Compare commits

..

13 Commits

Author SHA1 Message Date
Thomas Röhl
9ca73a9f50 Add documentation of the internal structure of the LikwidCollector to its documentation 2024-04-25 17:26:18 +02:00
Thomas Röhl
0186dce521 Create lockfile if it does not exist 2024-04-25 17:25:53 +02:00
Thomas Roehl
16c796a2b8 Merge branch 'develop' of github.com:ClusterCockpit/cc-metric-collector into develop 2024-04-10 19:57:54 +02:00
Thomas Roehl
b6c4769db3 Remove stray error check 2024-04-10 19:57:46 +02:00
Holger Obermaier
7bbee70c14 Update golang toolchain to 1.21 2024-03-06 15:14:44 +01:00
Holger Obermaier
902f4349b6 Read sensors through redfish 2024-03-06 14:59:47 +01:00
Holger Obermaier
6aada60d97 Update requirements to latest version 2024-01-22 16:21:14 +01:00
Holger Obermaier
06ca37e705 Fix for API changes in gofish@v0.15.0 2024-01-22 15:46:18 +01:00
Thomas Roehl
9b671ce68f Add comment about precision requirement for cc-metric-store 2023-12-11 16:06:28 +01:00
Thomas Roehl
226e8425cb Allow selection of timestamp precision in HttpSink 2023-12-11 14:57:06 +01:00
Thomas Gruber
a37f6603c8 Update cc-metric-collector.init 2023-12-11 13:47:53 +01:00
Thomas Roehl
78902305e8 Merge branch 'develop' of github.com:ClusterCockpit/cc-metric-collector into develop 2023-12-08 15:11:40 +01:00
Thomas Röhl
e7b77f7721 Add cpu_used (all-cpu_idle) to CpustatCollector 2023-04-05 11:20:09 +02:00
86 changed files with 1375 additions and 4687 deletions

View File

@@ -15,7 +15,7 @@ jobs:
#
# Build on AlmaLinux 8 using go-toolset
#
AlmaLinux8-RPM-build:
AlmaLinux-RPM-build:
runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux
container: almalinux:8
@@ -41,17 +41,14 @@ jobs:
submodules: recursive
fetch-depth: 0
# - name: Setup Golang
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
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 \
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 \
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 \
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
dnf --assumeyes install \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
@@ -73,101 +70,20 @@ jobs:
NEW_SRPM=${OLD_SRPM/el8/alma8}
mv "${OLD_RPM}" "${NEW_RPM}"
mv "${OLD_SRPM}" "${NEW_SRPM}"
echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
echo "::set-output name=SRPM::${NEW_SRPM}"
echo "::set-output name=RPM::${NEW_RPM}"
# See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector RPM for AlmaLinux 8
path: ${{ steps.rpmrename.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector SRPM for AlmaLinux 8
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
@@ -195,17 +111,14 @@ jobs:
submodules: recursive
fetch-depth: 0
# - name: Setup Golang
# uses: actions/setup-go@v5
# with:
# go-version: 'stable'
- name: Setup Golang
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
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 \
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 \
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 \
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/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
@@ -215,78 +128,15 @@ jobs:
# See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector RPM for UBI 8
path: ${{ steps.rpmbuild.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector SRPM for UBI 8
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: ${{ steps.rpmbuild.outputs.SRPM }}
overwrite: true
#
# Build on Ubuntu 22.04 using official go package
@@ -312,15 +162,17 @@ jobs:
with:
submodules: recursive
fetch-depth: 0
- name: Setup Golang
uses: actions/setup-go@v5
with:
go-version: 'stable'
# Use official golang package
- name: Install Golang
run: |
wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
tar --directory=/usr/local --extract --gzip
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
go version
- name: DEB build MetricCollector
id: dpkg-build
run: |
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make DEB
- name: Rename DEB (add '_ubuntu22.04')
@@ -329,65 +181,13 @@ jobs:
OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu22.04.deb"
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
- name: Save DEB as artifact
uses: actions/upload-artifact@v4
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector DEB for Ubuntu 22.04
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
@@ -395,56 +195,33 @@ jobs:
Release:
runs-on: ubuntu-latest
# 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-focal-build]
steps:
# See: https://github.com/actions/download-artifact
- name: Download AlmaLinux 8 RPM
uses: actions/download-artifact@v4
uses: actions/download-artifact@v2
with:
name: cc-metric-collector RPM for AlmaLinux 8
- name: Download AlmaLinux 8 SRPM
uses: actions/download-artifact@v4
uses: actions/download-artifact@v2
with:
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
uses: actions/download-artifact@v4
uses: actions/download-artifact@v2
with:
name: cc-metric-collector RPM for UBI 8
- name: Download UBI 8 SRPM
uses: actions/download-artifact@v4
uses: actions/download-artifact@v2
with:
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
uses: actions/download-artifact@v4
uses: actions/download-artifact@v2
with:
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,
# so we re-use the job outputs of the parent jobs. The files are all
# downloaded to the current folder.
@@ -454,51 +231,31 @@ jobs:
- name: Set RPM variables
id: files
run: |
ALMA_8_RPM=$(basename "${{ needs.AlmaLinux8-RPM-build.outputs.rpm}}")
ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux8-RPM-build.outputs.srpm}}")
ALMA_9_RPM=$(basename "${{ needs.AlmaLinux9-RPM-build.outputs.rpm}}")
ALMA_9_SRPM=$(basename "${{ needs.AlmaLinux9-RPM-build.outputs.srpm}}")
ALMA_8_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
UBI_9_RPM=$(basename "${{ needs.UBI-9-RPM-build.outputs.rpm}}")
UBI_9_SRPM=$(basename "${{ needs.UBI-9-RPM-build.outputs.srpm}}")
U_2204_DEB=$(basename "${{ needs.Ubuntu-jammy-build.outputs.deb}}")
U_2404_DEB=$(basename "${{ needs.Ubuntu-noblenumbat-build.outputs.deb}}")
U_2004_DEB=$(basename "${{ needs.Ubuntu-focal-build.outputs.deb}}")
echo "ALMA_8_RPM::${ALMA_8_RPM}"
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_SRPM::${UBI_8_SRPM}"
echo "UBI_9_RPM::${UBI_9_RPM}"
echo "UBI_9_SRPM::${UBI_9_SRPM}"
echo "U_2204_DEB::${U_2204_DEB}"
echo "U_2404_DEB::${U_2404_DEB}"
echo "ALMA_8_RPM=${ALMA_8_RPM}" >> $GITHUB_OUTPUT
echo "ALMA_8_SRPM=${ALMA_8_SRPM}" >> $GITHUB_OUTPUT
echo "ALMA_9_RPM=${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}" >> $GITHUB_OUTPUT
echo "U_2004_DEB::${U_2004_DEB}"
echo "::set-output name=ALMA_8_RPM::${ALMA_8_RPM}"
echo "::set-output name=ALMA_8_SRPM::${ALMA_8_SRPM}"
echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
echo "::set-output name=U_2004_DEB::${U_2004_DEB}"
# See: https://github.com/softprops/action-gh-release
- name: Release
uses: softprops/action-gh-release@v2
uses: softprops/action-gh-release@v1
if: startsWith(github.ref, 'refs/tags/')
with:
name: cc-metric-collector-${{github.ref_name}}
files: |
${{ steps.files.outputs.ALMA_8_RPM }}
${{ 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_SRPM }}
${{ steps.files.outputs.UBI_9_RPM }}
${{ steps.files.outputs.UBI_9_SRPM }}
${{ steps.files.outputs.U_2204_DEB }}
${{ steps.files.outputs.U_2404_DEB }}
${{ steps.files.outputs.U_2004_DEB }}

View File

@@ -26,7 +26,7 @@ jobs:
# See: https://github.com/marketplace/actions/setup-go-environment
- name: Setup Golang
uses: actions/setup-go@v5
uses: actions/setup-go@v4
with:
go-version: '1.21'
@@ -52,7 +52,7 @@ jobs:
# See: https://github.com/marketplace/actions/setup-go-environment
- name: Setup Golang
uses: actions/setup-go@v5
uses: actions/setup-go@v4
with:
go-version: '1.22'
@@ -63,35 +63,9 @@ jobs:
run: ./cc-metric-collector --once --config .github/ci-config.json
#
# Job build-1-23
# Build on latest Ubuntu using golang version 1.23
# Build on AlmaLinux 8 using go-toolset
#
build-1-23:
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@v5
with:
go-version: '1.23'
- name: Build MetricCollector
run: make
- name: Run MetricCollector once
run: ./cc-metric-collector --once --config .github/ci-config.json
#
# Build on AlmaLinux 8
#
AlmaLinux8-RPM-build:
AlmaLinux-RPM-build:
runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux
container: almalinux:8
@@ -114,18 +88,14 @@ jobs:
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
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
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 \
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 \
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 \
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
dnf --assumeyes install \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
@@ -133,60 +103,13 @@ jobs:
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
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
#
UBI-8-RPM-build:
runs-on: ubuntu-latest
# 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
steps:
@@ -203,61 +126,14 @@ jobs:
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
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
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 \
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 \
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 \
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
- 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
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
@@ -287,48 +163,15 @@ jobs:
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: Install Golang
run: |
wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
tar --directory=/usr/local --extract --gzip
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
go version
- name: DEB build MetricCollector
id: dpkg-build
run: |
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
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

@@ -17,7 +17,7 @@ import (
mr "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
)
@@ -54,7 +54,7 @@ type RuntimeConfig struct {
ReceiveManager receivers.ReceiveManager
MultiChanTicker mct.MultiChanTicker
Channels []chan lp.CCMessage
Channels []chan lp.CCMetric
Sync sync.WaitGroup
}
@@ -242,7 +242,7 @@ func mainFunc() int {
}
// Connect metric router to sink manager
RouterToSinksChannel := make(chan lp.CCMessage, 200)
RouterToSinksChannel := make(chan lp.CCMetric, 200)
rcfg.SinkManager.AddInput(RouterToSinksChannel)
rcfg.MetricRouter.AddOutput(RouterToSinksChannel)
@@ -254,7 +254,7 @@ func mainFunc() int {
}
// Connect collector manager to metric router
CollectToRouterChannel := make(chan lp.CCMessage, 200)
CollectToRouterChannel := make(chan lp.CCMetric, 200)
rcfg.CollectManager.AddOutput(CollectToRouterChannel)
rcfg.MetricRouter.AddCollectorInput(CollectToRouterChannel)
@@ -267,7 +267,7 @@ func mainFunc() int {
}
// Connect receive manager to metric router
ReceiveToRouterChannel := make(chan lp.CCMessage, 200)
ReceiveToRouterChannel := make(chan lp.CCMetric, 200)
rcfg.ReceiveManager.AddOutput(ReceiveToRouterChannel)
rcfg.MetricRouter.AddReceiverInput(ReceiveToRouterChannel)
use_recv = true

View File

@@ -1,5 +1,5 @@
# LIKWID version
LIKWID_VERSION := 5.4.1
LIKWID_VERSION := 5.2.2
LIKWID_INSTALLED_FOLDER := $(shell dirname $$(which likwid-topology 2>/dev/null) 2>/dev/null)
LIKWID_FOLDER := $(CURDIR)/likwid
@@ -23,7 +23,7 @@ likwid:
mkdir --parents --verbose "$${BUILD_FOLDER}"
wget --output-document=- http://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.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}"
fi

View File

@@ -15,7 +15,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
@@ -110,7 +110,7 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
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 {
return
}
@@ -216,7 +216,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
for key, data := range m.matches {
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 {
output <- y
}

View File

@@ -15,7 +15,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// Struct for the collector-specific JSON config
@@ -103,7 +103,7 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
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 {
return
}
@@ -208,7 +208,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
for key, data := range m.matches {
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 {
output <- y
}

View File

@@ -6,8 +6,8 @@ import (
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
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"
)
@@ -47,7 +47,7 @@ var AvailableCollectors = map[string]MetricCollector{
type collectorManager struct {
collectors []MetricCollector // List of metric collectors to read in parallel
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
ticker mct.MultiChanTicker // periodically ticking once each interval
duration time.Duration // duration (for metrics that measure over a given duration)
@@ -60,7 +60,7 @@ type collectorManager struct {
// Metric collector manager access functions
type CollectorManager interface {
Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error
AddOutput(output chan lp.CCMessage)
AddOutput(output chan lp.CCMetric)
Start()
Close()
}
@@ -187,7 +187,7 @@ func (cm *collectorManager) Start() {
}
// 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
}

View File

@@ -10,8 +10,8 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// CPUFreqCollector
@@ -112,14 +112,14 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
// Check if at least one CPU with frequency information was detected
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
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
if !m.init {
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))
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
}
}

View File

@@ -10,7 +10,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
"golang.org/x/sys/unix"
)
@@ -91,7 +91,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
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
if !m.init {
return
@@ -117,7 +117,7 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage
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
}
}

View File

@@ -9,8 +9,8 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
sysconf "github.com/tklauser/go-sysconf"
)
@@ -34,7 +34,7 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
m.name = "CpustatCollector"
m.setup()
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"}
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
@@ -105,7 +105,7 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
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)
clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK)
for match, index := range m.matches {
@@ -122,23 +122,21 @@ func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]st
sum := float64(0)
for name, value := range values {
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 {
y.AddTag("unit", "Percent")
output <- y
}
}
if v, ok := values["cpu_idle"]; ok {
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 {
y.AddTag("unit", "Percent")
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 {
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.meta,
map[string]interface{}{"value": int(num_cpus)},

View File

@@ -13,15 +13,14 @@ The `cpustat` collector reads data from `/proc/stat` and outputs a handful **nod
Metrics:
* `cpu_user` with `unit=Percent`
* `cpu_nice` with `unit=Percent`
* `cpu_system` with `unit=Percent`
* `cpu_idle` with `unit=Percent`
* `cpu_iowait` with `unit=Percent`
* `cpu_irq` with `unit=Percent`
* `cpu_softirq` with `unit=Percent`
* `cpu_steal` with `unit=Percent`
* `cpu_guest` with `unit=Percent`
* `cpu_guest_nice` with `unit=Percent`
* `cpu_used` = `cpu_* - cpu_idle` with `unit=Percent`
* `num_cpus`
* `cpu_user`
* `cpu_nice`
* `cpu_system`
* `cpu_idle`
* `cpu_iowait`
* `cpu_irq`
* `cpu_softirq`
* `cpu_steal`
* `cpu_guest`
* `cpu_guest_nice`
* `cpu_used` = `cpu_* - cpu_idle`

View File

@@ -9,7 +9,7 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol"
)
@@ -75,7 +75,7 @@ var DefaultTime = func() time.Time {
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 {
return
}

View File

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

View File

@@ -6,13 +6,10 @@
"exclude_metrics": [
"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):
* `disk_total` (unit `GBytes`)

View File

@@ -14,7 +14,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const DEFAULT_GPFS_CMD = "mmpmon"
@@ -94,7 +94,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
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
if !m.init {
return
@@ -218,7 +218,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue
}
if y, err :=
lp.NewMessage(
lp.New(
"gpfs_bytes_read",
m.tags,
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 {
bwRead := float64(bytesRead-lastBytesRead) / timeDiff
if y, err :=
lp.NewMessage(
lp.New(
"gpfs_bw_read",
m.tags,
m.meta,
@@ -258,7 +258,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue
}
if y, err :=
lp.NewMessage(
lp.New(
"gpfs_bytes_written",
m.tags,
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 {
bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
if y, err :=
lp.NewMessage(
lp.New(
"gpfs_bw_write",
m.tags,
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))
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
}
@@ -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))
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
}
@@ -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))
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
}
@@ -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))
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
}
@@ -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))
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
}
@@ -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))
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
}
@@ -372,7 +372,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
if m.config.SendTotalValues {
bytesTotal := bytesRead + bytesWritten
if y, err :=
lp.NewMessage("gpfs_bytes_total",
lp.New("gpfs_bytes_total",
m.tags,
m.meta,
map[string]interface{}{
@@ -385,7 +385,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
}
iops := numReads + numWrites
if y, err :=
lp.NewMessage("gpfs_iops",
lp.New("gpfs_iops",
m.tags,
m.meta,
map[string]interface{}{
@@ -397,7 +397,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
}
metaops := numInodeUpdates + numCloses + numOpens + numReaddirs
if y, err :=
lp.NewMessage("gpfs_metaops",
lp.New("gpfs_metaops",
m.tags,
m.meta,
map[string]interface{}{

View File

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

View File

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

View File

@@ -4,17 +4,12 @@
```json
"iostat": {
"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:
* `io_reads`

View File

@@ -12,9 +12,8 @@ import (
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
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
p, err := exec.LookPath(m.config.IpmitoolPath)
if err == nil {
command := exec.Command(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
}
m.ipmitool = p
}
p, err = exec.LookPath(m.config.IpmisensorsPath)
if err == nil {
command := exec.Command(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
}
m.ipmisensors = p
}
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
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
command := exec.Command(cmd, "sensor")
@@ -121,7 +105,7 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
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 {
y.AddMeta("unit", unit)
output <- y
@@ -135,13 +119,13 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
cclog.ComponentError(
m.name,
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
}
}
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.Wait()
@@ -159,7 +143,7 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
v, err := strconv.ParseFloat(lv[3], 64)
if err == nil {
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 len(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
if !m.init {

View File

@@ -24,9 +24,9 @@ import (
"time"
"unsafe"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
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"
"github.com/NVIDIA/go-nvml/pkg/dl"
"github.com/fsnotify/fsnotify"
@@ -43,7 +43,7 @@ const (
type LikwidCollectorMetricConfig struct {
Name string `json:"name"` // Name of the metric
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"`
SendCoreTotalVal bool `json:"send_core_total_values,omitempty"`
SendSocketTotalVal bool `json:"send_socket_total_values,omitempty"`
@@ -91,8 +91,6 @@ type LikwidCollector struct {
running bool
initialized bool
needs_reinit bool
myuid int
lock_err_once bool
likwidGroups map[C.int]LikwidEventsetConfig
lock sync.Mutex
measureThread thread.Thread
@@ -206,7 +204,6 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
m.initialized = false
m.needs_reinit = true
m.running = false
m.myuid = os.Getuid()
m.config.AccessMode = LIKWID_DEF_ACCESSMODE
m.config.LibraryPath = LIKWID_LIB_NAME
m.config.LockfilePath = LIKWID_DEF_LOCKFILE
@@ -377,41 +374,27 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
}
defer watcher.Close()
if len(m.config.LockfilePath) > 0 {
// Check if the lock file exists
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)
if _, err := os.Stat(m.config.LockfilePath); os.IsNotExist(err) {
file, err := os.Create(m.config.LockfilePath)
if err != nil {
cclog.ComponentError(m.name, "Cannot create lockfile", m.config.LockfilePath, ":", err.Error())
return true, err
}
file.Close()
info, err = os.Stat(m.config.LockfilePath) // Recheck the file after creation
}
info, err := os.Stat(m.config.LockfilePath)
if err != nil {
return true, err
}
// Check file ownership
uid := info.Sys().(*syscall.Stat_t).Uid
if uid != uint32(m.myuid) {
if uid != uint32(os.Getuid()) {
usr, err := user.LookupId(fmt.Sprint(uid))
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 {
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)
if err != nil {
cclog.ComponentError(m.name, err.Error())
@@ -449,7 +432,9 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
gid = C.perfmon_addEventSet(evset.estr)
}
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
@@ -560,12 +545,11 @@ 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
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)
for _, tid := range m.cpu2tid {
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
@@ -594,7 +578,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
if !math.IsNaN(value) && metric.Publish {
fields := map[string]interface{}{"value": value}
y, err :=
lp.NewMessage(
lp.New(
metric.Name,
map[string]string{
"type": metric.Type,
@@ -631,7 +615,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
for coreID, value := range totalCoreValues {
y, err :=
lp.NewMessage(
lp.New(
metric.Name,
map[string]string{
"type": "core",
@@ -668,7 +652,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
for socketID, value := range totalSocketValues {
y, err :=
lp.NewMessage(
lp.New(
metric.Name,
map[string]string{
"type": "socket",
@@ -703,7 +687,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
}
y, err :=
lp.NewMessage(
lp.New(
metric.Name,
map[string]string{
"type": "node",
@@ -728,7 +712,7 @@ 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
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
// This function does only computiation, counter measurement is done before
now := time.Now()
@@ -749,7 +733,6 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
params[mname] = mres
}
}
params["gotime"] = interval.Seconds()
// Evaluate the metric
value, err := agg.EvalFloat64Condition(metric.Calc, params)
if err != nil {
@@ -763,7 +746,7 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
if !math.IsNaN(value) {
if metric.Publish {
y, err :=
lp.NewMessage(
lp.New(
metric.Name,
map[string]string{
"type": metric.Type,
@@ -791,7 +774,7 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
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
groups := make([]LikwidEventsetConfig, 0)
@@ -811,17 +794,15 @@ func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMe
if !skip {
// read measurements and derive event set metrics
m.calcEventsetMetrics(e, interval, output)
groups = append(groups, e)
}
groups = append(groups, e)
}
if len(groups) > 0 {
// calculate global metrics
m.calcGlobalMetrics(groups, interval, output)
}
// calculate global metrics
m.calcGlobalMetrics(groups, interval, output)
}
// 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 {
return
}

View File

@@ -15,7 +15,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
{
"events" : {
"COUNTER0": "EVENT0",
"COUNTER1": "EVENT1"
"COUNTER1": "EVENT1",
},
"metrics" : [
{
@@ -27,7 +27,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
}
]
}
],
]
"globalmetrics" : [
{
"name": "global_sum",
@@ -132,9 +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).
### `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_core_total_values`: Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU core.
@@ -270,3 +267,45 @@ IPC PMC0/PMC1 -> {
```
The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.
### Internal structure
This section describes the internal structure of the `likwid` collector.
#### At initialization
After setting the defaults, the configuration is read.
Based on the configuration, the library is searched using `dlopen` to see whether it makes sense to proceed.
Next, the user-given metrics are tested to ensure they can be evaluated. For this, it creates a list of all user-given events/counters with the value `1.0` which is provided to the metric evaluator. The same is done for the global metrics by using the metric names with value `1.0`. If the evaluator does not fail, the metric can be evaluated and the collector initialization can proceed.
A separate thread is started to do the measurement. This is not done using a common goroutine but a real application thread with full control. This is required because LIKWID's access system tracks the processes of the using application and the PID should not change between measurements because that would require teardown and reopening of the access system.
With the separate thread, the access system is initialized by setting the user-given access mode and adding all hardware threads.
LIKWID measures per hardware thread in general but only some HW threads read the counters available only e.g. per CPU socket (often memory traffic). For this, the collector gets the system topology through LIKWID and creates different mappings like 'hwthread to list offset' and others. With this, the hardware threads responsible for a topological entity can be determined because those read the counters of the per CPU socket units. These mappings are later used in the measurement phase.
In the end, we read the base CPU frequency of the system. It may be used in the metric evaluation.
#### Measurements
The reading of events is done by the separate application thread.
It traverses over all configured event sets, creates valid LIKWID eventstrings out of them and pass them to take a measurement. This could be done only once but when the LIKWID lock changes, LIKWID has to be completely reopened to provide access again. With this reopening, the already added event sets are gone.
LIKWID has it's own locking mechanism using a lock file. But not the content of the file is of interest but the owner. In order to track changes of the file, a `fsnotify` watcher is installed on the file. If the file does not exist, it is created and consequently is owned by the same user as `cc-metric-collector`. The LikwidCollector has to watch the file on it's own because LIKWID does not provide proper error handling for this.
Each call to the LIKWID library for loading the event set, setting up the counting facilities as well as starting and stopping of the counters is wrapped into lockfile checks to ensure no state change happens. If the file owner changed, the LikwidCollector cannot access the counters anymore, so no further operation can be done and measurment stops.
Although start/stop would be sufficient, the LikwidCollector performs start, read, wait, read, `getLastResult`, stop. Reason might be "historic" but is not 100% clear anymore. The author failed to document ;)
#### Metric evaluation
After each meaurement, the metrics of the event set are directly evaluated. It updates the counter->result mapping with the new measurements, calls the evaluator and generates the `CCMetric` with the user-given settings if it should be published. Each metric name to result calculation is stored for the global metric evaluation, which is done as a final step.
#### Shutdown
Since each measurment involves a complete initialize to finalize cycle of the LIKWID library, only the topology module needs to be closed.
Moreover, the separate application thread is stopped.

View File

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

View File

@@ -11,7 +11,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const LUSTRE_SYSFS = `/sys/fs/lustre`
@@ -377,7 +377,7 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
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 {
return
}
@@ -388,7 +388,7 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage)
for _, def := range m.definitions {
var use_x int64
var err error
var y lp.CCMessage
var y lp.CCMetric
x, err := getMetricData(data, def.lineprefix, def.lineoffset)
if err == nil {
use_x = x
@@ -399,19 +399,19 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage)
switch def.calc {
case "none":
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":
value = use_x - devData[def.name]
if value.(int64) < 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":
value = float64(use_x-devData[def.name]) / tdiff.Seconds()
if value.(float64) < 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 {
y.AddTag("device", device)

View File

@@ -12,8 +12,8 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const MEMSTATFILE = "/proc/meminfo"
@@ -159,7 +159,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
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 {
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 len(unit) > 0 {
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 len(unit) > 0 {
y.AddMeta("unit", unit)

View File

@@ -5,7 +5,7 @@ import (
"fmt"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type MetricCollector interface {
@@ -13,7 +13,7 @@ type MetricCollector interface {
Init(config json.RawMessage) error // Initialize metric collector
Initialized() bool // Is metric collector initialized?
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
}

View File

@@ -9,17 +9,16 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const NETSTATFILE = "/proc/net/dev"
type NetstatCollectorConfig struct {
IncludeDevices []string `json:"include_devices"`
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
InterfaceAliases map[string][]string `json:"interface_aliases,omitempty"`
IncludeDevices []string `json:"include_devices"`
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
}
type NetstatCollectorMetric struct {
@@ -33,26 +32,9 @@ type NetstatCollectorMetric struct {
type NetstatCollector struct {
metricCollector
config NetstatCollectorConfig
aliasToCanonical map[string]string
matches map[string][]NetstatCollectorMetric
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
config NetstatCollectorConfig
matches map[string][]NetstatCollectorMetric
lastTimestamp time.Time
}
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
file, err := os.Open(NETSTATFILE)
if err != nil {
@@ -117,20 +97,18 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
// Split line into fields
f := strings.Fields(l)
// Get raw and canonical names
raw := strings.Trim(f[0], ": ")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Get net device entry
dev := strings.Trim(f[0], ": ")
// Check if device is a included device
if _, ok := stringArrayContains(m.config.IncludeDevices, canonical); ok {
// Tag will contain original device name (raw).
tags := map[string]string{"stype": "network", "stype-id": raw, "type": "node"}
if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
tags := map[string]string{"stype": "network", "stype-id": dev, "type": "node"}
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_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"}
m.matches[canonical] = []NetstatCollectorMetric{
m.matches[dev] = []NetstatCollectorMetric{
{
name: "net_bytes_in",
index: fieldReceiveBytes,
@@ -165,6 +143,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
},
}
}
}
if len(m.matches) == 0 {
@@ -174,7 +153,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
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 {
return
}
@@ -185,7 +164,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
// Save current timestamp
m.lastTimestamp = now
file, err := os.Open(NETSTATFILE)
file, err := os.Open(string(NETSTATFILE))
if err != nil {
cclog.ComponentError(m.name, err.Error())
return
@@ -204,12 +183,11 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
// Split line into fields
f := strings.Fields(l)
// Get raw and canonical names
raw := strings.Trim(f[0], ":")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Get net device entry
dev := strings.Trim(f[0], ":")
// 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 {
metric := &devmetrics[i]
@@ -219,14 +197,14 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
continue
}
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
}
}
if m.config.SendDerivedValues {
if metric.lastValue >= 0 {
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
}
}

View File

@@ -4,19 +4,14 @@
```json
"netstat": {
"include_devices": [
"eth0",
"eno1"
"eth0"
],
"send_abs_values": true,
"send_derived_values": true,
"interface_aliases": {
"eno1": ["eno1np0", "eno1_alt"],
"eth0": ["eth0_alias"]
}
"send_abs_values" : true,
"send_derived_values" : true
}
```
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:
* `net_bytes_in` (`unit=bytes`)
@@ -28,4 +23,5 @@ Metrics:
* `net_pkts_in_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

@@ -11,7 +11,7 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// First part contains the code for the general NfsCollector.
@@ -118,7 +118,7 @@ func (m *nfsCollector) MainInit(config json.RawMessage) error {
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 {
return
}
@@ -140,7 +140,7 @@ func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue
}
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 {
y.AddMeta("version", m.version)
output <- y

View File

@@ -9,8 +9,8 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// These are the fields we read from the JSON configuration
@@ -18,20 +18,17 @@ type NfsIOStatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ExcludeFilesystem []string `json:"exclude_filesystem,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
// defined by metricCollector (name, init, ...)
type NfsIOStatCollector struct {
metricCollector
config NfsIOStatCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
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'
lastTimestamp time.Time
config NfsIOStatCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
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', see NfsIOStatCollectorConfig.UseServerAddressAsSType
}
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
}
}
}
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.tags = map[string]string{"type": "node"}
m.config.UseServerAddressAsSType = false
// Set default configuration
m.config.SendAbsoluteValues = true
m.config.SendDerivedValues = false
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
@@ -115,15 +110,12 @@ func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
m.key = "server"
}
m.data = m.readNfsiostats()
m.lastTimestamp = time.Now()
m.init = true
return err
}
func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
now := time.Now()
timeDiff := now.Sub(m.lastTimestamp).Seconds()
m.lastTimestamp = now
func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
timestamp := time.Now()
// Get the current values for all mountpoints
newdata := m.readNfsiostats()
@@ -131,30 +123,21 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
for mntpoint, values := range newdata {
// Was the mount point already present in the last iteration
if old, ok := m.data[mntpoint]; ok {
for name, newVal := range values {
if m.config.SendAbsoluteValues {
msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s", name), m.tags, m.meta, map[string]interface{}{"value": newVal}, now)
if err == nil {
msg.AddTag("stype", "filesystem")
msg.AddTag("stype-id", mntpoint)
output <- msg
// Calculate the difference of old and new values
for i := range values {
x := values[i] - old[i]
y, err := lp.New(fmt.Sprintf("nfsio_%s", i), m.tags, m.meta, map[string]interface{}{"value": x}, timestamp)
if err == nil {
if strings.HasPrefix(i, "page") {
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 {
rate := float64(newVal-old[name]) / timeDiff
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
// Update old to the new value for the next iteration
old[i] = values[i]
}
} else {
// First time we see this mount point, store all values
@@ -174,6 +157,7 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
m.data[mntpoint] = nil
}
}
}
func (m *NfsIOStatCollector) Close() {

View File

@@ -3,18 +3,16 @@
```json
"nfsiostat": {
"exclude_metrics": [
"oread", "pageread"
"nfsio_oread"
],
"exclude_filesystems": [
"/mnt"
"exclude_filesystems" : [
"/mnt",
],
"use_server_as_stype": false,
"send_abs_values": false,
"send_derived_values": true
"use_server_as_stype": false
}
```
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:
* `nfsio_nread`: Bytes transferred by normal `read()` calls
@@ -26,9 +24,4 @@ Metrics:
* `nfsio_nfsread`: Bytes transferred for reading from 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:
* 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.
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"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
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
//
// numa_hit:
@@ -52,16 +47,13 @@ type NUMAStatsCollectorConfig struct {
//
// See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
type NUMAStatsCollectorTopolgy struct {
file string
tagSet map[string]string
previousValues map[string]int64
file string
tagSet map[string]string
}
type NUMAStatsCollector struct {
metricCollector
topology []NUMAStatsCollectorTopolgy
config NUMAStatsCollectorConfig
lastTimestamp time.Time
topology []NUMAStatsCollectorTopolgy
}
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")
m.topology = append(m.topology,
NUMAStatsCollectorTopolgy{
file: file,
tagSet: map[string]string{"memoryDomain": node},
previousValues: make(map[string]int64),
file: file,
tagSet: map[string]string{"memoryDomain": node},
})
}
@@ -106,32 +97,28 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
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 {
return
}
now := time.Now()
timeDiff := now.Sub(m.lastTimestamp).Seconds()
m.lastTimestamp = now
for i := range m.topology {
// Loop for all NUMA domains
t := &m.topology[i]
now := time.Now()
file, err := os.Open(t.file)
if err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", t.file, err))
continue
return
}
scanner := bufio.NewScanner(file)
// Read line by line
for scanner.Scan() {
line := scanner.Text()
split := strings.Fields(line)
split := strings.Fields(scanner.Text())
if len(split) != 2 {
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))
continue
}
if m.config.SendAbsoluteValues {
msg, err := lp.NewMessage(
"numastats_"+key,
t.tagSet,
m.meta,
map[string]interface{}{"value": value},
now,
)
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
y, err := lp.New(
"numastats_"+key,
t.tagSet,
m.meta,
map[string]interface{}{"value": value},
now,
)
if err == nil {
output <- y
}
}
file.Close()
}
}

View File

@@ -2,10 +2,7 @@
## `numastat` collector
```json
"numastats": {
"send_abs_values" : true,
"send_derived_values" : true
}
"numastats": {}
```
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>
@@ -18,9 +15,3 @@ Metrics:
* `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_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"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/NVIDIA/go-nvml/pkg/nvml"
)
@@ -206,7 +206,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
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"] {
var total uint64
var used uint64
@@ -222,7 +222,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
if !device.excludeMetrics["nv_fb_mem_total"] {
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 {
y.AddMeta("unit", "MByte")
output <- y
@@ -231,7 +231,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
if !device.excludeMetrics["nv_fb_mem_used"] {
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 {
y.AddMeta("unit", "MByte")
output <- y
@@ -240,7 +240,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
if v2 && !device.excludeMetrics["nv_fb_mem_reserved"] {
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 {
y.AddMeta("unit", "MByte")
output <- y
@@ -250,7 +250,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
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"] {
meminfo, ret := nvml.DeviceGetBAR1MemoryInfo(device.device)
if ret != nvml.SUCCESS {
@@ -259,7 +259,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
}
if !device.excludeMetrics["nv_bar1_mem_total"] {
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 {
y.AddMeta("unit", "MByte")
output <- y
@@ -267,7 +267,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
}
if !device.excludeMetrics["nv_bar1_mem_used"] {
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 {
y.AddMeta("unit", "MByte")
output <- y
@@ -277,7 +277,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
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)
if ret != nvml.SUCCESS {
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)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "%")
output <- y
}
}
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 {
y.AddMeta("unit", "%")
output <- y
@@ -319,7 +319,7 @@ func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) err
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"] {
// 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
temp, ret := nvml.DeviceGetTemperature(device.device, nvml.TEMPERATURE_GPU)
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 {
y.AddMeta("unit", "degC")
output <- y
@@ -338,7 +338,7 @@ func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
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"] {
// 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.
fan, ret := nvml.DeviceGetFanSpeed(device.device)
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 {
y.AddMeta("unit", "%")
output <- y
@@ -361,14 +361,14 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
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"] {
// numFans, ret := nvml.DeviceGetNumFans(device.device)
// if ret == nvml.SUCCESS {
// for i := 0; i < numFans; i++ {
// fan, ret := nvml.DeviceGetFanSpeed_v2(device.device, i)
// 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 {
// y.AddMeta("unit", "%")
// y.AddTag("stype", "fan")
@@ -382,7 +382,7 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
// 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"] {
// 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.
_, ecc_pend, ret := nvml.DeviceGetEccMode(device.device)
if ret == nvml.SUCCESS {
var y lp.CCMessage
var y lp.CCMetric
var err error
switch ecc_pend {
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:
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:
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 {
output <- y
}
} 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 {
output <- y
}
@@ -416,7 +416,7 @@ func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
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"] {
// 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.
pState, ret := nvml.DeviceGetPerformanceState(device.device)
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 {
output <- y
}
@@ -436,7 +436,7 @@ func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error
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"] {
// 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 {
power, ret := nvml.DeviceGetPowerUsage(device.device)
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 {
y.AddMeta("unit", "watts")
output <- y
@@ -461,7 +461,7 @@ func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
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.
//
// Available clock information:
@@ -471,7 +471,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_graphics_clock"] {
graphicsClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_GRAPHICS)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -482,7 +482,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_sm_clock"] {
smCock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -493,7 +493,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_mem_clock"] {
memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -503,7 +503,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
if !device.excludeMetrics["nv_video_clock"] {
memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -513,7 +513,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
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.
//
// Available clock information:
@@ -528,7 +528,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_graphics_clock"] {
max_gclk, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_GRAPHICS)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -539,7 +539,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_sm_clock"] {
maxSmClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -550,7 +550,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_mem_clock"] {
maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -561,7 +561,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_max_video_clock"] {
maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
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 {
y.AddMeta("unit", "MHz")
output <- y
@@ -571,7 +571,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
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"] {
// 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.
ecc_db, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_UNCORRECTED, nvml.AGGREGATE_ECC)
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 {
output <- y
}
@@ -593,7 +593,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error
if !device.excludeMetrics["nv_ecc_corrected_error"] {
ecc_sb, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_CORRECTED, nvml.AGGREGATE_ECC)
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 {
output <- y
}
@@ -602,7 +602,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error
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"] {
// 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.
pwr_limit, ret := nvml.DeviceGetPowerManagementLimit(device.device)
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 {
y.AddMeta("unit", "watts")
output <- y
@@ -622,7 +622,7 @@ func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
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)
if ret != nvml.SUCCESS {
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.
enc_util, _, ret := nvml.DeviceGetEncoderUtilization(device.device)
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 {
y.AddMeta("unit", "%")
output <- y
@@ -649,7 +649,7 @@ func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
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)
if ret != nvml.SUCCESS {
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.
dec_util, _, ret := nvml.DeviceGetDecoderUtilization(device.device)
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 {
y.AddMeta("unit", "%")
output <- y
@@ -676,7 +676,7 @@ func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
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"] ||
!device.excludeMetrics["nv_remapped_rows_uncorrected"] ||
!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)
if ret == nvml.SUCCESS {
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 {
output <- y
}
}
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 {
output <- y
}
@@ -709,7 +709,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
if pending {
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 {
output <- y
}
@@ -719,7 +719,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
if failure {
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 {
output <- y
}
@@ -729,7 +729,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
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"] {
// 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.
procList, ret := nvml.DeviceGetComputeRunningProcesses(device.device)
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 {
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.
procList, ret := nvml.DeviceGetGraphicsRunningProcesses(device.device)
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 {
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.
// procList, ret := nvml.DeviceGetMPSComputeRunningProcesses(device.device)
// 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 {
// output <- y
// }
@@ -821,7 +821,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
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 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)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
output <- y
@@ -852,7 +852,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_THERMAL)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
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)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
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)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
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)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
output <- y
@@ -900,7 +900,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_RELIABILITY)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
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)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
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)
if ret == nvml.SUCCESS {
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 {
y.AddMeta("unit", "sec")
output <- y
@@ -935,18 +935,12 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
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
// Please refer to \a nvmlNvLinkErrorCounter_t for error counters that are available
//
// 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++ {
state, ret := nvml.DeviceGetNvLinkState(device.device, i)
if ret == nvml.SUCCESS {
@@ -954,9 +948,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
if !device.excludeMetrics["nv_nvlink_crc_errors"] {
// Data link receive data CRC error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_CRC_DATA)
aggregate_crc_errors = aggregate_crc_errors + count
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 {
y.AddTag("stype", "nvlink")
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"] {
// Data link receive data ECC error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_ECC_DATA)
aggregate_ecc_errors = aggregate_ecc_errors + count
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 {
y.AddTag("stype", "nvlink")
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"] {
// Data link transmit replay error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_REPLAY)
aggregate_replay_errors = aggregate_replay_errors + count
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 {
y.AddTag("stype", "nvlink")
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"] {
// Data link transmit recovery error counter
count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_RECOVERY)
aggregate_recovery_errors = aggregate_recovery_errors + count
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 {
y.AddTag("stype", "nvlink")
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"] {
// Data link receive flow control digit CRC error counter
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 {
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 {
y.AddTag("stype", "nvlink")
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
}
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
if !m.init {
return
}
readAll := func(device NvidiaCollectorDevice, output chan lp.CCMessage) {
readAll := func(device NvidiaCollectorDevice, output chan lp.CCMetric) {
name, ret := nvml.DeviceGetName(device.device)
if ret != nvml.SUCCESS {
name = "NoName"

View File

@@ -9,29 +9,20 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// running average power limit (RAPL) monitoring attributes for a zone
// Only for Intel systems
type RAPLZoneInfo struct {
energy int64 // current reading of the energy counter in micro joules
maxEnergyRange int64 // Range of the above energy counter in micro-joules
energyTimestamp time.Time // timestamp when energy counter was read
energyFilepath string // path to a file containing the zones current energy counter in micro joules
shortTermFilepath string // path to short term power limit
longTermFilepath string // path to long term power limit
enabledFilepath string // path to check whether limits are enabled
name string
// tags describing the RAPL zone:
// * zone_name, subzone_name: e.g. psys, dram, core, uncore, package-0
// * zone_id: e.g. 0:1 (zone 0 sub zone 1)
// type=socket for dram, core, uncore, package-* and type=node for psys
// type-id=socket id
tags map[string]string
tags map[string]string
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
}
type RAPLCollector struct {
@@ -42,40 +33,12 @@ type RAPLCollector struct {
// * 0:1 for zone 0 subzone 1
ExcludeByID []string `json:"exclude_device_by_id,omitempty"`
// Exclude names for RAPL zones, e.g. psys, dram, core, uncore, package-0
ExcludeByName []string `json:"exclude_device_by_name,omitempty"`
SkipEnergyReading bool `json:"skip_energy_reading,omitempty"`
SkipLimitsReading bool `json:"skip_limits_reading,omitempty"`
OnlyEnabledLimits bool `json:"only_enabled_limits,omitempty"`
ExcludeByName []string `json:"exclude_device_by_name,omitempty"`
}
raplZoneInfo []RAPLZoneInfo
RAPLZoneInfo []RAPLZoneInfo
meta map[string]string // default meta information
}
// Get the path to the power limit file for zone selectable by limit name
// Common limit names for Intel systems are
// - long_term
// - short_term
// Does not support AMD as AMD systems do not provide the power limits
// through sysfs
func ZoneLimitFile(folder string, limit_name string) string {
nameGlob := filepath.Join(folder, "constraint_*_name")
candidates, err := filepath.Glob(nameGlob)
if err == nil {
for _, c := range candidates {
if v, err := os.ReadFile(c); err == nil {
if strings.TrimSpace(string(v)) == limit_name {
var i int
n, err := fmt.Sscanf(filepath.Base(c), "constraint_%d_name", &i)
if err == nil && n == 1 {
return filepath.Join(folder, fmt.Sprintf("constraint_%d_power_limit_uw", i))
}
}
}
}
}
return ""
}
// Init initializes the running average power limit (RAPL) collector
func (m *RAPLCollector) Init(config json.RawMessage) error {
@@ -95,9 +58,6 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
}
// Read in the JSON configuration
m.config.SkipEnergyReading = false
m.config.SkipLimitsReading = false
m.config.OnlyEnabledLimits = true
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
@@ -123,62 +83,50 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// readZoneInfo reads RAPL monitoring attributes for a zone given by zonePath
// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
readZoneInfo := func(zonePath string) (z struct {
name string // zones name e.g. psys, dram, core, uncore, package-0
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
shortTermFilepath string
longTermFilepath string
enabledFilepath string
name string // zones name e.g. psys, dram, core, uncore, package-0
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
ok bool // Are all information available?
}) {
// zones name e.g. psys, dram, core, uncore, package-0
foundName := false
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "name")); err == nil {
foundName = true
z.name = strings.TrimSpace(string(v))
}
if os.Geteuid() == 0 && (!m.config.SkipEnergyReading) {
// path to a file containing the zones current energy counter in micro joules
z.energyFilepath = filepath.Join(zonePath, "energy_uj")
// current reading of the energy counter in micro joules
if v, err := os.ReadFile(z.energyFilepath); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
z.energy = i
// timestamp when energy counter was read
z.energyTimestamp = time.Now()
}
} else {
cclog.ComponentError(m.name, "Cannot read energy file for ", z.name, ":", err.Error())
// path to a file containing the zones current energy counter in micro joules
z.energyFilepath = filepath.Join(zonePath, "energy_uj")
// current reading of the energy counter in micro joules
foundEnergy := false
if v, err := os.ReadFile(z.energyFilepath); err == nil {
// timestamp when energy counter was read
z.energyTimestamp = time.Now()
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
foundEnergy = true
z.energy = i
}
// Range of the above energy counter in micro-joules
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
z.maxEnergyRange = i
}
}
} else {
cclog.ComponentInfo(m.name, "Energy readings for", zonePath, "disabled")
}
if !m.config.SkipLimitsReading {
z.shortTermFilepath = ZoneLimitFile(zonePath, "short_term")
if _, err := os.Stat(z.shortTermFilepath); err != nil {
z.shortTermFilepath = ""
// Range of the above energy counter in micro-joules
foundMaxEnergyRange := false
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
foundMaxEnergyRange = true
z.maxEnergyRange = i
}
z.longTermFilepath = ZoneLimitFile(zonePath, "long_term")
if _, err := os.Stat(z.longTermFilepath); err != nil {
z.longTermFilepath = ""
}
z.enabledFilepath = filepath.Join(zonePath, "enabled")
} else {
cclog.ComponentInfo(m.name, "Power limit readings for", zonePath, "disabled")
}
// Are all information available?
z.ok = foundName && foundEnergy && foundMaxEnergyRange
return
}
@@ -195,42 +143,25 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
for _, zonePath := range zonesPath {
zoneID := strings.TrimPrefix(zonePath, zonePrefix)
zonetags := make(map[string]string)
z := readZoneInfo(zonePath)
if !isIDExcluded[zoneID] &&
if z.ok &&
!isIDExcluded[zoneID] &&
!isNameExcluded[z.name] {
si := RAPLZoneInfo{
tags: make(map[string]string),
energyFilepath: z.energyFilepath,
energy: z.energy,
energyTimestamp: z.energyTimestamp,
maxEnergyRange: z.maxEnergyRange,
shortTermFilepath: z.shortTermFilepath,
longTermFilepath: z.longTermFilepath,
enabledFilepath: z.enabledFilepath,
name: z.name,
}
si.tags["type"] = "node"
si.tags["type-id"] = "0"
var pid int = 0
if strings.HasPrefix(z.name, "package-") {
n, err := fmt.Sscanf(z.name, "package-%d", &pid)
if err == nil && n == 1 {
si.tags["type-id"] = fmt.Sprintf("%d", pid)
si.tags["type"] = "socket"
}
si.name = "pkg"
}
// Add RAPL monitoring attributes for a zone
if _, ok1 := si.tags["type"]; ok1 {
if _, ok2 := si.tags["type-id"]; ok2 {
m.raplZoneInfo = append(m.raplZoneInfo, si)
zonetags["type"] = si.tags["type"]
zonetags["type-id"] = si.tags["type-id"]
}
}
m.RAPLZoneInfo =
append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID,
"zone_name": z.name,
},
energyFilepath: z.energyFilepath,
energy: z.energy,
energyTimestamp: z.energyTimestamp,
maxEnergyRange: z.maxEnergyRange,
})
}
// find all sub zones for the given zone
@@ -243,32 +174,29 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
for _, subZonePath := range subZonesPath {
subZoneID := strings.TrimPrefix(subZonePath, subZonePrefix)
sz := readZoneInfo(subZonePath)
if len(zoneID) > 0 && len(z.name) > 0 &&
sz.ok &&
!isIDExcluded[zoneID+":"+subZoneID] &&
!isNameExcluded[sz.name] {
si := RAPLZoneInfo{
tags: zonetags,
energyFilepath: sz.energyFilepath,
energy: sz.energy,
energyTimestamp: sz.energyTimestamp,
maxEnergyRange: sz.maxEnergyRange,
shortTermFilepath: sz.shortTermFilepath,
longTermFilepath: sz.longTermFilepath,
enabledFilepath: sz.enabledFilepath,
name: sz.name,
}
if _, ok1 := si.tags["type"]; ok1 {
if _, ok2 := si.tags["type-id"]; ok2 {
m.raplZoneInfo = append(m.raplZoneInfo, si)
}
}
m.RAPLZoneInfo =
append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID + ":" + subZoneID,
"zone_name": z.name,
"sub_zone_name": sz.name,
},
energyFilepath: sz.energyFilepath,
energy: sz.energy,
energyTimestamp: sz.energyTimestamp,
maxEnergyRange: sz.maxEnergyRange,
})
}
}
}
if m.raplZoneInfo == nil {
if m.RAPLZoneInfo == nil {
return fmt.Errorf("no running average power limit (RAPL) device found in %s", controlTypePath)
}
@@ -277,7 +205,7 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
cclog.ComponentDebug(
m.name,
"initialized",
len(m.raplZoneInfo),
len(m.RAPLZoneInfo),
"zones with running average power limit (RAPL) monitoring attributes")
m.init = true
@@ -286,91 +214,42 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// 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
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 {
p := &m.raplZoneInfo[i]
for i := range m.RAPLZoneInfo {
p := &m.RAPLZoneInfo[i]
if os.Geteuid() == 0 && (!m.config.SkipEnergyReading) {
// Read current value of the energy counter in micro joules
if v, err := os.ReadFile(p.energyFilepath); err == nil {
energyTimestamp := time.Now()
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
energy := i
// Read current value of the energy counter in micro joules
if v, err := os.ReadFile(p.energyFilepath); err == nil {
energyTimestamp := time.Now()
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
energy := i
// Compute average power (Δ energy / Δ time)
energyDiff := energy - p.energy
if energyDiff < 0 {
// Handle overflow:
// ( p.maxEnergyRange - p.energy ) + energy
// = p.maxEnergyRange + ( energy - p.energy )
// = p.maxEnergyRange + diffEnergy
energyDiff += p.maxEnergyRange
}
timeDiff := energyTimestamp.Sub(p.energyTimestamp)
averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
y, err := lp.NewMetric(
fmt.Sprintf("rapl_%s_average_power", p.name),
p.tags,
m.meta,
averagePower,
energyTimestamp)
if err == nil {
output <- y
}
e, err := lp.NewMetric(
fmt.Sprintf("rapl_%s_energy", p.name),
p.tags,
m.meta,
float64(energyDiff)*1e-3,
energyTimestamp)
if err == nil {
e.AddMeta("unit", "Joules")
output <- e
}
// Save current energy counter state
p.energy = energy
p.energyTimestamp = energyTimestamp
// Compute average power (Δ energy / Δ time)
energyDiff := energy - p.energy
if energyDiff < 0 {
// Handle overflow:
// ( p.maxEnergyRange - p.energy ) + energy
// = p.maxEnergyRange + ( energy - p.energy )
// = p.maxEnergyRange + diffEnergy
energyDiff += p.maxEnergyRange
}
}
}
// https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#constraints
if !m.config.SkipLimitsReading {
skip := false
if m.config.OnlyEnabledLimits {
if v, err := os.ReadFile(p.enabledFilepath); err == nil {
if strings.TrimSpace(string(v)) == "0" {
skip = true
}
}
}
if !skip {
if len(p.shortTermFilepath) > 0 {
if v, err := os.ReadFile(p.shortTermFilepath); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
name := fmt.Sprintf("rapl_%s_limit_short_term", p.name)
y, err := lp.NewMetric(name, p.tags, m.meta, i/1e6, time.Now())
if err == nil {
output <- y
}
}
}
timeDiff := energyTimestamp.Sub(p.energyTimestamp)
averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
y, err := lp.New(
"rapl_average_power",
p.tags,
m.meta,
map[string]interface{}{"value": averagePower},
energyTimestamp)
if err == nil {
output <- y
}
if len(p.longTermFilepath) > 0 {
if v, err := os.ReadFile(p.longTermFilepath); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
name := fmt.Sprintf("rapl_%s_limit_long_term", p.name)
y, err := lp.NewMetric(name, p.tags, m.meta, i/1e6, time.Now())
if err == nil {
output <- y
}
}
}
}
// Save current energy counter state
p.energy = energy
p.energyTimestamp = energyTimestamp
}
}
}

View File

@@ -1,23 +1,18 @@
## `rapl` collector
# Running average power limit (RAPL) metric 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>.
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.
## Configuration
```json
"rapl": {
"exclude_device_by_id": ["0:1", "0:2"],
"exclude_device_by_name": ["psys"],
"skip_energy_reading": false,
"skip_limits_reading": false,
"only_enabled_limits": true
"exclude_device_by_name": ["psys"]
}
```
Metrics:
* `rapl_<domain>_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement
* `rapl_<domain>_energy`: Difference from the last measurement
* `rapl_<domain>_limit_short_term`: Short term powercap setting for the domain
* `rapl_<domain>_limit_long_term`: Long term powercap setting for the domain
## Metrics
Only the `rapl_<domain>_average_power` and `rapl_<domain>_energy` metrics require root-permissions. The limits can be read as user. Some domains have limits available but they are not enabled. By default, only enabled domain limits are collected.
Energy and power measurments can also be done with the Likwid metric collector.
* `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

@@ -7,7 +7,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"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
// 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
timestamp := time.Now()
@@ -175,119 +175,119 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
if !dev.excludeMetrics["rocm_gfx_util"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_umc_util"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_mm_util"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_avg_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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_temp_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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_temp_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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_temp_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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_temp_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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_temp_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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_temp_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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_gfx_clock"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_soc_clock"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_u_clock"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_v0_clock"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_v1_clock"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_d0_clock"] {
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 {
output <- y
}
}
if !dev.excludeMetrics["rocm_d1_clock"] {
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 {
output <- y
}
@@ -295,7 +295,7 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
if !dev.excludeMetrics["rocm_temp_hbm"] {
for i := 0; i < rocm_smi.NUM_HBM_INSTANCES; 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 {
y.AddTag("stype", "device")
y.AddTag("stype-id", fmt.Sprintf("%d", i))

View File

@@ -4,8 +4,8 @@ import (
"encoding/json"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// 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 {
var err error = nil
// 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
m.setup()
// 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
// 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
timestamp := time.Now()
@@ -85,7 +85,7 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMessage)
// stop := readState()
// 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 {
// Send it to output channel
output <- y

View File

@@ -5,8 +5,8 @@ import (
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// These are the fields we read from the JSON configuration
@@ -25,7 +25,7 @@ type SampleTimerCollector struct {
config SampleTimerCollectorConfig // the configuration structure
interval time.Duration // the interval parsed from configuration
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 {
@@ -100,14 +100,14 @@ func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
// stop := readState()
// 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 {
// Send it to output channel if we have a valid channel
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
m.output = output
}

View File

@@ -11,7 +11,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const SCHEDSTATFILE = `/proc/schedstat`
@@ -96,7 +96,7 @@ func (m *SchedstatCollector) Init(config json.RawMessage) error {
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)
waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
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
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 {
// Send it to output channel
output <- y
@@ -118,7 +118,7 @@ func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]
// Read collects all metrics belonging to the sample collector
// 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 {
return
}

View File

@@ -7,7 +7,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type SelfCollectorConfig struct {
@@ -42,56 +42,56 @@ func (m *SelfCollector) Init(config json.RawMessage) error {
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()
if m.config.MemStats {
var memstats runtime.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 {
y.AddMeta("unit", "Bytes")
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 {
y.AddMeta("unit", "Bytes")
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 {
y.AddMeta("unit", "Bytes")
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 {
y.AddMeta("unit", "Bytes")
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 {
y.AddMeta("unit", "Bytes")
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 {
y.AddMeta("unit", "Bytes")
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 {
output <- y
}
}
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 {
output <- y
}
}
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 {
output <- y
}
@@ -102,35 +102,35 @@ func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMessage) {
if err == nil {
sec, nsec := rusage.Utime.Unix()
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 {
y.AddMeta("unit", "seconds")
output <- y
}
sec, nsec = rusage.Stime.Unix()
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 {
y.AddMeta("unit", "seconds")
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 {
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 {
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 {
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 {
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 {
output <- y
}

View File

@@ -10,7 +10,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// 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
}
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 {
// Read sensor file
@@ -190,7 +190,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
continue
}
x /= 1000
y, err := lp.NewMessage(
y, err := lp.New(
sensor.metricName,
sensor.tags,
m.meta,
@@ -203,7 +203,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// max temperature
if m.config.ReportMaxTemp && sensor.maxTemp != 0 {
y, err := lp.NewMessage(
y, err := lp.New(
sensor.maxTempName,
sensor.tags,
m.meta,
@@ -217,7 +217,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// critical temperature
if m.config.ReportCriticalTemp && sensor.critTemp != 0 {
y, err := lp.NewMessage(
y, err := lp.New(
sensor.critTempName,
sensor.tags,
m.meta,

View File

@@ -9,7 +9,7 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const MAX_NUM_PROCS = 10
@@ -53,7 +53,7 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
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 {
return
}
@@ -68,7 +68,7 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessag
lines := strings.Split(string(stdout), "\n")
for i := 1; i < m.config.Num_procs+1; 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 {
output <- y
}

View File

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

38
go.mod
View File

@@ -1,49 +1,41 @@
module github.com/ClusterCockpit/cc-metric-collector
go 1.23.0
toolchain go1.23.2
go 1.21
require (
github.com/ClusterCockpit/cc-energy-manager v0.0.0-20240709142550-dd446f7ab900
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1
github.com/ClusterCockpit/cc-units v0.4.0
github.com/ClusterCockpit/go-rocm-smi v0.3.0
github.com/NVIDIA/go-nvml v0.12.0-2
github.com/PaesslerAG/gval v1.2.2
github.com/expr-lang/expr v1.16.9
github.com/fsnotify/fsnotify v1.7.0
github.com/gorilla/mux v1.8.1
github.com/influxdata/influxdb-client-go/v2 v2.14.0
github.com/influxdata/influxdb-client-go/v2 v2.13.0
github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
github.com/influxdata/line-protocol/v2 v2.2.1
github.com/nats-io/nats.go v1.39.0
github.com/prometheus/client_golang v1.20.5
github.com/nats-io/nats.go v1.33.1
github.com/prometheus/client_golang v1.19.0
github.com/stmcginnis/gofish v0.15.0
github.com/tklauser/go-sysconf v0.3.13
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f
golang.org/x/sys v0.28.0
golang.org/x/exp v0.0.0-20240222234643-814bf88cf225
golang.org/x/sys v0.18.0
)
require (
github.com/ClusterCockpit/cc-backend v1.4.2 // indirect
github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
github.com/beorn7/perks v1.0.1 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/cespare/xxhash/v2 v2.2.0 // indirect
github.com/google/uuid v1.6.0 // indirect
github.com/klauspost/compress v1.17.9 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
github.com/nats-io/nkeys v0.4.9 // indirect
github.com/klauspost/compress v1.17.7 // indirect
github.com/nats-io/nkeys v0.4.7 // indirect
github.com/nats-io/nuid v1.0.1 // indirect
github.com/oapi-codegen/runtime v1.1.1 // indirect
github.com/prometheus/client_model v0.6.1 // indirect
github.com/prometheus/common v0.55.0 // indirect
github.com/prometheus/procfs v0.15.1 // indirect
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 // indirect
github.com/prometheus/client_model v0.6.0 // indirect
github.com/prometheus/common v0.49.0 // indirect
github.com/prometheus/procfs v0.12.0 // indirect
github.com/shopspring/decimal v1.3.1 // indirect
github.com/tklauser/numcpus v0.7.0 // indirect
golang.org/x/crypto v0.31.0 // indirect
golang.org/x/net v0.31.0 // indirect
google.golang.org/protobuf v1.35.2 // indirect
golang.org/x/crypto v0.21.0 // indirect
golang.org/x/net v0.22.0 // indirect
google.golang.org/protobuf v1.33.0 // indirect
)

85
go.sum
View File

@@ -1,9 +1,3 @@
github.com/ClusterCockpit/cc-backend v1.4.2 h1:kTOzqkh9N0564N9nqQThnSs7TAfg8RLgvSm00e5HtIc=
github.com/ClusterCockpit/cc-backend v1.4.2/go.mod h1:g8TNHXe4AXej26snu2//jO3mUF980elT93iV/k11O/c=
github.com/ClusterCockpit/cc-energy-manager v0.0.0-20240709142550-dd446f7ab900 h1:6+WNav16uWTEDC09hkZKEHfBhtc91p/ZcjgCtyntuIg=
github.com/ClusterCockpit/cc-energy-manager v0.0.0-20240709142550-dd446f7ab900/go.mod h1:EbYeC5t+Y0kW1Q1pP2n9zMqbeYEJITG8YGvAUihXVn4=
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1 h1:dz9j0g2cod8+SMDjuoIY6ISpiHHeekhX6yQaeiwiwJw=
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1/go.mod h1:kXMskla1i5ZSfXW0vVRIHgGeXMU5zu2PzYOYnUaOr80=
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/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8=
@@ -13,7 +7,6 @@ github.com/NVIDIA/go-nvml v0.12.0-2 h1:Sg239yy7jmopu/cuvYauoMj9fOpcGMngxVxxS1EBX
github.com/NVIDIA/go-nvml v0.12.0-2/go.mod h1:7ruy85eOM73muOc/I37euONSwEyFqZsv5ED9AogD4G0=
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/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
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/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
@@ -21,76 +14,57 @@ github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP
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/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
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 v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
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/expr-lang/expr v1.16.9/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
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 v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
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 v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
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 v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
github.com/gorilla/mux v1.8.1/go.mod h1:AKf9I4AEqPTmMytcMc0KkNouC66V3BtZ4qD5fmWSiMQ=
github.com/influxdata/influxdb-client-go/v2 v2.14.0 h1:AjbBfJuq+QoaXNcrova8smSjwJdUHnwvfjMF71M1iI4=
github.com/influxdata/influxdb-client-go/v2 v2.14.0/go.mod h1:Ahpm3QXKMJslpXl3IftVLVezreAUtBOTZssDrjZEFHI=
github.com/influxdata/influxdb-client-go/v2 v2.13.0 h1:ioBbLmR5NMbAjP4UVA5r9b5xGjpABD7j65pI8kFphDM=
github.com/influxdata/influxdb-client-go/v2 v2.13.0/go.mod h1:k+spCbt9hcvqvUiz0sr5D8LolXHqAAOfPw9v/RIRHl4=
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-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/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 v2.2.1 h1:EAPkqJ9Km4uAxtMRgUubJyqAr6zgWM0dznKMLRauQRE=
github.com/influxdata/line-protocol/v2 v2.2.1/go.mod h1:DmB3Cnh+3oxmG6LOBIxce4oaL4CPj3OmMPgvauXh+tM=
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/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
github.com/klauspost/compress v1.17.7 h1:ehO88t2UGzQK66LMdE8tibEd1ErmzZjNEqWkjLAKQQg=
github.com/klauspost/compress v1.17.7/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
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/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/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
github.com/nats-io/nats.go v1.39.0 h1:2/yg2JQjiYYKLwDuBzV0FbB2sIV+eFNkEevlRi4n9lI=
github.com/nats-io/nats.go v1.39.0/go.mod h1:MgRb8oOdigA6cYpEPhXJuRVH6UE/V4jblJ2jQ27IXYM=
github.com/nats-io/nkeys v0.4.9 h1:qe9Faq2Gxwi6RZnZMXfmGMZkg3afLLOtrU+gDZJ35b0=
github.com/nats-io/nkeys v0.4.9/go.mod h1:jcMqs+FLG+W5YO36OX6wFIFcmpdAns+w1Wm6D3I/evE=
github.com/nats-io/nats.go v1.33.1 h1:8TxLZZ/seeEfR97qV0/Bl939tpDnt2Z2fK3HkPypj70=
github.com/nats-io/nats.go v1.33.1/go.mod h1:Ubdu4Nh9exXdSz0RVWRFBbRfrbSxOYd26oF0wkWclB8=
github.com/nats-io/nkeys v0.4.7 h1:RwNJbbIdYCoClSDNY7QVKZlyb/wfT6ugvFCiKy6vDvI=
github.com/nats-io/nkeys v0.4.7/go.mod h1:kqXRgRDPlGy7nGaEDMuYzmiJCIAAWDK0IMBtDmGD0nc=
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/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+bR9r+8l63Y=
github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
github.com/prometheus/common v0.55.0 h1:KEi6DK7lXW/m7Ig5i47x0vRzuBsHuvJdi5ee6Y3G1dc=
github.com/prometheus/common v0.55.0/go.mod h1:2SECS4xJG1kd8XF9IcM1gMX6510RAEL65zxzNImwdc8=
github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 h1:lZUw3E0/J3roVtGQ+SCrUrg3ON6NgVqpn3+iol9aGu4=
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1/go.mod h1:uToXkOrWAZ6/Oc07xWQrPOhJotwFIyu2bBVN41fcDUY=
github.com/prometheus/client_golang v1.19.0 h1:ygXvpU1AoN1MhdzckN+PyD9QJOSD4x7kmXYlnfbA6JU=
github.com/prometheus/client_golang v1.19.0/go.mod h1:ZRM9uEAypZakd+q/x7+gmsvXdURP+DABIEIjnmDdp+k=
github.com/prometheus/client_model v0.6.0 h1:k1v3CzpSRUTrKMppY35TLwPvxHqBu0bYgxZzqGIgaos=
github.com/prometheus/client_model v0.6.0/go.mod h1:NTQHnmxFpouOD0DpvP4XujX3CdOAGQPoaGhyTchlyt8=
github.com/prometheus/common v0.49.0 h1:ToNTdK4zSnPVJmh698mGFkDor9wBI/iGaJy5dbH1EgI=
github.com/prometheus/common v0.49.0/go.mod h1:Kxm+EULxRbUkjGU6WFsQqo3ORzB4tyKvlWFOE9mB2sE=
github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
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/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
@@ -103,29 +77,26 @@ github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UV
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 v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
github.com/tklauser/go-sysconf v0.3.13 h1:GBUpcahXSpR2xN01jhkNAbTLRk2Yzgggk8IM08lq3r4=
github.com/tklauser/go-sysconf v0.3.13/go.mod h1:zwleP4Q4OehZHGn4CYZDipCgg9usW5IJePewFCGVEa0=
github.com/tklauser/numcpus v0.7.0 h1:yjuerZP127QG9m5Zh/mSO4wqurYil27tHrqwRoRjpr4=
github.com/tklauser/numcpus v0.7.0/go.mod h1:bb6dMVcj8A42tSE7i32fsIUCbQNllK5iDguyOZRUzAY=
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.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f h1:oFMYAjX0867ZD2jcNiLBrI9BdpmEkvPyi5YrBGXbamg=
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk=
golang.org/x/net v0.31.0 h1:68CPQngjLL0r2AlUKiSxtQFKvzRVbnzLwMUn5SzcLHo=
golang.org/x/net v0.31.0/go.mod h1:P4fl1q7dY2hnZFxEk4pPSkDHF+QqjitcnDjUQyMM+pM=
golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
golang.org/x/exp v0.0.0-20240222234643-814bf88cf225 h1:LfspQV/FYTatPTr/3HzIcmiUFH7PGP+OQ6mgDYo3yuQ=
golang.org/x/exp v0.0.0-20240222234643-814bf88cf225/go.mod h1:CxmFvTBINI24O/j8iY7H1xHzx2i4OsyguNBmN/uPtqc=
golang.org/x/net v0.22.0 h1:9sGLhx7iRIHEiX0oAJ3MRZMUCElJgy7Br1nO+AMN3Tc=
golang.org/x/net v0.22.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
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 v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
google.golang.org/protobuf v1.35.2 h1:8Ar7bF+apOIoThw1EdZl0p1oWvMqTHmpA2fRTyZO8io=
google.golang.org/protobuf v1.35.2/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI=
google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
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/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 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

View File

@@ -11,7 +11,7 @@ import (
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
"github.com/PaesslerAG/gval"
@@ -31,14 +31,14 @@ type metricAggregator struct {
functions []*MetricAggregatorIntervalConfig
constants map[string]interface{}
language gval.Language
output chan lp.CCMessage
output chan lp.CCMetric
}
type MetricAggregator interface {
AddAggregation(name, function, condition string, tags, meta map[string]string) error
DeleteAggregation(name string) error
Init(output chan lp.CCMessage) error
Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMessage)
Init(output chan lp.CCMetric) error
Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMetric)
}
var metricCacheLanguage = gval.NewLanguage(
@@ -74,7 +74,7 @@ var evaluables = struct {
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.functions = make([]*MetricAggregatorIntervalConfig, 0)
c.constants = make(map[string]interface{})
@@ -112,7 +112,7 @@ func (c *metricAggregator) Init(output chan lp.CCMessage) error {
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{})
for k, v := range c.constants {
vars[k] = v
@@ -127,7 +127,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
var valuesInt32 []int32
var valuesInt64 []int64
var valuesBool []bool
matches := make([]lp.CCMessage, 0)
matches := make([]lp.CCMetric, 0)
for _, m := range metrics {
vars["metric"] = m
//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
}
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)
for key, value := range tags {
switch value {
@@ -233,7 +233,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
}
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)
for key, value := range meta {
switch value {
@@ -253,18 +253,18 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
tags := copy_tags(f.Tags, matches)
meta := copy_meta(f.Meta, matches)
var m lp.CCMessage
var m lp.CCMetric
switch t := value.(type) {
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:
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:
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:
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:
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:
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
}
func NewAggregator(output chan lp.CCMessage) (MetricAggregator, error) {
func NewAggregator(output chan lp.CCMetric) (MetricAggregator, error) {
a := new(metricAggregator)
err := a.Init(output)
if err != nil {

View File

@@ -1,21 +1,15 @@
# 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-energy-manager@v0.0.0-20240919152819-92a17f2da4f7/pkg/cc-message.
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
**Note**: Use the [message processor configuration](../../pkg/messageProcessor/README.md) with option `process_messages`.
```json
{
"num_cache_intervals" : 1,
"interval_timestamp" : true,
"hostname_tag" : "hostname",
"max_forward" : 50,
"process_messages": {
"see": "pkg/messageProcessor/README.md"
},
"add_tags" : [
{
"key" : "cluster",
@@ -69,8 +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.
**Note**: Use the [message processor configuration](../../pkg/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
- Add the `hostname_tag` tag (if sent by collectors or cache)
@@ -104,8 +96,6 @@ Every time the router receives a metric through any of the channels, it tries to
# 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`
```json
@@ -117,8 +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`)
__deprecated__
Common config format:
```json
{
@@ -130,8 +118,6 @@ Common config format:
## 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.
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.
@@ -143,8 +129,6 @@ Never delete tags:
## 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`.
If the CCMetric name is equal to `temp_package_id_0`, it adds an additional tag `test=testing` to the metric.
@@ -186,8 +170,6 @@ In some cases, you want to drop a metric and don't get it forwarded to the sinks
## The `drop_metrics` section
__deprecated__
The argument is a list of metric names. No futher checks are performed, only a comparison of the metric name
```json
@@ -203,8 +185,6 @@ The example drops all metrics with the name `drop_metric_1` and `drop_metric_2`.
## 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`).
```json
@@ -220,22 +200,15 @@ The first line is comparable with the example in `drop_metrics`, it drops all me
# Manipulating the metric units
## 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-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
__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.
# 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.

View File

@@ -7,7 +7,7 @@ import (
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
)
@@ -16,7 +16,7 @@ type metricCachePeriod struct {
stopstamp time.Time
numMetrics int
sizeMetrics int
metrics []lp.CCMessage
metrics []lp.CCMetric
}
// Metric cache data structure
@@ -29,21 +29,21 @@ type metricCache struct {
ticker mct.MultiChanTicker
tickchan chan time.Time
done chan bool
output chan lp.CCMessage
output chan lp.CCMetric
aggEngine agg.MetricAggregator
}
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()
Add(metric lp.CCMessage)
GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage)
Add(metric lp.CCMetric)
GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric)
AddAggregation(name, function, condition string, tags, meta map[string]string) error
DeleteAggregation(name string) error
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
c.done = make(chan bool)
c.wg = wg
@@ -55,7 +55,7 @@ func (c *metricCache) Init(output chan lp.CCMessage, ticker mct.MultiChanTicker,
p := new(metricCachePeriod)
p.numMetrics = 0
p.sizeMetrics = 0
p.metrics = make([]lp.CCMessage, 0)
p.metrics = make([]lp.CCMetric, 0)
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())
// The intervals list is used as round-robin buffer and the metric list grows dynamically and
// 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 {
c.lock.Lock()
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
// 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, ...)
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 stop time.Time = time.Now()
var metrics []lp.CCMessage
var metrics []lp.CCMetric
if index >= 0 && index < c.numPeriods {
pindex := c.curPeriod - index
if pindex < 0 {
@@ -168,10 +168,10 @@ func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage
metrics = c.intervals[pindex].metrics
//return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
} else {
metrics = make([]lp.CCMessage, 0)
metrics = make([]lp.CCMetric, 0)
}
} else {
metrics = make([]lp.CCMessage, 0)
metrics = make([]lp.CCMetric, 0)
}
return start, stop, metrics
}
@@ -182,7 +182,7 @@ func (c *metricCache) Close() {
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)
err := c.Init(output, ticker, wg, numPeriods)
if err != nil {

View File

@@ -2,7 +2,6 @@ package metricRouter
import (
"encoding/json"
"fmt"
"os"
"strings"
"sync"
@@ -10,10 +9,10 @@ import (
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
units "github.com/ClusterCockpit/cc-units"
)
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
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
// dropMetrics map[string]bool // Internal map for O(1) lookup
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
dropMetrics map[string]bool // Internal map for O(1) lookup
}
// Metric router data structure
type metricRouter struct {
hostname string // Hostname used in tags
coll_input chan lp.CCMessage // Input channel from CollectorManager
recv_input chan lp.CCMessage // Input channel from ReceiveManager
cache_input chan lp.CCMessage // Input channel from MetricCache
outputs []chan lp.CCMessage // List of all output channels
coll_input chan lp.CCMetric // Input channel from CollectorManager
recv_input chan lp.CCMetric // Input channel from ReceiveManager
cache_input chan lp.CCMetric // Input channel from MetricCache
outputs []chan lp.CCMetric // List of all output channels
done chan bool // channel to finish / stop metric router
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
timestamp time.Time // timestamp periodically updated by ticker each interval
@@ -58,15 +56,14 @@ type metricRouter struct {
cache MetricCache // pointer to MetricCache
cachewg sync.WaitGroup // wait group for MetricCache
maxForward int // number of metrics to forward maximally in one iteration
mp mp.MessageProcessor
}
// MetricRouter access functions
type MetricRouter interface {
Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) error
AddCollectorInput(input chan lp.CCMessage)
AddReceiverInput(input chan lp.CCMessage)
AddOutput(output chan lp.CCMessage)
AddCollectorInput(input chan lp.CCMetric)
AddReceiverInput(input chan lp.CCMetric)
AddOutput(output chan lp.CCMetric)
Start()
Close()
}
@@ -78,9 +75,9 @@ type MetricRouter interface {
// * ticker (from variable ticker)
// * configuration (read from config file in variable routerConfigFile)
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.cache_input = make(chan lp.CCMessage)
r.cache_input = make(chan lp.CCMetric)
r.wg = wg
r.ticker = ticker
r.config.MaxForward = ROUTER_MAX_FORWARD
@@ -122,56 +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)
}
}
p, err := mp.NewMessageProcessor()
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())
}
}
r.config.dropMetrics = make(map[string]bool)
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
}
func getParamMap(point lp.CCMessage) map[string]interface{} {
func getParamMap(point lp.CCMetric) map[string]interface{} {
params := make(map[string]interface{})
params["metric"] = point
params["name"] = point.Name()
@@ -189,7 +144,7 @@ func getParamMap(point lp.CCMessage) map[string]interface{} {
}
// 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
for _, m := range r.config.AddTags {
if m.Condition == "*" {
@@ -211,81 +166,81 @@ func (r *metricRouter) DoAddTags(point lp.CCMessage) {
}
// DoDelTags removes a tag when condition is fullfiled
// func (r *metricRouter) DoDelTags(point lp.CCMessage) {
// var conditionMatches bool
// for _, m := range r.config.DelTags {
// if m.Condition == "*" {
// // Condition is always matched
// conditionMatches = true
// } else {
// // Evaluate condition
// var err error
// conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
// if err != nil {
// cclog.ComponentError("MetricRouter", err.Error())
// conditionMatches = false
// }
// }
// if conditionMatches {
// point.RemoveTag(m.Key)
// }
// }
// }
func (r *metricRouter) DoDelTags(point lp.CCMetric) {
var conditionMatches bool
for _, m := range r.config.DelTags {
if m.Condition == "*" {
// Condition is always matched
conditionMatches = true
} else {
// Evaluate condition
var err error
conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
if err != nil {
cclog.ComponentError("MetricRouter", err.Error())
conditionMatches = false
}
}
if conditionMatches {
point.RemoveTag(m.Key)
}
}
}
// Conditional test whether a metric should be dropped
// func (r *metricRouter) dropMetric(point lp.CCMessage) bool {
// // Simple drop check
// if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
// return conditionMatches
// }
func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
// Simple drop check
if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
return conditionMatches
}
// // Checking the dropping conditions
// for _, m := range r.config.DropMetricsIf {
// conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point))
// if err != nil {
// cclog.ComponentError("MetricRouter", err.Error())
// conditionMatches = false
// }
// if conditionMatches {
// return conditionMatches
// }
// }
// Checking the dropping conditions
for _, m := range r.config.DropMetricsIf {
conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point))
if err != nil {
cclog.ComponentError("MetricRouter", err.Error())
conditionMatches = false
}
if conditionMatches {
return conditionMatches
}
}
// // No dropping condition met
// return false
// }
// No dropping condition met
return false
}
// func (r *metricRouter) prepareUnit(point lp.CCMessage) bool {
// if r.config.NormalizeUnits {
// if in_unit, ok := point.GetMeta("unit"); ok {
// u := units.NewUnit(in_unit)
// if u.Valid() {
// point.AddMeta("unit", u.Short())
// }
// }
// }
// if newP, ok := r.config.ChangeUnitPrefix[point.Name()]; ok {
func (r *metricRouter) prepareUnit(point lp.CCMetric) bool {
if r.config.NormalizeUnits {
if in_unit, ok := point.GetMeta("unit"); ok {
u := units.NewUnit(in_unit)
if u.Valid() {
point.AddMeta("unit", u.Short())
}
}
}
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 {
// u := units.NewUnit(in_unit)
// if u.Valid() {
// cclog.ComponentDebug("MetricRouter", "Change prefix to", newP, "for metric", point.Name())
// conv, out_unit := units.GetUnitPrefixFactor(u, newPrefix)
// if conv != nil && out_unit.Valid() {
// if val, ok := point.GetField("value"); ok {
// point.AddField("value", conv(val))
// point.AddMeta("unit", out_unit.Short())
// }
// }
// }
if in_unit, ok := point.GetMeta("unit"); ok && newPrefix != units.InvalidPrefix {
u := units.NewUnit(in_unit)
if u.Valid() {
cclog.ComponentDebug("MetricRouter", "Change prefix to", newP, "for metric", point.Name())
conv, out_unit := units.GetUnitPrefixFactor(u, newPrefix)
if conv != nil && out_unit.Valid() {
if val, ok := point.GetField("value"); ok {
point.AddField("value", conv(val))
point.AddMeta("unit", out_unit.Short())
}
}
}
// }
// }
}
}
// return true
// }
return true
}
// Start starts the metric router
func (r *metricRouter) Start() {
@@ -304,75 +259,59 @@ func (r *metricRouter) Start() {
// Forward takes a received metric, adds or deletes tags
// and forwards it to the output channels
// forward := func(point lp.CCMessage) {
// cclog.ComponentDebug("MetricRouter", "FORWARD", point)
// r.DoAddTags(point)
// r.DoDelTags(point)
// name := point.Name()
// if new, ok := r.config.RenameMetrics[name]; ok {
// point.SetName(new)
// point.AddMeta("oldname", name)
// r.DoAddTags(point)
// r.DoDelTags(point)
// }
forward := func(point lp.CCMetric) {
cclog.ComponentDebug("MetricRouter", "FORWARD", point)
r.DoAddTags(point)
r.DoDelTags(point)
name := point.Name()
if new, ok := r.config.RenameMetrics[name]; ok {
point.SetName(new)
point.AddMeta("oldname", name)
r.DoAddTags(point)
r.DoDelTags(point)
}
// r.prepareUnit(point)
r.prepareUnit(point)
// for _, o := range r.outputs {
// o <- point
// }
// }
for _, o := range r.outputs {
o <- point
}
}
// Foward message received from collector channel
coll_forward := func(p lp.CCMessage) {
coll_forward := func(p lp.CCMetric) {
// receive from metric collector
//p.AddTag(r.config.HostnameTagName, r.hostname)
p.AddTag(r.config.HostnameTagName, r.hostname)
if r.config.IntervalStamp {
p.SetTime(r.timestamp)
}
m, err := r.mp.ProcessMessage(p)
if err == nil && m != nil {
for _, o := range r.outputs {
o <- m
}
if !r.dropMetric(p) {
forward(p)
}
// if !r.dropMetric(p) {
// for _, o := range r.outputs {
// o <- point
// }
// }
// even if the metric is dropped, it is stored in the cache for
// aggregations
if r.config.NumCacheIntervals > 0 {
r.cache.Add(m)
r.cache.Add(p)
}
}
// Forward message received from receivers channel
recv_forward := func(p lp.CCMessage) {
recv_forward := func(p lp.CCMetric) {
// receive from receive manager
if r.config.IntervalStamp {
p.SetTime(r.timestamp)
}
m, err := r.mp.ProcessMessage(p)
if err == nil && m != nil {
for _, o := range r.outputs {
o <- m
}
if !r.dropMetric(p) {
forward(p)
}
// if !r.dropMetric(p) {
// forward(p)
// }
}
// Forward message received from cache channel
cache_forward := func(p lp.CCMessage) {
cache_forward := func(p lp.CCMetric) {
// receive from metric collector
m, err := r.mp.ProcessMessage(p)
if err == nil && m != nil {
for _, o := range r.outputs {
o <- m
}
if !r.dropMetric(p) {
p.AddTag(r.config.HostnameTagName, r.hostname)
forward(p)
}
}
@@ -419,17 +358,17 @@ func (r *metricRouter) Start() {
}
// 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
}
// 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
}
// 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)
}

View File

@@ -296,25 +296,6 @@ func GetTypeList(topology_type string) []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
func CpuData() []HwthreadEntry {
// return a deep copy to protect cache data
@@ -442,22 +423,3 @@ func GetCoreHwthreads(core int) []int {
}
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

@@ -1,266 +0,0 @@
# Message Processor Component
Multiple parts of in the ClusterCockit ecosystem require the processing of CCMessages.
The main CC application using it is `cc-metric-collector`. The processing part there was originally in the metric router, the central
hub connecting collectors (reading local data), receivers (receiving remote data) and sinks (sending data). Already in early stages, the
lack of flexibility caused some trouble:
> The sysadmins wanted to keep operating their Ganglia based monitoring infrastructure while we developed the CC stack. Ganglia wants the core metrics with
> a specific name and resolution (right unit prefix) but there was no conversion of the data in the CC stack, so CC frontend developers wanted a different
> resolution for some metrics. The issue was basically the `mem_used` metric showing the currently used memory of the node. Ganglia wants it in `kByte` as provided
> by the Linux operating system but CC wanted it in `GByte`.
With the message processor, the Ganglia sinks can apply the unit prefix changes individually and name the metrics as required by Ganglia.
## For developers
Whenever you receive or are about to send a message out, you should provide some processing.
### Configuration of component
New operations can be added to the message processor at runtime. Of course, they can also be removed again. For the initial setup, having a configuration file
or some fields in a configuration file for the processing.
The message processor uses the following configuration
```json
{
"drop_messages": [
"name_of_message_to_drop"
],
"drop_messages_if": [
"condition_when_to_drop_message",
"name == 'drop_this'",
"tag.hostname == 'this_host'",
"meta.unit != 'MB'"
],
"rename_messages" : {
"old_message_name" : "new_message_name"
},
"rename_messages_if": {
"condition_when_to_rename_message" : "new_name"
},
"add_tags_if": [
{
"if" : "condition_when_to_add_tag",
"key": "name_for_new_tag",
"value": "new_tag_value"
}
],
"delete_tags_if": [
{
"if" : "condition_when_to_delete_tag",
"key": "name_of_tag"
}
],
"add_meta_if": [
{
"if" : "condition_when_to_add_meta_info",
"key": "name_for_new_meta_info",
"value": "new_meta_info_value"
}
],
"delete_meta_if": [
{
"if" : "condition_when_to_delete_meta_info",
"key": "name_of_meta_info"
}
],
"add_field_if": [
{
"if" : "condition_when_to_add_field",
"key": "name_for_new_field",
"value": "new_field_value_but_only_string_at_the_moment"
}
],
"delete_field_if": [
{
"if" : "condition_when_to_delete_field",
"key": "name_of_field"
}
],
"move_tag_to_meta_if": [
{
"if" : "condition_when_to_move_tag_to_meta_info_including_its_value",
"key": "name_of_tag",
"value": "name_of_meta_info"
}
],
"move_tag_to_field_if": [
{
"if" : "condition_when_to_move_tag_to_fields_including_its_value",
"key": "name_of_tag",
"value": "name_of_field"
}
],
"move_meta_to_tag_if": [
{
"if" : "condition_when_to_move_meta_info_to_tags_including_its_value",
"key": "name_of_meta_info",
"value": "name_of_tag"
}
],
"move_meta_to_field_if": [
{
"if" : "condition_when_to_move_meta_info_to_fields_including_its_value",
"key": "name_of_tag",
"value": "name_of_meta_info"
}
],
"move_field_to_tag_if": [
{
"if" : "condition_when_to_move_field_to_tags_including_its_stringified_value",
"key": "name_of_field",
"value": "name_of_tag"
}
],
"move_field_to_meta_if": [
{
"if" : "condition_when_to_move_field_to_meta_info_including_its_stringified_value",
"key": "name_of_field",
"value": "name_of_meta_info"
}
],
"drop_by_message_type": [
"metric",
"event",
"log",
"control"
],
"change_unit_prefix": {
"name == 'metric_with_wrong_unit_prefix'" : "G",
"only_if_messagetype == 'metric'": "T"
},
"normalize_units": true,
"add_base_env": {
"MY_CONSTANT_FOR_CUSTOM_CONDITIONS": 1.0,
"output_value_for_test_metrics": 42.0,
},
"stage_order": [
"rename_messages_if",
"drop_messages"
]
}
```
The options `change_unit_prefix` and `normalize_units` are only applied to CCMetrics. It is not possible to delete the field related to each message type as defined in [cc-specification](https://github.com/ClusterCockpit/cc-specifications/tree/master/interfaces/lineprotocol). In short:
- CCMetrics always have to have a field named `value`
- CCEvents always have to have a field named `event`
- CCLogs always have to have a field named `log`
- CCControl messages always have to have a field named `control`
With `add_base_env`, one can specifiy mykey=myvalue pairs that can be used in conditions like `tag.type == mykey`.
The order in which each message is processed, can be specified with the `stage_order` option. The stage names are the keys in the JSON configuration, thus `change_unit_prefix`, `move_field_to_meta_if`, etc. Stages can be listed multiple times.
### Using the component
In order to load the configuration from a `json.RawMessage`:
```golang
mp, err := NewMessageProcessor()
if err != nil {
log.Error("failed to create new message processor")
}
mp.FromConfigJSON(configJson)
```
After initialization and adding the different operations, the `ProcessMessage()` function applies all operations and returns whether the message should be dropped.
```golang
m := lp.CCMetric{}
x, err := mp.ProcessMessage(m)
if err != nil {
// handle error
}
if x != nil {
// process x further
} else {
// this message got dropped
}
```
Single operations can be added and removed at runtime
```golang
type MessageProcessor interface {
// Functions to set the execution order of the processing stages
SetStages([]string) error
DefaultStages() []string
// Function to add variables to the base evaluation environment
AddBaseEnv(env map[string]interface{}) error
// Functions to add and remove rules
AddDropMessagesByName(name string) error
RemoveDropMessagesByName(name string)
AddDropMessagesByCondition(condition string) error
RemoveDropMessagesByCondition(condition string)
AddRenameMetricByCondition(condition string, name string) error
RemoveRenameMetricByCondition(condition string)
AddRenameMetricByName(from, to string) error
RemoveRenameMetricByName(from string)
SetNormalizeUnits(settings bool)
AddChangeUnitPrefix(condition string, prefix string) error
RemoveChangeUnitPrefix(condition string)
AddAddTagsByCondition(condition, key, value string) error
RemoveAddTagsByCondition(condition string)
AddDeleteTagsByCondition(condition, key, value string) error
RemoveDeleteTagsByCondition(condition string)
AddAddMetaByCondition(condition, key, value string) error
RemoveAddMetaByCondition(condition string)
AddDeleteMetaByCondition(condition, key, value string) error
RemoveDeleteMetaByCondition(condition string)
AddMoveTagToMeta(condition, key, value string) error
RemoveMoveTagToMeta(condition string)
AddMoveTagToFields(condition, key, value string) error
RemoveMoveTagToFields(condition string)
AddMoveMetaToTags(condition, key, value string) error
RemoveMoveMetaToTags(condition string)
AddMoveMetaToFields(condition, key, value string) error
RemoveMoveMetaToFields(condition string)
AddMoveFieldToTags(condition, key, value string) error
RemoveMoveFieldToTags(condition string)
AddMoveFieldToMeta(condition, key, value string) error
RemoveMoveFieldToMeta(condition string)
// Read in a JSON configuration
FromConfigJSON(config json.RawMessage) error
ProcessMessage(m lp2.CCMessage) (lp2.CCMessage, error)
// Processing functions for legacy CCMetric and current CCMessage
ProcessMetric(m lp.CCMetric) (lp2.CCMessage, error)
}
```
### Syntax for evaluatable terms
The message processor uses `gval` for evaluating the terms. It provides a basic set of operators like string comparison and arithmetic operations.
Accessible for operations are
- `name` of the message
- `timestamp` or `time` of the message
- `type`, `type-id` of the message (also `tag_type`, `tag_type-id` and `tag_typeid`)
- `stype`, `stype-id` of the message (if message has theses tags, also `tag_stype`, `tag_stype-id` and `tag_stypeid`)
- `value` for a CCMetric message (also `field_value`)
- `event` for a CCEvent message (also `field_event`)
- `control` for a CCControl message (also `field_control`)
- `log` for a CCLog message (also `field_log`)
- `messagetype` or `msgtype`. Possible values `event`, `metric`, `log` and `control`.
Generally, all tags are accessible with `tag_<tagkey>`, `tags_<tagkey>` or `tags.<tagkey>`. Similarly for all fields with `field[s]?[_.]<fieldkey>`. For meta information `meta[_.]<metakey>` (there is no `metas[_.]<metakey>`).
The [syntax of `expr`](https://expr-lang.org/docs/language-definition) is accepted with some additions:
- Comparing strings: `==`, `!=`, `str matches regex` (use `%` instead of `\`!)
- Combining conditions: `&&`, `||`
- Comparing numbers: `==`, `!=`, `<`, `>`, `<=`, `>=`
- Test lists: `<value> in <list>`
- Topological tests: `tag_type-id in getCpuListOfType("socket", "1")` (test if the metric belongs to socket 1 in local node topology)
Often the operations are written in JSON files for loading them at startup. In JSON, some characters are not allowed. Therefore, the term syntax reflects that:
- use `''` instead of `""` for strings
- for the regexes, use `%` instead of `\`
For operations that should be applied on all messages, use the condition `true`.
### Overhead
The operations taking conditions are pre-processed, which is commonly the time consuming part but, of course, with each added operation, the time to process a message
increases. Moreover, the processing creates a copy of the message.

View File

@@ -1,988 +0,0 @@
package messageprocessor
import (
"encoding/json"
"fmt"
"strings"
"sync"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lplegacy "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/expr-lang/expr"
"github.com/expr-lang/expr/vm"
)
// Message processor add/delete tag/meta configuration
type messageProcessorTagConfig struct {
Key string `json:"key"` // Tag name
Value string `json:"value,omitempty"` // Tag value
Condition string `json:"if"` // Condition for adding or removing corresponding tag
}
type messageProcessorConfig struct {
StageOrder []string `json:"stage_order,omitempty"` // List of stages to execute them in the specified order and to skip unrequired ones
DropMessages []string `json:"drop_messages,omitempty"` // List of metric names to drop. For fine-grained dropping use drop_messages_if
DropMessagesIf []string `json:"drop_messages_if,omitempty"` // List of evaluatable terms to drop messages
RenameMessages map[string]string `json:"rename_messages,omitempty"` // Map of metric names to rename
RenameMessagesIf map[string]string `json:"rename_messages_if,omitempty"` // Map to rename metric name based on a condition
NormalizeUnits bool `json:"normalize_units,omitempty"` // Check unit meta flag and normalize it using cc-units
ChangeUnitPrefix map[string]string `json:"change_unit_prefix,omitempty"` // Add prefix that should be applied to the messages
AddTagsIf []messageProcessorTagConfig `json:"add_tags_if,omitempty"` // List of tags that are added when the condition is met
DelTagsIf []messageProcessorTagConfig `json:"delete_tags_if,omitempty"` // List of tags that are removed when the condition is met
AddMetaIf []messageProcessorTagConfig `json:"add_meta_if,omitempty"` // List of meta infos that are added when the condition is met
DelMetaIf []messageProcessorTagConfig `json:"delete_meta_if,omitempty"` // List of meta infos that are removed when the condition is met
AddFieldIf []messageProcessorTagConfig `json:"add_field_if,omitempty"` // List of fields that are added when the condition is met
DelFieldIf []messageProcessorTagConfig `json:"delete_field_if,omitempty"` // List of fields that are removed when the condition is met
DropByType []string `json:"drop_by_message_type,omitempty"` // List of message types that should be dropped
MoveTagToMeta []messageProcessorTagConfig `json:"move_tag_to_meta_if,omitempty"`
MoveTagToField []messageProcessorTagConfig `json:"move_tag_to_field_if,omitempty"`
MoveMetaToTag []messageProcessorTagConfig `json:"move_meta_to_tag_if,omitempty"`
MoveMetaToField []messageProcessorTagConfig `json:"move_meta_to_field_if,omitempty"`
MoveFieldToTag []messageProcessorTagConfig `json:"move_field_to_tag_if,omitempty"`
MoveFieldToMeta []messageProcessorTagConfig `json:"move_field_to_meta_if,omitempty"`
AddBaseEnv map[string]interface{} `json:"add_base_env,omitempty"`
}
type messageProcessor struct {
// For thread-safety
mutex sync.RWMutex
// mapping contains all evalables as strings to gval.Evaluable
// because it is not possible to get the original string out of
// a gval.Evaluable
mapping map[string]*vm.Program
stages []string // order of stage execution
dropMessages map[string]struct{} // internal lookup map
dropTypes map[string]struct{} // internal lookup map
dropMessagesIf map[*vm.Program]struct{} // pre-processed dropMessagesIf
renameMessages map[string]string // internal lookup map
renameMessagesIf map[*vm.Program]string // pre-processed RenameMessagesIf
changeUnitPrefix map[*vm.Program]string // pre-processed ChangeUnitPrefix
normalizeUnits bool
addTagsIf map[*vm.Program]messageProcessorTagConfig // pre-processed AddTagsIf
deleteTagsIf map[*vm.Program]messageProcessorTagConfig // pre-processed DelTagsIf
addMetaIf map[*vm.Program]messageProcessorTagConfig // pre-processed AddMetaIf
deleteMetaIf map[*vm.Program]messageProcessorTagConfig // pre-processed DelMetaIf
addFieldIf map[*vm.Program]messageProcessorTagConfig // pre-processed AddFieldIf
deleteFieldIf map[*vm.Program]messageProcessorTagConfig // pre-processed DelFieldIf
moveTagToMeta map[*vm.Program]messageProcessorTagConfig // pre-processed MoveTagToMeta
moveTagToField map[*vm.Program]messageProcessorTagConfig // pre-processed MoveTagToField
moveMetaToTag map[*vm.Program]messageProcessorTagConfig // pre-processed MoveMetaToTag
moveMetaToField map[*vm.Program]messageProcessorTagConfig // pre-processed MoveMetaToField
moveFieldToTag map[*vm.Program]messageProcessorTagConfig // pre-processed MoveFieldToTag
moveFieldToMeta map[*vm.Program]messageProcessorTagConfig // pre-processed MoveFieldToMeta
}
type MessageProcessor interface {
// Functions to set the execution order of the processing stages
SetStages([]string) error
DefaultStages() []string
// Function to add variables to the base evaluation environment
AddBaseEnv(env map[string]interface{}) error
// Functions to add and remove rules
AddDropMessagesByName(name string) error
RemoveDropMessagesByName(name string)
AddDropMessagesByCondition(condition string) error
RemoveDropMessagesByCondition(condition string)
AddRenameMetricByCondition(condition string, name string) error
RemoveRenameMetricByCondition(condition string)
AddRenameMetricByName(from, to string) error
RemoveRenameMetricByName(from string)
SetNormalizeUnits(settings bool)
AddChangeUnitPrefix(condition string, prefix string) error
RemoveChangeUnitPrefix(condition string)
AddAddTagsByCondition(condition, key, value string) error
RemoveAddTagsByCondition(condition string)
AddDeleteTagsByCondition(condition, key, value string) error
RemoveDeleteTagsByCondition(condition string)
AddAddMetaByCondition(condition, key, value string) error
RemoveAddMetaByCondition(condition string)
AddDeleteMetaByCondition(condition, key, value string) error
RemoveDeleteMetaByCondition(condition string)
AddMoveTagToMeta(condition, key, value string) error
RemoveMoveTagToMeta(condition string)
AddMoveTagToFields(condition, key, value string) error
RemoveMoveTagToFields(condition string)
AddMoveMetaToTags(condition, key, value string) error
RemoveMoveMetaToTags(condition string)
AddMoveMetaToFields(condition, key, value string) error
RemoveMoveMetaToFields(condition string)
AddMoveFieldToTags(condition, key, value string) error
RemoveMoveFieldToTags(condition string)
AddMoveFieldToMeta(condition, key, value string) error
RemoveMoveFieldToMeta(condition string)
// Read in a JSON configuration
FromConfigJSON(config json.RawMessage) error
// Processing functions for legacy CCMetric and current CCMessage
ProcessMetric(m lplegacy.CCMetric) (lp.CCMessage, error)
ProcessMessage(m lp.CCMessage) (lp.CCMessage, error)
//EvalToBool(condition string, parameters map[string]interface{}) (bool, error)
//EvalToFloat64(condition string, parameters map[string]interface{}) (float64, error)
//EvalToString(condition string, parameters map[string]interface{}) (string, error)
}
const (
STAGENAME_DROP_BY_NAME string = "drop_by_name"
STAGENAME_DROP_BY_TYPE string = "drop_by_type"
STAGENAME_DROP_IF string = "drop_if"
STAGENAME_ADD_TAG string = "add_tag"
STAGENAME_DELETE_TAG string = "delete_tag"
STAGENAME_MOVE_TAG_META string = "move_tag_to_meta"
STAGENAME_MOVE_TAG_FIELD string = "move_tag_to_fields"
STAGENAME_ADD_META string = "add_meta"
STAGENAME_DELETE_META string = "delete_meta"
STAGENAME_MOVE_META_TAG string = "move_meta_to_tags"
STAGENAME_MOVE_META_FIELD string = "move_meta_to_fields"
STAGENAME_ADD_FIELD string = "add_field"
STAGENAME_DELETE_FIELD string = "delete_field"
STAGENAME_MOVE_FIELD_TAG string = "move_field_to_tags"
STAGENAME_MOVE_FIELD_META string = "move_field_to_meta"
STAGENAME_RENAME_BY_NAME string = "rename"
STAGENAME_RENAME_IF string = "rename_if"
STAGENAME_CHANGE_UNIT_PREFIX string = "change_unit_prefix"
STAGENAME_NORMALIZE_UNIT string = "normalize_unit"
)
var StageNames = []string{
STAGENAME_DROP_BY_NAME,
STAGENAME_DROP_BY_TYPE,
STAGENAME_DROP_IF,
STAGENAME_ADD_TAG,
STAGENAME_DELETE_TAG,
STAGENAME_MOVE_TAG_META,
STAGENAME_MOVE_TAG_FIELD,
STAGENAME_ADD_META,
STAGENAME_DELETE_META,
STAGENAME_MOVE_META_TAG,
STAGENAME_MOVE_META_FIELD,
STAGENAME_ADD_FIELD,
STAGENAME_DELETE_FIELD,
STAGENAME_MOVE_FIELD_TAG,
STAGENAME_MOVE_FIELD_META,
STAGENAME_RENAME_BY_NAME,
STAGENAME_RENAME_IF,
STAGENAME_CHANGE_UNIT_PREFIX,
STAGENAME_NORMALIZE_UNIT,
}
var paramMapPool = sync.Pool{
New: func() any {
return make(map[string]interface{})
},
}
func sanitizeExprString(key string) string {
return strings.ReplaceAll(key, "type-id", "typeid")
}
func getParamMap(point lp.CCMetric) map[string]interface{} {
params := paramMapPool.Get().(map[string]interface{})
params["message"] = point
params["msg"] = point
params["name"] = point.Name()
params["timestamp"] = point.Time().Unix()
params["time"] = params["timestamp"]
fields := paramMapPool.Get().(map[string]interface{})
for key, value := range point.Fields() {
fields[key] = value
switch key {
case "value":
params["messagetype"] = "metric"
params["value"] = value
params["metric"] = value
case "event":
params["messagetype"] = "event"
params["event"] = value
case "control":
params["messagetype"] = "control"
params["control"] = value
case "log":
params["messagetype"] = "log"
params["log"] = value
default:
params["messagetype"] = "unknown"
}
}
params["msgtype"] = params["messagetype"]
params["fields"] = fields
params["field"] = fields
tags := paramMapPool.Get().(map[string]interface{})
for key, value := range point.Tags() {
tags[sanitizeExprString(key)] = value
}
params["tags"] = tags
params["tag"] = tags
meta := paramMapPool.Get().(map[string]interface{})
for key, value := range point.Meta() {
meta[sanitizeExprString(key)] = value
}
params["meta"] = meta
return params
}
var baseenv = map[string]interface{}{
"name": "",
"messagetype": "unknown",
"msgtype": "unknown",
"tag": map[string]interface{}{
"type": "unknown",
"typeid": "0",
"stype": "unknown",
"stypeid": "0",
"hostname": "localhost",
"cluster": "nocluster",
},
"tags": map[string]interface{}{
"type": "unknown",
"typeid": "0",
"stype": "unknown",
"stypeid": "0",
"hostname": "localhost",
"cluster": "nocluster",
},
"meta": map[string]interface{}{
"unit": "invalid",
"source": "unknown",
},
"fields": map[string]interface{}{
"value": 0,
"event": "",
"control": "",
"log": "",
},
"field": map[string]interface{}{
"value": 0,
"event": "",
"control": "",
"log": "",
},
"timestamp": 1234567890,
"msg": lp.EmptyMessage(),
"message": lp.EmptyMessage(),
}
func addBaseEnvWalker(values map[string]interface{}) map[string]interface{} {
out := make(map[string]interface{})
for k, v := range values {
switch value := v.(type) {
case int, int32, int64, uint, uint32, uint64, string, float32, float64:
out[k] = value
case map[string]interface{}:
if _, ok := baseenv[k]; !ok {
out[k] = addBaseEnvWalker(value)
}
}
}
return out
}
func (mp *messageProcessor) AddBaseEnv(env map[string]interface{}) error {
for k, v := range env {
switch value := v.(type) {
case int, int32, int64, uint, uint32, uint64, string, float32, float64:
baseenv[k] = value
case map[string]interface{}:
if _, ok := baseenv[k]; !ok {
baseenv[k] = addBaseEnvWalker(value)
}
}
}
return nil
}
func (mp *messageProcessor) init() error {
mp.stages = make([]string, 0)
mp.mapping = make(map[string]*vm.Program)
mp.dropMessages = make(map[string]struct{})
mp.dropTypes = make(map[string]struct{})
mp.dropMessagesIf = make(map[*vm.Program]struct{})
mp.renameMessages = make(map[string]string)
mp.renameMessagesIf = make(map[*vm.Program]string)
mp.changeUnitPrefix = make(map[*vm.Program]string)
mp.addTagsIf = make(map[*vm.Program]messageProcessorTagConfig)
mp.addMetaIf = make(map[*vm.Program]messageProcessorTagConfig)
mp.addFieldIf = make(map[*vm.Program]messageProcessorTagConfig)
mp.deleteTagsIf = make(map[*vm.Program]messageProcessorTagConfig)
mp.deleteMetaIf = make(map[*vm.Program]messageProcessorTagConfig)
mp.deleteFieldIf = make(map[*vm.Program]messageProcessorTagConfig)
mp.moveFieldToMeta = make(map[*vm.Program]messageProcessorTagConfig)
mp.moveFieldToTag = make(map[*vm.Program]messageProcessorTagConfig)
mp.moveMetaToField = make(map[*vm.Program]messageProcessorTagConfig)
mp.moveMetaToTag = make(map[*vm.Program]messageProcessorTagConfig)
mp.moveTagToField = make(map[*vm.Program]messageProcessorTagConfig)
mp.moveTagToMeta = make(map[*vm.Program]messageProcessorTagConfig)
mp.normalizeUnits = false
return nil
}
func (mp *messageProcessor) AddDropMessagesByName(name string) error {
mp.mutex.Lock()
if _, ok := mp.dropMessages[name]; !ok {
mp.dropMessages[name] = struct{}{}
}
mp.mutex.Unlock()
return nil
}
func (mp *messageProcessor) RemoveDropMessagesByName(name string) {
mp.mutex.Lock()
delete(mp.dropMessages, name)
mp.mutex.Unlock()
}
func (mp *messageProcessor) AddDropMessagesByType(typestring string) error {
valid := []string{"metric", "event", "control", "log"}
isValid := false
for _, t := range valid {
if t == typestring {
isValid = true
break
}
}
if isValid {
mp.mutex.Lock()
if _, ok := mp.dropTypes[typestring]; !ok {
cclog.ComponentDebug("MessageProcessor", "Adding type", typestring, "for dropping")
mp.dropTypes[typestring] = struct{}{}
}
mp.mutex.Unlock()
} else {
return fmt.Errorf("invalid message type %s", typestring)
}
return nil
}
func (mp *messageProcessor) RemoveDropMessagesByType(typestring string) {
mp.mutex.Lock()
delete(mp.dropTypes, typestring)
mp.mutex.Unlock()
}
func (mp *messageProcessor) addTagConfig(condition, key, value string, config *map[*vm.Program]messageProcessorTagConfig) error {
var err error
evaluable, err := expr.Compile(sanitizeExprString(condition), expr.Env(baseenv), expr.AsBool())
if err != nil {
return fmt.Errorf("failed to create condition evaluable of '%s': %v", condition, err.Error())
}
mp.mutex.Lock()
if _, ok := (*config)[evaluable]; !ok {
mp.mapping[condition] = evaluable
(*config)[evaluable] = messageProcessorTagConfig{
Condition: condition,
Key: key,
Value: value,
}
}
mp.mutex.Unlock()
return nil
}
func (mp *messageProcessor) removeTagConfig(condition string, config *map[*vm.Program]messageProcessorTagConfig) {
mp.mutex.Lock()
if e, ok := mp.mapping[condition]; ok {
delete(mp.mapping, condition)
delete(*config, e)
}
mp.mutex.Unlock()
}
func (mp *messageProcessor) AddAddTagsByCondition(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.addTagsIf)
}
func (mp *messageProcessor) RemoveAddTagsByCondition(condition string) {
mp.removeTagConfig(condition, &mp.addTagsIf)
}
func (mp *messageProcessor) AddDeleteTagsByCondition(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.deleteTagsIf)
}
func (mp *messageProcessor) RemoveDeleteTagsByCondition(condition string) {
mp.removeTagConfig(condition, &mp.deleteTagsIf)
}
func (mp *messageProcessor) AddAddMetaByCondition(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.addMetaIf)
}
func (mp *messageProcessor) RemoveAddMetaByCondition(condition string) {
mp.removeTagConfig(condition, &mp.addMetaIf)
}
func (mp *messageProcessor) AddDeleteMetaByCondition(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.deleteMetaIf)
}
func (mp *messageProcessor) RemoveDeleteMetaByCondition(condition string) {
mp.removeTagConfig(condition, &mp.deleteMetaIf)
}
func (mp *messageProcessor) AddAddFieldByCondition(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.addFieldIf)
}
func (mp *messageProcessor) RemoveAddFieldByCondition(condition string) {
mp.removeTagConfig(condition, &mp.addFieldIf)
}
func (mp *messageProcessor) AddDeleteFieldByCondition(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.deleteFieldIf)
}
func (mp *messageProcessor) RemoveDeleteFieldByCondition(condition string) {
mp.removeTagConfig(condition, &mp.deleteFieldIf)
}
func (mp *messageProcessor) AddDropMessagesByCondition(condition string) error {
var err error
evaluable, err := expr.Compile(sanitizeExprString(condition), expr.Env(baseenv), expr.AsBool())
if err != nil {
return fmt.Errorf("failed to create condition evaluable of '%s': %v", condition, err.Error())
}
mp.mutex.Lock()
if _, ok := mp.dropMessagesIf[evaluable]; !ok {
mp.mapping[condition] = evaluable
mp.dropMessagesIf[evaluable] = struct{}{}
}
mp.mutex.Unlock()
return nil
}
func (mp *messageProcessor) RemoveDropMessagesByCondition(condition string) {
mp.mutex.Lock()
if e, ok := mp.mapping[condition]; ok {
delete(mp.mapping, condition)
delete(mp.dropMessagesIf, e)
}
mp.mutex.Unlock()
}
func (mp *messageProcessor) AddRenameMetricByCondition(condition string, name string) error {
var err error
evaluable, err := expr.Compile(sanitizeExprString(condition), expr.Env(baseenv), expr.AsBool())
if err != nil {
return fmt.Errorf("failed to create condition evaluable of '%s': %v", condition, err.Error())
}
mp.mutex.Lock()
if _, ok := mp.renameMessagesIf[evaluable]; !ok {
mp.mapping[condition] = evaluable
mp.renameMessagesIf[evaluable] = name
} else {
mp.renameMessagesIf[evaluable] = name
}
mp.mutex.Unlock()
return nil
}
func (mp *messageProcessor) RemoveRenameMetricByCondition(condition string) {
mp.mutex.Lock()
if e, ok := mp.mapping[condition]; ok {
delete(mp.mapping, condition)
delete(mp.renameMessagesIf, e)
}
mp.mutex.Unlock()
}
func (mp *messageProcessor) SetNormalizeUnits(setting bool) {
mp.normalizeUnits = setting
}
func (mp *messageProcessor) AddChangeUnitPrefix(condition string, prefix string) error {
var err error
evaluable, err := expr.Compile(sanitizeExprString(condition), expr.Env(baseenv), expr.AsBool())
if err != nil {
return fmt.Errorf("failed to create condition evaluable of '%s': %v", condition, err.Error())
}
mp.mutex.Lock()
if _, ok := mp.changeUnitPrefix[evaluable]; !ok {
mp.mapping[condition] = evaluable
mp.changeUnitPrefix[evaluable] = prefix
} else {
mp.changeUnitPrefix[evaluable] = prefix
}
mp.mutex.Unlock()
return nil
}
func (mp *messageProcessor) RemoveChangeUnitPrefix(condition string) {
mp.mutex.Lock()
if e, ok := mp.mapping[condition]; ok {
delete(mp.mapping, condition)
delete(mp.changeUnitPrefix, e)
}
mp.mutex.Unlock()
}
func (mp *messageProcessor) AddRenameMetricByName(from, to string) error {
mp.mutex.Lock()
if _, ok := mp.renameMessages[from]; !ok {
mp.renameMessages[from] = to
}
mp.mutex.Unlock()
return nil
}
func (mp *messageProcessor) RemoveRenameMetricByName(from string) {
mp.mutex.Lock()
delete(mp.renameMessages, from)
mp.mutex.Unlock()
}
func (mp *messageProcessor) AddMoveTagToMeta(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.moveTagToMeta)
}
func (mp *messageProcessor) RemoveMoveTagToMeta(condition string) {
mp.removeTagConfig(condition, &mp.moveTagToMeta)
}
func (mp *messageProcessor) AddMoveTagToFields(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.moveTagToField)
}
func (mp *messageProcessor) RemoveMoveTagToFields(condition string) {
mp.removeTagConfig(condition, &mp.moveTagToField)
}
func (mp *messageProcessor) AddMoveMetaToTags(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.moveMetaToTag)
}
func (mp *messageProcessor) RemoveMoveMetaToTags(condition string) {
mp.removeTagConfig(condition, &mp.moveMetaToTag)
}
func (mp *messageProcessor) AddMoveMetaToFields(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.moveMetaToField)
}
func (mp *messageProcessor) RemoveMoveMetaToFields(condition string) {
mp.removeTagConfig(condition, &mp.moveMetaToField)
}
func (mp *messageProcessor) AddMoveFieldToTags(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.moveFieldToTag)
}
func (mp *messageProcessor) RemoveMoveFieldToTags(condition string) {
mp.removeTagConfig(condition, &mp.moveFieldToTag)
}
func (mp *messageProcessor) AddMoveFieldToMeta(condition, key, value string) error {
return mp.addTagConfig(condition, key, value, &mp.moveFieldToMeta)
}
func (mp *messageProcessor) RemoveMoveFieldToMeta(condition string) {
mp.removeTagConfig(condition, &mp.moveFieldToMeta)
}
func (mp *messageProcessor) SetStages(stages []string) error {
newstages := make([]string, 0)
if len(stages) == 0 {
mp.mutex.Lock()
mp.stages = newstages
mp.mutex.Unlock()
return nil
}
for i, s := range stages {
valid := false
for _, v := range StageNames {
if s == v {
valid = true
}
}
if valid {
newstages = append(newstages, s)
} else {
return fmt.Errorf("invalid stage %s at index %d", s, i)
}
}
mp.mutex.Lock()
mp.stages = newstages
mp.mutex.Unlock()
return nil
}
func (mp *messageProcessor) DefaultStages() []string {
return StageNames
}
func (mp *messageProcessor) FromConfigJSON(config json.RawMessage) error {
var c messageProcessorConfig
err := json.Unmarshal(config, &c)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
if len(c.StageOrder) > 0 {
err = mp.SetStages(c.StageOrder)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
} else {
err = mp.SetStages(mp.DefaultStages())
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, m := range c.DropMessages {
err = mp.AddDropMessagesByName(m)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, m := range c.DropByType {
err = mp.AddDropMessagesByType(m)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, m := range c.DropMessagesIf {
err = mp.AddDropMessagesByCondition(m)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for k, v := range c.RenameMessagesIf {
err = mp.AddRenameMetricByCondition(k, v)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for k, v := range c.RenameMessages {
err = mp.AddRenameMetricByName(k, v)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for k, v := range c.ChangeUnitPrefix {
err = mp.AddChangeUnitPrefix(k, v)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.AddTagsIf {
err = mp.AddAddTagsByCondition(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.AddMetaIf {
err = mp.AddAddMetaByCondition(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.AddFieldIf {
err = mp.AddAddFieldByCondition(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.DelTagsIf {
err = mp.AddDeleteTagsByCondition(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.DelMetaIf {
err = mp.AddDeleteMetaByCondition(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.DelFieldIf {
err = mp.AddDeleteFieldByCondition(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.MoveTagToMeta {
err = mp.AddMoveTagToMeta(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.MoveTagToField {
err = mp.AddMoveTagToFields(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.MoveMetaToTag {
err = mp.AddMoveMetaToTags(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.MoveMetaToField {
err = mp.AddMoveMetaToFields(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.MoveFieldToTag {
err = mp.AddMoveFieldToTags(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, c := range c.MoveFieldToMeta {
err = mp.AddMoveFieldToMeta(c.Condition, c.Key, c.Value)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
for _, m := range c.DropByType {
err = mp.AddDropMessagesByType(m)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
if len(c.AddBaseEnv) > 0 {
err = mp.AddBaseEnv(c.AddBaseEnv)
if err != nil {
return fmt.Errorf("failed to process config JSON: %v", err.Error())
}
}
mp.SetNormalizeUnits(c.NormalizeUnits)
return nil
}
func (mp *messageProcessor) ProcessMetric(metric lplegacy.CCMetric) (lp.CCMessage, error) {
m, err := lp.NewMessage(
metric.Name(),
metric.Tags(),
metric.Meta(),
metric.Fields(),
metric.Time(),
)
if err != nil {
return m, fmt.Errorf("failed to parse metric to message: %v", err.Error())
}
return mp.ProcessMessage(m)
}
func (mp *messageProcessor) ProcessMessage(m lp.CCMessage) (lp.CCMessage, error) {
var err error = nil
var out lp.CCMessage = lp.FromMessage(m)
name := out.Name()
if len(mp.stages) == 0 {
mp.SetStages(mp.DefaultStages())
}
mp.mutex.RLock()
defer mp.mutex.RUnlock()
params := getParamMap(out)
defer func() {
params["field"] = nil
params["tag"] = nil
paramMapPool.Put(params["fields"])
paramMapPool.Put(params["tags"])
paramMapPool.Put(params["meta"])
paramMapPool.Put(params)
}()
for _, s := range mp.stages {
switch s {
case STAGENAME_DROP_BY_NAME:
if len(mp.dropMessages) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Dropping by message name ", name)
if _, ok := mp.dropMessages[name]; ok {
//cclog.ComponentDebug("MessageProcessor", "Drop")
return nil, nil
}
}
case STAGENAME_DROP_BY_TYPE:
if len(mp.dropTypes) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Dropping by message type")
if _, ok := mp.dropTypes[params["messagetype"].(string)]; ok {
//cclog.ComponentDebug("MessageProcessor", "Drop")
return nil, nil
}
}
case STAGENAME_DROP_IF:
if len(mp.dropMessagesIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Dropping by condition")
drop, err := dropMessagesIf(&params, &mp.dropMessagesIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
if drop {
//cclog.ComponentDebug("MessageProcessor", "Drop")
return nil, nil
}
}
case STAGENAME_RENAME_BY_NAME:
if len(mp.renameMessages) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Renaming by name match")
if newname, ok := mp.renameMessages[name]; ok {
//cclog.ComponentDebug("MessageProcessor", "Rename to", newname)
out.SetName(newname)
//cclog.ComponentDebug("MessageProcessor", "Add old name as 'oldname' to meta", name)
out.AddMeta("oldname", name)
}
}
case STAGENAME_RENAME_IF:
if len(mp.renameMessagesIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Renaming by condition")
_, err := renameMessagesIf(out, &params, &mp.renameMessagesIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_ADD_TAG:
if len(mp.addTagsIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Adding tags")
_, err = addTagIf(out, &params, &mp.addTagsIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_DELETE_TAG:
if len(mp.deleteTagsIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Delete tags")
_, err = deleteTagIf(out, &params, &mp.deleteTagsIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_ADD_META:
if len(mp.addMetaIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Adding meta information")
_, err = addMetaIf(out, &params, &mp.addMetaIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_DELETE_META:
if len(mp.deleteMetaIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Delete meta information")
_, err = deleteMetaIf(out, &params, &mp.deleteMetaIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_ADD_FIELD:
if len(mp.addFieldIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Adding fields")
_, err = addFieldIf(out, &params, &mp.addFieldIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_DELETE_FIELD:
if len(mp.deleteFieldIf) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Delete fields")
_, err = deleteFieldIf(out, &params, &mp.deleteFieldIf)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_MOVE_TAG_META:
if len(mp.moveTagToMeta) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Move tag to meta")
_, err := moveTagToMeta(out, &params, &mp.moveTagToMeta)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_MOVE_TAG_FIELD:
if len(mp.moveTagToField) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Move tag to fields")
_, err := moveTagToField(out, &params, &mp.moveTagToField)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_MOVE_META_TAG:
if len(mp.moveMetaToTag) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Move meta to tags")
_, err := moveMetaToTag(out, &params, &mp.moveMetaToTag)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_MOVE_META_FIELD:
if len(mp.moveMetaToField) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Move meta to fields")
_, err := moveMetaToField(out, &params, &mp.moveMetaToField)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_MOVE_FIELD_META:
if len(mp.moveFieldToMeta) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Move field to meta")
_, err := moveFieldToMeta(out, &params, &mp.moveFieldToMeta)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_MOVE_FIELD_TAG:
if len(mp.moveFieldToTag) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Move field to tags")
_, err := moveFieldToTag(out, &params, &mp.moveFieldToTag)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
}
case STAGENAME_NORMALIZE_UNIT:
if mp.normalizeUnits {
//cclog.ComponentDebug("MessageProcessor", "Normalize units")
if lp.IsMetric(out) {
_, err := normalizeUnits(out)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
} else {
cclog.ComponentDebug("MessageProcessor", "skipped, no metric")
}
}
case STAGENAME_CHANGE_UNIT_PREFIX:
if len(mp.changeUnitPrefix) > 0 {
//cclog.ComponentDebug("MessageProcessor", "Change unit prefix")
if lp.IsMetric(out) {
_, err := changeUnitPrefix(out, &params, &mp.changeUnitPrefix)
if err != nil {
return out, fmt.Errorf("failed to evaluate: %v", err.Error())
}
} else {
cclog.ComponentDebug("MessageProcessor", "skipped, no metric")
}
}
}
}
return out, nil
}
// Get a new instace of a message processor.
func NewMessageProcessor() (MessageProcessor, error) {
mp := new(messageProcessor)
err := mp.init()
if err != nil {
err := fmt.Errorf("failed to create MessageProcessor: %v", err.Error())
cclog.ComponentError("MessageProcessor", err.Error())
return nil, err
}
return mp, nil
}

View File

@@ -1,262 +0,0 @@
package messageprocessor
import (
"errors"
"fmt"
lp2 "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
units "github.com/ClusterCockpit/cc-units"
"github.com/expr-lang/expr"
"github.com/expr-lang/expr/vm"
)
type MessageLocation int
const (
MESSAGE_LOCATION_TAGS MessageLocation = iota
MESSAGE_LOCATION_META
MESSAGE_LOCATION_FIELDS
)
// Abstract function to move entries from one location to another
func moveInMessage(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig, from, to MessageLocation) (bool, error) {
for d, data := range *checks {
value, err := expr.Run(d, *params)
if err != nil {
return false, fmt.Errorf("failed to evaluate: %v", err.Error())
}
//cclog.ComponentDebug("MessageProcessor", "Move from", from, "to", to)
if value.(bool) {
var v string
var ok bool = false
switch from {
case MESSAGE_LOCATION_TAGS:
//cclog.ComponentDebug("MessageProcessor", "Getting tag key", data.Key)
v, ok = message.GetTag(data.Key)
case MESSAGE_LOCATION_META:
//cclog.ComponentDebug("MessageProcessor", "Getting meta key", data.Key)
//cclog.ComponentDebug("MessageProcessor", message.Meta())
v, ok = message.GetMeta(data.Key)
case MESSAGE_LOCATION_FIELDS:
var x interface{}
//cclog.ComponentDebug("MessageProcessor", "Getting field key", data.Key)
x, ok = message.GetField(data.Key)
v = fmt.Sprintf("%v", x)
}
if ok {
switch from {
case MESSAGE_LOCATION_TAGS:
//cclog.ComponentDebug("MessageProcessor", "Removing tag key", data.Key)
message.RemoveTag(data.Key)
case MESSAGE_LOCATION_META:
//cclog.ComponentDebug("MessageProcessor", "Removing meta key", data.Key)
message.RemoveMeta(data.Key)
case MESSAGE_LOCATION_FIELDS:
//cclog.ComponentDebug("MessageProcessor", "Removing field key", data.Key)
message.RemoveField(data.Key)
}
switch to {
case MESSAGE_LOCATION_TAGS:
//cclog.ComponentDebug("MessageProcessor", "Adding tag", data.Value, "->", v)
message.AddTag(data.Value, v)
case MESSAGE_LOCATION_META:
//cclog.ComponentDebug("MessageProcessor", "Adding meta", data.Value, "->", v)
message.AddMeta(data.Value, v)
case MESSAGE_LOCATION_FIELDS:
//cclog.ComponentDebug("MessageProcessor", "Adding field", data.Value, "->", v)
message.AddField(data.Value, v)
}
}
}
}
return false, nil
}
func deleteIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig, location MessageLocation) (bool, error) {
for d, data := range *checks {
value, err := expr.Run(d, *params)
if err != nil {
return true, fmt.Errorf("failed to evaluate: %v", err.Error())
}
if value.(bool) {
switch location {
case MESSAGE_LOCATION_FIELDS:
switch data.Key {
case "value", "event", "log", "control":
return false, errors.New("cannot delete protected fields")
default:
//cclog.ComponentDebug("MessageProcessor", "Removing field for", data.Key)
message.RemoveField(data.Key)
}
case MESSAGE_LOCATION_TAGS:
//cclog.ComponentDebug("MessageProcessor", "Removing tag for", data.Key)
message.RemoveTag(data.Key)
case MESSAGE_LOCATION_META:
//cclog.ComponentDebug("MessageProcessor", "Removing meta for", data.Key)
message.RemoveMeta(data.Key)
}
}
}
return false, nil
}
func addIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig, location MessageLocation) (bool, error) {
for d, data := range *checks {
value, err := expr.Run(d, *params)
if err != nil {
return true, fmt.Errorf("failed to evaluate: %v", err.Error())
}
if value.(bool) {
switch location {
case MESSAGE_LOCATION_FIELDS:
//cclog.ComponentDebug("MessageProcessor", "Adding field", data.Value, "->", data.Value)
message.AddField(data.Key, data.Value)
case MESSAGE_LOCATION_TAGS:
//cclog.ComponentDebug("MessageProcessor", "Adding tag", data.Value, "->", data.Value)
message.AddTag(data.Key, data.Value)
case MESSAGE_LOCATION_META:
//cclog.ComponentDebug("MessageProcessor", "Adding meta", data.Value, "->", data.Value)
message.AddMeta(data.Key, data.Value)
}
}
}
return false, nil
}
func deleteTagIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return deleteIf(message, params, checks, MESSAGE_LOCATION_TAGS)
}
func addTagIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return addIf(message, params, checks, MESSAGE_LOCATION_TAGS)
}
func moveTagToMeta(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return moveInMessage(message, params, checks, MESSAGE_LOCATION_TAGS, MESSAGE_LOCATION_META)
}
func moveTagToField(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return moveInMessage(message, params, checks, MESSAGE_LOCATION_TAGS, MESSAGE_LOCATION_FIELDS)
}
func deleteMetaIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return deleteIf(message, params, checks, MESSAGE_LOCATION_META)
}
func addMetaIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return addIf(message, params, checks, MESSAGE_LOCATION_META)
}
func moveMetaToTag(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return moveInMessage(message, params, checks, MESSAGE_LOCATION_META, MESSAGE_LOCATION_TAGS)
}
func moveMetaToField(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return moveInMessage(message, params, checks, MESSAGE_LOCATION_META, MESSAGE_LOCATION_FIELDS)
}
func deleteFieldIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return deleteIf(message, params, checks, MESSAGE_LOCATION_FIELDS)
}
func addFieldIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return addIf(message, params, checks, MESSAGE_LOCATION_FIELDS)
}
func moveFieldToTag(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return moveInMessage(message, params, checks, MESSAGE_LOCATION_FIELDS, MESSAGE_LOCATION_TAGS)
}
func moveFieldToMeta(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]messageProcessorTagConfig) (bool, error) {
return moveInMessage(message, params, checks, MESSAGE_LOCATION_FIELDS, MESSAGE_LOCATION_META)
}
func dropMessagesIf(params *map[string]interface{}, checks *map[*vm.Program]struct{}) (bool, error) {
for d := range *checks {
value, err := expr.Run(d, *params)
if err != nil {
return false, fmt.Errorf("failed to evaluate: %v", err.Error())
}
if value.(bool) {
return true, nil
}
}
return false, nil
}
func normalizeUnits(message lp2.CCMessage) (bool, error) {
if in_unit, ok := message.GetMeta("unit"); ok {
u := units.NewUnit(in_unit)
if u.Valid() {
//cclog.ComponentDebug("MessageProcessor", "Update unit with", u.Short())
message.AddMeta("unit", u.Short())
}
} else if in_unit, ok := message.GetTag("unit"); ok {
u := units.NewUnit(in_unit)
if u.Valid() {
//cclog.ComponentDebug("MessageProcessor", "Update unit with", u.Short())
message.AddTag("unit", u.Short())
}
}
return false, nil
}
func changeUnitPrefix(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]string) (bool, error) {
for r, n := range *checks {
value, err := expr.Run(r, *params)
if err != nil {
return false, fmt.Errorf("failed to evaluate: %v", err.Error())
}
if value.(bool) {
newPrefix := units.NewPrefix(n)
//cclog.ComponentDebug("MessageProcessor", "Condition matches, change to prefix", newPrefix.String())
if in_unit, ok := message.GetMeta("unit"); ok && newPrefix != units.InvalidPrefix {
u := units.NewUnit(in_unit)
if u.Valid() {
//cclog.ComponentDebug("MessageProcessor", "Input unit", u.Short())
conv, out_unit := units.GetUnitPrefixFactor(u, newPrefix)
if conv != nil && out_unit.Valid() {
if val, ok := message.GetField("value"); ok {
//cclog.ComponentDebug("MessageProcessor", "Update unit with", out_unit.Short())
message.AddField("value", conv(val))
message.AddMeta("unit", out_unit.Short())
}
}
}
} else if in_unit, ok := message.GetTag("unit"); ok && newPrefix != units.InvalidPrefix {
u := units.NewUnit(in_unit)
if u.Valid() {
//cclog.ComponentDebug("MessageProcessor", "Input unit", u.Short())
conv, out_unit := units.GetUnitPrefixFactor(u, newPrefix)
if conv != nil && out_unit.Valid() {
if val, ok := message.GetField("value"); ok {
//cclog.ComponentDebug("MessageProcessor", "Update unit with", out_unit.Short())
message.AddField("value", conv(val))
message.AddTag("unit", out_unit.Short())
}
}
}
}
}
}
return false, nil
}
func renameMessagesIf(message lp2.CCMessage, params *map[string]interface{}, checks *map[*vm.Program]string) (bool, error) {
for d, n := range *checks {
value, err := expr.Run(d, *params)
if err != nil {
return true, fmt.Errorf("failed to evaluate: %v", err.Error())
}
if value.(bool) {
old := message.Name()
//cclog.ComponentDebug("MessageProcessor", "Rename to", n)
message.SetName(n)
//cclog.ComponentDebug("MessageProcessor", "Add old name as 'oldname' to meta", old)
message.AddMeta("oldname", old)
}
}
return false, nil
}

View File

@@ -1,396 +0,0 @@
package messageprocessor
import (
"encoding/json"
"errors"
"fmt"
"testing"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
func generate_message_lists(num_lists, num_entries int) ([][]lp.CCMessage, error) {
mlist := make([][]lp.CCMessage, 0)
for j := 0; j < num_lists; j++ {
out := make([]lp.CCMessage, 0)
for i := 0; i < num_entries; i++ {
var x lp.CCMessage
var err error = nil
switch {
case i%4 == 0:
x, err = lp.NewEvent("myevent", map[string]string{"type": "socket", "type-id": "0"}, map[string]string{}, "nothing happend", time.Now())
case i%4 == 1:
x, err = lp.NewMetric("mymetric", map[string]string{"type": "socket", "type-id": "0"}, map[string]string{"unit": "kByte"}, 12.145, time.Now())
case i%4 == 2:
x, err = lp.NewLog("mylog", map[string]string{"type": "socket", "type-id": "0"}, map[string]string{}, "disk status: OK", time.Now())
case i%4 == 3:
x, err = lp.NewGetControl("mycontrol", map[string]string{"type": "socket", "type-id": "0"}, map[string]string{}, time.Now())
}
if err == nil {
x.AddTag("hostname", "myhost")
out = append(out, x)
} else {
return nil, errors.New("failed to create message")
}
}
mlist = append(mlist, out)
}
return mlist, nil
}
func TestNewMessageProcessor(t *testing.T) {
_, err := NewMessageProcessor()
if err != nil {
t.Error(err.Error())
}
}
type Configs struct {
name string
config json.RawMessage
drop bool
errors bool
pre func(msg lp.CCMessage) error
check func(msg lp.CCMessage) error
}
var test_configs = []Configs{
{
name: "single_dropif_nomatch",
config: json.RawMessage(`{"drop_messages_if": [ "name == 'testname' && tags.type == 'socket' && tags.typeid % 2 == 1"]}`),
},
{
name: "drop_by_name",
config: json.RawMessage(`{"drop_messages": [ "net_bytes_in"]}`),
drop: true,
},
{
name: "drop_by_type_match",
config: json.RawMessage(`{"drop_by_message_type": [ "metric"]}`),
drop: true,
},
{
name: "drop_by_type_nomatch",
config: json.RawMessage(`{"drop_by_message_type": [ "event"]}`),
},
{
name: "single_dropif_match",
config: json.RawMessage(`{"drop_messages_if": [ "name == 'net_bytes_in' && tags.type == 'node'"]}`),
drop: true,
},
{
name: "double_dropif_match_nomatch",
config: json.RawMessage(`{"drop_messages_if": [ "name == 'net_bytes_in' && tags.type == 'node'", "name == 'testname' && tags.type == 'socket' && tags.typeid % 2 == 1"]}`),
drop: true,
},
{
name: "rename_simple",
config: json.RawMessage(`{"rename_messages": { "net_bytes_in" : "net_bytes_out", "rapl_power": "cpu_power"}}`),
check: func(msg lp.CCMessage) error {
if msg.Name() != "net_bytes_out" {
return errors.New("expected name net_bytes_out but still have net_bytes_in")
}
return nil
},
},
{
name: "rename_match",
config: json.RawMessage(`{"rename_messages_if": { "name == 'net_bytes_in'" : "net_bytes_out", "name == 'rapl_power'": "cpu_power"}}`),
check: func(msg lp.CCMessage) error {
if msg.Name() != "net_bytes_out" {
return errors.New("expected name net_bytes_out but still have net_bytes_in")
}
return nil
},
},
{
name: "rename_nomatch",
config: json.RawMessage(`{"rename_messages_if": { "name == 'net_bytes_out'" : "net_bytes_in", "name == 'rapl_power'": "cpu_power"}}`),
check: func(msg lp.CCMessage) error {
if msg.Name() != "net_bytes_in" {
return errors.New("expected name net_bytes_in but still have net_bytes_out")
}
return nil
},
},
{
name: "add_tag",
config: json.RawMessage(`{"add_tags_if": [{"if": "name == 'net_bytes_in'", "key" : "cluster", "value" : "mycluster"}]}`),
check: func(msg lp.CCMessage) error {
if !msg.HasTag("cluster") {
return errors.New("expected new tag 'cluster' but not present")
}
return nil
},
},
{
name: "del_tag",
config: json.RawMessage(`{"delete_tags_if": [{"if": "name == 'net_bytes_in'", "key" : "type"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasTag("type") {
return errors.New("expected to have no 'type' but still present")
}
return nil
},
},
{
name: "add_meta",
config: json.RawMessage(`{"add_meta_if": [{"if": "name == 'net_bytes_in'", "key" : "source", "value" : "example"}]}`),
check: func(msg lp.CCMessage) error {
if !msg.HasMeta("source") {
return errors.New("expected new tag 'source' but not present")
}
return nil
},
},
{
name: "del_meta",
config: json.RawMessage(`{"delete_meta_if": [{"if": "name == 'net_bytes_in'", "key" : "unit"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasMeta("unit") {
return errors.New("expected to have no 'unit' but still present")
}
return nil
},
},
{
name: "add_field",
config: json.RawMessage(`{"add_fields_if": [{"if": "name == 'net_bytes_in'", "key" : "myfield", "value" : "example"}]}`),
check: func(msg lp.CCMessage) error {
if !msg.HasField("myfield") {
return errors.New("expected new tag 'source' but not present")
}
return nil
},
},
{
name: "delete_fields_if_protected",
config: json.RawMessage(`{"delete_fields_if": [{"if": "name == 'net_bytes_in'", "key" : "value"}]}`),
errors: true,
check: func(msg lp.CCMessage) error {
if !msg.HasField("value") {
return errors.New("expected to still have 'value' field because it is a protected field key")
}
return nil
},
},
{
name: "delete_fields_if_unprotected",
config: json.RawMessage(`{"delete_fields_if": [{"if": "name == 'net_bytes_in'", "key" : "testfield"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasField("testfield") {
return errors.New("expected to still have 'testfield' field but should be deleted")
}
return nil
},
pre: func(msg lp.CCMessage) error {
msg.AddField("testfield", 4.123)
return nil
},
},
{
name: "single_change_prefix_match",
config: json.RawMessage(`{"change_unit_prefix": {"name == 'net_bytes_in' && tags.type == 'node'": "M"}}`),
check: func(msg lp.CCMessage) error {
if u, ok := msg.GetMeta("unit"); ok {
if u != "MB" {
return fmt.Errorf("expected unit MB but have %s", u)
}
} else if u, ok := msg.GetTag("unit"); ok {
if u != "MB" {
return fmt.Errorf("expected unit MB but have %s", u)
}
}
return nil
},
},
{
name: "normalize_units",
config: json.RawMessage(`{"normalize_units": true}`),
check: func(msg lp.CCMessage) error {
if u, ok := msg.GetMeta("unit"); ok {
if u != "B" {
return fmt.Errorf("expected unit B but have %s", u)
}
} else if u, ok := msg.GetTag("unit"); ok {
if u != "B" {
return fmt.Errorf("expected unit B but have %s", u)
}
}
return nil
},
},
{
name: "move_tag_to_meta",
config: json.RawMessage(`{"move_tag_to_meta_if": [{"if": "name == 'net_bytes_in'", "key" : "type-id", "value": "typeid"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasTag("type-id") || !msg.HasMeta("typeid") {
return errors.New("moving tag 'type-id' to meta 'typeid' failed")
}
return nil
},
pre: func(msg lp.CCMessage) error {
msg.AddTag("type-id", "0")
return nil
},
},
{
name: "move_tag_to_field",
config: json.RawMessage(`{"move_tag_to_field_if": [{"if": "name == 'net_bytes_in'", "key" : "type-id", "value": "typeid"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasTag("type-id") || !msg.HasField("typeid") {
return errors.New("moving tag 'type-id' to field 'typeid' failed")
}
return nil
},
pre: func(msg lp.CCMessage) error {
msg.AddTag("type-id", "0")
return nil
},
},
{
name: "move_meta_to_tag",
config: json.RawMessage(`{"move_meta_to_tag_if": [{"if": "name == 'net_bytes_in'", "key" : "unit", "value": "unit"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasMeta("unit") || !msg.HasTag("unit") {
return errors.New("moving meta 'unit' to tag 'unit' failed")
}
return nil
},
},
{
name: "move_meta_to_field",
config: json.RawMessage(`{"move_meta_to_field_if": [{"if": "name == 'net_bytes_in'", "key" : "unit", "value": "unit"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasMeta("unit") || !msg.HasField("unit") {
return errors.New("moving meta 'unit' to field 'unit' failed")
}
return nil
},
},
{
name: "move_field_to_tag",
config: json.RawMessage(`{"move_field_to_tag_if": [{"if": "name == 'net_bytes_in'", "key" : "myfield", "value": "field"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasField("myfield") || !msg.HasTag("field") {
return errors.New("moving meta 'myfield' to tag 'field' failed")
}
return nil
},
pre: func(msg lp.CCMessage) error {
msg.AddField("myfield", 12)
return nil
},
},
{
name: "move_field_to_meta",
config: json.RawMessage(`{"move_field_to_meta_if": [{"if": "name == 'net_bytes_in'", "key" : "myfield", "value": "field"}]}`),
check: func(msg lp.CCMessage) error {
if msg.HasField("myfield") || !msg.HasMeta("field") {
return errors.New("moving meta 'myfield' to meta 'field' failed")
}
return nil
},
pre: func(msg lp.CCMessage) error {
msg.AddField("myfield", 12)
return nil
},
},
}
func TestConfigList(t *testing.T) {
for _, c := range test_configs {
t.Run(c.name, func(t *testing.T) {
m, err := lp.NewMetric("net_bytes_in", map[string]string{"type": "node", "type-id": "0"}, map[string]string{"unit": "Byte"}, float64(1024.0), time.Now())
if err != nil {
t.Error(err.Error())
return
}
if c.pre != nil {
if err = c.pre(m); err != nil {
t.Errorf("error running pre-test function: %v", err.Error())
return
}
}
mp, err := NewMessageProcessor()
if err != nil {
t.Error(err.Error())
return
}
err = mp.FromConfigJSON(c.config)
if err != nil {
t.Error(err.Error())
return
}
//t.Log(m.ToLineProtocol(nil))
out, err := mp.ProcessMessage(m)
if err != nil && !c.errors {
cclog.SetDebug()
mp.ProcessMessage(m)
t.Error(err.Error())
return
}
if out == nil && !c.drop {
t.Error("fail, message should NOT be dropped but processor signalled dropping")
return
} else if out != nil && c.drop {
t.Error("fail, message should be dropped but processor signalled NO dropping")
return
}
// {
// if c.drop {
// t.Error("fail, message should be dropped but processor signalled NO dropping")
// } else {
// t.Error("fail, message should NOT be dropped but processor signalled dropping")
// }
// cclog.SetDebug()
// mp.ProcessMessage(m)
// return
// }
if c.check != nil {
if err := c.check(out); err != nil {
t.Errorf("check failed with %v", err.Error())
t.Log("Rerun with debugging")
cclog.SetDebug()
mp.ProcessMessage(m)
return
}
}
})
}
}
func BenchmarkProcessing(b *testing.B) {
mlist, err := generate_message_lists(b.N, 1000)
if err != nil {
b.Error(err.Error())
return
}
mp, err := NewMessageProcessor()
if err != nil {
b.Error(err.Error())
return
}
err = mp.FromConfigJSON(json.RawMessage(`{"move_meta_to_tag_if": [{"if" : "name == 'mymetric'", "key":"unit", "value":"unit"}]}`))
if err != nil {
b.Error(err.Error())
return
}
b.StartTimer()
for i := 0; i < b.N; i++ {
for _, m := range mlist[i] {
if _, err := mp.ProcessMessage(m); err != nil {
b.Errorf("failed processing message '%s': %v", m.ToLineProtocol(nil), err.Error())
return
}
}
}
b.StopTimer()
b.ReportMetric(float64(b.Elapsed())/float64(len(mlist)*b.N), "ns/message")
}

View File

@@ -10,15 +10,15 @@ import (
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
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 {
defaultReceiverConfig
Type string `json:"type"`
Addr string `json:"address"`
Port string `json:"port"`
Path string `json:"path"`
@@ -39,7 +39,7 @@ type HttpReceiverConfig struct {
type HttpReceiver struct {
receiver
//meta map[string]string
meta map[string]string
config HttpReceiverConfig
server *http.Server
wg sync.WaitGroup
@@ -85,20 +85,8 @@ func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
if r.config.useBasicAuth && len(r.config.Password) == 0 {
return errors.New("basic authentication requires password")
}
msgp, err := mp.NewMessageProcessor()
if err != nil {
return fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
r.mp = msgp
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())
}
}
r.mp.AddAddMetaByCondition("true", "source", r.name)
//r.meta = map[string]string{"source": r.name}
r.meta = map[string]string{"source": r.name}
p := r.config.Path
if !strings.HasPrefix(p, "/") {
p = "/" + p
@@ -149,24 +137,80 @@ func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
return
}
}
if r.sink != nil {
buf := make([]byte, 0, req.ContentLength)
len, err := req.Body.Read(buf)
if err == nil && len > 0 {
messages, err := lp.FromBytes(buf)
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 messages: " + err.Error()
msg := "ServerHttp: Failed to decode tag: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
for _, y := range messages {
m, err := r.mp.ProcessMessage(y)
if err == nil && m != nil {
r.sink <- m
}
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)

View File

@@ -13,10 +13,9 @@ import (
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
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"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
)
type IPMIReceiverClientConfig struct {
@@ -32,13 +31,11 @@ type IPMIReceiverClientConfig struct {
Password string // Password to use for authentication
CLIOptions []string // Additional command line options for ipmi-sensors
isExcluded map[string]bool // is metric excluded
mp mp.MessageProcessor
}
type IPMIReceiver struct {
receiver
config struct {
defaultReceiverConfig
Interval time.Duration
// Client config for each IPMI hosts
@@ -46,11 +43,10 @@ type IPMIReceiver struct {
}
// Storage for static information
//meta map[string]string
meta map[string]string
done chan bool // channel to finish / stop IPMI receiver
wg sync.WaitGroup // wait group for IPMI receiver
mp mp.MessageProcessor
}
// doReadMetrics reads metrics from all configure IPMI hosts.
@@ -217,7 +213,7 @@ func (r *IPMIReceiver) doReadMetric() {
continue
}
y, err := lp.NewMessage(
y, err := lp.New(
metric,
map[string]string{
"hostname": host,
@@ -234,14 +230,7 @@ func (r *IPMIReceiver) doReadMetric() {
},
time.Now())
if err == nil {
mc, err := clientConfig.mp.ProcessMessage(y)
if err == nil && mc != nil {
m, err := r.mp.ProcessMessage(mc)
if err == nil && m != nil {
r.sink <- m
}
}
r.sink <- y
}
}
@@ -307,12 +296,11 @@ func (r *IPMIReceiver) Close() {
// 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) {
var err error
r := new(IPMIReceiver)
// Config options from config file
configJSON := struct {
defaultReceiverConfig
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"`
@@ -343,8 +331,7 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
// Additional command line options for ipmi-sensors
CLIOptions []string `json:"cli_options,omitempty"`
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
CLIOptions []string `json:"cli_options,omitempty"`
} `json:"client_config"`
}{
// Set defaults values
@@ -360,15 +347,8 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
// Create done channel
r.done = make(chan bool)
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
r.mp = p
// Set static information
//r.meta = map[string]string{"source": r.name}
r.mp.AddAddMetaByCondition("true", "source", r.name)
r.meta = map[string]string{"source": r.name}
// Read the IPMI receiver specific JSON config
if len(config) > 0 {
@@ -380,18 +360,12 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
}
}
if len(r.config.MessageProcessor) > 0 {
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// 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",
"Failed to parse duration string interval='%s': %w",
configJSON.IntervalString,
err,
)
@@ -532,16 +506,6 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
for _, key := range configJSON.ExcludeMetrics {
isExcluded[key] = true
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
if len(clientConfigJSON.MessageProcessor) > 0 {
err = p.FromConfigJSON(clientConfigJSON.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
r.config.ClientConfigs = append(
r.config.ClientConfigs,
@@ -556,7 +520,6 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
Password: password,
CLIOptions: cliOptions,
isExcluded: isExcluded,
mp: p,
})
}

View File

@@ -1,15 +1,11 @@
package receivers
import (
"encoding/json"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type defaultReceiverConfig struct {
Type string `json:"type"`
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
Type string `json:"type"`
}
// Receiver configuration: Listen address, port
@@ -23,15 +19,14 @@ type ReceiverConfig struct {
type receiver struct {
name string
sink chan lp.CCMessage
mp mp.MessageProcessor
sink chan lp.CCMetric
}
type Receiver interface {
Start()
Close() // Close / finish metric receiver
Name() string // Name of the metric receiver
SetSink(sink chan lp.CCMessage) // Set sink channel
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
@@ -40,6 +35,6 @@ func (r *receiver) Name() string {
}
// SetSink set the sink channel
func (r *receiver) SetSink(sink chan lp.CCMessage) {
func (r *receiver) SetSink(sink chan lp.CCMetric) {
r.sink = sink
}

View File

@@ -4,28 +4,25 @@ import (
"encoding/json"
"errors"
"fmt"
"os"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
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 {
defaultReceiverConfig
Addr string `json:"address"`
Port string `json:"port"`
Subject string `json:"subject"`
User string `json:"user,omitempty"`
Password string `json:"password,omitempty"`
NkeyFile string `json:"nkey_file,omitempty"`
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
nc *nats.Conn
meta map[string]string
config NatsReceiverConfig
}
@@ -39,17 +36,65 @@ func (r *NatsReceiver) Start() {
// _NatsReceive receives subscribed messages from the NATS server
func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
if r.sink != nil {
messages, err := lp.FromBytes(m.Data)
d := influx.NewDecoderWithBytes(m.Data)
for d.Next() {
// Decode measurement name
measurement, err := d.Measurement()
if err != nil {
msg := "_NatsReceive: Failed to decode messages: " + err.Error()
msg := "_NatsReceive: Failed to decode measurement: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
for _, y := range messages {
m, err := r.mp.ProcessMessage(y)
if err == nil && m != nil && r.sink != nil {
r.sink <- m
// 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
}
}
}
@@ -64,7 +109,6 @@ func (r *NatsReceiver) Close() {
// NewNatsReceiver creates a new Receiver which subscribes to messages from a NATS server
func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
var uinfo nats.Option = nil
r := new(NatsReceiver)
r.name = fmt.Sprintf("NatsReceiver(%s)", name)
@@ -83,40 +127,16 @@ func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
len(r.config.Subject) == 0 {
return nil, errors.New("not all configuration variables set required by NatsReceiver")
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, 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 nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// Set metadata
// r.meta = map[string]string{
// "source": r.name,
// }
r.mp.AddAddMetaByCondition("true", "source", r.name)
if len(r.config.User) > 0 && len(r.config.Password) > 0 {
uinfo = nats.UserInfo(r.config.User, r.config.Password)
} else if len(r.config.NkeyFile) > 0 {
_, err := os.Stat(r.config.NkeyFile)
if err == nil {
uinfo = nats.UserCredentials(r.config.NkeyFile)
} else {
cclog.ComponentError(r.name, "NKEY file", r.config.NkeyFile, "does not exist: %v", err.Error())
return nil, err
}
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, uinfo); err == nil {
if nc, err := nats.Connect(url); err == nil {
r.nc = nc
} else {
r.nc = nil

View File

@@ -10,10 +10,7 @@ The `nats` receiver can be used receive metrics from the NATS network. The `nats
"type": "nats",
"address" : "nats-server.example.org",
"port" : "4222",
"subject" : "subject",
"user": "natsuser",
"password": "natssecret",
"nkey_file": "/path/to/nkey_file"
"subject" : "subject"
}
}
```
@@ -22,9 +19,6 @@ The `nats` receiver can be used receive metrics from the NATS network. The `nats
- `address`: Address of the NATS control server
- `port`: Port of the NATS control server
- `subject`: Subscribes to this subject and receive metrics
- `user`: Connect to nats using this user
- `password`: Connect to nats using this password
- `nkey_file`: Path to credentials file with NKEY
### Debugging

View File

@@ -13,7 +13,7 @@ import (
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type PrometheusReceiverConfig struct {
@@ -74,7 +74,7 @@ func (r *PrometheusReceiver) Start() {
}
value, err := strconv.ParseFloat(lineSplit[1], 64)
if err == nil {
y, err := lp.NewMessage(name, tags, r.meta, map[string]interface{}{"value": value}, t)
y, err := lp.New(name, tags, r.meta, map[string]interface{}{"value": value}, t)
if err == nil {
r.sink <- y
}

View File

@@ -7,7 +7,7 @@ import (
"sync"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
@@ -19,14 +19,14 @@ var AvailableReceivers = map[string]func(name string, config json.RawMessage) (R
type receiveManager struct {
inputs []Receiver
output chan lp.CCMessage
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.CCMessage)
AddOutput(output chan lp.CCMetric)
Start()
Close()
}
@@ -93,7 +93,7 @@ func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error
return nil
}
func (rm *receiveManager) AddOutput(output chan lp.CCMessage) {
func (rm *receiveManager) AddOutput(output chan lp.CCMetric) {
rm.output = output
for _, r := range rm.inputs {
r.SetSink(rm.output)

View File

@@ -13,10 +13,9 @@ import (
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
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"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
// See: https://pkg.go.dev/github.com/stmcginnis/gofish
"github.com/stmcginnis/gofish"
@@ -43,8 +42,6 @@ type RedfishReceiverClientConfig struct {
readSensorURLs map[string][]string
gofish gofish.ClientConfig
mp mp.MessageProcessor
}
// RedfishReceiver configuration:
@@ -52,7 +49,6 @@ type RedfishReceiver struct {
receiver
config struct {
defaultReceiverConfig
fanout int
Interval time.Duration
HttpTimeout time.Duration
@@ -83,19 +79,13 @@ func setMetricValue(value any) map[string]interface{} {
}
// sendMetric sends the metric through the sink channel
func (r *RedfishReceiver) sendMetric(mp mp.MessageProcessor, name string, tags map[string]string, meta map[string]string, value any, timestamp time.Time) {
func (r *RedfishReceiver) sendMetric(name string, tags map[string]string, meta map[string]string, value any, timestamp time.Time) {
deleteEmptyTags(tags)
deleteEmptyTags(meta)
y, err := lp.NewMessage(name, tags, meta, setMetricValue(value), timestamp)
y, err := lp.New(name, tags, meta, setMetricValue(value), timestamp)
if err == nil {
mc, err := mp.ProcessMessage(y)
if err == nil && mc != nil {
m, err := r.mp.ProcessMessage(mc)
if err == nil && m != nil {
r.sink <- m
}
}
r.sink <- y
}
}
@@ -129,7 +119,7 @@ func (r *RedfishReceiver) readSensors(
"unit": "degC",
}
r.sendMetric(clientConfig.mp, "temperature", tags, meta, sensor.Reading, time.Now())
r.sendMetric("temperature", tags, meta, sensor.Reading, time.Now())
}
writeFanSpeedSensor := func(sensor *redfish.Sensor) {
@@ -155,7 +145,7 @@ func (r *RedfishReceiver) readSensors(
"unit": string(sensor.ReadingUnits),
}
r.sendMetric(clientConfig.mp, "fan_speed", tags, meta, sensor.Reading, time.Now())
r.sendMetric("fan_speed", tags, meta, sensor.Reading, time.Now())
}
writePowerSensor := func(sensor *redfish.Sensor) {
@@ -182,7 +172,7 @@ func (r *RedfishReceiver) readSensors(
"unit": "watts",
}
r.sendMetric(clientConfig.mp, "power", tags, meta, sensor.Reading, time.Now())
r.sendMetric("power", tags, meta, sensor.Reading, time.Now())
}
if _, ok := clientConfig.readSensorURLs[chassis.ID]; !ok {
@@ -350,7 +340,7 @@ func (r *RedfishReceiver) readThermalMetrics(
// ReadingCelsius shall be the current value of the temperature sensor's reading.
value := temperature.ReadingCelsius
r.sendMetric(clientConfig.mp, "temperature", tags, meta, value, timestamp)
r.sendMetric("temperature", tags, meta, value, timestamp)
}
for _, fan := range thermal.Fans {
@@ -391,7 +381,7 @@ func (r *RedfishReceiver) readThermalMetrics(
"unit": string(fan.ReadingUnits),
}
r.sendMetric(clientConfig.mp, "fan_speed", tags, meta, fan.Reading, timestamp)
r.sendMetric("fan_speed", tags, meta, fan.Reading, timestamp)
}
return nil
@@ -489,7 +479,7 @@ func (r *RedfishReceiver) readPowerMetrics(
}
for name, value := range metrics {
r.sendMetric(clientConfig.mp, name, tags, meta, value, timestamp)
r.sendMetric(name, tags, meta, value, timestamp)
}
}
@@ -571,7 +561,7 @@ func (r *RedfishReceiver) readProcessorMetrics(
if !clientConfig.isExcluded[namePower] &&
// Some servers return "ConsumedPowerWatt":65535 instead of "ConsumedPowerWatt":null
processorMetrics.ConsumedPowerWatt != 65535 {
r.sendMetric(clientConfig.mp, namePower, tags, metaPower, processorMetrics.ConsumedPowerWatt, timestamp)
r.sendMetric(namePower, tags, metaPower, processorMetrics.ConsumedPowerWatt, timestamp)
}
// Set meta data tags
metaThermal := map[string]string{
@@ -583,7 +573,7 @@ func (r *RedfishReceiver) readProcessorMetrics(
nameThermal := "temperature"
if !clientConfig.isExcluded[nameThermal] {
r.sendMetric(clientConfig.mp, nameThermal, tags, metaThermal, processorMetrics.TemperatureCelsius, timestamp)
r.sendMetric(nameThermal, tags, metaThermal, processorMetrics.TemperatureCelsius, timestamp)
}
return nil
}
@@ -786,13 +776,11 @@ func (r *RedfishReceiver) Close() {
// 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) {
var err error
r := new(RedfishReceiver)
// Config options from config file
configJSON := struct {
Type string `json:"type"`
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
Type string `json:"type"`
// Maximum number of simultaneous redfish connections (default: 64)
Fanout int `json:"fanout,omitempty"`
@@ -832,8 +820,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
DisableThermalMetrics bool `json:"disable_thermal_metrics"`
// Per client excluded metrics
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
} `json:"client_config"`
}{
// Set defaults values
@@ -859,24 +846,13 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
return nil, err
}
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, 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 nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// 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",
"Failed to parse duration string interval='%s': %w",
configJSON.IntervalString,
err,
)
@@ -888,7 +864,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
r.config.HttpTimeout, err = time.ParseDuration(configJSON.HttpTimeoutString)
if err != nil {
err := fmt.Errorf(
"failed to parse duration string http_timeout='%s': %w",
"Failed to parse duration string http_timeout='%s': %w",
configJSON.HttpTimeoutString,
err,
)
@@ -972,18 +948,6 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
for _, key := range configJSON.ExcludeMetrics {
isExcluded[key] = true
}
p, err = mp.NewMessageProcessor()
if err != nil {
cclog.ComponentError(r.name, err.Error())
return nil, err
}
if len(clientConfigJSON.MessageProcessor) > 0 {
err = p.FromConfigJSON(clientConfigJSON.MessageProcessor)
if err != nil {
cclog.ComponentError(r.name, err.Error())
return nil, err
}
}
hostList, err := hostlist.Expand(clientConfigJSON.HostList)
if err != nil {
@@ -1014,7 +978,6 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
Endpoint: endpoint,
HTTPClient: httpClient,
},
mp: p,
})
}
@@ -1039,7 +1002,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
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)
err := fmt.Errorf("Found duplicate client config for host %s", host)
cclog.ComponentError(r.name, err)
return nil, err
}

View File

@@ -5,13 +5,11 @@ import (
"fmt"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
)
// SampleReceiver configuration: receiver type, listen address, port
// The defaultReceiverConfig contains the keys 'type' and 'process_messages'
type SampleReceiverConfig struct {
defaultReceiverConfig
Type string `json:"type"`
Addr string `json:"address"`
Port string `json:"port"`
}
@@ -21,6 +19,7 @@ type SampleReceiver struct {
config SampleReceiverConfig
// Storage for static information
meta map[string]string
// Use in case of own go routine
// done chan bool
// wg sync.WaitGroup
@@ -80,19 +79,8 @@ func NewSampleReceiver(name string, config json.RawMessage) (Receiver, error) {
// The name should be chosen in such a way that different instances of SampleReceiver can be distinguished
r.name = fmt.Sprintf("SampleReceiver(%s)", name)
// create new message processor
p, err := mp.NewMessageProcessor()
if err != nil {
cclog.ComponentError(r.name, "Initialization of message processor failed:", err.Error())
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
r.mp = p
// Set static information
err = r.mp.AddAddMetaByCondition("true", "source", r.name)
if err != nil {
cclog.ComponentError(r.name, fmt.Sprintf("Failed to add static information source=%s:", r.name), err.Error())
return nil, fmt.Errorf("failed to add static information source=%s: %v", r.name, err.Error())
}
r.meta = map[string]string{"source": r.name}
// Set defaults in r.config
// Allow overwriting these defaults by reading config JSON
@@ -106,15 +94,6 @@ func NewSampleReceiver(name string, config json.RawMessage) (Receiver, error) {
}
}
// Add message processor config
if len(r.config.MessageProcessor) > 0 {
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
if err != nil {
cclog.ComponentError(r.name, "Failed parsing JSON for message processor:", err.Error())
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// Check that all required fields in the configuration are set
// Use 'if len(r.config.Option) > 0' for strings

View File

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

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

View File

@@ -17,7 +17,7 @@ This folder contains the SinkManager and sink implementations for the cc-metric-
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" : [
@@ -31,7 +31,7 @@ The configuration file for the sinks is a list of configurations. The `type` fie
"database" : "ccmetric",
"password" : "<jwt token>"
}
}
]
```

View File

@@ -4,10 +4,10 @@ import (
"fmt"
"strings"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
func GangliaMetricName(point lp.CCMessage) string {
func GangliaMetricName(point lp.CCMetric) string {
name := point.Name()
metricType, typeOK := point.GetTag("type")
metricTid, tidOk := point.GetTag("type-id")
@@ -39,7 +39,7 @@ func GangliaMetricRename(name string) string {
return name
}
func GangliaSlopeType(point lp.CCMessage) uint {
func GangliaSlopeType(point lp.CCMetric) uint {
name := point.Name()
if name == "mem_total" || name == "swap_total" {
return 0
@@ -151,7 +151,7 @@ type GangliaMetricConfig struct {
Name string
}
func GetCommonGangliaConfig(point lp.CCMessage) GangliaMetricConfig {
func GetCommonGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
mname := GangliaMetricRename(point.Name())
if oldname, ok := point.GetMeta("oldname"); ok {
mname = GangliaMetricRename(oldname)
@@ -207,7 +207,7 @@ func GetCommonGangliaConfig(point lp.CCMessage) GangliaMetricConfig {
}
}
func GetGangliaConfig(point lp.CCMessage) GangliaMetricConfig {
func GetGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
mname := GangliaMetricRename(point.Name())
if oldname, ok := point.GetMeta("oldname"); ok {
mname = GangliaMetricRename(oldname)

View File

@@ -10,9 +10,8 @@ import (
// "time"
"os/exec"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const GMETRIC_EXEC = `gmetric`
@@ -36,53 +35,50 @@ type GangliaSink struct {
config GangliaSinkConfig
}
func (s *GangliaSink) Write(msg lp.CCMessage) error {
func (s *GangliaSink) Write(point lp.CCMetric) error {
var err error = nil
//var tagsstr []string
var argstr []string
point, err := s.mp.ProcessMessage(msg)
if err == nil && point != nil {
// 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()
// 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
}
@@ -108,13 +104,6 @@ func NewGangliaSink(name string, config json.RawMessage) (Sink, error) {
}
s.gmetric_path = ""
s.gmetric_config = ""
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
if len(s.config.GmetricPath) > 0 {
p, err := exec.LookPath(s.config.GmetricPath)
if err == nil {
@@ -133,15 +122,5 @@ func NewGangliaSink(name string, config json.RawMessage) (Sink, error) {
if len(s.config.GmetricConfig) > 0 {
s.gmetric_config = s.config.GmetricConfig
}
if len(s.config.MessageProcessor) > 0 {
err = s.mp.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
}
return s, nil
}

View File

@@ -8,18 +8,14 @@ The `ganglia` sink uses the `gmetric` tool of the [Ganglia Monitoring System](ht
{
"<name>": {
"type": "ganglia",
"meta_as_tags" : true,
"gmetric_path" : "/path/to/gmetric",
"add_ganglia_group" : true,
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"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.
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)
- `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.

View File

@@ -9,9 +9,8 @@ import (
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
"golang.org/x/exp/slices"
)
@@ -51,12 +50,18 @@ type HttpSinkConfig struct {
Precision string `json:"precision,omitempty"`
}
type key_value_pair struct {
key string
value string
}
type HttpSink struct {
sink
client *http.Client
// influx line protocol encoder
encoder influx.Encoder
// List of tags and meta data tags which should be used as tags
extended_tag_list []key_value_pair
// Flush() runs in another goroutine and accesses the influx line protocol encoder,
// so this encoderLock has to protect the encoder
encoderLock sync.Mutex
@@ -70,25 +75,78 @@ type HttpSink struct {
}
// Write sends metric m as http message
func (s *HttpSink) Write(msg lp.CCMessage) error {
func (s *HttpSink) Write(m lp.CCMetric) error {
// submit m only after applying processing/dropping rules
m, err := s.mp.ProcessMessage(msg)
if err == nil && m != nil {
// Lock for encoder usage
s.encoderLock.Lock()
// Lock for encoder usage
s.encoderLock.Lock()
err = EncoderAdd(&s.encoder, m)
// Encode measurement name
s.encoder.StartLine(m.Name())
// Unlock encoder usage
s.encoderLock.Unlock()
// Check that encoding worked
if err != nil {
return fmt.Errorf("encoding failed: %v", err)
// copy tags and meta data which should be used as tags
s.extended_tag_list = s.extended_tag_list[:0]
for key, value := range m.Tags() {
s.extended_tag_list =
append(
s.extended_tag_list,
key_value_pair{
key: key,
value: value,
},
)
}
for _, key := range s.config.MetaAsTags {
if value, ok := m.GetMeta(key); ok {
s.extended_tag_list =
append(
s.extended_tag_list,
key_value_pair{
key: key,
value: value,
},
)
}
}
// Encode tags (they musts be in lexical order)
slices.SortFunc(
s.extended_tag_list,
func(a key_value_pair, b key_value_pair) int {
if a.key < b.key {
return -1
}
if a.key > b.key {
return +1
}
return 0
},
)
for i := range s.extended_tag_list {
s.encoder.AddTag(
s.extended_tag_list[i].key,
s.extended_tag_list[i].value,
)
}
// Encode fields
for key, value := range m.Fields() {
s.encoder.AddField(key, influx.MustNewValue(value))
}
// Encode time stamp
s.encoder.EndLine(m.Time())
// Check for encoder errors
err := s.encoder.Err()
// Unlock encoder usage
s.encoderLock.Unlock()
// Check that encoding worked
if err != nil {
return fmt.Errorf("encoding failed: %v", err)
}
if s.config.flushDelay == 0 {
// Directly flush if no flush delay is configured
@@ -213,7 +271,7 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
s.config.Timeout = "5s"
s.config.FlushDelay = "5s"
s.config.MaxRetries = 3
s.config.Precision = "s"
s.config.Precision = "ns"
cclog.ComponentDebug(s.name, "Init()")
// Read config
@@ -239,11 +297,6 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
if s.config.useBasicAuth && len(s.config.Password) == 0 {
return nil, errors.New("basic authentication requires password")
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
if len(s.config.IdleConnTimeout) > 0 {
t, err := time.ParseDuration(s.config.IdleConnTimeout)
@@ -266,17 +319,7 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
cclog.ComponentDebug(s.name, "Init(): flushDelay", t)
}
}
if len(s.config.MessageProcessor) > 0 {
err = p.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
}
precision := influx.Second
precision := influx.Nanosecond
if len(s.config.Precision) > 0 {
switch s.config.Precision {
case "s":
@@ -301,6 +344,7 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
// Configure influx line protocol encoder
s.encoder.SetPrecision(precision)
s.extended_tag_list = make([]key_value_pair, 0)
return s, nil
}

View File

@@ -8,6 +8,9 @@ The `http` sink uses POST requests to a HTTP server to submit the metrics in the
{
"<name>": {
"type": "http",
"meta_as_tags" : [
"meta-key"
],
"url" : "https://my-monitoring.example.com:1234/api/write",
"jwt" : "blabla.blabla.blabla",
"username": "myUser",
@@ -16,16 +19,13 @@ The `http` sink uses POST requests to a HTTP server to submit the metrics in the
"idle_connection_timeout" : "5s",
"flush_delay": "2s",
"batch_size": 1000,
"precision": "s",
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"precision": "s"
}
}
```
- `type`: makes the sink an `http` sink
- `meta_as_tags`: Move specific meta information to the tags in the output (optional)
- `url`: The full URL of the endpoint
- `jwt`: JSON web tokens for authentication (Using the *Bearer* scheme)
- `username`: username for basic authentication
@@ -35,10 +35,8 @@ The `http` sink uses POST requests to a HTTP server to submit the metrics in the
- `idle_connection_timeout`: Timeout for idle connections (default '120s'). Should be larger than the measurement interval to keep the connection open
- `flush_delay`: Batch all writes arriving in during this duration (default '1s', batching can be disabled by setting it to 0)
- `batch_size`: Maximal batch size. If `batch_size` is reached before the end of `flush_delay`, the metrics are sent without further delay
- `precision`: Precision of the timestamp. Valid values are 's', 'ms', 'us' and 'ns'. (default is 's')
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)
- `precision`: Precision of the timestamp. Valid values are 's', 'ms', 'us' and 'ns'. (default is 'ns')
### Using `http` sink for communication with cc-metric-store
### Using HttpSink for communication with cc-metric-store
The cc-metric-store only accepts metrics with a timestamp precision in seconds, so it is required to use `"precision": "s"`.
The cc-metric-store only accepts metrics with a timestamp precision in seconds, so it is required to set `"precision": "s"`.

View File

@@ -10,9 +10,8 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influxdb2 "github.com/influxdata/influxdb-client-go/v2"
influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
influxdb2ApiHttp "github.com/influxdata/influxdb-client-go/v2/api/http"
@@ -37,8 +36,6 @@ type InfluxAsyncSinkConfig struct {
InfluxMaxRetryTime string `json:"max_retry_time,omitempty"`
CustomFlushInterval string `json:"custom_flush_interval,omitempty"`
MaxRetryAttempts uint `json:"max_retry_attempts,omitempty"`
// Timestamp precision
Precision string `json:"precision,omitempty"`
}
type InfluxAsyncSink struct {
@@ -96,22 +93,7 @@ func (s *InfluxAsyncSink) connect() error {
&tls.Config{
InsecureSkipVerify: true,
},
)
precision := time.Second
if len(s.config.Precision) > 0 {
switch s.config.Precision {
case "s":
precision = time.Second
case "ms":
precision = time.Millisecond
case "us":
precision = time.Microsecond
case "ns":
precision = time.Nanosecond
}
}
clientOptions.SetPrecision(precision)
).SetPrecision(time.Second)
s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
s.writeApi = s.client.WriteAPI(s.config.Organization, s.config.Database)
@@ -130,7 +112,7 @@ func (s *InfluxAsyncSink) connect() error {
return nil
}
func (s *InfluxAsyncSink) Write(m lp.CCMessage) error {
func (s *InfluxAsyncSink) Write(m lp.CCMetric) error {
if s.customFlushInterval != 0 && s.flushTimer == nil {
// Run a batched flush for all lines that have arrived in the defined interval
s.flushTimer = time.AfterFunc(s.customFlushInterval, func() {
@@ -139,10 +121,9 @@ func (s *InfluxAsyncSink) Write(m lp.CCMessage) error {
}
})
}
msg, err := s.mp.ProcessMessage(m)
if err == nil && msg != nil {
s.writeApi.WritePoint(msg.ToPoint(nil))
}
s.writeApi.WritePoint(
m.ToPoint(s.meta_as_tags),
)
return nil
}
@@ -177,7 +158,6 @@ func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
s.config.CustomFlushInterval = ""
s.customFlushInterval = time.Duration(0)
s.config.MaxRetryAttempts = 1
s.config.Precision = "s"
// Default retry intervals (in seconds)
// 1 2
@@ -220,24 +200,10 @@ func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
if len(s.config.Password) == 0 {
return nil, errors.New("missing password configuration required by InfluxSink")
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
if len(s.config.MessageProcessor) > 0 {
err = s.mp.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// Create lookup map to use meta infos as tags in the output metric
// s.meta_as_tags = make(map[string]bool)
// for _, k := range s.config.MetaAsTags {
// s.meta_as_tags[k] = true
// }
s.meta_as_tags = make(map[string]bool)
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
s.meta_as_tags[k] = true
}
toUint := func(duration string, def uint) uint {

View File

@@ -19,13 +19,9 @@ The `influxasync` sink uses the official [InfluxDB golang client](https://pkg.go
"batch_size": 200,
"retry_interval" : "1s",
"retry_exponential_base" : 2,
"precision": "s",
"max_retries": 20,
"max_retry_time" : "168h",
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"meta_as_tags" : [],
}
}
```
@@ -43,12 +39,6 @@ The `influxasync` sink uses the official [InfluxDB golang client](https://pkg.go
- `retry_exponential_base`: The retry interval is exponentially increased with this base, default 2
- `max_retries`: Maximal number of retry attempts
- `max_retry_time`: Maximal time to retry failed writes, default 168h (one week)
- `precision`: Precision of the timestamp. Valid values are 's', 'ms', 'us' and 'ns'. (default is 's')
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)
- `meta_as_tags`: move meta information keys to tags (optional)
For information about the calculation of the retry interval settings, see [offical influxdb-client-go documentation](https://github.com/influxdata/influxdb-client-go#handling-of-failed-async-writes)
### Using `influxasync` sink for communication with cc-metric-store
The cc-metric-store only accepts metrics with a timestamp precision in seconds, so it is required to use `"precision": "s"`.

View File

@@ -10,9 +10,8 @@ import (
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influxdb2 "github.com/influxdata/influxdb-client-go/v2"
influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
@@ -59,8 +58,6 @@ type InfluxSink struct {
InfluxMaxRetryTime string `json:"max_retry_time,omitempty"`
// Specify whether to use GZip compression in write requests
InfluxUseGzip bool `json:"use_gzip"`
// Timestamp precision
Precision string `json:"precision,omitempty"`
}
// influx line protocol encoder
@@ -209,20 +206,7 @@ func (s *InfluxSink) connect() error {
)
// Set time precision
precision := time.Second
if len(s.config.Precision) > 0 {
switch s.config.Precision {
case "s":
precision = time.Second
case "ms":
precision = time.Millisecond
case "us":
precision = time.Microsecond
case "ns":
precision = time.Nanosecond
}
}
clientOptions.SetPrecision(precision)
clientOptions.SetPrecision(time.Nanosecond)
// Create new writeAPI
s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
@@ -240,19 +224,28 @@ func (s *InfluxSink) connect() error {
}
// Write sends metric m in influxDB line protocol
func (s *InfluxSink) Write(msg lp.CCMessage) error {
func (s *InfluxSink) Write(m lp.CCMetric) error {
m, err := s.mp.ProcessMessage(msg)
if err == nil && m != nil {
// Lock for encoder usage
s.encoderLock.Lock()
// Lock for encoder usage
s.encoderLock.Lock()
// Encode measurement name
s.encoder.StartLine(m.Name())
// Encode measurement name
s.encoder.StartLine(m.Name())
// copy tags and meta data which should be used as tags
s.extended_tag_list = s.extended_tag_list[:0]
for key, value := range m.Tags() {
// copy tags and meta data which should be used as tags
s.extended_tag_list = s.extended_tag_list[:0]
for key, value := range m.Tags() {
s.extended_tag_list =
append(
s.extended_tag_list,
key_value_pair{
key: key,
value: value,
},
)
}
for _, key := range s.config.MetaAsTags {
if value, ok := m.GetMeta(key); ok {
s.extended_tag_list =
append(
s.extended_tag_list,
@@ -262,57 +255,45 @@ func (s *InfluxSink) Write(msg lp.CCMessage) error {
},
)
}
// for _, key := range s.config.MetaAsTags {
// if value, ok := m.GetMeta(key); ok {
// s.extended_tag_list =
// append(
// s.extended_tag_list,
// key_value_pair{
// key: key,
// value: value,
// },
// )
// }
// }
// Encode tags (they musts be in lexical order)
slices.SortFunc(
s.extended_tag_list,
func(a key_value_pair, b key_value_pair) int {
if a.key < b.key {
return -1
}
if a.key > b.key {
return +1
}
return 0
},
)
for i := range s.extended_tag_list {
s.encoder.AddTag(
s.extended_tag_list[i].key,
s.extended_tag_list[i].value,
)
}
// Encode fields
for key, value := range m.Fields() {
s.encoder.AddField(key, influx.MustNewValue(value))
}
// Encode time stamp
s.encoder.EndLine(m.Time())
// Check for encoder errors
if err := s.encoder.Err(); err != nil {
// Unlock encoder usage
s.encoderLock.Unlock()
return fmt.Errorf("encoding failed: %v", err)
}
s.numRecordsInEncoder++
}
// Encode tags (they musts be in lexical order)
slices.SortFunc(
s.extended_tag_list,
func(a key_value_pair, b key_value_pair) int {
if a.key < b.key {
return -1
}
if a.key > b.key {
return +1
}
return 0
},
)
for i := range s.extended_tag_list {
s.encoder.AddTag(
s.extended_tag_list[i].key,
s.extended_tag_list[i].value,
)
}
// Encode fields
for key, value := range m.Fields() {
s.encoder.AddField(key, influx.MustNewValue(value))
}
// Encode time stamp
s.encoder.EndLine(m.Time())
// Check for encoder errors
if err := s.encoder.Err(); err != nil {
// Unlock encoder usage
s.encoderLock.Unlock()
return fmt.Errorf("Encoding failed: %v", err)
}
s.numRecordsInEncoder++
if s.config.flushDelay == 0 {
// Unlock encoder usage
s.encoderLock.Unlock()
@@ -436,7 +417,6 @@ func NewInfluxSink(name string, config json.RawMessage) (Sink, error) {
// Set config default values
s.config.BatchSize = 1000
s.config.FlushInterval = "1s"
s.config.Precision = "s"
// Read config
if len(config) > 0 {
@@ -463,20 +443,11 @@ func NewInfluxSink(name string, config json.RawMessage) (Sink, error) {
if len(s.config.Password) == 0 {
return s, errors.New("missing password configuration required by InfluxSink")
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
if len(s.config.MessageProcessor) > 0 {
err = p.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// Create lookup map to use meta infos as tags in the output metric
s.meta_as_tags = make(map[string]bool)
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
s.meta_as_tags[k] = true
}
// Configure flush delay duration

View File

@@ -17,17 +17,14 @@ The `influxdb` sink uses the official [InfluxDB golang client](https://pkg.go.de
"ssl": true,
"flush_delay" : "1s",
"batch_size" : 1000,
"use_gzip": true,
"precision": "s",
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"use_gzip": true
"meta_as_tags" : [],
}
}
```
- `type`: makes the sink an `influxdb` sink
- `meta_as_tags`: print all meta information as tags in the output (optional)
- `database`: All metrics are written to this bucket
- `host`: Hostname of the InfluxDB database server
- `port`: Port number (as string) of the InfluxDB database server
@@ -37,9 +34,6 @@ The `influxdb` sink uses the official [InfluxDB golang client](https://pkg.go.de
- `ssl`: Use SSL connection
- `flush_delay`: Group metrics coming in to a single batch
- `batch_size`: Maximal batch size. If `batch_size` is reached before the end of `flush_delay`, the metrics are sent without further delay
- `precision`: Precision of the timestamp. Valid values are 's', 'ms', 'us' and 'ns'. (default is 's')
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)
Influx client options:
=======
@@ -52,7 +46,3 @@ Influx client options:
- `max_retries`: maximum count of retry attempts of failed writes
- `max_retry_time`: maximum total retry timeout
- `use_gzip`: Specify whether to use GZip compression in write requests
### Using `influxdb` sink for communication with cc-metric-store
The cc-metric-store only accepts metrics with a timestamp precision in seconds, so it is required to use `"precision": "s"`.

View File

@@ -72,9 +72,8 @@ import (
"fmt"
"unsafe"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/NVIDIA/go-nvml/pkg/dl"
)
@@ -111,102 +110,99 @@ type LibgangliaSink struct {
cstrCache map[string]*C.char
}
func (s *LibgangliaSink) Write(msg lp.CCMessage) error {
func (s *LibgangliaSink) Write(point lp.CCMetric) error {
var err error = nil
var c_name *C.char
var c_value *C.char
var c_type *C.char
var c_unit *C.char
point, err := s.mp.ProcessMessage(msg)
if err == nil && point != nil {
// helper function for looking up C strings in the cache
lookup := func(key string) *C.char {
if _, exist := s.cstrCache[key]; !exist {
s.cstrCache[key] = C.CString(key)
}
return s.cstrCache[key]
// helper function for looking up C strings in the cache
lookup := func(key string) *C.char {
if _, exist := s.cstrCache[key]; !exist {
s.cstrCache[key] = C.CString(key)
}
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.AddTypeToName {
conf.Name = GangliaMetricName(point)
}
c_value = C.CString(conf.Value)
c_type = lookup(conf.Type)
c_name = lookup(conf.Name)
// Add unit
unit := ""
if s.config.AddUnits {
unit = conf.Unit
}
c_unit = lookup(unit)
// Determine the slope of the metric. Ganglia's own collector mostly use
// 'both' but the mem and swap total uses 'zero'.
slope_type := C.GANGLIA_SLOPE_BOTH
switch conf.Slope {
case "zero":
slope_type = C.GANGLIA_SLOPE_ZERO
case "both":
slope_type = C.GANGLIA_SLOPE_BOTH
}
// Create a new Ganglia metric
gmetric := C.Ganglia_metric_create(s.global_context)
// Set name, value, type and unit in the Ganglia metric
// The default slope_type is both directions, so up and down. Some metrics want 'zero' slope, probably constant.
// The 'tmax' value is by default 300.
rval := C.int(0)
rval = C.Ganglia_metric_set(gmetric, c_name, c_value, c_type, c_unit, C.uint(slope_type), C.uint(conf.Tmax), 0)
switch rval {
case 1:
C.free(unsafe.Pointer(c_value))
return errors.New("invalid parameters")
case 2:
C.free(unsafe.Pointer(c_value))
return errors.New("one of your parameters has an invalid character '\"'")
case 3:
C.free(unsafe.Pointer(c_value))
return fmt.Errorf("the type parameter \"%s\" is not a valid type", conf.Type)
case 4:
C.free(unsafe.Pointer(c_value))
return fmt.Errorf("the value parameter \"%s\" does not represent a number", conf.Value)
default:
}
// Set the cluster name, otherwise it takes it from the configuration file
if len(s.config.ClusterName) > 0 {
C.Ganglia_metadata_add(gmetric, lookup("CLUSTER"), lookup(s.config.ClusterName))
}
// Set the group metadata in the Ganglia metric if configured
if s.config.AddGangliaGroup {
c_group := lookup(conf.Group)
C.Ganglia_metadata_add(gmetric, lookup("GROUP"), c_group)
}
// Now we send the metric
// gmetric does provide some more options like description and other options
// but they are not provided by the collectors
rval = C.Ganglia_metric_send(gmetric, s.send_channels)
if rval != 0 {
err = fmt.Errorf("there was an error sending metric %s to %d of the send channels ", point.Name(), rval)
// fall throuph to use Ganglia_metric_destroy from common cleanup
}
// Cleanup Ganglia metric
C.Ganglia_metric_destroy(gmetric)
// Free the value C string, the only one not stored in the cache
C.free(unsafe.Pointer(c_value))
return s.cstrCache[key]
}
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.AddTypeToName {
conf.Name = GangliaMetricName(point)
}
c_value = C.CString(conf.Value)
c_type = lookup(conf.Type)
c_name = lookup(conf.Name)
// Add unit
unit := ""
if s.config.AddUnits {
unit = conf.Unit
}
c_unit = lookup(unit)
// Determine the slope of the metric. Ganglia's own collector mostly use
// 'both' but the mem and swap total uses 'zero'.
slope_type := C.GANGLIA_SLOPE_BOTH
switch conf.Slope {
case "zero":
slope_type = C.GANGLIA_SLOPE_ZERO
case "both":
slope_type = C.GANGLIA_SLOPE_BOTH
}
// Create a new Ganglia metric
gmetric := C.Ganglia_metric_create(s.global_context)
// Set name, value, type and unit in the Ganglia metric
// The default slope_type is both directions, so up and down. Some metrics want 'zero' slope, probably constant.
// The 'tmax' value is by default 300.
rval := C.int(0)
rval = C.Ganglia_metric_set(gmetric, c_name, c_value, c_type, c_unit, C.uint(slope_type), C.uint(conf.Tmax), 0)
switch rval {
case 1:
C.free(unsafe.Pointer(c_value))
return errors.New("invalid parameters")
case 2:
C.free(unsafe.Pointer(c_value))
return errors.New("one of your parameters has an invalid character '\"'")
case 3:
C.free(unsafe.Pointer(c_value))
return fmt.Errorf("the type parameter \"%s\" is not a valid type", conf.Type)
case 4:
C.free(unsafe.Pointer(c_value))
return fmt.Errorf("the value parameter \"%s\" does not represent a number", conf.Value)
default:
}
// Set the cluster name, otherwise it takes it from the configuration file
if len(s.config.ClusterName) > 0 {
C.Ganglia_metadata_add(gmetric, lookup("CLUSTER"), lookup(s.config.ClusterName))
}
// Set the group metadata in the Ganglia metric if configured
if s.config.AddGangliaGroup {
c_group := lookup(conf.Group)
C.Ganglia_metadata_add(gmetric, lookup("GROUP"), c_group)
}
// Now we send the metric
// gmetric does provide some more options like description and other options
// but they are not provided by the collectors
rval = C.Ganglia_metric_send(gmetric, s.send_channels)
if rval != 0 {
err = fmt.Errorf("there was an error sending metric %s to %d of the send channels ", point.Name(), rval)
// fall throuph to use Ganglia_metric_destroy from common cleanup
}
// Cleanup Ganglia metric
C.Ganglia_metric_destroy(gmetric)
// Free the value C string, the only one not stored in the cache
C.free(unsafe.Pointer(c_value))
return err
}
@@ -245,20 +241,6 @@ func NewLibgangliaSink(name string, config json.RawMessage) (Sink, error) {
return nil, err
}
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
if len(s.config.MessageProcessor) > 0 {
err = s.mp.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
}
lib := dl.New(s.config.GangliaLib, GANGLIA_LIB_DL_FLAGS)
if lib == nil {
return nil, fmt.Errorf("error instantiating DynamicLibrary for %s", s.config.GangliaLib)

View File

@@ -15,23 +15,18 @@ The `libganglia` sink has probably less overhead compared to the `ganglia` sink
"cluster_name": "MyCluster",
"add_ganglia_group" : true,
"add_type_to_name": true,
"add_units" : true,
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"add_units" : true
}
}
```
- `type`: makes the sink an `libganglia` sink
- `meta_as_tags`: print all meta information as tags in the output (optional)
- `gmond_config`: Path to the Ganglia configuration file `gmond.conf` (default: `/etc/ganglia/gmond.conf`)
- `cluster_name`: Set a cluster name for the metric. If not set, it is taken from `gmond_config`
- `add_ganglia_group`: Add a Ganglia metric group based on meta information. Some old versions of `gmetric` do not support the `--group` option
- `add_type_to_name`: Ganglia commonly uses only node-level metrics but with cc-metric-collector, there are metrics for cpus, memory domains, CPU sockets and the whole node. In order to get eeng, this option prefixes the metric name with `<type><type-id>_` or `device_` depending on the metric tags and meta information. For metrics of the whole node `type=node`, no prefix is added
- `add_units`: Add metric value unit if there is a `unit` entry in the metric tags or meta information
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)
### Ganglia Installation

View File

@@ -1,88 +1,27 @@
package sinks
import (
"encoding/json"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
"golang.org/x/exp/slices"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type defaultSinkConfig struct {
MetaAsTags []string `json:"meta_as_tags,omitempty"`
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
Type string `json:"type"`
MetaAsTags []string `json:"meta_as_tags,omitempty"`
Type string `json:"type"`
}
type sink struct {
meta_as_tags map[string]bool // Use meta data tags as tags
mp mp.MessageProcessor // message processor for the sink
name string // Name of the sink
meta_as_tags map[string]bool // Use meta data tags as tags
name string // Name of the sink
}
type Sink interface {
Write(point lp.CCMessage) error // Write metric to the sink
Flush() error // Flush buffered metrics
Close() // Close / finish metric sink
Name() string // Name of the metric sink
Write(point lp.CCMetric) error // Write metric to the sink
Flush() error // Flush buffered metrics
Close() // Close / finish metric sink
Name() string // Name of the metric sink
}
// Name returns the name of the metric sink
func (s *sink) Name() string {
return s.name
}
type key_value_pair struct {
key string
value string
}
func EncoderAdd(encoder *influx.Encoder, msg lp.CCMessage) error {
// Encode measurement name
encoder.StartLine(msg.Name())
tag_list := make([]key_value_pair, 0, 10)
// copy tags and meta data which should be used as tags
for key, value := range msg.Tags() {
tag_list =
append(
tag_list,
key_value_pair{
key: key,
value: value,
},
)
}
// Encode tags (they musts be in lexical order)
slices.SortFunc(
tag_list,
func(a key_value_pair, b key_value_pair) int {
if a.key < b.key {
return -1
}
if a.key > b.key {
return +1
}
return 0
},
)
for i := range tag_list {
encoder.AddTag(
tag_list[i].key,
tag_list[i].value,
)
}
// Encode fields
for key, value := range msg.Fields() {
encoder.AddField(key, influx.MustNewValue(value))
}
// Encode time stamp
encoder.EndLine(msg.Time())
// Return encoder errors
return encoder.Err()
}

View File

@@ -5,16 +5,13 @@ import (
"encoding/json"
"errors"
"fmt"
"os"
"sync"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol"
nats "github.com/nats-io/nats.go"
"golang.org/x/exp/slices"
)
type NatsSinkConfig struct {
@@ -25,21 +22,18 @@ type NatsSinkConfig struct {
User string `json:"user,omitempty"`
Password string `json:"password,omitempty"`
FlushDelay string `json:"flush_delay,omitempty"`
flushDelay time.Duration
NkeyFile string `json:"nkey_file,omitempty"`
// Timestamp precision
Precision string `json:"precision,omitempty"`
}
type NatsSink struct {
sink
client *nats.Conn
encoder influx.Encoder
encoderLock sync.Mutex
config NatsSinkConfig
client *nats.Conn
encoder *influx.Encoder
buffer *bytes.Buffer
config NatsSinkConfig
lock sync.Mutex
flushDelay time.Duration
flushTimer *time.Timer
timerLock sync.Mutex
}
func (s *NatsSink) connect() error {
@@ -48,13 +42,6 @@ func (s *NatsSink) connect() error {
var nc *nats.Conn
if len(s.config.User) > 0 && len(s.config.Password) > 0 {
uinfo = nats.UserInfo(s.config.User, s.config.Password)
} else if len(s.config.NkeyFile) > 0 {
if _, err := os.Stat(s.config.NkeyFile); err == nil {
uinfo = nats.UserCredentials(s.config.NkeyFile)
} else {
cclog.ComponentError(s.name, "NKEY file", s.config.NkeyFile, "does not exist: %v", err.Error())
return err
}
}
uri := fmt.Sprintf("nats://%s:%s", s.config.Host, s.config.Port)
cclog.ComponentDebug(s.name, "Connect to", uri)
@@ -72,65 +59,33 @@ func (s *NatsSink) connect() error {
return nil
}
func (s *NatsSink) Write(m lp.CCMessage) error {
msg, err := s.mp.ProcessMessage(m)
if err == nil && msg != nil {
// Lock for encoder usage
s.encoderLock.Lock()
// Add message to encoder
err = EncoderAdd(&s.encoder, m)
// Unlock encoder usage
s.encoderLock.Unlock()
// Check that encoding worked
if err != nil {
cclog.ComponentError(s.name, "Write:", err.Error())
return err
}
func (s *NatsSink) Write(m lp.CCMetric) error {
s.lock.Lock()
_, err := s.encoder.Encode(m.ToPoint(s.meta_as_tags))
s.lock.Unlock()
if err != nil {
cclog.ComponentError(s.name, "Write:", err.Error())
return err
}
if s.config.flushDelay == 0 {
// Directly flush if no flush delay is configured
return s.Flush()
} else if s.timerLock.TryLock() {
// Setup flush timer when flush delay is configured
// and no other timer is already running
if s.flushTimer != nil {
// Restarting existing flush timer
cclog.ComponentDebug(s.name, "Write(): Restarting flush timer")
s.flushTimer.Reset(s.config.flushDelay)
} else {
// Creating and starting flush timer
cclog.ComponentDebug(s.name, "Write(): Starting new flush timer")
s.flushTimer = time.AfterFunc(
s.config.flushDelay,
func() {
defer s.timerLock.Unlock()
cclog.ComponentDebug(s.name, "Starting flush triggered by flush timer")
if err := s.Flush(); err != nil {
cclog.ComponentError(s.name, "Flush triggered by flush timer: flush failed:", err)
}
})
}
if s.flushDelay == 0 {
s.Flush()
} else if s.flushTimer == nil {
s.flushTimer = time.AfterFunc(s.flushDelay, func() {
s.Flush()
})
} else {
s.flushTimer.Reset(s.flushDelay)
}
return nil
}
func (s *NatsSink) Flush() error {
// Lock for encoder usage
// Own lock for as short as possible: the time it takes to clone the buffer.
s.encoderLock.Lock()
buf := slices.Clone(s.encoder.Bytes())
s.encoder.Reset()
// Unlock encoder usage
s.encoderLock.Unlock()
s.lock.Lock()
buf := append([]byte{}, s.buffer.Bytes()...) // copy bytes
s.buffer.Reset()
s.lock.Unlock()
if len(buf) == 0 {
return nil
@@ -144,23 +99,14 @@ func (s *NatsSink) Flush() error {
}
func (s *NatsSink) Close() {
// Stop existing timer and immediately flush
if s.flushTimer != nil {
if ok := s.flushTimer.Stop(); ok {
s.timerLock.Unlock()
}
}
cclog.ComponentDebug(s.name, "Close NATS connection")
cclog.ComponentDebug(s.name, "Close")
s.client.Close()
}
func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
s := new(NatsSink)
s.name = fmt.Sprintf("NatsSink(%s)", name)
s.config.flushDelay = 5 * time.Second
s.config.FlushDelay = "5s"
s.config.Port = "4222"
s.config.Precision = "s"
s.flushDelay = 10 * time.Second
if len(config) > 0 {
d := json.NewDecoder(bytes.NewReader(config))
d.DisallowUnknownFields()
@@ -174,51 +120,28 @@ func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
len(s.config.Subject) == 0 {
return nil, errors.New("not all configuration variables set required by NatsSink")
}
// Create a new message processor
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
// Read config related to message processor
if len(s.config.MessageProcessor) > 0 {
err = s.mp.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// Add meta_as_tags list to message processor
// Create lookup map to use meta infos as tags in the output metric
s.meta_as_tags = make(map[string]bool)
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
s.meta_as_tags[k] = true
}
// Setup Influx line protocol encoder
precision := influx.Second
if len(s.config.Precision) > 0 {
switch s.config.Precision {
case "s":
precision = influx.Second
case "ms":
precision = influx.Millisecond
case "us":
precision = influx.Microsecond
case "ns":
precision = influx.Nanosecond
}
}
s.encoder.SetPrecision(precision)
// Setup Influx line protocol
s.buffer = &bytes.Buffer{}
s.buffer.Grow(1025)
s.encoder = influx.NewEncoder(s.buffer)
s.encoder.SetPrecision(time.Second)
s.encoder.SetMaxLineBytes(1024)
// Setup infos for connection
if err := s.connect(); err != nil {
return nil, fmt.Errorf("unable to connect: %v", err)
}
s.flushTimer = nil
if len(s.config.FlushDelay) > 0 {
t, err := time.ParseDuration(s.config.FlushDelay)
if err == nil {
s.config.flushDelay = t
cclog.ComponentDebug(s.name, "Init(): flushDelay", t)
if len(s.config.FlushDelay) != 0 {
var err error
s.flushDelay, err = time.ParseDuration(s.config.FlushDelay)
if err != nil {
return nil, err
}
}

View File

@@ -13,13 +13,7 @@ The `nats` sink publishes all metrics into a NATS network. The publishing key is
"port": "4222",
"user": "exampleuser",
"password" : "examplepw",
"nkey_file": "/path/to/nkey_file",
"flush_delay": "10s",
"precision": "s",
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"meta_as_tags" : [],
}
}
```
@@ -30,12 +24,4 @@ The `nats` sink publishes all metrics into a NATS network. The publishing key is
- `port`: Port number (as string) of the NATS server
- `user`: Username for basic authentication
- `password`: Password for basic authentication
- `nkey_file`: Path to credentials file with NKEY
- `flush_delay`: Maximum time until metrics are sent out (default '5s')
- `precision`: Precision of the timestamp. Valid values are 's', 'ms', 'us' and 'ns'. (default is 's')
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)
### Using `nats` sink for communication with cc-metric-store
The cc-metric-store only accepts metrics with a timestamp precision in seconds, so it is required to use `"precision": "s"`.
- `meta_as_tags`: print all meta information as tags in the output (optional)

View File

@@ -10,9 +10,8 @@ import (
"strings"
"sync"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/gorilla/mux"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promhttp"
@@ -50,13 +49,11 @@ func intToFloat64(input interface{}) (float64, error) {
return float64(value), nil
case int64:
return float64(value), nil
case uint64:
return float64(value), nil
}
return 0, errors.New("cannot cast value to float64")
}
func getLabelValue(metric lp.CCMessage) []string {
func getLabelValue(metric lp.CCMetric) []string {
labelValues := []string{}
if tid, tidok := metric.GetTag("type-id"); tidok && metric.HasTag("type") {
labelValues = append(labelValues, tid)
@@ -69,7 +66,7 @@ func getLabelValue(metric lp.CCMessage) []string {
return labelValues
}
func getLabelNames(metric lp.CCMessage) []string {
func getLabelNames(metric lp.CCMetric) []string {
labelNames := []string{}
if t, tok := metric.GetTag("type"); tok && metric.HasTag("type-id") {
labelNames = append(labelNames, t)
@@ -82,7 +79,7 @@ func getLabelNames(metric lp.CCMessage) []string {
return labelNames
}
func (s *PrometheusSink) newMetric(metric lp.CCMessage) error {
func (s *PrometheusSink) newMetric(metric lp.CCMetric) error {
var value float64 = 0
name := metric.Name()
opts := prometheus.GaugeOpts{
@@ -120,7 +117,7 @@ func (s *PrometheusSink) newMetric(metric lp.CCMessage) error {
return nil
}
func (s *PrometheusSink) updateMetric(metric lp.CCMessage) error {
func (s *PrometheusSink) updateMetric(metric lp.CCMetric) error {
var value float64 = 0.0
name := metric.Name()
labelValues := getLabelValue(metric)
@@ -153,12 +150,8 @@ func (s *PrometheusSink) updateMetric(metric lp.CCMessage) error {
return nil
}
func (s *PrometheusSink) Write(m lp.CCMessage) error {
msg, err := s.mp.ProcessMessage(m)
if err == nil && msg != nil {
err = s.updateMetric(m)
}
return err
func (s *PrometheusSink) Write(m lp.CCMetric) error {
return s.updateMetric(m)
}
func (s *PrometheusSink) Flush() error {
@@ -187,20 +180,6 @@ func NewPrometheusSink(name string, config json.RawMessage) (Sink, error) {
cclog.ComponentError(s.name, err.Error())
return nil, err
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
if len(s.config.MessageProcessor) > 0 {
err = p.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
}
s.labelMetrics = make(map[string]*prometheus.GaugeVec)
s.nodeMetrics = make(map[string]prometheus.Gauge)
s.promWg.Add(1)

View File

@@ -11,11 +11,7 @@ The `prometheus` sink publishes all metrics via an HTTP server ready to be scrap
"type": "prometheus",
"host": "localhost",
"port": "8080",
"path": "metrics",
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"path": "metrics"
}
}
```
@@ -25,5 +21,3 @@ The `prometheus` sink publishes all metrics via an HTTP server ready to be scrap
- `port`: Portnumber (as string) for the HTTP server
- `path`: Path where the metrics should be servered. The metrics will be published at `host`:`port`/`path`
- `group_as_namespace`: Most metrics contain a group as meta information like 'memory', 'load'. With this the metric names are extended to `group`_`name` if possible.
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)

View File

@@ -6,9 +6,8 @@ import (
"fmt"
"log"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type SampleSinkConfig struct {
@@ -29,14 +28,9 @@ type SampleSink struct {
// See: metricSink.go
// Code to submit a single CCMetric to the sink
func (s *SampleSink) Write(point lp.CCMessage) error {
func (s *SampleSink) Write(point lp.CCMetric) error {
// based on s.meta_as_tags use meta infos as tags
// moreover, submit the point to the message processor
// to apply drop/modify rules
msg, err := s.mp.ProcessMessage(point)
if err == nil && msg != nil {
log.Print(msg)
}
log.Print(point)
return nil
}
@@ -72,24 +66,10 @@ func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
}
}
// Initialize and configure the message processor
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
// Add message processor configuration
if len(s.config.MessageProcessor) > 0 {
err = p.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// Add rules to move meta information to tag space
// Replacing the legacy 'meta_as_tags' configuration
// Create lookup map to use meta infos as tags in the output metric
s.meta_as_tags = make(map[string]bool)
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
s.meta_as_tags[k] = true
}
// Check if all required fields in the config are set

View File

@@ -7,7 +7,7 @@ import (
"sync"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const SINK_MAX_FORWARD = 50
@@ -21,12 +21,11 @@ var AvailableSinks = map[string]func(name string, config json.RawMessage) (Sink,
"influxdb": NewInfluxSink,
"influxasync": NewInfluxAsyncSink,
"http": NewHttpSink,
"prometheus": NewPrometheusSink,
}
// Metric collector manager data structure
type sinkManager struct {
input chan lp.CCMessage // input channel
input chan lp.CCMetric // input channel
done chan bool // channel to finish / stop metric sink manager
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
sinks map[string]Sink // Mapping sink name to sink
@@ -36,7 +35,7 @@ type sinkManager struct {
// Sink manager access functions
type SinkManager interface {
Init(wg *sync.WaitGroup, sinkConfigFile string) error
AddInput(input chan lp.CCMessage)
AddInput(input chan lp.CCMetric)
AddOutput(name string, config json.RawMessage) error
Start()
Close()
@@ -108,7 +107,7 @@ func (sm *sinkManager) Start() {
cclog.ComponentDebug("SinkManager", "DONE")
}
toTheSinks := func(p lp.CCMessage) {
toTheSinks := func(p lp.CCMetric) {
// Send received metric to all outputs
cclog.ComponentDebug("SinkManager", "WRITE", p)
for _, s := range sm.sinks {
@@ -139,7 +138,7 @@ func (sm *sinkManager) Start() {
}
// AddInput adds the input channel to the sink manager
func (sm *sinkManager) AddInput(input chan lp.CCMessage) {
func (sm *sinkManager) AddInput(input chan lp.CCMetric) {
sm.input = input
}

View File

@@ -8,9 +8,8 @@ import (
"strings"
// "time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type StdoutSink struct {
@@ -22,14 +21,11 @@ type StdoutSink struct {
}
}
func (s *StdoutSink) Write(m lp.CCMessage) error {
msg, err := s.mp.ProcessMessage(m)
if err == nil && msg != nil {
fmt.Fprint(
s.output,
msg.ToLineProtocol(s.meta_as_tags),
)
}
func (s *StdoutSink) Write(m lp.CCMetric) error {
fmt.Fprint(
s.output,
m.ToLineProtocol(s.meta_as_tags),
)
return nil
}
@@ -45,7 +41,6 @@ func (s *StdoutSink) Close() {
}
func NewStdoutSink(name string, config json.RawMessage) (Sink, error) {
s := new(StdoutSink)
s.name = fmt.Sprintf("StdoutSink(%s)", name)
if len(config) > 0 {
@@ -56,11 +51,6 @@ func NewStdoutSink(name string, config json.RawMessage) (Sink, error) {
return nil, err
}
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
s.output = os.Stdout
if len(s.config.Output) > 0 {
@@ -77,21 +67,10 @@ func NewStdoutSink(name string, config json.RawMessage) (Sink, error) {
s.output = f
}
}
// Add message processor configuration
if len(s.config.MessageProcessor) > 0 {
err = s.mp.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
// Create lookup map to use meta infos as tags in the output metric
// s.meta_as_tags = make(map[string]bool)
// for _, k := range s.config.MetaAsTags {
// s.meta_as_tags[k] = true
// }
s.meta_as_tags = make(map[string]bool)
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
s.meta_as_tags[k] = true
}
return s, nil

View File

@@ -10,11 +10,7 @@ The `stdout` sink is the most simple sink provided by cc-metric-collector. It wr
"<name>": {
"type": "stdout",
"meta_as_tags" : [],
"output_file" : "mylogfile.log",
"process_messages" : {
"see" : "docs of message processor for valid fields"
},
"meta_as_tags" : []
"output_file" : "mylogfile.log"
}
}
```
@@ -22,6 +18,5 @@ The `stdout` sink is the most simple sink provided by cc-metric-collector. It wr
- `type`: makes the sink an `stdout` sink
- `meta_as_tags`: print meta information as tags in the output (optional)
- `output_file`: Write all data to the selected file (optional). There are two 'special' files: `stdout` and `stderr`. If this option is not provided, the default value is `stdout`
- `process_messages`: Process messages with given rules before progressing or dropping, see [here](../pkg/messageProcessor/README.md) (optional)
- `meta_as_tags`: print all meta information as tags in the output (deprecated, optional)