics to collect")
} }
file, err := os.Open(IOSTATFILE) file, err := os.Open(string(IOSTATFILE))
if err != nil { if err != nil {
cclog.ComponentError(m.name, err.Error()) cclog.ComponentError(m.name, err.Error())
return err return err
@ -87,24 +87,17 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
for scanner.Scan() { for scanner.Scan() {
line := scanner.Text() line := scanner.Text()
linefields := strings.Fields(line) linefields := strings.Fields(line)
if len(linefields) < 3 {
continue
}
device := linefields[2] device := linefields[2]
if strings.Contains(device, "loop") { if strings.Contains(device, "loop") {
continue continue
} }
if _, skip := stringArrayContains(m.config.ExcludeDevices, device); skip {
continue
}
values := make(map[string]int64) values := make(map[string]int64)
for m := range m.matches { for m := range m.matches {
values[m] = 0 values[m] = 0
} }
m.devices[device] = IOstatCollectorEntry{ m.devices[device] = IOstatCollectorEntry{
tags: map[string]string{ tags: map[string]string{
"device": device, "device": linefields[2],
"type": "node", "type": "node",
}, },
lastValues: values, lastValues: values,
@ -114,12 +107,12 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
return err return err
} }
func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
file, err := os.Open(IOSTATFILE) file, err := os.Open(string(IOSTATFILE))
if err != nil { if err != nil {
cclog.ComponentError(m.name, err.Error()) cclog.ComponentError(m.name, err.Error())
return return
@ -133,16 +126,10 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
continue continue
} }
linefields := strings.Fields(line) linefields := strings.Fields(line)
if len(linefields) < 3 {
continue
}
device := linefields[2] device := linefields[2]
if strings.Contains(device, "loop") { if strings.Contains(device, "loop") {
continue continue
} }
if _, skip := stringArrayContains(m.config.ExcludeDevices, device); skip {
continue
}
if _, ok := m.devices[device]; !ok { if _, ok := m.devices[device]; !ok {
continue continue
} }
@ -152,7 +139,7 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
x, err := strconv.ParseInt(linefields[idx], 0, 64) x, err := strconv.ParseInt(linefields[idx], 0, 64)
if err == nil { if err == nil {
diff := x - entry.lastValues[name] diff := x - entry.lastValues[name]
y, err := lp.NewMessage(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now()) y, err := lp.New(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }

View File

@ -1,30 +1,15 @@
<!--
---
title: IOStat Metric collector
description: Collect metrics from `/proc/diskstats`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/iostat.md
---
-->
## `iostat` collector ## `iostat` collector
```json ```json
"iostat": { "iostat": {
"exclude_metrics": [ "exclude_metrics": [
"io_read_ms" "read_ms"
], ],
"exclude_devices": [
"nvme0n1p1",
"nvme0n1p2",
"md127"
]
} }
``` ```
The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric or device is not required, it can be excluded from forwarding it to the sink. The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
Metrics: Metrics:
* `io_reads` * `io_reads`

View File

@ -12,9 +12,8 @@ import (
"strconv" "strconv"
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
lp "github.com/ClusterCockpit/cc-lib/ccMessage"
) )
const IPMISENSORS_PATH = `ipmi-sensors` const IPMISENSORS_PATH = `ipmi-sensors`
@ -55,35 +54,20 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
// Check if executables ipmitool or ipmisensors are found // Check if executables ipmitool or ipmisensors are found
p, err := exec.LookPath(m.config.IpmitoolPath) p, err := exec.LookPath(m.config.IpmitoolPath)
if err == nil { if err == nil {
command := exec.Command(p) m.ipmitool = p
err := command.Run()
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Failed to execute %s: %v", p, err.Error()))
m.ipmitool = ""
} else {
m.ipmitool = p
}
} }
p, err = exec.LookPath(m.config.IpmisensorsPath) p, err = exec.LookPath(m.config.IpmisensorsPath)
if err == nil { if err == nil {
command := exec.Command(p) m.ipmisensors = p
err := command.Run()
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Failed to execute %s: %v", p, err.Error()))
m.ipmisensors = ""
} else {
m.ipmisensors = p
}
} }
if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 { if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
return errors.New("no usable IPMI reader found") return errors.New("no IPMI reader found")
} }
m.init = true m.init = true
return nil return nil
} }
func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) { func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
// Setup ipmitool command // Setup ipmitool command
command := exec.Command(cmd, "sensor") command := exec.Command(cmd, "sensor")
@ -121,7 +105,7 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
unit = "Watts" unit = "Watts"
} }
y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now()) y, err := lp.New(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", unit) y.AddMeta("unit", unit)
output <- y output <- y
@ -135,13 +119,13 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
cclog.ComponentError( cclog.ComponentError(
m.name, m.name,
fmt.Sprintf("readIpmiTool(): Failed to wait for the end of command \"%s\": %v\n", command.String(), err), fmt.Sprintf("readIpmiTool(): Failed to wait for the end of command \"%s\": %v\n", command.String(), err),
fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", string(errMsg)),
) )
cclog.ComponentError(m.name, fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", strings.TrimSpace(string(errMsg))))
return return
} }
} }
func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) { func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
command := exec.Command(cmd, "--comma-separated-output", "--sdr-cache-recreate") command := exec.Command(cmd, "--comma-separated-output", "--sdr-cache-recreate")
command.Wait() command.Wait()
@ -159,7 +143,7 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
v, err := strconv.ParseFloat(lv[3], 64) v, err := strconv.ParseFloat(lv[3], 64)
if err == nil { if err == nil {
name := strings.ToLower(strings.Replace(lv[1], " ", "_", -1)) name := strings.ToLower(strings.Replace(lv[1], " ", "_", -1))
y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now()) y, err := lp.New(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
if err == nil { if err == nil {
if len(lv) > 4 { if len(lv) > 4 {
y.AddMeta("unit", lv[4]) y.AddMeta("unit", lv[4])
@ -171,7 +155,7 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
} }
} }
func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Check if already initialized // Check if already initialized
if !m.init { if !m.init {

View File

@ -1,13 +1,3 @@
<!--
---
title: IPMI Metric collector
description: Collect metrics using ipmitool or ipmi-sensors
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/ipmi.md
---
-->
## `ipmistat` collector ## `ipmistat` collector

View File

@ -24,9 +24,9 @@ import (
"time" "time"
"unsafe" "unsafe"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage"
agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator" agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology" topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
"github.com/NVIDIA/go-nvml/pkg/dl" "github.com/NVIDIA/go-nvml/pkg/dl"
"github.com/fsnotify/fsnotify" "github.com/fsnotify/fsnotify"
@ -43,7 +43,7 @@ const (
type LikwidCollectorMetricConfig struct { type LikwidCollectorMetricConfig struct {
Name string `json:"name"` // Name of the metric Name string `json:"name"` // Name of the metric
Calc string `json:"calc"` // Calculation for the metric using Calc string `json:"calc"` // Calculation for the metric using
Type string `json:"type"` // Metric type (aka node, socket, hwthread, ...) Type string `json:"type"` // Metric type (aka node, socket, cpu, ...)
Publish bool `json:"publish"` Publish bool `json:"publish"`
SendCoreTotalVal bool `json:"send_core_total_values,omitempty"` SendCoreTotalVal bool `json:"send_core_total_values,omitempty"`
SendSocketTotalVal bool `json:"send_socket_total_values,omitempty"` SendSocketTotalVal bool `json:"send_socket_total_values,omitempty"`
@ -91,8 +91,6 @@ type LikwidCollector struct {
running bool running bool
initialized bool initialized bool
needs_reinit bool needs_reinit bool
myuid int
lock_err_once bool
likwidGroups map[C.int]LikwidEventsetConfig likwidGroups map[C.int]LikwidEventsetConfig
lock sync.Mutex lock sync.Mutex
measureThread thread.Thread measureThread thread.Thread
@ -190,8 +188,12 @@ func getBaseFreq() float64 {
} }
if math.IsNaN(freq) { if math.IsNaN(freq) {
C.timer_init() C.power_init(0)
freq = float64(C.timer_getCycleClock()) / 1e3 info := C.get_powerInfo()
if float64(info.baseFrequency) != 0 {
freq = float64(info.baseFrequency)
}
C.power_finalize()
} }
return freq * 1e3 return freq * 1e3
} }
@ -202,7 +204,6 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
m.initialized = false m.initialized = false
m.needs_reinit = true m.needs_reinit = true
m.running = false m.running = false
m.myuid = os.Getuid()
m.config.AccessMode = LIKWID_DEF_ACCESSMODE m.config.AccessMode = LIKWID_DEF_ACCESSMODE
m.config.LibraryPath = LIKWID_LIB_NAME m.config.LibraryPath = LIKWID_LIB_NAME
m.config.LockfilePath = LIKWID_DEF_LOCKFILE m.config.LockfilePath = LIKWID_DEF_LOCKFILE
@ -373,41 +374,19 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
} }
defer watcher.Close() defer watcher.Close()
if len(m.config.LockfilePath) > 0 { if len(m.config.LockfilePath) > 0 {
// Check if the lock file exists
info, err := os.Stat(m.config.LockfilePath) info, err := os.Stat(m.config.LockfilePath)
if os.IsNotExist(err) {
// Create the lock file if it does not exist
file, createErr := os.Create(m.config.LockfilePath)
if createErr != nil {
return true, fmt.Errorf("failed to create lock file: %v", createErr)
}
file.Close()
info, err = os.Stat(m.config.LockfilePath) // Recheck the file after creation
}
if err != nil { if err != nil {
return true, err return true, err
} }
// Check file ownership
uid := info.Sys().(*syscall.Stat_t).Uid uid := info.Sys().(*syscall.Stat_t).Uid
if uid != uint32(m.myuid) { if uid != uint32(os.Getuid()) {
usr, err := user.LookupId(fmt.Sprint(uid)) usr, err := user.LookupId(fmt.Sprint(uid))
if err == nil { if err == nil {
err = fmt.Errorf("access to performance counters locked by %s", usr.Username) return true, fmt.Errorf("Access to performance counters locked by %s", usr.Username)
} else { } else {
err = fmt.Errorf("access to performance counters locked by %d", uid) return true, fmt.Errorf("Access to performance counters locked by %d", uid)
} }
// delete error if we already returned the error once.
if !m.lock_err_once {
m.lock_err_once = true
} else {
err = nil
}
return true, err
} }
// reset lock_err_once
m.lock_err_once = false
// Add the lock file to the watcher
err = watcher.Add(m.config.LockfilePath) err = watcher.Add(m.config.LockfilePath)
if err != nil { if err != nil {
cclog.ComponentError(m.name, err.Error()) cclog.ComponentError(m.name, err.Error())
@ -445,7 +424,9 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
gid = C.perfmon_addEventSet(evset.estr) gid = C.perfmon_addEventSet(evset.estr)
} }
if gid < 0 { if gid < 0 {
return true, fmt.Errorf("failed to add events %s, id %d, error %d", evset.go_estr, evidx, gid) return true, fmt.Errorf("failed to add events %s, error %d", evset.go_estr, gid)
} else {
evset.gid = gid
} }
// Setup all performance monitoring counters of an eventSet // Setup all performance monitoring counters of an eventSet
@ -556,12 +537,11 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
} }
// Get all measurement results for an event set, derive the metric values out of the measurement results and send it // Get all measurement results for an event set, derive the metric values out of the measurement results and send it
func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMessage) error { func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
invClock := float64(1.0 / m.basefreq) invClock := float64(1.0 / m.basefreq)
for _, tid := range m.cpu2tid { for _, tid := range m.cpu2tid {
evset.results[tid]["inverseClock"] = invClock evset.results[tid]["inverseClock"] = invClock
evset.results[tid]["gotime"] = interval.Seconds()
} }
// Go over the event set metrics, derive the value out of the event:counter values and send it // Go over the event set metrics, derive the value out of the event:counter values and send it
@ -590,7 +570,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
if !math.IsNaN(value) && metric.Publish { if !math.IsNaN(value) && metric.Publish {
fields := map[string]interface{}{"value": value} fields := map[string]interface{}{"value": value}
y, err := y, err :=
lp.NewMessage( lp.New(
metric.Name, metric.Name,
map[string]string{ map[string]string{
"type": metric.Type, "type": metric.Type,
@ -627,7 +607,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
for coreID, value := range totalCoreValues { for coreID, value := range totalCoreValues {
y, err := y, err :=
lp.NewMessage( lp.New(
metric.Name, metric.Name,
map[string]string{ map[string]string{
"type": "core", "type": "core",
@ -664,7 +644,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
for socketID, value := range totalSocketValues { for socketID, value := range totalSocketValues {
y, err := y, err :=
lp.NewMessage( lp.New(
metric.Name, metric.Name,
map[string]string{ map[string]string{
"type": "socket", "type": "socket",
@ -699,7 +679,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
} }
y, err := y, err :=
lp.NewMessage( lp.New(
metric.Name, metric.Name,
map[string]string{ map[string]string{
"type": "node", "type": "node",
@ -724,7 +704,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
} }
// Go over the global metrics, derive the value out of the event sets' metric values and send it // Go over the global metrics, derive the value out of the event sets' metric values and send it
func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, interval time.Duration, output chan lp.CCMessage) error { func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
// Send all metrics with same time stamp // Send all metrics with same time stamp
// This function does only computiation, counter measurement is done before // This function does only computiation, counter measurement is done before
now := time.Now() now := time.Now()
@ -745,7 +725,6 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
params[mname] = mres params[mname] = mres
} }
} }
params["gotime"] = interval.Seconds()
// Evaluate the metric // Evaluate the metric
value, err := agg.EvalFloat64Condition(metric.Calc, params) value, err := agg.EvalFloat64Condition(metric.Calc, params)
if err != nil { if err != nil {
@ -759,7 +738,7 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
if !math.IsNaN(value) { if !math.IsNaN(value) {
if metric.Publish { if metric.Publish {
y, err := y, err :=
lp.NewMessage( lp.New(
metric.Name, metric.Name,
map[string]string{ map[string]string{
"type": metric.Type, "type": metric.Type,
@ -787,7 +766,7 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
return nil return nil
} }
func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMessage) { func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMetric) {
var err error = nil var err error = nil
groups := make([]LikwidEventsetConfig, 0) groups := make([]LikwidEventsetConfig, 0)
@ -807,17 +786,15 @@ func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMe
if !skip { if !skip {
// read measurements and derive event set metrics // read measurements and derive event set metrics
m.calcEventsetMetrics(e, interval, output) m.calcEventsetMetrics(e, interval, output)
groups = append(groups, e)
} }
groups = append(groups, e)
} }
if len(groups) > 0 { // calculate global metrics
// calculate global metrics m.calcGlobalMetrics(groups, interval, output)
m.calcGlobalMetrics(groups, interval, output)
}
} }
// main read function taking multiple measurement rounds, each 'interval' seconds long // main read function taking multiple measurement rounds, each 'interval' seconds long
func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }

View File

@ -1,13 +1,3 @@
<!--
---
title: LIKWID collector
description: Collect hardware performance events and metrics using LIKWID
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/likwid.md
---
-->
## `likwid` collector ## `likwid` collector
@ -25,7 +15,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
{ {
"events" : { "events" : {
"COUNTER0": "EVENT0", "COUNTER0": "EVENT0",
"COUNTER1": "EVENT1" "COUNTER1": "EVENT1",
}, },
"metrics" : [ "metrics" : [
{ {
@ -37,7 +27,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
} }
] ]
} }
], ]
"globalmetrics" : [ "globalmetrics" : [
{ {
"name": "global_sum", "name": "global_sum",
@ -142,9 +132,6 @@ In some cases LIKWID returns `0.0` for some events that are further used in proc
One might think this does not happen often but often used metrics in the world of performance engineering like Instructions-per-Cycle (IPC) or more frequently the actual CPU clock are derived with events like `CPU_CLK_UNHALTED_CORE` (Intel) which do not increment in halted state (as the name implies). In there are different power management systems in a chip which can cause a hardware thread to go in such a state. Moreover, if no cycles are executed by the core, also many other events are not incremented as well (like `INSTR_RETIRED_ANY` for retired instructions and part of IPC). One might think this does not happen often but often used metrics in the world of performance engineering like Instructions-per-Cycle (IPC) or more frequently the actual CPU clock are derived with events like `CPU_CLK_UNHALTED_CORE` (Intel) which do not increment in halted state (as the name implies). In there are different power management systems in a chip which can cause a hardware thread to go in such a state. Moreover, if no cycles are executed by the core, also many other events are not incremented as well (like `INSTR_RETIRED_ANY` for retired instructions and part of IPC).
### `lockfile_path` option
LIKWID can be configured with a lock file with which the access to the performance monitoring registers can be disabled (only the owner of the lock file is allowed to access the registers). When the `lockfile_path` option is set, the collector subscribes to changes to this file to stop monitoring if the owner of the lock file changes. This feature is useful when users should be able to perform own hardware performance counter measurements through LIKWID or any other tool.
### `send_*_total values` option ### `send_*_total values` option
- `send_core_total_values`: Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU core. - `send_core_total_values`: Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU core.

View File

@ -8,16 +8,18 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
//
// LoadavgCollector collects: // LoadavgCollector collects:
// * load average of last 1, 5 & 15 minutes // * load average of last 1, 5 & 15 minutes
// * number of processes currently runnable // * number of processes currently runnable
// * total number of processes in system // * total number of processes in system
// //
// See: https://www.kernel.org/doc/html/latest/filesystems/proc.html // See: https://www.kernel.org/doc/html/latest/filesystems/proc.html
//
const LOADAVGFILE = "/proc/loadavg" const LOADAVGFILE = "/proc/loadavg"
type LoadavgCollector struct { type LoadavgCollector struct {
@ -66,15 +68,17 @@ func (m *LoadavgCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
buffer, err := os.ReadFile(LOADAVGFILE) buffer, err := os.ReadFile(LOADAVGFILE)
if err != nil { if err != nil {
cclog.ComponentError( if err != nil {
m.name, cclog.ComponentError(
fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err)) m.name,
fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
}
return return
} }
now := time.Now() now := time.Now()
@ -92,7 +96,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
if m.load_skips[i] { if m.load_skips[i] {
continue continue
} }
y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now) y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
if err == nil { if err == nil {
output <- y output <- y
} }
@ -111,7 +115,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
if m.proc_skips[i] { if m.proc_skips[i] {
continue continue
} }
y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now) y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
if err == nil { if err == nil {
output <- y output <- y
} }

View File

@ -1,14 +1,3 @@
<!--
---
title: Load average metric collector
description: Collect metrics from `/proc/loadavg`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/loadavg.md
---
-->
## `loadavg` collector ## `loadavg` collector

View File

@ -10,8 +10,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
const LUSTRE_SYSFS = `/sys/fs/lustre` const LUSTRE_SYSFS = `/sys/fs/lustre`
@ -377,7 +377,7 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -388,7 +388,7 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage)
for _, def := range m.definitions { for _, def := range m.definitions {
var use_x int64 var use_x int64
var err error var err error
var y lp.CCMessage var y lp.CCMetric
x, err := getMetricData(data, def.lineprefix, def.lineoffset) x, err := getMetricData(data, def.lineprefix, def.lineoffset)
if err == nil { if err == nil {
use_x = x use_x = x
@ -399,19 +399,19 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage)
switch def.calc { switch def.calc {
case "none": case "none":
value = use_x value = use_x
y, err = lp.NewMessage(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now()) y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
case "difference": case "difference":
value = use_x - devData[def.name] value = use_x - devData[def.name]
if value.(int64) < 0 { if value.(int64) < 0 {
value = 0 value = 0
} }
y, err = lp.NewMessage(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now()) y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
case "derivative": case "derivative":
value = float64(use_x-devData[def.name]) / tdiff.Seconds() value = float64(use_x-devData[def.name]) / tdiff.Seconds()
if value.(float64) < 0 { if value.(float64) < 0 {
value = 0 value = 0
} }
y, err = lp.NewMessage(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now()) y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
} }
if err == nil { if err == nil {
y.AddTag("device", device) y.AddTag("device", device)

View File

@ -1,14 +1,3 @@
<!--
---
title: Lustre filesystem metric collector
description: Collect metrics for Lustre filesystems
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/lustre.md
---
-->
## `lustrestat` collector ## `lustrestat` collector
@ -54,4 +43,4 @@ Metrics:
* `lustre_statfs_diff` (if `send_diff_values == true`) * `lustre_statfs_diff` (if `send_diff_values == true`)
* `lustre_inode_permission_diff` (if `send_diff_values == true`) * `lustre_inode_permission_diff` (if `send_diff_values == true`)
This collector adds an `device` tag. This collector adds an `device` tag.

View File

@ -12,8 +12,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
const MEMSTATFILE = "/proc/meminfo" const MEMSTATFILE = "/proc/meminfo"
@ -159,7 +159,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
return err return err
} }
func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -175,7 +175,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage
} }
} }
y, err := lp.NewMessage(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now()) y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
if err == nil { if err == nil {
if len(unit) > 0 { if len(unit) > 0 {
y.AddMeta("unit", unit) y.AddMeta("unit", unit)
@ -208,7 +208,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage
} }
} }
} }
y, err := lp.NewMessage("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now()) y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
if err == nil { if err == nil {
if len(unit) > 0 { if len(unit) > 0 {
y.AddMeta("unit", unit) y.AddMeta("unit", unit)

View File

@ -1,14 +1,3 @@
<!--
---
title: Memory statistics metric collector
description: Collect metrics from `/proc/meminfo`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/memstat.md
---
-->
## `memstat` collector ## `memstat` collector

View File

@ -5,7 +5,7 @@ import (
"fmt" "fmt"
"time" "time"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
type MetricCollector interface { type MetricCollector interface {
@ -13,8 +13,8 @@ type MetricCollector interface {
Init(config json.RawMessage) error // Initialize metric collector Init(config json.RawMessage) error // Initialize metric collector
Initialized() bool // Is metric collector initialized? Initialized() bool // Is metric collector initialized?
Parallel() bool Parallel() bool
Read(duration time.Duration, output chan lp.CCMessage) // Read metrics from metric collector Read(duration time.Duration, output chan lp.CCMetric) // Read metrics from metric collector
Close() // Close / finish metric collector Close() // Close / finish metric collector
} }
type metricCollector struct { type metricCollector struct {

View File

@ -9,17 +9,16 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
const NETSTATFILE = "/proc/net/dev" const NETSTATFILE = "/proc/net/dev"
type NetstatCollectorConfig struct { type NetstatCollectorConfig struct {
IncludeDevices []string `json:"include_devices"` IncludeDevices []string `json:"include_devices"`
SendAbsoluteValues bool `json:"send_abs_values"` SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"` SendDerivedValues bool `json:"send_derived_values"`
InterfaceAliases map[string][]string `json:"interface_aliases,omitempty"`
} }
type NetstatCollectorMetric struct { type NetstatCollectorMetric struct {
@ -33,26 +32,9 @@ type NetstatCollectorMetric struct {
type NetstatCollector struct { type NetstatCollector struct {
metricCollector metricCollector
config NetstatCollectorConfig config NetstatCollectorConfig
aliasToCanonical map[string]string matches map[string][]NetstatCollectorMetric
matches map[string][]NetstatCollectorMetric lastTimestamp time.Time
lastTimestamp time.Time
}
func (m *NetstatCollector) buildAliasMapping() {
m.aliasToCanonical = make(map[string]string)
for canon, aliases := range m.config.InterfaceAliases {
for _, alias := range aliases {
m.aliasToCanonical[alias] = canon
}
}
}
func getCanonicalName(raw string, aliasToCanonical map[string]string) string {
if canon, ok := aliasToCanonical[raw]; ok {
return canon
}
return raw
} }
func (m *NetstatCollector) Init(config json.RawMessage) error { func (m *NetstatCollector) Init(config json.RawMessage) error {
@ -95,8 +77,6 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
} }
} }
m.buildAliasMapping()
// Check access to net statistic file // Check access to net statistic file
file, err := os.Open(NETSTATFILE) file, err := os.Open(NETSTATFILE)
if err != nil { if err != nil {
@ -117,20 +97,18 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
// Split line into fields // Split line into fields
f := strings.Fields(l) f := strings.Fields(l)
// Get raw and canonical names // Get net device entry
raw := strings.Trim(f[0], ": ") dev := strings.Trim(f[0], ": ")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Check if device is a included device // Check if device is a included device
if _, ok := stringArrayContains(m.config.IncludeDevices, canonical); ok { if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
// Tag will contain original device name (raw). tags := map[string]string{"stype": "network", "stype-id": dev, "type": "node"}
tags := map[string]string{"stype": "network", "stype-id": raw, "type": "node"}
meta_unit_byte := map[string]string{"source": m.name, "group": "Network", "unit": "bytes"} meta_unit_byte := map[string]string{"source": m.name, "group": "Network", "unit": "bytes"}
meta_unit_byte_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "bytes/sec"} meta_unit_byte_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "bytes/sec"}
meta_unit_pkts := map[string]string{"source": m.name, "group": "Network", "unit": "packets"} meta_unit_pkts := map[string]string{"source": m.name, "group": "Network", "unit": "packets"}
meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"} meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"}
m.matches[canonical] = []NetstatCollectorMetric{ m.matches[dev] = []NetstatCollectorMetric{
{ {
name: "net_bytes_in", name: "net_bytes_in",
index: fieldReceiveBytes, index: fieldReceiveBytes,
@ -165,6 +143,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
}, },
} }
} }
} }
if len(m.matches) == 0 { if len(m.matches) == 0 {
@ -174,7 +153,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -185,7 +164,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
// Save current timestamp // Save current timestamp
m.lastTimestamp = now m.lastTimestamp = now
file, err := os.Open(NETSTATFILE) file, err := os.Open(string(NETSTATFILE))
if err != nil { if err != nil {
cclog.ComponentError(m.name, err.Error()) cclog.ComponentError(m.name, err.Error())
return return
@ -204,12 +183,11 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
// Split line into fields // Split line into fields
f := strings.Fields(l) f := strings.Fields(l)
// Get raw and canonical names // Get net device entry
raw := strings.Trim(f[0], ":") dev := strings.Trim(f[0], ":")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Check if device is a included device // Check if device is a included device
if devmetrics, ok := m.matches[canonical]; ok { if devmetrics, ok := m.matches[dev]; ok {
for i := range devmetrics { for i := range devmetrics {
metric := &devmetrics[i] metric := &devmetrics[i]
@ -219,14 +197,14 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
continue continue
} }
if m.config.SendAbsoluteValues { if m.config.SendAbsoluteValues {
if y, err := lp.NewMessage(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil { if y, err := lp.New(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
output <- y output <- y
} }
} }
if m.config.SendDerivedValues { if m.config.SendDerivedValues {
if metric.lastValue >= 0 { if metric.lastValue >= 0 {
rate := float64(v-metric.lastValue) / timeDiff rate := float64(v-metric.lastValue) / timeDiff
if y, err := lp.NewMessage(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil { if y, err := lp.New(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
output <- y output <- y
} }
} }

View File

@ -1,32 +1,17 @@
<!--
---
title: Network device metric collector
description: Collect metrics for network devices through procfs
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/netstat.md
---
-->
## `netstat` collector ## `netstat` collector
```json ```json
"netstat": { "netstat": {
"include_devices": [ "include_devices": [
"eth0", "eth0"
"eno1"
], ],
"send_abs_values": true, "send_abs_values" : true,
"send_derived_values": true, "send_derived_values" : true
"interface_aliases": {
"eno1": ["eno1np0", "eno1_alt"],
"eth0": ["eth0_alias"]
}
} }
``` ```
The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list. Optionally, you can define an interface_aliases mapping. For each canonical device (as listed in include_devices), you may provide an array of aliases that may be reported by the system. When an alias is detected, it is preferred for matching, while the output tag stype-id always shows the actual system-reported name. The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list.
Metrics: Metrics:
* `net_bytes_in` (`unit=bytes`) * `net_bytes_in` (`unit=bytes`)
@ -39,3 +24,4 @@ Metrics:
* `net_pkts_out_bw` (`unit=packets/sec` if `send_derived_values == true`) * `net_pkts_out_bw` (`unit=packets/sec` if `send_derived_values == true`)
The device name is added as tag `stype=network,stype-id=<device>`. The device name is added as tag `stype=network,stype-id=<device>`.

View File

@ -1,14 +1,3 @@
<!--
---
title: NFS network filesystem (v3) metric collector
description: Collect metrics for NFS network filesystems in version 3
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/nfs3.md
---
-->
## `nfs3stat` collector ## `nfs3stat` collector

View File

@ -1,14 +1,3 @@
<!--
---
title: NFS network filesystem (v4) metric collector
description: Collect metrics for NFS network filesystems in version 4
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/nfs4.md
---
-->
## `nfs4stat` collector ## `nfs4stat` collector

View File

@ -11,7 +11,7 @@ import (
"strings" "strings"
"time" "time"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// First part contains the code for the general NfsCollector. // First part contains the code for the general NfsCollector.
@ -118,7 +118,7 @@ func (m *nfsCollector) MainInit(config json.RawMessage) error {
return nil return nil
} }
func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -140,7 +140,7 @@ func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue continue
} }
value := data.current - data.last value := data.current - data.last
y, err := lp.NewMessage(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
y.AddMeta("version", m.version) y.AddMeta("version", m.version)
output <- y output <- y

View File

@ -9,8 +9,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// These are the fields we read from the JSON configuration // These are the fields we read from the JSON configuration
@ -18,20 +18,17 @@ type NfsIOStatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"` ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"` ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
UseServerAddressAsSType bool `json:"use_server_as_stype,omitempty"` UseServerAddressAsSType bool `json:"use_server_as_stype,omitempty"`
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
} }
// This contains all variables we need during execution and the variables // This contains all variables we need during execution and the variables
// defined by metricCollector (name, init, ...) // defined by metricCollector (name, init, ...)
type NfsIOStatCollector struct { type NfsIOStatCollector struct {
metricCollector metricCollector
config NfsIOStatCollectorConfig // the configuration structure config NfsIOStatCollectorConfig // the configuration structure
meta map[string]string // default meta information meta map[string]string // default meta information
tags map[string]string // default tags tags map[string]string // default tags
data map[string]map[string]int64 // data storage for difference calculation data map[string]map[string]int64 // data storage for difference calculation
key string // which device info should be used as subtype ID? 'server' or 'mntpoint' key string // which device info should be used as subtype ID? 'server' or 'mntpoint', see NfsIOStatCollectorConfig.UseServerAddressAsSType
lastTimestamp time.Time
} }
var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`) var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
@ -84,6 +81,7 @@ func (m *NfsIOStatCollector) readNfsiostats() map[string]map[string]int64 {
data[current[m.key]][name] = val data[current[m.key]][name] = val
} }
} }
} }
current = nil current = nil
} }
@ -100,9 +98,6 @@ func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
m.meta = map[string]string{"source": m.name, "group": "NFS", "unit": "bytes"} m.meta = map[string]string{"source": m.name, "group": "NFS", "unit": "bytes"}
m.tags = map[string]string{"type": "node"} m.tags = map[string]string{"type": "node"}
m.config.UseServerAddressAsSType = false m.config.UseServerAddressAsSType = false
// Set default configuration
m.config.SendAbsoluteValues = true
m.config.SendDerivedValues = false
if len(config) > 0 { if len(config) > 0 {
err = json.Unmarshal(config, &m.config) err = json.Unmarshal(config, &m.config)
if err != nil { if err != nil {
@ -115,15 +110,12 @@ func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
m.key = "server" m.key = "server"
} }
m.data = m.readNfsiostats() m.data = m.readNfsiostats()
m.lastTimestamp = time.Now()
m.init = true m.init = true
return err return err
} }
func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
now := time.Now() timestamp := time.Now()
timeDiff := now.Sub(m.lastTimestamp).Seconds()
m.lastTimestamp = now
// Get the current values for all mountpoints // Get the current values for all mountpoints
newdata := m.readNfsiostats() newdata := m.readNfsiostats()
@ -131,30 +123,21 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
for mntpoint, values := range newdata { for mntpoint, values := range newdata {
// Was the mount point already present in the last iteration // Was the mount point already present in the last iteration
if old, ok := m.data[mntpoint]; ok { if old, ok := m.data[mntpoint]; ok {
for name, newVal := range values { // Calculate the difference of old and new values
if m.config.SendAbsoluteValues { for i := range values {
msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s", name), m.tags, m.meta, map[string]interface{}{"value": newVal}, now) x := values[i] - old[i]
if err == nil { y, err := lp.New(fmt.Sprintf("nfsio_%s", i), m.tags, m.meta, map[string]interface{}{"value": x}, timestamp)
msg.AddTag("stype", "filesystem") if err == nil {
msg.AddTag("stype-id", mntpoint) if strings.HasPrefix(i, "page") {
output <- msg y.AddMeta("unit", "4K_Pages")
} }
y.AddTag("stype", "filesystem")
y.AddTag("stype-id", mntpoint)
// Send it to output channel
output <- y
} }
if m.config.SendDerivedValues { // Update old to the new value for the next iteration
rate := float64(newVal-old[name]) / timeDiff old[i] = values[i]
msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s_bw", name), m.tags, m.meta, map[string]interface{}{"value": rate}, now)
if err == nil {
if strings.HasPrefix(name, "page") {
msg.AddMeta("unit", "4K_pages/s")
} else {
msg.AddMeta("unit", "bytes/sec")
}
msg.AddTag("stype", "filesystem")
msg.AddTag("stype-id", mntpoint)
output <- msg
}
}
old[name] = newVal
} }
} else { } else {
// First time we see this mount point, store all values // First time we see this mount point, store all values
@ -171,9 +154,10 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
} }
} }
if !found { if !found {
delete(m.data, mntpoint) m.data[mntpoint] = nil
} }
} }
} }
func (m *NfsIOStatCollector) Close() { func (m *NfsIOStatCollector) Close() {

View File

@ -1,31 +1,18 @@
<!--
---
title: NFS network filesystem metrics from procfs
description: Collect NFS network filesystem metrics for mounts from `/proc/self/mountstats`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/nfsio.md
---
-->
## `nfsiostat` collector ## `nfsiostat` collector
```json ```json
"nfsiostat": { "nfsiostat": {
"exclude_metrics": [ "exclude_metrics": [
"oread", "pageread" "nfsio_oread"
], ],
"exclude_filesystems": [ "exclude_filesystems" : [
"/mnt" "/mnt",
], ],
"use_server_as_stype": false, "use_server_as_stype": false
"send_abs_values": false,
"send_derived_values": true
} }
``` ```
The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink. **Note:** When excluding metrics, you must provide the base metric name (e.g. pageread) without the nfsio_ prefix. This exclusion applies to both absolute and derived values. The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink.
Metrics: Metrics:
* `nfsio_nread`: Bytes transferred by normal `read()` calls * `nfsio_nread`: Bytes transferred by normal `read()` calls
@ -37,9 +24,4 @@ Metrics:
* `nfsio_nfsread`: Bytes transferred for reading from the server * `nfsio_nfsread`: Bytes transferred for reading from the server
* `nfsio_nfswrite`: Pages transferred by writing to the server * `nfsio_nfswrite`: Pages transferred by writing to the server
For each of these, if derived values are enabled, an additional metric is sent with the `_bw` suffix, which represents the rate: The `nfsiostat` collector adds the mountpoint to the tags as `stype=filesystem,stype-id=<mountpoint>`. If the server address should be used instead of the mountpoint, use the `use_server_as_stype` config setting.
* For normal byte metrics: `unit=bytes/sec`
* For page metrics: `unit=4K_pages/s`
The `nfsiostat` collector adds the mountpoint to the tags as `stype=filesystem,stype-id=<mountpoint>`. If the server address should be used instead of the mountpoint, use the `use_server_as_stype` config setting.

View File

@ -10,15 +10,10 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
type NUMAStatsCollectorConfig struct {
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
}
// Non-Uniform Memory Access (NUMA) policy hit/miss statistics // Non-Uniform Memory Access (NUMA) policy hit/miss statistics
// //
// numa_hit: // numa_hit:
@ -52,16 +47,13 @@ type NUMAStatsCollectorConfig struct {
// //
// See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html // See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
type NUMAStatsCollectorTopolgy struct { type NUMAStatsCollectorTopolgy struct {
file string file string
tagSet map[string]string tagSet map[string]string
previousValues map[string]int64
} }
type NUMAStatsCollector struct { type NUMAStatsCollector struct {
metricCollector metricCollector
topology []NUMAStatsCollectorTopolgy topology []NUMAStatsCollectorTopolgy
config NUMAStatsCollectorConfig
lastTimestamp time.Time
} }
func (m *NUMAStatsCollector) Init(config json.RawMessage) error { func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
@ -94,9 +86,8 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
file := filepath.Join(dir, "numastat") file := filepath.Join(dir, "numastat")
m.topology = append(m.topology, m.topology = append(m.topology,
NUMAStatsCollectorTopolgy{ NUMAStatsCollectorTopolgy{
file: file, file: file,
tagSet: map[string]string{"memoryDomain": node}, tagSet: map[string]string{"memoryDomain": node},
previousValues: make(map[string]int64),
}) })
} }
@ -106,32 +97,28 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
now := time.Now()
timeDiff := now.Sub(m.lastTimestamp).Seconds()
m.lastTimestamp = now
for i := range m.topology { for i := range m.topology {
// Loop for all NUMA domains // Loop for all NUMA domains
t := &m.topology[i] t := &m.topology[i]
now := time.Now()
file, err := os.Open(t.file) file, err := os.Open(t.file)
if err != nil { if err != nil {
cclog.ComponentError( cclog.ComponentError(
m.name, m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", t.file, err)) fmt.Sprintf("Read(): Failed to open file '%s': %v", t.file, err))
continue return
} }
scanner := bufio.NewScanner(file) scanner := bufio.NewScanner(file)
// Read line by line // Read line by line
for scanner.Scan() { for scanner.Scan() {
line := scanner.Text() split := strings.Fields(scanner.Text())
split := strings.Fields(line)
if len(split) != 2 { if len(split) != 2 {
continue continue
} }
@ -143,38 +130,18 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessa
fmt.Sprintf("Read(): Failed to convert %s='%s' to int64: %v", key, split[1], err)) fmt.Sprintf("Read(): Failed to convert %s='%s' to int64: %v", key, split[1], err))
continue continue
} }
y, err := lp.New(
if m.config.SendAbsoluteValues { "numastats_"+key,
msg, err := lp.NewMessage( t.tagSet,
"numastats_"+key, m.meta,
t.tagSet, map[string]interface{}{"value": value},
m.meta, now,
map[string]interface{}{"value": value}, )
now, if err == nil {
) output <- y
if err == nil {
output <- msg
}
}
if m.config.SendDerivedValues {
prev, ok := t.previousValues[key]
if ok {
rate := float64(value-prev) / timeDiff
msg, err := lp.NewMessage(
"numastats_"+key+"_rate",
t.tagSet,
m.meta,
map[string]interface{}{"value": rate},
now,
)
if err == nil {
output <- msg
}
}
t.previousValues[key] = value
} }
} }
file.Close() file.Close()
} }
} }

View File

@ -1,21 +1,8 @@
<!--
---
title: NUMAStat collector
description: Collect infos about NUMA domains
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/numastat.md
---
-->
## `numastat` collector ## `numastat` collector
```json ```json
"numastats": { "numastats": {}
"send_abs_values" : true,
"send_derived_values" : true
}
``` ```
The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: <https://www.kernel.org/doc/html/latest/admin-guide/numastat.html> The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: <https://www.kernel.org/doc/html/latest/admin-guide/numastat.html>
@ -28,9 +15,3 @@ Metrics:
* `numastats_local_node`: A process ran on this node's CPU, and got memory from this node. * `numastats_local_node`: A process ran on this node's CPU, and got memory from this node.
* `numastats_other_node`: A process ran on a different node's CPU, and got memory from this node. * `numastats_other_node`: A process ran on a different node's CPU, and got memory from this node.
* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded. * `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.
* `numastats_numa_hit_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_numa_miss_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_numa_foreign_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_local_node_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_other_node_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_interleave_hit_rate` (if `send_derived_values == true`): Derived rate value per second.

View File

@ -8,8 +8,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/NVIDIA/go-nvml/pkg/nvml" "github.com/NVIDIA/go-nvml/pkg/nvml"
) )
@ -206,7 +206,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_fb_mem_total"] || !device.excludeMetrics["nv_fb_mem_used"] || !device.excludeMetrics["nv_fb_mem_reserved"] { if !device.excludeMetrics["nv_fb_mem_total"] || !device.excludeMetrics["nv_fb_mem_used"] || !device.excludeMetrics["nv_fb_mem_reserved"] {
var total uint64 var total uint64
var used uint64 var used uint64
@ -222,7 +222,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
if !device.excludeMetrics["nv_fb_mem_total"] { if !device.excludeMetrics["nv_fb_mem_total"] {
t := float64(total) / (1024 * 1024) t := float64(total) / (1024 * 1024)
y, err := lp.NewMessage("nv_fb_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_fb_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MByte") y.AddMeta("unit", "MByte")
output <- y output <- y
@ -231,7 +231,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
if !device.excludeMetrics["nv_fb_mem_used"] { if !device.excludeMetrics["nv_fb_mem_used"] {
f := float64(used) / (1024 * 1024) f := float64(used) / (1024 * 1024)
y, err := lp.NewMessage("nv_fb_mem_used", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now()) y, err := lp.New("nv_fb_mem_used", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MByte") y.AddMeta("unit", "MByte")
output <- y output <- y
@ -240,7 +240,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
if v2 && !device.excludeMetrics["nv_fb_mem_reserved"] { if v2 && !device.excludeMetrics["nv_fb_mem_reserved"] {
r := float64(reserved) / (1024 * 1024) r := float64(reserved) / (1024 * 1024)
y, err := lp.NewMessage("nv_fb_mem_reserved", device.tags, device.meta, map[string]interface{}{"value": r}, time.Now()) y, err := lp.New("nv_fb_mem_reserved", device.tags, device.meta, map[string]interface{}{"value": r}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MByte") y.AddMeta("unit", "MByte")
output <- y output <- y
@ -250,7 +250,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
return nil return nil
} }
func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_bar1_mem_total"] || !device.excludeMetrics["nv_bar1_mem_used"] { if !device.excludeMetrics["nv_bar1_mem_total"] || !device.excludeMetrics["nv_bar1_mem_used"] {
meminfo, ret := nvml.DeviceGetBAR1MemoryInfo(device.device) meminfo, ret := nvml.DeviceGetBAR1MemoryInfo(device.device)
if ret != nvml.SUCCESS { if ret != nvml.SUCCESS {
@ -259,7 +259,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
} }
if !device.excludeMetrics["nv_bar1_mem_total"] { if !device.excludeMetrics["nv_bar1_mem_total"] {
t := float64(meminfo.Bar1Total) / (1024 * 1024) t := float64(meminfo.Bar1Total) / (1024 * 1024)
y, err := lp.NewMessage("nv_bar1_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_bar1_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MByte") y.AddMeta("unit", "MByte")
output <- y output <- y
@ -267,7 +267,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
} }
if !device.excludeMetrics["nv_bar1_mem_used"] { if !device.excludeMetrics["nv_bar1_mem_used"] {
t := float64(meminfo.Bar1Used) / (1024 * 1024) t := float64(meminfo.Bar1Used) / (1024 * 1024)
y, err := lp.NewMessage("nv_bar1_mem_used", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_bar1_mem_used", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MByte") y.AddMeta("unit", "MByte")
output <- y output <- y
@ -277,7 +277,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
return nil return nil
} }
func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device) isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
if ret != nvml.SUCCESS { if ret != nvml.SUCCESS {
err := errors.New(nvml.ErrorString(ret)) err := errors.New(nvml.ErrorString(ret))
@ -301,14 +301,14 @@ func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) err
util, ret := nvml.DeviceGetUtilizationRates(device.device) util, ret := nvml.DeviceGetUtilizationRates(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
if !device.excludeMetrics["nv_util"] { if !device.excludeMetrics["nv_util"] {
y, err := lp.NewMessage("nv_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Gpu)}, time.Now()) y, err := lp.New("nv_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Gpu)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "%") y.AddMeta("unit", "%")
output <- y output <- y
} }
} }
if !device.excludeMetrics["nv_mem_util"] { if !device.excludeMetrics["nv_mem_util"] {
y, err := lp.NewMessage("nv_mem_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now()) y, err := lp.New("nv_mem_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "%") y.AddMeta("unit", "%")
output <- y output <- y
@ -319,7 +319,7 @@ func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) err
return nil return nil
} }
func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readTemp(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_temp"] { if !device.excludeMetrics["nv_temp"] {
// Retrieves the current temperature readings for the device, in degrees C. // Retrieves the current temperature readings for the device, in degrees C.
// //
@ -328,7 +328,7 @@ func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
// * NVML_TEMPERATURE_COUNT // * NVML_TEMPERATURE_COUNT
temp, ret := nvml.DeviceGetTemperature(device.device, nvml.TEMPERATURE_GPU) temp, ret := nvml.DeviceGetTemperature(device.device, nvml.TEMPERATURE_GPU)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_temp", device.tags, device.meta, map[string]interface{}{"value": float64(temp)}, time.Now()) y, err := lp.New("nv_temp", device.tags, device.meta, map[string]interface{}{"value": float64(temp)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "degC") y.AddMeta("unit", "degC")
output <- y output <- y
@ -338,7 +338,7 @@ func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
return nil return nil
} }
func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readFan(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_fan"] { if !device.excludeMetrics["nv_fan"] {
// Retrieves the intended operating speed of the device's fan. // Retrieves the intended operating speed of the device's fan.
// //
@ -351,7 +351,7 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
// This value may exceed 100% in certain cases. // This value may exceed 100% in certain cases.
fan, ret := nvml.DeviceGetFanSpeed(device.device) fan, ret := nvml.DeviceGetFanSpeed(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now()) y, err := lp.New("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "%") y.AddMeta("unit", "%")
output <- y output <- y
@ -361,14 +361,14 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
return nil return nil
} }
// func readFans(device NvidiaCollectorDevice, output chan lp.CCMessage) error { // func readFans(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
// if !device.excludeMetrics["nv_fan"] { // if !device.excludeMetrics["nv_fan"] {
// numFans, ret := nvml.DeviceGetNumFans(device.device) // numFans, ret := nvml.DeviceGetNumFans(device.device)
// if ret == nvml.SUCCESS { // if ret == nvml.SUCCESS {
// for i := 0; i < numFans; i++ { // for i := 0; i < numFans; i++ {
// fan, ret := nvml.DeviceGetFanSpeed_v2(device.device, i) // fan, ret := nvml.DeviceGetFanSpeed_v2(device.device, i)
// if ret == nvml.SUCCESS { // if ret == nvml.SUCCESS {
// y, err := lp.NewMessage("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now()) // y, err := lp.New("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
// if err == nil { // if err == nil {
// y.AddMeta("unit", "%") // y.AddMeta("unit", "%")
// y.AddTag("stype", "fan") // y.AddTag("stype", "fan")
@ -382,7 +382,7 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
// return nil // return nil
// } // }
func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_ecc_mode"] { if !device.excludeMetrics["nv_ecc_mode"] {
// Retrieves the current and pending ECC modes for the device. // Retrieves the current and pending ECC modes for the device.
// //
@ -393,21 +393,21 @@ func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
// The "pending" ECC mode refers to the target mode following the next reboot. // The "pending" ECC mode refers to the target mode following the next reboot.
_, ecc_pend, ret := nvml.DeviceGetEccMode(device.device) _, ecc_pend, ret := nvml.DeviceGetEccMode(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
var y lp.CCMessage var y lp.CCMetric
var err error var err error
switch ecc_pend { switch ecc_pend {
case nvml.FEATURE_DISABLED: case nvml.FEATURE_DISABLED:
y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "OFF"}, time.Now()) y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "OFF"}, time.Now())
case nvml.FEATURE_ENABLED: case nvml.FEATURE_ENABLED:
y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "ON"}, time.Now()) y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "ON"}, time.Now())
default: default:
y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "UNKNOWN"}, time.Now()) y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "UNKNOWN"}, time.Now())
} }
if err == nil { if err == nil {
output <- y output <- y
} }
} else if ret == nvml.ERROR_NOT_SUPPORTED { } else if ret == nvml.ERROR_NOT_SUPPORTED {
y, err := lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "N/A"}, time.Now()) y, err := lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "N/A"}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -416,7 +416,7 @@ func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
return nil return nil
} }
func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_perf_state"] { if !device.excludeMetrics["nv_perf_state"] {
// Retrieves the current performance state for the device. // Retrieves the current performance state for the device.
// //
@ -427,7 +427,7 @@ func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error
// 32: Unknown performance state. // 32: Unknown performance state.
pState, ret := nvml.DeviceGetPerformanceState(device.device) pState, ret := nvml.DeviceGetPerformanceState(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_perf_state", device.tags, device.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pState))}, time.Now()) y, err := lp.New("nv_perf_state", device.tags, device.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pState))}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -436,7 +436,7 @@ func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error
return nil return nil
} }
func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_power_usage"] { if !device.excludeMetrics["nv_power_usage"] {
// Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory) // Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory)
// //
@ -450,7 +450,7 @@ func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
if mode == nvml.FEATURE_ENABLED { if mode == nvml.FEATURE_ENABLED {
power, ret := nvml.DeviceGetPowerUsage(device.device) power, ret := nvml.DeviceGetPowerUsage(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_power_usage", device.tags, device.meta, map[string]interface{}{"value": float64(power) / 1000}, time.Now()) y, err := lp.New("nv_power_usage", device.tags, device.meta, map[string]interface{}{"value": float64(power) / 1000}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "watts") y.AddMeta("unit", "watts")
output <- y output <- y
@ -461,7 +461,7 @@ func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
return nil return nil
} }
func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
// Retrieves the current clock speeds for the device. // Retrieves the current clock speeds for the device.
// //
// Available clock information: // Available clock information:
@ -471,7 +471,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_graphics_clock"] { if !device.excludeMetrics["nv_graphics_clock"] {
graphicsClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_GRAPHICS) graphicsClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_GRAPHICS)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(graphicsClock)}, time.Now()) y, err := lp.New("nv_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(graphicsClock)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -482,7 +482,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_sm_clock"] { if !device.excludeMetrics["nv_sm_clock"] {
smCock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM) smCock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(smCock)}, time.Now()) y, err := lp.New("nv_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(smCock)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -493,7 +493,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_mem_clock"] { if !device.excludeMetrics["nv_mem_clock"] {
memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM) memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now()) y, err := lp.New("nv_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -503,7 +503,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_video_clock"] { if !device.excludeMetrics["nv_video_clock"] {
memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO) memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now()) y, err := lp.New("nv_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -513,7 +513,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
return nil return nil
} }
func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
// Retrieves the maximum clock speeds for the device. // Retrieves the maximum clock speeds for the device.
// //
// Available clock information: // Available clock information:
@ -528,7 +528,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_graphics_clock"] { if !device.excludeMetrics["nv_max_graphics_clock"] {
max_gclk, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_GRAPHICS) max_gclk, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_GRAPHICS)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_max_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now()) y, err := lp.New("nv_max_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -539,7 +539,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_sm_clock"] { if !device.excludeMetrics["nv_max_sm_clock"] {
maxSmClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM) maxSmClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_max_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxSmClock)}, time.Now()) y, err := lp.New("nv_max_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxSmClock)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -550,7 +550,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_mem_clock"] { if !device.excludeMetrics["nv_max_mem_clock"] {
maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM) maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_max_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now()) y, err := lp.New("nv_max_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -561,7 +561,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_video_clock"] { if !device.excludeMetrics["nv_max_video_clock"] {
maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO) maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_max_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now()) y, err := lp.New("nv_max_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "MHz") y.AddMeta("unit", "MHz")
output <- y output <- y
@ -571,7 +571,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
return nil return nil
} }
func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_ecc_uncorrected_error"] { if !device.excludeMetrics["nv_ecc_uncorrected_error"] {
// Retrieves the total ECC error counts for the device. // Retrieves the total ECC error counts for the device.
// //
@ -584,7 +584,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error
// i.e. the total set of errors across the entire device. // i.e. the total set of errors across the entire device.
ecc_db, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_UNCORRECTED, nvml.AGGREGATE_ECC) ecc_db, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_UNCORRECTED, nvml.AGGREGATE_ECC)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_ecc_uncorrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now()) y, err := lp.New("nv_ecc_uncorrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -593,7 +593,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_ecc_corrected_error"] { if !device.excludeMetrics["nv_ecc_corrected_error"] {
ecc_sb, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_CORRECTED, nvml.AGGREGATE_ECC) ecc_sb, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_CORRECTED, nvml.AGGREGATE_ECC)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_ecc_corrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now()) y, err := lp.New("nv_ecc_corrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -602,7 +602,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error
return nil return nil
} }
func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_power_max_limit"] { if !device.excludeMetrics["nv_power_max_limit"] {
// Retrieves the power management limit associated with this device. // Retrieves the power management limit associated with this device.
// //
@ -612,7 +612,7 @@ func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
// If the card's total power draw reaches this limit the power management algorithm kicks in. // If the card's total power draw reaches this limit the power management algorithm kicks in.
pwr_limit, ret := nvml.DeviceGetPowerManagementLimit(device.device) pwr_limit, ret := nvml.DeviceGetPowerManagementLimit(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_power_max_limit", device.tags, device.meta, map[string]interface{}{"value": float64(pwr_limit) / 1000}, time.Now()) y, err := lp.New("nv_power_max_limit", device.tags, device.meta, map[string]interface{}{"value": float64(pwr_limit) / 1000}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "watts") y.AddMeta("unit", "watts")
output <- y output <- y
@ -622,7 +622,7 @@ func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
return nil return nil
} }
func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device) isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
if ret != nvml.SUCCESS { if ret != nvml.SUCCESS {
err := errors.New(nvml.ErrorString(ret)) err := errors.New(nvml.ErrorString(ret))
@ -639,7 +639,7 @@ func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
// Note: On MIG-enabled GPUs, querying encoder utilization is not currently supported. // Note: On MIG-enabled GPUs, querying encoder utilization is not currently supported.
enc_util, _, ret := nvml.DeviceGetEncoderUtilization(device.device) enc_util, _, ret := nvml.DeviceGetEncoderUtilization(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_encoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now()) y, err := lp.New("nv_encoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "%") y.AddMeta("unit", "%")
output <- y output <- y
@ -649,7 +649,7 @@ func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
return nil return nil
} }
func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device) isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
if ret != nvml.SUCCESS { if ret != nvml.SUCCESS {
err := errors.New(nvml.ErrorString(ret)) err := errors.New(nvml.ErrorString(ret))
@ -666,7 +666,7 @@ func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
// Note: On MIG-enabled GPUs, querying encoder utilization is not currently supported. // Note: On MIG-enabled GPUs, querying encoder utilization is not currently supported.
dec_util, _, ret := nvml.DeviceGetDecoderUtilization(device.device) dec_util, _, ret := nvml.DeviceGetDecoderUtilization(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_decoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now()) y, err := lp.New("nv_decoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "%") y.AddMeta("unit", "%")
output <- y output <- y
@ -676,7 +676,7 @@ func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
return nil return nil
} }
func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_remapped_rows_corrected"] || if !device.excludeMetrics["nv_remapped_rows_corrected"] ||
!device.excludeMetrics["nv_remapped_rows_uncorrected"] || !device.excludeMetrics["nv_remapped_rows_uncorrected"] ||
!device.excludeMetrics["nv_remapped_rows_pending"] || !device.excludeMetrics["nv_remapped_rows_pending"] ||
@ -693,13 +693,13 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
corrected, uncorrected, pending, failure, ret := nvml.DeviceGetRemappedRows(device.device) corrected, uncorrected, pending, failure, ret := nvml.DeviceGetRemappedRows(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
if !device.excludeMetrics["nv_remapped_rows_corrected"] { if !device.excludeMetrics["nv_remapped_rows_corrected"] {
y, err := lp.NewMessage("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(corrected)}, time.Now()) y, err := lp.New("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(corrected)}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !device.excludeMetrics["nv_remapped_rows_uncorrected"] { if !device.excludeMetrics["nv_remapped_rows_uncorrected"] {
y, err := lp.NewMessage("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(uncorrected)}, time.Now()) y, err := lp.New("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(uncorrected)}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -709,7 +709,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
if pending { if pending {
p = 1 p = 1
} }
y, err := lp.NewMessage("nv_remapped_rows_pending", device.tags, device.meta, map[string]interface{}{"value": p}, time.Now()) y, err := lp.New("nv_remapped_rows_pending", device.tags, device.meta, map[string]interface{}{"value": p}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -719,7 +719,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
if failure { if failure {
f = 1 f = 1
} }
y, err := lp.NewMessage("nv_remapped_rows_failure", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now()) y, err := lp.New("nv_remapped_rows_failure", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -729,7 +729,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
return nil return nil
} }
func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
if !device.excludeMetrics["nv_compute_processes"] { if !device.excludeMetrics["nv_compute_processes"] {
// Get information about processes with a compute context on a device // Get information about processes with a compute context on a device
// //
@ -753,7 +753,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
// Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode. // Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode.
procList, ret := nvml.DeviceGetComputeRunningProcesses(device.device) procList, ret := nvml.DeviceGetComputeRunningProcesses(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now()) y, err := lp.New("nv_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -782,7 +782,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
// Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode. // Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode.
procList, ret := nvml.DeviceGetGraphicsRunningProcesses(device.device) procList, ret := nvml.DeviceGetGraphicsRunningProcesses(device.device)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_graphics_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now()) y, err := lp.New("nv_graphics_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }
@ -812,7 +812,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
// // Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode. // // Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode.
// procList, ret := nvml.DeviceGetMPSComputeRunningProcesses(device.device) // procList, ret := nvml.DeviceGetMPSComputeRunningProcesses(device.device)
// if ret == nvml.SUCCESS { // if ret == nvml.SUCCESS {
// y, err := lp.NewMessage("nv_mps_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now()) // y, err := lp.New("nv_mps_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
// if err == nil { // if err == nil {
// output <- y // output <- y
// } // }
@ -821,7 +821,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
return nil return nil
} }
func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
var violTime nvml.ViolationTime var violTime nvml.ViolationTime
var ret nvml.Return var ret nvml.Return
@ -840,7 +840,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_POWER) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_POWER)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_power", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_power", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -852,7 +852,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_THERMAL) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_THERMAL)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_thermal", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_thermal", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -864,7 +864,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_SYNC_BOOST) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_SYNC_BOOST)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_sync_boost", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_sync_boost", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -876,7 +876,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_BOARD_LIMIT) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_BOARD_LIMIT)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_board_limit", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_board_limit", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -888,7 +888,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_LOW_UTILIZATION) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_LOW_UTILIZATION)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_low_util", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_low_util", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -900,7 +900,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_RELIABILITY) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_RELIABILITY)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_reliability", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_reliability", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -912,7 +912,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_TOTAL_APP_CLOCKS) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_TOTAL_APP_CLOCKS)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_below_app_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_below_app_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -924,7 +924,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_TOTAL_BASE_CLOCKS) violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_TOTAL_BASE_CLOCKS)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
t := float64(violTime.ViolationTime) * 1e-9 t := float64(violTime.ViolationTime) * 1e-9
y, err := lp.NewMessage("nv_violation_below_base_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now()) y, err := lp.New("nv_violation_below_base_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
if err == nil { if err == nil {
y.AddMeta("unit", "sec") y.AddMeta("unit", "sec")
output <- y output <- y
@ -935,18 +935,12 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
return nil return nil
} }
func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) error { func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
// Retrieves the specified error counter value // Retrieves the specified error counter value
// Please refer to \a nvmlNvLinkErrorCounter_t for error counters that are available // Please refer to \a nvmlNvLinkErrorCounter_t for error counters that are available
// //
// For Pascal &tm; or newer fully supported devices. // For Pascal &tm; or newer fully supported devices.
var aggregate_crc_errors uint64 = 0
var aggregate_ecc_errors uint64 = 0
var aggregate_replay_errors uint64 = 0
var aggregate_recovery_errors uint64 = 0
var aggregate_crc_flit_errors uint64 = 0
for i := 0; i < nvml.NVLINK_MAX_LINKS; i++ { for i := 0; i < nvml.NVLINK_MAX_LINKS; i++ {
state, ret := nvml.DeviceGetNvLinkState(device.device, i) state, ret := nvml.DeviceGetNvLinkState(device.device, i)
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
@ -954,9 +948,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
if !device.excludeMetrics["nv_nvlink_crc_errors"] { if !device.excludeMetrics["nv_nvlink_crc_errors"] {
// Data link receive data CRC error counter // Data link receive data CRC error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_CRC_DATA) count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_CRC_DATA)
aggregate_crc_errors = aggregate_crc_errors + count
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_nvlink_crc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now()) y, err := lp.New("nv_nvlink_crc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
if err == nil { if err == nil {
y.AddTag("stype", "nvlink") y.AddTag("stype", "nvlink")
y.AddTag("stype-id", fmt.Sprintf("%d", i)) y.AddTag("stype-id", fmt.Sprintf("%d", i))
@ -967,9 +960,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
if !device.excludeMetrics["nv_nvlink_ecc_errors"] { if !device.excludeMetrics["nv_nvlink_ecc_errors"] {
// Data link receive data ECC error counter // Data link receive data ECC error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_ECC_DATA) count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_ECC_DATA)
aggregate_ecc_errors = aggregate_ecc_errors + count
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_nvlink_ecc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now()) y, err := lp.New("nv_nvlink_ecc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
if err == nil { if err == nil {
y.AddTag("stype", "nvlink") y.AddTag("stype", "nvlink")
y.AddTag("stype-id", fmt.Sprintf("%d", i)) y.AddTag("stype-id", fmt.Sprintf("%d", i))
@ -980,9 +972,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
if !device.excludeMetrics["nv_nvlink_replay_errors"] { if !device.excludeMetrics["nv_nvlink_replay_errors"] {
// Data link transmit replay error counter // Data link transmit replay error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_REPLAY) count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_REPLAY)
aggregate_replay_errors = aggregate_replay_errors + count
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_nvlink_replay_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now()) y, err := lp.New("nv_nvlink_replay_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
if err == nil { if err == nil {
y.AddTag("stype", "nvlink") y.AddTag("stype", "nvlink")
y.AddTag("stype-id", fmt.Sprintf("%d", i)) y.AddTag("stype-id", fmt.Sprintf("%d", i))
@ -993,9 +984,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
if !device.excludeMetrics["nv_nvlink_recovery_errors"] { if !device.excludeMetrics["nv_nvlink_recovery_errors"] {
// Data link transmit recovery error counter // Data link transmit recovery error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_RECOVERY) count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_RECOVERY)
aggregate_recovery_errors = aggregate_recovery_errors + count
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_nvlink_recovery_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now()) y, err := lp.New("nv_nvlink_recovery_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
if err == nil { if err == nil {
y.AddTag("stype", "nvlink") y.AddTag("stype", "nvlink")
y.AddTag("stype-id", fmt.Sprintf("%d", i)) y.AddTag("stype-id", fmt.Sprintf("%d", i))
@ -1006,9 +996,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
if !device.excludeMetrics["nv_nvlink_crc_flit_errors"] { if !device.excludeMetrics["nv_nvlink_crc_flit_errors"] {
// Data link receive flow control digit CRC error counter // Data link receive flow control digit CRC error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_CRC_FLIT) count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_CRC_FLIT)
aggregate_crc_flit_errors = aggregate_crc_flit_errors + count
if ret == nvml.SUCCESS { if ret == nvml.SUCCESS {
y, err := lp.NewMessage("nv_nvlink_crc_flit_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now()) y, err := lp.New("nv_nvlink_crc_flit_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
if err == nil { if err == nil {
y.AddTag("stype", "nvlink") y.AddTag("stype", "nvlink")
y.AddTag("stype-id", fmt.Sprintf("%d", i)) y.AddTag("stype-id", fmt.Sprintf("%d", i))
@ -1019,58 +1008,16 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
} }
} }
} }
// Export aggegated values
if !device.excludeMetrics["nv_nvlink_crc_errors"] {
// Data link receive data CRC error counter
y, err := lp.NewMessage("nv_nvlink_crc_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_crc_errors}, time.Now())
if err == nil {
y.AddTag("stype", "nvlink")
output <- y
}
}
if !device.excludeMetrics["nv_nvlink_ecc_errors"] {
// Data link receive data ECC error counter
y, err := lp.NewMessage("nv_nvlink_ecc_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_ecc_errors}, time.Now())
if err == nil {
y.AddTag("stype", "nvlink")
output <- y
}
}
if !device.excludeMetrics["nv_nvlink_replay_errors"] {
// Data link transmit replay error counter
y, err := lp.NewMessage("nv_nvlink_replay_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_replay_errors}, time.Now())
if err == nil {
y.AddTag("stype", "nvlink")
output <- y
}
}
if !device.excludeMetrics["nv_nvlink_recovery_errors"] {
// Data link transmit recovery error counter
y, err := lp.NewMessage("nv_nvlink_recovery_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_recovery_errors}, time.Now())
if err == nil {
y.AddTag("stype", "nvlink")
output <- y
}
}
if !device.excludeMetrics["nv_nvlink_crc_flit_errors"] {
// Data link receive flow control digit CRC error counter
y, err := lp.NewMessage("nv_nvlink_crc_flit_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_crc_flit_errors}, time.Now())
if err == nil {
y.AddTag("stype", "nvlink")
output <- y
}
}
return nil return nil
} }
func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
var err error var err error
if !m.init { if !m.init {
return return
} }
readAll := func(device NvidiaCollectorDevice, output chan lp.CCMessage) { readAll := func(device NvidiaCollectorDevice, output chan lp.CCMetric) {
name, ret := nvml.DeviceGetName(device.device) name, ret := nvml.DeviceGetName(device.device)
if ret != nvml.SUCCESS { if ret != nvml.SUCCESS {
name = "NoName" name = "NoName"

View File

@ -1,13 +1,3 @@
<!--
---
title: "Nvidia NVML metric collector"
description: Collect metrics for Nvidia GPUs using the NVML
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/nvidia.md
---
-->
## `nvidia` collector ## `nvidia` collector
@ -83,4 +73,4 @@ Metrics:
* `nv_nvlink_replay_errors` * `nv_nvlink_replay_errors`
* `nv_nvlink_recovery_errors` * `nv_nvlink_recovery_errors`
Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`. Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`.

View File

@ -9,8 +9,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// running average power limit (RAPL) monitoring attributes for a zone // running average power limit (RAPL) monitoring attributes for a zone
@ -214,7 +214,7 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// Read reads running average power limit (RAPL) monitoring attributes for all initialized zones // Read reads running average power limit (RAPL) monitoring attributes for all initialized zones
// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes // See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMetric) {
for i := range m.RAPLZoneInfo { for i := range m.RAPLZoneInfo {
p := &m.RAPLZoneInfo[i] p := &m.RAPLZoneInfo[i]
@ -237,7 +237,7 @@ func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMessage) {
timeDiff := energyTimestamp.Sub(p.energyTimestamp) timeDiff := energyTimestamp.Sub(p.energyTimestamp)
averagePower := float64(energyDiff) / float64(timeDiff.Microseconds()) averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
y, err := lp.NewMessage( y, err := lp.New(
"rapl_average_power", "rapl_average_power",
p.tags, p.tags,
m.meta, m.meta,

View File

@ -1,20 +1,11 @@
<!-- # Running average power limit (RAPL) metric collector
---
title: RAPL metric collector
description: Collect energy data through the RAPL sysfs interface
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/rapl.md
---
-->
## `rapl` collector
This collector reads running average power limit (RAPL) monitoring attributes to compute average power consumption metrics. See <https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes>. This collector reads running average power limit (RAPL) monitoring attributes to compute average power consumption metrics. See <https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes>.
The Likwid metric collector provides similar functionality. The Likwid metric collector provides similar functionality.
## Configuration
```json ```json
"rapl": { "rapl": {
"exclude_device_by_id": ["0:1", "0:2"], "exclude_device_by_id": ["0:1", "0:2"],
@ -22,5 +13,6 @@ The Likwid metric collector provides similar functionality.
} }
``` ```
Metrics: ## Metrics
* `rapl_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement * `rapl_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement

View File

@ -6,8 +6,8 @@ import (
"fmt" "fmt"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/ClusterCockpit/go-rocm-smi/pkg/rocm_smi" "github.com/ClusterCockpit/go-rocm-smi/pkg/rocm_smi"
) )
@ -162,7 +162,7 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
// Read collects all metrics belonging to the sample collector // Read collects all metrics belonging to the sample collector
// and sends them through the output channel to the collector manager // and sends them through the output channel to the collector manager
func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Create a sample metric // Create a sample metric
timestamp := time.Now() timestamp := time.Now()
@ -175,119 +175,119 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
if !dev.excludeMetrics["rocm_gfx_util"] { if !dev.excludeMetrics["rocm_gfx_util"] {
value := metrics.Average_gfx_activity value := metrics.Average_gfx_activity
y, err := lp.NewMessage("rocm_gfx_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_gfx_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_umc_util"] { if !dev.excludeMetrics["rocm_umc_util"] {
value := metrics.Average_umc_activity value := metrics.Average_umc_activity
y, err := lp.NewMessage("rocm_umc_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_umc_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_mm_util"] { if !dev.excludeMetrics["rocm_mm_util"] {
value := metrics.Average_mm_activity value := metrics.Average_mm_activity
y, err := lp.NewMessage("rocm_mm_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_mm_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_avg_power"] { if !dev.excludeMetrics["rocm_avg_power"] {
value := metrics.Average_socket_power value := metrics.Average_socket_power
y, err := lp.NewMessage("rocm_avg_power", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_avg_power", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_temp_mem"] { if !dev.excludeMetrics["rocm_temp_mem"] {
value := metrics.Temperature_mem value := metrics.Temperature_mem
y, err := lp.NewMessage("rocm_temp_mem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_temp_mem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_temp_hotspot"] { if !dev.excludeMetrics["rocm_temp_hotspot"] {
value := metrics.Temperature_hotspot value := metrics.Temperature_hotspot
y, err := lp.NewMessage("rocm_temp_hotspot", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_temp_hotspot", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_temp_edge"] { if !dev.excludeMetrics["rocm_temp_edge"] {
value := metrics.Temperature_edge value := metrics.Temperature_edge
y, err := lp.NewMessage("rocm_temp_edge", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_temp_edge", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_temp_vrgfx"] { if !dev.excludeMetrics["rocm_temp_vrgfx"] {
value := metrics.Temperature_vrgfx value := metrics.Temperature_vrgfx
y, err := lp.NewMessage("rocm_temp_vrgfx", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_temp_vrgfx", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_temp_vrsoc"] { if !dev.excludeMetrics["rocm_temp_vrsoc"] {
value := metrics.Temperature_vrsoc value := metrics.Temperature_vrsoc
y, err := lp.NewMessage("rocm_temp_vrsoc", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_temp_vrsoc", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_temp_vrmem"] { if !dev.excludeMetrics["rocm_temp_vrmem"] {
value := metrics.Temperature_vrmem value := metrics.Temperature_vrmem
y, err := lp.NewMessage("rocm_temp_vrmem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_temp_vrmem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_gfx_clock"] { if !dev.excludeMetrics["rocm_gfx_clock"] {
value := metrics.Average_gfxclk_frequency value := metrics.Average_gfxclk_frequency
y, err := lp.NewMessage("rocm_gfx_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_gfx_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_soc_clock"] { if !dev.excludeMetrics["rocm_soc_clock"] {
value := metrics.Average_socclk_frequency value := metrics.Average_socclk_frequency
y, err := lp.NewMessage("rocm_soc_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_soc_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_u_clock"] { if !dev.excludeMetrics["rocm_u_clock"] {
value := metrics.Average_uclk_frequency value := metrics.Average_uclk_frequency
y, err := lp.NewMessage("rocm_u_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_u_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_v0_clock"] { if !dev.excludeMetrics["rocm_v0_clock"] {
value := metrics.Average_vclk0_frequency value := metrics.Average_vclk0_frequency
y, err := lp.NewMessage("rocm_v0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_v0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_v1_clock"] { if !dev.excludeMetrics["rocm_v1_clock"] {
value := metrics.Average_vclk1_frequency value := metrics.Average_vclk1_frequency
y, err := lp.NewMessage("rocm_v1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_v1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_d0_clock"] { if !dev.excludeMetrics["rocm_d0_clock"] {
value := metrics.Average_dclk0_frequency value := metrics.Average_dclk0_frequency
y, err := lp.NewMessage("rocm_d0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_d0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if !dev.excludeMetrics["rocm_d1_clock"] { if !dev.excludeMetrics["rocm_d1_clock"] {
value := metrics.Average_dclk1_frequency value := metrics.Average_dclk1_frequency
y, err := lp.NewMessage("rocm_d1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_d1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
@ -295,7 +295,7 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
if !dev.excludeMetrics["rocm_temp_hbm"] { if !dev.excludeMetrics["rocm_temp_hbm"] {
for i := 0; i < rocm_smi.NUM_HBM_INSTANCES; i++ { for i := 0; i < rocm_smi.NUM_HBM_INSTANCES; i++ {
value := metrics.Temperature_hbm[i] value := metrics.Temperature_hbm[i]
y, err := lp.NewMessage("rocm_temp_hbm", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("rocm_temp_hbm", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
y.AddTag("stype", "device") y.AddTag("stype", "device")
y.AddTag("stype-id", fmt.Sprintf("%d", i)) y.AddTag("stype-id", fmt.Sprintf("%d", i))

View File

@ -1,14 +1,3 @@
<!--
---
title: "ROCm SMI metric collector"
description: Collect metrics for AMD GPUs using the SMI library
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/rocmsmi.md
---
-->
## `rocm_smi` collector ## `rocm_smi` collector

View File

@ -4,8 +4,8 @@ import (
"encoding/json" "encoding/json"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// These are the fields we read from the JSON configuration // These are the fields we read from the JSON configuration
@ -32,7 +32,7 @@ type SampleCollector struct {
func (m *SampleCollector) Init(config json.RawMessage) error { func (m *SampleCollector) Init(config json.RawMessage) error {
var err error = nil var err error = nil
// Always set the name early in Init() to use it in cclog.Component* functions // Always set the name early in Init() to use it in cclog.Component* functions
m.name = "SampleCollector" m.name = "InternalCollector"
// This is for later use, also call it early // This is for later use, also call it early
m.setup() m.setup()
// Tell whether the collector should be run in parallel with others (reading files, ...) // Tell whether the collector should be run in parallel with others (reading files, ...)
@ -74,7 +74,7 @@ func (m *SampleCollector) Init(config json.RawMessage) error {
// Read collects all metrics belonging to the sample collector // Read collects all metrics belonging to the sample collector
// and sends them through the output channel to the collector manager // and sends them through the output channel to the collector manager
func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Create a sample metric // Create a sample metric
timestamp := time.Now() timestamp := time.Now()
@ -85,7 +85,7 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMessage)
// stop := readState() // stop := readState()
// value = (stop - start) / interval.Seconds() // value = (stop - start) / interval.Seconds()
y, err := lp.NewMessage("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil { if err == nil {
// Send it to output channel // Send it to output channel
output <- y output <- y

View File

@ -5,8 +5,8 @@ import (
"sync" "sync"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// These are the fields we read from the JSON configuration // These are the fields we read from the JSON configuration
@ -25,7 +25,7 @@ type SampleTimerCollector struct {
config SampleTimerCollectorConfig // the configuration structure config SampleTimerCollectorConfig // the configuration structure
interval time.Duration // the interval parsed from configuration interval time.Duration // the interval parsed from configuration
ticker *time.Ticker // own timer ticker *time.Ticker // own timer
output chan lp.CCMessage // own internal output channel output chan lp.CCMetric // own internal output channel
} }
func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error { func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
@ -100,14 +100,14 @@ func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
// stop := readState() // stop := readState()
// value = (stop - start) / interval.Seconds() // value = (stop - start) / interval.Seconds()
y, err := lp.NewMessage("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp) y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil && m.output != nil { if err == nil && m.output != nil {
// Send it to output channel if we have a valid channel // Send it to output channel if we have a valid channel
m.output <- y m.output <- y
} }
} }
func (m *SampleTimerCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *SampleTimerCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Capture output channel // Capture output channel
m.output = output m.output = output
} }

View File

@ -10,8 +10,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
const SCHEDSTATFILE = `/proc/schedstat` const SCHEDSTATFILE = `/proc/schedstat`
@ -96,7 +96,7 @@ func (m *SchedstatCollector) Init(config json.RawMessage) error {
return err return err
} }
func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]string, output chan lp.CCMessage, now time.Time, tsdelta time.Duration) { func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
running, _ := strconv.ParseInt(linefields[7], 10, 64) running, _ := strconv.ParseInt(linefields[7], 10, 64)
waiting, _ := strconv.ParseInt(linefields[8], 10, 64) waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
diff_running := running - m.olddata[linefields[0]]["running"] diff_running := running - m.olddata[linefields[0]]["running"]
@ -109,7 +109,7 @@ func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]
m.olddata[linefields[0]]["waiting"] = waiting m.olddata[linefields[0]]["waiting"] = waiting
value := l_running + l_waiting value := l_running + l_waiting
y, err := lp.NewMessage("cpu_load_core", tags, m.meta, map[string]interface{}{"value": value}, now) y, err := lp.New("cpu_load_core", tags, m.meta, map[string]interface{}{"value": value}, now)
if err == nil { if err == nil {
// Send it to output channel // Send it to output channel
output <- y output <- y
@ -118,7 +118,7 @@ func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]
// Read collects all metrics belonging to the sample collector // Read collects all metrics belonging to the sample collector
// and sends them through the output channel to the collector manager // and sends them through the output channel to the collector manager
func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }

View File

@ -1,13 +1,3 @@
<!--
---
title: SchedStat Metric collector
description: Collect metrics from `/proc/schedstat`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/schedstat.md
---
-->
## `schedstat` collector ## `schedstat` collector
```json ```json
@ -18,4 +8,4 @@ hugo_path: docs/reference/cc-metric-collector/collectors/schedstat.md
The `schedstat` collector reads data from /proc/schedstat and calculates a load value, separated by hwthread. This might be useful to detect bad cpu pinning on shared nodes etc. The `schedstat` collector reads data from /proc/schedstat and calculates a load value, separated by hwthread. This might be useful to detect bad cpu pinning on shared nodes etc.
Metric: Metric:
* `cpu_load_core` * `cpu_load_core`

View File

@ -6,8 +6,8 @@ import (
"syscall" "syscall"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
type SelfCollectorConfig struct { type SelfCollectorConfig struct {
@ -42,56 +42,56 @@ func (m *SelfCollector) Init(config json.RawMessage) error {
return err return err
} }
func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMetric) {
timestamp := time.Now() timestamp := time.Now()
if m.config.MemStats { if m.config.MemStats {
var memstats runtime.MemStats var memstats runtime.MemStats
runtime.ReadMemStats(&memstats) runtime.ReadMemStats(&memstats)
y, err := lp.NewMessage("total_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.TotalAlloc}, timestamp) y, err := lp.New("total_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.TotalAlloc}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "Bytes") y.AddMeta("unit", "Bytes")
output <- y output <- y
} }
y, err = lp.NewMessage("heap_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapAlloc}, timestamp) y, err = lp.New("heap_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapAlloc}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "Bytes") y.AddMeta("unit", "Bytes")
output <- y output <- y
} }
y, err = lp.NewMessage("heap_sys", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapSys}, timestamp) y, err = lp.New("heap_sys", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapSys}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "Bytes") y.AddMeta("unit", "Bytes")
output <- y output <- y
} }
y, err = lp.NewMessage("heap_idle", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapIdle}, timestamp) y, err = lp.New("heap_idle", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapIdle}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "Bytes") y.AddMeta("unit", "Bytes")
output <- y output <- y
} }
y, err = lp.NewMessage("heap_inuse", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapInuse}, timestamp) y, err = lp.New("heap_inuse", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapInuse}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "Bytes") y.AddMeta("unit", "Bytes")
output <- y output <- y
} }
y, err = lp.NewMessage("heap_released", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapReleased}, timestamp) y, err = lp.New("heap_released", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapReleased}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "Bytes") y.AddMeta("unit", "Bytes")
output <- y output <- y
} }
y, err = lp.NewMessage("heap_objects", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapObjects}, timestamp) y, err = lp.New("heap_objects", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapObjects}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if m.config.GoRoutines { if m.config.GoRoutines {
y, err := lp.NewMessage("num_goroutines", m.tags, m.meta, map[string]interface{}{"value": runtime.NumGoroutine()}, timestamp) y, err := lp.New("num_goroutines", m.tags, m.meta, map[string]interface{}{"value": runtime.NumGoroutine()}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
} }
if m.config.CgoCalls { if m.config.CgoCalls {
y, err := lp.NewMessage("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp) y, err := lp.New("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
@ -102,35 +102,35 @@ func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMessage) {
if err == nil { if err == nil {
sec, nsec := rusage.Utime.Unix() sec, nsec := rusage.Utime.Unix()
t := float64(sec) + (float64(nsec) * 1e-9) t := float64(sec) + (float64(nsec) * 1e-9)
y, err := lp.NewMessage("rusage_user_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp) y, err := lp.New("rusage_user_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "seconds") y.AddMeta("unit", "seconds")
output <- y output <- y
} }
sec, nsec = rusage.Stime.Unix() sec, nsec = rusage.Stime.Unix()
t = float64(sec) + (float64(nsec) * 1e-9) t = float64(sec) + (float64(nsec) * 1e-9)
y, err = lp.NewMessage("rusage_system_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp) y, err = lp.New("rusage_system_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
if err == nil { if err == nil {
y.AddMeta("unit", "seconds") y.AddMeta("unit", "seconds")
output <- y output <- y
} }
y, err = lp.NewMessage("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp) y, err = lp.New("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
y, err = lp.NewMessage("rusage_invol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nivcsw}, timestamp) y, err = lp.New("rusage_invol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nivcsw}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
y, err = lp.NewMessage("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp) y, err = lp.New("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
y, err = lp.NewMessage("rusage_major_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Majflt}, timestamp) y, err = lp.New("rusage_major_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Majflt}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }
y, err = lp.NewMessage("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp) y, err = lp.New("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp)
if err == nil { if err == nil {
output <- y output <- y
} }

View File

@ -1,14 +1,3 @@
<!--
---
title: Self-monitoring metric collector
description: Collect metrics from the execution of cc-metric-collector itself
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/self.md
---
-->
## `self` collector ## `self` collector
```json ```json

View File

@ -9,8 +9,8 @@ import (
"strings" "strings"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
// See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html // See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
@ -171,7 +171,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
for _, sensor := range m.sensors { for _, sensor := range m.sensors {
// Read sensor file // Read sensor file
@ -190,7 +190,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue continue
} }
x /= 1000 x /= 1000
y, err := lp.NewMessage( y, err := lp.New(
sensor.metricName, sensor.metricName,
sensor.tags, sensor.tags,
m.meta, m.meta,
@ -203,7 +203,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// max temperature // max temperature
if m.config.ReportMaxTemp && sensor.maxTemp != 0 { if m.config.ReportMaxTemp && sensor.maxTemp != 0 {
y, err := lp.NewMessage( y, err := lp.New(
sensor.maxTempName, sensor.maxTempName,
sensor.tags, sensor.tags,
m.meta, m.meta,
@ -217,7 +217,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// critical temperature // critical temperature
if m.config.ReportCriticalTemp && sensor.critTemp != 0 { if m.config.ReportCriticalTemp && sensor.critTemp != 0 {
y, err := lp.NewMessage( y, err := lp.New(
sensor.critTempName, sensor.critTempName,
sensor.tags, sensor.tags,
m.meta, m.meta,

View File

@ -1,14 +1,3 @@
<!--
---
title: Temperature metric collector
description: Collect thermal metrics from `/sys/class/hwmon/*`
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/temp.md
---
-->
## `tempstat` collector ## `tempstat` collector

View File

@ -9,7 +9,7 @@ import (
"strings" "strings"
"time" "time"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
) )
const MAX_NUM_PROCS = 10 const MAX_NUM_PROCS = 10
@ -53,7 +53,7 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
return nil return nil
} }
func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessage) { func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init { if !m.init {
return return
} }
@ -68,7 +68,7 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessag
lines := strings.Split(string(stdout), "\n") lines := strings.Split(string(stdout), "\n")
for i := 1; i < m.config.Num_procs+1; i++ { for i := 1; i < m.config.Num_procs+1; i++ {
name := fmt.Sprintf("topproc%d", i) name := fmt.Sprintf("topproc%d", i)
y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now()) y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now())
if err == nil { if err == nil {
output <- y output <- y
} }

View File

@ -1,15 +1,3 @@
<!--
---
title: TopProcs collector
description: Collect infos about most CPU-consuming processes
categories: [cc-metric-collector]
tags: ['Admin']
weight: 2
hugo_path: docs/reference/cc-metric-collector/collectors/topprocs.md
---
-->
## `topprocs` collector ## `topprocs` collector

View File

@ -1,10 +1,8 @@
{ {
"sinks-file": "./sinks.json", "sinks": "./sinks.json",
"collectors-file" : "./collectors.json", "collectors" : "./collectors.json",
"receivers-file" : "./receivers.json", "receivers" : "./receivers.json",
"router-file" : "./router.json", "router" : "./router.json",
"main" : { "interval": "10s",
"interval": "10s", "duration": "1s"
"duration": "1s"
}
} }

View File

@ -12,8 +12,8 @@ The global file contains the paths to the other four files and some global optio
"collectors" : "collectors.json", "collectors" : "collectors.json",
"receivers" : "receivers.json", "receivers" : "receivers.json",
"router" : "router.json", "router" : "router.json",
"interval": "10s", "interval": 10,
"duration": "1s" "duration": 1
} }
``` ```

119
go.mod
View File

@ -1,48 +1,105 @@
module github.com/ClusterCockpit/cc-metric-collector module github.com/ClusterCockpit/cc-metric-collector
go 1.23.4 go 1.20
toolchain go1.23.7
require ( require (
github.com/ClusterCockpit/cc-lib v0.1.1 github.com/ClusterCockpit/cc-units v0.4.0
github.com/ClusterCockpit/go-rocm-smi v0.3.0 github.com/ClusterCockpit/go-rocm-smi v0.3.0
github.com/NVIDIA/go-nvml v0.12.0-2 github.com/NVIDIA/go-nvml v0.12.0-1
github.com/PaesslerAG/gval v1.2.2 github.com/PaesslerAG/gval v1.2.2
github.com/fsnotify/fsnotify v1.7.0 github.com/fsnotify/fsnotify v1.6.0
github.com/gorilla/mux v1.8.1 github.com/gorilla/mux v1.8.0
github.com/influxdata/influxdb-client-go/v2 v2.14.0 github.com/influxdata/influxdb-client-go/v2 v2.12.3
github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
github.com/influxdata/line-protocol/v2 v2.2.1 github.com/influxdata/line-protocol/v2 v2.2.1
github.com/nats-io/nats.go v1.39.0 github.com/nats-io/nats.go v1.30.2
github.com/prometheus/client_golang v1.20.5 github.com/prometheus/client_golang v1.17.0
github.com/stmcginnis/gofish v0.15.0 github.com/stmcginnis/gofish v0.14.0
github.com/tklauser/go-sysconf v0.3.13 github.com/tklauser/go-sysconf v0.3.12
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f golang.org/x/exp v0.0.0-20231006140011-7918f672742d
golang.org/x/sys v0.30.0 golang.org/x/sys v0.13.0
) )
require ( require (
github.com/ClusterCockpit/cc-backend v1.4.2 // indirect github.com/BurntSushi/toml v1.3.2 // indirect
github.com/ClusterCockpit/cc-units v0.4.0 // indirect github.com/CloudyKit/fastprinter v0.0.0-20200109182630-33d98a066a53 // indirect
github.com/CloudyKit/jet/v6 v6.2.0 // indirect
github.com/Joker/jade v1.1.3 // indirect
github.com/Shopify/goreferrer v0.0.0-20220729165902-8cddb4f5de06 // indirect
github.com/andybalholm/brotli v1.0.5 // indirect
github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
github.com/aymerick/douceur v0.2.0 // indirect
github.com/beorn7/perks v1.0.1 // indirect github.com/beorn7/perks v1.0.1 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect github.com/bytedance/sonic v1.10.2 // indirect
github.com/expr-lang/expr v1.17.0 // indirect github.com/cespare/xxhash/v2 v2.2.0 // indirect
github.com/google/uuid v1.6.0 // indirect github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d // indirect
github.com/klauspost/compress v1.17.9 // indirect github.com/chenzhuoyu/iasm v0.9.0 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect github.com/deepmap/oapi-codegen v1.15.0 // indirect
github.com/nats-io/nkeys v0.4.9 // indirect github.com/fatih/structs v1.1.0 // indirect
github.com/flosch/pongo2/v4 v4.0.2 // indirect
github.com/gabriel-vasile/mimetype v1.4.2 // indirect
github.com/gin-contrib/sse v0.1.0 // indirect
github.com/gin-gonic/gin v1.9.1 // indirect
github.com/go-playground/locales v0.14.1 // indirect
github.com/go-playground/universal-translator v0.18.1 // indirect
github.com/go-playground/validator/v10 v10.15.5 // indirect
github.com/goccy/go-json v0.10.2 // indirect
github.com/golang/protobuf v1.5.3 // indirect
github.com/golang/snappy v0.0.4 // indirect
github.com/gomarkdown/markdown v0.0.0-20230922112808-5421fefb8386 // indirect
github.com/google/uuid v1.3.1 // indirect
github.com/gorilla/css v1.0.0 // indirect
github.com/iris-contrib/schema v0.0.6 // indirect
github.com/josharian/intern v1.0.0 // indirect
github.com/json-iterator/go v1.1.12 // indirect
github.com/kataras/blocks v0.0.8 // indirect
github.com/kataras/golog v0.1.9 // indirect
github.com/kataras/iris/v12 v12.2.7 // indirect
github.com/kataras/pio v0.0.12 // indirect
github.com/kataras/sitemap v0.0.6 // indirect
github.com/kataras/tunnel v0.0.4 // indirect
github.com/klauspost/compress v1.17.0 // indirect
github.com/klauspost/cpuid/v2 v2.2.5 // indirect
github.com/labstack/echo/v4 v4.11.1 // indirect
github.com/labstack/gommon v0.4.0 // indirect
github.com/leodido/go-urn v1.2.4 // indirect
github.com/mailgun/raymond/v2 v2.0.48 // indirect
github.com/mailru/easyjson v0.7.7 // indirect
github.com/mattn/go-colorable v0.1.13 // indirect
github.com/mattn/go-isatty v0.0.19 // indirect
github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
github.com/microcosm-cc/bluemonday v1.0.25 // indirect
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
github.com/modern-go/reflect2 v1.0.2 // indirect
github.com/nats-io/nats-server/v2 v2.8.4 // indirect
github.com/nats-io/nkeys v0.4.5 // indirect
github.com/nats-io/nuid v1.0.1 // indirect github.com/nats-io/nuid v1.0.1 // indirect
github.com/oapi-codegen/runtime v1.1.1 // indirect github.com/pelletier/go-toml/v2 v2.1.0 // indirect
github.com/prometheus/client_model v0.6.1 // indirect github.com/pkg/errors v0.9.1 // indirect
github.com/prometheus/common v0.55.0 // indirect github.com/prometheus/client_model v0.5.0 // indirect
github.com/prometheus/procfs v0.15.1 // indirect github.com/prometheus/common v0.44.0 // indirect
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 // indirect github.com/prometheus/procfs v0.12.0 // indirect
github.com/russross/blackfriday/v2 v2.1.0 // indirect
github.com/schollz/closestmatch v2.1.0+incompatible // indirect
github.com/shopspring/decimal v1.3.1 // indirect github.com/shopspring/decimal v1.3.1 // indirect
github.com/tklauser/numcpus v0.7.0 // indirect github.com/sirupsen/logrus v1.9.3 // indirect
golang.org/x/crypto v0.35.0 // indirect github.com/tdewolff/minify/v2 v2.12.9 // indirect
golang.org/x/net v0.36.0 // indirect github.com/tdewolff/parse/v2 v2.6.8 // indirect
google.golang.org/protobuf v1.35.2 // indirect github.com/tklauser/numcpus v0.6.1 // indirect
github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
github.com/ugorji/go/codec v1.2.11 // indirect
github.com/valyala/bytebufferpool v1.0.0 // indirect
github.com/valyala/fasttemplate v1.2.2 // indirect
github.com/vmihailenco/msgpack/v5 v5.4.0 // indirect
github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
github.com/yosssi/ace v0.0.5 // indirect
golang.org/x/arch v0.5.0 // indirect
golang.org/x/crypto v0.14.0 // indirect
golang.org/x/net v0.16.0 // indirect
golang.org/x/text v0.13.0 // indirect
golang.org/x/time v0.3.0 // indirect
google.golang.org/protobuf v1.31.0 // indirect
gopkg.in/ini.v1 v1.67.0 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
) )

316
go.sum
View File

@ -1,139 +1,295 @@
github.com/ClusterCockpit/cc-backend v1.4.2 h1:kTOzqkh9N0564N9nqQThnSs7TAfg8RLgvSm00e5HtIc= github.com/BurntSushi/toml v1.3.2 h1:o7IhLm0Msx3BaB+n3Ag7L8EVlByGnpq14C4YWiu/gL8=
github.com/ClusterCockpit/cc-backend v1.4.2/go.mod h1:g8TNHXe4AXej26snu2//jO3mUF980elT93iV/k11O/c= github.com/BurntSushi/toml v1.3.2/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ=
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1 h1:dz9j0g2cod8+SMDjuoIY6ISpiHHeekhX6yQaeiwiwJw= github.com/CloudyKit/fastprinter v0.0.0-20200109182630-33d98a066a53 h1:sR+/8Yb4slttB4vD+b9btVEnWgL3Q00OBTzVT8B9C0c=
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1/go.mod h1:kXMskla1i5ZSfXW0vVRIHgGeXMU5zu2PzYOYnUaOr80= github.com/CloudyKit/fastprinter v0.0.0-20200109182630-33d98a066a53/go.mod h1:+3IMCy2vIlbG1XG/0ggNQv0SvxCAIpPM5b1nCz56Xno=
github.com/ClusterCockpit/cc-lib v0.1.1 h1:AXZWYUzgTaE/WdxLNSWPR7FJoA5WlzvYZxw4gIw3gNw= github.com/CloudyKit/jet/v6 v6.2.0 h1:EpcZ6SR9n28BUGtNJSvlBqf90IpjeFr36Tizxhn/oME=
github.com/ClusterCockpit/cc-lib v0.1.1/go.mod h1:SHKcWW/+kN+pcofAtHJFxvmx1FV0VIJuQv5PuT0HDcc= github.com/CloudyKit/jet/v6 v6.2.0/go.mod h1:d3ypHeIRNo2+XyqnGA8s+aphtcVpjP5hPwP/Lzo7Ro4=
github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoONEOh4cI0= github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoONEOh4cI0=
github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw= github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw=
github.com/ClusterCockpit/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8= github.com/ClusterCockpit/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8=
github.com/ClusterCockpit/go-rocm-smi v0.3.0/go.mod h1:+I3UMeX3OlizXDf1WpGD43W4KGZZGVSGmny6rTeOnWA= github.com/ClusterCockpit/go-rocm-smi v0.3.0/go.mod h1:+I3UMeX3OlizXDf1WpGD43W4KGZZGVSGmny6rTeOnWA=
github.com/Joker/hpp v1.0.0/go.mod h1:8x5n+M1Hp5hC0g8okX3sR3vFQwynaX/UgSOM9MeBKzY=
github.com/Joker/jade v1.1.3 h1:Qbeh12Vq6BxURXT1qZBRHsDxeURB8ztcL6f3EXSGeHk=
github.com/Joker/jade v1.1.3/go.mod h1:T+2WLyt7VH6Lp0TRxQrUYEs64nRc83wkMQrfeIQKduM=
github.com/NVIDIA/go-nvml v0.11.6-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs= github.com/NVIDIA/go-nvml v0.11.6-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
github.com/NVIDIA/go-nvml v0.12.0-2 h1:Sg239yy7jmopu/cuvYauoMj9fOpcGMngxVxxS1EBXeY= github.com/NVIDIA/go-nvml v0.12.0-1 h1:6mdjtlFo+17dWL7VFPfuRMtf0061TF4DKls9pkSw6uM=
github.com/NVIDIA/go-nvml v0.12.0-2/go.mod h1:7ruy85eOM73muOc/I37euONSwEyFqZsv5ED9AogD4G0= github.com/NVIDIA/go-nvml v0.12.0-1/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E= github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E=
github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac= github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
github.com/PaesslerAG/jsonpath v0.1.0/go.mod h1:4BzmtoM/PI8fPO4aQGIusjGxGir2BzcV0grWtFzq1Y8= github.com/PaesslerAG/jsonpath v0.1.0/go.mod h1:4BzmtoM/PI8fPO4aQGIusjGxGir2BzcV0grWtFzq1Y8=
github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk= github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
github.com/Shopify/goreferrer v0.0.0-20220729165902-8cddb4f5de06 h1:KkH3I3sJuOLP3TjA/dfr4NAY8bghDwnXiU7cTKxQqo0=
github.com/Shopify/goreferrer v0.0.0-20220729165902-8cddb4f5de06/go.mod h1:7erjKLwalezA0k99cWs5L11HWOAPNjdUZ6RxH1BXbbM=
github.com/andybalholm/brotli v1.0.5 h1:8uQZIdzKmjc/iuPu7O2ioW48L81FgatrcpfFmiq/cCs=
github.com/andybalholm/brotli v1.0.5/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig=
github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ= github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk= github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk=
github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM= 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/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w= github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs= github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs= github.com/bytedance/sonic v1.10.0-rc/go.mod h1:ElCzW+ufi8qKqNW0FY314xriJhyJhuoJ3gFZdAHF7NM=
github.com/bytedance/sonic v1.10.2 h1:GQebETVBxYB7JGWJtLBi07OVzWwt+8dWA00gEVW2ZFE=
github.com/bytedance/sonic v1.10.2/go.mod h1:iZcSUejdk5aukTND/Eu/ivjQuEL0Cu9/rf50Hi0u/g4=
github.com/cespare/xxhash v1.1.0 h1:a6HrQnmkObjyL+Gs60czilIUGqrzKutQD6XZog3p+ko=
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/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d h1:77cEq6EriyTZ0g/qfRdp61a3Uu/AWrgIq2s0ClJV1g0=
github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d/go.mod h1:8EPpVsBuRksnlj1mLy4AWzRNQYxauNi62uWcE3to6eA=
github.com/chenzhuoyu/iasm v0.9.0 h1:9fhXjVzq5hUy2gkhhgHl95zG2cEAhw9OSGs8toWWAwo=
github.com/chenzhuoyu/iasm v0.9.0/go.mod h1:Xjy2NpN3h7aUqeqM+woSuuvxmIe6+DDsiNLIrkAmYog=
github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/expr-lang/expr v1.16.9 h1:WUAzmR0JNI9JCiF0/ewwHB1gmcGw5wW7nWt8gc6PpCI= github.com/deepmap/oapi-codegen v1.15.0 h1:SQqViaeb4k2vMul8gx12oDOIadEtoRqTdLkxjzqtQ90=
github.com/expr-lang/expr v1.16.9/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4= github.com/deepmap/oapi-codegen v1.15.0/go.mod h1:a6KoHV7lMRwsPoEg2C6NDHiXYV3EQfiFocOlJ8dgJQE=
github.com/expr-lang/expr v1.17.0 h1:+vpszOyzKLQXC9VF+wA8cVA0tlA984/Wabc/1hF9Whg= github.com/fatih/structs v1.1.0 h1:Q7juDM0QtcnhCpeyLGQKyg4TOIghuNXrkL32pHAUMxo=
github.com/expr-lang/expr v1.17.0/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4= github.com/fatih/structs v1.1.0/go.mod h1:9NiDSp5zOcgEDl+j00MP/WkGVPOlPRLejGD8Ga6PJ7M=
github.com/flosch/pongo2/v4 v4.0.2 h1:gv+5Pe3vaSVmiJvh/BZa82b7/00YUGm0PIyVVLop0Hw=
github.com/flosch/pongo2/v4 v4.0.2/go.mod h1:B5ObFANs/36VwxxlgKpdchIJHMvHB562PW+BWPhwZD8=
github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s= github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
github.com/frankban/quicktest v1.11.2/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s= github.com/frankban/quicktest v1.11.2/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
github.com/frankban/quicktest v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU= github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU=
github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA= github.com/fsnotify/fsnotify v1.6.0 h1:n+5WquG0fcWoWp6xPWfHdbskMCQaFnG6PfBrh1Ky4HY=
github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM= github.com/fsnotify/fsnotify v1.6.0/go.mod h1:sl3t1tCWJFWoRz9R8WJCbQihKKwmorjAbSClcnxKAGw=
github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
github.com/go-playground/validator/v10 v10.15.5 h1:LEBecTWb/1j5TNY1YYG2RcOUN3R7NLylN+x8TTueE24=
github.com/go-playground/validator/v10 v10.15.5/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
github.com/golang/protobuf v1.2.0/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/golang/snappy v0.0.4 h1:yAGX7huGHXlcLOEtBnF4w7FQwA26wojNCwOYAEhLjQM=
github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
github.com/gomarkdown/markdown v0.0.0-20230922112808-5421fefb8386 h1:EcQR3gusLHN46TAD+G+EbaaqJArt5vHhNpXAa12PQf4=
github.com/gomarkdown/markdown v0.0.0-20230922112808-5421fefb8386/go.mod h1:JDGcbDT52eL4fju3sZ4TeHGsQwhG9nbDV21aMyhwPoA=
github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= 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/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= github.com/google/uuid v1.3.1 h1:KjJaJ9iWZ3jOFZIf1Lqf4laDRCasjl0BCmnEGxkdLb4=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= github.com/google/uuid v1.3.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY= github.com/gorilla/css v1.0.0/go.mod h1:Dn721qIggHpt4+EFCcTLTU/vk5ySda2ReITrtgBl60c=
github.com/gorilla/mux v1.8.1/go.mod h1:AKf9I4AEqPTmMytcMc0KkNouC66V3BtZ4qD5fmWSiMQ= github.com/gorilla/mux v1.8.0 h1:i40aqfkR1h2SlN9hojwV5ZA91wcXFOvkdNIeFDP5koI=
github.com/influxdata/influxdb-client-go/v2 v2.14.0 h1:AjbBfJuq+QoaXNcrova8smSjwJdUHnwvfjMF71M1iI4= github.com/gorilla/mux v1.8.0/go.mod h1:DVbg23sWSpFRCP0SfiEN6jmj59UnW/n46BH5rLB71So=
github.com/influxdata/influxdb-client-go/v2 v2.14.0/go.mod h1:Ahpm3QXKMJslpXl3IftVLVezreAUtBOTZssDrjZEFHI= github.com/influxdata/influxdb-client-go/v2 v2.12.3 h1:28nRlNMRIV4QbtIUvxhWqaxn0IpXeMSkY/uJa/O/vC4=
github.com/influxdata/influxdb-client-go/v2 v2.12.3/go.mod h1:IrrLUbCjjfkmRuaCiGQg4m2GbkaeJDcuWoxiWdQEbA0=
github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf h1:7JTmneyiNEwVBOHSjoMxiWAqB992atOeepeFYegn5RU= github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf h1:7JTmneyiNEwVBOHSjoMxiWAqB992atOeepeFYegn5RU=
github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo= github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
github.com/influxdata/line-protocol-corpus v0.0.0-20210519164801-ca6fa5da0184/go.mod h1:03nmhxzZ7Xk2pdG+lmMd7mHDfeVOYFyhOgwO61qWU98= github.com/influxdata/line-protocol-corpus v0.0.0-20210519164801-ca6fa5da0184/go.mod h1:03nmhxzZ7Xk2pdG+lmMd7mHDfeVOYFyhOgwO61qWU98=
github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937 h1:MHJNQ+p99hFATQm6ORoLmpUCF7ovjwEFshs/NHzAbig=
github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937/go.mod h1:BKR9c0uHSmRgM/se9JhFHtTT7JTO67X23MtKMHtZcpo= github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937/go.mod h1:BKR9c0uHSmRgM/se9JhFHtTT7JTO67X23MtKMHtZcpo=
github.com/influxdata/line-protocol/v2 v2.0.0-20210312151457-c52fdecb625a/go.mod h1:6+9Xt5Sq1rWx+glMgxhcg2c0DUaehK+5TDcPZ76GypY= github.com/influxdata/line-protocol/v2 v2.0.0-20210312151457-c52fdecb625a/go.mod h1:6+9Xt5Sq1rWx+glMgxhcg2c0DUaehK+5TDcPZ76GypY=
github.com/influxdata/line-protocol/v2 v2.1.0/go.mod h1:QKw43hdUBg3GTk2iC3iyCxksNj7PX9aUSeYOYE/ceHY= github.com/influxdata/line-protocol/v2 v2.1.0/go.mod h1:QKw43hdUBg3GTk2iC3iyCxksNj7PX9aUSeYOYE/ceHY=
github.com/influxdata/line-protocol/v2 v2.2.1 h1:EAPkqJ9Km4uAxtMRgUubJyqAr6zgWM0dznKMLRauQRE= github.com/influxdata/line-protocol/v2 v2.2.1 h1:EAPkqJ9Km4uAxtMRgUubJyqAr6zgWM0dznKMLRauQRE=
github.com/influxdata/line-protocol/v2 v2.2.1/go.mod h1:DmB3Cnh+3oxmG6LOBIxce4oaL4CPj3OmMPgvauXh+tM= github.com/influxdata/line-protocol/v2 v2.2.1/go.mod h1:DmB3Cnh+3oxmG6LOBIxce4oaL4CPj3OmMPgvauXh+tM=
github.com/iris-contrib/schema v0.0.6 h1:CPSBLyx2e91H2yJzPuhGuifVRnZBBJ3pCOMbOvPZaTw=
github.com/iris-contrib/schema v0.0.6/go.mod h1:iYszG0IOsuIsfzjymw1kMzTL8YQcCWlm65f3wX8J5iA=
github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE= github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
github.com/klauspost/compress v1.17.9 h1:6KIumPrER1LHsvBVuDa0r5xaG0Es51mhhB9BQB2qeMA= github.com/kataras/blocks v0.0.8 h1:MrpVhoFTCR2v1iOOfGng5VJSILKeZZI+7NGfxEh3SUM=
github.com/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw= github.com/kataras/blocks v0.0.8/go.mod h1:9Jm5zx6BB+06NwA+OhTbHW1xkMOYxahnqTN5DveZ2Yg=
github.com/kataras/golog v0.1.9 h1:vLvSDpP7kihFGKFAvBSofYo7qZNULYSHOH2D7rPTKJk=
github.com/kataras/golog v0.1.9/go.mod h1:jlpk/bOaYCyqDqH18pgDHdaJab72yBE6i0O3s30hpWY=
github.com/kataras/iris/v12 v12.2.7 h1:C9KWZmZT5pB5f2ot1XYWDBdi5XeTz0CGweHRXCDARZg=
github.com/kataras/iris/v12 v12.2.7/go.mod h1:mD76k/tIBFy8pHTFIgUPrVrkI4lTKvFbIcfbStJSBnA=
github.com/kataras/pio v0.0.12 h1:o52SfVYauS3J5X08fNjlGS5arXHjW/ItLkyLcKjoH6w=
github.com/kataras/pio v0.0.12/go.mod h1:ODK/8XBhhQ5WqrAhKy+9lTPS7sBf6O3KcLhc9klfRcY=
github.com/kataras/sitemap v0.0.6 h1:w71CRMMKYMJh6LR2wTgnk5hSgjVNB9KL60n5e2KHvLY=
github.com/kataras/sitemap v0.0.6/go.mod h1:dW4dOCNs896OR1HmG+dMLdT7JjDk7mYBzoIRwuj5jA4=
github.com/kataras/tunnel v0.0.4 h1:sCAqWuJV7nPzGrlb0os3j49lk2JhILT0rID38NHNLpA=
github.com/kataras/tunnel v0.0.4/go.mod h1:9FkU4LaeifdMWqZu7o20ojmW4B7hdhv2CMLwfnHGpYw=
github.com/klauspost/compress v1.17.0 h1:Rnbp4K9EjcDuVuHtd0dgA4qNuv9yKDYKK1ulpJwgrqM=
github.com/klauspost/compress v1.17.0/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
github.com/klauspost/cpuid/v2 v2.2.5 h1:0E5MSMDEoAulmXNFquVs//DdoomxaoTY1kUhbc/qbZg=
github.com/klauspost/cpuid/v2 v2.2.5/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws=
github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI= github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI= github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE= github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc= github.com/labstack/echo/v4 v4.11.1 h1:dEpLU2FLg4UVmvCGPuk/APjlH6GDpbEPti61srUUUs4=
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw= github.com/labstack/echo/v4 v4.11.1/go.mod h1:YuYRTSM3CHs2ybfrL8Px48bO6BAnYIN4l8wSTMP6BDQ=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA= github.com/labstack/gommon v0.4.0 h1:y7cvthEAEbU0yHOf4axH8ZG2NH8knB9iNSoTO8dyIk8=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ= github.com/labstack/gommon v0.4.0/go.mod h1:uW6kP17uPlLJsD3ijUYn3/M5bAxtlZhMI6m3MFxTMTM=
github.com/nats-io/nats.go v1.39.0 h1:2/yg2JQjiYYKLwDuBzV0FbB2sIV+eFNkEevlRi4n9lI= github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
github.com/nats-io/nats.go v1.39.0/go.mod h1:MgRb8oOdigA6cYpEPhXJuRVH6UE/V4jblJ2jQ27IXYM= github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
github.com/nats-io/nkeys v0.4.9 h1:qe9Faq2Gxwi6RZnZMXfmGMZkg3afLLOtrU+gDZJ35b0= github.com/mailgun/raymond/v2 v2.0.48 h1:5dmlB680ZkFG2RN/0lvTAghrSxIESeu9/2aeDqACtjw=
github.com/nats-io/nkeys v0.4.9/go.mod h1:jcMqs+FLG+W5YO36OX6wFIFcmpdAns+w1Wm6D3I/evE= github.com/mailgun/raymond/v2 v2.0.48/go.mod h1:lsgvL50kgt1ylcFJYZiULi5fjPBkkhNfj4KA0W54Z18=
github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
github.com/mattn/go-colorable v0.1.11/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
github.com/microcosm-cc/bluemonday v1.0.25 h1:4NEwSfiJ+Wva0VxN5B8OwMicaJvD8r9tlJWm9rtloEg=
github.com/microcosm-cc/bluemonday v1.0.25/go.mod h1:ZIOjCQp1OrzBBPIJmfX4qDYFuhU02nx4bn030ixfHLE=
github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
github.com/nats-io/nats-server/v2 v2.8.4/go.mod h1:8zZa+Al3WsESfmgSs98Fi06dRWLH5Bnq90m5bKD/eT4=
github.com/nats-io/nats.go v1.30.2 h1:aloM0TGpPorZKQhbAkdCzYDj+ZmsJDyeo3Gkbr72NuY=
github.com/nats-io/nats.go v1.30.2/go.mod h1:dcfhUgmQNN4GJEfIb2f9R7Fow+gzBF4emzDHrVBd5qM=
github.com/nats-io/nkeys v0.4.5 h1:Zdz2BUlFm4fJlierwvGK+yl20IAKUm7eV6AAZXEhkPk=
github.com/nats-io/nkeys v0.4.5/go.mod h1:XUkxdLPTufzlihbamfzQ7mw/VGx6ObUs+0bN5sNvt64=
github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw= github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c= github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c=
github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno= github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro= github.com/pelletier/go-toml/v2 v2.1.0 h1:FnwAJ4oYMvbT/34k9zzHuZNrhlz48GB3/s6at6/MHO4=
github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg= github.com/pelletier/go-toml/v2 v2.1.0/go.mod h1:tJU2Z3ZkXwnxa4DPO899bsyIoywizdUvyaeZurnPPDc=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+bR9r+8l63Y= github.com/prometheus/client_golang v1.17.0 h1:rl2sfwZMtSthVU752MqfjQozy7blglC+1SOtjMAMh+Q=
github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE= github.com/prometheus/client_golang v1.17.0/go.mod h1:VeL+gMmOAxkS2IqfCq0ZmHSL+LjWfWDUmp1mBz9JgUY=
github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E= github.com/prometheus/client_model v0.5.0 h1:VQw1hfvPvk3Uv6Qf29VrPF32JB6rtbgI6cYPYQjL0Qw=
github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY= github.com/prometheus/client_model v0.5.0/go.mod h1:dTiFglRmd66nLR9Pv9f0mZi7B7fk5Pm3gvsjB5tr+kI=
github.com/prometheus/common v0.55.0 h1:KEi6DK7lXW/m7Ig5i47x0vRzuBsHuvJdi5ee6Y3G1dc= github.com/prometheus/common v0.44.0 h1:+5BrQJwiBB9xsMygAB3TNvpQKOwlkc25LbISbrdOOfY=
github.com/prometheus/common v0.55.0/go.mod h1:2SECS4xJG1kd8XF9IcM1gMX6510RAEL65zxzNImwdc8= github.com/prometheus/common v0.44.0/go.mod h1:ofAIvZbQ1e/nugmZGz4/qCb9Ap1VoSTIO7x0VV9VvuY=
github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc= github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk= github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ= github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog= github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 h1:lZUw3E0/J3roVtGQ+SCrUrg3ON6NgVqpn3+iol9aGu4= github.com/schollz/closestmatch v2.1.0+incompatible h1:Uel2GXEpJqOWBrlyI+oY9LTiyyjYS17cCYRqP13/SHk=
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1/go.mod h1:uToXkOrWAZ6/Oc07xWQrPOhJotwFIyu2bBVN41fcDUY= github.com/schollz/closestmatch v2.1.0+incompatible/go.mod h1:RtP1ddjLong6gTkbtmuhtR2uUrrJOpYzYRvbcPAid+g=
github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8= github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8=
github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o= github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
github.com/sirupsen/logrus v1.8.1/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0= github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
github.com/stmcginnis/gofish v0.15.0 h1:8TG41+lvJk/0Nf8CIIYErxbMlQUy80W0JFRZP3Ld82A= github.com/stmcginnis/gofish v0.14.0 h1:geECNAiG33JDB2x2xDkerpOOuXFqxp5YP3EFE3vd5iM=
github.com/stmcginnis/gofish v0.15.0/go.mod h1:BLDSFTp8pDlf/xDbLZa+F7f7eW0E/CHCboggsu8CznI= github.com/stmcginnis/gofish v0.14.0/go.mod h1:BLDSFTp8pDlf/xDbLZa+F7f7eW0E/CHCboggsu8CznI=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw= github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo= github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU= github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo= github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg= github.com/tdewolff/minify/v2 v2.12.9 h1:dvn5MtmuQ/DFMwqf5j8QhEVpPX6fi3WGImhv8RUB4zA=
github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY= github.com/tdewolff/minify/v2 v2.12.9/go.mod h1:qOqdlDfL+7v0/fyymB+OP497nIxJYSvX4MQWA8OoiXU=
github.com/tklauser/go-sysconf v0.3.13 h1:GBUpcahXSpR2xN01jhkNAbTLRk2Yzgggk8IM08lq3r4= github.com/tdewolff/parse/v2 v2.6.8 h1:mhNZXYCx//xG7Yq2e/kVLNZw4YfYmeHbhx+Zc0OvFMA=
github.com/tklauser/go-sysconf v0.3.13/go.mod h1:zwleP4Q4OehZHGn4CYZDipCgg9usW5IJePewFCGVEa0= github.com/tdewolff/parse/v2 v2.6.8/go.mod h1:XHDhaU6IBgsryfdnpzUXBlT6leW/l25yrFBTEb4eIyM=
github.com/tklauser/numcpus v0.7.0 h1:yjuerZP127QG9m5Zh/mSO4wqurYil27tHrqwRoRjpr4= github.com/tdewolff/test v1.0.9/go.mod h1:6DAvZliBAAnD7rhVgwaM7DE5/d9NMOAJ09SqYqeK4QE=
github.com/tklauser/numcpus v0.7.0/go.mod h1:bb6dMVcj8A42tSE7i32fsIUCbQNllK5iDguyOZRUzAY= github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU=
github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk=
github.com/tklauser/numcpus v0.6.1/go.mod h1:1XfjsgE2zo8GVw7POkMbHENHzVg3GzmoZ9fESEdAacY=
github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6KllzawFIhcdPw=
github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
github.com/valyala/fasttemplate v1.2.1/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
github.com/valyala/fasttemplate v1.2.2 h1:lxLXG0uE3Qnshl9QyaK6XJxMXlQZELvChBOCmQD0Loo=
github.com/valyala/fasttemplate v1.2.2/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
github.com/vmihailenco/msgpack/v5 v5.4.0 h1:hRM0digJwyR6vll33NNAwCFguy5JuBD6jxDmQP3l608=
github.com/vmihailenco/msgpack/v5 v5.4.0/go.mod h1:GaZTsDaehaPpQVyxrf5mtQlH+pc21PIudVV/E3rRQok=
github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAhO7/IwNM9g=
github.com/vmihailenco/tagparser/v2 v2.0.0/go.mod h1:Wri+At7QHww0WTrCBeu4J6bNtoV6mEfg5OIWRZA9qds=
github.com/yosssi/ace v0.0.5 h1:tUkIP/BLdKqrlrPwcmH0shwEEhTRHoGnc1wFIWmaBUA=
github.com/yosssi/ace v0.0.5/go.mod h1:ALfIzm2vT7t5ZE7uoIZqF3TQ7SAOyupFZnkrF5id+K0=
github.com/yuin/goldmark v1.4.1/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg= golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg=
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE= golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE=
golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U= golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk= golang.org/x/arch v0.5.0 h1:jpGode6huXQxcskEIpOCvrU+tzo81b6+oFLUYXWtH/Y=
golang.org/x/crypto v0.35.0 h1:b15kiHdrGCHrP6LvwaQ3c03kgNhhiMgvlhxHQhmg2Xs= golang.org/x/arch v0.5.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
golang.org/x/crypto v0.35.0/go.mod h1:dy7dXNW32cAb/6/PRuTNsix8T+vJAqvuIy5Bli/x0YQ= golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f h1:oFMYAjX0867ZD2jcNiLBrI9BdpmEkvPyi5YrBGXbamg= golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk= golang.org/x/crypto v0.14.0 h1:wBqGXzWJW6m1XrIKlAH0Hs1JJ7+9KBwnIO8v66Q9cHc=
golang.org/x/net v0.31.0 h1:68CPQngjLL0r2AlUKiSxtQFKvzRVbnzLwMUn5SzcLHo= golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
golang.org/x/net v0.31.0/go.mod h1:P4fl1q7dY2hnZFxEk4pPSkDHF+QqjitcnDjUQyMM+pM= golang.org/x/exp v0.0.0-20231006140011-7918f672742d h1:jtJma62tbqLibJ5sFQz8bKtEM8rJBtfilJ2qTU199MI=
golang.org/x/net v0.36.0 h1:vWF2fRbw4qslQsQzgFqZff+BItCvGFQqKzKIzx1rmoA= golang.org/x/exp v0.0.0-20231006140011-7918f672742d/go.mod h1:ldy0pHrwJyGW56pPQzzkH36rKxoZW1tw7ZJpeKx+hdo=
golang.org/x/net v0.36.0/go.mod h1:bFmbeoIPfrw4sMHNhb4J9f6+tPziuGjq7Jk/38fxi1I= golang.org/x/mod v0.5.1/go.mod h1:5OXOZSfqPIIbmVBIIKWRFfZjPR0E5r58TLhUjH0a2Ro=
golang.org/x/net v0.0.0-20190327091125-710a502c58a2/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20211015210444-4f30a5c0130f/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.16.0 h1:7eBu7KsSvFDtSXUIDbh3aqlK4DPsZ1rByC8PFfBThos=
golang.org/x/net v0.16.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA= golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.30.0 h1:QjkSwP/36a20jFYWkSue1YwXzLmsV5Gfq7Eiy72C1uc= golang.org/x/sys v0.0.0-20210927094055-39ccf1dd6fa6/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.30.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.0.0-20211019181941-9d821ace8654/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20211103235746-7861aae1554b/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.13.0 h1:Af8nKPmuFypiUBjVoU9V20FiaFXOcuZI21p0ycVYYGE=
golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=
golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
golang.org/x/time v0.3.0 h1:rg5rLMjNzMS1RkNLzCG38eapWhnYLFYXDXj2gOlr8j4=
golang.org/x/time v0.3.0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.9/go.mod h1:nABZi5QlRsZVlzPpHl034qft6wpY4eDcsTt5AaioBiU=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
google.golang.org/protobuf v1.35.2 h1:8Ar7bF+apOIoThw1EdZl0p1oWvMqTHmpA2fRTyZO8io= golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
google.golang.org/protobuf v1.35.2/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE= 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 v1.31.0 h1:g0LDEJHgrBl9N9r17Ru3sqWhkIx2NB67okBHPwC7hs8=
google.golang.org/protobuf v1.31.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/ini.v1 v1.67.0 h1:Dgnx+6+nfE+IfzjUEISNeydPJh9AXNNsWbGP9KzCsOA=
gopkg.in/ini.v1 v1.67.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

View File

@ -1,14 +1,3 @@
<!--
---
title: Metric Aggregator
description: Subsystem for evaluating expressions on metrics (deprecated)
categories: [cc-metric-collector]
tags: ['Developer']
weight: 1
hugo_path: docs/reference/cc-metric-collector/internal/metricaggregator/_index.md
---
-->
# The MetricAggregator # The MetricAggregator
In some cases, further combination of metrics or raw values is required. For that strings like `foo + 1` with runtime dependent `foo` need to be evaluated. The MetricAggregator relies on the [`gval`](https://github.com/PaesslerAG/gval) Golang package to perform all expression evaluation. The `gval` package provides the basic arithmetic operations but the MetricAggregator defines additional ones. In some cases, further combination of metrics or raw values is required. For that strings like `foo + 1` with runtime dependent `foo` need to be evaluated. The MetricAggregator relies on the [`gval`](https://github.com/PaesslerAG/gval) Golang package to perform all expression evaluation. The `gval` package provides the basic arithmetic operations but the MetricAggregator defines additional ones.
@ -46,4 +35,4 @@ The MetricAggregator provides these functions additional to the `Full` language
## Limitations ## Limitations
- Since the metrics are written in JSON files which do not allow `""` without proper escaping inside of JSON strings, you have to use `''` for strings. - Since the metrics are written in JSON files which do not allow `""` without proper escaping inside of JSON strings, you have to use `''` for strings.
- Since `\` is interpreted by JSON as escape character, it cannot be used in metrics. But it is required to write regular expressions. So instead of `/`, use `%` and the MetricAggregator replaces them after reading the JSON file. - Since `\` is interpreted by JSON as escape character, it cannot be used in metrics. But it is required to write regular expressions. So instead of `/`, use `%` and the MetricAggregator replaces them after reading the JSON file.

View File

@ -9,9 +9,9 @@ import (
"sync" "sync"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage" lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology" topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
"github.com/PaesslerAG/gval" "github.com/PaesslerAG/gval"
@ -31,14 +31,14 @@ type metricAggregator struct {
functions []*MetricAggregatorIntervalConfig functions []*MetricAggregatorIntervalConfig
constants map[string]interface{} constants map[string]interface{}
language gval.Language language gval.Language
output chan lp.CCMessage output chan lp.CCMetric
} }
type MetricAggregator interface { type MetricAggregator interface {
AddAggregation(name, function, condition string, tags, meta map[string]string) error AddAggregation(name, function, condition string, tags, meta map[string]string) error
DeleteAggregation(name string) error DeleteAggregation(name string) error
Init(output chan lp.CCMessage) error Init(output chan lp.CCMetric) error
Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMessage) Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMetric)
} }
var metricCacheLanguage = gval.NewLanguage( var metricCacheLanguage = gval.NewLanguage(
@ -74,7 +74,7 @@ var evaluables = struct {
mapping: make(map[string]gval.Evaluable), mapping: make(map[string]gval.Evaluable),
} }
func (c *metricAggregator) Init(output chan lp.CCMessage) error { func (c *metricAggregator) Init(output chan lp.CCMetric) error {
c.output = output c.output = output
c.functions = make([]*MetricAggregatorIntervalConfig, 0) c.functions = make([]*MetricAggregatorIntervalConfig, 0)
c.constants = make(map[string]interface{}) c.constants = make(map[string]interface{})
@ -112,7 +112,7 @@ func (c *metricAggregator) Init(output chan lp.CCMessage) error {
return nil return nil
} }
func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMessage) { func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMetric) {
vars := make(map[string]interface{}) vars := make(map[string]interface{})
for k, v := range c.constants { for k, v := range c.constants {
vars[k] = v vars[k] = v
@ -127,7 +127,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
var valuesInt32 []int32 var valuesInt32 []int32
var valuesInt64 []int64 var valuesInt64 []int64
var valuesBool []bool var valuesBool []bool
matches := make([]lp.CCMessage, 0) matches := make([]lp.CCMetric, 0)
for _, m := range metrics { for _, m := range metrics {
vars["metric"] = m vars["metric"] = m
//value, err := gval.Evaluate(f.Condition, vars, c.language) //value, err := gval.Evaluate(f.Condition, vars, c.language)
@ -216,7 +216,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
break break
} }
copy_tags := func(tags map[string]string, metrics []lp.CCMessage) map[string]string { copy_tags := func(tags map[string]string, metrics []lp.CCMetric) map[string]string {
out := make(map[string]string) out := make(map[string]string)
for key, value := range tags { for key, value := range tags {
switch value { switch value {
@ -233,7 +233,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
} }
return out return out
} }
copy_meta := func(meta map[string]string, metrics []lp.CCMessage) map[string]string { copy_meta := func(meta map[string]string, metrics []lp.CCMetric) map[string]string {
out := make(map[string]string) out := make(map[string]string)
for key, value := range meta { for key, value := range meta {
switch value { switch value {
@ -253,18 +253,18 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
tags := copy_tags(f.Tags, matches) tags := copy_tags(f.Tags, matches)
meta := copy_meta(f.Meta, matches) meta := copy_meta(f.Meta, matches)
var m lp.CCMessage var m lp.CCMetric
switch t := value.(type) { switch t := value.(type) {
case float64: case float64:
m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime) m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
case float32: case float32:
m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime) m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
case int: case int:
m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime) m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
case int64: case int64:
m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime) m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
case string: case string:
m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime) m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
default: default:
cclog.ComponentError("MetricCache", "Gval returned invalid type", t, "skipping metric", f.Name) cclog.ComponentError("MetricCache", "Gval returned invalid type", t, "skipping metric", f.Name)
} }
@ -389,7 +389,7 @@ func EvalFloat64Condition(condition string, params map[string]float64) (float64,
return value, err return value, err
} }
func NewAggregator(output chan lp.CCMessage) (MetricAggregator, error) { func NewAggregator(output chan lp.CCMetric) (MetricAggregator, error) {
a := new(metricAggregator) a := new(metricAggregator)
err := a.Init(output) err := a.Init(output)
if err != nil { if err != nil {

View File

@ -1,32 +1,15 @@
<!--
---
title: Message Router
description: Routing component inside cc-metric-collector
categories: [cc-metric-collector]
tags: ['Developer']
weight: 1
hugo_path: docs/reference/cc-metric-collector/internal/metricrouter/_index.md
---
-->
# CC Metric Router # CC Metric Router
The CCMetric router sits in between the collectors and the sinks and can be used to add and remove tags to/from traversing [CCMessages](https://pkg.go.dev/github.com/ClusterCockpit/cc-lib/ccMessage). The CCMetric router sits in between the collectors and the sinks and can be used to add and remove tags to/from traversing [CCMetrics](../ccMetric/README.md).
# Configuration # Configuration
**Note**: Use the [message processor configuration](https://github.com/ClusterCockpit/cc-lib/blob/main/messageProcessor/README.md) with option `process_messages`.
```json ```json
{ {
"num_cache_intervals" : 1, "num_cache_intervals" : 1,
"interval_timestamp" : true, "interval_timestamp" : true,
"hostname_tag" : "hostname", "hostname_tag" : "hostname",
"max_forward" : 50, "max_forward" : 50,
"process_messages": {
"see": "pkg/messageProcessor/README.md"
},
"add_tags" : [ "add_tags" : [
{ {
"key" : "cluster", "key" : "cluster",
@ -80,8 +63,6 @@ The CCMetric router sits in between the collectors and the sinks and can be used
There are three main options `add_tags`, `delete_tags` and `interval_timestamp`. `add_tags` and `delete_tags` are lists consisting of dicts with `key`, `value` and `if`. The `value` can be omitted in the `delete_tags` part as it only uses the `key` for removal. The `interval_timestamp` setting means that a unique timestamp is applied to all metrics traversing the router during an interval. There are three main options `add_tags`, `delete_tags` and `interval_timestamp`. `add_tags` and `delete_tags` are lists consisting of dicts with `key`, `value` and `if`. The `value` can be omitted in the `delete_tags` part as it only uses the `key` for removal. The `interval_timestamp` setting means that a unique timestamp is applied to all metrics traversing the router during an interval.
**Note**: Use the [message processor configuration](https://github.com/ClusterCockpit/cc-lib/blob/main/messageProcessor/README.md) (option `process_messages`) instead of `add_tags`, `delete_tags`, `drop_metrics`, `drop_metrics_if`, `rename_metrics`, `normalize_units` and `change_unit_prefix`. These options are deprecated and will be removed in future versions. Until then, they are added to the message processor.
# Processing order in the router # Processing order in the router
- Add the `hostname_tag` tag (if sent by collectors or cache) - Add the `hostname_tag` tag (if sent by collectors or cache)
@ -115,8 +96,6 @@ Every time the router receives a metric through any of the channels, it tries to
# The `rename_metrics` option # The `rename_metrics` option
__deprecated__
In the ClusterCockpit world we specified a set of standard metrics. Since some collectors determine the metric names based on files, execuables and libraries, they might change from system to system (or installation to installtion, OS to OS, ...). In order to get the common names, you can rename incoming metrics before sending them to the sink. If the metric name matches the `oldname`, it is changed to `newname` In the ClusterCockpit world we specified a set of standard metrics. Since some collectors determine the metric names based on files, execuables and libraries, they might change from system to system (or installation to installtion, OS to OS, ...). In order to get the common names, you can rename incoming metrics before sending them to the sink. If the metric name matches the `oldname`, it is changed to `newname`
```json ```json
@ -128,8 +107,6 @@ In the ClusterCockpit world we specified a set of standard metrics. Since some c
# Conditional manipulation of tags (`add_tags` and `del_tags`) # Conditional manipulation of tags (`add_tags` and `del_tags`)
__deprecated__
Common config format: Common config format:
```json ```json
{ {
@ -141,8 +118,6 @@ Common config format:
## The `del_tags` option ## The `del_tags` option
__deprecated__
The collectors are free to add whatever `key=value` pair to the metric tags (although the usage of tags should be minimized). If you want to delete a tag afterwards, you can do that. When the `if` condition matches on a metric, the `key` is removed from the metric's tags. The collectors are free to add whatever `key=value` pair to the metric tags (although the usage of tags should be minimized). If you want to delete a tag afterwards, you can do that. When the `if` condition matches on a metric, the `key` is removed from the metric's tags.
If you want to remove a tag for all metrics, use the condition wildcard `*`. The `value` field can be omitted in the `del_tags` case. If you want to remove a tag for all metrics, use the condition wildcard `*`. The `value` field can be omitted in the `del_tags` case.
@ -154,8 +129,6 @@ Never delete tags:
## The `add_tags` option ## The `add_tags` option
__deprecated__
In some cases, metrics should be tagged or an existing tag changed based on some condition. This can be done in the `add_tags` section. When the `if` condition evaluates to `true`, the tag `key` is added or gets changed to the new `value`. In some cases, metrics should be tagged or an existing tag changed based on some condition. This can be done in the `add_tags` section. When the `if` condition evaluates to `true`, the tag `key` is added or gets changed to the new `value`.
If the CCMetric name is equal to `temp_package_id_0`, it adds an additional tag `test=testing` to the metric. If the CCMetric name is equal to `temp_package_id_0`, it adds an additional tag `test=testing` to the metric.
@ -197,8 +170,6 @@ In some cases, you want to drop a metric and don't get it forwarded to the sinks
## The `drop_metrics` section ## The `drop_metrics` section
__deprecated__
The argument is a list of metric names. No futher checks are performed, only a comparison of the metric name The argument is a list of metric names. No futher checks are performed, only a comparison of the metric name
```json ```json
@ -214,8 +185,6 @@ The example drops all metrics with the name `drop_metric_1` and `drop_metric_2`.
## The `drop_metrics_if` section ## The `drop_metrics_if` section
__deprecated__
This option takes a list of evaluable conditions and performs them one after the other on **all** metrics incoming from the collectors and the metric cache (aka `interval_aggregates`). This option takes a list of evaluable conditions and performs them one after the other on **all** metrics incoming from the collectors and the metric cache (aka `interval_aggregates`).
```json ```json
@ -231,22 +200,15 @@ The first line is comparable with the example in `drop_metrics`, it drops all me
# Manipulating the metric units # Manipulating the metric units
## The `normalize_units` option ## The `normalize_units` option
__deprecated__
The cc-metric-collector tries to read the data from the system as it is reported. If available, it tries to read the metric unit from the system as well (e.g. from `/proc/meminfo`). The problem is that, depending on the source, the metric units are named differently. Just think about `byte`, `Byte`, `B`, `bytes`, ... The cc-metric-collector tries to read the data from the system as it is reported. If available, it tries to read the metric unit from the system as well (e.g. from `/proc/meminfo`). The problem is that, depending on the source, the metric units are named differently. Just think about `byte`, `Byte`, `B`, `bytes`, ...
The [cc-units](https://github.com/ClusterCockpit/cc-units) package provides us a normalization option to use the same metric unit name for all metrics. It this option is set to true, all `unit` meta tags are normalized. The [cc-units](https://github.com/ClusterCockpit/cc-units) package provides us a normalization option to use the same metric unit name for all metrics. It this option is set to true, all `unit` meta tags are normalized.
## The `change_unit_prefix` section ## The `change_unit_prefix` section
__deprecated__
It is often the case that metrics are reported by the system using a rather outdated unit prefix (like `/proc/meminfo` still uses kByte despite current memory sizes are in the GByte range). If you want to change the prefix of a unit, you can do that with the help of [cc-units](https://github.com/ClusterCockpit/cc-units). The setting works on the metric name and requires the new prefix for the metric. The cc-units package determines the scaling factor. It is often the case that metrics are reported by the system using a rather outdated unit prefix (like `/proc/meminfo` still uses kByte despite current memory sizes are in the GByte range). If you want to change the prefix of a unit, you can do that with the help of [cc-units](https://github.com/ClusterCockpit/cc-units). The setting works on the metric name and requires the new prefix for the metric. The cc-units package determines the scaling factor.
# Aggregate metric values of the current interval with the `interval_aggregates` option # Aggregate metric values of the current interval with the `interval_aggregates` option
**Note:** `interval_aggregates` works only if `num_cache_intervals` > 0 and is **experimental** **Note:** `interval_aggregates` works only if `num_cache_intervals` > 0
In some cases, you need to derive new metrics based on the metrics arriving during an interval. This can be done in the `interval_aggregates` section. The logic is similar to the other metric manipulation and filtering options. A cache stores all metrics that arrive during an interval. At the beginning of the *next* interval, the list of metrics is submitted to the MetricAggregator. It derives new metrics and submits them back to the MetricRouter, so they are sent in the next interval but have the timestamp of the previous interval beginning. In some cases, you need to derive new metrics based on the metrics arriving during an interval. This can be done in the `interval_aggregates` section. The logic is similar to the other metric manipulation and filtering options. A cache stores all metrics that arrive during an interval. At the beginning of the *next* interval, the list of metrics is submitted to the MetricAggregator. It derives new metrics and submits them back to the MetricRouter, so they are sent in the next interval but have the timestamp of the previous interval beginning.
@ -274,7 +236,7 @@ The above configuration, collects all metric values for metrics evaluating `if`
If you are not interested in the input metrics `sub_metric_%d+` at all, you can add the same condition used here to the `drop_metrics_if` section to drop them. If you are not interested in the input metrics `sub_metric_%d+` at all, you can add the same condition used here to the `drop_metrics_if` section to drop them.
Use cases for `interval_aggregates`: Use cases for `interval_aggregates`:
- Combine multiple metrics of the a collector to a new one like the [MemstatCollector](../../collectors/memstatMetric.md) does it for `mem_used`: - Combine multiple metrics of the a collector to a new one like the [MemstatCollector](../../collectors/memstatMetric.md) does it for `mem_used`)):
```json ```json
{ {
"name" : "mem_used", "name" : "mem_used",

View File

@ -4,10 +4,10 @@ import (
"sync" "sync"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage"
agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator" agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker" mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
) )
@ -16,7 +16,7 @@ type metricCachePeriod struct {
stopstamp time.Time stopstamp time.Time
numMetrics int numMetrics int
sizeMetrics int sizeMetrics int
metrics []lp.CCMessage metrics []lp.CCMetric
} }
// Metric cache data structure // Metric cache data structure
@ -29,21 +29,21 @@ type metricCache struct {
ticker mct.MultiChanTicker ticker mct.MultiChanTicker
tickchan chan time.Time tickchan chan time.Time
done chan bool done chan bool
output chan lp.CCMessage output chan lp.CCMetric
aggEngine agg.MetricAggregator aggEngine agg.MetricAggregator
} }
type MetricCache interface { type MetricCache interface {
Init(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error Init(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error
Start() Start()
Add(metric lp.CCMessage) Add(metric lp.CCMetric)
GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage) GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric)
AddAggregation(name, function, condition string, tags, meta map[string]string) error AddAggregation(name, function, condition string, tags, meta map[string]string) error
DeleteAggregation(name string) error DeleteAggregation(name string) error
Close() Close()
} }
func (c *metricCache) Init(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error { func (c *metricCache) Init(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error {
var err error = nil var err error = nil
c.done = make(chan bool) c.done = make(chan bool)
c.wg = wg c.wg = wg
@ -55,7 +55,7 @@ func (c *metricCache) Init(output chan lp.CCMessage, ticker mct.MultiChanTicker,
p := new(metricCachePeriod) p := new(metricCachePeriod)
p.numMetrics = 0 p.numMetrics = 0
p.sizeMetrics = 0 p.sizeMetrics = 0
p.metrics = make([]lp.CCMessage, 0) p.metrics = make([]lp.CCMetric, 0)
c.intervals = append(c.intervals, p) c.intervals = append(c.intervals, p)
} }
@ -124,7 +124,7 @@ func (c *metricCache) Start() {
// Add a metric to the cache. The interval is defined by the global timer (rotate() in Start()) // Add a metric to the cache. The interval is defined by the global timer (rotate() in Start())
// The intervals list is used as round-robin buffer and the metric list grows dynamically and // The intervals list is used as round-robin buffer and the metric list grows dynamically and
// to avoid reallocations // to avoid reallocations
func (c *metricCache) Add(metric lp.CCMessage) { func (c *metricCache) Add(metric lp.CCMetric) {
if c.curPeriod >= 0 && c.curPeriod < c.numPeriods { if c.curPeriod >= 0 && c.curPeriod < c.numPeriods {
c.lock.Lock() c.lock.Lock()
p := c.intervals[c.curPeriod] p := c.intervals[c.curPeriod]
@ -153,10 +153,10 @@ func (c *metricCache) DeleteAggregation(name string) error {
// Get all metrics of a interval. The index is the difference to the current interval, so index=0 // Get all metrics of a interval. The index is the difference to the current interval, so index=0
// is the current one, index=1 the last interval and so on. Returns and empty array if a wrong index // is the current one, index=1 the last interval and so on. Returns and empty array if a wrong index
// is given (negative index, index larger than configured number of total intervals, ...) // is given (negative index, index larger than configured number of total intervals, ...)
func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage) { func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric) {
var start time.Time = time.Now() var start time.Time = time.Now()
var stop time.Time = time.Now() var stop time.Time = time.Now()
var metrics []lp.CCMessage var metrics []lp.CCMetric
if index >= 0 && index < c.numPeriods { if index >= 0 && index < c.numPeriods {
pindex := c.curPeriod - index pindex := c.curPeriod - index
if pindex < 0 { if pindex < 0 {
@ -168,10 +168,10 @@ func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage
metrics = c.intervals[pindex].metrics metrics = c.intervals[pindex].metrics
//return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics //return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
} else { } else {
metrics = make([]lp.CCMessage, 0) metrics = make([]lp.CCMetric, 0)
} }
} else { } else {
metrics = make([]lp.CCMessage, 0) metrics = make([]lp.CCMetric, 0)
} }
return start, stop, metrics return start, stop, metrics
} }
@ -182,7 +182,7 @@ func (c *metricCache) Close() {
c.done <- true c.done <- true
} }
func NewCache(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) (MetricCache, error) { func NewCache(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) (MetricCache, error) {
c := new(metricCache) c := new(metricCache)
err := c.Init(output, ticker, wg, numPeriods) err := c.Init(output, ticker, wg, numPeriods)
if err != nil { if err != nil {

View File

@ -2,18 +2,17 @@ package metricRouter
import ( import (
"encoding/json" "encoding/json"
"fmt"
"os" "os"
"strings" "strings"
"sync" "sync"
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage"
mp "github.com/ClusterCockpit/cc-lib/messageProcessor"
agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator" agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker" mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
units "github.com/ClusterCockpit/cc-units"
) )
const ROUTER_MAX_FORWARD = 50 const ROUTER_MAX_FORWARD = 50
@ -39,17 +38,16 @@ type metricRouterConfig struct {
MaxForward int `json:"max_forward"` // Number of maximal forwarded metrics at one select MaxForward int `json:"max_forward"` // Number of maximal forwarded metrics at one select
NormalizeUnits bool `json:"normalize_units"` // Check unit meta flag and normalize it using cc-units NormalizeUnits bool `json:"normalize_units"` // Check unit meta flag and normalize it using cc-units
ChangeUnitPrefix map[string]string `json:"change_unit_prefix"` // Add prefix that should be applied to the metrics ChangeUnitPrefix map[string]string `json:"change_unit_prefix"` // Add prefix that should be applied to the metrics
// dropMetrics map[string]bool // Internal map for O(1) lookup dropMetrics map[string]bool // Internal map for O(1) lookup
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
} }
// Metric router data structure // Metric router data structure
type metricRouter struct { type metricRouter struct {
hostname string // Hostname used in tags hostname string // Hostname used in tags
coll_input chan lp.CCMessage // Input channel from CollectorManager coll_input chan lp.CCMetric // Input channel from CollectorManager
recv_input chan lp.CCMessage // Input channel from ReceiveManager recv_input chan lp.CCMetric // Input channel from ReceiveManager
cache_input chan lp.CCMessage // Input channel from MetricCache cache_input chan lp.CCMetric // Input channel from MetricCache
outputs []chan lp.CCMessage // List of all output channels outputs []chan lp.CCMetric // List of all output channels
done chan bool // channel to finish / stop metric router done chan bool // channel to finish / stop metric router
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
timestamp time.Time // timestamp periodically updated by ticker each interval timestamp time.Time // timestamp periodically updated by ticker each interval
@ -58,15 +56,14 @@ type metricRouter struct {
cache MetricCache // pointer to MetricCache cache MetricCache // pointer to MetricCache
cachewg sync.WaitGroup // wait group for MetricCache cachewg sync.WaitGroup // wait group for MetricCache
maxForward int // number of metrics to forward maximally in one iteration maxForward int // number of metrics to forward maximally in one iteration
mp mp.MessageProcessor
} }
// MetricRouter access functions // MetricRouter access functions
type MetricRouter interface { type MetricRouter interface {
Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfig json.RawMessage) error Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) error
AddCollectorInput(input chan lp.CCMessage) AddCollectorInput(input chan lp.CCMetric)
AddReceiverInput(input chan lp.CCMessage) AddReceiverInput(input chan lp.CCMetric)
AddOutput(output chan lp.CCMessage) AddOutput(output chan lp.CCMetric)
Start() Start()
Close() Close()
} }
@ -77,10 +74,10 @@ type MetricRouter interface {
// * wait group synchronization (from variable wg) // * wait group synchronization (from variable wg)
// * ticker (from variable ticker) // * ticker (from variable ticker)
// * configuration (read from config file in variable routerConfigFile) // * configuration (read from config file in variable routerConfigFile)
func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfig json.RawMessage) error { func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) error {
r.outputs = make([]chan lp.CCMessage, 0) r.outputs = make([]chan lp.CCMetric, 0)
r.done = make(chan bool) r.done = make(chan bool)
r.cache_input = make(chan lp.CCMessage) r.cache_input = make(chan lp.CCMetric)
r.wg = wg r.wg = wg
r.ticker = ticker r.ticker = ticker
r.config.MaxForward = ROUTER_MAX_FORWARD r.config.MaxForward = ROUTER_MAX_FORWARD
@ -95,7 +92,15 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
// Drop domain part of host name // Drop domain part of host name
r.hostname = strings.SplitN(hostname, `.`, 2)[0] r.hostname = strings.SplitN(hostname, `.`, 2)[0]
err = json.Unmarshal(routerConfig, &r.config) // Read metric router config file
configFile, err := os.Open(routerConfigFile)
if err != nil {
cclog.ComponentError("MetricRouter", err.Error())
return err
}
defer configFile.Close()
jsonParser := json.NewDecoder(configFile)
err = jsonParser.Decode(&r.config)
if err != nil { if err != nil {
cclog.ComponentError("MetricRouter", err.Error()) cclog.ComponentError("MetricRouter", err.Error())
return err return err
@ -114,56 +119,14 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
r.cache.AddAggregation(agg.Name, agg.Function, agg.Condition, agg.Tags, agg.Meta) r.cache.AddAggregation(agg.Name, agg.Function, agg.Condition, agg.Tags, agg.Meta)
} }
} }
p, err := mp.NewMessageProcessor() r.config.dropMetrics = make(map[string]bool)
if err != nil {
return fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
r.mp = p
if len(r.config.MessageProcessor) > 0 {
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
if err != nil {
return fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
for _, mname := range r.config.DropMetrics { for _, mname := range r.config.DropMetrics {
r.mp.AddDropMessagesByName(mname) r.config.dropMetrics[mname] = true
} }
for _, cond := range r.config.DropMetricsIf {
r.mp.AddDropMessagesByCondition(cond)
}
for _, data := range r.config.AddTags {
cond := data.Condition
if cond == "*" {
cond = "true"
}
r.mp.AddAddTagsByCondition(cond, data.Key, data.Value)
}
for _, data := range r.config.DelTags {
cond := data.Condition
if cond == "*" {
cond = "true"
}
r.mp.AddDeleteTagsByCondition(cond, data.Key, data.Value)
}
for oldname, newname := range r.config.RenameMetrics {
r.mp.AddRenameMetricByName(oldname, newname)
}
for metricName, prefix := range r.config.ChangeUnitPrefix {
r.mp.AddChangeUnitPrefix(fmt.Sprintf("name == '%s'", metricName), prefix)
}
r.mp.SetNormalizeUnits(r.config.NormalizeUnits)
r.mp.AddAddTagsByCondition("true", r.config.HostnameTagName, r.hostname)
// r.config.dropMetrics = make(map[string]bool)
// for _, mname := range r.config.DropMetrics {
// r.config.dropMetrics[mname] = true
// }
return nil return nil
} }
func getParamMap(point lp.CCMessage) map[string]interface{} { func getParamMap(point lp.CCMetric) map[string]interface{} {
params := make(map[string]interface{}) params := make(map[string]interface{})
params["metric"] = point params["metric"] = point
params["name"] = point.Name() params["name"] = point.Name()
@ -181,7 +144,7 @@ func getParamMap(point lp.CCMessage) map[string]interface{} {
} }
// DoAddTags adds a tag when condition is fullfiled // DoAddTags adds a tag when condition is fullfiled
func (r *metricRouter) DoAddTags(point lp.CCMessage) { func (r *metricRouter) DoAddTags(point lp.CCMetric) {
var conditionMatches bool var conditionMatches bool
for _, m := range r.config.AddTags { for _, m := range r.config.AddTags {
if m.Condition == "*" { if m.Condition == "*" {
@ -203,81 +166,81 @@ func (r *metricRouter) DoAddTags(point lp.CCMessage) {
} }
// DoDelTags removes a tag when condition is fullfiled // DoDelTags removes a tag when condition is fullfiled
// func (r *metricRouter) DoDelTags(point lp.CCMessage) { func (r *metricRouter) DoDelTags(point lp.CCMetric) {
// var conditionMatches bool var conditionMatches bool
// for _, m := range r.config.DelTags { for _, m := range r.config.DelTags {
// if m.Condition == "*" { if m.Condition == "*" {
// // Condition is always matched // Condition is always matched
// conditionMatches = true conditionMatches = true
// } else { } else {
// // Evaluate condition // Evaluate condition
// var err error var err error
// conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point)) conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
// if err != nil { if err != nil {
// cclog.ComponentError("MetricRouter", err.Error()) cclog.ComponentError("MetricRouter", err.Error())
// conditionMatches = false conditionMatches = false
// } }
// } }
// if conditionMatches { if conditionMatches {
// point.RemoveTag(m.Key) point.RemoveTag(m.Key)
// } }
// } }
// } }
// Conditional test whether a metric should be dropped // Conditional test whether a metric should be dropped
// func (r *metricRouter) dropMetric(point lp.CCMessage) bool { func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
// // Simple drop check // Simple drop check
// if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok { if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
// return conditionMatches return conditionMatches
// } }
// // Checking the dropping conditions // Checking the dropping conditions
// for _, m := range r.config.DropMetricsIf { for _, m := range r.config.DropMetricsIf {
// conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point)) conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point))
// if err != nil { if err != nil {
// cclog.ComponentError("MetricRouter", err.Error()) cclog.ComponentError("MetricRouter", err.Error())
// conditionMatches = false conditionMatches = false
// } }
// if conditionMatches { if conditionMatches {
// return conditionMatches return conditionMatches
// } }
// } }
// // No dropping condition met // No dropping condition met
// return false return false
// } }
// func (r *metricRouter) prepareUnit(point lp.CCMessage) bool { func (r *metricRouter) prepareUnit(point lp.CCMetric) bool {
// if r.config.NormalizeUnits { if r.config.NormalizeUnits {
// if in_unit, ok := point.GetMeta("unit"); ok { if in_unit, ok := point.GetMeta("unit"); ok {
// u := units.NewUnit(in_unit) u := units.NewUnit(in_unit)
// if u.Valid() { if u.Valid() {
// point.AddMeta("unit", u.Short()) point.AddMeta("unit", u.Short())
// } }
// } }
// } }
// if newP, ok := r.config.ChangeUnitPrefix[point.Name()]; ok { if newP, ok := r.config.ChangeUnitPrefix[point.Name()]; ok {
// newPrefix := units.NewPrefix(newP) newPrefix := units.NewPrefix(newP)
// if in_unit, ok := point.GetMeta("unit"); ok && newPrefix != units.InvalidPrefix { if in_unit, ok := point.GetMeta("unit"); ok && newPrefix != units.InvalidPrefix {
// u := units.NewUnit(in_unit) u := units.NewUnit(in_unit)
// if u.Valid() { if u.Valid() {
// cclog.ComponentDebug("MetricRouter", "Change prefix to", newP, "for metric", point.Name()) cclog.ComponentDebug("MetricRouter", "Change prefix to", newP, "for metric", point.Name())
// conv, out_unit := units.GetUnitPrefixFactor(u, newPrefix) conv, out_unit := units.GetUnitPrefixFactor(u, newPrefix)
// if conv != nil && out_unit.Valid() { if conv != nil && out_unit.Valid() {
// if val, ok := point.GetField("value"); ok { if val, ok := point.GetField("value"); ok {
// point.AddField("value", conv(val)) point.AddField("value", conv(val))
// point.AddMeta("unit", out_unit.Short()) point.AddMeta("unit", out_unit.Short())
// } }
// } }
// } }
// } }
// } }
// return true return true
// } }
// Start starts the metric router // Start starts the metric router
func (r *metricRouter) Start() { func (r *metricRouter) Start() {
@ -296,75 +259,59 @@ func (r *metricRouter) Start() {
// Forward takes a received metric, adds or deletes tags // Forward takes a received metric, adds or deletes tags
// and forwards it to the output channels // and forwards it to the output channels
// forward := func(point lp.CCMessage) { forward := func(point lp.CCMetric) {
// cclog.ComponentDebug("MetricRouter", "FORWARD", point) cclog.ComponentDebug("MetricRouter", "FORWARD", point)
// r.DoAddTags(point) r.DoAddTags(point)
// r.DoDelTags(point) r.DoDelTags(point)
// name := point.Name() name := point.Name()
// if new, ok := r.config.RenameMetrics[name]; ok { if new, ok := r.config.RenameMetrics[name]; ok {
// point.SetName(new) point.SetName(new)
// point.AddMeta("oldname", name) point.AddMeta("oldname", name)
// r.DoAddTags(point) r.DoAddTags(point)
// r.DoDelTags(point) r.DoDelTags(point)
// } }
// r.prepareUnit(point) r.prepareUnit(point)
// for _, o := range r.outputs { for _, o := range r.outputs {
// o <- point o <- point
// } }
// } }
// Foward message received from collector channel // Foward message received from collector channel
coll_forward := func(p lp.CCMessage) { coll_forward := func(p lp.CCMetric) {
// receive from metric collector // receive from metric collector
//p.AddTag(r.config.HostnameTagName, r.hostname) p.AddTag(r.config.HostnameTagName, r.hostname)
if r.config.IntervalStamp { if r.config.IntervalStamp {
p.SetTime(r.timestamp) p.SetTime(r.timestamp)
} }
m, err := r.mp.ProcessMessage(p) if !r.dropMetric(p) {
if err == nil && m != nil { forward(p)
for _, o := range r.outputs {
o <- m
}
} }
// if !r.dropMetric(p) {
// for _, o := range r.outputs {
// o <- point
// }
// }
// even if the metric is dropped, it is stored in the cache for // even if the metric is dropped, it is stored in the cache for
// aggregations // aggregations
if r.config.NumCacheIntervals > 0 { if r.config.NumCacheIntervals > 0 {
r.cache.Add(m) r.cache.Add(p)
} }
} }
// Forward message received from receivers channel // Forward message received from receivers channel
recv_forward := func(p lp.CCMessage) { recv_forward := func(p lp.CCMetric) {
// receive from receive manager // receive from receive manager
if r.config.IntervalStamp { if r.config.IntervalStamp {
p.SetTime(r.timestamp) p.SetTime(r.timestamp)
} }
m, err := r.mp.ProcessMessage(p) if !r.dropMetric(p) {
if err == nil && m != nil { forward(p)
for _, o := range r.outputs {
o <- m
}
} }
// if !r.dropMetric(p) {
// forward(p)
// }
} }
// Forward message received from cache channel // Forward message received from cache channel
cache_forward := func(p lp.CCMessage) { cache_forward := func(p lp.CCMetric) {
// receive from metric collector // receive from metric collector
m, err := r.mp.ProcessMessage(p) if !r.dropMetric(p) {
if err == nil && m != nil { p.AddTag(r.config.HostnameTagName, r.hostname)
for _, o := range r.outputs { forward(p)
o <- m
}
} }
} }
@ -411,17 +358,17 @@ func (r *metricRouter) Start() {
} }
// AddCollectorInput adds a channel between metric collector and metric router // AddCollectorInput adds a channel between metric collector and metric router
func (r *metricRouter) AddCollectorInput(input chan lp.CCMessage) { func (r *metricRouter) AddCollectorInput(input chan lp.CCMetric) {
r.coll_input = input r.coll_input = input
} }
// AddReceiverInput adds a channel between metric receiver and metric router // AddReceiverInput adds a channel between metric receiver and metric router
func (r *metricRouter) AddReceiverInput(input chan lp.CCMessage) { func (r *metricRouter) AddReceiverInput(input chan lp.CCMetric) {
r.recv_input = input r.recv_input = input
} }
// AddOutput adds a output channel to the metric router // AddOutput adds a output channel to the metric router
func (r *metricRouter) AddOutput(output chan lp.CCMessage) { func (r *metricRouter) AddOutput(output chan lp.CCMetric) {
r.outputs = append(r.outputs, output) r.outputs = append(r.outputs, output)
} }
@ -441,9 +388,9 @@ func (r *metricRouter) Close() {
} }
// New creates a new initialized metric router // New creates a new initialized metric router
func New(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfig json.RawMessage) (MetricRouter, error) { func New(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) (MetricRouter, error) {
r := new(metricRouter) r := new(metricRouter)
err := r.Init(ticker, wg, routerConfig) err := r.Init(ticker, wg, routerConfigFile)
if err != nil { if err != nil {
return nil, err return nil, err
} }

113
pkg/ccLogger/cclogger.go Normal file
View File

@ -0,0 +1,113 @@
package cclogger
import (
"fmt"
"log"
"os"
"runtime"
)
var (
globalDebug = false
stdout = os.Stdout
stderr = os.Stderr
debugLog *log.Logger = nil
infoLog *log.Logger = nil
errorLog *log.Logger = nil
warnLog *log.Logger = nil
defaultLog *log.Logger = nil
)
func initLogger() {
if debugLog == nil {
debugLog = log.New(stderr, "DEBUG ", log.LstdFlags)
}
if infoLog == nil {
infoLog = log.New(stdout, "INFO ", log.LstdFlags)
}
if errorLog == nil {
errorLog = log.New(stderr, "ERROR ", log.LstdFlags)
}
if warnLog == nil {
warnLog = log.New(stderr, "WARN ", log.LstdFlags)
}
if defaultLog == nil {
defaultLog = log.New(stdout, "", log.LstdFlags)
}
}
func Print(e ...interface{}) {
initLogger()
defaultLog.Print(e...)
}
func ComponentPrint(component string, e ...interface{}) {
initLogger()
defaultLog.Print(fmt.Sprintf("[%s] ", component), e)
}
func Info(e ...interface{}) {
initLogger()
infoLog.Print(e...)
}
func ComponentInfo(component string, e ...interface{}) {
initLogger()
infoLog.Print(fmt.Sprintf("[%s] ", component), e)
}
func Debug(e ...interface{}) {
initLogger()
if globalDebug {
debugLog.Print(e...)
}
}
func ComponentDebug(component string, e ...interface{}) {
initLogger()
if globalDebug && debugLog != nil {
//CCComponentPrint(debugLog, component, e)
debugLog.Print(fmt.Sprintf("[%s] ", component), e)
}
}
func Error(e ...interface{}) {
initLogger()
_, fn, line, _ := runtime.Caller(1)
errorLog.Print(fmt.Sprintf("[%s:%d] ", fn, line), e)
}
func ComponentError(component string, e ...interface{}) {
initLogger()
_, fn, line, _ := runtime.Caller(1)
errorLog.Print(fmt.Sprintf("[%s|%s:%d] ", component, fn, line), e)
}
func SetDebug() {
globalDebug = true
initLogger()
}
func SetOutput(filename string) {
if filename == "stderr" {
if stderr != os.Stderr && stderr != os.Stdout {
stderr.Close()
}
stderr = os.Stderr
} else if filename == "stdout" {
if stderr != os.Stderr && stderr != os.Stdout {
stderr.Close()
}
stderr = os.Stdout
} else {
file, err := os.OpenFile(filename, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0600)
if err == nil {
defer file.Close()
stderr = file
}
}
debugLog = nil
errorLog = nil
warnLog = nil
initLogger()
}

57
pkg/ccMetric/README.md Normal file
View File

@ -0,0 +1,57 @@
# ClusterCockpit metrics
As described in the [ClusterCockpit specifications](https://github.com/ClusterCockpit/cc-specifications), the whole ClusterCockpit stack uses metrics in the InfluxDB line protocol format. This is also the input and output format for the ClusterCockpit Metric Collector but internally it uses an extended format while processing, named CCMetric.
It is basically a copy of the [InfluxDB line protocol](https://github.com/influxdata/line-protocol) `MutableMetric` interface with one extension. Besides the tags and fields, it contains a list of meta information (re-using the `Tag` structure of the original protocol):
```golang
type ccMetric struct {
name string // Measurement name
meta map[string]string // map of meta data tags
tags map[string]string // map of of tags
fields map[string]interface{} // map of of fields
tm time.Time // timestamp
}
type CCMetric interface {
ToPoint(metaAsTags map[string]bool) *write.Point // Generate influxDB point for data type ccMetric
ToLineProtocol(metaAsTags map[string]bool) string // Generate influxDB line protocol for data type ccMetric
String() string // Return line-protocol like string
Name() string // Get metric name
SetName(name string) // Set metric name
Time() time.Time // Get timestamp
SetTime(t time.Time) // Set timestamp
Tags() map[string]string // Map of tags
AddTag(key, value string) // Add a tag
GetTag(key string) (value string, ok bool) // Get a tag by its key
HasTag(key string) (ok bool) // Check if a tag key is present
RemoveTag(key string) // Remove a tag by its key
Meta() map[string]string // Map of meta data tags
AddMeta(key, value string) // Add a meta data tag
GetMeta(key string) (value string, ok bool) // Get a meta data tab addressed by its key
HasMeta(key string) (ok bool) // Check if a meta data key is present
RemoveMeta(key string) // Remove a meta data tag by its key
Fields() map[string]interface{} // Map of fields
AddField(key string, value interface{}) // Add a field
GetField(key string) (value interface{}, ok bool) // Get a field addressed by its key
HasField(key string) (ok bool) // Check if a field key is present
RemoveField(key string) // Remove a field addressed by its key
}
func New(name string, tags map[string]string, meta map[string]string, fields map[string]interface{}, tm time.Time) (CCMetric, error)
func FromMetric(other CCMetric) CCMetric
func FromInfluxMetric(other lp.Metric) CCMetric
```
The `CCMetric` interface provides the same functions as the `MutableMetric` like `{Add, Get, Remove, Has}{Tag, Field}` and additionally provides `{Add, Get, Remove, Has}Meta`.
The InfluxDB protocol creates a new metric with `influx.New(name, tags, fields, time)` while CCMetric uses `ccMetric.New(name, tags, meta, fields, time)` where `tags` and `meta` are both of type `map[string]string`.
You can copy a CCMetric with `FromMetric(other CCMetric) CCMetric`. If you get an `influx.Metric` from a function, like the line protocol parser, you can use `FromInfluxMetric(other influx.Metric) CCMetric` to get a CCMetric out of it (see `NatsReceiver` for an example).
Although the [cc-specifications](https://github.com/ClusterCockpit/cc-specifications/blob/master/interfaces/lineprotocol/README.md) defines that there is only a `value` field for the metric value, the CCMetric still can have multiple values similar to the InfluxDB line protocol.

353
pkg/ccMetric/ccMetric.go Normal file
View File

@ -0,0 +1,353 @@
package ccmetric
import (
"fmt"
"time"
influxdb2 "github.com/influxdata/influxdb-client-go/v2"
write "github.com/influxdata/influxdb-client-go/v2/api/write"
lp "github.com/influxdata/line-protocol" // MIT license
"golang.org/x/exp/maps"
)
// Most functions are derived from github.com/influxdata/line-protocol/metric.go
// The metric type is extended with an extra meta information list re-using the Tag
// type.
//
// See: https://docs.influxdata.com/influxdb/latest/reference/syntax/line-protocol/
type ccMetric struct {
name string // Measurement name
meta map[string]string // map of meta data tags
tags map[string]string // map of of tags
fields map[string]interface{} // map of of fields
tm time.Time // timestamp
}
// ccMetric access functions
type CCMetric interface {
ToPoint(metaAsTags map[string]bool) *write.Point // Generate influxDB point for data type ccMetric
ToLineProtocol(metaAsTags map[string]bool) string // Generate influxDB line protocol for data type ccMetric
Name() string // Get metric name
SetName(name string) // Set metric name
Time() time.Time // Get timestamp
SetTime(t time.Time) // Set timestamp
Tags() map[string]string // Map of tags
AddTag(key, value string) // Add a tag
GetTag(key string) (value string, ok bool) // Get a tag by its key
HasTag(key string) (ok bool) // Check if a tag key is present
RemoveTag(key string) // Remove a tag by its key
Meta() map[string]string // Map of meta data tags
AddMeta(key, value string) // Add a meta data tag
GetMeta(key string) (value string, ok bool) // Get a meta data tab addressed by its key
HasMeta(key string) (ok bool) // Check if a meta data key is present
RemoveMeta(key string) // Remove a meta data tag by its key
Fields() map[string]interface{} // Map of fields
AddField(key string, value interface{}) // Add a field
GetField(key string) (value interface{}, ok bool) // Get a field addressed by its key
HasField(key string) (ok bool) // Check if a field key is present
RemoveField(key string) // Remove a field addressed by its key
String() string // Return line-protocol like string
}
// String implements the stringer interface for data type ccMetric
func (m *ccMetric) String() string {
return fmt.Sprintf(
"Name: %s, Tags: %+v, Meta: %+v, fields: %+v, Timestamp: %d",
m.name, m.tags, m.meta, m.fields, m.tm.UnixNano(),
)
}
// ToLineProtocol generates influxDB line protocol for data type ccMetric
func (m *ccMetric) ToPoint(metaAsTags map[string]bool) (p *write.Point) {
p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
for key, use_as_tag := range metaAsTags {
if use_as_tag {
if value, ok := m.GetMeta(key); ok {
p.AddTag(key, value)
}
}
}
return p
}
// ToLineProtocol generates influxDB line protocol for data type ccMetric
func (m *ccMetric) ToLineProtocol(metaAsTags map[string]bool) string {
return write.PointToLineProtocol(
m.ToPoint(metaAsTags),
time.Nanosecond,
)
}
// Name returns the measurement name
func (m *ccMetric) Name() string {
return m.name
}
// SetName sets the measurement name
func (m *ccMetric) SetName(name string) {
m.name = name
}
// Time returns timestamp
func (m *ccMetric) Time() time.Time {
return m.tm
}
// SetTime sets the timestamp
func (m *ccMetric) SetTime(t time.Time) {
m.tm = t
}
// Tags returns the the list of tags as key-value-mapping
func (m *ccMetric) Tags() map[string]string {
return m.tags
}
// AddTag adds a tag (consisting of key and value) to the map of tags
func (m *ccMetric) AddTag(key, value string) {
m.tags[key] = value
}
// GetTag returns the tag with tag's key equal to <key>
func (m *ccMetric) GetTag(key string) (string, bool) {
value, ok := m.tags[key]
return value, ok
}
// HasTag checks if a tag with key equal to <key> is present in the list of tags
func (m *ccMetric) HasTag(key string) bool {
_, ok := m.tags[key]
return ok
}
// RemoveTag removes the tag with tag's key equal to <key>
func (m *ccMetric) RemoveTag(key string) {
delete(m.tags, key)
}
// Meta returns the meta data tags as key-value mapping
func (m *ccMetric) Meta() map[string]string {
return m.meta
}
// AddMeta adds a meta data tag (consisting of key and value) to the map of meta data tags
func (m *ccMetric) AddMeta(key, value string) {
m.meta[key] = value
}
// GetMeta returns the meta data tag with meta data's key equal to <key>
func (m *ccMetric) GetMeta(key string) (string, bool) {
value, ok := m.meta[key]
return value, ok
}
// HasMeta checks if a meta data tag with meta data's key equal to <key> is present in the map of meta data tags
func (m *ccMetric) HasMeta(key string) bool {
_, ok := m.meta[key]
return ok
}
// RemoveMeta removes the meta data tag with tag's key equal to <key>
func (m *ccMetric) RemoveMeta(key string) {
delete(m.meta, key)
}
// Fields returns the list of fields as key-value-mapping
func (m *ccMetric) Fields() map[string]interface{} {
return m.fields
}
// AddField adds a field (consisting of key and value) to the map of fields
func (m *ccMetric) AddField(key string, value interface{}) {
m.fields[key] = value
}
// GetField returns the field with field's key equal to <key>
func (m *ccMetric) GetField(key string) (interface{}, bool) {
v, ok := m.fields[key]
return v, ok
}
// HasField checks if a field with field's key equal to <key> is present in the map of fields
func (m *ccMetric) HasField(key string) bool {
_, ok := m.fields[key]
return ok
}
// RemoveField removes the field with field's key equal to <key>
// from the map of fields
func (m *ccMetric) RemoveField(key string) {
delete(m.fields, key)
}
// New creates a new measurement point
func New(
name string,
tags map[string]string,
meta map[string]string,
fields map[string]interface{},
tm time.Time,
) (CCMetric, error) {
m := &ccMetric{
name: name,
tags: maps.Clone(tags),
meta: maps.Clone(meta),
fields: make(map[string]interface{}, len(fields)),
tm: tm,
}
// deep copy fields
for k, v := range fields {
v := convertField(v)
if v == nil {
continue
}
m.fields[k] = v
}
return m, nil
}
// FromMetric copies the metric <other>
func FromMetric(other CCMetric) CCMetric {
return &ccMetric{
name: other.Name(),
tags: maps.Clone(other.Tags()),
meta: maps.Clone(other.Meta()),
fields: maps.Clone(other.Fields()),
tm: other.Time(),
}
}
// FromInfluxMetric copies the influxDB line protocol metric <other>
func FromInfluxMetric(other lp.Metric) CCMetric {
m := &ccMetric{
name: other.Name(),
tags: make(map[string]string),
meta: make(map[string]string),
fields: make(map[string]interface{}),
tm: other.Time(),
}
// deep copy tags and fields
for _, otherTag := range other.TagList() {
m.tags[otherTag.Key] = otherTag.Value
}
for _, otherField := range other.FieldList() {
m.fields[otherField.Key] = otherField.Value
}
return m
}
// convertField converts data types of fields by the following schemata:
//
// *float32, *float64, float32, float64 -> float64
// *int, *int8, *int16, *int32, *int64, int, int8, int16, int32, int64 -> int64
//
// *uint, *uint8, *uint16, *uint32, *uint64, uint, uint8, uint16, uint32, uint64 -> uint64
// *[]byte, *string, []byte, string -> string
// *bool, bool -> bool
func convertField(v interface{}) interface{} {
switch v := v.(type) {
case float64:
return v
case int64:
return v
case string:
return v
case bool:
return v
case int:
return int64(v)
case uint:
return uint64(v)
case uint64:
return uint64(v)
case []byte:
return string(v)
case int32:
return int64(v)
case int16:
return int64(v)
case int8:
return int64(v)
case uint32:
return uint64(v)
case uint16:
return uint64(v)
case uint8:
return uint64(v)
case float32:
return float64(v)
case *float64:
if v != nil {
return *v
}
case *int64:
if v != nil {
return *v
}
case *string:
if v != nil {
return *v
}
case *bool:
if v != nil {
return *v
}
case *int:
if v != nil {
return int64(*v)
}
case *uint:
if v != nil {
return uint64(*v)
}
case *uint64:
if v != nil {
return uint64(*v)
}
case *[]byte:
if v != nil {
return string(*v)
}
case *int32:
if v != nil {
return int64(*v)
}
case *int16:
if v != nil {
return int64(*v)
}
case *int8:
if v != nil {
return int64(*v)
}
case *uint32:
if v != nil {
return uint64(*v)
}
case *uint16:
if v != nil {
return uint64(*v)
}
case *uint8:
if v != nil {
return uint64(*v)
}
case *float32:
if v != nil {
return float64(*v)
}
default:
return nil
}
return nil
}

View File

@ -9,7 +9,7 @@ import (
"strconv" "strconv"
"strings" "strings"
cclogger "github.com/ClusterCockpit/cc-lib/ccLogger" cclogger "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
"golang.org/x/exp/slices" "golang.org/x/exp/slices"
) )
@ -296,25 +296,6 @@ func GetTypeList(topology_type string) []int {
return []int{} return []int{}
} }
func GetTypeId(hwt HwthreadEntry, topology_type string) (int, error) {
var err error = nil
switch topology_type {
case "node":
return 0, err
case "socket":
return hwt.Socket, err
case "die":
return hwt.Die, err
case "memoryDomain":
return hwt.NumaDomain, err
case "core":
return hwt.Core, err
case "hwthread":
return hwt.CpuID, err
}
return -1, fmt.Errorf("unknown topology type '%s'", topology_type)
}
// CpuData returns CPU data for each hardware thread // CpuData returns CPU data for each hardware thread
func CpuData() []HwthreadEntry { func CpuData() []HwthreadEntry {
// return a deep copy to protect cache data // return a deep copy to protect cache data
@ -442,22 +423,3 @@ func GetCoreHwthreads(core int) []int {
} }
return cpuList return cpuList
} }
// GetTypeList gets the list of specified type using the naming format inside ClusterCockpit
func GetTypeHwthreads(topology_type string, id int) []int {
switch topology_type {
case "node":
return HwthreadList()
case "socket":
return GetSocketHwthreads(id)
case "die":
return GetDieHwthreads(id)
case "memoryDomain":
return GetNumaDomainHwthreads(id)
case "core":
return GetCoreHwthreads(id)
case "hwthread":
return []int{id}
}
return []int{}
}

View File

@ -1,14 +1,3 @@
<!--
---
title: Multi-channel Ticker
description: Timer ticker that sends out the tick to multiple channels
categories: [cc-metric-collector]
tags: ['Developer']
weight: 1
hugo_path: docs/reference/cc-metric-collector/pkg/multichanticker/_index.md
---
-->
# MultiChanTicker # MultiChanTicker
The idea of this ticker is to multiply the output channels. The original Golang `time.Ticker` provides only a single output channel, so the signal can only be received by a single other class. This ticker allows to add multiple channels which get all notified about the time tick. The idea of this ticker is to multiply the output channels. The original Golang `time.Ticker` provides only a single output channel, so the signal can only be received by a single other class. This ticker allows to add multiple channels which get all notified about the time tick.

View File

@ -3,7 +3,7 @@ package multiChanTicker
import ( import (
"time" "time"
cclog "github.com/ClusterCockpit/cc-lib/ccLogger" cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
) )
type multiChanTicker struct { type multiChanTicker struct {

32
receivers/README.md Normal file
View File

@ -0,0 +1,32 @@
# CCMetric receivers
This folder contains the ReceiveManager and receiver implementations for the cc-metric-collector.
## Configuration
The configuration file for the receivers is a list of configurations. The `type` field in each specifies which receiver to initialize.
```json
{
"myreceivername" : {
"type": "receiver-type",
<receiver-specific configuration>
}
}
```
This allows to specify
## Available receivers
- [`nats`](./natsReceiver.md): Receive metrics from the NATS network
- [`prometheus`](./prometheusReceiver.md): Scrape data from a Prometheus client
- [`http`](./httpReceiver.md): Listen for HTTP Post requests transporting metrics in InfluxDB line protocol
- [`ipmi`](./ipmiReceiver.md): Read IPMI sensor readings
- [`redfish`](redfishReceiver.md) Use the Redfish (specification) to query thermal and power metrics
## Contributing own receivers
A receiver contains a few functions and is derived from the type `Receiver` (in `metricReceiver.go`):
For an example, check the [sample receiver](./sampleReceiver.go)

227
receivers/httpReceiver.go Normal file
View File

@ -0,0 +1,227 @@
package receivers
import (
"context"
"encoding/json"
"errors"
"fmt"
"net/http"
"strings"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
)
const HTTP_RECEIVER_PORT = "8080"
type HttpReceiverConfig struct {
Type string `json:"type"`
Addr string `json:"address"`
Port string `json:"port"`
Path string `json:"path"`
// Maximum amount of time to wait for the next request when keep-alives are enabled
// should be larger than the measurement interval to keep the connection open
IdleTimeout string `json:"idle_timeout"`
idleTimeout time.Duration
// Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled
KeepAlivesEnabled bool `json:"keep_alives_enabled"`
// Basic authentication
Username string `json:"username"`
Password string `json:"password"`
useBasicAuth bool
}
type HttpReceiver struct {
receiver
meta map[string]string
config HttpReceiverConfig
server *http.Server
wg sync.WaitGroup
}
func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
r.name = fmt.Sprintf("HttpReceiver(%s)", name)
// Set default values
r.config.Port = HTTP_RECEIVER_PORT
r.config.KeepAlivesEnabled = true
// should be larger than the measurement interval to keep the connection open
r.config.IdleTimeout = "120s"
// Read config
if len(config) > 0 {
err := json.Unmarshal(config, &r.config)
if err != nil {
cclog.ComponentError(r.name, "Error reading config:", err.Error())
return err
}
}
if len(r.config.Port) == 0 {
return errors.New("not all configuration variables set required by HttpReceiver")
}
// Check idle timeout config
if len(r.config.IdleTimeout) > 0 {
t, err := time.ParseDuration(r.config.IdleTimeout)
if err == nil {
cclog.ComponentDebug(r.name, "idleTimeout", t)
r.config.idleTimeout = t
}
}
// Check basic authentication config
if len(r.config.Username) > 0 || len(r.config.Password) > 0 {
r.config.useBasicAuth = true
}
if r.config.useBasicAuth && len(r.config.Username) == 0 {
return errors.New("basic authentication requires username")
}
if r.config.useBasicAuth && len(r.config.Password) == 0 {
return errors.New("basic authentication requires password")
}
r.meta = map[string]string{"source": r.name}
p := r.config.Path
if !strings.HasPrefix(p, "/") {
p = "/" + p
}
addr := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
uri := addr + p
cclog.ComponentDebug(r.name, "INIT", "listen on:", uri)
// Register handler function r.ServerHttp for path p in the DefaultServeMux
http.HandleFunc(p, r.ServerHttp)
// Create http server
r.server = &http.Server{
Addr: addr,
Handler: nil, // handler to invoke, http.DefaultServeMux if nil
IdleTimeout: r.config.idleTimeout,
}
r.server.SetKeepAlivesEnabled(r.config.KeepAlivesEnabled)
return nil
}
func (r *HttpReceiver) Start() {
cclog.ComponentDebug(r.name, "START")
r.wg.Add(1)
go func() {
err := r.server.ListenAndServe()
if err != nil && err.Error() != "http: Server closed" {
cclog.ComponentError(r.name, err.Error())
}
r.wg.Done()
}()
}
func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
// Check request method, only post method is handled
if req.Method != http.MethodPost {
http.Error(w, "Method Not Allowed", http.StatusMethodNotAllowed)
return
}
// Check basic authentication
if r.config.useBasicAuth {
username, password, ok := req.BasicAuth()
if !ok || username != r.config.Username || password != r.config.Password {
http.Error(w, "Unauthorized", http.StatusUnauthorized)
return
}
}
d := influx.NewDecoder(req.Body)
for d.Next() {
// Decode measurement name
measurement, err := d.Measurement()
if err != nil {
msg := "ServerHttp: Failed to decode measurement: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
// Decode tags
tags := make(map[string]string)
for {
key, value, err := d.NextTag()
if err != nil {
msg := "ServerHttp: Failed to decode tag: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
if key == nil {
break
}
tags[string(key)] = string(value)
}
// Decode fields
fields := make(map[string]interface{})
for {
key, value, err := d.NextField()
if err != nil {
msg := "ServerHttp: Failed to decode field: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
if key == nil {
break
}
fields[string(key)] = value.Interface()
}
// Decode time stamp
t, err := d.Time(influx.Nanosecond, time.Time{})
if err != nil {
msg := "ServerHttp: Failed to decode time stamp: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
y, _ := lp.New(
string(measurement),
tags,
r.meta,
fields,
t,
)
if r.sink != nil {
r.sink <- y
}
}
// Check for IO errors
err := d.Err()
if err != nil {
msg := "ServerHttp: Failed to decode: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
w.WriteHeader(http.StatusOK)
}
func (r *HttpReceiver) Close() {
r.server.Shutdown(context.Background())
}
func NewHttpReceiver(name string, config json.RawMessage) (Receiver, error) {
r := new(HttpReceiver)
err := r.Init(name, config)
return r, err
}

43
receivers/httpReceiver.md Normal file
View File

@ -0,0 +1,43 @@
## `http` receiver
The `http` receiver can be used receive metrics through HTTP POST requests.
### Configuration structure
```json
{
"<name>": {
"type": "http",
"address" : "",
"port" : "8080",
"path" : "/write",
"idle_timeout": "120s",
"username": "myUser",
"password": "myPW"
}
}
```
- `type`: makes the receiver a `http` receiver
- `address`: Listen address
- `port`: Listen port
- `path`: URL path for the write endpoint
- `idle_timeout`: Maximum amount of time to wait for the next request when keep-alives are enabled should be larger than the measurement interval to keep the connection open
- `keep_alives_enabled`: Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled.
- `username`: username for basic authentication
- `password`: password for basic authentication
The HTTP endpoint listens to `http://<address>:<port>/<path>`
### Debugging
- Install [curl](https://curl.se/)
- Use curl to send message to `http` receiver
```bash
curl http://localhost:8080/write \
--user "myUser:myPW" \
--data \
"myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
```

534
receivers/ipmiReceiver.go Normal file
View File

@ -0,0 +1,534 @@
package receivers
import (
"bufio"
"bytes"
"encoding/json"
"fmt"
"io"
"os/exec"
"regexp"
"strconv"
"strings"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/ClusterCockpit/cc-metric-collector/pkg/hostlist"
)
type IPMIReceiverClientConfig struct {
// Hostname the IPMI service belongs to
Protocol string // Protocol / tool to use for IPMI sensor reading
DriverType string // Out of band IPMI driver
Fanout int // Maximum number of simultaneous IPMI connections
NumHosts int // Number of remote IPMI devices with the same configuration
IPMIHosts string // List of remote IPMI devices to communicate with
IPMI2HostMapping map[string]string // Mapping between IPMI device name and host name
Username string // User name to authenticate with
Password string // Password to use for authentication
CLIOptions []string // Additional command line options for ipmi-sensors
isExcluded map[string]bool // is metric excluded
}
type IPMIReceiver struct {
receiver
config struct {
Interval time.Duration
// Client config for each IPMI hosts
ClientConfigs []IPMIReceiverClientConfig
}
// Storage for static information
meta map[string]string
done chan bool // channel to finish / stop IPMI receiver
wg sync.WaitGroup // wait group for IPMI receiver
}
// doReadMetrics reads metrics from all configure IPMI hosts.
func (r *IPMIReceiver) doReadMetric() {
for i := range r.config.ClientConfigs {
clientConfig := &r.config.ClientConfigs[i]
var cmd_options []string
if clientConfig.Protocol == "ipmi-sensors" {
cmd_options = append(cmd_options,
"--always-prefix",
"--sdr-cache-recreate",
// Attempt to interpret OEM data, such as event data, sensor readings, or general extra info
"--interpret-oem-data",
// Ignore not-available (i.e. N/A) sensors in output
"--ignore-not-available-sensors",
// Ignore unrecognized sensor events
"--ignore-unrecognized-events",
// Output fields in comma separated format
"--comma-separated-output",
// Do not output column headers
"--no-header-output",
// Output non-abbreviated units (e.g. 'Amps' instead of 'A').
// May aid in disambiguation of units (e.g. 'C' for Celsius or Coulombs).
"--non-abbreviated-units",
"--fanout", fmt.Sprint(clientConfig.Fanout),
"--driver-type", clientConfig.DriverType,
"--hostname", clientConfig.IPMIHosts,
"--username", clientConfig.Username,
"--password", clientConfig.Password,
)
cmd_options := append(cmd_options, clientConfig.CLIOptions...)
command := exec.Command("ipmi-sensors", cmd_options...)
stdout, _ := command.StdoutPipe()
errBuf := new(bytes.Buffer)
command.Stderr = errBuf
// start command
if err := command.Start(); err != nil {
cclog.ComponentError(
r.name,
fmt.Sprintf("doReadMetric(): Failed to start command \"%s\": %v", command.String(), err),
)
continue
}
// Read command output
const (
idxID = iota
idxName
idxType
idxReading
idxUnits
idxEvent
)
numPrefixRegex := regexp.MustCompile("^[[:digit:]][[:digit:]]-(.*)$")
scanner := bufio.NewScanner(stdout)
for scanner.Scan() {
// Read host
v1 := strings.Split(scanner.Text(), ": ")
if len(v1) != 2 {
continue
}
host, ok := clientConfig.IPMI2HostMapping[v1[0]]
if !ok {
continue
}
// Read sensors
v2 := strings.Split(v1[1], ",")
if len(v2) != 6 {
continue
}
// Skip sensors with non available sensor readings
if v2[idxReading] == "N/A" {
continue
}
metric := strings.ToLower(v2[idxType])
name := strings.ToLower(
strings.Replace(
strings.TrimSpace(
v2[idxName]), " ", "_", -1))
// remove prefix enumeration like 01-...
if v := numPrefixRegex.FindStringSubmatch(name); v != nil {
name = v[1]
}
unit := v2[idxUnits]
if unit == "Watts" {
// Power
metric = "power"
name = strings.TrimSuffix(name, "_power")
name = strings.TrimSuffix(name, "_pwr")
name = strings.TrimPrefix(name, "pwr_")
} else if metric == "voltage" &&
unit == "Volts" {
// Voltage
name = strings.TrimPrefix(name, "volt_")
} else if metric == "current" &&
unit == "Amps" {
// Current
unit = "Ampere"
} else if metric == "temperature" &&
unit == "degrees C" {
// Temperature
name = strings.TrimSuffix(name, "_temp")
unit = "degC"
} else if metric == "temperature" &&
unit == "degrees F" {
// Temperature
name = strings.TrimSuffix(name, "_temp")
unit = "degF"
} else if metric == "fan" && unit == "RPM" {
// Fan speed
metric = "fan_speed"
name = strings.TrimSuffix(name, "_tach")
name = strings.TrimPrefix(name, "spd_")
} else if (metric == "cooling device" ||
metric == "other units based sensor") &&
name == "system_air_flow" &&
unit == "CFM" {
// Air flow
metric = "air_flow"
name = strings.TrimSuffix(name, "_air_flow")
unit = "CubicFeetPerMinute"
} else if (metric == "processor" ||
metric == "other units based sensor") &&
(name == "cpu_utilization" ||
name == "io_utilization" ||
name == "mem_utilization" ||
name == "sys_utilization") &&
(unit == "unspecified" ||
unit == "%") {
// Utilization
metric = "utilization"
name = strings.TrimSuffix(name, "_utilization")
unit = "percent"
} else {
if false {
// Debug output for unprocessed metrics
fmt.Printf(
"host: '%s', metric: '%s', name: '%s', unit: '%s'\n",
host, metric, name, unit)
}
continue
}
// Skip excluded metrics
if clientConfig.isExcluded[metric] {
continue
}
// Parse sensor value
value, err := strconv.ParseFloat(v2[idxReading], 64)
if err != nil {
continue
}
y, err := lp.New(
metric,
map[string]string{
"hostname": host,
"type": "node",
"name": name,
},
map[string]string{
"source": r.name,
"group": "IPMI",
"unit": unit,
},
map[string]interface{}{
"value": value,
},
time.Now())
if err == nil {
r.sink <- y
}
}
// Wait for command end
if err := command.Wait(); err != nil {
errMsg, _ := io.ReadAll(errBuf)
cclog.ComponentError(
r.name,
fmt.Sprintf("doReadMetric(): Failed to wait for the end of command \"%s\": %v\n",
strings.Replace(command.String(), clientConfig.Password, "<PW>", -1), err),
fmt.Sprintf("doReadMetric(): command stderr: \"%s\"\n", string(errMsg)),
)
}
}
}
}
func (r *IPMIReceiver) Start() {
cclog.ComponentDebug(r.name, "START")
// Start IPMI receiver
r.wg.Add(1)
go func() {
defer r.wg.Done()
// Create ticker
ticker := time.NewTicker(r.config.Interval)
defer ticker.Stop()
for {
r.doReadMetric()
select {
case tickerTime := <-ticker.C:
// Check if we missed the ticker event
if since := time.Since(tickerTime); since > 5*time.Second {
cclog.ComponentInfo(r.name, "Missed ticker event for more then", since)
}
// process ticker event -> continue
continue
case <-r.done:
// process done event
return
}
}
}()
cclog.ComponentDebug(r.name, "STARTED")
}
// Close receiver: close network connection, close files, close libraries, ...
func (r *IPMIReceiver) Close() {
cclog.ComponentDebug(r.name, "CLOSE")
// Send the signal and wait
close(r.done)
r.wg.Wait()
cclog.ComponentDebug(r.name, "DONE")
}
// NewIPMIReceiver creates a new instance of the redfish receiver
// Initialize the receiver by giving it a name and reading in the config JSON
func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
r := new(IPMIReceiver)
// Config options from config file
configJSON := struct {
Type string `json:"type"`
// How often the IPMI sensor metrics should be read and send to the sink (default: 30 s)
IntervalString string `json:"interval,omitempty"`
// Maximum number of simultaneous IPMI connections (default: 64)
Fanout int `json:"fanout,omitempty"`
// Out of band IPMI driver (default: LAN_2_0)
DriverType string `json:"driver_type,omitempty"`
// Default client username, password and endpoint
Username *string `json:"username"` // User name to authenticate with
Password *string `json:"password"` // Password to use for authentication
Endpoint *string `json:"endpoint"` // URL of the IPMI device
// Globally excluded metrics
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ClientConfigs []struct {
Fanout int `json:"fanout,omitempty"` // Maximum number of simultaneous IPMI connections (default: 64)
DriverType string `json:"driver_type,omitempty"` // Out of band IPMI driver (default: LAN_2_0)
HostList string `json:"host_list"` // List of hosts with the same client configuration
Username *string `json:"username"` // User name to authenticate with
Password *string `json:"password"` // Password to use for authentication
Endpoint *string `json:"endpoint"` // URL of the IPMI service
// Per client excluded metrics
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
// Additional command line options for ipmi-sensors
CLIOptions []string `json:"cli_options,omitempty"`
} `json:"client_config"`
}{
// Set defaults values
// Allow overwriting these defaults by reading config JSON
Fanout: 64,
DriverType: "LAN_2_0",
IntervalString: "30s",
}
// Set name of IPMIReceiver
r.name = fmt.Sprintf("IPMIReceiver(%s)", name)
// Create done channel
r.done = make(chan bool)
// Set static information
r.meta = map[string]string{"source": r.name}
// Read the IPMI receiver specific JSON config
if len(config) > 0 {
d := json.NewDecoder(bytes.NewReader(config))
d.DisallowUnknownFields()
if err := d.Decode(&configJSON); err != nil {
cclog.ComponentError(r.name, "Error reading config:", err.Error())
return nil, err
}
}
// Convert interval string representation to duration
var err error
r.config.Interval, err = time.ParseDuration(configJSON.IntervalString)
if err != nil {
err := fmt.Errorf(
"Failed to parse duration string interval='%s': %w",
configJSON.IntervalString,
err,
)
cclog.Error(r.name, err)
return nil, err
}
// Create client config from JSON config
totalNumHosts := 0
for i := range configJSON.ClientConfigs {
clientConfigJSON := &configJSON.ClientConfigs[i]
var endpoint string
if clientConfigJSON.Endpoint != nil {
endpoint = *clientConfigJSON.Endpoint
} else if configJSON.Endpoint != nil {
endpoint = *configJSON.Endpoint
} else {
err := fmt.Errorf("client config number %v requires endpoint", i)
cclog.ComponentError(r.name, err)
return nil, err
}
fanout := configJSON.Fanout
if clientConfigJSON.Fanout != 0 {
fanout = clientConfigJSON.Fanout
}
driverType := configJSON.DriverType
if clientConfigJSON.DriverType != "" {
driverType = clientConfigJSON.DriverType
}
if driverType != "LAN" && driverType != "LAN_2_0" {
err := fmt.Errorf("client config number %v has invalid driver type %s", i, driverType)
cclog.ComponentError(r.name, err)
return nil, err
}
var protocol string
var host_pattern string
if e := strings.Split(endpoint, "://"); len(e) == 2 {
protocol = e[0]
host_pattern = e[1]
} else {
err := fmt.Errorf("client config number %v has invalid endpoint %s", i, endpoint)
cclog.ComponentError(r.name, err)
return nil, err
}
var username string
if clientConfigJSON.Username != nil {
username = *clientConfigJSON.Username
} else if configJSON.Username != nil {
username = *configJSON.Username
} else {
err := fmt.Errorf("client config number %v requires username", i)
cclog.ComponentError(r.name, err)
return nil, err
}
var password string
if clientConfigJSON.Password != nil {
password = *clientConfigJSON.Password
} else if configJSON.Password != nil {
password = *configJSON.Password
} else {
err := fmt.Errorf("client config number %v requires password", i)
cclog.ComponentError(r.name, err)
return nil, err
}
// Create mapping between IPMI host name and node host name
// This also guaranties that all IPMI host names are unique
ipmi2HostMapping := make(map[string]string)
hostList, err := hostlist.Expand(clientConfigJSON.HostList)
if err != nil {
err := fmt.Errorf("client config number %d failed to parse host list %s: %v",
i, clientConfigJSON.HostList, err)
cclog.ComponentError(r.name, err)
return nil, err
}
for _, host := range hostList {
ipmiHost := strings.Replace(host_pattern, "%h", host, -1)
ipmi2HostMapping[ipmiHost] = host
}
numHosts := len(ipmi2HostMapping)
totalNumHosts += numHosts
ipmiHostList := make([]string, 0, numHosts)
for ipmiHost := range ipmi2HostMapping {
ipmiHostList = append(ipmiHostList, ipmiHost)
}
// Additional command line options
for _, v := range clientConfigJSON.CLIOptions {
switch {
case v == "-u" || strings.HasPrefix(v, "--username"):
err := fmt.Errorf("client config number %v: do not set username in cli_options. Use json config username instead", i)
cclog.ComponentError(r.name, err)
return nil, err
case v == "-p" || strings.HasPrefix(v, "--password"):
err := fmt.Errorf("client config number %v: do not set password in cli_options. Use json config password instead", i)
cclog.ComponentError(r.name, err)
return nil, err
case v == "-h" || strings.HasPrefix(v, "--hostname"):
err := fmt.Errorf("client config number %v: do not set hostname in cli_options. Use json config host_list instead", i)
cclog.ComponentError(r.name, err)
return nil, err
case v == "-D" || strings.HasPrefix(v, "--driver-type"):
err := fmt.Errorf("client config number %v: do not set driver type in cli_options. Use json config driver_type instead", i)
cclog.ComponentError(r.name, err)
return nil, err
case v == "-F" || strings.HasPrefix(v, " --fanout"):
err := fmt.Errorf("client config number %v: do not set fanout in cli_options. Use json config fanout instead", i)
cclog.ComponentError(r.name, err)
return nil, err
case v == "--always-prefix" ||
v == "--sdr-cache-recreate" ||
v == "--interpret-oem-data" ||
v == "--ignore-not-available-sensors" ||
v == "--ignore-unrecognized-events" ||
v == "--comma-separated-output" ||
v == "--no-header-output" ||
v == "--non-abbreviated-units":
err := fmt.Errorf("client config number %v: Do not use option %s in cli_options, it is used internally", i, v)
cclog.ComponentError(r.name, err)
return nil, err
}
}
cliOptions := make([]string, 0)
cliOptions = append(cliOptions, clientConfigJSON.CLIOptions...)
// Is metrics excluded globally or per client
isExcluded := make(map[string]bool)
for _, key := range clientConfigJSON.ExcludeMetrics {
isExcluded[key] = true
}
for _, key := range configJSON.ExcludeMetrics {
isExcluded[key] = true
}
r.config.ClientConfigs = append(
r.config.ClientConfigs,
IPMIReceiverClientConfig{
Protocol: protocol,
Fanout: fanout,
DriverType: driverType,
NumHosts: numHosts,
IPMIHosts: strings.Join(ipmiHostList, ","),
IPMI2HostMapping: ipmi2HostMapping,
Username: username,
Password: password,
CLIOptions: cliOptions,
isExcluded: isExcluded,
})
}
if totalNumHosts == 0 {
err := fmt.Errorf("at least one IPMI host config is required")
cclog.ComponentError(r.name, err)
return nil, err
}
cclog.ComponentInfo(r.name, "monitoring", totalNumHosts, "IPMI hosts")
return r, nil
}

48
receivers/ipmiReceiver.md Normal file
View File

@ -0,0 +1,48 @@
## IPMI Receiver
The IPMI Receiver uses `ipmi-sensors` from the [FreeIPMI](https://www.gnu.org/software/freeipmi/) project to read IPMI sensor readings and sensor data repository (SDR) information. The available metrics depend on the sensors provided by the hardware vendor but typically contain temperature, fan speed, voltage and power metrics.
### Configuration structure
```json
{
"<IPMI receiver name>": {
"type": "ipmi",
"interval": "30s",
"fanout": 256,
"username": "<Username>",
"password": "<Password>",
"endpoint": "ipmi-sensors://%h-bmc",
"exclude_metrics": [ "fan_speed", "voltage" ],
"client_config": [
{
"host_list": "n[1,2-4]"
},
{
"host_list": "n[5-6]",
"driver_type": "LAN",
"cli_options": [ "--workaround-flags=..." ],
"password": "<Password 2>"
}
]
}
}
```
Global settings:
- `interval`: How often the IPMI sensor metrics should be read and send to the sink (default: 30 s)
Global and per IPMI device settings (per IPMI device settings overwrite the global settings):
- `exclude_metrics`: list of excluded metrics e.g. fan_speed, power, temperature, utilization, voltage
- `fanout`: Maximum number of simultaneous IPMI connections (default: 64)
- `driver_type`: Out of band IPMI driver (default: LAN_2_0)
- `username`: User name to authenticate with
- `password`: Password to use for authentication
- `endpoint`: URL of the IPMI device (placeholder `%h` gets replaced by the hostname)
Per IPMI device settings:
- `host_list`: List of hosts with the same client configuration
- `cli_options`: Additional command line options for ipmi-sensors

View File

@ -0,0 +1,40 @@
package receivers
import (
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type defaultReceiverConfig struct {
Type string `json:"type"`
}
// Receiver configuration: Listen address, port
type ReceiverConfig struct {
Addr string `json:"address"`
Port string `json:"port"`
Database string `json:"database"`
Organization string `json:"organization,omitempty"`
Type string `json:"type"`
}
type receiver struct {
name string
sink chan lp.CCMetric
}
type Receiver interface {
Start()
Close() // Close / finish metric receiver
Name() string // Name of the metric receiver
SetSink(sink chan lp.CCMetric) // Set sink channel
}
// Name returns the name of the metric receiver
func (r *receiver) Name() string {
return r.name
}
// SetSink set the sink channel
func (r *receiver) SetSink(sink chan lp.CCMetric) {
r.sink = sink
}

147
receivers/natsReceiver.go Normal file
View File

@ -0,0 +1,147 @@
package receivers
import (
"encoding/json"
"errors"
"fmt"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
nats "github.com/nats-io/nats.go"
)
type NatsReceiverConfig struct {
Type string `json:"type"`
Addr string `json:"address"`
Port string `json:"port"`
Subject string `json:"subject"`
}
type NatsReceiver struct {
receiver
nc *nats.Conn
meta map[string]string
config NatsReceiverConfig
}
// Start subscribes to the configured NATS subject
// Messages wil be handled by r._NatsReceive
func (r *NatsReceiver) Start() {
cclog.ComponentDebug(r.name, "START")
r.nc.Subscribe(r.config.Subject, r._NatsReceive)
}
// _NatsReceive receives subscribed messages from the NATS server
func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
d := influx.NewDecoderWithBytes(m.Data)
for d.Next() {
// Decode measurement name
measurement, err := d.Measurement()
if err != nil {
msg := "_NatsReceive: Failed to decode measurement: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
// Decode tags
tags := make(map[string]string)
for {
key, value, err := d.NextTag()
if err != nil {
msg := "_NatsReceive: Failed to decode tag: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
if key == nil {
break
}
tags[string(key)] = string(value)
}
// Decode fields
fields := make(map[string]interface{})
for {
key, value, err := d.NextField()
if err != nil {
msg := "_NatsReceive: Failed to decode field: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
if key == nil {
break
}
fields[string(key)] = value.Interface()
}
// Decode time stamp
t, err := d.Time(influx.Nanosecond, time.Time{})
if err != nil {
msg := "_NatsReceive: Failed to decode time: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
y, _ := lp.New(
string(measurement),
tags,
r.meta,
fields,
t,
)
if r.sink != nil {
r.sink <- y
}
}
}
// Close closes the connection to the NATS server
func (r *NatsReceiver) Close() {
if r.nc != nil {
cclog.ComponentDebug(r.name, "CLOSE")
r.nc.Close()
}
}
// NewNatsReceiver creates a new Receiver which subscribes to messages from a NATS server
func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
r := new(NatsReceiver)
r.name = fmt.Sprintf("NatsReceiver(%s)", name)
// Read configuration file, allow overwriting default config
r.config.Addr = "localhost"
r.config.Port = "4222"
if len(config) > 0 {
err := json.Unmarshal(config, &r.config)
if err != nil {
cclog.ComponentError(r.name, "Error reading config:", err.Error())
return nil, err
}
}
if len(r.config.Addr) == 0 ||
len(r.config.Port) == 0 ||
len(r.config.Subject) == 0 {
return nil, errors.New("not all configuration variables set required by NatsReceiver")
}
// Set metadata
r.meta = map[string]string{
"source": r.name,
}
// Connect to NATS server
url := fmt.Sprintf("nats://%s:%s", r.config.Addr, r.config.Port)
cclog.ComponentDebug(r.name, "NewNatsReceiver", url, "Subject", r.config.Subject)
if nc, err := nats.Connect(url); err == nil {
r.nc = nc
} else {
r.nc = nil
return nil, err
}
return r, nil
}

50
receivers/natsReceiver.md Normal file
View File

@ -0,0 +1,50 @@
## `nats` receiver
The `nats` receiver can be used receive metrics from the NATS network. The `nats` receiver subscribes to the topic `database` and listens on `address` and `port` for metrics in the InfluxDB line protocol.
### Configuration structure
```json
{
"<name>": {
"type": "nats",
"address" : "nats-server.example.org",
"port" : "4222",
"subject" : "subject"
}
}
```
- `type`: makes the receiver a `nats` receiver
- `address`: Address of the NATS control server
- `port`: Port of the NATS control server
- `subject`: Subscribes to this subject and receive metrics
### Debugging
- Install NATS server and command line client
- Start NATS server
```bash
nats-server --net nats-server.example.org --port 4222
```
- Check NATS server works as expected
```bash
nats --server=nats-server-db.example.org:4222 server check
```
- Use NATS command line client to subscribe to all messages
```bash
nats --server=nats-server-db.example.org:4222 sub ">"
```
- Use NATS command line client to send message to NATS receiver
```bash
nats --server=nats-server-db.example.org:4222 pub subject \
"myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
```

View File

@ -0,0 +1,122 @@
package receivers
import (
"bufio"
"encoding/json"
"errors"
"fmt"
"log"
"net/http"
"strconv"
"strings"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type PrometheusReceiverConfig struct {
defaultReceiverConfig
Addr string `json:"address"`
Port string `json:"port"`
Path string `json:"path"`
Interval string `json:"interval"`
SSL bool `json:"ssl"`
}
type PrometheusReceiver struct {
receiver
meta map[string]string
config PrometheusReceiverConfig
interval time.Duration
done chan bool
wg sync.WaitGroup
ticker *time.Ticker
uri string
}
func (r *PrometheusReceiver) Start() {
cclog.ComponentDebug(r.name, "START", r.uri)
r.wg.Add(1)
r.ticker = time.NewTicker(r.interval)
go func() {
for {
select {
case <-r.done:
r.wg.Done()
return
case t := <-r.ticker.C:
resp, err := http.Get(r.uri)
if err != nil {
log.Fatal(err)
}
defer resp.Body.Close()
scanner := bufio.NewScanner(resp.Body)
for scanner.Scan() {
line := scanner.Text()
if strings.HasPrefix(line, "#") {
continue
}
lineSplit := strings.Fields(line)
// separate metric name from tags (labels in Prometheus)
tags := map[string]string{}
name := lineSplit[0]
if sindex := strings.Index(name, "{"); sindex >= 0 {
eindex := strings.Index(name, "}")
for _, kv := range strings.Split(name[sindex+1:eindex], ",") {
eq := strings.Index(kv, "=")
tags[kv[0:eq]] = strings.Trim(kv[eq+1:], "\"")
}
name = lineSplit[0][0:sindex]
}
value, err := strconv.ParseFloat(lineSplit[1], 64)
if err == nil {
y, err := lp.New(name, tags, r.meta, map[string]interface{}{"value": value}, t)
if err == nil {
r.sink <- y
}
}
}
}
}
}()
}
func (r *PrometheusReceiver) Close() {
cclog.ComponentDebug(r.name, "CLOSE")
r.done <- true
r.wg.Wait()
}
func NewPrometheusReceiver(name string, config json.RawMessage) (Receiver, error) {
r := new(PrometheusReceiver)
r.name = fmt.Sprintf("PrometheusReceiver(%s)", name)
if len(config) > 0 {
err := json.Unmarshal(config, &r.config)
if err != nil {
cclog.ComponentError(r.name, "Error reading config:", err.Error())
return nil, err
}
}
if len(r.config.Addr) == 0 ||
len(r.config.Port) == 0 ||
len(r.config.Interval) == 0 {
return nil, errors.New("not all configuration variables set required by PrometheusReceiver (address and port)")
}
if len(r.config.Interval) > 0 {
t, err := time.ParseDuration(r.config.Interval)
if err == nil {
r.interval = t
}
}
r.meta = map[string]string{"source": r.name}
proto := "http"
if r.config.SSL {
proto = "https"
}
r.uri = fmt.Sprintf("%s://%s:%s/%s", proto, r.config.Addr, r.config.Port, r.config.Path)
return r, nil
}

View File

@ -0,0 +1,27 @@
## `prometheus` receiver
The `prometheus` receiver can be used to scrape the metrics of a single `prometheus` client. It does **not** use any official Golang library but making simple HTTP get requests and parse the response.
### Configuration structure
```json
{
"<name>": {
"type": "prometheus",
"address" : "testpromhost",
"port" : "12345",
"path" : "/prometheus",
"interval": "5s",
"ssl" : true,
}
}
```
- `type`: makes the receiver a `prometheus` receiver
- `address`: Hostname or IP of the Prometheus agent
- `port`: Port of Prometheus agent
- `path`: Path to the Prometheus endpoint
- `interval`: Scrape the Prometheus endpoint in this interval (default '5s')
- `ssl`: Use SSL or not
The receiver requests data from `http(s)://<address>:<port>/<path>`.

122
receivers/receiveManager.go Normal file
View File

@ -0,0 +1,122 @@
package receivers
import (
"encoding/json"
"fmt"
"os"
"sync"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
"http": NewHttpReceiver,
"ipmi": NewIPMIReceiver,
"nats": NewNatsReceiver,
"redfish": NewRedfishReceiver,
}
type receiveManager struct {
inputs []Receiver
output chan lp.CCMetric
config []json.RawMessage
}
type ReceiveManager interface {
Init(wg *sync.WaitGroup, receiverConfigFile string) error
AddInput(name string, rawConfig json.RawMessage) error
AddOutput(output chan lp.CCMetric)
Start()
Close()
}
func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) error {
// Initialize struct fields
rm.inputs = make([]Receiver, 0)
rm.output = nil
rm.config = make([]json.RawMessage, 0)
configFile, err := os.Open(receiverConfigFile)
if err != nil {
cclog.ComponentError("ReceiveManager", err.Error())
return err
}
defer configFile.Close()
jsonParser := json.NewDecoder(configFile)
var rawConfigs map[string]json.RawMessage
err = jsonParser.Decode(&rawConfigs)
if err != nil {
cclog.ComponentError("ReceiveManager", err.Error())
return err
}
for name, raw := range rawConfigs {
rm.AddInput(name, raw)
}
return nil
}
func (rm *receiveManager) Start() {
cclog.ComponentDebug("ReceiveManager", "START")
for _, r := range rm.inputs {
cclog.ComponentDebug("ReceiveManager", "START", r.Name())
r.Start()
}
cclog.ComponentDebug("ReceiveManager", "STARTED")
}
func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error {
var config defaultReceiverConfig
err := json.Unmarshal(rawConfig, &config)
if err != nil {
cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "JSON config error:", err.Error())
return err
}
if config.Type == "" {
cclog.ComponentError("ReceiveManager", "SKIP", "JSON config for receiver", name, "does not contain a receiver type")
return fmt.Errorf("JSON config for receiver %s does not contain a receiver type", name)
}
if _, found := AvailableReceivers[config.Type]; !found {
cclog.ComponentError("ReceiveManager", "SKIP", "unknown receiver type:", config.Type)
return fmt.Errorf("unknown receiver type: %s", config.Type)
}
r, err := AvailableReceivers[config.Type](name, rawConfig)
if err != nil {
cclog.ComponentError("ReceiveManager", "SKIP", name, "initialization failed:", err.Error())
return err
}
rm.inputs = append(rm.inputs, r)
rm.config = append(rm.config, rawConfig)
cclog.ComponentDebug("ReceiveManager", "ADD RECEIVER", r.Name())
return nil
}
func (rm *receiveManager) AddOutput(output chan lp.CCMetric) {
rm.output = output
for _, r := range rm.inputs {
r.SetSink(rm.output)
}
}
func (rm *receiveManager) Close() {
cclog.ComponentDebug("ReceiveManager", "CLOSE")
// Close all receivers
for _, r := range rm.inputs {
cclog.ComponentDebug("ReceiveManager", "CLOSE", r.Name())
r.Close()
}
cclog.ComponentDebug("ReceiveManager", "DONE")
}
func New(wg *sync.WaitGroup, receiverConfigFile string) (ReceiveManager, error) {
r := new(receiveManager)
err := r.Init(wg, receiverConfigFile)
if err != nil {
return nil, err
}
return r, err
}

View File

@ -0,0 +1,843 @@
package receivers
import (
"bytes"
"crypto/tls"
"encoding/json"
"fmt"
"io"
"net/http"
"strconv"
"strings"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/ClusterCockpit/cc-metric-collector/pkg/hostlist"
// See: https://pkg.go.dev/github.com/stmcginnis/gofish
"github.com/stmcginnis/gofish"
"github.com/stmcginnis/gofish/common"
"github.com/stmcginnis/gofish/redfish"
)
type RedfishReceiverClientConfig struct {
// Hostname the redfish service belongs to
Hostname string
// is metric excluded globally or per client
isExcluded map[string](bool)
doPowerMetric bool
doProcessorMetrics bool
doThermalMetrics bool
skipProcessorMetricsURL map[string]bool
gofish gofish.ClientConfig
}
// RedfishReceiver configuration:
type RedfishReceiver struct {
receiver
config struct {
fanout int
Interval time.Duration
HttpTimeout time.Duration
// Client config for each redfish service
ClientConfigs []RedfishReceiverClientConfig
}
done chan bool // channel to finish / stop redfish receiver
wg sync.WaitGroup // wait group for redfish receiver
}
// readThermalMetrics reads thermal metrics from a redfish device
func (r *RedfishReceiver) readThermalMetrics(
clientConfig *RedfishReceiverClientConfig,
chassis *redfish.Chassis) error {
// Get thermal information for each chassis
thermal, err := chassis.Thermal()
if err != nil {
return fmt.Errorf("readMetrics: chassis.Thermal() failed: %v", err)
}
// Skip empty thermal information
if thermal == nil {
return nil
}
timestamp := time.Now()
for _, temperature := range thermal.Temperatures {
// Skip, when temperature metric is excluded
if clientConfig.isExcluded["temperature"] {
break
}
// Skip all temperatures which are not in enabled state
if temperature.Status.State != "" && temperature.Status.State != common.EnabledState {
continue
}
tags := map[string]string{
"hostname": clientConfig.Hostname,
"type": "node",
// ChassisType shall indicate the physical form factor for the type of chassis
"chassis_typ": string(chassis.ChassisType),
// Chassis name
"chassis_name": chassis.Name,
// ID uniquely identifies the resource
"temperature_id": temperature.ID,
// MemberID shall uniquely identify the member within the collection. For
// services supporting Redfish v1.6 or higher, this value shall be the
// zero-based array index.
"temperature_member_id": temperature.MemberID,
// PhysicalContext shall be a description of the affected device or region
// within the chassis to which this temperature measurement applies
"temperature_physical_context": string(temperature.PhysicalContext),
// Name
"temperature_name": temperature.Name,
}
// Delete empty tags
for key, value := range tags {
if value == "" {
delete(tags, key)
}
}
// Set meta data tags
meta := map[string]string{
"source": r.name,
"group": "Temperature",
"unit": "degC",
}
// ReadingCelsius shall be the current value of the temperature sensor's reading.
value := temperature.ReadingCelsius
y, err := lp.New("temperature", tags, meta,
map[string]interface{}{
"value": value,
},
timestamp)
if err == nil {
r.sink <- y
}
}
for _, fan := range thermal.Fans {
// Skip, when fan_speed metric is excluded
if clientConfig.isExcluded["fan_speed"] {
break
}
// Skip all fans which are not in enabled state
if fan.Status.State != common.EnabledState {
continue
}
tags := map[string]string{
"hostname": clientConfig.Hostname,
"type": "node",
// ChassisType shall indicate the physical form factor for the type of chassis
"chassis_typ": string(chassis.ChassisType),
// Chassis name
"chassis_name": chassis.Name,
// ID uniquely identifies the resource
"fan_id": fan.ID,
// MemberID shall uniquely identify the member within the collection. For
// services supporting Redfish v1.6 or higher, this value shall be the
// zero-based array index.
"fan_member_id": fan.MemberID,
// PhysicalContext shall be a description of the affected device or region
// within the chassis to which this fan is associated
"fan_physical_context": string(fan.PhysicalContext),
// Name
"fan_name": fan.Name,
}
// Delete empty tags
for key, value := range tags {
if value == "" {
delete(tags, key)
}
}
// Set meta data tags
meta := map[string]string{
"source": r.name,
"group": "FanSpeed",
"unit": string(fan.ReadingUnits),
}
// Reading shall be the current value of the fan sensor's reading
value := fan.Reading
y, err := lp.New("fan_speed", tags, meta,
map[string]interface{}{
"value": value,
},
timestamp)
if err == nil {
r.sink <- y
}
}
return nil
}
// readPowerMetrics reads power metrics from a redfish device
func (r *RedfishReceiver) readPowerMetrics(
clientConfig *RedfishReceiverClientConfig,
chassis *redfish.Chassis) error {
// Get power information for each chassis
power, err := chassis.Power()
if err != nil {
return fmt.Errorf("readMetrics: chassis.Power() failed: %v", err)
}
// Skip empty power information
if power == nil {
return nil
}
timestamp := time.Now()
// Read min, max and average consumed watts for each power control
for _, pc := range power.PowerControl {
// Skip all power controls which are not in enabled state
if pc.Status.State != "" && pc.Status.State != common.EnabledState {
continue
}
// Map of collected metrics
metrics := make(map[string]float32)
// PowerConsumedWatts shall represent the actual power being consumed (in
// Watts) by the chassis
if !clientConfig.isExcluded["consumed_watts"] {
metrics["consumed_watts"] = pc.PowerConsumedWatts
}
// AverageConsumedWatts shall represent the
// average power level that occurred averaged over the last IntervalInMin
// minutes.
if !clientConfig.isExcluded["average_consumed_watts"] {
metrics["average_consumed_watts"] = pc.PowerMetrics.AverageConsumedWatts
}
// MinConsumedWatts shall represent the
// minimum power level in watts that occurred within the last
// IntervalInMin minutes.
if !clientConfig.isExcluded["min_consumed_watts"] {
metrics["min_consumed_watts"] = pc.PowerMetrics.MinConsumedWatts
}
// MaxConsumedWatts shall represent the
// maximum power level in watts that occurred within the last
// IntervalInMin minutes
if !clientConfig.isExcluded["max_consumed_watts"] {
metrics["max_consumed_watts"] = pc.PowerMetrics.MaxConsumedWatts
}
// IntervalInMin shall represent the time interval (or window), in minutes,
// in which the PowerMetrics properties are measured over.
// Should be an integer, but some Dell implementations return as a float
intervalInMin :=
strconv.FormatFloat(
float64(pc.PowerMetrics.IntervalInMin), 'f', -1, 32)
// Set tags
tags := map[string]string{
"hostname": clientConfig.Hostname,
"type": "node",
// ChassisType shall indicate the physical form factor for the type of chassis
"chassis_typ": string(chassis.ChassisType),
// Chassis name
"chassis_name": chassis.Name,
// ID uniquely identifies the resource
"power_control_id": pc.ID,
// MemberID shall uniquely identify the member within the collection. For
// services supporting Redfish v1.6 or higher, this value shall be the
// zero-based array index.
"power_control_member_id": pc.MemberID,
// PhysicalContext shall be a description of the affected device(s) or region
// within the chassis to which this power control applies.
"power_control_physical_context": string(pc.PhysicalContext),
// Name
"power_control_name": pc.Name,
}
// Delete empty tags
for key, value := range tags {
if value == "" {
delete(tags, key)
}
}
// Set meta data tags
meta := map[string]string{
"source": r.name,
"group": "Energy",
"interval_in_minutes": intervalInMin,
"unit": "watts",
}
// Delete empty meta data tags
for key, value := range meta {
if value == "" {
delete(meta, key)
}
}
for name, value := range metrics {
y, err := lp.New(name, tags, meta,
map[string]interface{}{
"value": value,
},
timestamp)
if err == nil {
r.sink <- y
}
}
}
return nil
}
// readProcessorMetrics reads processor metrics from a redfish device
// See: https://redfish.dmtf.org/schemas/v1/ProcessorMetrics.json
func (r *RedfishReceiver) readProcessorMetrics(
clientConfig *RedfishReceiverClientConfig,
processor *redfish.Processor) error {
timestamp := time.Now()
// URL to processor metrics
URL := processor.ODataID + "/ProcessorMetrics"
// Skip previously detected non existing URLs
if clientConfig.skipProcessorMetricsURL[URL] {
return nil
}
resp, err := processor.Client.Get(URL)
if err != nil {
// Skip non existing URLs
if statusCode := err.(*common.Error).HTTPReturnedStatusCode; statusCode == http.StatusNotFound {
clientConfig.skipProcessorMetricsURL[URL] = true
return nil
}
return fmt.Errorf("processor.Client.Get(%v) failed: %+w", URL, err)
}
var processorMetrics struct {
common.Entity
ODataType string `json:"@odata.type"`
ODataEtag string `json:"@odata.etag"`
Description string `json:"Description"`
// This property shall contain the power, in watts, that the processor has consumed.
ConsumedPowerWatt float32 `json:"ConsumedPowerWatt"`
// This property shall contain the temperature, in Celsius, of the processor.
TemperatureCelsius float32 `json:"TemperatureCelsius"`
}
body, err := io.ReadAll(resp.Body)
if err != nil {
return fmt.Errorf("unable to read JSON for processor metrics: %+w", err)
}
err = json.Unmarshal(body, &processorMetrics)
if err != nil {
return fmt.Errorf(
"unable to unmarshal JSON='%s' for processor metrics: %+w",
string(body),
err,
)
}
processorMetrics.SetClient(processor.Client)
// Set tags
tags := map[string]string{
"hostname": clientConfig.Hostname,
"type": "socket",
// ProcessorType shall contain the string which identifies the type of processor contained in this Socket
"processor_typ": string(processor.ProcessorType),
// Processor name
"processor_name": processor.Name,
// ID uniquely identifies the resource
"processor_id": processor.ID,
}
// Delete empty tags
for key, value := range tags {
if value == "" {
delete(tags, key)
}
}
// Set meta data tags
metaPower := map[string]string{
"source": r.name,
"group": "Energy",
"unit": "watts",
}
namePower := "consumed_power"
if !clientConfig.isExcluded[namePower] &&
// Some servers return "ConsumedPowerWatt":65535 instead of "ConsumedPowerWatt":null
processorMetrics.ConsumedPowerWatt != 65535 {
y, err := lp.New(namePower, tags, metaPower,
map[string]interface{}{
"value": processorMetrics.ConsumedPowerWatt,
},
timestamp)
if err == nil {
r.sink <- y
}
}
// Set meta data tags
metaThermal := map[string]string{
"source": r.name,
"group": "Temperature",
"unit": "degC",
}
nameThermal := "temperature"
if !clientConfig.isExcluded[nameThermal] {
y, err := lp.New(nameThermal, tags, metaThermal,
map[string]interface{}{
"value": processorMetrics.TemperatureCelsius,
},
timestamp)
if err == nil {
r.sink <- y
}
}
return nil
}
// readMetrics reads redfish thermal, power and processor metrics from the redfish device
// configured in clientConfig
func (r *RedfishReceiver) readMetrics(clientConfig *RedfishReceiverClientConfig) error {
// Connect to redfish service
c, err := gofish.Connect(clientConfig.gofish)
if err != nil {
return fmt.Errorf(
"readMetrics: gofish.Connect({Username: %v, Endpoint: %v, BasicAuth: %v, HttpTimeout: %v, HttpInsecure: %v}) failed: %v",
clientConfig.gofish.Username,
clientConfig.gofish.Endpoint,
clientConfig.gofish.BasicAuth,
clientConfig.gofish.HTTPClient.Timeout,
clientConfig.gofish.HTTPClient.Transport.(*http.Transport).TLSClientConfig.InsecureSkipVerify,
err)
}
defer c.Logout()
// Create a session, when required
if _, err = c.GetSession(); err != nil {
c, err = c.CloneWithSession()
if err != nil {
return fmt.Errorf("readMetrics: Failed to create a session: %+w", err)
}
}
// Get all chassis managed by this service
isChassisListRequired :=
clientConfig.doThermalMetrics ||
clientConfig.doPowerMetric
var chassisList []*redfish.Chassis
if isChassisListRequired {
chassisList, err = c.Service.Chassis()
if err != nil {
return fmt.Errorf("readMetrics: c.Service.Chassis() failed: %v", err)
}
}
// Get all computer systems managed by this service
isComputerSystemListRequired := clientConfig.doProcessorMetrics
var computerSystemList []*redfish.ComputerSystem
if isComputerSystemListRequired {
computerSystemList, err = c.Service.Systems()
if err != nil {
return fmt.Errorf("readMetrics: c.Service.Systems() failed: %v", err)
}
}
// read thermal metrics
if clientConfig.doThermalMetrics {
for _, chassis := range chassisList {
err := r.readThermalMetrics(clientConfig, chassis)
if err != nil {
return err
}
}
}
// read power metrics
if clientConfig.doPowerMetric {
for _, chassis := range chassisList {
err = r.readPowerMetrics(clientConfig, chassis)
if err != nil {
return err
}
}
}
// read processor metrics
if clientConfig.doProcessorMetrics {
// loop for all computer systems
for _, system := range computerSystemList {
// loop for all processors
processors, err := system.Processors()
if err != nil {
return fmt.Errorf("readMetrics: system.Processors() failed: %v", err)
}
for _, processor := range processors {
err := r.readProcessorMetrics(clientConfig, processor)
if err != nil {
return err
}
}
}
}
return nil
}
// doReadMetrics reads metrics from all configure redfish devices.
// To compensate latencies of the Redfish devices a fanout is used.
func (r *RedfishReceiver) doReadMetric() {
// Create wait group and input channel for workers
var workerWaitGroup sync.WaitGroup
workerInput := make(chan *RedfishReceiverClientConfig, r.config.fanout)
// Create worker go routines
for i := 0; i < r.config.fanout; i++ {
// Increment worker wait group counter
workerWaitGroup.Add(1)
go func() {
// Decrement worker wait group counter
defer workerWaitGroup.Done()
// Read power metrics for each client config
for clientConfig := range workerInput {
err := r.readMetrics(clientConfig)
if err != nil {
cclog.ComponentError(r.name, err)
}
}
}()
}
// Distribute client configs to workers
for i := range r.config.ClientConfigs {
// Check done channel status
select {
case workerInput <- &r.config.ClientConfigs[i]:
case <-r.done:
// process done event
// Stop workers, clear channel and wait for all workers to finish
close(workerInput)
for range workerInput {
}
workerWaitGroup.Wait()
return
}
}
// Stop workers and wait for all workers to finish
close(workerInput)
workerWaitGroup.Wait()
}
// Start starts the redfish receiver
func (r *RedfishReceiver) Start() {
cclog.ComponentDebug(r.name, "START")
// Start redfish receiver
r.wg.Add(1)
go func() {
defer r.wg.Done()
// Create ticker
ticker := time.NewTicker(r.config.Interval)
defer ticker.Stop()
for {
r.doReadMetric()
select {
case tickerTime := <-ticker.C:
// Check if we missed the ticker event
if since := time.Since(tickerTime); since > 5*time.Second {
cclog.ComponentInfo(r.name, "Missed ticker event for more then", since)
}
// process ticker event -> continue
continue
case <-r.done:
// process done event
return
}
}
}()
cclog.ComponentDebug(r.name, "STARTED")
}
// Close closes the redfish receiver
func (r *RedfishReceiver) Close() {
cclog.ComponentDebug(r.name, "CLOSE")
// Send the signal and wait
close(r.done)
r.wg.Wait()
cclog.ComponentDebug(r.name, "DONE")
}
// NewRedfishReceiver creates a new instance of the redfish receiver
// Initialize the receiver by giving it a name and reading in the config JSON
func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
r := new(RedfishReceiver)
// Config options from config file
configJSON := struct {
Type string `json:"type"`
// Maximum number of simultaneous redfish connections (default: 64)
Fanout int `json:"fanout,omitempty"`
// How often the redfish power metrics should be read and send to the sink (default: 30 s)
IntervalString string `json:"interval,omitempty"`
// Control whether a client verifies the server's certificate
// (default: true == do not verify server's certificate)
HttpInsecure bool `json:"http_insecure,omitempty"`
// Time limit for requests made by this HTTP client (default: 10 s)
HttpTimeoutString string `json:"http_timeout,omitempty"`
// Default client username, password and endpoint
Username *string `json:"username"` // User name to authenticate with
Password *string `json:"password"` // Password to use for authentication
Endpoint *string `json:"endpoint"` // URL of the redfish service
// Globally disable collection of power, processor or thermal metrics
DisablePowerMetrics bool `json:"disable_power_metrics"`
DisableProcessorMetrics bool `json:"disable_processor_metrics"`
DisableThermalMetrics bool `json:"disable_thermal_metrics"`
// Globally excluded metrics
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ClientConfigs []struct {
HostList string `json:"host_list"` // List of hosts with the same client configuration
Username *string `json:"username"` // User name to authenticate with
Password *string `json:"password"` // Password to use for authentication
Endpoint *string `json:"endpoint"` // URL of the redfish service
// Per client disable collection of power,processor or thermal metrics
DisablePowerMetrics bool `json:"disable_power_metrics"`
DisableProcessorMetrics bool `json:"disable_processor_metrics"`
DisableThermalMetrics bool `json:"disable_thermal_metrics"`
// Per client excluded metrics
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
} `json:"client_config"`
}{
// Set defaults values
// Allow overwriting these defaults by reading config JSON
Fanout: 64,
IntervalString: "30s",
HttpTimeoutString: "10s",
HttpInsecure: true,
}
// Set name
r.name = fmt.Sprintf("RedfishReceiver(%s)", name)
// Create done channel
r.done = make(chan bool)
// Read the redfish receiver specific JSON config
if len(config) > 0 {
d := json.NewDecoder(bytes.NewReader(config))
d.DisallowUnknownFields()
if err := d.Decode(&configJSON); err != nil {
cclog.ComponentError(r.name, "Error reading config:", err.Error())
return nil, err
}
}
// Convert interval string representation to duration
var err error
r.config.Interval, err = time.ParseDuration(configJSON.IntervalString)
if err != nil {
err := fmt.Errorf(
"Failed to parse duration string interval='%s': %w",
configJSON.IntervalString,
err,
)
cclog.Error(r.name, err)
return nil, err
}
// HTTP timeout duration
r.config.HttpTimeout, err = time.ParseDuration(configJSON.HttpTimeoutString)
if err != nil {
err := fmt.Errorf(
"Failed to parse duration string http_timeout='%s': %w",
configJSON.HttpTimeoutString,
err,
)
cclog.Error(r.name, err)
return nil, err
}
// Create new http client
customTransport := http.DefaultTransport.(*http.Transport).Clone()
customTransport.TLSClientConfig = &tls.Config{
InsecureSkipVerify: configJSON.HttpInsecure,
}
httpClient := &http.Client{
Timeout: r.config.HttpTimeout,
Transport: customTransport,
}
// Initialize client configurations
r.config.ClientConfigs = make([]RedfishReceiverClientConfig, 0)
// Create client config from JSON config
for i := range configJSON.ClientConfigs {
clientConfigJSON := &configJSON.ClientConfigs[i]
var endpoint_pattern string
if clientConfigJSON.Endpoint != nil {
endpoint_pattern = *clientConfigJSON.Endpoint
} else if configJSON.Endpoint != nil {
endpoint_pattern = *configJSON.Endpoint
} else {
err := fmt.Errorf("client config number %v requires endpoint", i)
cclog.ComponentError(r.name, err)
return nil, err
}
var username string
if clientConfigJSON.Username != nil {
username = *clientConfigJSON.Username
} else if configJSON.Username != nil {
username = *configJSON.Username
} else {
err := fmt.Errorf("client config number %v requires username", i)
cclog.ComponentError(r.name, err)
return nil, err
}
var password string
if clientConfigJSON.Password != nil {
password = *clientConfigJSON.Password
} else if configJSON.Password != nil {
password = *configJSON.Password
} else {
err := fmt.Errorf("client config number %v requires password", i)
cclog.ComponentError(r.name, err)
return nil, err
}
// Which metrics should be collected
doPowerMetric :=
!(configJSON.DisablePowerMetrics ||
clientConfigJSON.DisablePowerMetrics)
doProcessorMetrics :=
!(configJSON.DisableProcessorMetrics ||
clientConfigJSON.DisableProcessorMetrics)
doThermalMetrics :=
!(configJSON.DisableThermalMetrics ||
clientConfigJSON.DisableThermalMetrics)
// Is metrics excluded globally or per client
isExcluded := make(map[string]bool)
for _, key := range clientConfigJSON.ExcludeMetrics {
isExcluded[key] = true
}
for _, key := range configJSON.ExcludeMetrics {
isExcluded[key] = true
}
hostList, err := hostlist.Expand(clientConfigJSON.HostList)
if err != nil {
err := fmt.Errorf("client config number %d failed to parse host list %s: %v",
i, clientConfigJSON.HostList, err)
cclog.ComponentError(r.name, err)
return nil, err
}
for _, host := range hostList {
// Endpoint of the redfish service
endpoint := strings.Replace(endpoint_pattern, "%h", host, -1)
r.config.ClientConfigs = append(
r.config.ClientConfigs,
RedfishReceiverClientConfig{
Hostname: host,
isExcluded: isExcluded,
doPowerMetric: doPowerMetric,
doProcessorMetrics: doProcessorMetrics,
doThermalMetrics: doThermalMetrics,
skipProcessorMetricsURL: make(map[string]bool),
gofish: gofish.ClientConfig{
Username: username,
Password: password,
Endpoint: endpoint,
HTTPClient: httpClient,
},
})
}
}
// Compute parallel fanout to use
numClients := len(r.config.ClientConfigs)
r.config.fanout = configJSON.Fanout
if numClients < r.config.fanout {
r.config.fanout = numClients
}
if numClients == 0 {
err := fmt.Errorf("at least one client config is required")
cclog.ComponentError(r.name, err)
return nil, err
}
// Check for duplicate client configurations
isDuplicate := make(map[string]bool)
for i := range r.config.ClientConfigs {
host := r.config.ClientConfigs[i].Hostname
if isDuplicate[host] {
err := fmt.Errorf("Found duplicate client config for host %s", host)
cclog.ComponentError(r.name, err)
return nil, err
}
isDuplicate[host] = true
}
// Give some basic info about redfish receiver status
cclog.ComponentInfo(r.name, "Monitoring", numClients, "clients")
cclog.ComponentInfo(r.name, "Monitoring interval:", r.config.Interval)
cclog.ComponentInfo(r.name, "Monitoring parallel fanout:", r.config.fanout)
return r, nil
}

View File

@ -0,0 +1,54 @@
## Redfish receiver
The Redfish receiver uses the [Redfish (specification)](https://www.dmtf.org/standards/redfish) to query thermal and power metrics. Thermal metrics may include various fan speeds and temperatures. Power metrics may include the current power consumption of various hardware components. It may also include the minimum, maximum and average power consumption of these components in a given time interval. The receiver will poll each configured redfish device once in a given interval. Multiple devices can be accessed in parallel to increase throughput.
### Configuration structure
```json
{
"<redfish receiver name>": {
"type": "redfish",
"username": "<Username>",
"password": "<Password>",
"endpoint": "https://%h-bmc",
"exclude_metrics": [ "min_consumed_watts" ],
"client_config": [
{
"host_list": "n[1,2-4]"
},
{
"host_list": "n5"
"disable_power_metrics": true
},
{
"host_list": "n6" ],
"username": "<Username 2>",
"password": "<Password 2>",
"endpoint": "https://%h-BMC",
"disable_thermal_metrics": true
}
]
}
}
```
Global settings:
- `fanout`: Maximum number of simultaneous redfish connections (default: 64)
- `interval`: How often the redfish power metrics should be read and send to the sink (default: 30 s)
- `http_insecure`: Control whether a client verifies the server's certificate (default: true == do not verify server's certificate)
- `http_timeout`: Time limit for requests made by this HTTP client (default: 10 s)
Global and per redfish device settings (per redfish device settings overwrite the global settings):
- `disable_power_metrics`: disable collection of power metrics
- `disable_processor_metrics`: disable collection of processor metrics
- `disable_thermal_metrics`: disable collection of thermal metrics
- `exclude_metrics`: list of excluded metrics
- `username`: User name to authenticate with
- `password`: Password to use for authentication
- `endpoint`: URL of the redfish service (placeholder `%h` gets replaced by the hostname)
Per redfish device settings:
- `host_list`: List of hosts with the same client configuration

101
receivers/sampleReceiver.go Normal file
View File

@ -0,0 +1,101 @@
package receivers
import (
"encoding/json"
"fmt"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
// SampleReceiver configuration: receiver type, listen address, port
type SampleReceiverConfig struct {
Type string `json:"type"`
Addr string `json:"address"`
Port string `json:"port"`
}
type SampleReceiver struct {
receiver
config SampleReceiverConfig
// Storage for static information
meta map[string]string
// Use in case of own go routine
// done chan bool
// wg sync.WaitGroup
}
// Implement functions required for Receiver interface
// Start(), Close()
// See: metricReceiver.go
func (r *SampleReceiver) Start() {
cclog.ComponentDebug(r.name, "START")
// Start server process like http.ListenAndServe()
// or use own go routine but always make sure it exits
// as soon as it gets the signal of the r.done channel
//
// r.done = make(chan bool)
// r.wg.Add(1)
// go func() {
// defer r.wg.Done()
//
// // Create ticker
// ticker := time.NewTicker(30 * time.Second)
// defer ticker.Stop()
//
// for {
// readMetric()
// select {
// case <-ticker.C:
// // process ticker event -> continue
// continue
// case <-r.done:
// return
// }
// }
// }()
}
// Close receiver: close network connection, close files, close libraries, ...
func (r *SampleReceiver) Close() {
cclog.ComponentDebug(r.name, "CLOSE")
// Close server like http.Shutdown()
// in case of own go routine, send the signal and wait
// r.done <- true
// r.wg.Wait()
}
// New function to create a new instance of the receiver
// Initialize the receiver by giving it a name and reading in the config JSON
func NewSampleReceiver(name string, config json.RawMessage) (Receiver, error) {
r := new(SampleReceiver)
// Set name of SampleReceiver
// The name should be chosen in such a way that different instances of SampleReceiver can be distinguished
r.name = fmt.Sprintf("SampleReceiver(%s)", name)
// Set static information
r.meta = map[string]string{"source": r.name}
// Set defaults in r.config
// Allow overwriting these defaults by reading config JSON
// Read the sample receiver specific JSON config
if len(config) > 0 {
err := json.Unmarshal(config, &r.config)
if err != nil {
cclog.ComponentError(r.name, "Error reading config:", err.Error())
return nil, err
}
}
// Check that all required fields in the configuration are set
// Use 'if len(r.config.Option) > 0' for strings
return r, nil
}

View File

@ -1,23 +1,22 @@
{ {
"process_messages" : { "add_tags" : [
"add_tag_if": [ {
{ "key" : "cluster",
"key" : "cluster", "value" : "testcluster",
"value" : "testcluster", "if" : "*"
"if" : "true" },
}, {
{ "key" : "test",
"key" : "test", "value" : "testing",
"value" : "testing", "if" : "name == 'temp_package_id_0'"
"if" : "name == 'temp_package_id_0'" }
} ],
], "delete_tags" : [
"delete_tag_if": [ {
{ "key" : "unit",
"key" : "unit", "value" : "*",
"if" : "true" "if" : "*"
} }
] ],
},
"interval_timestamp" : true "interval_timestamp" : true
} }

View File

@ -25,7 +25,7 @@ CC_USER=clustercockpit
CC_GROUP=clustercockpit CC_GROUP=clustercockpit
CONF_DIR=/etc/cc-metric-collector CONF_DIR=/etc/cc-metric-collector
PID_FILE=/var/run/$NAME.pid PID_FILE=/var/run/$NAME.pid
DAEMON=/usr/bin/$NAME DAEMON=/usr/sbin/$NAME
CONF_FILE=${CONF_DIR}/cc-metric-collector.json CONF_FILE=${CONF_DIR}/cc-metric-collector.json
umask 0027 umask 0027

View File

@ -1,175 +0,0 @@
#!/bin/bash -l
SRCDIR="$(pwd)"
DESTDIR="$1"
if [ -z "$DESTDIR" ]; then
echo "Destination folder not provided"
exit 1
fi
COLLECTORS=$(find "${SRCDIR}/collectors" -name "*Metric.md")
SINKS=$(find "${SRCDIR}/sinks" -name "*Sink.md")
RECEIVERS=$(find "${SRCDIR}/receivers" -name "*Receiver.md")
# Collectors
mkdir -p "${DESTDIR}/collectors"
for F in $COLLECTORS; do
echo "$F"
FNAME=$(basename "$F")
TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
echo "'${TITLE//\`/}'"
if [ "${TITLE}" == "" ]; then continue; fi
rm --force "${DESTDIR}/collectors/${FNAME}"
cat << EOF >> "${DESTDIR}/collectors/${FNAME}"
---
title: ${TITLE//\`/}
description: >
Toplevel ${FNAME/.md/}
categories: [cc-metric-collector]
tags: [cc-metric-collector, Collector, ${FNAME/Metric.md/}]
weight: 2
---
EOF
cat "$F" >> "${DESTDIR}/collectors/${FNAME}"
done
if [ -e "${SRCDIR}/collectors/README.md" ]; then
cat << EOF > "${DESTDIR}/collectors/_index.md"
---
title: cc-metric-collector's collectors
description: Documentation of cc-metric-collector's collectors
categories: [cc-metric-collector]
tags: [cc-metric-collector, Collector, General]
weight: 40
---
EOF
cat "${SRCDIR}/collectors/README.md" >> "${DESTDIR}/collectors/_index.md"
fi
# Sinks
mkdir -p "${DESTDIR}/sinks"
for F in $SINKS; do
echo "$F"
FNAME=$(basename "$F")
TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
echo "'${TITLE//\`/}'"
if [ "${TITLE}" == "" ]; then continue; fi
rm --force "${DESTDIR}/sinks/${FNAME}"
cat << EOF >> "${DESTDIR}/sinks/${FNAME}"
---
title: ${TITLE//\`/}
description: >
Toplevel ${FNAME/.md/}
categories: [cc-metric-collector]
tags: [cc-metric-collector, Sink, ${FNAME/Sink.md/}]
weight: 2
---
EOF
cat "$F" >> "${DESTDIR}/sinks/${FNAME}"
done
if [ -e "${SRCDIR}/collectors/README.md" ]; then
cat << EOF > "${DESTDIR}/sinks/_index.md"
---
title: cc-metric-collector's sinks
description: Documentation of cc-metric-collector's sinks
categories: [cc-metric-collector]
tags: [cc-metric-collector, Sink, General]
weight: 40
---
EOF
cat "${SRCDIR}/sinks/README.md" >> "${DESTDIR}/sinks/_index.md"
fi
# Receivers
mkdir -p "${DESTDIR}/receivers"
for F in $RECEIVERS; do
echo "$F"
FNAME=$(basename "$F")
TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
echo "'${TITLE//\`/}'"
if [ "${TITLE}" == "" ]; then continue; fi
rm --force "${DESTDIR}/receivers/${FNAME}"
cat << EOF >> "${DESTDIR}/receivers/${FNAME}"
---
title: ${TITLE//\`/}
description: >
Toplevel ${FNAME/.md/}
categories: [cc-metric-collector]
tags: [cc-metric-collector, Receiver, ${FNAME/Receiver.md/}]
weight: 2
---
EOF
cat "$F" >> "${DESTDIR}/receivers/${FNAME}"
done
if [ -e "${SRCDIR}/receivers/README.md" ]; then
cat << EOF > "${DESTDIR}/receivers/_index.md"
---
title: cc-metric-collector's receivers
description: Documentation of cc-metric-collector's receivers
categories: [cc-metric-collector]
tags: [cc-metric-collector, Receiver, General]
weight: 40
---
EOF
cat "${SRCDIR}/receivers/README.md" >> "${DESTDIR}/receivers/_index.md"
fi
mkdir -p "${DESTDIR}/internal/metricRouter"
if [ -e "${SRCDIR}/internal/metricRouter/README.md" ]; then
cat << EOF > "${DESTDIR}/internal/metricRouter/_index.md"
---
title: cc-metric-collector's router
description: Documentation of cc-metric-collector's router
categories: [cc-metric-collector]
tags: [cc-metric-collector, Router, General]
weight: 40
---
EOF
cat "${SRCDIR}/internal/metricRouter/README.md" >> "${DESTDIR}/internal/metricRouter/_index.md"
fi
if [ -e "${SRCDIR}/README.md" ]; then
cat << EOF > "${DESTDIR}/_index.md"
---
title: cc-metric-collector
description: Documentation of cc-metric-collector
categories: [cc-metric-collector]
tags: [cc-metric-collector, General]
weight: 40
---
EOF
cat "${SRCDIR}/README.md" >> "${DESTDIR}/_index.md"
sed -i -e 's+README.md+_index.md+g' "${DESTDIR}/_index.md"
fi
mkdir -p "${DESTDIR}/pkg/messageProcessor"
if [ -e "${SRCDIR}/pkg/messageProcessor/README.md" ]; then
cat << EOF > "${DESTDIR}/pkg/messageProcessor/_index.md"
---
title: cc-metric-collector's message processor
description: Documentation of cc-metric-collector's message processor
categories: [cc-metric-collector]
tags: [cc-metric-collector, Message Processor]
weight: 40
---
EOF
cat "${SRCDIR}/pkg/messageProcessor/README.md" >> "${DESTDIR}/pkg/messageProcessor/_index.md"
fi

108
sinks/README.md Normal file
View File

@ -0,0 +1,108 @@
# CCMetric sinks
This folder contains the SinkManager and sink implementations for the cc-metric-collector.
# Available sinks:
- [`stdout`](./stdoutSink.md): Print all metrics to `stdout`, `stderr` or a file
- [`http`](./httpSink.md): Send metrics to an HTTP server as POST requests
- [`influxdb`](./influxSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database
- [`influxasync`](./influxAsyncSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database with non-blocking write API
- [`nats`](./natsSink.md): Publish metrics to the [NATS](https://nats.io/) network overlay system
- [`ganglia`](./gangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) using the `gmetric` CLI tool
- [`libganglia`](./libgangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) directly using `libganglia.so`
- [`prometeus`](./prometheusSink.md): Publish metrics for the [Prometheus Monitoring System](https://prometheus.io/)
# Configuration
The configuration file for the sinks is a list of configurations. The `type` field in each specifies which sink to initialize.
```json
[
"mystdout" : {
"type" : "stdout",
"meta_as_tags" : [
"unit"
]
},
"metricstore" : {
"type" : "http",
"host" : "localhost",
"port" : "4123",
"database" : "ccmetric",
"password" : "<jwt token>"
}
]
```
# Contributing own sinks
A sink contains five functions and is derived from the type `sink`:
* `Init(name string, config json.RawMessage) error`
* `Write(point CCMetric) error`
* `Flush() error`
* `Close()`
* `New<Typename>(name string, config json.RawMessage) (Sink, error)` (calls the `Init()` function)
The data structures should be set up in `Init()` like opening a file or server connection. The `Write()` function writes/sends the data. For non-blocking sinks, the `Flush()` method tells the sink to drain its internal buffers. The `Close()` function should tear down anything created in `Init()`.
Finally, the sink needs to be registered in the `sinkManager.go`. There is a list of sinks called `AvailableSinks` which is a map (`sink_type_string` -> `pointer to sink interface`). Add a new entry with a descriptive name and the new sink.
## Sample sink
```go
package sinks
import (
"encoding/json"
"log"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
)
type SampleSinkConfig struct {
defaultSinkConfig // defines JSON tags for 'name' and 'meta_as_tags'
}
type SampleSink struct {
sink // declarate 'name' and 'meta_as_tags'
config StdoutSinkConfig // entry point to the SampleSinkConfig
}
// Initialize the sink by giving it a name and reading in the config JSON
func (s *SampleSink) Init(name string, config json.RawMessage) error {
s.name = fmt.Sprintf("SampleSink(%s)", name) // Always specify a name here
// Read in the config JSON
if len(config) > 0 {
err := json.Unmarshal(config, &s.config)
if err != nil {
return err
}
}
return nil
}
// Code to submit a single CCMetric to the sink
func (s *SampleSink) Write(point lp.CCMetric) error {
log.Print(point)
return nil
}
// If the sink uses batched sends internally, you can tell to flush its buffers
func (s *SampleSink) Flush() error {
return nil
}
// Close sink: close network connection, close files, close libraries, ...
func (s *SampleSink) Close() {}
// New function to create a new instance of the sink
func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
s := new(SampleSink)
err := s.Init(name, config)
return s, err
}
```

269
sinks/gangliaCommon.go Normal file
View File

@ -0,0 +1,269 @@
package sinks
import (
"fmt"
"strings"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
func GangliaMetricName(point lp.CCMetric) string {
name := point.Name()
metricType, typeOK := point.GetTag("type")
metricTid, tidOk := point.GetTag("type-id")
gangliaType := metricType + metricTid
if strings.Contains(name, metricType) && tidOk {
name = strings.Replace(name, metricType, gangliaType, -1)
} else if typeOK && tidOk {
name = metricType + metricTid + "_" + name
} else if point.HasTag("device") {
device, _ := point.GetTag("device")
name = name + "_" + device
}
return name
}
func GangliaMetricRename(name string) string {
if name == "net_bytes_in" {
return "bytes_in"
} else if name == "net_bytes_out" {
return "bytes_out"
} else if name == "net_pkts_in" {
return "pkts_in"
} else if name == "net_pkts_out" {
return "pkts_out"
} else if name == "cpu_iowait" {
return "cpu_wio"
}
return name
}
func GangliaSlopeType(point lp.CCMetric) uint {
name := point.Name()
if name == "mem_total" || name == "swap_total" {
return 0
}
return 3
}
const DEFAULT_GANGLIA_METRIC_TMAX = 300
const DEFAULT_GANGLIA_METRIC_SLOPE = "both"
type GangliaMetric struct {
Name string
Type string
Slope string
Tmax int
Unit string
}
type GangliaMetricGroup struct {
Name string
Metrics []GangliaMetric
}
var CommonGangliaMetrics = []GangliaMetricGroup{
{
Name: "memory",
Metrics: []GangliaMetric{
{"mem_total", "float", "zero", 1200, "KB"},
{"swap_total", "float", "zero", 1200, "KB"},
{"mem_free", "float", "both", 180, "KB"},
{"mem_shared", "float", "both", 180, "KB"},
{"mem_buffers", "float", "both", 180, "KB"},
{"mem_cached", "float", "both", 180, "KB"},
{"swap_free", "float", "both", 180, "KB"},
{"mem_sreclaimable", "float", "both", 180, "KB"},
{"mem_slab", "float", "both", 180, "KB"},
},
},
{
Name: "cpu",
Metrics: []GangliaMetric{
{"cpu_num", "uint32", "zero", 1200, "CPUs"},
{"cpu_speed", "uint32", "zero", 1200, "MHz"},
{"cpu_user", "float", "both", 90, "%"},
{"cpu_nice", "float", "both", 90, "%"},
{"cpu_system", "float", "both", 90, "%"},
{"cpu_idle", "float", "both", 3800, "%"},
{"cpu_aidle", "float", "both", 90, "%"},
{"cpu_wio", "float", "both", 90, "%"},
{"cpu_intr", "float", "both", 90, "%"},
{"cpu_sintr", "float", "both", 90, "%"},
{"cpu_steal", "float", "both", 90, "%"},
{"cpu_guest", "float", "both", 90, "%"},
{"cpu_gnice", "float", "both", 90, "%"},
},
},
{
Name: "load",
Metrics: []GangliaMetric{
{"load_one", "float", "both", 70, ""},
{"load_five", "float", "both", 325, ""},
{"load_fifteen", "float", "both", 950, ""},
},
},
{
Name: "disk",
Metrics: []GangliaMetric{
{"disk_total", "double", "both", 1200, "GB"},
{"disk_free", "double", "both", 180, "GB"},
{"part_max_used", "float", "both", 180, "%"},
},
},
{
Name: "network",
Metrics: []GangliaMetric{
{"bytes_out", "float", "both", 300, "bytes/sec"},
{"bytes_in", "float", "both", 300, "bytes/sec"},
{"pkts_in", "float", "both", 300, "packets/sec"},
{"pkts_out", "float", "both", 300, "packets/sec"},
},
},
{
Name: "process",
Metrics: []GangliaMetric{
{"proc_run", "uint32", "both", 950, ""},
{"proc_total", "uint32", "both", 950, ""},
},
},
{
Name: "system",
Metrics: []GangliaMetric{
{"boottime", "uint32", "zero", 1200, "s"},
{"sys_clock", "uint32", "zero", 1200, "s"},
{"machine_type", "string", "zero", 1200, ""},
{"os_name", "string", "zero", 1200, ""},
{"os_release", "string", "zero", 1200, ""},
{"mtu", "uint32", "both", 1200, ""},
},
},
}
type GangliaMetricConfig struct {
Type string
Slope string
Tmax int
Unit string
Group string
Value string
Name string
}
func GetCommonGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
mname := GangliaMetricRename(point.Name())
if oldname, ok := point.GetMeta("oldname"); ok {
mname = GangliaMetricRename(oldname)
}
for _, group := range CommonGangliaMetrics {
for _, metric := range group.Metrics {
if metric.Name == mname {
valueStr := ""
value, ok := point.GetField("value")
if ok {
switch real := value.(type) {
case float64:
valueStr = fmt.Sprintf("%f", real)
case float32:
valueStr = fmt.Sprintf("%f", real)
case int64:
valueStr = fmt.Sprintf("%d", real)
case int32:
valueStr = fmt.Sprintf("%d", real)
case int:
valueStr = fmt.Sprintf("%d", real)
case uint64:
valueStr = fmt.Sprintf("%d", real)
case uint32:
valueStr = fmt.Sprintf("%d", real)
case uint:
valueStr = fmt.Sprintf("%d", real)
case string:
valueStr = real
default:
}
}
return GangliaMetricConfig{
Group: group.Name,
Type: metric.Type,
Slope: metric.Slope,
Tmax: metric.Tmax,
Unit: metric.Unit,
Value: valueStr,
Name: GangliaMetricRename(mname),
}
}
}
}
return GangliaMetricConfig{
Group: "",
Type: "",
Slope: "",
Tmax: 0,
Unit: "",
Value: "",
Name: "",
}
}
func GetGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
mname := GangliaMetricRename(point.Name())
if oldname, ok := point.GetMeta("oldname"); ok {
mname = GangliaMetricRename(oldname)
}
group := ""
if g, ok := point.GetMeta("group"); ok {
group = g
}
unit := ""
if u, ok := point.GetMeta("unit"); ok {
unit = u
}
valueType := "double"
valueStr := ""
value, ok := point.GetField("value")
if ok {
switch real := value.(type) {
case float64:
valueStr = fmt.Sprintf("%f", real)
valueType = "double"
case float32:
valueStr = fmt.Sprintf("%f", real)
valueType = "float"
case int64:
valueStr = fmt.Sprintf("%d", real)
valueType = "int32"
case int32:
valueStr = fmt.Sprintf("%d", real)
valueType = "int32"
case int:
valueStr = fmt.Sprintf("%d", real)
valueType = "int32"
case uint64:
valueStr = fmt.Sprintf("%d", real)
valueType = "uint32"
case uint32:
valueStr = fmt.Sprintf("%d", real)
valueType = "uint32"
case uint:
valueStr = fmt.Sprintf("%d", real)
valueType = "uint32"
case string:
valueStr = real
valueType = "string"
default:
valueType = "invalid"
}
}
return GangliaMetricConfig{
Group: group,
Type: valueType,
Slope: DEFAULT_GANGLIA_METRIC_SLOPE,
Tmax: DEFAULT_GANGLIA_METRIC_TMAX,
Unit: unit,
Value: valueStr,
Name: GangliaMetricRename(mname),
}
}

126
sinks/gangliaSink.go Normal file
View File

@ -0,0 +1,126 @@
package sinks
import (
"bytes"
"encoding/json"
"errors"
"fmt"
"strings"
// "time"
"os/exec"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const GMETRIC_EXEC = `gmetric`
const GMETRIC_CONFIG = `/etc/ganglia/gmond.conf`
type GangliaSinkConfig struct {
defaultSinkConfig
GmetricPath string `json:"gmetric_path,omitempty"`
GmetricConfig string `json:"gmetric_config,omitempty"`
AddGangliaGroup bool `json:"add_ganglia_group,omitempty"`
AddTagsAsDesc bool `json:"add_tags_as_desc,omitempty"`
ClusterName string `json:"cluster_name,omitempty"`
AddTypeToName bool `json:"add_type_to_name,omitempty"`
AddUnits bool `json:"add_units,omitempty"`
}
type GangliaSink struct {
sink
gmetric_path string
gmetric_config string
config GangliaSinkConfig
}
func (s *GangliaSink) Write(point lp.CCMetric) error {
var err error = nil
//var tagsstr []string
var argstr []string
// Get metric config (type, value, ... in suitable format)
conf := GetCommonGangliaConfig(point)
if len(conf.Type) == 0 {
conf = GetGangliaConfig(point)
}
if len(conf.Type) == 0 {
return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
}
if s.config.AddGangliaGroup {
argstr = append(argstr, fmt.Sprintf("--group=%s", conf.Group))
}
if s.config.AddUnits && len(conf.Unit) > 0 {
argstr = append(argstr, fmt.Sprintf("--units=%s", conf.Unit))
}
if len(s.config.ClusterName) > 0 {
argstr = append(argstr, fmt.Sprintf("--cluster=%s", s.config.ClusterName))
}
// if s.config.AddTagsAsDesc && len(tagsstr) > 0 {
// argstr = append(argstr, fmt.Sprintf("--desc=%q", strings.Join(tagsstr, ",")))
// }
if len(s.gmetric_config) > 0 {
argstr = append(argstr, fmt.Sprintf("--conf=%s", s.gmetric_config))
}
if s.config.AddTypeToName {
argstr = append(argstr, fmt.Sprintf("--name=%s", GangliaMetricName(point)))
} else {
argstr = append(argstr, fmt.Sprintf("--name=%s", conf.Name))
}
argstr = append(argstr, fmt.Sprintf("--slope=%s", conf.Slope))
argstr = append(argstr, fmt.Sprintf("--value=%s", conf.Value))
argstr = append(argstr, fmt.Sprintf("--type=%s", conf.Type))
argstr = append(argstr, fmt.Sprintf("--tmax=%d", conf.Tmax))
cclog.ComponentDebug(s.name, s.gmetric_path, strings.Join(argstr, " "))
command := exec.Command(s.gmetric_path, argstr...)
command.Wait()
_, err = command.Output()
return err
}
func (s *GangliaSink) Flush() error {
return nil
}
func (s *GangliaSink) Close() {
}
func NewGangliaSink(name string, config json.RawMessage) (Sink, error) {
s := new(GangliaSink)
s.name = fmt.Sprintf("GangliaSink(%s)", name)
s.config.AddTagsAsDesc = false
s.config.AddGangliaGroup = false
if len(config) > 0 {
d := json.NewDecoder(bytes.NewReader(config))
d.DisallowUnknownFields()
if err := d.Decode(&s.config); err != nil {
cclog.ComponentError(s.name, "Error reading config:", err.Error())
return nil, err
}
}
s.gmetric_path = ""
s.gmetric_config = ""
if len(s.config.GmetricPath) > 0 {
p, err := exec.LookPath(s.config.GmetricPath)
if err == nil {
s.gmetric_path = p
}
}
if len(s.gmetric_path) == 0 {
p, err := exec.LookPath(string(GMETRIC_EXEC))
if err == nil {
s.gmetric_path = p
}
}
if len(s.gmetric_path) == 0 {
return nil, errors.New("cannot find executable 'gmetric'")
}
if len(s.config.GmetricConfig) > 0 {
s.gmetric_config = s.config.GmetricConfig
}
return s, nil
}

21
sinks/gangliaSink.md Normal file
View File

@ -0,0 +1,21 @@
## `ganglia` sink
The `ganglia` sink uses the `gmetric` tool of the [Ganglia Monitoring System](http://ganglia.info/) to submit the metrics
### Configuration structure
```json
{
"<name>": {
"type": "ganglia",
"meta_as_tags" : true,
"gmetric_path" : "/path/to/gmetric",
"add_ganglia_group" : true
}
}
```
- `type`: makes the sink an `ganglia` sink
- `meta_as_tags`: print all meta information as tags in the output (optional)
- `gmetric_path`: Path to `gmetric` executable (optional). If not given, the sink searches in `$PATH` for `gmetric`.
- `add_ganglia_group`: Add `--group=X` based on meta information to the `gmetric` call. Some old versions of `gmetric` do not support the `--group` option.

Some files were not shown because too many files have changed in this diff Show More