Compare commits

..

5 Commits

Author SHA1 Message Date
Thomas Roehl
9dd6ff1a76 Add StatsAPI to README 2022-04-02 16:07:13 +02:00
Thomas Roehl
257b4a64b5 Add missing main API file 2022-04-02 16:06:51 +02:00
Thomas Roehl
5eeb097136 Add stats counters to sinks 2022-04-02 16:06:03 +02:00
Thomas Roehl
4a4992877c Add stats counters to collectors 2022-04-02 16:05:52 +02:00
Thomas Roehl
9447685a69 Add StatsApi. Started if a configuration file is set in global config.json 2022-04-02 16:05:27 +02:00
121 changed files with 3148 additions and 8841 deletions

View File

@@ -3,6 +3,6 @@
"collectors" : ".github/ci-collectors.json",
"receivers" : ".github/ci-receivers.json",
"router" : ".github/ci-router.json",
"interval": "5s",
"duration": "1s"
"interval": 5,
"duration": 1
}

View File

@@ -1,8 +1,6 @@
{
"testoutput" : {
"type" : "stdout",
"meta_as_tags" : [
"unit"
]
"meta_as_tags" : true
}
}

View File

@@ -8,17 +8,16 @@ on:
push:
tags:
- '**'
workflow_dispatch:
jobs:
#
# Build on AlmaLinux 8 using go-toolset
# Build on AlmaLinux 8.5 using go-toolset
#
AlmaLinux-RPM-build:
runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux
container: almalinux:8
container: almalinux:8.5
# The job outputs link to the outputs of the 'rpmrename' step
# Only job outputs can be used in child jobs
outputs:
@@ -28,46 +27,37 @@ jobs:
# 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
run: dnf --assumeyes group install "Development Tools" "RPM Development Tools"
# 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
uses: actions/checkout@v2
with:
submodules: recursive
fetch-depth: 0
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
dnf --assumeyes install \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
run: dnf --assumeyes builddep scripts/cc-metric-collector.spec
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
# AlmaLinux 8 is a derivate of RedHat Enterprise Linux 8 (UBI8),
run: make RPM
# AlmaLinux 8.5 is a derivate of RedHat Enterprise Linux 8 (UBI8),
# so the created RPM both contain the substring 'el8' 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
# This step replaces the substring 'el8' to 'alma85'. It uses the move operation
# because it is unclear whether the default AlmaLinux 8.5 container contains the
# 'rename' command. This way we also get the new names for output.
- name: Rename RPMs (s/el8/alma8/)
- name: Rename RPMs (s/el8/alma85/)
id: rpmrename
run: |
OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
NEW_RPM="${OLD_RPM/el8/alma8}"
NEW_SRPM=${OLD_SRPM/el8/alma8}
NEW_RPM="${OLD_RPM/el8/alma85}"
NEW_SRPM=${OLD_SRPM/el8/alma85}
mv "${OLD_RPM}" "${NEW_RPM}"
mv "${OLD_SRPM}" "${NEW_SRPM}"
echo "::set-output name=SRPM::${NEW_SRPM}"
@@ -77,12 +67,12 @@ jobs:
- name: Save RPM as artifact
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector RPM for AlmaLinux 8
name: cc-metric-collector RPM for AlmaLinux 8.5
path: ${{ steps.rpmrename.outputs.RPM }}
- name: Save SRPM as artifact
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector SRPM for AlmaLinux 8
name: cc-metric-collector SRPM for AlmaLinux 8.5
path: ${{ steps.rpmrename.outputs.SRPM }}
#
@@ -90,8 +80,8 @@ jobs:
#
UBI-8-RPM-build:
runs-on: ubuntu-latest
# See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c35984d70cc534b3a3784e?container-tabs=gti
container: registry.access.redhat.com/ubi8/ubi:8.8-1032.1692772289
# See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
container: registry.access.redhat.com/ubi8/ubi:8.5-226.1645809065
# The job outputs link to the outputs of the 'rpmbuild' step
outputs:
rpm : ${{steps.rpmbuild.outputs.RPM}}
@@ -100,31 +90,24 @@ jobs:
# Use dnf to install development packages
- name: Install development packages
run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git wget openssl-devel diffutils delve which
run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git
# 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
uses: actions/checkout@v2
with:
submodules: recursive
fetch-depth: 0
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
dnf --assumeyes --disableplugin=subscription-manager install \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
run: dnf --assumeyes --disableplugin=subscription-manager builddep scripts/cc-metric-collector.spec
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
run: make RPM
# See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact
@@ -138,76 +121,25 @@ jobs:
name: cc-metric-collector SRPM for UBI 8
path: ${{ steps.rpmbuild.outputs.SRPM }}
#
# Build on Ubuntu 22.04 using official go package
#
Ubuntu-jammy-build:
runs-on: ubuntu-latest
container: ubuntu:22.04
# The job outputs link to the outputs of the 'debrename' step
# Only job outputs can be used in child jobs
outputs:
deb : ${{steps.debrename.outputs.DEB}}
steps:
# Use apt to install development packages
- name: Install development packages
run: |
apt update && apt --assume-yes upgrade
apt --assume-yes install build-essential sed git wget bash
# Checkout git repository and submodules
# fetch-depth must be 0 to use git describe
# See: https://github.com/marketplace/actions/checkout
- name: Checkout
uses: actions/checkout@v4
with:
submodules: recursive
fetch-depth: 0
# Use official golang package
- name: Install Golang
run: |
wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
tar --directory=/usr/local --extract --gzip
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
go version
- name: DEB build MetricCollector
id: dpkg-build
run: |
export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make DEB
- name: Rename DEB (add '_ubuntu22.04')
id: debrename
run: |
OLD_DEB_NAME=$(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 "::set-output name=DEB::${NEW_DEB_FILE}"
# See: https://github.com/actions/upload-artifact
- name: Save DEB as artifact
uses: actions/upload-artifact@v2
with:
name: cc-metric-collector DEB for Ubuntu 22.04
path: ${{ steps.debrename.outputs.DEB }}
#
# Create release with fresh RPMs
#
Release:
runs-on: ubuntu-latest
# We need the RPMs, so add dependency
needs: [AlmaLinux-RPM-build, UBI-8-RPM-build, Ubuntu-jammy-build]
needs: [AlmaLinux-RPM-build, UBI-8-RPM-build]
steps:
# See: https://github.com/actions/download-artifact
- name: Download AlmaLinux 8 RPM
- name: Download AlmaLinux 8.5 RPM
uses: actions/download-artifact@v2
with:
name: cc-metric-collector RPM for AlmaLinux 8
- name: Download AlmaLinux 8 SRPM
name: cc-metric-collector RPM for AlmaLinux 8.5
- name: Download AlmaLinux 8.5 SRPM
uses: actions/download-artifact@v2
with:
name: cc-metric-collector SRPM for AlmaLinux 8
name: cc-metric-collector SRPM for AlmaLinux 8.5
- name: Download UBI 8 RPM
uses: actions/download-artifact@v2
with:
@@ -217,11 +149,6 @@ jobs:
with:
name: cc-metric-collector SRPM for UBI 8
- name: Download Ubuntu 22.04 DEB
uses: actions/download-artifact@v2
with:
name: cc-metric-collector DEB for Ubuntu 22.04
# The download actions do not publish the name of the downloaded file,
# so we re-use the job outputs of the parent jobs. The files are all
# downloaded to the current folder.
@@ -231,21 +158,18 @@ jobs:
- name: Set RPM variables
id: files
run: |
ALMA_8_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
ALMA_85_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
ALMA_85_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
U_2004_DEB=$(basename "${{ needs.Ubuntu-focal-build.outputs.deb}}")
echo "ALMA_8_RPM::${ALMA_8_RPM}"
echo "ALMA_8_SRPM::${ALMA_8_SRPM}"
echo "ALMA_85_RPM::${ALMA_85_RPM}"
echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
echo "UBI_8_RPM::${UBI_8_RPM}"
echo "UBI_8_SRPM::${UBI_8_SRPM}"
echo "U_2004_DEB::${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=ALMA_85_RPM::${ALMA_85_RPM}"
echo "::set-output name=ALMA_85_SRPM::${ALMA_85_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::${U_2004_DEB}"
# See: https://github.com/softprops/action-gh-release
- name: Release
@@ -254,8 +178,7 @@ jobs:
with:
name: cc-metric-collector-${{github.ref_name}}
files: |
${{ steps.files.outputs.ALMA_8_RPM }}
${{ steps.files.outputs.ALMA_8_SRPM }}
${{ steps.files.outputs.ALMA_85_RPM }}
${{ steps.files.outputs.ALMA_85_SRPM }}
${{ steps.files.outputs.UBI_8_RPM }}
${{ steps.files.outputs.UBI_8_SRPM }}
${{ steps.files.outputs.U_2004_DEB }}
${{ steps.files.outputs.UBI_8_SRPM }}

View File

@@ -4,31 +4,32 @@
name: Run Test
# Run on event push
on:
push:
workflow_dispatch:
on: push
jobs:
#
# Job build-1-20
# Build on latest Ubuntu using golang version 1.20
# Job build-1-17
# Build on latest Ubuntu using golang version 1.17
#
build-1-20:
build-1-17:
runs-on: ubuntu-latest
steps:
# See: https://github.com/marketplace/actions/checkout
# Checkout git repository and submodules
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@v2
with:
submodules: recursive
# See: https://github.com/marketplace/actions/setup-go-environment
- name: Setup Golang
uses: actions/setup-go@v4
uses: actions/setup-go@v2
with:
go-version: '1.20'
go-version: '^1.17.7'
# Install libganglia
- name: Setup Ganglia
run: sudo apt install ganglia-monitor libganglia1
- name: Build MetricCollector
run: make
@@ -37,141 +38,31 @@ jobs:
run: ./cc-metric-collector --once --config .github/ci-config.json
#
# Job build-1-21
# Build on latest Ubuntu using golang version 1.21
# Job build-1-16
# Build on latest Ubuntu using golang version 1.16
#
build-1-21:
build-1-16:
runs-on: ubuntu-latest
steps:
# See: https://github.com/marketplace/actions/checkout
# Checkout git repository and submodules
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@v2
with:
submodules: recursive
# See: https://github.com/marketplace/actions/setup-go-environment
- name: Setup Golang
uses: actions/setup-go@v4
uses: actions/setup-go@v2
with:
go-version: '1.21'
go-version: '^1.16.7' # The version AlmaLinux 8.5 uses
# Install libganglia
- name: Setup Ganglia
run: sudo apt install ganglia-monitor libganglia1
- name: Build MetricCollector
run: make
- name: Run MetricCollector once
run: ./cc-metric-collector --once --config .github/ci-config.json
#
# Build on AlmaLinux 8 using go-toolset
#
AlmaLinux-RPM-build:
runs-on: ubuntu-latest
# See: https://hub.docker.com/_/almalinux
container: almalinux:8
# 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
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
dnf --assumeyes install \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
#
# Build on UBI 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: registry.access.redhat.com/ubi8/ubi:8.8-1032.1692772289
# 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 rpm-build-libs rpm-libs gcc make python38 git 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
# Use dnf to install build dependencies
- name: Install build dependencies
run: |
dnf --assumeyes --disableplugin=subscription-manager install \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
- name: RPM build MetricCollector
id: rpmbuild
run: |
git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
make RPM
#
# Build on Ubuntu 22.04 using official go package
#
Ubuntu-jammy-build:
runs-on: ubuntu-latest
container: ubuntu:22.04
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
- 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

View File

@@ -1,29 +0,0 @@
{
"title": "cc-metric-collector",
"description": "Monitoring agent for ClusterCockpit.",
"creators": [
{
"affiliation": "Regionales Rechenzentrum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg",
"name": "Thomas Gruber",
"orcid": "0000-0001-5560-6964"
},
{
"affiliation": "Steinbuch Centre for Computing, Karlsruher Institut für Technologie",
"name": "Holger Obermaier",
"orcid": "0000-0002-6830-6626"
}
],
"upload_type": "software",
"license": "MIT",
"access_right": "open",
"keywords": [
"performance-monitoring",
"cluster-monitoring",
"open-source"
],
"communities": [
{
"identifier": "clustercockpit"
}
]
}

View File

@@ -16,16 +16,15 @@ COMPONENT_DIRS := collectors \
internal/multiChanTicker
BINDIR = bin
GOBIN = $(shell which go)
.PHONY: all
all: $(APP)
$(APP): $(GOSRC) go.mod
$(APP): $(GOSRC)
make -C collectors
$(GOBIN) get
$(GOBIN) build -o $(APP) $(GOSRC_APP)
go get
go build -o $(APP) $(GOSRC_APP)
install: $(APP)
@WORKSPACE=$(PREFIX)
@@ -52,25 +51,25 @@ clean:
.PHONY: fmt
fmt:
$(GOBIN) fmt $(GOSRC_COLLECTORS)
$(GOBIN) fmt $(GOSRC_SINKS)
$(GOBIN) fmt $(GOSRC_RECEIVERS)
$(GOBIN) fmt $(GOSRC_APP)
@for F in $(GOSRC_INTERNAL); do $(GOBIN) fmt $$F; done
go fmt $(GOSRC_COLLECTORS)
go fmt $(GOSRC_SINKS)
go fmt $(GOSRC_RECEIVERS)
go fmt $(GOSRC_APP)
@for F in $(GOSRC_INTERNAL); do go fmt $$F; done
# Examine Go source code and reports suspicious constructs
.PHONY: vet
vet:
$(GOBIN) vet ./...
go vet ./...
# Run linter for the Go programming language.
# Using static analysis, it finds bugs and performance issues, offers simplifications, and enforces style rules
.PHONY: staticcheck
staticcheck:
$(GOBIN) install honnef.co/go/tools/cmd/staticcheck@latest
$$($(GOBIN) env GOPATH)/bin/staticcheck ./...
go install honnef.co/go/tools/cmd/staticcheck@latest
$$(go env GOPATH)/bin/staticcheck ./...
.ONESHELL:
.PHONY: RPM
@@ -84,7 +83,7 @@ RPM: scripts/cc-metric-collector.spec
@COMMITISH="HEAD"
@VERS=$$(git describe --tags $${COMMITISH})
@VERS=$${VERS#v}
@VERS=$$(echo $${VERS} | sed -e s+'-'+'_'+g)
@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
@eval $$(rpmspec --query --queryformat "NAME='%{name}' VERSION='%{version}' RELEASE='%{release}' NVR='%{NVR}' NVRA='%{NVRA}'" --define="VERS $${VERS}" "$${SPECFILE}")
@PREFIX="$${NAME}-$${VERSION}"
@FORMAT="tar.gz"
@@ -96,8 +95,10 @@ RPM: scripts/cc-metric-collector.spec
@if [[ "$${GITHUB_ACTIONS}" == true ]]; then
@ RPMFILE="$${RPMDIR}/$${ARCH}/$${NVRA}.rpm"
@ SRPMFILE="$${SRPMDIR}/$${NVR}.src.rpm"
@ echo "SRPM=$${SRPMFILE}" >> $${GITHUB_OUTPUT}
@ echo "RPM=$${RPMFILE}" >> $${GITHUB_OUTPUT}
@ echo "RPM: $${RPMFILE}"
@ echo "SRPM: $${SRPMFILE}"
@ echo "::set-output name=SRPM::$${SRPMFILE}"
@ echo "::set-output name=RPM::$${RPMFILE}"
@fi
.PHONY: DEB
@@ -106,24 +107,21 @@ DEB: scripts/cc-metric-collector.deb.control $(APP)
@WORKSPACE=$${PWD}/.dpkgbuild
@DEBIANDIR=$${WORKSPACE}/debian
@DEBIANBINDIR=$${WORKSPACE}/DEBIAN
@mkdir --parents --verbose $${WORKSPACE} $${DEBIANBINDIR}
@mkdir --parents --verbose $$WORKSPACE $$DEBIANBINDIR
#@mkdir --parents --verbose $$DEBIANDIR
@CONTROLFILE="$${BASEDIR}/scripts/cc-metric-collector.deb.control"
@COMMITISH="HEAD"
@VERS=$$(git describe --tags --abbrev=0 $${COMMITISH})
@if [ -z "$${VERS}" ]; then VERS=${GITHUB_REF_NAME}; fi
@VERS=$${VERS#v}
@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
@ARCH=$$(uname -m)
@ARCH=$$(echo $${ARCH} | sed -e s+'_'+'-'+g)
@if [ "$${ARCH}" = "x86-64" ]; then ARCH=amd64; fi
@ARCH=$$(echo $$ARCH | sed -e s+'_'+'-'+g)
@PREFIX="$${NAME}-$${VERSION}_$${ARCH}"
@SIZE_BYTES=$$(du -bcs --exclude=.dpkgbuild "$${WORKSPACE}"/ | awk '{print $$1}' | head -1 | sed -e 's/^0\+//')
@SIZE="$$(awk -v size="$${SIZE_BYTES}" 'BEGIN {print (size/1024)+1}' | awk '{print int($$0)}')"
@sed -e s+"{VERSION}"+"$${VERS}"+g -e s+"{INSTALLED_SIZE}"+"$${SIZE}"+g -e s+"{ARCH}"+"$${ARCH}"+g $${CONTROLFILE} > $${DEBIANBINDIR}/control
@SIZE_BYTES=$$(du -bcs --exclude=.dpkgbuild "$$WORKSPACE"/ | awk '{print $$1}' | head -1 | sed -e 's/^0\+//')
@SIZE="$$(awk -v size="$$SIZE_BYTES" 'BEGIN {print (size/1024)+1}' | awk '{print int($$0)}')"
#@sed -e s+"{VERSION}"+"$$VERS"+g -e s+"{INSTALLED_SIZE}"+"$$SIZE"+g -e s+"{ARCH}"+"$$ARCH"+g $$CONTROLFILE > $${DEBIANDIR}/control
@sed -e s+"{VERSION}"+"$$VERS"+g -e s+"{INSTALLED_SIZE}"+"$$SIZE"+g -e s+"{ARCH}"+"$$ARCH"+g $$CONTROLFILE > $${DEBIANBINDIR}/control
@make PREFIX=$${WORKSPACE} install
@DEB_FILE="cc-metric-collector_$${VERS}_$${ARCH}.deb"
@dpkg-deb -b $${WORKSPACE} "$${DEB_FILE}"
@if [ "$${GITHUB_ACTIONS}" = "true" ]; then
@ echo "DEB=$${DEB_FILE}" >> $${GITHUB_OUTPUT}
@fi
@dpkg-deb -b $${WORKSPACE} "$$DEB_FILE"
@rm -r "$${WORKSPACE}"

View File

@@ -1,6 +1,5 @@
# cc-metric-collector
A node agent for measuring, processing and forwarding node level metrics. It is part of the [ClusterCockpit ecosystem](./docs/introduction.md).
A node agent for measuring, processing and forwarding node level metrics. It is part of the ClusterCockpit ecosystem.
The metric collector sends (and receives) metric in the [InfluxDB line protocol](https://docs.influxdata.com/influxdb/cloud/reference/syntax/line-protocol/) as it provides flexibility while providing a separation between tags (like index columns in relational databases) and fields (like data columns).
@@ -8,14 +7,10 @@ There is a single timer loop that triggers all collectors serially, collects the
The receiver runs as a go routine side-by-side with the timer loop and asynchronously forwards received metrics to the sink.
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7438287.svg)](https://doi.org/10.5281/zenodo.7438287)
# Configuration
Configuration is implemented using a single json document that is distributed over network and may be persisted as file.
Supported metrics are documented [here](https://github.com/ClusterCockpit/cc-specifications/blob/master/interfaces/lineprotocol/README.md).
Supported metrics are documented [here](https://github.com/ClusterCockpit/cc-specifications/blob/master/metrics/lineprotocol_alternative.md).
There is a main configuration file with basic settings that point to the other configuration files for the different components.
@@ -25,19 +20,21 @@ There is a main configuration file with basic settings that point to the other c
"collectors" : "collectors.json",
"receivers" : "receivers.json",
"router" : "router.json",
"interval": "10s",
"duration": "1s"
"stats_api" : "api.json",
"interval": 10,
"duration": 1
}
```
The `interval` defines how often the metrics should be read and send to the sink. The `duration` tells collectors how long one measurement has to take. This is important for some collectors, like the `likwid` collector. For more information, see [here](./docs/configuration.md).
The `interval` defines how often the metrics should be read and send to the sink. The `duration` tells collectors how long one measurement has to take. This is important for some collectors, like the `likwid` collector.
See the component READMEs for their configuration:
* [`collectors`](./collectors/README.md)
* [`sinks`](./sinks/README.md)
* [`receivers`](./receivers/README.md)
* [`router`](./internal/metricRouter/README.md)
* [`stats_api`](./internal/metricRouter/StatsApi.md)
# Installation
@@ -48,7 +45,6 @@ $ go get (requires at least golang 1.16)
$ make
```
For more information, see [here](./docs/building.md).
# Running
@@ -62,7 +58,6 @@ Usage of metric-collector:
-once
Run all collectors only once
```
# Scenarios
The metric collector was designed with flexibility in mind, so it can be used in many scenarios. Here are a few:
@@ -100,12 +95,11 @@ flowchart TD
```
# Contributing
The ClusterCockpit ecosystem is designed to be used by different HPC computing centers. Since configurations and setups differ between the centers, the centers likely have to put some work into the cc-metric-collector to gather all desired metrics.
You are free to open an issue to request a collector but we would also be happy about PRs.
# Contact
# Contact
* [Matrix.org ClusterCockpit General chat](https://matrix.to/#/#clustercockpit-dev:matrix.org)
* [Matrix.org ClusterCockpit Development chat](https://matrix.to/#/#clustercockpit:matrix.org)

View File

@@ -15,19 +15,20 @@ import (
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
mr "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
)
type CentralConfigFile struct {
Interval string `json:"interval"`
Duration string `json:"duration"`
Interval int `json:"interval"`
Duration int `json:"duration"`
CollectorConfigFile string `json:"collectors"`
RouterConfigFile string `json:"router"`
SinkConfigFile string `json:"sinks"`
ReceiverConfigFile string `json:"receivers,omitempty"`
StatsApiConfigFile string `json:"stats_api,omitempty"`
}
func LoadCentralConfiguration(file string, config *CentralConfigFile) error {
@@ -52,6 +53,7 @@ type RuntimeConfig struct {
CollectManager collectors.CollectorManager
SinkManager sinks.SinkManager
ReceiveManager receivers.ReceiveManager
StatsApi mr.StatsApi
MultiChanTicker mct.MultiChanTicker
Channels []chan lp.CCMetric
@@ -152,11 +154,16 @@ func shutdownHandler(config *RuntimeConfig, shutdownSignal chan os.Signal) {
cclog.Debug("Shutdown SinkManager...")
config.SinkManager.Close()
}
if config.StatsApi != nil {
cclog.Debug("Shutdown StatsApi...")
config.StatsApi.Close()
}
}
func mainFunc() int {
var err error
use_recv := false
use_api := false
// Initialize runtime configuration
rcfg := RuntimeConfig{
@@ -164,6 +171,7 @@ func mainFunc() int {
CollectManager: nil,
SinkManager: nil,
ReceiveManager: nil,
StatsApi: nil,
CliArgs: ReadCli(),
}
@@ -173,36 +181,16 @@ func mainFunc() int {
cclog.Error("Error reading configuration file ", rcfg.CliArgs["configfile"], ": ", err.Error())
return 1
}
// Properly use duration parser with inputs like '60s', '5m' or similar
if len(rcfg.ConfigFile.Interval) > 0 {
t, err := time.ParseDuration(rcfg.ConfigFile.Interval)
if err != nil {
cclog.Error("Configuration value 'interval' no valid duration")
}
rcfg.Interval = t
if rcfg.Interval == 0 {
cclog.Error("Configuration value 'interval' must be greater than zero")
return 1
}
}
// Properly use duration parser with inputs like '60s', '5m' or similar
if len(rcfg.ConfigFile.Duration) > 0 {
t, err := time.ParseDuration(rcfg.ConfigFile.Duration)
if err != nil {
cclog.Error("Configuration value 'duration' no valid duration")
}
rcfg.Duration = t
if rcfg.Duration == 0 {
cclog.Error("Configuration value 'duration' must be greater than zero")
return 1
}
}
if rcfg.Duration > rcfg.Interval {
cclog.Error("The interval should be greater than duration")
if rcfg.ConfigFile.Interval <= 0 || time.Duration(rcfg.ConfigFile.Interval)*time.Second <= 0 {
cclog.Error("Configuration value 'interval' must be greater than zero")
return 1
}
rcfg.Interval = time.Duration(rcfg.ConfigFile.Interval) * time.Second
if rcfg.ConfigFile.Duration <= 0 || time.Duration(rcfg.ConfigFile.Duration)*time.Second <= 0 {
cclog.Error("Configuration value 'duration' must be greater than zero")
return 1
}
rcfg.Duration = time.Duration(rcfg.ConfigFile.Duration) * time.Second
if len(rcfg.ConfigFile.RouterConfigFile) == 0 {
cclog.Error("Metric router configuration file must be set")
@@ -273,6 +261,16 @@ func mainFunc() int {
use_recv = true
}
// Create new statistics API manager
if len(rcfg.ConfigFile.StatsApiConfigFile) > 0 {
rcfg.StatsApi, err = mr.NewStatsApi(rcfg.MultiChanTicker, &rcfg.Sync, rcfg.ConfigFile.StatsApiConfigFile)
if err != nil {
cclog.Error(err.Error())
return 1
}
use_api = true
}
// Create shutdown handler
shutdownSignal := make(chan os.Signal, 1)
signal.Notify(shutdownSignal, os.Interrupt)
@@ -280,6 +278,11 @@ func mainFunc() int {
rcfg.Sync.Add(1)
go shutdownHandler(&rcfg, shutdownSignal)
// Start the stats api early to be prepared for init settings
if use_api {
rcfg.StatsApi.Start()
}
// Start the managers
rcfg.MetricRouter.Start()
rcfg.SinkManager.Start()
@@ -291,7 +294,7 @@ func mainFunc() int {
// Wait until one tick has passed. This is a workaround
if rcfg.CliArgs["once"] == "true" {
x := 1.2 * float64(rcfg.Interval.Seconds())
x := 1.2 * float64(rcfg.ConfigFile.Interval)
time.Sleep(time.Duration(int(x)) * time.Second)
shutdownSignal <- os.Interrupt
}

View File

@@ -12,7 +12,6 @@
"proc_total"
]
},
"memstat": {},
"netstat": {
"include_devices": [
"enp5s0"
@@ -34,8 +33,5 @@
"type-id": "1"
}
}
},
"topprocs": {
"num_procs": 5
}
}

View File

@@ -1,33 +1,25 @@
# LIKWID version
LIKWID_VERSION := 5.2.2
LIKWID_INSTALLED_FOLDER := $(shell dirname $$(which likwid-topology 2>/dev/null) 2>/dev/null)
LIKWID_FOLDER := $(CURDIR)/likwid
all: likwid
# LIKWID version
LIKWID_VERSION = 5.2.1
.ONESHELL:
.PHONY: likwid
likwid:
if [ -n "$(LIKWID_INSTALLED_FOLDER)" ]; then
# Using likwid include files from system installation
INCLUDE_DIR="$(LIKWID_INSTALLED_FOLDER)/../include"
mkdir --parents --verbose "$(LIKWID_FOLDER)"
cp "$${INCLUDE_DIR}"/*.h "$(LIKWID_FOLDER)"
else
# Using likwid include files from downloaded tar archive
if [ -d "$(LIKWID_FOLDER)" ]; then
rm --recursive "$(LIKWID_FOLDER)"
fi
BUILD_FOLDER="$${PWD}/likwidbuild"
mkdir --parents --verbose "$${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 "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/bstrlib.h
rm --recursive "$${BUILD_FOLDER}"
fi
INSTALL_FOLDER="$${PWD}/likwid"
BUILD_FOLDER="$${PWD}/likwidbuild"
if [ -d $${INSTALL_FOLDER} ]; then rm -r $${INSTALL_FOLDER}; fi
mkdir --parents --verbose $${INSTALL_FOLDER} $${BUILD_FOLDER}
wget -P "$${BUILD_FOLDER}" ftp://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz
tar -C $${BUILD_FOLDER} -xf $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION).tar.gz
install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h $${INSTALL_FOLDER}/
install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h $${INSTALL_FOLDER}/
rm -r $${BUILD_FOLDER}
.PHONY: clean
clean:
rm -rf likwid
.PHONY: clean

View File

@@ -35,11 +35,10 @@ In contrast to the configuration files for sinks and receivers, the collectors c
* [`nfs4stat`](./nfs4Metric.md)
* [`cpufreq`](./cpufreqMetric.md)
* [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
* [`numastats`](./numastatsMetric.md)
* [`numastat`](./numastatMetric.md)
* [`gpfs`](./gpfsMetric.md)
* [`beegfs_meta`](./beegfsmetaMetric.md)
* [`beegfs_storage`](./beegfsstorageMetric.md)
* [`rocm_smi`](./rocmsmiMetric.md)
## Todos
@@ -51,7 +50,7 @@ A collector reads data from any source, parses it to metrics and submits these m
* `Name() string`: Return the name of the collector
* `Init(config json.RawMessage) error`: Initializes the collector using the given collector-specific config in JSON. Check if needed files/commands exists, ...
* `Initialized() bool`: Check if a collector is successfully initialized
* `Read(duration time.Duration, output chan ccMetric.CCMetric)`: Read, parse and submit data to the `output` channel as [`CCMetric`](../internal/ccMetric/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`.
* `Read(duration time.Duration, output chan ccMetric.CCMetric)`: Read, parse and submit data to the `output` channel as [`CCMetric`](../internal/ccMetric/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`.
* `Close()`: Closes down the collector.
It is recommanded to call `setup()` in the `Init()` function.

View File

@@ -5,7 +5,7 @@ import (
"bytes"
"encoding/json"
"fmt"
"io"
"io/ioutil"
"os"
"os/exec"
"os/user"
@@ -14,8 +14,9 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
@@ -29,10 +30,11 @@ type BeegfsMetaCollectorConfig struct {
type BeegfsMetaCollector struct {
metricCollector
tags map[string]string
matches map[string]string
config BeegfsMetaCollectorConfig
skipFS map[string]struct{}
tags map[string]string
matches map[string]string
config BeegfsMetaCollectorConfig
skipFS map[string]struct{}
statsProcessedMetrics int64
}
func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
@@ -55,7 +57,6 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
m.name = "BeegfsMetaCollector"
m.setup()
m.parallel = true
// Set default beegfs-ctl binary
m.config.Beegfs = DEFAULT_BEEGFS_CMD
@@ -106,6 +107,7 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
if err != nil {
return fmt.Errorf("BeegfsMetaCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -115,7 +117,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
return
}
//get mounpoint
buffer, _ := os.ReadFile(string("/proc/mounts"))
buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
mounts := strings.Split(string(buffer), "\n")
var mountpoints []string
for _, line := range mounts {
@@ -157,9 +159,9 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
if err != nil {
fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
data, _ := io.ReadAll(cmdStderr)
data, _ := ioutil.ReadAll(cmdStderr)
fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stderr: \"%s\"\n", string(data))
data, _ = io.ReadAll(cmdStdout)
data, _ = ioutil.ReadAll(cmdStdout)
fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stdout: \"%s\"\n", string(data))
return
}
@@ -219,10 +221,12 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *BeegfsMetaCollector) Close() {

View File

@@ -5,7 +5,7 @@ import (
"bytes"
"encoding/json"
"fmt"
"io"
"io/ioutil"
"os"
"os/exec"
"os/user"
@@ -14,8 +14,9 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
// Struct for the collector-specific JSON config
@@ -27,10 +28,11 @@ type BeegfsStorageCollectorConfig struct {
type BeegfsStorageCollector struct {
metricCollector
tags map[string]string
matches map[string]string
config BeegfsStorageCollectorConfig
skipFS map[string]struct{}
tags map[string]string
matches map[string]string
config BeegfsStorageCollectorConfig
skipFS map[string]struct{}
statsProcessedMetrics int64
}
func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
@@ -48,7 +50,6 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
m.name = "BeegfsStorageCollector"
m.setup()
m.parallel = true
// Set default beegfs-ctl binary
m.config.Beegfs = DEFAULT_BEEGFS_CMD
@@ -99,6 +100,7 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
if err != nil {
return fmt.Errorf("BeegfsStorageCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -108,7 +110,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
return
}
//get mounpoint
buffer, _ := os.ReadFile(string("/proc/mounts"))
buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
mounts := strings.Split(string(buffer), "\n")
var mountpoints []string
for _, line := range mounts {
@@ -149,9 +151,9 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
if err != nil {
fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
data, _ := io.ReadAll(cmdStderr)
data, _ := ioutil.ReadAll(cmdStderr)
fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stderr: \"%s\"\n", string(data))
data, _ = io.ReadAll(cmdStdout)
data, _ = ioutil.ReadAll(cmdStdout)
fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stdout: \"%s\"\n", string(data))
return
}
@@ -211,10 +213,12 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *BeegfsStorageCollector) Close() {

View File

@@ -6,55 +6,47 @@ import (
"sync"
"time"
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"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
)
// Map of all available metric collectors
var AvailableCollectors = map[string]MetricCollector{
"likwid": new(LikwidCollector),
"loadavg": new(LoadavgCollector),
"memstat": new(MemstatCollector),
"netstat": new(NetstatCollector),
"ibstat": new(InfinibandCollector),
"lustrestat": new(LustreCollector),
"cpustat": new(CpustatCollector),
"topprocs": new(TopProcsCollector),
"nvidia": new(NvidiaCollector),
"customcmd": new(CustomCmdCollector),
"iostat": new(IOstatCollector),
"diskstat": new(DiskstatCollector),
"tempstat": new(TempCollector),
"ipmistat": new(IpmiCollector),
"gpfs": new(GpfsCollector),
"cpufreq": new(CPUFreqCollector),
"cpufreq_cpuinfo": new(CPUFreqCpuInfoCollector),
"nfs3stat": new(Nfs3Collector),
"nfs4stat": new(Nfs4Collector),
"numastats": new(NUMAStatsCollector),
"beegfs_meta": new(BeegfsMetaCollector),
"beegfs_storage": new(BeegfsStorageCollector),
"rapl": new(RAPLCollector),
"rocm_smi": new(RocmSmiCollector),
"self": new(SelfCollector),
"schedstat": new(SchedstatCollector),
"nfsiostat": new(NfsIOStatCollector),
"likwid": new(LikwidCollector),
"loadavg": new(LoadavgCollector),
"memstat": new(MemstatCollector),
"netstat": new(NetstatCollector),
"ibstat": new(InfinibandCollector),
"lustrestat": new(LustreCollector),
"cpustat": new(CpustatCollector),
"topprocs": new(TopProcsCollector),
"nvidia": new(NvidiaCollector),
"customcmd": new(CustomCmdCollector),
"iostat": new(IOstatCollector),
"diskstat": new(DiskstatCollector),
"tempstat": new(TempCollector),
"ipmistat": new(IpmiCollector),
"gpfs": new(GpfsCollector),
"cpufreq": new(CPUFreqCollector),
"cpufreq_cpuinfo": new(CPUFreqCpuInfoCollector),
"nfs3stat": new(Nfs3Collector),
"nfs4stat": new(Nfs4Collector),
"numastats": new(NUMAStatsCollector),
"beegfs_meta": new(BeegfsMetaCollector),
"beegfs_storage": new(BeegfsStorageCollector),
}
// Metric collector manager data structure
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.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)
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
config map[string]json.RawMessage // json encoded config for collector manager
collector_wg sync.WaitGroup // internally used wait group for the parallel reading of collector
parallel_run bool // Flag whether the collectors are currently read in parallel
collectors []MetricCollector // List of metric collectors to use
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)
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
config map[string]json.RawMessage // json encoded config for collector manager
}
// Metric collector manager access functions
@@ -74,7 +66,6 @@ type CollectorManager interface {
// Initialization is done for all configured collectors
func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error {
cm.collectors = make([]MetricCollector, 0)
cm.serial = make([]MetricCollector, 0)
cm.output = nil
cm.done = make(chan bool)
cm.wg = wg
@@ -109,11 +100,7 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
continue
}
cclog.ComponentDebug("CollectorManager", "ADD COLLECTOR", collector.Name())
if collector.Parallel() {
cm.collectors = append(cm.collectors, collector)
} else {
cm.serial = append(cm.serial, collector)
}
cm.collectors = append(cm.collectors, collector)
}
return nil
}
@@ -129,10 +116,6 @@ func (cm *collectorManager) Start() {
// Collector manager is done
done := func() {
// close all metric collectors
if cm.parallel_run {
cm.collector_wg.Wait()
cm.parallel_run = false
}
for _, c := range cm.collectors {
c.Close()
}
@@ -147,26 +130,7 @@ func (cm *collectorManager) Start() {
done()
return
case t := <-tick:
cm.parallel_run = true
for _, c := range cm.collectors {
// Wait for done signal or execute the collector
select {
case <-cm.done:
done()
return
default:
// Read metrics from collector c via goroutine
cclog.ComponentDebug("CollectorManager", c.Name(), t)
cm.collector_wg.Add(1)
go func(myc MetricCollector) {
myc.Read(cm.duration, cm.output)
cm.collector_wg.Done()
}(c)
}
}
cm.collector_wg.Wait()
cm.parallel_run = false
for _, c := range cm.serial {
// Wait for done signal or execute the collector
select {
case <-cm.done:

View File

@@ -10,22 +10,35 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
//
// CPUFreqCollector
// a metric collector to measure the current frequency of the CPUs
// as obtained from /proc/cpuinfo
// Only measure on the first hyperthread
//
type CPUFreqCpuInfoCollectorTopology struct {
isHT bool
tagSet map[string]string
processor string // logical processor number (continuous, starting at 0)
coreID string // socket local core ID
coreID_int int64
physicalPackageID string // socket / package ID
physicalPackageID_int int64
numPhysicalPackages string // number of sockets / packages
numPhysicalPackages_int int64
isHT bool
numNonHT string // number of non hyperthreading processors
numNonHT_int int64
tagSet map[string]string
}
type CPUFreqCpuInfoCollector struct {
metricCollector
topology []CPUFreqCpuInfoCollectorTopology
topology []*CPUFreqCpuInfoCollectorTopology
statsProcessedMetrics int64
}
func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
@@ -37,7 +50,6 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
m.setup()
m.name = "CPUFreqCpuInfoCollector"
m.parallel = true
m.meta = map[string]string{
"source": m.name,
"group": "CPU",
@@ -54,9 +66,11 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
// Collect topology information from file cpuinfo
foundFreq := false
processor := ""
var numNonHT_int int64 = 0
coreID := ""
physicalPackageID := ""
m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
var maxPhysicalPackageID int64 = 0
m.topology = make([]*CPUFreqCpuInfoCollectorTopology, 0)
coreSeenBefore := make(map[string]bool)
// Read cpuinfo file, line by line
@@ -85,22 +99,41 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
len(coreID) > 0 &&
len(physicalPackageID) > 0 {
topology := new(CPUFreqCpuInfoCollectorTopology)
// Processor
topology.processor = processor
// Core ID
topology.coreID = coreID
topology.coreID_int, err = strconv.ParseInt(coreID, 10, 64)
if err != nil {
return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
}
// Physical package ID
topology.physicalPackageID = physicalPackageID
topology.physicalPackageID_int, err = strconv.ParseInt(physicalPackageID, 10, 64)
if err != nil {
return fmt.Errorf("unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
}
// increase maximun socket / package ID, when required
if topology.physicalPackageID_int > maxPhysicalPackageID {
maxPhysicalPackageID = topology.physicalPackageID_int
}
// is hyperthread?
globalID := physicalPackageID + ":" + coreID
topology.isHT = coreSeenBefore[globalID]
coreSeenBefore[globalID] = true
if !topology.isHT {
// increase number on non hyper thread cores
numNonHT_int++
}
// store collected topology information
m.topology = append(m.topology,
CPUFreqCpuInfoCollectorTopology{
isHT: coreSeenBefore[globalID],
tagSet: map[string]string{
"type": "hwthread",
"type-id": processor,
"package_id": physicalPackageID,
},
},
)
// mark core as seen before
coreSeenBefore[globalID] = true
m.topology = append(m.topology, topology)
// reset topology information
foundFreq = false
@@ -110,11 +143,21 @@ 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)
numPhysicalPackageID_int := maxPhysicalPackageID + 1
numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
numNonHT := fmt.Sprint(numNonHT_int)
for _, t := range m.topology {
t.numPhysicalPackages = numPhysicalPackageID
t.numPhysicalPackages_int = numPhysicalPackageID_int
t.numNonHT = numNonHT
t.numNonHT_int = numNonHT_int
t.tagSet = map[string]string{
"type": "cpu",
"type-id": t.processor,
"package_id": t.physicalPackageID,
}
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -155,6 +198,7 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
return
}
if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
m.statsProcessedMetrics++
output <- y
}
}
@@ -162,6 +206,7 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
}
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *CPUFreqCpuInfoCollector) Close() {

View File

@@ -1,11 +1,10 @@
## `cpufreq_cpuinfo` collector
## `cpufreq_cpuinfo` collector
```json
"cpufreq_cpuinfo": {}
```
The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **hwthread** metrics.
The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **cpu** metrics.
Metrics:
* `cpufreq`

View File

@@ -3,33 +3,46 @@ package collectors
import (
"encoding/json"
"fmt"
"os"
"io/ioutil"
"path/filepath"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
"golang.org/x/sys/unix"
)
type CPUFreqCollectorTopology struct {
scalingCurFreqFile string
tagSet map[string]string
processor string // logical processor number (continuous, starting at 0)
coreID string // socket local core ID
coreID_int int64
physicalPackageID string // socket / package ID
physicalPackageID_int int64
numPhysicalPackages string // number of sockets / packages
numPhysicalPackages_int int64
isHT bool
numNonHT string // number of non hyperthreading processors
numNonHT_int int64
scalingCurFreqFile string
tagSet map[string]string
}
//
// CPUFreqCollector
// a metric collector to measure the current frequency of the CPUs
// as obtained from the hardware (in KHz)
// Only measure on the first hyper-thread
// Only measure on the first hyper thread
//
// See: https://www.kernel.org/doc/html/latest/admin-guide/pm/cpufreq.html
//
type CPUFreqCollector struct {
metricCollector
topology []CPUFreqCollectorTopology
config struct {
topology []CPUFreqCollectorTopology
statsProcessedMetrics int64
config struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
}
}
@@ -42,7 +55,6 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
m.name = "CPUFreqCollector"
m.setup()
m.parallel = true
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
if err != nil {
@@ -52,41 +64,111 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
m.meta = map[string]string{
"source": m.name,
"group": "CPU",
"unit": "Hz",
"unit": "MHz",
}
m.topology = make([]CPUFreqCollectorTopology, 0)
for _, c := range ccTopology.CpuData() {
// Loop for all CPU directories
baseDir := "/sys/devices/system/cpu"
globPattern := filepath.Join(baseDir, "cpu[0-9]*")
cpuDirs, err := filepath.Glob(globPattern)
if err != nil {
return fmt.Errorf("unable to glob files with pattern '%s': %v", globPattern, err)
}
if cpuDirs == nil {
return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
}
// Skip hyper threading CPUs
if c.CpuID != c.CoreCPUsList[0] {
continue
// Initialize CPU topology
m.topology = make([]CPUFreqCollectorTopology, len(cpuDirs))
for _, cpuDir := range cpuDirs {
processor := strings.TrimPrefix(cpuDir, "/sys/devices/system/cpu/cpu")
processor_int, err := strconv.ParseInt(processor, 10, 64)
if err != nil {
return fmt.Errorf("unable to convert cpuID '%s' to int64: %v", processor, err)
}
// Read package ID
physicalPackageIDFile := filepath.Join(cpuDir, "topology", "physical_package_id")
line, err := ioutil.ReadFile(physicalPackageIDFile)
if err != nil {
return fmt.Errorf("unable to read physical package ID from file '%s': %v", physicalPackageIDFile, err)
}
physicalPackageID := strings.TrimSpace(string(line))
physicalPackageID_int, err := strconv.ParseInt(physicalPackageID, 10, 64)
if err != nil {
return fmt.Errorf("unable to convert packageID '%s' to int64: %v", physicalPackageID, err)
}
// Read core ID
coreIDFile := filepath.Join(cpuDir, "topology", "core_id")
line, err = ioutil.ReadFile(coreIDFile)
if err != nil {
return fmt.Errorf("unable to read core ID from file '%s': %v", coreIDFile, err)
}
coreID := strings.TrimSpace(string(line))
coreID_int, err := strconv.ParseInt(coreID, 10, 64)
if err != nil {
return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
}
// Check access to current frequency file
scalingCurFreqFile := filepath.Join("/sys/devices/system/cpu", fmt.Sprintf("cpu%d", c.CpuID), "cpufreq/scaling_cur_freq")
err := unix.Access(scalingCurFreqFile, unix.R_OK)
scalingCurFreqFile := filepath.Join(cpuDir, "cpufreq", "scaling_cur_freq")
err = unix.Access(scalingCurFreqFile, unix.R_OK)
if err != nil {
return fmt.Errorf("unable to access file '%s': %v", scalingCurFreqFile, err)
}
m.topology = append(m.topology,
CPUFreqCollectorTopology{
tagSet: map[string]string{
"type": "hwthread",
"type-id": fmt.Sprint(c.CpuID),
"package_id": fmt.Sprint(c.Socket),
},
scalingCurFreqFile: scalingCurFreqFile,
},
)
t := &m.topology[processor_int]
t.processor = processor
t.physicalPackageID = physicalPackageID
t.physicalPackageID_int = physicalPackageID_int
t.coreID = coreID
t.coreID_int = coreID_int
t.scalingCurFreqFile = scalingCurFreqFile
}
// Initialized
cclog.ComponentDebug(
m.name,
"initialized",
len(m.topology), "non-hyper-threading CPUs")
// is processor a hyperthread?
coreSeenBefore := make(map[string]bool)
for i := range m.topology {
t := &m.topology[i]
globalID := t.physicalPackageID + ":" + t.coreID
t.isHT = coreSeenBefore[globalID]
coreSeenBefore[globalID] = true
}
// number of non hyper thread cores and packages / sockets
var numNonHT_int int64 = 0
var maxPhysicalPackageID int64 = 0
for i := range m.topology {
t := &m.topology[i]
// Update maxPackageID
if t.physicalPackageID_int > maxPhysicalPackageID {
maxPhysicalPackageID = t.physicalPackageID_int
}
if !t.isHT {
numNonHT_int++
}
}
numPhysicalPackageID_int := maxPhysicalPackageID + 1
numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
numNonHT := fmt.Sprint(numNonHT_int)
for i := range m.topology {
t := &m.topology[i]
t.numPhysicalPackages = numPhysicalPackageID
t.numPhysicalPackages_int = numPhysicalPackageID_int
t.numNonHT = numNonHT
t.numNonHT_int = numNonHT_int
t.tagSet = map[string]string{
"type": "cpu",
"type-id": t.processor,
"package_id": t.physicalPackageID,
}
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -101,8 +183,13 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
for i := range m.topology {
t := &m.topology[i]
// skip hyperthreads
if t.isHT {
continue
}
// Read current frequency
line, err := os.ReadFile(t.scalingCurFreqFile)
line, err := ioutil.ReadFile(t.scalingCurFreqFile)
if err != nil {
cclog.ComponentError(
m.name,
@@ -118,9 +205,11 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
}
if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
m.statsProcessedMetrics++
output <- y
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *CPUFreqCollector) Close() {

View File

@@ -1,13 +1,11 @@
## `cpufreq_cpuinfo` collector
```json
"cpufreq": {
"exclude_metrics": []
}
```
The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **hwthread** metrics.
The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **cpu** metrics.
Metrics:
* `cpufreq`
* `cpufreq`

View File

@@ -9,9 +9,9 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
sysconf "github.com/tklauser/go-sysconf"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const CPUSTATFILE = `/proc/stat`
@@ -22,18 +22,16 @@ type CpustatCollectorConfig struct {
type CpustatCollector struct {
metricCollector
config CpustatCollectorConfig
lastTimestamp time.Time // Store time stamp of last tick to derive values
matches map[string]int
cputags map[string]map[string]string
nodetags map[string]string
olddata map[string]map[string]int64
config CpustatCollectorConfig
matches map[string]int
cputags map[string]map[string]string
nodetags map[string]string
statsProcessedMetrics int64
}
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", "unit": "Percent"}
m.nodetags = map[string]string{"type": "node"}
if len(config) > 0 {
@@ -79,58 +77,39 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
// Pre-generate tags for all CPUs
num_cpus := 0
m.cputags = make(map[string]map[string]string)
m.olddata = make(map[string]map[string]int64)
scanner := bufio.NewScanner(file)
for scanner.Scan() {
line := scanner.Text()
linefields := strings.Fields(line)
if strings.Compare(linefields[0], "cpu") == 0 {
m.olddata["cpu"] = make(map[string]int64)
for k, v := range m.matches {
m.olddata["cpu"][k], _ = strconv.ParseInt(linefields[v], 0, 64)
}
} else if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
cpustr := strings.TrimLeft(linefields[0], "cpu")
cpu, _ := strconv.Atoi(cpustr)
m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
m.olddata[linefields[0]] = make(map[string]int64)
for k, v := range m.matches {
m.olddata[linefields[0]][k], _ = strconv.ParseInt(linefields[v], 0, 64)
}
m.cputags[linefields[0]] = map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", cpu)}
num_cpus++
}
}
m.lastTimestamp = time.Now()
m.statsProcessedMetrics = 0
m.init = true
return nil
}
func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric) {
values := make(map[string]float64)
clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK)
total := 0.0
for match, index := range m.matches {
if len(match) > 0 {
x, err := strconv.ParseInt(linefields[index], 0, 64)
if err == nil {
vdiff := x - m.olddata[linefields[0]][match]
m.olddata[linefields[0]][match] = x // Store new value for next run
values[match] = float64(vdiff) / float64(tsdelta.Seconds()) / float64(clktck)
values[match] = float64(x)
total += values[match]
}
}
}
sum := float64(0)
t := time.Now()
for name, value := range values {
sum += value
y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now)
if err == nil {
output <- y
}
}
if v, ok := values["cpu_idle"]; ok {
sum -= v
y, err := lp.New("cpu_used", tags, m.meta, map[string]interface{}{"value": sum * 100}, now)
y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": (value * 100.0) / total}, t)
if err == nil {
m.statsProcessedMetrics++
output <- y
}
}
@@ -141,9 +120,6 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
return
}
num_cpus := 0
now := time.Now()
tsdelta := now.Sub(m.lastTimestamp)
file, err := os.Open(string(CPUSTATFILE))
if err != nil {
cclog.ComponentError(m.name, err.Error())
@@ -155,9 +131,9 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
line := scanner.Text()
linefields := strings.Fields(line)
if strings.Compare(linefields[0], "cpu") == 0 {
m.parseStatLine(linefields, m.nodetags, output, now, tsdelta)
m.parseStatLine(linefields, m.nodetags, output)
} else if strings.HasPrefix(linefields[0], "cpu") {
m.parseStatLine(linefields, m.cputags[linefields[0]], output, now, tsdelta)
m.parseStatLine(linefields, m.cputags[linefields[0]], output)
num_cpus++
}
}
@@ -166,13 +142,13 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
m.nodetags,
m.meta,
map[string]interface{}{"value": int(num_cpus)},
now,
time.Now(),
)
if err == nil {
m.statsProcessedMetrics++
output <- num_cpus_metric
}
m.lastTimestamp = now
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *CpustatCollector) Close() {

View File

@@ -1,6 +1,5 @@
## `cpustat` collector
```json
"cpustat": {
"exclude_metrics": [
@@ -9,10 +8,9 @@
}
```
The `cpustat` collector reads data from `/proc/stat` and outputs a handful **node** and **hwthread** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
The `cpustat` collector reads data from `/proc/stats` and outputs a handful **node** and **hwthread** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
Metrics:
* `cpu_user`
* `cpu_nice`
* `cpu_system`
@@ -23,4 +21,3 @@ Metrics:
* `cpu_steal`
* `cpu_guest`
* `cpu_guest_nice`
* `cpu_used` = `cpu_* - cpu_idle`

View File

@@ -3,13 +3,14 @@ package collectors
import (
"encoding/json"
"errors"
"io/ioutil"
"log"
"os"
"os/exec"
"strings"
"time"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
influx "github.com/influxdata/line-protocol"
)
@@ -23,17 +24,19 @@ type CustomCmdCollectorConfig struct {
type CustomCmdCollector struct {
metricCollector
handler *influx.MetricHandler
parser *influx.Parser
config CustomCmdCollectorConfig
commands []string
files []string
handler *influx.MetricHandler
parser *influx.Parser
config CustomCmdCollectorConfig
commands []string
files []string
statsProcessedMetrics int64
statsProcessedCommands int64
statsProcessedFiles int64
}
func (m *CustomCmdCollector) Init(config json.RawMessage) error {
var err error
m.name = "CustomCmdCollector"
m.parallel = true
m.meta = map[string]string{"source": m.name, "group": "Custom"}
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
@@ -48,12 +51,12 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
command := exec.Command(cmdfields[0], strings.Join(cmdfields[1:], " "))
command.Wait()
_, err = command.Output()
if err == nil {
if err != nil {
m.commands = append(m.commands, c)
}
}
for _, f := range m.config.Files {
_, err = os.ReadFile(f)
_, err = ioutil.ReadFile(f)
if err == nil {
m.files = append(m.files, f)
} else {
@@ -67,6 +70,9 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
m.handler = influx.NewMetricHandler()
m.parser = influx.NewParser(m.handler)
m.parser.SetTimeFunc(DefaultTime)
m.statsProcessedMetrics = 0
m.statsProcessedFiles = 0
m.statsProcessedCommands = 0
m.init = true
return nil
}
@@ -101,12 +107,16 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
y := lp.FromInfluxMetric(c)
if err == nil {
m.statsProcessedMetrics++
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
output <- y
}
}
m.statsProcessedCommands++
stats.ComponentStatInt(m.name, "processed_commands", m.statsProcessedCommands)
}
for _, file := range m.files {
buffer, err := os.ReadFile(file)
buffer, err := ioutil.ReadFile(file)
if err != nil {
log.Print(err)
return
@@ -123,9 +133,13 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
}
y := lp.FromInfluxMetric(f)
if err == nil {
m.statsProcessedMetrics++
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
output <- y
}
}
m.statsProcessedFiles++
stats.ComponentStatInt(m.name, "processed_files", m.statsProcessedFiles)
}
}

View File

@@ -3,13 +3,15 @@ package collectors
import (
"bufio"
"encoding/json"
"fmt"
"os"
"strings"
"syscall"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
// "log"
@@ -22,14 +24,12 @@ type DiskstatCollectorConfig struct {
type DiskstatCollector struct {
metricCollector
//matches map[string]int
config IOstatCollectorConfig
//devices map[string]IOstatCollectorEntry
config DiskstatCollectorConfig
statsProcessedMetrics int64
}
func (m *DiskstatCollector) Init(config json.RawMessage) error {
m.name = "DiskstatCollector"
m.parallel = true
m.meta = map[string]string{"source": m.name, "group": "Disk"}
m.setup()
if len(config) > 0 {
@@ -44,6 +44,7 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
return err
}
defer file.Close()
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -78,41 +79,39 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
continue
}
path := strings.Replace(linefields[1], `\040`, " ", -1)
stat := syscall.Statfs_t{
Blocks: 0,
Bsize: 0,
Bfree: 0,
}
stat := syscall.Statfs_t{}
err := syscall.Statfs(path, &stat)
if err != nil {
continue
}
if stat.Blocks == 0 || stat.Bsize == 0 {
continue
fmt.Println(err.Error())
return
}
tags := map[string]string{"type": "node", "device": linefields[0]}
total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
y, err := lp.New("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
m.statsProcessedMetrics++
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
output <- y
}
free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
y, err = lp.New("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
m.statsProcessedMetrics++
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
output <- y
}
if total > 0 {
perc := (100 * (total - free)) / total
if perc > part_max_used {
part_max_used = perc
}
perc := (100 * (total - free)) / total
if perc > part_max_used {
part_max_used = perc
}
}
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")
m.statsProcessedMetrics++
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
output <- y
}
}

View File

@@ -5,7 +5,7 @@ import (
"bytes"
"encoding/json"
"fmt"
"io"
"io/ioutil"
"log"
"os/exec"
"os/user"
@@ -13,8 +13,9 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const DEFAULT_GPFS_CMD = "mmpmon"
@@ -31,11 +32,11 @@ type GpfsCollector struct {
Mmpmon string `json:"mmpmon_path,omitempty"`
ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
SendBandwidths bool `json:"send_bandwidths"`
SendTotalValues bool `json:"send_total_values"`
}
skipFS map[string]struct{}
lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
lastState map[string]GpfsCollectorLastState
skipFS map[string]struct{}
lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
lastState map[string]GpfsCollectorLastState
statsProcessedMetrics int64
}
func (m *GpfsCollector) Init(config json.RawMessage) error {
@@ -47,7 +48,6 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
var err error
m.name = "GpfsCollector"
m.setup()
m.parallel = true
// Set default mmpmon binary
m.config.Mmpmon = DEFAULT_GPFS_CMD
@@ -72,7 +72,6 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
for _, fs := range m.config.ExcludeFilesystem {
m.skipFS[fs] = struct{}{}
}
m.lastState = make(map[string]GpfsCollectorLastState)
// GPFS / IBM Spectrum Scale file system statistics can only be queried by user root
user, err := user.Current()
@@ -89,7 +88,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
return fmt.Errorf("failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
}
m.config.Mmpmon = p
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -119,8 +118,8 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
cmd.Stderr = cmdStderr
err := cmd.Run()
if err != nil {
dataStdErr, _ := io.ReadAll(cmdStderr)
dataStdOut, _ := io.ReadAll(cmdStdout)
dataStdErr, _ := ioutil.ReadAll(cmdStderr)
dataStdOut, _ := ioutil.ReadAll(cmdStdout)
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to execute command \"%s\": %v\n", cmd.String(), err),
@@ -165,16 +164,11 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
continue
}
// Add filesystem tag
m.tags["filesystem"] = filesystem
// Create initial last state
if m.config.SendBandwidths {
if _, ok := m.lastState[filesystem]; !ok {
m.lastState[filesystem] = GpfsCollectorLastState{
bytesRead: -1,
bytesWritten: -1,
}
if _, ok := m.lastState[filesystem]; !ok {
m.lastState[filesystem] = GpfsCollectorLastState{
bytesRead: -1,
bytesWritten: -1,
}
}
@@ -217,34 +211,16 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
fmt.Sprintf("Read(): Failed to convert bytes read '%s' to int64: %v", key_value["_br_"], err))
continue
}
if y, err :=
lp.New(
"gpfs_bytes_read",
m.tags,
m.meta,
map[string]interface{}{
"value": bytesRead,
},
timestamp,
); err == nil {
y.AddMeta("unit", "bytes")
if y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
if m.config.SendBandwidths {
if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 {
bwRead := float64(bytesRead-lastBytesRead) / timeDiff
if y, err :=
lp.New(
"gpfs_bw_read",
m.tags,
m.meta,
map[string]interface{}{
"value": bwRead,
},
timestamp,
); err == nil {
y.AddMeta("unit", "bytes/sec")
if y, err := lp.New("gpfs_bw_read", m.tags, m.meta, map[string]interface{}{"value": bwRead}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
}
}
@@ -257,34 +233,16 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
fmt.Sprintf("Read(): Failed to convert bytes written '%s' to int64: %v", key_value["_bw_"], err))
continue
}
if y, err :=
lp.New(
"gpfs_bytes_written",
m.tags,
m.meta,
map[string]interface{}{
"value": bytesWritten,
},
timestamp,
); err == nil {
y.AddMeta("unit", "bytes")
if y, err := lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
if m.config.SendBandwidths {
if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
if y, err :=
lp.New(
"gpfs_bw_write",
m.tags,
m.meta,
map[string]interface{}{
"value": bwWrite,
},
timestamp,
); err == nil {
y.AddMeta("unit", "bytes/sec")
if y, err := lp.New("gpfs_bw_write", m.tags, m.meta, map[string]interface{}{"value": bwWrite}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
}
}
@@ -306,6 +264,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
}
if y, err := lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
// number of closes
@@ -318,6 +277,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
}
if y, err := lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
// number of reads
@@ -330,6 +290,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
}
if y, err := lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
// number of writes
@@ -342,6 +303,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
}
if y, err := lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
// number of read directories
@@ -354,6 +316,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
}
if y, err := lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
output <- y
m.statsProcessedMetrics++
}
// Number of inode updates
@@ -365,50 +328,11 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
continue
}
if y, err := lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
m.statsProcessedMetrics++
output <- y
}
// Total values
if m.config.SendTotalValues {
bytesTotal := bytesRead + bytesWritten
if y, err :=
lp.New("gpfs_bytes_total",
m.tags,
m.meta,
map[string]interface{}{
"value": bytesTotal,
},
timestamp,
); err == nil {
y.AddMeta("unit", "bytes")
output <- y
}
iops := numReads + numWrites
if y, err :=
lp.New("gpfs_iops",
m.tags,
m.meta,
map[string]interface{}{
"value": iops,
},
timestamp,
); err == nil {
output <- y
}
metaops := numInodeUpdates + numCloses + numOpens + numReaddirs
if y, err :=
lp.New("gpfs_metaops",
m.tags,
m.meta,
map[string]interface{}{
"value": metaops,
},
timestamp,
); err == nil {
output <- y
}
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *GpfsCollector) Close() {

View File

@@ -6,8 +6,7 @@
"exclude_filesystem": [
"fs1"
],
"send_bandwidths": true,
"send_total_values": true
"send_bandwidths" : true
}
```
@@ -27,12 +26,8 @@ Metrics:
* `gpfs_num_opens`
* `gpfs_num_closes`
* `gpfs_num_reads`
* `gpfs_num_writes`
* `gpfs_num_readdirs`
* `gpfs_num_inode_updates`
* `gpfs_bytes_total = gpfs_bytes_read + gpfs_bytes_written` (if `send_total_values == true`)
* `gpfs_iops = gpfs_num_reads + gpfs_num_writes` (if `send_total_values == true`)
* `gpfs_metaops = gpfs_num_inode_updates + gpfs_num_closes + gpfs_num_opens + gpfs_num_readdirs` (if `send_total_values == true`)
* `gpfs_bw_read` (if `send_bandwidths == true`)
* `gpfs_bw_write` (if `send_bandwidths == true`)

View File

@@ -2,10 +2,12 @@ package collectors
import (
"fmt"
"io/ioutil"
"os"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
"golang.org/x/sys/unix"
"encoding/json"
@@ -18,22 +20,17 @@ import (
const IB_BASEPATH = "/sys/class/infiniband/"
type InfinibandCollectorMetric struct {
name string
path string
unit string
scale int64
addToIBTotal bool
addToIBTotalPkgs bool
currentState int64
lastState int64
path string
unit string
}
type InfinibandCollectorInfo struct {
LID string // IB local Identifier (LID)
device string // IB device
port string // IB device port
portCounterFiles []InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
tagSet map[string]string // corresponding tag list
LID string // IB local Identifier (LID)
device string // IB device
port string // IB device port
portCounterFiles map[string]InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
tagSet map[string]string // corresponding tag list
lastState map[string]int64 // State from last measurement
}
type InfinibandCollector struct {
@@ -41,11 +38,11 @@ type InfinibandCollector struct {
config struct {
ExcludeDevices []string `json:"exclude_devices,omitempty"` // IB device to exclude e.g. mlx5_0
SendAbsoluteValues bool `json:"send_abs_values"` // Send absolut values as read from sys filesystem
SendTotalValues bool `json:"send_total_values"` // Send computed total values
SendDerivedValues bool `json:"send_derived_values"` // Send derived values e.g. rates
}
info []InfinibandCollectorInfo
lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
info []*InfinibandCollectorInfo
lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
statsProcessedMetrics int64
}
// Init initializes the Infiniband collector by walking through files below IB_BASEPATH
@@ -59,7 +56,6 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
var err error
m.name = "InfinibandCollector"
m.setup()
m.parallel = true
m.meta = map[string]string{
"source": m.name,
"group": "Network",
@@ -89,7 +85,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
for _, path := range ibDirs {
// Skip, when no LID is assigned
line, err := os.ReadFile(filepath.Join(path, "lid"))
line, err := ioutil.ReadFile(filepath.Join(path, "lid"))
if err != nil {
continue
}
@@ -117,39 +113,11 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
// Check access to counter files
countersDir := filepath.Join(path, "counters")
portCounterFiles := []InfinibandCollectorMetric{
{
name: "ib_recv",
path: filepath.Join(countersDir, "port_rcv_data"),
unit: "bytes",
scale: 4,
addToIBTotal: true,
lastState: -1,
},
{
name: "ib_xmit",
path: filepath.Join(countersDir, "port_xmit_data"),
unit: "bytes",
scale: 4,
addToIBTotal: true,
lastState: -1,
},
{
name: "ib_recv_pkts",
path: filepath.Join(countersDir, "port_rcv_packets"),
unit: "packets",
scale: 1,
addToIBTotalPkgs: true,
lastState: -1,
},
{
name: "ib_xmit_pkts",
path: filepath.Join(countersDir, "port_xmit_packets"),
unit: "packets",
scale: 1,
addToIBTotalPkgs: true,
lastState: -1,
},
portCounterFiles := map[string]InfinibandCollectorMetric{
"ib_recv": {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes"},
"ib_xmit": {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes"},
"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets"},
"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets"},
}
for _, counter := range portCounterFiles {
err := unix.Access(counter.path, unix.R_OK)
@@ -158,8 +126,14 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
}
}
// Initialize last state
lastState := make(map[string]int64)
for counter := range portCounterFiles {
lastState[counter] = -1
}
m.info = append(m.info,
InfinibandCollectorInfo{
&InfinibandCollectorInfo{
LID: LID,
device: device,
port: port,
@@ -170,13 +144,14 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
"port": port,
"lid": LID,
},
lastState: lastState,
})
}
if len(m.info) == 0 {
return fmt.Errorf("found no IB devices")
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -196,15 +171,11 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
// Save current timestamp
m.lastTimestamp = now
for i := range m.info {
info := &m.info[i]
var ib_total, ib_total_pkts int64
for i := range info.portCounterFiles {
counterDef := &info.portCounterFiles[i]
for _, info := range m.info {
for counterName, counterDef := range info.portCounterFiles {
// Read counter file
line, err := os.ReadFile(counterDef.path)
line, err := ioutil.ReadFile(counterDef.path)
if err != nil {
cclog.ComponentError(
m.name,
@@ -218,92 +189,36 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
if err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterDef.name, data, err))
fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
continue
}
// Scale raw value
v *= counterDef.scale
// Save current state
counterDef.currentState = v
// Send absolut values
if m.config.SendAbsoluteValues {
if y, err :=
lp.New(
counterDef.name,
info.tagSet,
m.meta,
map[string]interface{}{
"value": counterDef.currentState,
},
now); err == nil {
if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
y.AddMeta("unit", counterDef.unit)
output <- y
m.statsProcessedMetrics++
}
}
// Send derived values
if m.config.SendDerivedValues {
if counterDef.lastState >= 0 {
rate := float64((counterDef.currentState - counterDef.lastState)) / timeDiff
if y, err :=
lp.New(
counterDef.name+"_bw",
info.tagSet,
m.meta,
map[string]interface{}{
"value": rate,
},
now); err == nil {
if info.lastState[counterName] >= 0 {
rate := float64((v - info.lastState[counterName])) / timeDiff
if y, err := lp.New(counterName+"_bw", info.tagSet, m.meta, map[string]interface{}{"value": rate}, now); err == nil {
y.AddMeta("unit", counterDef.unit+"/sec")
output <- y
m.statsProcessedMetrics++
}
}
counterDef.lastState = counterDef.currentState
}
// Sum up total values
if m.config.SendTotalValues {
switch {
case counterDef.addToIBTotal:
ib_total += counterDef.currentState
case counterDef.addToIBTotalPkgs:
ib_total_pkts += counterDef.currentState
}
// Save current state
info.lastState[counterName] = v
}
}
// Send total values
if m.config.SendTotalValues {
if y, err :=
lp.New(
"ib_total",
info.tagSet,
m.meta,
map[string]interface{}{
"value": ib_total,
},
now); err == nil {
y.AddMeta("unit", "bytes")
output <- y
}
if y, err :=
lp.New(
"ib_total_pkts",
info.tagSet,
m.meta,
map[string]interface{}{
"value": ib_total_pkts,
},
now); err == nil {
y.AddMeta("unit", "packets")
output <- y
}
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *InfinibandCollector) Close() {

View File

@@ -17,16 +17,13 @@ LID file (`/sys/class/infiniband/<dev>/ports/<port>/lid`)
The devices can be filtered with the `exclude_devices` option in the configuration.
For each found LID the collector reads data through the sysfs files below `/sys/class/infiniband/<device>`. (See: <https://www.kernel.org/doc/Documentation/ABI/stable/sysfs-class-infiniband>)
For each found LID the collector reads data through the sysfs files below `/sys/class/infiniband/<device>`.
Metrics:
* `ib_recv`
* `ib_xmit`
* `ib_recv_pkts`
* `ib_xmit_pkts`
* `ib_total = ib_recv + ib_xmit` (if `send_total_values == true`)
* `ib_total_pkts = ib_recv_pkts + ib_xmit_pkts` (if `send_total_values == true`)
* `ib_recv_bw` (if `send_derived_values == true`)
* `ib_xmit_bw` (if `send_derived_values == true`)
* `ib_recv_pkts_bw` (if `send_derived_values == true`)

View File

@@ -4,8 +4,9 @@ import (
"bufio"
"os"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
// "log"
"encoding/json"
@@ -29,15 +30,15 @@ type IOstatCollectorEntry struct {
type IOstatCollector struct {
metricCollector
matches map[string]int
config IOstatCollectorConfig
devices map[string]IOstatCollectorEntry
matches map[string]int
config IOstatCollectorConfig
devices map[string]IOstatCollectorEntry
statsProcessedMetrics int64
}
func (m *IOstatCollector) Init(config json.RawMessage) error {
var err error
m.name = "IOstatCollector"
m.parallel = true
m.meta = map[string]string{"source": m.name, "group": "Disk"}
m.setup()
if len(config) > 0 {
@@ -103,6 +104,7 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
lastValues: values,
}
}
m.statsProcessedMetrics = 0
m.init = true
return err
}
@@ -142,6 +144,7 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
y, err := lp.New(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
entry.lastValues[name] = x
@@ -149,6 +152,7 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
}
m.devices[device] = entry
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *IOstatCollector) Close() {

View File

@@ -1,57 +1,52 @@
package collectors
import (
"bufio"
"bytes"
"encoding/json"
"errors"
"fmt"
"io"
"log"
"os"
"os/exec"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const IPMITOOL_PATH = `ipmitool`
const IPMISENSORS_PATH = `ipmi-sensors`
type IpmiCollectorConfig struct {
ExcludeDevices []string `json:"exclude_devices"`
IpmitoolPath string `json:"ipmitool_path"`
IpmisensorsPath string `json:"ipmisensors_path"`
}
type IpmiCollector struct {
metricCollector
config struct {
ExcludeDevices []string `json:"exclude_devices"`
IpmitoolPath string `json:"ipmitool_path"`
IpmisensorsPath string `json:"ipmisensors_path"`
}
ipmitool string
ipmisensors string
//tags map[string]string
//matches map[string]string
config IpmiCollectorConfig
ipmitool string
ipmisensors string
statsProcessedMetrics int64
}
func (m *IpmiCollector) Init(config json.RawMessage) error {
// Check if already initialized
if m.init {
return nil
}
m.name = "IpmiCollector"
m.setup()
m.parallel = true
m.meta = map[string]string{
"source": m.name,
"group": "IPMI",
}
// default path to IPMI tools
m.config.IpmitoolPath = "ipmitool"
m.config.IpmisensorsPath = "ipmi-sensors"
m.meta = map[string]string{"source": m.name, "group": "IPMI"}
m.config.IpmitoolPath = string(IPMITOOL_PATH)
m.config.IpmisensorsPath = string(IPMISENSORS_PATH)
m.ipmitool = ""
m.ipmisensors = ""
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
if err != nil {
return err
}
}
// Check if executables ipmitool or ipmisensors are found
p, err := exec.LookPath(m.config.IpmitoolPath)
if err == nil {
m.ipmitool = p
@@ -63,38 +58,31 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
return errors.New("no IPMI reader found")
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
// Setup ipmitool command
command := exec.Command(cmd, "sensor")
stdout, _ := command.StdoutPipe()
errBuf := new(bytes.Buffer)
command.Stderr = errBuf
// start command
if err := command.Start(); err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("readIpmiTool(): Failed to start command \"%s\": %v", command.String(), err),
)
command.Wait()
stdout, err := command.Output()
if err != nil {
log.Print(err)
return
}
// Read command output
scanner := bufio.NewScanner(stdout)
for scanner.Scan() {
lv := strings.Split(scanner.Text(), "|")
ll := strings.Split(string(stdout), "\n")
for _, line := range ll {
lv := strings.Split(line, "|")
if len(lv) < 3 {
continue
}
v, err := strconv.ParseFloat(strings.TrimSpace(lv[1]), 64)
v, err := strconv.ParseFloat(strings.Trim(lv[1], " "), 64)
if err == nil {
name := strings.ToLower(strings.Replace(strings.TrimSpace(lv[0]), " ", "_", -1))
unit := strings.TrimSpace(lv[2])
name := strings.ToLower(strings.Replace(strings.Trim(lv[0], " "), " ", "_", -1))
unit := strings.Trim(lv[2], " ")
if unit == "Volts" {
unit = "Volts"
} else if unit == "degrees C" {
@@ -109,20 +97,10 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
if err == nil {
y.AddMeta("unit", unit)
output <- y
m.statsProcessedMetrics++
}
}
}
// Wait for command end
if err := command.Wait(); err != nil {
errMsg, _ := io.ReadAll(errBuf)
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)),
)
return
}
}
func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
@@ -149,6 +127,7 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
y.AddMeta("unit", lv[4])
}
output <- y
m.statsProcessedMetrics++
}
}
}
@@ -156,17 +135,18 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
}
func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Check if already initialized
if !m.init {
return
}
if len(m.config.IpmitoolPath) > 0 {
m.readIpmiTool(m.config.IpmitoolPath, output)
_, err := os.Stat(m.config.IpmitoolPath)
if err == nil {
m.readIpmiTool(m.config.IpmitoolPath, output)
}
} else if len(m.config.IpmisensorsPath) > 0 {
m.readIpmiSensors(m.config.IpmisensorsPath, output)
_, err := os.Stat(m.config.IpmisensorsPath)
if err == nil {
m.readIpmiSensors(m.config.IpmisensorsPath, output)
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *IpmiCollector) Close() {

View File

@@ -8,6 +8,9 @@
}
```
The `ipmistat` collector reads data from `ipmitool` (`ipmitool sensor`) or `ipmi-sensors` (`ipmi-sensors --sdr-cache-recreate --comma-separated-output`).
The `ipmistat` collector reads data from `ipmitool` (`ipmitool sensor`) or `ipmi-sensors` (`ipmi-sensors --sdr-cache-recreate --comma-separated-output`).
The metrics depend on the output of the underlying tools but contain temperature, power and energy metrics.

File diff suppressed because it is too large Load Diff

View File

@@ -3,77 +3,37 @@
The `likwid` collector is probably the most complicated collector. The LIKWID library is included as static library with *direct* access mode. The *direct* access mode is suitable if the daemon is executed by a root user. The static library does not contain the performance groups, so all information needs to be provided in the configuration.
```json
"likwid": {
"force_overwrite" : false,
"invalid_to_zero" : false,
"liblikwid_path" : "/path/to/liblikwid.so",
"accessdaemon_path" : "/folder/that/contains/likwid-accessD",
"access_mode" : "direct or accessdaemon or perf_event",
"lockfile_path" : "/var/run/likwid.lock",
"eventsets": [
{
"events" : {
"COUNTER0": "EVENT0",
"COUNTER1": "EVENT1",
},
"metrics" : [
{
"name": "sum_01",
"calc": "COUNTER0 + COUNTER1",
"publish": false,
"unit": "myunit",
"type": "hwthread"
}
]
}
]
"globalmetrics" : [
{
"name": "global_sum",
"calc": "sum_01",
"publish": true,
"unit": "myunit",
"type": "hwthread"
}
]
}
```
The `likwid` configuration consists of two parts, the `eventsets` and `globalmetrics`:
- An event set list itself has two parts, the `events` and a set of derivable `metrics`. Each of the `events` is a `counter:event` pair in LIKWID's syntax. The `metrics` are a list of formulas to derive the metric value from the measurements of the `events`' values. Each metric has a name, the formula, a type and a publish flag. There is an optional `unit` field. Counter names can be used like variables in the formulas, so `PMC0+PMC1` sums the measurements for the both events configured in the counters `PMC0` and `PMC1`. You can optionally use `time` for the measurement time and `inverseClock` for `1.0/baseCpuFrequency`. The type tells the LikwidCollector whether it is a metric for each hardware thread (`cpu`) or each CPU socket (`socket`). You may specify a unit for the metric with `unit`. The last one is the publishing flag. It tells the LikwidCollector whether a metric should be sent to the router or is only used internally to compute a global metric.
- The `globalmetrics` are metrics which require data from multiple event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a type and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. Also `time` and `inverseClock` cannot be used anymore. So, the idea is to derive a metric in the `eventsets` section and reuse it in the `globalmetrics` part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics (`"publish": false`). **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases. Similar to the metrics in the eventset, you can specify a metric unit with the `unit` field.
The `likwid` configuration consists of two parts, the "eventsets" and "globalmetrics":
- An event set list itself has two parts, the "events" and a set of derivable "metrics". Each of the "events" is a counter:event pair in LIKWID's syntax. The "metrics" are a list of formulas to derive the metric value from the measurements of the "events". Each metric has a name, the formula, a scope and a publish flag. Counter names can be used like variables in the formulas, so `PMC0+PMC1` sums the measurements for the both events configured in the counters `PMC0` and `PMC1`. The scope tells the Collector whether it is a metric for each hardware thread (`cpu`) or each CPU socket (`socket`). You may specify a unit for the metric with `unit`. The last one is the publishing flag. It tells the collector whether a metric should be sent to the router.
- The global metrics are metrics which require data from all event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a scope and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. So, the idea is to derive a metric in the "eventsets" section and reuse it in the "globalmetrics" part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics (`publish=false`). **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases. Similar to the metrics in the eventset, you can specify a metric unit with the `unit` field.
Additional options:
- `access_mode` : Method to use for hardware performance monitoring (`direct` access as root user, `accessdaemon` for the daemon mode)
- `accessdaemon_path`: Folder with the access daemon `likwid-accessD`, commonly `$LIKWID_INSTALL_LOC/sbin`
- `force_overwrite`: Same as setting `LIKWID_FORCE=1`. In case counters are already in-use, LIKWID overwrites their configuration to do its measurements
- `invalid_to_zero`: In some cases, the calculations result in `NaN` or `Inf`. With this option, all `NaN` and `Inf` values are replaces with `0.0`. See below in [seperate section](./likwidMetric.md#invalid_to_zero-option)
- `access_mode`: Specify LIKWID access mode: `direct` for direct register access as root user or `accessdaemon`. The access mode `perf_event` is current untested.
- `accessdaemon_path`: Folder of the accessDaemon `likwid-accessD` (like `/usr/local/sbin`)
- `liblikwid_path`: Location of `liblikwid.so` including file name like `/usr/local/lib/liblikwid.so`
- `lockfile_path`: Location of LIKWID's lock file if multiple tools should access the hardware counters. Default `/var/run/likwid.lock`
- `invalid_to_zero`: In some cases, the calculations result in `NaN` or `Inf`. With this option, all `NaN` and `Inf` values are replaces with `0.0`.
- `access_mode`: Specify LIKWID access mode: `direct` for direct register access as root user or `accessdaemon`
- `accessdaemon_path`: Folder of the accessDaemon `likwid-accessD`
- `liblikwid_path`: Location of `liblikwid.so`
### Available metric types
### Available metric scopes
Hardware performance counters are scattered all over the system nowadays. A counter coveres a specific part of the system. While there are hardware thread specific counter for CPU cycles, instructions and so on, some others are specific for a whole CPU socket/package. To address that, the LikwidCollector provides the specification of a `type` for each metric.
Hardware performance counters are scattered all over the system nowadays. A counter coveres a specific part of the system. While there are hardware thread specific counter for CPU cycles, instructions and so on, some others are specific for a whole CPU socket/package. To address that, the collector provides the specification of a 'scope' for each metric.
- `hwthread` : One metric per CPU hardware thread with the tags `"type" : "hwthread"` and `"type-id" : "$hwthread_id"`
- `cpu` : One metric per CPU hardware thread with the tags `"type" : "cpu"` and `"type-id" : "$cpu_id"`
- `socket` : One metric per CPU socket/package with the tags `"type" : "socket"` and `"type-id" : "$socket_id"`
**Note:** You cannot specify `socket` type for a metric that is measured at `hwthread` type, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the type of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
**Note:** You cannot specify `socket` scope for a metric that is measured at `cpu` scope, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the scope of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
As a guideline:
- All counters `FIXCx`, `PMCy` and `TMAz` have the type `hwthread`
- All counters names containing `BOX` have the type `socket`
- All `PWRx` counters have type `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `hwthread` type
- All `DFCx` counters have type `socket`
- All counters `FIXCx`, `PMCy` and `TMAz` have the scope `cpu`
- All counters names containing `BOX` have the scope `socket`
- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `cpu` scope
- All `DFCx` counters have scope `socket`
### Help with the configuration
The configuration for the `likwid` collector is quite complicated. Most users don't use LIKWID with the event:counter notation but rely on the performance groups defined by the LIKWID team for each architecture. In order to help with the `likwid` collector configuration, we included a script `scripts/likwid_perfgroup_to_cc_config.py` that creates the configuration of an `eventset` from a performance group (using a LIKWID installation in `$PATH`):
```
$ likwid-perfctr -i
[...]
@@ -90,7 +50,6 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
{
"events": {
"FIXC0": "INSTR_RETIRED_ANY",
"FIXC1": "CPU_CLK_UNHALTED_CORE",
"..." : "..."
},
"metrics" : [
@@ -99,7 +58,7 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
"name": "Runtime (RDTSC) [s]",
"publish": true,
"unit": "seconds"
"type": "hwthread"
"scope": "cpu"
},
{
"..." : "..."
@@ -115,37 +74,22 @@ You can copy this JSON and add it to the `eventsets` list. If you specify multip
LIKWID checks the file `/var/run/likwid.lock` before performing any interfering operations. Who is allowed to access the counters is determined by the owner of the file. If it does not exist, it is created for the current user. So, if you want to temporarly allow counter access to a user (e.g. in a job):
Before (SLURM prolog, ...)
```bash
chown $JOBUSER /var/run/likwid.lock
```
$ chwon $JOBUSER /var/run/likwid.lock
```
After (SLURM epilog, ...)
```bash
chown $CCUSER /var/run/likwid.lock
```
### `invalid_to_zero` option
In some cases LIKWID returns `0.0` for some events that are further used in processing and maybe used as divisor in a calculation. After evaluation of a metric, the result might be `NaN` or `+-Inf`. These resulting metrics are commonly not created and forwarded to the router because the [InfluxDB line protocol](https://docs.influxdata.com/influxdb/cloud/reference/syntax/line-protocol/#float) does not support these special floating-point values. If you want to have them sent, this option forces these metric values to be `0.0` instead.
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).
### `send_*_total values` option
- `send_core_total_values`: Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU core.
- `send_socket_total_values` Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU socket.
- `send_node_total_values` Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per node.
$ chwon $CCUSER /var/run/likwid.lock
```
### Example configuration
#### AMD Zen3
```json
"likwid": {
"force_overwrite" : false,
"invalid_to_zero" : false,
"nan_to_zero" : false,
"eventsets": [
{
"events": {
@@ -164,20 +108,20 @@ One might think this does not happen often but often used metrics in the world o
{
"name": "ipc",
"calc": "PMC0/PMC1",
"type": "hwthread",
"type": "cpu",
"publish": true
},
{
"name": "flops_any",
"calc": "0.000001*PMC2/time",
"unit": "MFlops/s",
"type": "hwthread",
"type": "cpu",
"publish": true
},
{
"name": "clock",
"calc": "0.000001*(FIXC1/FIXC2)/inverseClock",
"type": "hwthread",
"type": "cpu",
"unit": "MHz",
"publish": true
},
@@ -238,10 +182,9 @@ One might think this does not happen often but often used metrics in the world o
### How to get the eventsets and metrics from LIKWID
The `likwid` collector reads hardware performance counters at a **hwthread** and **socket** level. The configuration looks quite complicated but it is basically copy&paste from [LIKWID's performance groups](https://github.com/RRZE-HPC/likwid/tree/master/groups). The collector made multiple iterations and tried to use the performance groups but it lacked flexibility. The current way of configuration provides most flexibility.
The `likwid` collector reads hardware performance counters at a **cpu** and **socket** level. The configuration looks quite complicated but it is basically copy&paste from [LIKWID's performance groups](https://github.com/RRZE-HPC/likwid/tree/master/groups). The collector made multiple iterations and tried to use the performance groups but it lacked flexibility. The current way of configuration provides most flexibility.
The logic is as following: There are multiple eventsets, each consisting of a list of counters+events and a list of metrics. If you compare a common performance group with the example setting above, there is not much difference:
```
EVENTSET -> "events": {
FIXC1 ACTUAL_CPU_CLOCK -> "FIXC1": "ACTUAL_CPU_CLOCK",
@@ -260,10 +203,10 @@ METRICS -> "metrics": [
IPC PMC0/PMC1 -> {
-> "name" : "IPC",
-> "calc" : "PMC0/PMC1",
-> "type": "hwthread",
-> "scope": "cpu",
-> "publish": true
-> }
-> ]
```
The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.
The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.

View File

@@ -3,13 +3,14 @@ package collectors
import (
"encoding/json"
"fmt"
"os"
"io/ioutil"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
//
@@ -32,11 +33,11 @@ type LoadavgCollector struct {
config struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
}
statsProcessedMetrics int64
}
func (m *LoadavgCollector) Init(config json.RawMessage) error {
m.name = "LoadavgCollector"
m.parallel = true
m.setup()
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
@@ -64,6 +65,7 @@ func (m *LoadavgCollector) Init(config json.RawMessage) error {
for i, name := range m.proc_matches {
_, m.proc_skips[i] = stringArrayContains(m.config.ExcludeMetrics, name)
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -72,7 +74,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric)
if !m.init {
return
}
buffer, err := os.ReadFile(LOADAVGFILE)
buffer, err := ioutil.ReadFile(LOADAVGFILE)
if err != nil {
if err != nil {
cclog.ComponentError(
@@ -99,6 +101,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric)
y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
@@ -118,9 +121,10 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric)
y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *LoadavgCollector) Close() {

View File

@@ -10,8 +10,9 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const LUSTRE_SYSFS = `/sys/fs/lustre`
@@ -37,13 +38,14 @@ type LustreMetricDefinition struct {
type LustreCollector struct {
metricCollector
tags map[string]string
config LustreCollectorConfig
lctl string
sudoCmd string
lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
definitions []LustreMetricDefinition // Combined list without excluded metrics
stats map[string]map[string]int64 // Data for last value per device and metric
tags map[string]string
config LustreCollectorConfig
lctl string
sudoCmd string
lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
definitions []LustreMetricDefinition // Combined list without excluded metrics
stats map[string]map[string]int64 // Data for last value per device and metric
statsProcessedMetrics int64
}
func (m *LustreCollector) getDeviceDataCommand(device string) []string {
@@ -101,7 +103,7 @@ func getMetricData(lines []string, prefix string, offset int) (int64, error) {
// llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
// devdir := filepath.Join(llitedir, device)
// statsfile := filepath.Join(devdir, "stats")
// buffer, err := os.ReadFile(statsfile)
// buffer, err := ioutil.ReadFile(statsfile)
// if err != nil {
// return make([]string, 0)
// }
@@ -288,7 +290,6 @@ var LustreDeriveMetrics = []LustreMetricDefinition{
func (m *LustreCollector) Init(config json.RawMessage) error {
var err error
m.name = "LustreCollector"
m.parallel = true
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
@@ -373,6 +374,7 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
}
}
m.lastTimestamp = time.Now()
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -419,11 +421,13 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric)
y.AddMeta("unit", def.unit)
}
output <- y
m.statsProcessedMetrics++
}
devData[def.name] = use_x
}
}
m.lastTimestamp = now
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *LustreCollector) Close() {

View File

@@ -12,8 +12,9 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const MEMSTATFILE = "/proc/meminfo"
@@ -32,12 +33,13 @@ type MemstatCollectorNode struct {
type MemstatCollector struct {
metricCollector
stats map[string]int64
tags map[string]string
matches map[string]string
config MemstatCollectorConfig
nodefiles map[int]MemstatCollectorNode
sendMemUsed bool
stats map[string]int64
tags map[string]string
matches map[string]string
config MemstatCollectorConfig
nodefiles map[int]MemstatCollectorNode
sendMemUsed bool
statsProcessedMetrics int64
}
type MemstatStats struct {
@@ -68,8 +70,7 @@ func getStats(filename string) map[string]MemstatStats {
} else if len(linefields) == 5 {
v, err := strconv.ParseFloat(linefields[3], 64)
if err == nil {
cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
stats[strings.Trim(linefields[2], ":")] = MemstatStats{
stats[strings.Trim(linefields[0], ":")] = MemstatStats{
value: v,
unit: linefields[4],
}
@@ -82,7 +83,6 @@ func getStats(filename string) map[string]MemstatStats {
func (m *MemstatCollector) Init(config json.RawMessage) error {
var err error
m.name = "MemstatCollector"
m.parallel = true
m.config.NodeStats = true
m.config.NumaStats = false
if len(config) > 0 {
@@ -155,6 +155,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
}
}
}
m.statsProcessedMetrics = 0
m.init = true
return err
}
@@ -180,6 +181,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
if len(unit) > 0 {
y.AddMeta("unit", unit)
}
m.statsProcessedMetrics++
output <- y
}
}
@@ -188,20 +190,16 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
unit := ""
if totalVal, total := stats["MemTotal"]; total {
if freeVal, free := stats["MemFree"]; free {
memUsed = totalVal.value - freeVal.value
if len(totalVal.unit) > 0 {
unit = totalVal.unit
} else if len(freeVal.unit) > 0 {
unit = freeVal.unit
}
if bufVal, buffers := stats["Buffers"]; buffers {
memUsed -= bufVal.value
if len(bufVal.unit) > 0 && len(unit) == 0 {
unit = bufVal.unit
}
if cacheVal, cached := stats["Cached"]; cached {
memUsed -= cacheVal.value
if len(cacheVal.unit) > 0 && len(unit) == 0 {
memUsed = totalVal.value - (freeVal.value + bufVal.value + cacheVal.value)
if len(totalVal.unit) > 0 {
unit = totalVal.unit
} else if len(freeVal.unit) > 0 {
unit = freeVal.unit
} else if len(bufVal.unit) > 0 {
unit = bufVal.unit
} else if len(cacheVal.unit) > 0 {
unit = cacheVal.unit
}
}
@@ -213,6 +211,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
if len(unit) > 0 {
y.AddMeta("unit", unit)
}
m.statsProcessedMetrics++
output <- y
}
}
@@ -229,6 +228,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
sendStats(stats, nodeConf.tags)
}
}
stats.ComponentStatInt(m.name, "collected_metrics", m.statsProcessedMetrics)
}
func (m *MemstatCollector) Close() {

View File

@@ -3,25 +3,27 @@ package collectors
import (
"encoding/json"
"fmt"
"io/ioutil"
"log"
"strconv"
"strings"
"time"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
)
type MetricCollector interface {
Name() string // Name of the metric collector
Init(config json.RawMessage) error // Initialize metric collector
Initialized() bool // Is metric collector initialized?
Parallel() bool
Name() string // Name of the metric collector
Init(config json.RawMessage) error // Initialize metric collector
Initialized() bool // Is metric collector initialized?
Read(duration time.Duration, output chan lp.CCMetric) // Read metrics from metric collector
Close() // Close / finish metric collector
}
type metricCollector struct {
name string // name of the metric
init bool // is metric collector initialized?
parallel bool // can the metric collector be executed in parallel with others
meta map[string]string // static meta data tags
name string // name of the metric
init bool // is metric collector initialized?
meta map[string]string // static meta data tags
}
// Name returns the name of the metric collector
@@ -29,11 +31,6 @@ func (c *metricCollector) Name() string {
return c.name
}
// Name returns the name of the metric collector
func (c *metricCollector) Parallel() bool {
return c.parallel
}
// Setup is for future use
func (c *metricCollector) setup() error {
return nil
@@ -68,6 +65,58 @@ func stringArrayContains(array []string, str string) (int, bool) {
return -1, false
}
// SocketList returns the list of physical sockets as read from /proc/cpuinfo
func SocketList() []int {
buffer, err := ioutil.ReadFile("/proc/cpuinfo")
if err != nil {
log.Print(err)
return nil
}
ll := strings.Split(string(buffer), "\n")
var packs []int
for _, line := range ll {
if strings.HasPrefix(line, "physical id") {
lv := strings.Fields(line)
id, err := strconv.ParseInt(lv[3], 10, 32)
if err != nil {
log.Print(err)
return packs
}
_, found := intArrayContains(packs, int(id))
if !found {
packs = append(packs, int(id))
}
}
}
return packs
}
// CpuList returns the list of physical CPUs (in contrast to logical CPUs) as read from /proc/cpuinfo
func CpuList() []int {
buffer, err := ioutil.ReadFile("/proc/cpuinfo")
if err != nil {
log.Print(err)
return nil
}
ll := strings.Split(string(buffer), "\n")
var cpulist []int
for _, line := range ll {
if strings.HasPrefix(line, "processor") {
lv := strings.Fields(line)
id, err := strconv.ParseInt(lv[2], 10, 32)
if err != nil {
log.Print(err)
return cpulist
}
_, found := intArrayContains(cpulist, int(id))
if !found {
cpulist = append(cpulist, int(id))
}
}
}
return cpulist
}
// RemoveFromStringList removes the string r from the array of strings s
// If r is not contained in the array an error is returned
func RemoveFromStringList(s []string, r string) ([]string, error) {

View File

@@ -9,8 +9,9 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const NETSTATFILE = "/proc/net/dev"
@@ -32,14 +33,14 @@ type NetstatCollectorMetric struct {
type NetstatCollector struct {
metricCollector
config NetstatCollectorConfig
matches map[string][]NetstatCollectorMetric
lastTimestamp time.Time
config NetstatCollectorConfig
matches map[string][]NetstatCollectorMetric
lastTimestamp time.Time
statsProcessedMetrics int64
}
func (m *NetstatCollector) Init(config json.RawMessage) error {
m.name = "NetstatCollector"
m.parallel = true
m.setup()
m.lastTimestamp = time.Now()
@@ -102,7 +103,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
// Check if device is a included device
if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
tags := map[string]string{"stype": "network", "stype-id": dev, "type": "node"}
tags := map[string]string{"device": 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"}
@@ -149,6 +150,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
if len(m.matches) == 0 {
return errors.New("no devices to collector metrics found")
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -199,6 +201,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
if m.config.SendAbsoluteValues {
if y, err := lp.New(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
output <- y
m.statsProcessedMetrics++
}
}
if m.config.SendDerivedValues {
@@ -206,6 +209,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
rate := float64(v-metric.lastValue) / timeDiff
if y, err := lp.New(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
output <- y
m.statsProcessedMetrics++
}
}
metric.lastValue = v
@@ -213,6 +217,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
}
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *NetstatCollector) Close() {

View File

@@ -23,5 +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 `device`.

View File

@@ -11,7 +11,8 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
// First part contains the code for the general NfsCollector.
@@ -32,7 +33,8 @@ type nfsCollector struct {
Nfsstats string `json:"nfsstat"`
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
}
data map[string]NfsCollectorData
data map[string]NfsCollectorData
statsProcessedMetrics int64
}
func (m *nfsCollector) initStats() error {
@@ -113,8 +115,8 @@ func (m *nfsCollector) MainInit(config json.RawMessage) error {
}
m.data = make(map[string]NfsCollectorData)
m.initStats()
m.statsProcessedMetrics = 0
m.init = true
m.parallel = true
return nil
}
@@ -144,8 +146,10 @@ func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if err == nil {
y.AddMeta("version", m.version)
output <- y
m.statsProcessedMetrics++
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *nfsCollector) Close() {

View File

@@ -1,166 +0,0 @@
package collectors
import (
"encoding/json"
"fmt"
"os"
"regexp"
"strconv"
"strings"
"time"
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
type NfsIOStatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
UseServerAddressAsSType bool `json:"use_server_as_stype,omitempty"`
}
// 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', see NfsIOStatCollectorConfig.UseServerAddressAsSType
}
var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
var bytesRegex = regexp.MustCompile(`\s+bytes:\s+(?P<nread>[^ ]+) (?P<nwrite>[^ ]+) (?P<dread>[^ ]+) (?P<dwrite>[^ ]+) (?P<nfsread>[^ ]+) (?P<nfswrite>[^ ]+) (?P<pageread>[^ ]+) (?P<pagewrite>[^ ]+)`)
func resolve_regex_fields(s string, regex *regexp.Regexp) map[string]string {
fields := make(map[string]string)
groups := regex.SubexpNames()
for _, match := range regex.FindAllStringSubmatch(s, -1) {
for groupIdx, group := range match {
if len(groups[groupIdx]) > 0 {
fields[groups[groupIdx]] = group
}
}
}
return fields
}
func (m *NfsIOStatCollector) readNfsiostats() map[string]map[string]int64 {
data := make(map[string]map[string]int64)
filename := "/proc/self/mountstats"
stats, err := os.ReadFile(filename)
if err != nil {
return data
}
lines := strings.Split(string(stats), "\n")
var current map[string]string = nil
for _, l := range lines {
// Is this a device line with mount point, remote target and NFS version?
dev := resolve_regex_fields(l, deviceRegex)
if len(dev) > 0 {
if _, ok := stringArrayContains(m.config.ExcludeFilesystem, dev[m.key]); !ok {
current = dev
if len(current["version"]) == 0 {
current["version"] = "3"
}
}
}
if len(current) > 0 {
// Byte line parsing (if found the device for it)
bytes := resolve_regex_fields(l, bytesRegex)
if len(bytes) > 0 {
data[current[m.key]] = make(map[string]int64)
for name, sval := range bytes {
if _, ok := stringArrayContains(m.config.ExcludeMetrics, name); !ok {
val, err := strconv.ParseInt(sval, 10, 64)
if err == nil {
data[current[m.key]][name] = val
}
}
}
current = nil
}
}
}
return data
}
func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
var err error = nil
m.name = "NfsIOStatCollector"
m.setup()
m.parallel = true
m.meta = map[string]string{"source": m.name, "group": "NFS", "unit": "bytes"}
m.tags = map[string]string{"type": "node"}
m.config.UseServerAddressAsSType = false
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
cclog.ComponentError(m.name, "Error reading config:", err.Error())
return err
}
}
m.key = "mntpoint"
if m.config.UseServerAddressAsSType {
m.key = "server"
}
m.data = m.readNfsiostats()
m.init = true
return err
}
func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
timestamp := time.Now()
// Get the current values for all mountpoints
newdata := m.readNfsiostats()
for mntpoint, values := range newdata {
// Was the mount point already present in the last iteration
if old, ok := m.data[mntpoint]; ok {
// 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
}
// 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
m.data[mntpoint] = values
}
}
// Reset entries that do not exist anymore
for mntpoint := range m.data {
found := false
for new := range newdata {
if new == mntpoint {
found = true
break
}
}
if !found {
m.data[mntpoint] = nil
}
}
}
func (m *NfsIOStatCollector) Close() {
// Unset flag
m.init = false
}

View File

@@ -1,27 +0,0 @@
## `nfsiostat` collector
```json
"nfsiostat": {
"exclude_metrics": [
"nfsio_oread"
],
"exclude_filesystems" : [
"/mnt",
],
"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.
Metrics:
* `nfsio_nread`: Bytes transferred by normal `read()` calls
* `nfsio_nwrite`: Bytes transferred by normal `write()` calls
* `nfsio_oread`: Bytes transferred by `read()` calls with `O_DIRECT`
* `nfsio_owrite`: Bytes transferred by `write()` calls with `O_DIRECT`
* `nfsio_pageread`: Pages transferred by `read()` calls
* `nfsio_pagewrite`: Pages transferred by `write()` calls
* `nfsio_nfsread`: Bytes transferred for reading from the server
* `nfsio_nfswrite`: Pages transferred by writing to the server
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

@@ -10,42 +10,34 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
// Non-Uniform Memory Access (NUMA) policy hit/miss statistics
//
// Numa policy hit/miss statistics
//
// numa_hit:
//
// A process wanted to allocate memory from this node, and succeeded.
//
// A process wanted to allocate memory from this node, and succeeded.
// numa_miss:
//
// A process wanted to allocate memory from another node,
// but ended up with memory from this node.
//
// A process wanted to allocate memory from another node,
// but ended up with memory from this node.
// numa_foreign:
//
// A process wanted to allocate on this node,
// but ended up with memory from another node.
//
// A process wanted to allocate on this node,
// but ended up with memory from another node.
// local_node:
//
// A process ran on this node's CPU,
// and got memory from this node.
//
// A process ran on this node's CPU,
// and got memory from this node.
// other_node:
//
// A process ran on a different node's CPU
// and got memory from this node.
//
// A process ran on a different node's CPU
// and got memory from this node.
// interleave_hit:
//
// Interleaving wanted to allocate from this node
// and succeeded.
// Interleaving wanted to allocate from this node
// and succeeded.
//
// See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
//
type NUMAStatsCollectorTopolgy struct {
file string
tagSet map[string]string
@@ -53,7 +45,8 @@ type NUMAStatsCollectorTopolgy struct {
type NUMAStatsCollector struct {
metricCollector
topology []NUMAStatsCollectorTopolgy
topology []NUMAStatsCollectorTopolgy
statsProcessedMetrics int64
}
func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
@@ -63,7 +56,6 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
}
m.name = "NUMAStatsCollector"
m.parallel = true
m.setup()
m.meta = map[string]string{
"source": m.name,
@@ -90,9 +82,7 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
tagSet: map[string]string{"memoryDomain": node},
})
}
// Initialized
cclog.ComponentDebug(m.name, "initialized", len(m.topology), "NUMA domains")
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -139,11 +129,13 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMetri
)
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
file.Close()
}
stats.ComponentStatInt(m.name, "collected_metrics", m.statsProcessedMetrics)
}
func (m *NUMAStatsCollector) Close() {

View File

@@ -1,17 +1,15 @@
## `numastat` collector
```json
"numastats": {}
"numastat": {}
```
The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: <https://www.kernel.org/doc/html/latest/admin-guide/numastat.html>
The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
Metrics:
* `numastats_numa_hit`: A process wanted to allocate memory from this node, and succeeded.
* `numastats_numa_miss`: A process wanted to allocate memory from another node, but ended up with memory from this node.
* `numastats_numa_foreign`: A process wanted to allocate on this node, but ended up with memory from another node.
* `numastats_local_node`: A process ran on this node's CPU, and got memory from this node.
* `numastats_other_node`: A process ran on a different node's CPU, and got memory from this node.
* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.
* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.

File diff suppressed because it is too large Load Diff

View File

@@ -3,74 +3,38 @@
```json
"nvidia": {
"exclude_devices": [
"0","1", "0000000:ff:01.0"
"exclude_devices" : [
"0","1"
],
"exclude_metrics": [
"nv_fb_mem_used",
"nv_fb_memory",
"nv_fan"
],
"process_mig_devices": false,
"use_pci_info_as_type_id": true,
"add_pci_info_tag": false,
"add_uuid_meta": false,
"add_board_number_meta": false,
"add_serial_meta": false,
"use_uuid_for_mig_device": false,
"use_slice_for_mig_device": false
]
}
```
The `nvidia` collector can be configured to leave out specific devices with the `exclude_devices` option. It takes IDs as supplied to the NVML with `nvmlDeviceGetHandleByIndex()` or the PCI address in NVML format (`%08X:%02X:%02X.0`). Metrics (listed below) that should not be sent to the MetricRouter can be excluded with the `exclude_metrics` option. Commonly only the physical GPUs are monitored. If MIG devices should be analyzed as well, set `process_mig_devices` (adds `stype=mig,stype-id=<mig_index>`). With the options `use_uuid_for_mig_device` and `use_slice_for_mig_device`, the `<mig_index>` can be replaced with the UUID (e.g. `MIG-6a9f7cc8-6d5b-5ce0-92de-750edc4d8849`) or the MIG slice name (e.g. `1g.5gb`).
The metrics sent by the `nvidia` collector use `accelerator` as `type` tag. For the `type-id`, it uses the device handle index by default. With the `use_pci_info_as_type_id` option, the PCI ID is used instead. If both values should be added as tags, activate the `add_pci_info_tag` option. It uses the device handle index as `type-id` and adds the PCI ID as separate `pci_identifier` tag.
Optionally, it is possible to add the UUID, the board part number and the serial to the meta informations. They are not sent to the sinks (if not configured otherwise).
Metrics:
* `nv_util`
* `nv_mem_util`
* `nv_fb_mem_total`
* `nv_fb_mem_used`
* `nv_bar1_mem_total`
* `nv_bar1_mem_used`
* `nv_mem_total`
* `nv_fb_memory`
* `nv_temp`
* `nv_fan`
* `nv_ecc_mode`
* `nv_perf_state`
* `nv_power_usage`
* `nv_graphics_clock`
* `nv_sm_clock`
* `nv_mem_clock`
* `nv_video_clock`
* `nv_power_usage_report`
* `nv_graphics_clock_report`
* `nv_sm_clock_report`
* `nv_mem_clock_report`
* `nv_max_graphics_clock`
* `nv_max_sm_clock`
* `nv_max_mem_clock`
* `nv_max_video_clock`
* `nv_ecc_uncorrected_error`
* `nv_ecc_corrected_error`
* `nv_power_max_limit`
* `nv_ecc_db_error`
* `nv_ecc_sb_error`
* `nv_power_man_limit`
* `nv_encoder_util`
* `nv_decoder_util`
* `nv_remapped_rows_corrected`
* `nv_remapped_rows_uncorrected`
* `nv_remapped_rows_pending`
* `nv_remapped_rows_failure`
* `nv_compute_processes`
* `nv_graphics_processes`
* `nv_violation_power`
* `nv_violation_thermal`
* `nv_violation_sync_boost`
* `nv_violation_board_limit`
* `nv_violation_low_util`
* `nv_violation_reliability`
* `nv_violation_below_app_clock`
* `nv_violation_below_base_clock`
* `nv_nvlink_crc_flit_errors`
* `nv_nvlink_crc_errors`
* `nv_nvlink_ecc_errors`
* `nv_nvlink_replay_errors`
* `nv_nvlink_recovery_errors`
Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`.
It uses a separate `type` in the metrics. The output metric looks like this:
`<name>,type=accelerator,type-id=<nvidia-gpu-id> value=<metric value> <timestamp>`

View File

@@ -1,262 +0,0 @@
package collectors
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"strconv"
"strings"
"time"
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
type RAPLZoneInfo struct {
// 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)
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 {
metricCollector
config struct {
// Exclude IDs for RAPL zones, e.g.
// * 0 for zone 0
// * 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"`
}
RAPLZoneInfo []RAPLZoneInfo
meta map[string]string // default meta information
}
// Init initializes the running average power limit (RAPL) collector
func (m *RAPLCollector) Init(config json.RawMessage) error {
// Check if already initialized
if m.init {
return nil
}
var err error = nil
m.name = "RAPLCollector"
m.setup()
m.parallel = true
m.meta = map[string]string{
"source": m.name,
"group": "energy",
"unit": "Watt",
}
// Read in the JSON configuration
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
cclog.ComponentError(m.name, "Error reading config:", err.Error())
return err
}
}
// Configure excluded RAPL zones
isIDExcluded := make(map[string]bool)
if m.config.ExcludeByID != nil {
for _, ID := range m.config.ExcludeByID {
isIDExcluded[ID] = true
}
}
isNameExcluded := make(map[string]bool)
if m.config.ExcludeByName != nil {
for _, name := range m.config.ExcludeByName {
isNameExcluded[name] = true
}
}
// 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
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))
}
// 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
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
}
}
// Are all information available?
z.ok = foundName && foundEnergy && foundMaxEnergyRange
return
}
powerCapPrefix := "/sys/devices/virtual/powercap"
controlType := "intel-rapl"
controlTypePath := filepath.Join(powerCapPrefix, controlType)
// Find all RAPL zones
zonePrefix := filepath.Join(controlTypePath, controlType+":")
zonesPath, err := filepath.Glob(zonePrefix + "*")
if err != nil || zonesPath == nil {
return fmt.Errorf("unable to find any zones under %s", controlTypePath)
}
for _, zonePath := range zonesPath {
zoneID := strings.TrimPrefix(zonePath, zonePrefix)
z := readZoneInfo(zonePath)
if z.ok &&
!isIDExcluded[zoneID] &&
!isNameExcluded[z.name] {
// Add RAPL monitoring attributes for a zone
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
subZonePrefix := filepath.Join(zonePath, controlType+":"+zoneID+":")
subZonesPath, err := filepath.Glob(subZonePrefix + "*")
if err != nil || subZonesPath == nil {
continue
}
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] {
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 {
return fmt.Errorf("no running average power limit (RAPL) device found in %s", controlTypePath)
}
// Initialized
cclog.ComponentDebug(
m.name,
"initialized",
len(m.RAPLZoneInfo),
"zones with running average power limit (RAPL) monitoring attributes")
m.init = true
return err
}
// 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.CCMetric) {
for i := range m.RAPLZoneInfo {
p := &m.RAPLZoneInfo[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.New(
"rapl_average_power",
p.tags,
m.meta,
map[string]interface{}{"value": averagePower},
energyTimestamp)
if err == nil {
output <- y
}
// Save current energy counter state
p.energy = energy
p.energyTimestamp = energyTimestamp
}
}
}
}
// Close closes running average power limit (RAPL) metric collector
func (m *RAPLCollector) Close() {
// Unset flag
m.init = false
}

View File

@@ -1,18 +0,0 @@
# 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#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"]
}
```
## Metrics
* `rapl_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement

View File

@@ -1,319 +0,0 @@
package collectors
import (
"encoding/json"
"errors"
"fmt"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/ClusterCockpit/go-rocm-smi/pkg/rocm_smi"
)
type RocmSmiCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ExcludeDevices []string `json:"exclude_devices,omitempty"`
AddPciInfoTag bool `json:"add_pci_info_tag,omitempty"`
UsePciInfoAsTypeId bool `json:"use_pci_info_as_type_id,omitempty"`
AddSerialMeta bool `json:"add_serial_meta,omitempty"`
}
type RocmSmiCollectorDevice struct {
device rocm_smi.DeviceHandle
index int
tags map[string]string // default tags
meta map[string]string // default meta information
excludeMetrics map[string]bool // copy of exclude metrics from config
}
type RocmSmiCollector struct {
metricCollector
config RocmSmiCollectorConfig // the configuration structure
devices []RocmSmiCollectorDevice
}
// Functions to implement MetricCollector interface
// Init(...), Read(...), Close()
// See: metricCollector.go
// Init initializes the sample collector
// Called once by the collector manager
// All tags, meta data tags and metrics that do not change over the runtime should be set here
func (m *RocmSmiCollector) 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 = "RocmSmiCollector"
// This is for later use, also call it early
m.setup()
// Define meta information sent with each metric
// (Can also be dynamic or this is the basic set with extension through AddMeta())
//m.meta = map[string]string{"source": m.name, "group": "AMD"}
// Define tags sent with each metric
// The 'type' tag is always needed, it defines the granulatity of the metric
// node -> whole system
// socket -> CPU socket (requires socket ID as 'type-id' tag)
// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
//m.tags = map[string]string{"type": "node"}
// Read in the JSON configuration
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
cclog.ComponentError(m.name, "Error reading config:", err.Error())
return err
}
}
ret := rocm_smi.Init()
if ret != rocm_smi.STATUS_SUCCESS {
err = errors.New("failed to initialize ROCm SMI library")
cclog.ComponentError(m.name, err.Error())
return err
}
numDevs, ret := rocm_smi.NumMonitorDevices()
if ret != rocm_smi.STATUS_SUCCESS {
err = errors.New("failed to get number of GPUs from ROCm SMI library")
cclog.ComponentError(m.name, err.Error())
return err
}
exclDev := func(s string) bool {
skip_device := false
for _, excl := range m.config.ExcludeDevices {
if excl == s {
skip_device = true
break
}
}
return skip_device
}
m.devices = make([]RocmSmiCollectorDevice, 0)
for i := 0; i < numDevs; i++ {
str_i := fmt.Sprintf("%d", i)
if exclDev(str_i) {
continue
}
device, ret := rocm_smi.DeviceGetHandleByIndex(i)
if ret != rocm_smi.STATUS_SUCCESS {
err = fmt.Errorf("failed to get handle for GPU %d", i)
cclog.ComponentError(m.name, err.Error())
return err
}
pciInfo, ret := rocm_smi.DeviceGetPciInfo(device)
if ret != rocm_smi.STATUS_SUCCESS {
err = fmt.Errorf("failed to get PCI information for GPU %d", i)
cclog.ComponentError(m.name, err.Error())
return err
}
pciId := fmt.Sprintf(
"%08X:%02X:%02X.%X",
pciInfo.Domain,
pciInfo.Bus,
pciInfo.Device,
pciInfo.Function)
if exclDev(pciId) {
continue
}
dev := RocmSmiCollectorDevice{
device: device,
tags: map[string]string{
"type": "accelerator",
"type-id": str_i,
},
meta: map[string]string{
"source": m.name,
"group": "AMD",
},
}
if m.config.UsePciInfoAsTypeId {
dev.tags["type-id"] = pciId
} else if m.config.AddPciInfoTag {
dev.tags["pci_identifier"] = pciId
}
if m.config.AddSerialMeta {
serial, ret := rocm_smi.DeviceGetSerialNumber(device)
if ret != rocm_smi.STATUS_SUCCESS {
cclog.ComponentError(m.name, "Unable to get serial number for device at index", i, ":", rocm_smi.StatusStringNoError(ret))
} else {
dev.meta["serial"] = serial
}
}
// Add excluded metrics
dev.excludeMetrics = map[string]bool{}
for _, e := range m.config.ExcludeMetrics {
dev.excludeMetrics[e] = true
}
dev.index = i
m.devices = append(m.devices, dev)
}
// Set this flag only if everything is initialized properly, all required files exist, ...
m.init = true
return err
}
// 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.CCMetric) {
// Create a sample metric
timestamp := time.Now()
for _, dev := range m.devices {
metrics, ret := rocm_smi.DeviceGetMetrics(dev.device)
if ret != rocm_smi.STATUS_SUCCESS {
cclog.ComponentError(m.name, "Unable to get metrics for device at index", dev.index, ":", rocm_smi.StatusStringNoError(ret))
continue
}
if !dev.excludeMetrics["rocm_gfx_util"] {
value := metrics.Average_gfx_activity
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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.New("rocm_d1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil {
output <- y
}
}
if !dev.excludeMetrics["rocm_temp_hbm"] {
for i := 0; i < rocm_smi.NUM_HBM_INSTANCES; i++ {
value := metrics.Temperature_hbm[i]
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))
output <- y
}
}
}
}
}
// Close metric collector: close network connection, close files, close libraries, ...
// Called once by the collector manager
func (m *RocmSmiCollector) Close() {
// Unset flag
ret := rocm_smi.Shutdown()
if ret != rocm_smi.STATUS_SUCCESS {
cclog.ComponentError(m.name, "Failed to shutdown ROCm SMI library")
}
m.init = false
}

View File

@@ -1,47 +0,0 @@
## `rocm_smi` collector
```json
"rocm_smi": {
"exclude_devices": [
"0","1", "0000000:ff:01.0"
],
"exclude_metrics": [
"rocm_mm_util",
"rocm_temp_vrsoc"
],
"use_pci_info_as_type_id": true,
"add_pci_info_tag": false,
"add_serial_meta": false,
}
```
The `rocm_smi` collector can be configured to leave out specific devices with the `exclude_devices` option. It takes logical IDs in the list of available devices or the PCI address similar to NVML format (`%08X:%02X:%02X.0`). Metrics (listed below) that should not be sent to the MetricRouter can be excluded with the `exclude_metrics` option.
The metrics sent by the `rocm_smi` collector use `accelerator` as `type` tag. For the `type-id`, it uses the device handle index by default. With the `use_pci_info_as_type_id` option, the PCI ID is used instead. If both values should be added as tags, activate the `add_pci_info_tag` option. It uses the device handle index as `type-id` and adds the PCI ID as separate `pci_identifier` tag.
Optionally, it is possible to add the serial to the meta informations. They are not sent to the sinks (if not configured otherwise).
Metrics:
* `rocm_gfx_util`
* `rocm_umc_util`
* `rocm_mm_util`
* `rocm_avg_power`
* `rocm_temp_mem`
* `rocm_temp_hotspot`
* `rocm_temp_edge`
* `rocm_temp_vrgfx`
* `rocm_temp_vrsoc`
* `rocm_temp_vrmem`
* `rocm_gfx_clock`
* `rocm_soc_clock`
* `rocm_u_clock`
* `rocm_v0_clock`
* `rocm_v1_clock`
* `rocm_d0_clock`
* `rocm_d1_clock`
* `rocm_temp_hbm`
Some metrics add the additional sub type tag (`stype`) like the `rocm_temp_hbm` metrics set `stype=device,stype-id=<HBM_slice_number>`.

View File

@@ -4,8 +4,9 @@ import (
"encoding/json"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
// These are the fields we read from the JSON configuration
@@ -17,9 +18,10 @@ type SampleCollectorConfig struct {
// defined by metricCollector (name, init, ...)
type SampleCollector struct {
metricCollector
config SampleCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
config SampleTimerCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
statsCount int64
}
// Functions to implement MetricCollector interface
@@ -35,23 +37,14 @@ func (m *SampleCollector) Init(config json.RawMessage) error {
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, ...)
// or it should be run serially, mostly for collectors actually doing measurements
// because they should not measure the execution of the other collectors
m.parallel = true
// Define meta information sent with each metric
// (Can also be dynamic or this is the basic set with extension through AddMeta())
m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
// Define tags sent with each metric
// The 'type' tag is always needed, it defines the granularity of the metric
// The 'type' tag is always needed, it defines the granulatity of the metric
// node -> whole system
// socket -> CPU socket (requires socket ID as 'type-id' tag)
// die -> CPU die (requires CPU die ID as 'type-id' tag)
// memoryDomain -> NUMA domain (requires NUMA domain ID as 'type-id' tag)
// llc -> Last level cache (requires last level cache ID as 'type-id' tag)
// core -> single CPU core that may consist of multiple hardware threads (SMT) (requires core ID as 'type-id' tag)
// hwthtread -> single CPU hardware thread (requires hardware thread ID as 'type-id' tag)
// accelerator -> A accelerator device like GPU or FPGA (requires an accelerator ID as 'type-id' tag)
// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
m.tags = map[string]string{"type": "node"}
// Read in the JSON configuration
if len(config) > 0 {
@@ -67,6 +60,9 @@ func (m *SampleCollector) Init(config json.RawMessage) error {
// for all topological entities (sockets, NUMA domains, ...)
// Return some useful error message in case of any failures
// Initialize counts for statistics
m.statsCount = 0
// Set this flag only if everything is initialized properly, all required files exist, ...
m.init = true
return err
@@ -89,8 +85,11 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric)
if err == nil {
// Send it to output channel
output <- y
// increment count for each sent metric or any other operation
m.statsCount++
}
// Set stats for the component
stats.ComponentStatInt(m.name, "count", m.statsCount)
}
// Close metric collector: close network connection, close files, close libraries, ...

View File

@@ -5,8 +5,8 @@ import (
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
)
// These are the fields we read from the JSON configuration
@@ -38,7 +38,7 @@ func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
// (Can also be dynamic or this is the basic set with extension through AddMeta())
m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
// Define tags sent with each metric
// The 'type' tag is always needed, it defines the granularity of the metric
// The 'type' tag is always needed, it defines the granulatity of the metric
// node -> whole system
// socket -> CPU socket (requires socket ID as 'type-id' tag)
// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
@@ -60,7 +60,7 @@ func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
// Storage for output channel
m.output = nil
// Management channel for the timer function.
// Mangement channel for the timer function.
m.done = make(chan bool)
// Create the own ticker
m.ticker = time.NewTicker(m.interval)
@@ -94,7 +94,7 @@ func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
value := 1.0
// If you want to measure something for a specific amount of time, use interval
// If you want to measure something for a specific amout of time, use interval
// start := readState()
// time.Sleep(interval)
// stop := readState()

View File

@@ -1,154 +0,0 @@
package collectors
import (
"bufio"
"encoding/json"
"fmt"
"math"
"os"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
const SCHEDSTATFILE = `/proc/schedstat`
// These are the fields we read from the JSON configuration
type SchedstatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
}
// This contains all variables we need during execution and the variables
// defined by metricCollector (name, init, ...)
type SchedstatCollector struct {
metricCollector
config SchedstatCollectorConfig // the configuration structure
lastTimestamp time.Time // Store time stamp of last tick to derive values
meta map[string]string // default meta information
cputags map[string]map[string]string // default tags
olddata map[string]map[string]int64 // default tags
}
// Functions to implement MetricCollector interface
// Init(...), Read(...), Close()
// See: metricCollector.go
// Init initializes the sample collector
// Called once by the collector manager
// All tags, meta data tags and metrics that do not change over the runtime should be set here
func (m *SchedstatCollector) 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 = "SchedstatCollector"
// This is for later use, also call it early
m.setup()
// Tell whether the collector should be run in parallel with others (reading files, ...)
// or it should be run serially, mostly for collectors acutally doing measurements
// because they should not measure the execution of the other collectors
m.parallel = true
// Define meta information sent with each metric
// (Can also be dynamic or this is the basic set with extension through AddMeta())
m.meta = map[string]string{"source": m.name, "group": "SCHEDSTAT"}
// Read in the JSON configuration
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
cclog.ComponentError(m.name, "Error reading config:", err.Error())
return err
}
}
// Check input file
file, err := os.Open(string(SCHEDSTATFILE))
if err != nil {
cclog.ComponentError(m.name, err.Error())
}
defer file.Close()
// Pre-generate tags for all CPUs
num_cpus := 0
m.cputags = make(map[string]map[string]string)
m.olddata = make(map[string]map[string]int64)
scanner := bufio.NewScanner(file)
for scanner.Scan() {
line := scanner.Text()
linefields := strings.Fields(line)
if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
cpustr := strings.TrimLeft(linefields[0], "cpu")
cpu, _ := strconv.Atoi(cpustr)
running, _ := strconv.ParseInt(linefields[7], 10, 64)
waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
m.olddata[linefields[0]] = map[string]int64{"running": running, "waiting": waiting}
num_cpus++
}
}
// Save current timestamp
m.lastTimestamp = time.Now()
// Set this flag only if everything is initialized properly, all required files exist, ...
m.init = true
return err
}
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"]
diff_waiting := waiting - m.olddata[linefields[0]]["waiting"]
var l_running float64 = float64(diff_running) / tsdelta.Seconds() / (math.Pow(1000, 3))
var l_waiting float64 = float64(diff_waiting) / tsdelta.Seconds() / (math.Pow(1000, 3))
m.olddata[linefields[0]]["running"] = running
m.olddata[linefields[0]]["waiting"] = waiting
value := l_running + l_waiting
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
}
}
// 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.CCMetric) {
if !m.init {
return
}
//timestamps
now := time.Now()
tsdelta := now.Sub(m.lastTimestamp)
file, err := os.Open(string(SCHEDSTATFILE))
if err != nil {
cclog.ComponentError(m.name, err.Error())
}
defer file.Close()
scanner := bufio.NewScanner(file)
for scanner.Scan() {
line := scanner.Text()
linefields := strings.Fields(line)
if strings.HasPrefix(linefields[0], "cpu") {
m.ParseProcLine(linefields, m.cputags[linefields[0]], output, now, tsdelta)
}
}
m.lastTimestamp = now
}
// Close metric collector: close network connection, close files, close libraries, ...
// Called once by the collector manager
func (m *SchedstatCollector) Close() {
// Unset flag
m.init = false
}

View File

@@ -1,11 +0,0 @@
## `schedstat` collector
```json
"schedstat": {
}
```
The `schedstat` collector reads data from /proc/schedstat and calculates a load value, separated by hwthread. This might be useful to detect bad cpu pinning on shared nodes etc.
Metric:
* `cpu_load_core`

View File

@@ -1,144 +0,0 @@
package collectors
import (
"encoding/json"
"runtime"
"syscall"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
type SelfCollectorConfig struct {
MemStats bool `json:"read_mem_stats"`
GoRoutines bool `json:"read_goroutines"`
CgoCalls bool `json:"read_cgo_calls"`
Rusage bool `json:"read_rusage"`
}
type SelfCollector struct {
metricCollector
config SelfCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
}
func (m *SelfCollector) Init(config json.RawMessage) error {
var err error = nil
m.name = "SelfCollector"
m.setup()
m.parallel = true
m.meta = map[string]string{"source": m.name, "group": "Self"}
m.tags = map[string]string{"type": "node"}
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
cclog.ComponentError(m.name, "Error reading config:", err.Error())
return err
}
}
m.init = true
return err
}
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.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.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.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.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.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.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.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.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.New("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp)
if err == nil {
output <- y
}
}
if m.config.Rusage {
var rusage syscall.Rusage
err := syscall.Getrusage(syscall.RUSAGE_SELF, &rusage)
if err == nil {
sec, nsec := rusage.Utime.Unix()
t := float64(sec) + (float64(nsec) * 1e-9)
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.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.New("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp)
if err == nil {
output <- y
}
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.New("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp)
if err == nil {
output <- y
}
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.New("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp)
if err == nil {
output <- y
}
}
}
}
func (m *SelfCollector) Close() {
m.init = false
}

View File

@@ -1,34 +0,0 @@
## `self` collector
```json
"self": {
"read_mem_stats" : true,
"read_goroutines" : true,
"read_cgo_calls" : true,
"read_rusage" : true
}
```
The `self` collector reads the data from the `runtime` and `syscall` packages, so monitors the execution of the cc-metric-collector itself.
Metrics:
* If `read_mem_stats == true`:
* `total_alloc`: The metric reports cumulative bytes allocated for heap objects.
* `heap_alloc`: The metric reports bytes of allocated heap objects.
* `heap_sys`: The metric reports bytes of heap memory obtained from the OS.
* `heap_idle`: The metric reports bytes in idle (unused) spans.
* `heap_inuse`: The metric reports bytes in in-use spans.
* `heap_released`: The metric reports bytes of physical memory returned to the OS.
* `heap_objects`: The metric reports the number of allocated heap objects.
* If `read_goroutines == true`:
* `num_goroutines`: The metric reports the number of goroutines that currently exist.
* If `read_cgo_calls == true`:
* `num_cgo_calls`: The metric reports the number of cgo calls made by the current process.
* If `read_rusage == true`:
* `rusage_user_time`: The metric reports the amount of time that this process has been scheduled in user mode.
* `rusage_system_time`: The metric reports the amount of time that this process has been scheduled in kernel mode.
* `rusage_vol_ctx_switch`: The metric reports the amount of voluntary context switches.
* `rusage_invol_ctx_switch`: The metric reports the amount of involuntary context switches.
* `rusage_signals`: The metric reports the number of signals received.
* `rusage_major_pgfaults`: The metric reports the number of major faults the process has made which have required loading a memory page from disk.
* `rusage_minor_pgfaults`: The metric reports the number of minor faults the process has made which have not required loading a memory page from disk.

View File

@@ -3,14 +3,15 @@ package collectors
import (
"encoding/json"
"fmt"
"os"
"io/ioutil"
"path/filepath"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
// See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
@@ -40,7 +41,8 @@ type TempCollector struct {
ReportMaxTemp bool `json:"report_max_temperature"`
ReportCriticalTemp bool `json:"report_critical_temperature"`
}
sensors []*TempCollectorSensor
sensors []*TempCollectorSensor
statsProcessedMetrics int64
}
func (m *TempCollector) Init(config json.RawMessage) error {
@@ -50,7 +52,6 @@ func (m *TempCollector) Init(config json.RawMessage) error {
}
m.name = "TempCollector"
m.parallel = true
m.setup()
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
@@ -83,14 +84,14 @@ func (m *TempCollector) Init(config json.RawMessage) error {
// sensor name
nameFile := filepath.Join(filepath.Dir(file), "name")
name, err := os.ReadFile(nameFile)
name, err := ioutil.ReadFile(nameFile)
if err == nil {
sensor.name = strings.TrimSpace(string(name))
}
// sensor label
labelFile := strings.TrimSuffix(file, "_input") + "_label"
label, err := os.ReadFile(labelFile)
label, err := ioutil.ReadFile(labelFile)
if err == nil {
sensor.label = strings.TrimSpace(string(label))
}
@@ -117,10 +118,6 @@ func (m *TempCollector) Init(config json.RawMessage) error {
}
// Sensor file
_, err = os.ReadFile(file)
if err != nil {
continue
}
sensor.file = file
// Sensor tags
@@ -139,7 +136,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
// max temperature
if m.config.ReportMaxTemp {
maxTempFile := strings.TrimSuffix(file, "_input") + "_max"
if buffer, err := os.ReadFile(maxTempFile); err == nil {
if buffer, err := ioutil.ReadFile(maxTempFile); err == nil {
if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
sensor.maxTempName = strings.Replace(sensor.metricName, "temp", "max_temp", 1)
sensor.maxTemp = x / 1000
@@ -150,7 +147,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
// critical temperature
if m.config.ReportCriticalTemp {
criticalTempFile := strings.TrimSuffix(file, "_input") + "_crit"
if buffer, err := os.ReadFile(criticalTempFile); err == nil {
if buffer, err := ioutil.ReadFile(criticalTempFile); err == nil {
if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
sensor.critTempName = strings.Replace(sensor.metricName, "temp", "crit_temp", 1)
sensor.critTemp = x / 1000
@@ -167,6 +164,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
}
// Finished initialization
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -175,7 +173,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
for _, sensor := range m.sensors {
// Read sensor file
buffer, err := os.ReadFile(sensor.file)
buffer, err := ioutil.ReadFile(sensor.file)
if err != nil {
cclog.ComponentError(
m.name,
@@ -199,6 +197,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
)
if err == nil {
output <- y
m.statsProcessedMetrics++
}
// max temperature
@@ -212,6 +211,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
)
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
@@ -226,10 +226,11 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
)
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *TempCollector) Close() {

View File

@@ -9,7 +9,8 @@ import (
"strings"
"time"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
stats "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
)
const MAX_NUM_PROCS = 10
@@ -21,14 +22,14 @@ type TopProcsCollectorConfig struct {
type TopProcsCollector struct {
metricCollector
tags map[string]string
config TopProcsCollectorConfig
tags map[string]string
config TopProcsCollectorConfig
statsProcessedMetrics int64
}
func (m *TopProcsCollector) Init(config json.RawMessage) error {
var err error
m.name = "TopProcsCollector"
m.parallel = true
m.tags = map[string]string{"type": "node"}
m.meta = map[string]string{"source": m.name, "group": "TopProcs"}
if len(config) > 0 {
@@ -49,6 +50,7 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
if err != nil {
return errors.New("failed to execute command")
}
m.statsProcessedMetrics = 0
m.init = true
return nil
}
@@ -71,8 +73,10 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMetric
y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now())
if err == nil {
output <- y
m.statsProcessedMetrics++
}
}
stats.ComponentStatInt(m.name, "processed_metrics", m.statsProcessedMetrics)
}
func (m *TopProcsCollector) Close() {

View File

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

View File

@@ -1,74 +0,0 @@
# Building the cc-metric-collector
In most cases, a simple `make` in the main folder is enough to get a `cc-metric-collector` binary. It is basically a `go build` but some collectors require additional tasks. There is currently no Golang interface to LIKWID, so it uses `cgo` to create bindings but `cgo` requires the LIKWID header files. Therefore, it checks whether LIKWID is installed and if not it downloads LIKWID and copies the headers.
## System integration
The main configuration settings for system integration are pre-defined in `scripts/cc-metric-collector.config`. The file contains the UNIX user and group used for execution, the PID file location and other settings. Adjust it accordingly and copy it to `/etc/default/cc-metric-collector`
```bash
$ install --mode 644 \
--owner $CC_USER \
--group $CC_GROUP \
scripts/cc-metric-collector.config /etc/default/cc-metric-collector
$ edit /etc/default/cc-metric-collector
```
### SysVinit and similar
If you are using a init system based in `/etc/init.d` daemons, you can use the sample `scripts/cc-metric-collector.init`. It reads the basic configuration from `/etc/default/cc-metric-collector`
```bash
$ install --mode 755 \
--owner $CC_USER \
--group $CC_GROUP \
scripts/cc-metric-collector.init /etc/init.d/cc-metric-collector
```
### Systemd
If you are using `systemd` as init system, you can use the sample systemd service file `scripts/cc-metric-collector.service`, the configuration file `scripts/cc-metric-collector.config`.
```bash
$ install --mode 644 \
--owner $CC_USER \
--group $CC_GROUP \
scripts/cc-metric-collector.service /etc/systemd/system/cc-metric-collector.service
$ systemctl enable cc-metric-collector
```
## Packaging
### RPM
In order to get a RPM packages for cc-metric-collector, just use:
```bash
$ make RPM
```
It uses the RPM SPEC file `scripts/cc-metric-collector.spec` and requires the RPM tools (`rpm` and `rpmspec`) and `git`.
### DEB
In order to get very simple Debian packages for cc-metric-collector, just use:
```bash
$ make DEB
```
It uses the DEB control file `scripts/cc-metric-collector.control` and requires `dpkg-deb`, `awk`, `sed` and `git`. It creates only a binary deb package.
_This option is not well tested and therefore experimental_
### Customizing RPMs or DEB packages
If you want to customize the RPMs or DEB packages for your local system, use the following workflow.
- (if there is already a fork in the private account, delete it and wait until Github realizes the deletion)
- Fork the cc-metric-collector repository (if Github hasn't realized it, it creates a fork named cc-metric-collector2)
- Go to private cc-metric-collector repository and enable Github Actions
- Do changes to the scripts, code, ... Commit and push your changes.
- Tag the new commit with `v0.x.y-<myversion>` (`git tag v0.x.y-<myversion>`)
- Push tags to repository (`git push --tags`)
- Wait until the Release action finishes. It creates fresh RPMs and DEBs in your private repository on the Releases page.

View File

@@ -1,23 +0,0 @@
# The ClusterCockpit Project
The ClusterCockpit project is a joined project of computing centers in Europe to set up a cluster monitoring stack for small to mid-sized computing centers under the lead of NHR@FAU.
# The ClusterCockpit Stack
In cluster environment, there are commonly a lot of systems dedicated for computation, backend servers for file systems and frontend servers for the user interaction and cluster control. The ClusterCockpit Stack is mainly used for monitoring the compute systems with some interaction to the frontend servers. It consists of multiple components:
- cc-metric-collector: Monitor resource usage on the compute systems
- cc-metric-store: In-memory database
- cc-backend & cc-frontend: The web-based visualizer
# CC Metric Collector
The CC Metric Collector project was started to provide a useful set of metrics for HPC and data science related compute systems. It runs as a system daemon and gathers system data periodically to forward the metrics to one or more databases. One of the provided backends can be used for the cc-metric-store but many others exist like InfluxDB time-series databases, the Ganglia Monitoring System or the Prometheus Monitoring System.
The data is gathered by so-called "Collectors", forwarded to an internal router for on-the-fly manipulation (tagging, aggregation, ...) which pushes the metrics to the different metric writers called "Sinks". There is a forth component, the "Receivers", which receive data through some networking system like a HTTP server at any time.
# CC Metric Store
The CC Metric Store is a data management system with short-term in-memory and long-term file-base metric storage.
# CC Backend and CC Frontend
The CC Backend and Frontend form together the web interface for ClusterCockpit.

107
go.mod
View File

@@ -1,106 +1,19 @@
module github.com/ClusterCockpit/cc-metric-collector
go 1.20
go 1.16
require (
github.com/ClusterCockpit/cc-units v0.4.0
github.com/ClusterCockpit/go-rocm-smi v0.3.0
github.com/NVIDIA/go-nvml v0.12.0-1
github.com/PaesslerAG/gval v1.2.2
github.com/fsnotify/fsnotify v1.6.0
github.com/gorilla/mux v1.8.0
github.com/gosnmp/gosnmp v1.37.0
github.com/influxdata/influxdb-client-go/v2 v2.12.3
github.com/NVIDIA/go-nvml v0.11.1-0
github.com/influxdata/influxdb-client-go/v2 v2.7.0
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 v1.30.2
github.com/prometheus/client_golang v1.17.0
github.com/stmcginnis/gofish v0.14.0
github.com/tklauser/go-sysconf v0.3.12
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
golang.org/x/exp v0.0.0-20231006140011-7918f672742d
golang.org/x/sys v0.13.0
github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc
golang.org/x/sys v0.0.0-20220114195835-da31bd327af9
gopkg.in/Knetic/govaluate.v2 v2.3.0
)
require (
github.com/BurntSushi/toml v1.3.2 // indirect
github.com/CloudyKit/fastprinter v0.0.0-20200109182630-33d98a066a53 // indirect
github.com/CloudyKit/jet/v6 v6.2.0 // indirect
github.com/Joker/jade v1.1.3 // indirect
github.com/Shopify/goreferrer v0.0.0-20220729165902-8cddb4f5de06 // indirect
github.com/andybalholm/brotli v1.0.5 // indirect
github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
github.com/aymerick/douceur v0.2.0 // indirect
github.com/beorn7/perks v1.0.1 // indirect
github.com/bytedance/sonic v1.10.2 // indirect
github.com/cespare/xxhash/v2 v2.2.0 // indirect
github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d // indirect
github.com/chenzhuoyu/iasm v0.9.0 // indirect
github.com/deepmap/oapi-codegen v1.15.0 // indirect
github.com/fatih/structs v1.1.0 // indirect
github.com/flosch/pongo2/v4 v4.0.2 // indirect
github.com/gabriel-vasile/mimetype v1.4.2 // indirect
github.com/gin-contrib/sse v0.1.0 // indirect
github.com/gin-gonic/gin v1.9.1 // indirect
github.com/go-playground/locales v0.14.1 // indirect
github.com/go-playground/universal-translator v0.18.1 // indirect
github.com/go-playground/validator/v10 v10.15.5 // indirect
github.com/goccy/go-json v0.10.2 // indirect
github.com/golang/protobuf v1.5.3 // indirect
github.com/golang/snappy v0.0.4 // indirect
github.com/gomarkdown/markdown v0.0.0-20230922112808-5421fefb8386 // indirect
github.com/google/uuid v1.3.1 // indirect
github.com/gorilla/css v1.0.0 // indirect
github.com/iris-contrib/schema v0.0.6 // indirect
github.com/josharian/intern v1.0.0 // indirect
github.com/json-iterator/go v1.1.12 // indirect
github.com/kataras/blocks v0.0.8 // indirect
github.com/kataras/golog v0.1.9 // indirect
github.com/kataras/iris/v12 v12.2.7 // indirect
github.com/kataras/pio v0.0.12 // indirect
github.com/kataras/sitemap v0.0.6 // indirect
github.com/kataras/tunnel v0.0.4 // indirect
github.com/klauspost/compress v1.17.0 // indirect
github.com/klauspost/cpuid/v2 v2.2.5 // indirect
github.com/labstack/echo/v4 v4.11.1 // indirect
github.com/labstack/gommon v0.4.0 // indirect
github.com/leodido/go-urn v1.2.4 // indirect
github.com/mailgun/raymond/v2 v2.0.48 // indirect
github.com/mailru/easyjson v0.7.7 // indirect
github.com/mattn/go-colorable v0.1.13 // indirect
github.com/mattn/go-isatty v0.0.19 // indirect
github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
github.com/microcosm-cc/bluemonday v1.0.25 // indirect
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
github.com/modern-go/reflect2 v1.0.2 // indirect
github.com/nats-io/nats-server/v2 v2.8.4 // indirect
github.com/nats-io/nkeys v0.4.5 // indirect
github.com/nats-io/nuid v1.0.1 // indirect
github.com/pelletier/go-toml/v2 v2.1.0 // indirect
github.com/pkg/errors v0.9.1 // indirect
github.com/prometheus/client_model v0.5.0 // indirect
github.com/prometheus/common v0.44.0 // indirect
github.com/prometheus/procfs v0.12.0 // indirect
github.com/russross/blackfriday/v2 v2.1.0 // indirect
github.com/schollz/closestmatch v2.1.0+incompatible // indirect
github.com/shopspring/decimal v1.3.1 // indirect
github.com/sirupsen/logrus v1.9.3 // indirect
github.com/tdewolff/minify/v2 v2.12.9 // indirect
github.com/tdewolff/parse/v2 v2.6.8 // indirect
github.com/tklauser/numcpus v0.6.1 // indirect
github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
github.com/ugorji/go/codec v1.2.11 // indirect
github.com/valyala/bytebufferpool v1.0.0 // indirect
github.com/valyala/fasttemplate v1.2.2 // indirect
github.com/vmihailenco/msgpack/v5 v5.4.0 // indirect
github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
github.com/yosssi/ace v0.0.5 // indirect
golang.org/x/arch v0.5.0 // indirect
golang.org/x/crypto v0.14.0 // indirect
golang.org/x/net v0.16.0 // indirect
golang.org/x/text v0.13.0 // indirect
golang.org/x/time v0.3.0 // indirect
google.golang.org/protobuf v1.31.0 // indirect
gopkg.in/ini.v1 v1.67.0 // indirect
gopkg.in/yaml.v3 v3.0.1 // indirect
github.com/PaesslerAG/gval v1.1.2
github.com/golang/protobuf v1.5.2 // indirect
github.com/nats-io/nats-server/v2 v2.7.0 // indirect
google.golang.org/protobuf v1.27.1 // indirect
)

398
go.sum
View File

@@ -1,331 +1,145 @@
github.com/BurntSushi/toml v1.3.2 h1:o7IhLm0Msx3BaB+n3Ag7L8EVlByGnpq14C4YWiu/gL8=
github.com/BurntSushi/toml v1.3.2/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ=
github.com/CloudyKit/fastprinter v0.0.0-20200109182630-33d98a066a53 h1:sR+/8Yb4slttB4vD+b9btVEnWgL3Q00OBTzVT8B9C0c=
github.com/CloudyKit/fastprinter v0.0.0-20200109182630-33d98a066a53/go.mod h1:+3IMCy2vIlbG1XG/0ggNQv0SvxCAIpPM5b1nCz56Xno=
github.com/CloudyKit/jet/v6 v6.2.0 h1:EpcZ6SR9n28BUGtNJSvlBqf90IpjeFr36Tizxhn/oME=
github.com/CloudyKit/jet/v6 v6.2.0/go.mod h1:d3ypHeIRNo2+XyqnGA8s+aphtcVpjP5hPwP/Lzo7Ro4=
github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoONEOh4cI0=
github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw=
github.com/ClusterCockpit/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8=
github.com/ClusterCockpit/go-rocm-smi v0.3.0/go.mod h1:+I3UMeX3OlizXDf1WpGD43W4KGZZGVSGmny6rTeOnWA=
github.com/Joker/hpp v1.0.0 h1:65+iuJYdRXv/XyN62C1uEmmOx3432rNG/rKlX6V7Kkc=
github.com/Joker/hpp v1.0.0/go.mod h1:8x5n+M1Hp5hC0g8okX3sR3vFQwynaX/UgSOM9MeBKzY=
github.com/Joker/jade v1.1.3 h1:Qbeh12Vq6BxURXT1qZBRHsDxeURB8ztcL6f3EXSGeHk=
github.com/Joker/jade v1.1.3/go.mod h1:T+2WLyt7VH6Lp0TRxQrUYEs64nRc83wkMQrfeIQKduM=
github.com/NVIDIA/go-nvml v0.11.6-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
github.com/NVIDIA/go-nvml v0.12.0-1 h1:6mdjtlFo+17dWL7VFPfuRMtf0061TF4DKls9pkSw6uM=
github.com/NVIDIA/go-nvml v0.12.0-1/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E=
github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
github.com/NVIDIA/go-nvml v0.11.1-0 h1:XHSz3zZKC4NCP2ja1rI7++DXFhA+uDhdYa3MykCTGHY=
github.com/NVIDIA/go-nvml v0.11.1-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
github.com/PaesslerAG/gval v1.1.2 h1:EROKxV4/fAKWb0Qoj7NOxmHZA7gcpjOV9XgiRZMRCUU=
github.com/PaesslerAG/gval v1.1.2/go.mod h1:Fa8gfkCmUsELXgayr8sfL/sw+VzCVoa03dcOcR/if2w=
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/Shopify/goreferrer v0.0.0-20220729165902-8cddb4f5de06 h1:KkH3I3sJuOLP3TjA/dfr4NAY8bghDwnXiU7cTKxQqo0=
github.com/Shopify/goreferrer v0.0.0-20220729165902-8cddb4f5de06/go.mod h1:7erjKLwalezA0k99cWs5L11HWOAPNjdUZ6RxH1BXbbM=
github.com/ajg/form v1.5.1 h1:t9c7v8JUKu/XxOGBU0yjNpaMloxGEJhUkqFRq0ibGeU=
github.com/andybalholm/brotli v1.0.5 h1:8uQZIdzKmjc/iuPu7O2ioW48L81FgatrcpfFmiq/cCs=
github.com/andybalholm/brotli v1.0.5/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig=
github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk=
github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
github.com/bytedance/sonic v1.10.0-rc/go.mod h1:ElCzW+ufi8qKqNW0FY314xriJhyJhuoJ3gFZdAHF7NM=
github.com/bytedance/sonic v1.10.2 h1:GQebETVBxYB7JGWJtLBi07OVzWwt+8dWA00gEVW2ZFE=
github.com/bytedance/sonic v1.10.2/go.mod h1:iZcSUejdk5aukTND/Eu/ivjQuEL0Cu9/rf50Hi0u/g4=
github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d h1:77cEq6EriyTZ0g/qfRdp61a3Uu/AWrgIq2s0ClJV1g0=
github.com/chenzhuoyu/base64x v0.0.0-20230717121745-296ad89f973d/go.mod h1:8EPpVsBuRksnlj1mLy4AWzRNQYxauNi62uWcE3to6eA=
github.com/chenzhuoyu/iasm v0.9.0 h1:9fhXjVzq5hUy2gkhhgHl95zG2cEAhw9OSGs8toWWAwo=
github.com/chenzhuoyu/iasm v0.9.0/go.mod h1:Xjy2NpN3h7aUqeqM+woSuuvxmIe6+DDsiNLIrkAmYog=
github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
github.com/cyberdelia/templates v0.0.0-20141128023046-ca7fffd4298c/go.mod h1:GyV+0YP4qX0UQ7r2MoYZ+AvYDp12OF5yg4q8rGnyNh4=
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/deepmap/oapi-codegen v1.15.0 h1:SQqViaeb4k2vMul8gx12oDOIadEtoRqTdLkxjzqtQ90=
github.com/deepmap/oapi-codegen v1.15.0/go.mod h1:a6KoHV7lMRwsPoEg2C6NDHiXYV3EQfiFocOlJ8dgJQE=
github.com/fatih/color v1.15.0 h1:kOqh6YHBtK8aywxGerMG2Eq3H6Qgoqeo13Bk2Mv/nBs=
github.com/fatih/structs v1.1.0 h1:Q7juDM0QtcnhCpeyLGQKyg4TOIghuNXrkL32pHAUMxo=
github.com/fatih/structs v1.1.0/go.mod h1:9NiDSp5zOcgEDl+j00MP/WkGVPOlPRLejGD8Ga6PJ7M=
github.com/flosch/pongo2/v4 v4.0.2 h1:gv+5Pe3vaSVmiJvh/BZa82b7/00YUGm0PIyVVLop0Hw=
github.com/flosch/pongo2/v4 v4.0.2/go.mod h1:B5ObFANs/36VwxxlgKpdchIJHMvHB562PW+BWPhwZD8=
github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
github.com/frankban/quicktest v1.11.2/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 v1.6.0 h1:n+5WquG0fcWoWp6xPWfHdbskMCQaFnG6PfBrh1Ky4HY=
github.com/fsnotify/fsnotify v1.6.0/go.mod h1:sl3t1tCWJFWoRz9R8WJCbQihKKwmorjAbSClcnxKAGw=
github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
github.com/go-playground/validator/v10 v10.15.5 h1:LEBecTWb/1j5TNY1YYG2RcOUN3R7NLylN+x8TTueE24=
github.com/go-playground/validator/v10 v10.15.5/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
github.com/deepmap/oapi-codegen v1.8.2 h1:SegyeYGcdi0jLLrpbCMoJxnUUn8GBXHsvr4rbzjuhfU=
github.com/deepmap/oapi-codegen v1.8.2/go.mod h1:YLgSKSDv/bZQB7N4ws6luhozi3cEdRktEqrX88CvjIw=
github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
github.com/getkin/kin-openapi v0.61.0/go.mod h1:7Yn5whZr5kJi6t+kShccXS8ae1APpYTW6yheSwk8Yi4=
github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
github.com/go-chi/chi/v5 v5.0.0/go.mod h1:BBug9lr0cqtdAhsu6R4AAdvufI0/XBzAQSsUqJpoZOs=
github.com/go-openapi/jsonpointer v0.19.5/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
github.com/golang/protobuf v1.5.3 h1:KhyjKVUg7Usr/dYsdSqoFveMYd5ko72D+zANwlG1mmg=
github.com/golang/protobuf v1.5.3/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
github.com/golang/snappy v0.0.4 h1:yAGX7huGHXlcLOEtBnF4w7FQwA26wojNCwOYAEhLjQM=
github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
github.com/gomarkdown/markdown v0.0.0-20230922112808-5421fefb8386 h1:EcQR3gusLHN46TAD+G+EbaaqJArt5vHhNpXAa12PQf4=
github.com/gomarkdown/markdown v0.0.0-20230922112808-5421fefb8386/go.mod h1:JDGcbDT52eL4fju3sZ4TeHGsQwhG9nbDV21aMyhwPoA=
github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
github.com/golang/protobuf v1.5.2 h1:ROPKBNFfQgOUMifHyP+KYbvpjbdoFNs+aK7DXlji0Tw=
github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
github.com/golang/snappy v0.0.3/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
github.com/golangci/lint-1 v0.0.0-20181222135242-d2cdd8c08219/go.mod h1:/X8TswGSh1pIozq4ZwCfxS0WA5JGXguxk94ar/4c87Y=
github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
github.com/google/go-cmp v0.4.0/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-querystring v1.1.0 h1:AnCroh3fv4ZBgVIf1Iwtovgjaw/GiKJo8M8yD/fhyJ8=
github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
github.com/google/uuid v1.3.1 h1:KjJaJ9iWZ3jOFZIf1Lqf4laDRCasjl0BCmnEGxkdLb4=
github.com/google/uuid v1.3.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/gorilla/css v1.0.0 h1:BQqNyPTi50JCFMTw/b67hByjMVXZRwGha6wxVGkeihY=
github.com/gorilla/css v1.0.0/go.mod h1:Dn721qIggHpt4+EFCcTLTU/vk5ySda2ReITrtgBl60c=
github.com/gorilla/mux v1.8.0 h1:i40aqfkR1h2SlN9hojwV5ZA91wcXFOvkdNIeFDP5koI=
github.com/gorilla/mux v1.8.0/go.mod h1:DVbg23sWSpFRCP0SfiEN6jmj59UnW/n46BH5rLB71So=
github.com/gorilla/websocket v1.5.0 h1:PPwGk2jz7EePpoHN/+ClbZu8SPxiqlu12wZP/3sWmnc=
github.com/gosnmp/gosnmp v1.37.0 h1:/Tf8D3b9wrnNuf/SfbvO+44mPrjVphBhRtcGg22V07Y=
github.com/gosnmp/gosnmp v1.37.0/go.mod h1:GDH9vNqpsD7f2HvZhKs5dlqSEcAS6s6Qp099oZRCR+M=
github.com/imkira/go-interpol v1.1.0 h1:KIiKr0VSG2CUW1hl1jpiyuzuJeKUUpC8iM1AIE7N1Vk=
github.com/influxdata/influxdb-client-go/v2 v2.12.3 h1:28nRlNMRIV4QbtIUvxhWqaxn0IpXeMSkY/uJa/O/vC4=
github.com/influxdata/influxdb-client-go/v2 v2.12.3/go.mod h1:IrrLUbCjjfkmRuaCiGQg4m2GbkaeJDcuWoxiWdQEbA0=
github.com/influxdata/influxdb-client-go/v2 v2.7.0 h1:QgP5mlBE9sGnzplpnf96pr+p7uqlIlL4W2GAP3n+XZg=
github.com/influxdata/influxdb-client-go/v2 v2.7.0/go.mod h1:Y/0W1+TZir7ypoQZYd2IrnVOKB3Tq6oegAQeSVN/+EU=
github.com/influxdata/line-protocol v0.0.0-20200327222509-2487e7298839/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
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/iris-contrib/httpexpect/v2 v2.15.2 h1:T9THsdP1woyAqKHwjkEsbCnMefsAFvk8iJJKokcJ3Go=
github.com/iris-contrib/schema v0.0.6 h1:CPSBLyx2e91H2yJzPuhGuifVRnZBBJ3pCOMbOvPZaTw=
github.com/iris-contrib/schema v0.0.6/go.mod h1:iYszG0IOsuIsfzjymw1kMzTL8YQcCWlm65f3wX8J5iA=
github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
github.com/kataras/blocks v0.0.8 h1:MrpVhoFTCR2v1iOOfGng5VJSILKeZZI+7NGfxEh3SUM=
github.com/kataras/blocks v0.0.8/go.mod h1:9Jm5zx6BB+06NwA+OhTbHW1xkMOYxahnqTN5DveZ2Yg=
github.com/kataras/golog v0.1.9 h1:vLvSDpP7kihFGKFAvBSofYo7qZNULYSHOH2D7rPTKJk=
github.com/kataras/golog v0.1.9/go.mod h1:jlpk/bOaYCyqDqH18pgDHdaJab72yBE6i0O3s30hpWY=
github.com/kataras/iris/v12 v12.2.7 h1:C9KWZmZT5pB5f2ot1XYWDBdi5XeTz0CGweHRXCDARZg=
github.com/kataras/iris/v12 v12.2.7/go.mod h1:mD76k/tIBFy8pHTFIgUPrVrkI4lTKvFbIcfbStJSBnA=
github.com/kataras/pio v0.0.12 h1:o52SfVYauS3J5X08fNjlGS5arXHjW/ItLkyLcKjoH6w=
github.com/kataras/pio v0.0.12/go.mod h1:ODK/8XBhhQ5WqrAhKy+9lTPS7sBf6O3KcLhc9klfRcY=
github.com/kataras/sitemap v0.0.6 h1:w71CRMMKYMJh6LR2wTgnk5hSgjVNB9KL60n5e2KHvLY=
github.com/kataras/sitemap v0.0.6/go.mod h1:dW4dOCNs896OR1HmG+dMLdT7JjDk7mYBzoIRwuj5jA4=
github.com/kataras/tunnel v0.0.4 h1:sCAqWuJV7nPzGrlb0os3j49lk2JhILT0rID38NHNLpA=
github.com/kataras/tunnel v0.0.4/go.mod h1:9FkU4LaeifdMWqZu7o20ojmW4B7hdhv2CMLwfnHGpYw=
github.com/klauspost/compress v1.17.0 h1:Rnbp4K9EjcDuVuHtd0dgA4qNuv9yKDYKK1ulpJwgrqM=
github.com/klauspost/compress v1.17.0/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
github.com/klauspost/cpuid/v2 v2.2.5 h1:0E5MSMDEoAulmXNFquVs//DdoomxaoTY1kUhbc/qbZg=
github.com/klauspost/cpuid/v2 v2.2.5/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws=
github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/klauspost/compress v1.13.4 h1:0zhec2I8zGnjWcKyLl6i3gPqKANCCn5e9xmviEEeX6s=
github.com/klauspost/compress v1.13.4/go.mod h1:8dP1Hq4DHOhN9w426knH3Rhby4rFm6D8eO+e+Dq5Gzg=
github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
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/labstack/echo/v4 v4.11.1 h1:dEpLU2FLg4UVmvCGPuk/APjlH6GDpbEPti61srUUUs4=
github.com/labstack/echo/v4 v4.11.1/go.mod h1:YuYRTSM3CHs2ybfrL8Px48bO6BAnYIN4l8wSTMP6BDQ=
github.com/labstack/gommon v0.4.0 h1:y7cvthEAEbU0yHOf4axH8ZG2NH8knB9iNSoTO8dyIk8=
github.com/labstack/gommon v0.4.0/go.mod h1:uW6kP17uPlLJsD3ijUYn3/M5bAxtlZhMI6m3MFxTMTM=
github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
github.com/mailgun/raymond/v2 v2.0.48 h1:5dmlB680ZkFG2RN/0lvTAghrSxIESeu9/2aeDqACtjw=
github.com/mailgun/raymond/v2 v2.0.48/go.mod h1:lsgvL50kgt1ylcFJYZiULi5fjPBkkhNfj4KA0W54Z18=
github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
github.com/mattn/go-colorable v0.1.11/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
github.com/microcosm-cc/bluemonday v1.0.25 h1:4NEwSfiJ+Wva0VxN5B8OwMicaJvD8r9tlJWm9rtloEg=
github.com/microcosm-cc/bluemonday v1.0.25/go.mod h1:ZIOjCQp1OrzBBPIJmfX4qDYFuhU02nx4bn030ixfHLE=
github.com/minio/highwayhash v1.0.2 h1:Aak5U0nElisjDCfPSG79Tgzkn2gl66NxOMspRrKnA/g=
github.com/mitchellh/go-wordwrap v1.0.1 h1:TLuKupo69TCn6TQSyGxwI1EblZZEsQ0vMlAFQflz0v0=
github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
github.com/nats-io/jwt/v2 v2.5.0 h1:WQQ40AAlqqfx+f6ku+i0pOVm+ASirD4fUh+oQsiE9Ak=
github.com/nats-io/nats-server/v2 v2.8.4 h1:0jQzze1T9mECg8YZEl8+WYUXb9JKluJfCBriPUtluB4=
github.com/nats-io/nats-server/v2 v2.8.4/go.mod h1:8zZa+Al3WsESfmgSs98Fi06dRWLH5Bnq90m5bKD/eT4=
github.com/nats-io/nats.go v1.30.2 h1:aloM0TGpPorZKQhbAkdCzYDj+ZmsJDyeo3Gkbr72NuY=
github.com/nats-io/nats.go v1.30.2/go.mod h1:dcfhUgmQNN4GJEfIb2f9R7Fow+gzBF4emzDHrVBd5qM=
github.com/nats-io/nkeys v0.4.5 h1:Zdz2BUlFm4fJlierwvGK+yl20IAKUm7eV6AAZXEhkPk=
github.com/nats-io/nkeys v0.4.5/go.mod h1:XUkxdLPTufzlihbamfzQ7mw/VGx6ObUs+0bN5sNvt64=
github.com/labstack/echo/v4 v4.2.1/go.mod h1:AA49e0DZ8kk5jTOOCKNuPR6oTnBS0dYiM4FW1e6jwpg=
github.com/labstack/gommon v0.3.0/go.mod h1:MULnywXg0yavhxWKc+lOruYdAhDwPK9wf0OL7NoOu+k=
github.com/mailru/easyjson v0.0.0-20190614124828-94de47d64c63/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
github.com/mailru/easyjson v0.0.0-20190626092158-b2ccc519800e/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
github.com/matryer/moq v0.0.0-20190312154309-6cfb0558e1bd/go.mod h1:9ELz6aaclSIGnZBoaSLZ3NAl1VTufbOrXBPvtcy6WiQ=
github.com/mattn/go-colorable v0.1.2/go.mod h1:U0ppj6V5qS13XJ6of8GYAs25YV2eR4EVcfRqFIhoBtE=
github.com/mattn/go-colorable v0.1.7/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
github.com/mattn/go-isatty v0.0.9/go.mod h1:YNRxwqDuOph6SZLI9vUUz6OYw3QyUt7WiY2yME+cCiQ=
github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
github.com/minio/highwayhash v1.0.1 h1:dZ6IIu8Z14VlC0VpfKofAhCy74wu/Qb5gcn52yWoz/0=
github.com/minio/highwayhash v1.0.1/go.mod h1:BQskDq+xkJ12lmlUUi7U0M5Swg3EWR+dLTk+kldvVxY=
github.com/nats-io/jwt/v2 v2.2.1-0.20220113022732-58e87895b296 h1:vU9tpM3apjYlLLeY23zRWJ9Zktr5jp+mloR942LEOpY=
github.com/nats-io/jwt/v2 v2.2.1-0.20220113022732-58e87895b296/go.mod h1:0tqz9Hlu6bCBFLWAASKhE5vUA4c24L9KPUUgvwumE/k=
github.com/nats-io/nats-server/v2 v2.7.0 h1:UpqcAM93FI7AHlCyI2FD5QcV3QuHNCauQF2LBVU0238=
github.com/nats-io/nats-server/v2 v2.7.0/go.mod h1:cjxtMhZsZovK1XS2iiapCduR8HuqB/YpFamL0qntIcw=
github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc h1:SHr4MUUZJ/fAC0uSm2OzWOJYsHpapmR86mpw7q1qPXU=
github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc/go.mod h1:BPko4oXsySz4aSWeFgOHLZs3G4Jq4ZAyE6/zMCxRT6w=
github.com/nats-io/nkeys v0.3.0 h1:cgM5tL53EvYRU+2YLXIK0G2mJtK12Ft9oeooSZMA2G8=
github.com/nats-io/nkeys v0.3.0/go.mod h1:gvUNGjVcM2IPr5rCsRsC6Wb3Hr2CQAm08dsxtV6A5y4=
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/pelletier/go-toml/v2 v2.1.0 h1:FnwAJ4oYMvbT/34k9zzHuZNrhlz48GB3/s6at6/MHO4=
github.com/pelletier/go-toml/v2 v2.1.0/go.mod h1:tJU2Z3ZkXwnxa4DPO899bsyIoywizdUvyaeZurnPPDc=
github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/prometheus/client_golang v1.17.0 h1:rl2sfwZMtSthVU752MqfjQozy7blglC+1SOtjMAMh+Q=
github.com/prometheus/client_golang v1.17.0/go.mod h1:VeL+gMmOAxkS2IqfCq0ZmHSL+LjWfWDUmp1mBz9JgUY=
github.com/prometheus/client_model v0.5.0 h1:VQw1hfvPvk3Uv6Qf29VrPF32JB6rtbgI6cYPYQjL0Qw=
github.com/prometheus/client_model v0.5.0/go.mod h1:dTiFglRmd66nLR9Pv9f0mZi7B7fk5Pm3gvsjB5tr+kI=
github.com/prometheus/common v0.44.0 h1:+5BrQJwiBB9xsMygAB3TNvpQKOwlkc25LbISbrdOOfY=
github.com/prometheus/common v0.44.0/go.mod h1:ofAIvZbQ1e/nugmZGz4/qCb9Ap1VoSTIO7x0VV9VvuY=
github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/sanity-io/litter v1.5.5 h1:iE+sBxPBzoK6uaEP5Lt3fHNgpKcHXc/A2HGETy0uJQo=
github.com/schollz/closestmatch v2.1.0+incompatible h1:Uel2GXEpJqOWBrlyI+oY9LTiyyjYS17cCYRqP13/SHk=
github.com/schollz/closestmatch v2.1.0+incompatible/go.mod h1:RtP1ddjLong6gTkbtmuhtR2uUrrJOpYzYRvbcPAid+g=
github.com/sergi/go-diff v1.0.0 h1:Kpca3qRNrduNnOQeazBd0ysaKrUJiIuISHxogkT9RPQ=
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/sirupsen/logrus v1.8.1/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
github.com/stmcginnis/gofish v0.14.0 h1:geECNAiG33JDB2x2xDkerpOOuXFqxp5YP3EFE3vd5iM=
github.com/stmcginnis/gofish v0.14.0/go.mod h1:BLDSFTp8pDlf/xDbLZa+F7f7eW0E/CHCboggsu8CznI=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/tdewolff/minify/v2 v2.12.9 h1:dvn5MtmuQ/DFMwqf5j8QhEVpPX6fi3WGImhv8RUB4zA=
github.com/tdewolff/minify/v2 v2.12.9/go.mod h1:qOqdlDfL+7v0/fyymB+OP497nIxJYSvX4MQWA8OoiXU=
github.com/tdewolff/parse/v2 v2.6.8 h1:mhNZXYCx//xG7Yq2e/kVLNZw4YfYmeHbhx+Zc0OvFMA=
github.com/tdewolff/parse/v2 v2.6.8/go.mod h1:XHDhaU6IBgsryfdnpzUXBlT6leW/l25yrFBTEb4eIyM=
github.com/tdewolff/test v1.0.9 h1:SswqJCmeN4B+9gEAi/5uqT0qpi1y2/2O47V/1hhGZT0=
github.com/tdewolff/test v1.0.9/go.mod h1:6DAvZliBAAnD7rhVgwaM7DE5/d9NMOAJ09SqYqeK4QE=
github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU=
github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk=
github.com/tklauser/numcpus v0.6.1/go.mod h1:1XfjsgE2zo8GVw7POkMbHENHzVg3GzmoZ9fESEdAacY=
github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6KllzawFIhcdPw=
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
github.com/valyala/fasttemplate v1.0.1/go.mod h1:UQGH1tvbgY+Nz5t2n7tXsz52dQxojPUpymEIMZ47gx8=
github.com/valyala/fasttemplate v1.2.1/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
github.com/valyala/fasttemplate v1.2.2 h1:lxLXG0uE3Qnshl9QyaK6XJxMXlQZELvChBOCmQD0Loo=
github.com/valyala/fasttemplate v1.2.2/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
github.com/vmihailenco/msgpack/v5 v5.4.0 h1:hRM0digJwyR6vll33NNAwCFguy5JuBD6jxDmQP3l608=
github.com/vmihailenco/msgpack/v5 v5.4.0/go.mod h1:GaZTsDaehaPpQVyxrf5mtQlH+pc21PIudVV/E3rRQok=
github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAhO7/IwNM9g=
github.com/vmihailenco/tagparser/v2 v2.0.0/go.mod h1:Wri+At7QHww0WTrCBeu4J6bNtoV6mEfg5OIWRZA9qds=
github.com/xeipuuv/gojsonpointer v0.0.0-20180127040702-4e3ac2762d5f h1:J9EGpcZtP0E/raorCMxlFGSTBrsSlaDGf3jU/qvAE2c=
github.com/xeipuuv/gojsonreference v0.0.0-20180127040603-bd5ef7bd5415 h1:EzJWgHovont7NscjpAxXsDA8S8BMYve8Y5+7cuRE7R0=
github.com/xeipuuv/gojsonschema v1.2.0 h1:LhYJRs+L4fBtjZUfuSZIKGeVu0QRy8e5Xi7D17UxZ74=
github.com/yalp/jsonpath v0.0.0-20180802001716-5cc68e5049a0 h1:6fRhSjgLCkTD3JnJxvaJ4Sj+TYblw757bqYgZaOq5ZY=
github.com/yosssi/ace v0.0.5 h1:tUkIP/BLdKqrlrPwcmH0shwEEhTRHoGnc1wFIWmaBUA=
github.com/yosssi/ace v0.0.5/go.mod h1:ALfIzm2vT7t5ZE7uoIZqF3TQ7SAOyupFZnkrF5id+K0=
github.com/yudai/gojsondiff v1.0.0 h1:27cbfqXLVEJ1o8I6v3y9lg8Ydm53EKqHXAOMxEGlCOA=
github.com/yudai/golcs v0.0.0-20170316035057-ecda9a501e82 h1:BHyfKlQyqbsFN5p3IfnEUduWvb9is428/nNb5L3U01M=
github.com/yuin/goldmark v1.4.1/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg=
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE=
golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
golang.org/x/arch v0.5.0 h1:jpGode6huXQxcskEIpOCvrU+tzo81b6+oFLUYXWtH/Y=
golang.org/x/arch v0.5.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.14.0 h1:wBqGXzWJW6m1XrIKlAH0Hs1JJ7+9KBwnIO8v66Q9cHc=
golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
golang.org/x/exp v0.0.0-20231006140011-7918f672742d h1:jtJma62tbqLibJ5sFQz8bKtEM8rJBtfilJ2qTU199MI=
golang.org/x/exp v0.0.0-20231006140011-7918f672742d/go.mod h1:ldy0pHrwJyGW56pPQzzkH36rKxoZW1tw7ZJpeKx+hdo=
golang.org/x/mod v0.5.1/go.mod h1:5OXOZSfqPIIbmVBIIKWRFfZjPR0E5r58TLhUjH0a2Ro=
golang.org/x/net v0.0.0-20190327091125-710a502c58a2/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/crypto v0.0.0-20200820211705-5c72a883971a/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
golang.org/x/crypto v0.0.0-20201221181555-eec23a3978ad/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
golang.org/x/crypto v0.0.0-20210314154223-e6e6c4f2bb5b/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce h1:Roh6XWxHFKrPgC/EQhVubSAGQ6Ozk6IdxHSzt1mR0EI=
golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20211015210444-4f30a5c0130f/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.16.0 h1:7eBu7KsSvFDtSXUIDbh3aqlK4DPsZ1rByC8PFfBThos=
golang.org/x/net v0.16.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
golang.org/x/net v0.0.0-20210119194325-5f4716e94777/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2 h1:CIJ76btIcR3eFI5EgSo6k1qKw9KJexJuRLI9G7Hp5wE=
golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20190130150945-aca44879d564/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20190813064441-fde4db37ae7a/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200223170610-d5e6a3e2c0ae/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20200826173525-f9321e4c35a6/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20210927094055-39ccf1dd6fa6/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20211019181941-9d821ace8654/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20211103235746-7861aae1554b/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.13.0 h1:Af8nKPmuFypiUBjVoU9V20FiaFXOcuZI21p0ycVYYGE=
golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220111092808-5a964db01320/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220114195835-da31bd327af9 h1:XfKQ4OlFl8okEOr5UvAqFRVj8pY/4yfcXrddB8qAbU0=
golang.org/x/sys v0.0.0-20220114195835-da31bd327af9/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=
golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
golang.org/x/time v0.3.0 h1:rg5rLMjNzMS1RkNLzCG38eapWhnYLFYXDXj2gOlr8j4=
golang.org/x/time v0.3.0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
golang.org/x/time v0.0.0-20201208040808-7e3f01d25324/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
golang.org/x/time v0.0.0-20210220033141-f8bda1e9f3ba/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
golang.org/x/time v0.0.0-20211116232009-f0f3c7e86c11 h1:GZokNIeuVkl3aZHJchRrr13WCsols02MLUcz1U9is6M=
golang.org/x/time v0.0.0-20211116232009-f0f3c7e86c11/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.9/go.mod h1:nABZi5QlRsZVlzPpHl034qft6wpY4eDcsTt5AaioBiU=
golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
google.golang.org/protobuf v1.31.0 h1:g0LDEJHgrBl9N9r17Ru3sqWhkIx2NB67okBHPwC7hs8=
google.golang.org/protobuf v1.31.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
google.golang.org/protobuf v1.27.1 h1:SnqbnDw1V7RiZcXPx5MEeqPv2s79L9i7BJUlG/+RurQ=
google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
gopkg.in/Knetic/govaluate.v2 v2.3.0 h1:naJVc9CZlWA8rC8f5mvECJD7jreTrn7FvGXjBthkHJQ=
gopkg.in/Knetic/govaluate.v2 v2.3.0/go.mod h1:NW0gr10J8s7aNghEg6uhdxiEaBvc0+8VgJjVViHUKp4=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20200902074654-038fdea0a05b/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/ini.v1 v1.67.0 h1:Dgnx+6+nfE+IfzjUEISNeydPJh9AXNNsWbGP9KzCsOA=
gopkg.in/ini.v1 v1.67.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
moul.io/http2curl/v2 v2.3.0 h1:9r3JfDzWPcbIklMOs2TnIFzDYvfAZvjeavG6EzP7jYs=
nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33q108Sa+fhmuc+sWQYwY=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.3.0 h1:clyUAQHOM3G0M3f5vQj7LuJrETvjVot3Z5el9nffUtU=
gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=

View File

@@ -0,0 +1,32 @@
# ClusterCockpit metrics
As described in the [ClusterCockpit specifications](https://github.com/ClusterCockpit/cc-specifications), the whole ClusterCockpit stack uses metrics in the InfluxDB line protocol format. This is also the input and output format for the ClusterCockpit Metric Collector but internally it uses an extended format while processing, named CCMetric.
It is basically a copy of the [InfluxDB line protocol](https://github.com/influxdata/line-protocol) `MutableMetric` interface with one extension. Besides the tags and fields, it contains a list of meta information (re-using the `Tag` structure of the original protocol):
```golang
type ccMetric struct {
name string // same as
tags []*influx.Tag // original
fields []*influx.Field // Influx
tm time.Time // line-protocol
meta []*influx.Tag
}
type CCMetric interface {
influx.MutableMetric // the same functions as defined by influx.MutableMetric
RemoveTag(key string) // this is not published by the original influx.MutableMetric
Meta() map[string]string
MetaList() []*inlux.Tag
AddMeta(key, value string)
HasMeta(key string) bool
GetMeta(key string) (string, bool)
RemoveMeta(key string)
}
```
The `CCMetric` interface provides the same functions as the `MutableMetric` like `{Add, Remove, Has}{Tag, Field}` and additionally provides `{Add, Remove, Has}Meta`.
The InfluxDB protocol creates a new metric with `influx.New(name, tags, fields, time)` while CCMetric uses `ccMetric.New(name, tags, meta, fields, time)` where `tags` and `meta` are both of type `map[string]string`.
You can copy a CCMetric with `FromMetric(other CCMetric) CCMetric`. If you get an `influx.Metric` from a function, like the line protocol parser, you can use `FromInfluxMetric(other influx.Metric) CCMetric` to get a CCMetric out of it (see `NatsReceiver` for an example).

View File

@@ -7,7 +7,6 @@ import (
influxdb2 "github.com/influxdata/influxdb-client-go/v2"
write "github.com/influxdata/influxdb-client-go/v2/api/write"
lp "github.com/influxdata/line-protocol" // MIT license
"golang.org/x/exp/maps"
)
// Most functions are derived from github.com/influxdata/line-protocol/metric.go
@@ -51,7 +50,6 @@ type CCMetric interface {
GetField(key string) (value interface{}, ok bool) // Get a field addressed by its key
HasField(key string) (ok bool) // Check if a field key is present
RemoveField(key string) // Remove a field addressed by its key
String() string // Return line-protocol like string
}
// String implements the stringer interface for data type ccMetric
@@ -65,11 +63,9 @@ func (m *ccMetric) String() string {
// ToLineProtocol generates influxDB line protocol for data type ccMetric
func (m *ccMetric) ToPoint(metaAsTags map[string]bool) (p *write.Point) {
p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
for key, use_as_tag := range metaAsTags {
if use_as_tag {
if value, ok := m.GetMeta(key); ok {
p.AddTag(key, value)
}
for key, ok1 := range metaAsTags {
if val, ok2 := m.GetMeta(key); ok1 && ok2 {
p.AddTag(key, val)
}
}
return p
@@ -196,13 +192,19 @@ func New(
) (CCMetric, error) {
m := &ccMetric{
name: name,
tags: maps.Clone(tags),
meta: maps.Clone(meta),
tags: make(map[string]string, len(tags)),
meta: make(map[string]string, len(meta)),
fields: make(map[string]interface{}, len(fields)),
tm: tm,
}
// deep copy fields
// deep copy tags, meta data tags and fields
for k, v := range tags {
m.tags[k] = v
}
for k, v := range meta {
m.meta[k] = v
}
for k, v := range fields {
v := convertField(v)
if v == nil {
@@ -215,15 +217,26 @@ func New(
}
// FromMetric copies the metric <other>
func FromMetric(other CCMetric) CCMetric {
return &ccMetric{
func FromMetric(other ccMetric) CCMetric {
m := &ccMetric{
name: other.Name(),
tags: maps.Clone(other.Tags()),
meta: maps.Clone(other.Meta()),
fields: maps.Clone(other.Fields()),
tags: make(map[string]string, len(other.tags)),
meta: make(map[string]string, len(other.meta)),
fields: make(map[string]interface{}, len(other.fields)),
tm: other.Time(),
}
// deep copy tags, meta data tags and fields
for key, value := range other.tags {
m.tags[key] = value
}
for key, value := range other.meta {
m.meta[key] = value
}
for key, value := range other.fields {
m.fields[key] = value
}
return m
}
// FromInfluxMetric copies the influxDB line protocol metric <other>
@@ -247,10 +260,8 @@ func FromInfluxMetric(other lp.Metric) CCMetric {
}
// convertField converts data types of fields by the following schemata:
//
// *float32, *float64, float32, float64 -> float64
// *int, *int8, *int16, *int32, *int64, int, int8, int16, int32, int64 -> int64
//
// *float32, *float64, float32, float64 -> float64
// *int, *int8, *int16, *int32, *int64, int, int8, int16, int32, int64 -> int64
// *uint, *uint8, *uint16, *uint32, *uint64, uint, uint8, uint16, uint32, uint64 -> uint64
// *[]byte, *string, []byte, string -> string
// *bool, bool -> bool

View File

@@ -0,0 +1,427 @@
package ccTopology
import (
"fmt"
"io/ioutil"
"log"
"os"
"path/filepath"
"regexp"
"strconv"
"strings"
cclogger "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
)
const SYSFS_NUMABASE = `/sys/devices/system/node`
const SYSFS_CPUBASE = `/sys/devices/system/cpu`
const PROCFS_CPUINFO = `/proc/cpuinfo`
// intArrayContains scans an array of ints if the value str is present in the array
// If the specified value is found, the corresponding array index is returned.
// The bool value is used to signal success or failure
func intArrayContains(array []int, str int) (int, bool) {
for i, a := range array {
if a == str {
return i, true
}
}
return -1, false
}
func fileToInt(path string) int {
buffer, err := ioutil.ReadFile(path)
if err != nil {
log.Print(err)
cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
return -1
}
sbuffer := strings.Replace(string(buffer), "\n", "", -1)
var id int64
//_, err = fmt.Scanf("%d", sbuffer, &id)
id, err = strconv.ParseInt(sbuffer, 10, 32)
if err != nil {
cclogger.ComponentError("ccTopology", "Parsing", path, ":", sbuffer, err.Error())
return -1
}
return int(id)
}
func SocketList() []int {
buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
if err != nil {
log.Print(err)
return nil
}
ll := strings.Split(string(buffer), "\n")
var packs []int
for _, line := range ll {
if strings.HasPrefix(line, "physical id") {
lv := strings.Fields(line)
id, err := strconv.ParseInt(lv[3], 10, 32)
if err != nil {
log.Print(err)
return packs
}
_, found := intArrayContains(packs, int(id))
if !found {
packs = append(packs, int(id))
}
}
}
return packs
}
func CpuList() []int {
buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
if err != nil {
log.Print(err)
return nil
}
ll := strings.Split(string(buffer), "\n")
cpulist := make([]int, 0)
for _, line := range ll {
if strings.HasPrefix(line, "processor") {
lv := strings.Fields(line)
id, err := strconv.ParseInt(lv[2], 10, 32)
if err != nil {
log.Print(err)
return cpulist
}
_, found := intArrayContains(cpulist, int(id))
if !found {
cpulist = append(cpulist, int(id))
}
}
}
return cpulist
}
func CoreList() []int {
buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
if err != nil {
log.Print(err)
return nil
}
ll := strings.Split(string(buffer), "\n")
corelist := make([]int, 0)
for _, line := range ll {
if strings.HasPrefix(line, "core id") {
lv := strings.Fields(line)
id, err := strconv.ParseInt(lv[3], 10, 32)
if err != nil {
log.Print(err)
return corelist
}
_, found := intArrayContains(corelist, int(id))
if !found {
corelist = append(corelist, int(id))
}
}
}
return corelist
}
func NumaNodeList() []int {
numaList := make([]int, 0)
globPath := filepath.Join(string(SYSFS_NUMABASE), "node*")
regexPath := filepath.Join(string(SYSFS_NUMABASE), "node(\\d+)")
regex := regexp.MustCompile(regexPath)
files, err := filepath.Glob(globPath)
if err != nil {
cclogger.ComponentError("CCTopology", "NumaNodeList", err.Error())
}
for _, f := range files {
if !regex.MatchString(f) {
continue
}
finfo, err := os.Lstat(f)
if err != nil {
continue
}
if !finfo.IsDir() {
continue
}
matches := regex.FindStringSubmatch(f)
if len(matches) == 2 {
id, err := strconv.Atoi(matches[1])
if err == nil {
if _, found := intArrayContains(numaList, id); !found {
numaList = append(numaList, id)
}
}
}
}
return numaList
}
func DieList() []int {
cpulist := CpuList()
dielist := make([]int, 0)
for _, c := range cpulist {
diepath := filepath.Join(string(SYSFS_CPUBASE), fmt.Sprintf("cpu%d", c), "topology/die_id")
dieid := fileToInt(diepath)
if dieid > 0 {
_, found := intArrayContains(dielist, int(dieid))
if !found {
dielist = append(dielist, int(dieid))
}
}
}
if len(dielist) > 0 {
return dielist
}
return SocketList()
}
type CpuEntry struct {
Cpuid int
SMT int
Core int
Socket int
Numadomain int
Die int
}
func CpuData() []CpuEntry {
fileToInt := func(path string) int {
buffer, err := ioutil.ReadFile(path)
if err != nil {
log.Print(err)
//cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
return -1
}
sbuffer := strings.Replace(string(buffer), "\n", "", -1)
var id int64
//_, err = fmt.Scanf("%d", sbuffer, &id)
id, err = strconv.ParseInt(sbuffer, 10, 32)
if err != nil {
cclogger.ComponentError("ccTopology", "Parsing", path, ":", sbuffer, err.Error())
return -1
}
return int(id)
}
getCore := func(basepath string) int {
return fileToInt(fmt.Sprintf("%s/core_id", basepath))
}
getSocket := func(basepath string) int {
return fileToInt(fmt.Sprintf("%s/physical_package_id", basepath))
}
getDie := func(basepath string) int {
return fileToInt(fmt.Sprintf("%s/die_id", basepath))
}
getSMT := func(cpuid int, basepath string) int {
buffer, err := ioutil.ReadFile(fmt.Sprintf("%s/thread_siblings_list", basepath))
if err != nil {
cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
}
threadlist := make([]int, 0)
sbuffer := strings.Replace(string(buffer), "\n", "", -1)
for _, x := range strings.Split(sbuffer, ",") {
id, err := strconv.ParseInt(x, 10, 32)
if err != nil {
cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
}
threadlist = append(threadlist, int(id))
}
for i, x := range threadlist {
if x == cpuid {
return i
}
}
return 1
}
getNumaDomain := func(basepath string) int {
globPath := filepath.Join(basepath, "node*")
regexPath := filepath.Join(basepath, "node(\\d+)")
regex := regexp.MustCompile(regexPath)
files, err := filepath.Glob(globPath)
if err != nil {
cclogger.ComponentError("CCTopology", "CpuData:getNumaDomain", err.Error())
}
for _, f := range files {
finfo, err := os.Lstat(f)
if err == nil && finfo.IsDir() {
matches := regex.FindStringSubmatch(f)
if len(matches) == 2 {
id, err := strconv.Atoi(matches[1])
if err == nil {
return id
}
}
}
}
return 0
}
clist := make([]CpuEntry, 0)
for _, c := range CpuList() {
clist = append(clist, CpuEntry{Cpuid: c})
}
for i, centry := range clist {
centry.Socket = -1
centry.Numadomain = -1
centry.Die = -1
centry.Core = -1
// Set base directory for topology lookup
cpustr := fmt.Sprintf("cpu%d", centry.Cpuid)
base := filepath.Join("/sys/devices/system/cpu", cpustr)
topoBase := filepath.Join(base, "topology")
// Lookup CPU core id
centry.Core = getCore(topoBase)
// Lookup CPU socket id
centry.Socket = getSocket(topoBase)
// Lookup CPU die id
centry.Die = getDie(topoBase)
if centry.Die < 0 {
centry.Die = centry.Socket
}
// Lookup SMT thread id
centry.SMT = getSMT(centry.Cpuid, topoBase)
// Lookup NUMA domain id
centry.Numadomain = getNumaDomain(base)
// Update values in output list
clist[i] = centry
}
return clist
}
type CpuInformation struct {
NumHWthreads int
SMTWidth int
NumSockets int
NumDies int
NumCores int
NumNumaDomains int
}
func CpuInfo() CpuInformation {
var c CpuInformation
smtList := make([]int, 0)
numaList := make([]int, 0)
dieList := make([]int, 0)
socketList := make([]int, 0)
coreList := make([]int, 0)
cdata := CpuData()
for _, d := range cdata {
if _, ok := intArrayContains(smtList, d.SMT); !ok {
smtList = append(smtList, d.SMT)
}
if _, ok := intArrayContains(numaList, d.Numadomain); !ok {
numaList = append(numaList, d.Numadomain)
}
if _, ok := intArrayContains(dieList, d.Die); !ok {
dieList = append(dieList, d.Die)
}
if _, ok := intArrayContains(socketList, d.Socket); !ok {
socketList = append(socketList, d.Socket)
}
if _, ok := intArrayContains(coreList, d.Core); !ok {
coreList = append(coreList, d.Core)
}
}
c.NumNumaDomains = len(numaList)
c.SMTWidth = len(smtList)
c.NumDies = len(dieList)
c.NumCores = len(coreList)
c.NumSockets = len(socketList)
c.NumHWthreads = len(cdata)
return c
}
func GetCpuSocket(cpuid int) int {
cdata := CpuData()
for _, d := range cdata {
if d.Cpuid == cpuid {
return d.Socket
}
}
return -1
}
func GetCpuNumaDomain(cpuid int) int {
cdata := CpuData()
for _, d := range cdata {
if d.Cpuid == cpuid {
return d.Numadomain
}
}
return -1
}
func GetCpuDie(cpuid int) int {
cdata := CpuData()
for _, d := range cdata {
if d.Cpuid == cpuid {
return d.Die
}
}
return -1
}
func GetCpuCore(cpuid int) int {
cdata := CpuData()
for _, d := range cdata {
if d.Cpuid == cpuid {
return d.Core
}
}
return -1
}
func GetSocketCpus(socket int) []int {
all := CpuData()
cpulist := make([]int, 0)
for _, d := range all {
if d.Socket == socket {
cpulist = append(cpulist, d.Cpuid)
}
}
return cpulist
}
func GetNumaDomainCpus(domain int) []int {
all := CpuData()
cpulist := make([]int, 0)
for _, d := range all {
if d.Numadomain == domain {
cpulist = append(cpulist, d.Cpuid)
}
}
return cpulist
}
func GetDieCpus(die int) []int {
all := CpuData()
cpulist := make([]int, 0)
for _, d := range all {
if d.Die == die {
cpulist = append(cpulist, d.Cpuid)
}
}
return cpulist
}
func GetCoreCpus(core int) []int {
all := CpuData()
cpulist := make([]int, 0)
for _, d := range all {
if d.Core == core {
cpulist = append(cpulist, d.Cpuid)
}
}
return cpulist
}

View File

@@ -9,10 +9,10 @@ import (
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
"github.com/PaesslerAG/gval"
)
@@ -121,12 +121,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
vars["endtime"] = endtime
for _, f := range c.functions {
cclog.ComponentDebug("MetricCache", "COLLECT", f.Name, "COND", f.Condition)
var valuesFloat64 []float64
var valuesFloat32 []float32
var valuesInt []int
var valuesInt32 []int32
var valuesInt64 []int64
var valuesBool []bool
values := make([]float64, 0)
matches := make([]lp.CCMetric, 0)
for _, m := range metrics {
vars["metric"] = m
@@ -141,17 +136,17 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
if valid {
switch x := v.(type) {
case float64:
valuesFloat64 = append(valuesFloat64, x)
values = append(values, x)
case float32:
valuesFloat32 = append(valuesFloat32, x)
case int:
valuesInt = append(valuesInt, x)
case int32:
valuesInt32 = append(valuesInt32, x)
case int64:
valuesInt64 = append(valuesInt64, x)
values = append(values, float64(x))
case bool:
valuesBool = append(valuesBool, x)
if x {
values = append(values, float64(1.0))
} else {
values = append(values, float64(0.0))
}
default:
cclog.ComponentError("MetricCache", "COLLECT ADD VALUE", v, "FAILED")
}
@@ -160,59 +155,13 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
}
}
delete(vars, "metric")
// Check, that only values of one type were collected
countValueTypes := 0
if len(valuesFloat64) > 0 {
countValueTypes += 1
}
if len(valuesFloat32) > 0 {
countValueTypes += 1
}
if len(valuesInt) > 0 {
countValueTypes += 1
}
if len(valuesInt32) > 0 {
countValueTypes += 1
}
if len(valuesInt64) > 0 {
countValueTypes += 1
}
if len(valuesBool) > 0 {
countValueTypes += 1
}
if countValueTypes > 1 {
cclog.ComponentError("MetricCache", "Collected values of different types")
}
var len_values int
switch {
case len(valuesFloat64) > 0:
vars["values"] = valuesFloat64
len_values = len(valuesFloat64)
case len(valuesFloat32) > 0:
vars["values"] = valuesFloat32
len_values = len(valuesFloat32)
case len(valuesInt) > 0:
vars["values"] = valuesInt
len_values = len(valuesInt)
case len(valuesInt32) > 0:
vars["values"] = valuesInt32
len_values = len(valuesInt32)
case len(valuesInt64) > 0:
vars["values"] = valuesInt64
len_values = len(valuesInt64)
case len(valuesBool) > 0:
vars["values"] = valuesBool
len_values = len(valuesBool)
}
cclog.ComponentDebug("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function)
cclog.ComponentDebug("MetricCache", "EVALUATE", f.Name, "METRICS", len(values), "CALC", f.Function)
vars["values"] = values
vars["metrics"] = matches
if len_values > 0 {
if len(values) > 0 {
value, err := gval.Evaluate(f.Function, vars, c.language)
if err != nil {
cclog.ComponentError("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function, ":", err.Error())
cclog.ComponentError("MetricCache", "EVALUATE", f.Name, "METRICS", len(values), "CALC", f.Function, ":", err.Error())
break
}
@@ -367,7 +316,7 @@ func EvalBoolCondition(condition string, params map[string]interface{}) (bool, e
return value, err
}
func EvalFloat64Condition(condition string, params map[string]float64) (float64, error) {
func EvalFloat64Condition(condition string, params map[string]interface{}) (float64, error) {
evaluables.mutex.Lock()
evaluable, ok := evaluables.mapping[condition]
evaluables.mutex.Unlock()

View File

@@ -3,167 +3,162 @@ package metricAggregator
import (
"errors"
"fmt"
"math"
"regexp"
"sort"
"strings"
"golang.org/x/exp/slices"
topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
)
/*
* Arithmetic functions on value arrays
*/
func sumAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
if len(values) == 0 {
return 0.0, errors.New("sum function requires at least one argument")
// Sum up values
func sumfunc(args ...interface{}) (interface{}, error) {
s := 0.0
values, ok := args[0].([]float64)
if ok {
cclog.ComponentDebug("MetricCache", "SUM FUNC START")
for _, x := range values {
s += x
}
cclog.ComponentDebug("MetricCache", "SUM FUNC END", s)
} else {
cclog.ComponentDebug("MetricCache", "SUM FUNC CAST FAILED")
}
var sum T
for _, value := range values {
sum += value
}
return sum, nil
return s, nil
}
// Sum up values
func sumfunc(args interface{}) (interface{}, error) {
var err error
switch values := args.(type) {
// Get the minimum value
func minfunc(args ...interface{}) (interface{}, error) {
var err error = nil
switch values := args[0].(type) {
case []float64:
return sumAnyType(values)
var s float64 = math.MaxFloat64
for _, x := range values {
if x < s {
s = x
}
}
return s, nil
case []float32:
return sumAnyType(values)
var s float32 = math.MaxFloat32
for _, x := range values {
if x < s {
s = x
}
}
return s, nil
case []int:
return sumAnyType(values)
var s int = int(math.MaxInt32)
for _, x := range values {
if x < s {
s = x
}
}
return s, nil
case []int64:
return sumAnyType(values)
var s int64 = math.MaxInt64
for _, x := range values {
if x < s {
s = x
}
}
return s, nil
case []int32:
return sumAnyType(values)
var s int32 = math.MaxInt32
for _, x := range values {
if x < s {
s = x
}
}
return s, nil
default:
err = errors.New("function 'sum' only on list of values (float64, float32, int, int32, int64)")
err = errors.New("function 'min' only on list of values (float64, float32, int, int32, int64)")
}
return 0.0, err
}
func minAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
if len(values) == 0 {
return 0.0, errors.New("min function requires at least one argument")
}
return slices.Min(values), nil
}
// Get the minimum value
func minfunc(args interface{}) (interface{}, error) {
switch values := args.(type) {
case []float64:
return minAnyType(values)
case []float32:
return minAnyType(values)
case []int:
return minAnyType(values)
case []int64:
return minAnyType(values)
case []int32:
return minAnyType(values)
default:
return 0.0, errors.New("function 'min' only on list of values (float64, float32, int, int32, int64)")
}
}
func avgAnyType[T float64 | float32 | int | int32 | int64](values []T) (float64, error) {
if len(values) == 0 {
return 0.0, errors.New("average function requires at least one argument")
}
sum, err := sumAnyType[T](values)
return float64(sum) / float64(len(values)), err
}
// Get the average or mean value
func avgfunc(args interface{}) (interface{}, error) {
switch values := args.(type) {
func avgfunc(args ...interface{}) (interface{}, error) {
switch values := args[0].(type) {
case []float64:
return avgAnyType(values)
var s float64 = 0
for _, x := range values {
s += x
}
return s / float64(len(values)), nil
case []float32:
return avgAnyType(values)
var s float32 = 0
for _, x := range values {
s += x
}
return s / float32(len(values)), nil
case []int:
return avgAnyType(values)
var s int = 0
for _, x := range values {
s += x
}
return s / len(values), nil
case []int64:
return avgAnyType(values)
case []int32:
return avgAnyType(values)
default:
return 0.0, errors.New("function 'average' only on list of values (float64, float32, int, int32, int64)")
var s int64 = 0
for _, x := range values {
s += x
}
return s / int64(len(values)), nil
}
}
func maxAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
if len(values) == 0 {
return 0.0, errors.New("max function requires at least one argument")
}
return slices.Max(values), nil
return 0.0, nil
}
// Get the maximum value
func maxfunc(args interface{}) (interface{}, error) {
switch values := args.(type) {
case []float64:
return maxAnyType(values)
case []float32:
return maxAnyType(values)
case []int:
return maxAnyType(values)
case []int64:
return maxAnyType(values)
case []int32:
return maxAnyType(values)
default:
return 0.0, errors.New("function 'max' only on list of values (float64, float32, int, int32, int64)")
func maxfunc(args ...interface{}) (interface{}, error) {
s := 0.0
values, ok := args[0].([]float64)
if ok {
for _, x := range values {
if x > s {
s = x
}
}
}
}
func medianAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
if len(values) == 0 {
return 0.0, errors.New("median function requires at least one argument")
}
slices.Sort(values)
var median T
if midPoint := len(values) % 2; midPoint == 0 {
median = (values[midPoint-1] + values[midPoint]) / 2
} else {
median = values[midPoint]
}
return median, nil
return s, nil
}
// Get the median value
func medianfunc(args interface{}) (interface{}, error) {
switch values := args.(type) {
func medianfunc(args ...interface{}) (interface{}, error) {
switch values := args[0].(type) {
case []float64:
return medianAnyType(values)
case []float32:
return medianAnyType(values)
sort.Float64s(values)
return values[len(values)/2], nil
// case []float32:
// sort.Float64s(values)
// return values[len(values)/2], nil
case []int:
return medianAnyType(values)
case []int64:
return medianAnyType(values)
case []int32:
return medianAnyType(values)
default:
return 0.0, errors.New("function 'median' only on list of values (float64, float32, int, int32, int64)")
sort.Ints(values)
return values[len(values)/2], nil
// case []int64:
// sort.Ints(values)
// return values[len(values)/2], nil
// case []int32:
// sort.Ints(values)
// return values[len(values)/2], nil
}
return 0.0, errors.New("function 'median()' only on lists of type float64 and int")
}
/*
* Get number of values in list. Returns always an int
*/
func lenfunc(args interface{}) (interface{}, error) {
func lenfunc(args ...interface{}) (interface{}, error) {
var err error = nil
var length int = 0
switch values := args.(type) {
switch values := args[0].(type) {
case []float64:
length = len(values)
case []float32:
@@ -248,49 +243,49 @@ func matchfunc(args ...interface{}) (interface{}, error) {
*/
// for a given cpuid, it returns the core id
func getCpuCoreFunc(args interface{}) (interface{}, error) {
switch cpuid := args.(type) {
func getCpuCoreFunc(args ...interface{}) (interface{}, error) {
switch cpuid := args[0].(type) {
case int:
return topo.GetHwthreadCore(cpuid), nil
return topo.GetCpuCore(cpuid), nil
}
return -1, errors.New("function 'getCpuCore' accepts only an 'int' cpuid")
}
// for a given cpuid, it returns the socket id
func getCpuSocketFunc(args interface{}) (interface{}, error) {
switch cpuid := args.(type) {
func getCpuSocketFunc(args ...interface{}) (interface{}, error) {
switch cpuid := args[0].(type) {
case int:
return topo.GetHwthreadSocket(cpuid), nil
return topo.GetCpuSocket(cpuid), nil
}
return -1, errors.New("function 'getCpuCore' accepts only an 'int' cpuid")
}
// for a given cpuid, it returns the id of the NUMA node
func getCpuNumaDomainFunc(args interface{}) (interface{}, error) {
switch cpuid := args.(type) {
func getCpuNumaDomainFunc(args ...interface{}) (interface{}, error) {
switch cpuid := args[0].(type) {
case int:
return topo.GetHwthreadNumaDomain(cpuid), nil
return topo.GetCpuNumaDomain(cpuid), nil
}
return -1, errors.New("function 'getCpuNuma' accepts only an 'int' cpuid")
}
// for a given cpuid, it returns the id of the CPU die
func getCpuDieFunc(args interface{}) (interface{}, error) {
switch cpuid := args.(type) {
func getCpuDieFunc(args ...interface{}) (interface{}, error) {
switch cpuid := args[0].(type) {
case int:
return topo.GetHwthreadDie(cpuid), nil
return topo.GetCpuDie(cpuid), nil
}
return -1, errors.New("function 'getCpuDie' accepts only an 'int' cpuid")
}
// for a given core id, it returns the list of cpuids
func getCpuListOfCoreFunc(args interface{}) (interface{}, error) {
func getCpuListOfCoreFunc(args ...interface{}) (interface{}, error) {
cpulist := make([]int, 0)
switch in := args.(type) {
switch in := args[0].(type) {
case int:
for _, c := range topo.CpuData() {
if c.Core == in {
cpulist = append(cpulist, c.CpuID)
cpulist = append(cpulist, c.Cpuid)
}
}
}
@@ -298,13 +293,13 @@ func getCpuListOfCoreFunc(args interface{}) (interface{}, error) {
}
// for a given socket id, it returns the list of cpuids
func getCpuListOfSocketFunc(args interface{}) (interface{}, error) {
func getCpuListOfSocketFunc(args ...interface{}) (interface{}, error) {
cpulist := make([]int, 0)
switch in := args.(type) {
switch in := args[0].(type) {
case int:
for _, c := range topo.CpuData() {
if c.Socket == in {
cpulist = append(cpulist, c.CpuID)
cpulist = append(cpulist, c.Cpuid)
}
}
}
@@ -312,13 +307,13 @@ func getCpuListOfSocketFunc(args interface{}) (interface{}, error) {
}
// for a given id of a NUMA domain, it returns the list of cpuids
func getCpuListOfNumaDomainFunc(args interface{}) (interface{}, error) {
func getCpuListOfNumaDomainFunc(args ...interface{}) (interface{}, error) {
cpulist := make([]int, 0)
switch in := args.(type) {
switch in := args[0].(type) {
case int:
for _, c := range topo.CpuData() {
if c.NumaDomain == in {
cpulist = append(cpulist, c.CpuID)
if c.Numadomain == in {
cpulist = append(cpulist, c.Cpuid)
}
}
}
@@ -326,13 +321,13 @@ func getCpuListOfNumaDomainFunc(args interface{}) (interface{}, error) {
}
// for a given CPU die id, it returns the list of cpuids
func getCpuListOfDieFunc(args interface{}) (interface{}, error) {
func getCpuListOfDieFunc(args ...interface{}) (interface{}, error) {
cpulist := make([]int, 0)
switch in := args.(type) {
switch in := args[0].(type) {
case int:
for _, c := range topo.CpuData() {
if c.Die == in {
cpulist = append(cpulist, c.CpuID)
cpulist = append(cpulist, c.Cpuid)
}
}
}
@@ -340,8 +335,8 @@ func getCpuListOfDieFunc(args interface{}) (interface{}, error) {
}
// wrapper function to get a list of all cpuids of the node
func getCpuListOfNode() (interface{}, error) {
return topo.HwthreadList(), nil
func getCpuListOfNode(args ...interface{}) (interface{}, error) {
return topo.CpuList(), nil
}
// helper function to get the cpuid list for a CCMetric type tag set (type and type-id)
@@ -353,14 +348,14 @@ func getCpuListOfType(args ...interface{}) (interface{}, error) {
case string:
switch typ {
case "node":
return topo.HwthreadList(), nil
return topo.CpuList(), nil
case "socket":
return getCpuListOfSocketFunc(args[1])
case "numadomain":
return getCpuListOfNumaDomainFunc(args[1])
case "core":
return getCpuListOfCoreFunc(args[1])
case "hwthread":
case "cpu":
var cpu int
switch id := args[1].(type) {

View File

@@ -52,11 +52,6 @@ The CCMetric router sits in between the collectors and the sinks and can be used
],
"rename_metrics" : {
"metric_12345" : "mymetric"
},
"normalize_units" : true,
"change_unit_prefix" : {
"mem_used" : "G",
"mem_total" : "G"
}
}
```
@@ -197,14 +192,6 @@ This option takes a list of evaluable conditions and performs them one after the
```
The first line is comparable with the example in `drop_metrics`, it drops all metrics starting with `drop_metric_` and ending with a number. The second line drops all metrics of the first hardware thread (**not** recommended)
# Manipulating the metric units
## The `normalize_units` option
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
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
@@ -252,22 +239,3 @@ Use cases for `interval_aggregates`:
}
}
```
# Order of operations
The router performs the above mentioned options in a specific order. In order to get the logic you want for a specific metric, it is crucial to know the processing order:
- Add the `hostname` tag (c)
- Manipulate the timestamp to the interval timestamp (c,r)
- Drop metrics based on `drop_metrics` and `drop_metrics_if` (c,r)
- Add tags based on `add_tags` (c,r)
- Delete tags based on `del_tags` (c,r)
- Rename metric based on `rename_metric` (c,r)
- Add tags based on `add_tags` to still work if the configuration uses the new name (c,r)
- Delete tags based on `del_tags` to still work if the configuration uses the new name (c,r)
- Normalize units when `normalize_units` is set (c,r)
- Convert unit prefix based on `change_unit_prefix` (c,r)
Legend:
- 'c' if metric is coming from a collector
- 'r' if metric is coming from a receiver

View File

@@ -0,0 +1,17 @@
# Stats API
The Stats API can be used for debugging. It publishes counts at an HTTP endpoint as JSON from different componenets of the CC Metric Collector.
# Configuration
The Stats API has an own configuration file to specify the listen host and port. The defaults are `localhost` and `8080`.
```json
{
"bindhost" : "",
"port" : "8080",
"publish_collectorstate" : true
}
```
The `bindhost` and `port` can be used to specify the listen host and port. The `publish_collectorstate` needs to be `true`, otherwise nothing is presented. This option is for future use if we need to publish more infos using different domains.

View File

@@ -0,0 +1,232 @@
package metricRouter
import (
"context"
"encoding/json"
"fmt"
"io"
"net/http"
"os"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
"github.com/gorilla/mux"
)
type statsApiConfig struct {
PublishCollectorState bool `json:"publish_collectorstate"`
Host string `json:"bindhost"`
Port string `json:"port"`
}
// Metric cache data structure
type statsApi struct {
name string
input chan lp.CCMetric
indone chan bool
outdone chan bool
config statsApiConfig
wg *sync.WaitGroup
statsWg sync.WaitGroup
ticker mct.MultiChanTicker
tickchan chan time.Time
server *http.Server
router *mux.Router
lock sync.Mutex
baseurl string
stats map[string]map[string]int64
outStats map[string]map[string]int64
}
type StatsApi interface {
Start()
Close()
StatsFunc(w http.ResponseWriter, r *http.Request)
}
var statsApiServer *statsApi = nil
func (a *statsApi) updateStats(point lp.CCMetric) {
switch point.Name() {
case "_stats":
if name, nok := point.GetMeta("source"); nok {
var compStats map[string]int64
var ok bool
if compStats, ok = a.stats[name]; !ok {
a.stats[name] = make(map[string]int64)
compStats = a.stats[name]
}
for k, v := range point.Fields() {
switch value := v.(type) {
case int:
compStats[k] = int64(value)
case uint:
compStats[k] = int64(value)
case int32:
compStats[k] = int64(value)
case uint32:
compStats[k] = int64(value)
case int64:
compStats[k] = int64(value)
case uint64:
compStats[k] = int64(value)
default:
cclog.ComponentDebug(a.name, "Unusable stats for", k, ". Values should be int64")
}
}
a.stats[name] = compStats
}
}
}
func (a *statsApi) Start() {
a.ticker.AddChannel(a.tickchan)
a.wg.Add(1)
a.statsWg.Add(1)
go func() {
a.stats = make(map[string]map[string]int64)
defer a.statsWg.Done()
for {
select {
case <-a.indone:
cclog.ComponentDebug(a.name, "INPUT DONE")
close(a.indone)
return
case p := <-a.input:
a.lock.Lock()
a.updateStats(p)
a.lock.Unlock()
}
}
}()
a.statsWg.Add(1)
go func() {
a.outStats = make(map[string]map[string]int64)
defer a.statsWg.Done()
a.lock.Lock()
for comp, compData := range a.stats {
var outData map[string]int64
var ok bool
if outData, ok = a.outStats[comp]; !ok {
outData = make(map[string]int64)
}
for k, v := range compData {
outData[k] = v
}
a.outStats[comp] = outData
}
a.lock.Unlock()
for {
select {
case <-a.outdone:
cclog.ComponentDebug(a.name, "OUTPUT DONE")
close(a.outdone)
return
case <-a.tickchan:
a.lock.Lock()
for comp, compData := range a.stats {
var outData map[string]int64
var ok bool
if outData, ok = a.outStats[comp]; !ok {
outData = make(map[string]int64)
}
for k, v := range compData {
outData[k] = v
}
a.outStats[comp] = outData
}
a.lock.Unlock()
}
}
}()
a.statsWg.Add(1)
go func() {
defer a.statsWg.Done()
err := a.server.ListenAndServe()
if err != nil && err.Error() != "http: Server closed" {
cclog.ComponentError(a.name, err.Error())
}
cclog.ComponentDebug(a.name, "SERVER DONE")
}()
cclog.ComponentDebug(a.name, "STARTED")
}
func (a *statsApi) StatsFunc(w http.ResponseWriter, r *http.Request) {
data, err := json.Marshal(a.outStats)
if err == nil {
w.Header().Set("Content-Type", "application/json")
io.WriteString(w, string(data))
}
}
// Close finishes / stops the metric cache
func (a *statsApi) Close() {
cclog.ComponentDebug(a.name, "CLOSE")
a.indone <- true
a.outdone <- true
a.server.Shutdown(context.Background())
// wait for close of channel r.done
<-a.indone
<-a.outdone
a.statsWg.Wait()
a.wg.Done()
//a.wg.Wait()
}
func NewStatsApi(ticker mct.MultiChanTicker, wg *sync.WaitGroup, statsApiConfigfile string) (StatsApi, error) {
a := new(statsApi)
a.name = "StatsApi"
a.config.Host = "localhost"
a.config.Port = "8080"
configFile, err := os.Open(statsApiConfigfile)
if err != nil {
cclog.ComponentError(a.name, err.Error())
return nil, err
}
defer configFile.Close()
jsonParser := json.NewDecoder(configFile)
err = jsonParser.Decode(&a.config)
if err != nil {
cclog.ComponentError(a.name, err.Error())
return nil, err
}
a.input = make(chan lp.CCMetric)
a.ticker = ticker
a.tickchan = make(chan time.Time)
a.wg = wg
a.indone = make(chan bool)
a.outdone = make(chan bool)
a.router = mux.NewRouter()
a.baseurl = fmt.Sprintf("%s:%s", a.config.Host, a.config.Port)
a.server = &http.Server{Addr: a.baseurl, Handler: a.router}
if a.config.PublishCollectorState {
a.router.HandleFunc("/", a.StatsFunc)
}
statsApiServer = a
return a, nil
}
func ComponentStatInt(component string, key string, value int64) {
if statsApiServer == nil {
return
}
y, err := lp.New("_stats", map[string]string{}, map[string]string{"source": component}, map[string]interface{}{key: value}, time.Now())
if err == nil {
statsApiServer.input <- y
}
}
func ComponentStatString(component string, key string, value int64) {
if statsApiServer == nil {
return
}
y, err := lp.New("_stats", map[string]string{}, map[string]string{"source": component}, map[string]interface{}{key: value}, time.Now())
if err == nil {
statsApiServer.input <- y
}
}

View File

@@ -4,11 +4,11 @@ import (
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
)
type metricCachePeriod struct {

View File

@@ -7,12 +7,11 @@ import (
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
units "github.com/ClusterCockpit/cc-units"
mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
)
const ROUTER_MAX_FORWARD = 50
@@ -36,26 +35,31 @@ type metricRouterConfig struct {
IntervalStamp bool `json:"interval_timestamp"` // Update timestamp periodically by ticker each interval?
NumCacheIntervals int `json:"num_cache_intervals"` // Number of intervals of cached metrics for evaluation
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
}
// Metric router data structure
type metricRouter struct {
hostname string // Hostname used in tags
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
ticker mct.MultiChanTicker // periodically ticking once each interval
config metricRouterConfig // json encoded config for metric router
cache MetricCache // pointer to MetricCache
cachewg sync.WaitGroup // wait group for MetricCache
maxForward int // number of metrics to forward maximally in one iteration
hostname string // Hostname used in tags
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
timerdone chan bool // channel to finish / stop timestamp updater
ticker mct.MultiChanTicker // periodically ticking once each interval
config metricRouterConfig // json encoded config for metric router
cache MetricCache // pointer to MetricCache
cachewg sync.WaitGroup // wait group for MetricCache
maxForward int // number of metrics to forward maximally in one iteration
statsCollForward int64
statsRecvForward int64
statsCacheForward int64
statsTotalForward int64
statsDropped int64
statsRenamed int64
}
// MetricRouter access functions
@@ -123,9 +127,39 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
for _, mname := range r.config.DropMetrics {
r.config.dropMetrics[mname] = true
}
r.statsCollForward = 0
r.statsRecvForward = 0
r.statsCacheForward = 0
r.statsTotalForward = 0
r.statsDropped = 0
r.statsRenamed = 0
return nil
}
// StartTimer starts a timer which updates timestamp periodically
func (r *metricRouter) StartTimer() {
m := make(chan time.Time)
r.ticker.AddChannel(m)
r.timerdone = make(chan bool)
r.wg.Add(1)
go func() {
defer r.wg.Done()
for {
select {
case <-r.timerdone:
close(r.timerdone)
cclog.ComponentDebug("MetricRouter", "TIMER DONE")
return
case t := <-m:
cclog.ComponentDebug("MetricRouter", "INTERVAL_TICK", t.Unix())
r.timestamp = t
}
}
}()
cclog.ComponentDebug("MetricRouter", "TIMER START")
}
func getParamMap(point lp.CCMetric) map[string]interface{} {
params := make(map[string]interface{})
params["metric"] = point
@@ -210,45 +244,12 @@ func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
return false
}
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)
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
}
// Start starts the metric router
func (r *metricRouter) Start() {
// start timer if configured
r.timestamp = time.Now()
timeChan := make(chan time.Time)
if r.config.IntervalStamp {
r.ticker.AddChannel(timeChan)
r.StartTimer()
}
// Router manager is done
@@ -265,13 +266,13 @@ func (r *metricRouter) Start() {
r.DoDelTags(point)
name := point.Name()
if new, ok := r.config.RenameMetrics[name]; ok {
r.statsRenamed++
ComponentStatInt("MetricRouter", "renamed", r.statsRenamed)
point.SetName(new)
point.AddMeta("oldname", name)
r.DoAddTags(point)
r.DoDelTags(point)
}
r.prepareUnit(point)
r.DoAddTags(point)
r.DoDelTags(point)
for _, o := range r.outputs {
o <- point
@@ -286,7 +287,14 @@ func (r *metricRouter) Start() {
p.SetTime(r.timestamp)
}
if !r.dropMetric(p) {
r.statsCollForward++
r.statsTotalForward++
ComponentStatInt("MetricRouter", "collector_forward", r.statsCollForward)
ComponentStatInt("MetricRouter", "total_forward", r.statsTotalForward)
forward(p)
} else {
r.statsDropped++
ComponentStatInt("MetricRouter", "dropped", r.statsDropped)
}
// even if the metric is dropped, it is stored in the cache for
// aggregations
@@ -302,7 +310,14 @@ func (r *metricRouter) Start() {
p.SetTime(r.timestamp)
}
if !r.dropMetric(p) {
r.statsRecvForward++
r.statsTotalForward++
ComponentStatInt("MetricRouter", "receiver_forward", r.statsRecvForward)
ComponentStatInt("MetricRouter", "total_forward", r.statsTotalForward)
forward(p)
} else {
r.statsDropped++
ComponentStatInt("MetricRouter", "dropped", r.statsDropped)
}
}
@@ -311,7 +326,14 @@ func (r *metricRouter) Start() {
// receive from metric collector
if !r.dropMetric(p) {
p.AddTag(r.config.HostnameTagName, r.hostname)
r.statsCacheForward++
r.statsTotalForward++
ComponentStatInt("MetricRouter", "cache_forward", r.statsCacheForward)
ComponentStatInt("MetricRouter", "total_forward", r.statsTotalForward)
forward(p)
} else {
r.statsDropped++
ComponentStatInt("MetricRouter", "dropped", r.statsDropped)
}
}
@@ -330,10 +352,6 @@ func (r *metricRouter) Start() {
done()
return
case timestamp := <-timeChan:
r.timestamp = timestamp
cclog.ComponentDebug("MetricRouter", "Update timestamp", r.timestamp.UnixNano())
case p := <-r.coll_input:
coll_forward(p)
for i := 0; len(r.coll_input) > 0 && i < (r.maxForward-1); i++ {
@@ -379,6 +397,14 @@ func (r *metricRouter) Close() {
// wait for close of channel r.done
<-r.done
// stop timer
if r.config.IntervalStamp {
cclog.ComponentDebug("MetricRouter", "TIMER CLOSE")
r.timerdone <- true
// wait for close of channel r.timerdone
<-r.timerdone
}
// stop metric cache
if r.config.NumCacheIntervals > 0 {
cclog.ComponentDebug("MetricRouter", "CACHE CLOSE")

View File

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

View File

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

View File

@@ -1,425 +0,0 @@
package ccTopology
import (
"fmt"
"log"
"os"
"path/filepath"
"regexp"
"strconv"
"strings"
cclogger "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
"golang.org/x/exp/slices"
)
const SYSFS_CPUBASE = `/sys/devices/system/cpu`
// Structure holding all information about a hardware thread
// See https://www.kernel.org/doc/Documentation/ABI/stable/sysfs-devices-system-cpu
type HwthreadEntry struct {
// for each CPUx:
CpuID int // CPU / hardware thread ID
SMT int // Simultaneous Multithreading ID
CoreCPUsList []int // CPUs within the same core
Core int // Socket local core ID
Socket int // Sockets (physical) ID
Die int // Die ID
NumaDomain int // NUMA Domain
}
var cache struct {
HwthreadList []int // List of CPU hardware threads
SMTList []int // List of symmetric hyper threading IDs
CoreList []int // List of CPU core IDs
SocketList []int // List of CPU sockets (physical) IDs
DieList []int // List of CPU Die IDs
NumaDomainList []int // List of NUMA Domains
CpuData []HwthreadEntry
}
// fileToInt reads an integer value from a sysfs file
// In case of an error -1 is returned
func fileToInt(path string) int {
buffer, err := os.ReadFile(path)
if err != nil {
log.Print(err)
cclogger.ComponentError("ccTopology", "fileToInt", "Reading", path, ":", err.Error())
return -1
}
stringBuffer := strings.TrimSpace(string(buffer))
id, err := strconv.Atoi(stringBuffer)
if err != nil {
cclogger.ComponentError("ccTopology", "fileToInt", "Parsing", path, ":", stringBuffer, err.Error())
return -1
}
return id
}
// fileToList reads a list from a sysfs file
// A list consists of value ranges separated by colon
// A range can be a single value or a range of values given by a startValue-endValue
// In case of an error nil is returned
func fileToList(path string) []int {
// Read list
buffer, err := os.ReadFile(path)
if err != nil {
log.Print(err)
cclogger.ComponentError("ccTopology", "fileToList", "Reading", path, ":", err.Error())
return nil
}
// Create list
list := make([]int, 0)
stringBuffer := strings.TrimSpace(string(buffer))
for _, valueRangeString := range strings.Split(stringBuffer, ",") {
valueRange := strings.Split(valueRangeString, "-")
switch len(valueRange) {
case 1:
singleValue, err := strconv.Atoi(valueRange[0])
if err != nil {
cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[0], ":", err.Error())
return nil
}
list = append(list, singleValue)
case 2:
startValue, err := strconv.Atoi(valueRange[0])
if err != nil {
cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[0], ":", err.Error())
return nil
}
endValue, err := strconv.Atoi(valueRange[1])
if err != nil {
cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[1], ":", err.Error())
return nil
}
for value := startValue; value <= endValue; value++ {
list = append(list, value)
}
}
}
return list
}
// init initializes the cache structure
func init() {
getHWThreads :=
func() []int {
globPath := filepath.Join(SYSFS_CPUBASE, "cpu[0-9]*")
regexPath := filepath.Join(SYSFS_CPUBASE, "cpu([[:digit:]]+)")
regex := regexp.MustCompile(regexPath)
// File globbing for hardware threads
files, err := filepath.Glob(globPath)
if err != nil {
cclogger.ComponentError("CCTopology", "init:getHWThreads", err.Error())
return nil
}
hwThreadIDs := make([]int, len(files))
for i, file := range files {
// Extract hardware thread ID
matches := regex.FindStringSubmatch(file)
if len(matches) != 2 {
cclogger.ComponentError("CCTopology", "init:getHWThreads: Failed to extract hardware thread ID from ", file)
return nil
}
// Convert hardware thread ID to int
id, err := strconv.Atoi(matches[1])
if err != nil {
cclogger.ComponentError("CCTopology", "init:getHWThreads: Failed to convert to int hardware thread ID ", matches[1])
return nil
}
hwThreadIDs[i] = id
}
// Sort hardware thread IDs
slices.Sort(hwThreadIDs)
return hwThreadIDs
}
getNumaDomain :=
func(basePath string) int {
globPath := filepath.Join(basePath, "node*")
regexPath := filepath.Join(basePath, "node([[:digit:]]+)")
regex := regexp.MustCompile(regexPath)
// File globbing for NUMA node
files, err := filepath.Glob(globPath)
if err != nil {
cclogger.ComponentError("CCTopology", "init:getNumaDomain", err.Error())
return -1
}
// Check, that exactly one NUMA domain was found
if len(files) != 1 {
cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Number of NUMA domains != 1: ", len(files))
return -1
}
// Extract NUMA node ID
matches := regex.FindStringSubmatch(files[0])
if len(matches) != 2 {
cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Failed to extract NUMA node ID from: ", files[0])
return -1
}
id, err := strconv.Atoi(matches[1])
if err != nil {
cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Failed to parse NUMA node ID from: ", matches[1])
return -1
}
return id
}
cache.HwthreadList = getHWThreads()
cache.CoreList = make([]int, len(cache.HwthreadList))
cache.SocketList = make([]int, len(cache.HwthreadList))
cache.DieList = make([]int, len(cache.HwthreadList))
cache.SMTList = make([]int, len(cache.HwthreadList))
cache.NumaDomainList = make([]int, len(cache.HwthreadList))
cache.CpuData = make([]HwthreadEntry, len(cache.HwthreadList))
for i, c := range cache.HwthreadList {
// Set cpuBase directory for topology lookup
cpuBase := filepath.Join(SYSFS_CPUBASE, fmt.Sprintf("cpu%d", c))
topoBase := filepath.Join(cpuBase, "topology")
// Lookup Core ID
cache.CoreList[i] = fileToInt(filepath.Join(topoBase, "core_id"))
// Lookup socket / physical package ID
cache.SocketList[i] = fileToInt(filepath.Join(topoBase, "physical_package_id"))
// Lookup CPU die id
cache.DieList[i] = fileToInt(filepath.Join(topoBase, "die_id"))
if cache.DieList[i] < 0 {
cache.DieList[i] = cache.SocketList[i]
}
// Lookup List of CPUs within the same core
coreCPUsList := fileToList(filepath.Join(topoBase, "core_cpus_list"))
// Find index of CPU ID in List of CPUs within the same core
// if not found return -1
cache.SMTList[i] = slices.Index(coreCPUsList, c)
// Lookup NUMA domain id
cache.NumaDomainList[i] = getNumaDomain(cpuBase)
cache.CpuData[i] =
HwthreadEntry{
CpuID: cache.HwthreadList[i],
SMT: cache.SMTList[i],
CoreCPUsList: coreCPUsList,
Socket: cache.SocketList[i],
NumaDomain: cache.NumaDomainList[i],
Die: cache.DieList[i],
Core: cache.CoreList[i],
}
}
slices.Sort(cache.HwthreadList)
cache.HwthreadList = slices.Compact(cache.HwthreadList)
slices.Sort(cache.SMTList)
cache.SMTList = slices.Compact(cache.SMTList)
slices.Sort(cache.CoreList)
cache.CoreList = slices.Compact(cache.CoreList)
slices.Sort(cache.SocketList)
cache.SocketList = slices.Compact(cache.SocketList)
slices.Sort(cache.DieList)
cache.DieList = slices.Compact(cache.DieList)
slices.Sort(cache.NumaDomainList)
cache.NumaDomainList = slices.Compact(cache.NumaDomainList)
}
// SocketList gets the list of CPU socket IDs
func SocketList() []int {
return slices.Clone(cache.SocketList)
}
// HwthreadList gets the list of hardware thread IDs in the order of listing in /proc/cpuinfo
func HwthreadList() []int {
return slices.Clone(cache.HwthreadList)
}
// Get list of hardware thread IDs in the order of listing in /proc/cpuinfo
// Deprecated! Use HwthreadList()
func CpuList() []int {
return HwthreadList()
}
// CoreList gets the list of CPU core IDs in the order of listing in /proc/cpuinfo
func CoreList() []int {
return slices.Clone(cache.CoreList)
}
// Get list of NUMA node IDs
func NumaNodeList() []int {
return slices.Clone(cache.NumaDomainList)
}
// DieList gets the list of CPU die IDs
func DieList() []int {
if len(cache.DieList) > 0 {
return slices.Clone(cache.DieList)
}
return SocketList()
}
// GetTypeList gets the list of specified type using the naming format inside ClusterCockpit
func GetTypeList(topology_type string) []int {
switch topology_type {
case "node":
return []int{0}
case "socket":
return SocketList()
case "die":
return DieList()
case "memoryDomain":
return NumaNodeList()
case "core":
return CoreList()
case "hwthread":
return HwthreadList()
}
return []int{}
}
// CpuData returns CPU data for each hardware thread
func CpuData() []HwthreadEntry {
// return a deep copy to protect cache data
c := slices.Clone(cache.CpuData)
for i := range c {
c[i].CoreCPUsList = slices.Clone(cache.CpuData[i].CoreCPUsList)
}
return c
}
// Structure holding basic information about a CPU
type CpuInformation struct {
NumHWthreads int
SMTWidth int
NumSockets int
NumDies int
NumCores int
NumNumaDomains int
}
// CpuInformation reports basic information about the CPU
func CpuInfo() CpuInformation {
return CpuInformation{
NumNumaDomains: len(cache.NumaDomainList),
SMTWidth: len(cache.SMTList),
NumDies: len(cache.DieList),
NumCores: len(cache.CoreList),
NumSockets: len(cache.SocketList),
NumHWthreads: len(cache.HwthreadList),
}
}
// GetHwthreadSocket gets the CPU socket ID for a given hardware thread ID
// In case hardware thread ID is not found -1 is returned
func GetHwthreadSocket(cpuID int) int {
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.CpuID == cpuID {
return d.Socket
}
}
return -1
}
// GetHwthreadNumaDomain gets the NUMA domain ID for a given hardware thread ID
// In case hardware thread ID is not found -1 is returned
func GetHwthreadNumaDomain(cpuID int) int {
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.CpuID == cpuID {
return d.NumaDomain
}
}
return -1
}
// GetHwthreadDie gets the CPU die ID for a given hardware thread ID
// In case hardware thread ID is not found -1 is returned
func GetHwthreadDie(cpuID int) int {
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.CpuID == cpuID {
return d.Die
}
}
return -1
}
// GetHwthreadCore gets the CPU core ID for a given hardware thread ID
// In case hardware thread ID is not found -1 is returned
func GetHwthreadCore(cpuID int) int {
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.CpuID == cpuID {
return d.Core
}
}
return -1
}
// GetSocketHwthreads gets all hardware thread IDs associated with a CPU socket
func GetSocketHwthreads(socket int) []int {
cpuList := make([]int, 0)
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.Socket == socket {
cpuList = append(cpuList, d.CpuID)
}
}
return cpuList
}
// GetNumaDomainHwthreads gets the all hardware thread IDs associated with a NUMA domain
func GetNumaDomainHwthreads(numaDomain int) []int {
cpuList := make([]int, 0)
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.NumaDomain == numaDomain {
cpuList = append(cpuList, d.CpuID)
}
}
return cpuList
}
// GetDieHwthreads gets all hardware thread IDs associated with a CPU die
func GetDieHwthreads(die int) []int {
cpuList := make([]int, 0)
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.Die == die {
cpuList = append(cpuList, d.CpuID)
}
}
return cpuList
}
// GetCoreHwthreads get all hardware thread IDs associated with a CPU core
func GetCoreHwthreads(core int) []int {
cpuList := make([]int, 0)
for i := range cache.CpuData {
d := &cache.CpuData[i]
if d.Core == core {
cpuList = append(cpuList, d.CpuID)
}
}
return cpuList
}

View File

@@ -1,125 +0,0 @@
package hostlist
import (
"fmt"
"regexp"
"sort"
"strconv"
"strings"
)
func Expand(in string) (result []string, err error) {
// Create ranges regular expression
reStNumber := "[[:digit:]]+"
reStRange := reStNumber + "-" + reStNumber
reStOptionalNumberOrRange := "(" + reStNumber + ",|" + reStRange + ",)*"
reStNumberOrRange := "(" + reStNumber + "|" + reStRange + ")"
reStBraceLeft := "[[]"
reStBraceRight := "[]]"
reStRanges := reStBraceLeft +
reStOptionalNumberOrRange +
reStNumberOrRange +
reStBraceRight
reRanges := regexp.MustCompile(reStRanges)
// Create host list regular expression
reStDNSChars := "[a-zA-Z0-9-]+"
reStPrefix := "^(" + reStDNSChars + ")"
reStOptionalSuffix := "(" + reStDNSChars + ")?"
re := regexp.MustCompile(reStPrefix + "([[][0-9,-]+[]])?" + reStOptionalSuffix)
// Remove all delimiters from the input
in = strings.TrimLeft(in, ", ")
for len(in) > 0 {
if v := re.FindStringSubmatch(in); v != nil {
// Remove matched part from the input
lenPrefix := len(v[0])
in = in[lenPrefix:]
// Remove all delimiters from the input
in = strings.TrimLeft(in, ", ")
// matched prefix, range and suffix
hlPrefix := v[1]
hlRanges := v[2]
hlSuffix := v[3]
// Single node without ranges
if hlRanges == "" {
result = append(result, hlPrefix)
continue
}
// Node with ranges
if v := reRanges.FindStringSubmatch(hlRanges); v != nil {
// Remove braces
hlRanges = hlRanges[1 : len(hlRanges)-1]
// Split host ranges at ,
for _, hlRange := range strings.Split(hlRanges, ",") {
// Split host range at -
RangeStartEnd := strings.Split(hlRange, "-")
// Range is only a single number
if len(RangeStartEnd) == 1 {
result = append(result, hlPrefix+RangeStartEnd[0]+hlSuffix)
continue
}
// Range has a start and an end
widthRangeStart := len(RangeStartEnd[0])
widthRangeEnd := len(RangeStartEnd[1])
iStart, _ := strconv.ParseUint(RangeStartEnd[0], 10, 64)
iEnd, _ := strconv.ParseUint(RangeStartEnd[1], 10, 64)
if iStart > iEnd {
return nil, fmt.Errorf("single range start is greater than end: %s", hlRange)
}
// Create print format string for range numbers
doPadding := widthRangeStart == widthRangeEnd
widthPadding := widthRangeStart
var formatString string
if doPadding {
formatString = "%0" + fmt.Sprint(widthPadding) + "d"
} else {
formatString = "%d"
}
formatString = hlPrefix + formatString + hlSuffix
// Add nodes from this range
for i := iStart; i <= iEnd; i++ {
result = append(result, fmt.Sprintf(formatString, i))
}
}
} else {
return nil, fmt.Errorf("not at hostlist range: %s", hlRanges)
}
} else {
return nil, fmt.Errorf("not a hostlist: %s", in)
}
}
if result != nil {
// sort
sort.Strings(result)
// uniq
previous := 1
for current := 1; current < len(result); current++ {
if result[current-1] != result[current] {
if previous != current {
result[previous] = result[current]
}
previous++
}
}
result = result[:previous]
}
return
}

View File

@@ -1,126 +0,0 @@
package hostlist
import (
"testing"
)
func TestExpand(t *testing.T) {
// Compare two slices of strings
equal := func(a, b []string) bool {
if len(a) != len(b) {
return false
}
for i, v := range a {
if v != b[i] {
return false
}
}
return true
}
type testDefinition struct {
input string
resultExpected []string
errorExpected bool
}
expandTests := []testDefinition{
{
// Single node
input: "n1",
resultExpected: []string{"n1"},
errorExpected: false,
},
{
// Single node, duplicated
input: "n1,n1",
resultExpected: []string{"n1"},
errorExpected: false,
},
{
// Single node with padding
input: "n[01]",
resultExpected: []string{"n01"},
errorExpected: false,
},
{
// Single node with suffix
input: "n[01]-p",
resultExpected: []string{"n01-p"},
errorExpected: false,
},
{
// Multiple nodes with a single range
input: "n[1-2]",
resultExpected: []string{"n1", "n2"},
errorExpected: false,
},
{
// Multiple nodes with a single range and a single index
input: "n[1-2,3]",
resultExpected: []string{"n1", "n2", "n3"},
errorExpected: false,
},
{
// Multiple nodes with different prefixes
input: "n[1-2],m[1,2]",
resultExpected: []string{"m1", "m2", "n1", "n2"},
errorExpected: false,
},
{
// Multiple nodes with different suffixes
input: "n[1-2]-p,n[1,2]-q",
resultExpected: []string{"n1-p", "n1-q", "n2-p", "n2-q"},
errorExpected: false,
},
{
// Multiple nodes with and without node ranges
input: " n09, n[01-04,06-07,09] , , n10,n04",
resultExpected: []string{"n01", "n02", "n03", "n04", "n06", "n07", "n09", "n10"},
errorExpected: false,
},
{
// Forbidden DNS character
input: "n@",
resultExpected: []string{},
errorExpected: true,
},
{
// Forbidden range
input: "n[1-2-2,3]",
resultExpected: []string{},
errorExpected: true,
},
{
// Forbidden range limits
input: "n[2-1]",
resultExpected: []string{},
errorExpected: true,
},
}
for _, expandTest := range expandTests {
result, err := Expand(expandTest.input)
hasError := err != nil
if hasError != expandTest.errorExpected && hasError {
t.Errorf("Expand('%s') failed: unexpected error '%v'",
expandTest.input, err)
continue
}
if hasError != expandTest.errorExpected && !hasError {
t.Errorf("Expand('%s') did not fail as expected: got result '%+v'",
expandTest.input, result)
continue
}
if !hasError && !equal(result, expandTest.resultExpected) {
t.Errorf("Expand('%s') failed: got result '%+v', expected result '%v'",
expandTest.input, result, expandTest.resultExpected)
continue
}
t.Logf("Checked hostlist.Expand('%s'): result = '%+v', err = '%v'",
expandTest.input, result, err)
}
}

View File

@@ -1,44 +1,8 @@
{
"natsrecv": {
"natsrecv" : {
"type": "nats",
"address": "nats://my-url",
"port": "4222",
"port" : "4222",
"database": "testcluster"
},
"redfish_recv": {
"type": "redfish",
"endpoint": "https://%h-bmc",
"client_config": [
{
"host_list": "my-host-1-[1-2]",
"username": "username-1",
"password": "password-1"
},
{
"host_list": "my-host-2-[1,2]",
"username": "username-2",
"password": "password-2"
}
]
},
"ipmi_recv": {
"type": "ipmi",
"endpoint": "ipmi-sensors://%h-ipmi",
"exclude_metrics": [
"fan_speed",
"voltage"
],
"client_config": [
{
"username": "username-1",
"password": "password-1",
"host_list": "my-host-1-[1-2]"
},
{
"username": "username-2",
"password": "password-2",
"host_list": "my-host-2-[1,2]"
}
]
}
}
}

View File

@@ -2,7 +2,7 @@
This folder contains the ReceiveManager and receiver implementations for the cc-metric-collector.
## Configuration
# Configuration
The configuration file for the receivers is a list of configurations. The `type` field in each specifies which receiver to initialize.
@@ -22,12 +22,8 @@ This allows to specify
- [`nats`](./natsReceiver.md): Receive metrics from the NATS network
- [`prometheus`](./prometheusReceiver.md): Scrape data from a Prometheus client
- [`http`](./httpReceiver.md): Listen for HTTP Post requests transporting metrics in InfluxDB line protocol
- [`ipmi`](./ipmiReceiver.md): Read IPMI sensor readings
- [`redfish`](redfishReceiver.md) Use the Redfish (specification) to query thermal and power metrics
- [`snmp`](./snmpReceiver.md) Query SNMP endpoints in the network
## Contributing own receivers
# Contributing own receivers
A receiver contains a few functions and is derived from the type `Receiver` (in `metricReceiver.go`):
For an example, check the [sample receiver](./sampleReceiver.go)

View File

@@ -5,14 +5,15 @@ import (
"encoding/json"
"errors"
"fmt"
"io/ioutil"
"net/http"
"strings"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
"github.com/gorilla/mux"
influx "github.com/influxdata/line-protocol"
)
const HTTP_RECEIVER_PORT = "8080"
@@ -22,39 +23,22 @@ type HttpReceiverConfig struct {
Addr string `json:"address"`
Port string `json:"port"`
Path string `json:"path"`
// Maximum amount of time to wait for the next request when keep-alives are enabled
// should be larger than the measurement interval to keep the connection open
IdleTimeout string `json:"idle_timeout"`
idleTimeout time.Duration
// Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled
KeepAlivesEnabled bool `json:"keep_alives_enabled"`
// Basic authentication
Username string `json:"username"`
Password string `json:"password"`
useBasicAuth bool
}
type HttpReceiver struct {
receiver
meta map[string]string
config HttpReceiverConfig
server *http.Server
wg sync.WaitGroup
handler *influx.MetricHandler
parser *influx.Parser
meta map[string]string
config HttpReceiverConfig
router *mux.Router
server *http.Server
wg sync.WaitGroup
}
func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
r.name = fmt.Sprintf("HttpReceiver(%s)", name)
// Set default values
r.config.Port = HTTP_RECEIVER_PORT
r.config.KeepAlivesEnabled = true
// should be larger than the measurement interval to keep the connection open
r.config.IdleTimeout = "120s"
// Read config
if len(config) > 0 {
err := json.Unmarshal(config, &r.config)
if err != nil {
@@ -65,47 +49,20 @@ func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
if len(r.config.Port) == 0 {
return errors.New("not all configuration variables set required by HttpReceiver")
}
// Check idle timeout config
if len(r.config.IdleTimeout) > 0 {
t, err := time.ParseDuration(r.config.IdleTimeout)
if err == nil {
cclog.ComponentDebug(r.name, "idleTimeout", t)
r.config.idleTimeout = t
}
}
// Check basic authentication config
if len(r.config.Username) > 0 || len(r.config.Password) > 0 {
r.config.useBasicAuth = true
}
if r.config.useBasicAuth && len(r.config.Username) == 0 {
return errors.New("basic authentication requires username")
}
if r.config.useBasicAuth && len(r.config.Password) == 0 {
return errors.New("basic authentication requires password")
}
r.meta = map[string]string{"source": r.name}
p := r.config.Path
if !strings.HasPrefix(p, "/") {
p = "/" + p
}
addr := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
uri := addr + p
cclog.ComponentDebug(r.name, "INIT", "listen on:", uri)
// Register handler function r.ServerHttp for path p in the DefaultServeMux
http.HandleFunc(p, r.ServerHttp)
// Create http server
r.server = &http.Server{
Addr: addr,
Handler: nil, // handler to invoke, http.DefaultServeMux if nil
IdleTimeout: r.config.idleTimeout,
}
r.server.SetKeepAlivesEnabled(r.config.KeepAlivesEnabled)
uri := fmt.Sprintf("%s:%s%s", r.config.Addr, r.config.Port, p)
cclog.ComponentDebug(r.name, "INIT", uri)
r.handler = influx.NewMetricHandler()
r.parser = influx.NewParser(r.handler)
r.parser.SetTimeFunc(DefaultTime)
r.router = mux.NewRouter()
r.router.Path(p).HandlerFunc(r.ServerHttp)
r.server = &http.Server{Addr: uri, Handler: r.router}
return nil
}
@@ -122,97 +79,31 @@ func (r *HttpReceiver) Start() {
}
func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
// Check request method, only post method is handled
if req.Method != http.MethodPost {
http.Error(w, "Method Not Allowed", http.StatusMethodNotAllowed)
return
}
// Check basic authentication
if r.config.useBasicAuth {
username, password, ok := req.BasicAuth()
if !ok || username != r.config.Username || password != r.config.Password {
http.Error(w, "Unauthorized", http.StatusUnauthorized)
return
}
body, err := ioutil.ReadAll(req.Body)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
metrics, err := r.parser.Parse(body)
if err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
}
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
for _, m := range metrics {
y := lp.FromInfluxMetric(m)
for k, v := range r.meta {
y.AddMeta(k, v)
}
// Decode tags
tags := make(map[string]string)
for {
key, value, err := d.NextTag()
if err != nil {
msg := "ServerHttp: Failed to decode tag: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
if key == nil {
break
}
tags[string(key)] = string(value)
}
// Decode fields
fields := make(map[string]interface{})
for {
key, value, err := d.NextField()
if err != nil {
msg := "ServerHttp: Failed to decode field: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
if key == nil {
break
}
fields[string(key)] = value.Interface()
}
// Decode time stamp
t, err := d.Time(influx.Nanosecond, time.Time{})
if err != nil {
msg := "ServerHttp: Failed to decode time stamp: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
y, _ := lp.New(
string(measurement),
tags,
r.meta,
fields,
t,
)
if r.sink != nil {
r.sink <- y
}
}
// Check for IO errors
err := d.Err()
if err != nil {
msg := "ServerHttp: Failed to decode: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
w.WriteHeader(http.StatusOK)
}

View File

@@ -10,10 +10,7 @@ The `http` receiver can be used receive metrics through HTTP POST requests.
"type": "http",
"address" : "",
"port" : "8080",
"path" : "/write",
"idle_timeout": "120s",
"username": "myUser",
"password": "myPW"
"path" : "/write"
}
}
```
@@ -22,22 +19,5 @@ The `http` receiver can be used receive metrics through HTTP POST requests.
- `address`: Listen address
- `port`: Listen port
- `path`: URL path for the write endpoint
- `idle_timeout`: Maximum amount of time to wait for the next request when keep-alives are enabled should be larger than the measurement interval to keep the connection open
- `keep_alives_enabled`: Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled.
- `username`: username for basic authentication
- `password`: password for basic authentication
The HTTP endpoint listens to `http://<address>:<port>/<path>`
### Debugging
- Install [curl](https://curl.se/)
- Use curl to send message to `http` receiver
```bash
curl http://localhost:8080/write \
--user "myUser:myPW" \
--data \
"myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
```

View File

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

View File

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

View File

@@ -1,7 +1,7 @@
package receivers
import (
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
)
type defaultReceiverConfig struct {

View File

@@ -6,9 +6,9 @@ import (
"fmt"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
influx "github.com/influxdata/line-protocol"
nats "github.com/nats-io/nats.go"
)
@@ -21,85 +21,37 @@ type NatsReceiverConfig struct {
type NatsReceiver struct {
receiver
nc *nats.Conn
meta map[string]string
config NatsReceiverConfig
nc *nats.Conn
handler *influx.MetricHandler
parser *influx.Parser
meta map[string]string
config NatsReceiverConfig
}
var DefaultTime = func() time.Time {
return time.Unix(42, 0)
}
// Start subscribes to the configured NATS subject
// Messages wil be handled by r._NatsReceive
func (r *NatsReceiver) Start() {
cclog.ComponentDebug(r.name, "START")
r.nc.Subscribe(r.config.Subject, r._NatsReceive)
}
// _NatsReceive receives subscribed messages from the NATS server
func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
d := influx.NewDecoderWithBytes(m.Data)
for d.Next() {
// Decode measurement name
measurement, err := d.Measurement()
if err != nil {
msg := "_NatsReceive: Failed to decode measurement: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
// Decode tags
tags := make(map[string]string)
for {
key, value, err := d.NextTag()
if err != nil {
msg := "_NatsReceive: Failed to decode tag: " + err.Error()
cclog.ComponentError(r.name, msg)
return
metrics, err := r.parser.Parse(m.Data)
if err == nil {
for _, m := range metrics {
y := lp.FromInfluxMetric(m)
for k, v := range r.meta {
y.AddMeta(k, v)
}
if key == nil {
break
if r.sink != nil {
r.sink <- y
}
tags[string(key)] = string(value)
}
// Decode fields
fields := make(map[string]interface{})
for {
key, value, err := d.NextField()
if err != nil {
msg := "_NatsReceive: Failed to decode field: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
if key == nil {
break
}
fields[string(key)] = value.Interface()
}
// Decode time stamp
t, err := d.Time(influx.Nanosecond, time.Time{})
if err != nil {
msg := "_NatsReceive: Failed to decode time: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
y, _ := lp.New(
string(measurement),
tags,
r.meta,
fields,
t,
)
if r.sink != nil {
r.sink <- y
}
}
}
// Close closes the connection to the NATS server
func (r *NatsReceiver) Close() {
if r.nc != nil {
cclog.ComponentDebug(r.name, "CLOSE")
@@ -107,13 +59,10 @@ 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) {
r := new(NatsReceiver)
r.name = fmt.Sprintf("NatsReceiver(%s)", name)
// Read configuration file, allow overwriting default config
r.config.Addr = "localhost"
r.config.Addr = nats.DefaultURL
r.config.Port = "4222"
if len(config) > 0 {
err := json.Unmarshal(config, &r.config)
@@ -127,21 +76,17 @@ 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")
}
// Set metadata
r.meta = map[string]string{
"source": r.name,
}
// Connect to NATS server
url := fmt.Sprintf("nats://%s:%s", r.config.Addr, r.config.Port)
cclog.ComponentDebug(r.name, "NewNatsReceiver", url, "Subject", r.config.Subject)
if nc, err := nats.Connect(url); err == nil {
r.meta = map[string]string{"source": r.name}
uri := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
cclog.ComponentDebug(r.name, "NewNatsReceiver", uri, "Subject", r.config.Subject)
if nc, err := nats.Connect(uri); err == nil {
r.nc = nc
} else {
r.nc = nil
return nil, err
}
r.handler = influx.NewMetricHandler()
r.parser = influx.NewParser(r.handler)
r.parser.SetTimeFunc(DefaultTime)
return r, nil
}

View File

@@ -19,32 +19,3 @@ 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
### Debugging
- Install NATS server and command line client
- Start NATS server
```bash
nats-server --net nats-server.example.org --port 4222
```
- Check NATS server works as expected
```bash
nats --server=nats-server-db.example.org:4222 server check
```
- Use NATS command line client to subscribe to all messages
```bash
nats --server=nats-server-db.example.org:4222 sub ">"
```
- Use NATS command line client to send message to NATS receiver
```bash
nats --server=nats-server-db.example.org:4222 pub subject \
"myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
```

View File

@@ -12,8 +12,8 @@ import (
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
)
type PrometheusReceiverConfig struct {

View File

@@ -2,25 +2,22 @@ package receivers
import (
"encoding/json"
"fmt"
"os"
"sync"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
)
var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
"http": NewHttpReceiver,
"ipmi": NewIPMIReceiver,
"nats": NewNatsReceiver,
"redfish": NewRedfishReceiver,
"snmp": NewSNMPReceiver,
"nats": NewNatsReceiver,
}
type receiveManager struct {
inputs []Receiver
output chan lp.CCMetric
done chan bool
wg *sync.WaitGroup
config []json.RawMessage
}
@@ -36,6 +33,8 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
// Initialize struct fields
rm.inputs = make([]Receiver, 0)
rm.output = nil
rm.done = make(chan bool)
rm.wg = wg
rm.config = make([]json.RawMessage, 0)
configFile, err := os.Open(receiverConfigFile)
@@ -59,7 +58,7 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
}
func (rm *receiveManager) Start() {
cclog.ComponentDebug("ReceiveManager", "START")
rm.wg.Add(1)
for _, r := range rm.inputs {
cclog.ComponentDebug("ReceiveManager", "START", r.Name())
@@ -75,13 +74,9 @@ func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error
cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "JSON config error:", err.Error())
return err
}
if config.Type == "" {
cclog.ComponentError("ReceiveManager", "SKIP", "JSON config for receiver", name, "does not contain a receiver type")
return fmt.Errorf("JSON config for receiver %s does not contain a receiver type", name)
}
if _, found := AvailableReceivers[config.Type]; !found {
cclog.ComponentError("ReceiveManager", "SKIP", "unknown receiver type:", config.Type)
return fmt.Errorf("unknown receiver type: %s", config.Type)
cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "unknown receiver:", err.Error())
return err
}
r, err := AvailableReceivers[config.Type](name, rawConfig)
if err != nil {
@@ -102,19 +97,16 @@ func (rm *receiveManager) AddOutput(output chan lp.CCMetric) {
}
func (rm *receiveManager) Close() {
cclog.ComponentDebug("ReceiveManager", "CLOSE")
// Close all receivers
for _, r := range rm.inputs {
cclog.ComponentDebug("ReceiveManager", "CLOSE", r.Name())
r.Close()
}
cclog.ComponentDebug("ReceiveManager", "DONE")
rm.wg.Done()
cclog.ComponentDebug("ReceiveManager", "CLOSE")
}
func New(wg *sync.WaitGroup, receiverConfigFile string) (ReceiveManager, error) {
r := new(receiveManager)
r := &receiveManager{}
err := r.Init(wg, receiverConfigFile)
if err != nil {
return nil, err

View File

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

View File

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

View File

@@ -4,7 +4,7 @@ import (
"encoding/json"
"fmt"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
)
// SampleReceiver configuration: receiver type, listen address, port
@@ -36,26 +36,16 @@ func (r *SampleReceiver) Start() {
// or use own go routine but always make sure it exits
// as soon as it gets the signal of the r.done channel
//
// r.done = make(chan bool)
// r.wg.Add(1)
// go func() {
// defer r.wg.Done()
//
// // Create ticker
// ticker := time.NewTicker(30 * time.Second)
// defer ticker.Stop()
//
// for {
// readMetric()
// select {
// case <-ticker.C:
// // process ticker event -> continue
// continue
// case <-r.done:
// return
// }
// }
// for {
// select {
// case <-r.done:
// r.wg.Done()
// return
// }
// }
// r.wg.Done()
// }()
}

View File

@@ -1,294 +0,0 @@
package receivers
import (
"encoding/json"
"fmt"
"regexp"
"strings"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
"github.com/gosnmp/gosnmp"
)
type SNMPReceiverTargetConfig struct {
Hostname string `json:"hostname"`
Port int `json:"port,omitempty"`
Community string `json:"community,omitempty"`
Timeout string `json:"timeout,omitempty"`
timeout time.Duration
Version string `json:"version,omitempty"`
Type string `json:"type,omitempty"`
TypeId string `json:"type-id,omitempty"`
SubType string `json:"subtype,omitempty"`
SubTypeId string `json:"subtype-id,omitempty"`
}
type SNMPReceiverMetricConfig struct {
Name string `json:"name"`
OID string `json:"oid"`
Unit string `json:"unit,omitempty"`
}
// SNMPReceiver configuration: receiver type, listen address, port
type SNMPReceiverConfig struct {
Type string `json:"type"`
Targets []SNMPReceiverTargetConfig `json:"targets"`
Metrics []SNMPReceiverMetricConfig `json:"metrics"`
ReadInterval string `json:"read_interval,omitempty"`
}
type SNMPReceiver struct {
receiver
config SNMPReceiverConfig
// Storage for static information
meta map[string]string
tags map[string]string
// Use in case of own go routine
done chan bool
wg sync.WaitGroup
interval time.Duration
}
func validOid(oid string) bool {
// Regex from https://github.com/BornToBeRoot/NETworkManager/blob/6805740762bf19b95051c7eaa73cf2b4727733c3/Source/NETworkManager.Utilities/RegexHelper.cs#L88
// Match on leading dot added by Thomas Gruber <thomas.gruber@fau.de>
match, err := regexp.MatchString(`^[\.]?[012]\.(?:[0-9]|[1-3][0-9])(\.\d+)*$`, oid)
if err != nil {
return false
}
return match
}
func (r *SNMPReceiver) readTarget(target SNMPReceiverTargetConfig, output chan lp.CCMetric) {
port := uint16(161)
comm := "public"
timeout := time.Duration(1) * time.Second
version := gosnmp.Version2c
timestamp := time.Now()
if target.Port > 0 {
port = uint16(target.Port)
}
if len(target.Community) > 0 {
comm = target.Community
}
if target.timeout > 0 {
timeout = target.timeout
}
if len(target.Version) > 0 {
switch target.Version {
case "1":
version = gosnmp.Version1
case "2c":
version = gosnmp.Version2c
case "3":
version = gosnmp.Version3
default:
cclog.ComponentError(r.name, "Invalid SNMP version ", target.Version)
return
}
}
params := &gosnmp.GoSNMP{
Target: target.Hostname,
Port: port,
Community: comm,
Version: version,
Timeout: timeout,
}
err := params.Connect()
if err != nil {
cclog.ComponentError(r.name, err.Error())
return
}
for _, metric := range r.config.Metrics {
if !validOid(metric.OID) {
cclog.ComponentDebug(r.name, "Skipping ", metric.Name, ", not valid OID: ", metric.OID)
continue
}
oids := make([]string, 0)
name := gosnmp.SnmpPDU{
Value: metric.Name,
Name: metric.Name,
}
nameidx := -1
value := gosnmp.SnmpPDU{
Value: nil,
Name: metric.OID,
}
valueidx := -1
unit := gosnmp.SnmpPDU{
Value: metric.Unit,
Name: metric.Unit,
}
unitidx := -1
idx := 0
if validOid(metric.Name) {
oids = append(oids, metric.Name)
nameidx = idx
idx = idx + 1
}
if validOid(metric.OID) {
oids = append(oids, metric.OID)
valueidx = idx
idx = idx + 1
}
if len(metric.Unit) > 0 && validOid(metric.Unit) {
oids = append(oids, metric.Unit)
unitidx = idx
}
//cclog.ComponentDebug(r.name, len(oids), oids)
result, err := params.Get(oids)
if err != nil {
cclog.ComponentError(r.name, "failed to get data for OIDs ", strings.Join(oids, ","), ": ", err.Error())
continue
}
if nameidx >= 0 && len(result.Variables) > nameidx {
name = result.Variables[nameidx]
}
if valueidx >= 0 && len(result.Variables) > valueidx {
value = result.Variables[valueidx]
}
if unitidx >= 0 && len(result.Variables) > unitidx {
unit = result.Variables[unitidx]
}
tags := r.tags
if len(target.Type) > 0 {
tags["type"] = target.Type
}
if len(target.TypeId) > 0 {
tags["type-id"] = target.TypeId
}
if len(target.SubType) > 0 {
tags["stype"] = target.SubType
}
if len(target.SubTypeId) > 0 {
tags["stype-id"] = target.SubTypeId
}
if value.Value != nil {
y, err := lp.New(name.Value.(string), tags, r.meta, map[string]interface{}{"value": value.Value}, timestamp)
if err == nil {
if len(unit.Name) > 0 && unit.Value != nil {
y.AddMeta("unit", unit.Value.(string))
}
output <- y
}
}
}
params.Conn.Close()
}
// Implement functions required for Receiver interface
// Start(), Close()
// See: metricReceiver.go
func (r *SNMPReceiver) Start() {
cclog.ComponentDebug(r.name, "START")
r.done = make(chan bool)
r.wg.Add(1)
go func() {
defer r.wg.Done()
// Create ticker
ticker := time.NewTicker(r.interval)
defer ticker.Stop()
for {
select {
case <-ticker.C:
// process ticker event -> continue
if r.sink != nil {
for _, t := range r.config.Targets {
select {
case <-r.done:
return
default:
r.readTarget(t, r.sink)
}
}
}
continue
case <-r.done:
return
}
}
}()
}
// Close receiver: close network connection, close files, close libraries, ...
func (r *SNMPReceiver) Close() {
cclog.ComponentDebug(r.name, "CLOSE")
r.done <- true
r.wg.Wait()
}
// New function to create a new instance of the receiver
// Initialize the receiver by giving it a name and reading in the config JSON
func NewSNMPReceiver(name string, config json.RawMessage) (Receiver, error) {
var err error = nil
r := new(SNMPReceiver)
// Set name of SNMPReceiver
// The name should be chosen in such a way that different instances of SNMPReceiver can be distinguished
r.name = fmt.Sprintf("SNMPReceiver(%s)", name)
// Set static information
r.meta = map[string]string{"source": r.name, "group": "SNMP"}
r.tags = map[string]string{"type": "node"}
// Set defaults in r.config
r.interval = time.Duration(30) * time.Second
// Read the sample receiver specific JSON config
if len(config) > 0 {
err := json.Unmarshal(config, &r.config)
if err != nil {
cclog.ComponentError(r.name, "Error reading config:", err.Error())
return nil, err
}
}
// Check that all required fields in the configuration are set
if len(r.config.Targets) == 0 {
err = fmt.Errorf("no targets configured, exiting")
cclog.ComponentError(r.name, err.Error())
return nil, err
}
if len(r.config.Metrics) == 0 {
err = fmt.Errorf("no metrics configured, exiting")
cclog.ComponentError(r.name, err.Error())
return nil, err
}
if len(r.config.ReadInterval) > 0 {
d, err := time.ParseDuration(r.config.ReadInterval)
if err != nil {
err = fmt.Errorf("failed to parse read interval, exiting")
cclog.ComponentError(r.name, err.Error())
return nil, err
}
r.interval = d
}
newtargets := make([]SNMPReceiverTargetConfig, 0)
for _, t := range r.config.Targets {
t.timeout = time.Duration(1) * time.Second
if len(t.Timeout) > 0 {
d, err := time.ParseDuration(t.Timeout)
if err != nil {
err = fmt.Errorf("failed to parse interval for target %s", t.Hostname)
cclog.ComponentError(r.name, err.Error())
continue
}
t.timeout = d
}
newtargets = append(newtargets, t)
}
r.config.Targets = newtargets
return r, nil
}

View File

@@ -1,60 +0,0 @@
# SNMP Receiver
```json
"<name>": {
"type": "snmp",
"read_interval": "30s",
"targets" : [{
"hostname" : "host1.example.com",
"port" : 161,
"community": "public",
"timeout" : 1,
}],
"metrics" : [
{
"name": "sensor1",
"value": "1.3.6.1.2.1.1.4.0",
"unit": "1.3.6.1.2.1.1.7.0",
},
{
"name": "1.3.6.1.2.1.1.2.0",
"value": "1.3.6.1.2.1.1.4.0",
"unit": "mb/s",
}
]
}
```
The `snmp` receiver uses [gosnmp](https://github.com/gosnmp/gosnmp) to read metrics from network-attached devices.
The configuration of SNMP is quite extensive due to it's flexibility.
## Configuration
- `type` has to be `snmp`
- `read_interval` as duration like '1s' or '20s' (default '30s')
For the receiver, the configuration is split in two parts:
### Target configuration
Each network-attached device that should be queried. A target consits of
- `hostname`
- `port` (default 161)
- `community` (default `public`)
- `timeout` as duration like '1s' or '20s' (default '1s')
- `version` SNMP version `X` (`X` in `1`, `2c`, `3`) (default `2c`)
- `type` to specify `type` tag for the target (default `node`)
- `type-id` to specify `type-id` tag for the target
- `stype` to specify `stype` tag (sub type) for the target
- `stype-id` to specify `stype-id` tag for the target
### Metric configuration
- `name` can be an OID or a user-given string
- `value` has to be an OID
- `unit` can be empty, an OID or a user-given string
If a OID is used for `name` or `unit`, the receiver will use the returned values to create the output metric. If there are any issues with the returned values, it uses the `OID`.
## Testing
For testing an SNMP endpoint and OIDs, you can use [`scripts/snmpReceiverTest`](../scripts/snmpReceiverTest)

View File

@@ -6,7 +6,7 @@ CC_HOME=/tmp
LOG_DIR=/var/log
DATA_DIR=/var/lib/cc-metric-collector
DATA_DIR=/var/lib/grafana
MAX_OPEN_FILES=10000
@@ -15,9 +15,3 @@ CONF_DIR=/etc/cc-metric-collector
CONF_FILE=/etc/cc-metric-collector/cc-metric-collector.json
RESTART_ON_UPGRADE=true
# Golang runtime debugging. (see: https://pkg.go.dev/runtime)
# GODEBUG=gctrace=1
# Golang garbage collection target percentage
# GOGC=100

View File

@@ -1,16 +0,0 @@
#!/usr/bin/make -f
# You must remove unused comment lines for the released package.
#export DH_VERBOSE = 1
#export DEB_BUILD_MAINT_OPTIONS = hardening=+all
#export DEB_CFLAGS_MAINT_APPEND = -Wall -pedantic
#export DEB_LDFLAGS_MAINT_APPEND = -Wl,--as-needed
%:
dh $@
override_dh_auto_build:
make
override_dh_auto_install:
make PREFIX=/usr install

View File

@@ -19,7 +19,7 @@
PATH=/bin:/usr/bin:/sbin:/usr/sbin
NAME=cc-metric-collector
DESC="ClusterCockpit metric collector"
DEFAULT=/etc/default/${NAME}
DEFAULT=/etc/default/${NAME}.json
CC_USER=clustercockpit
CC_GROUP=clustercockpit
@@ -75,7 +75,7 @@ case "$1" in
fi
# Start Daemon
start-stop-daemon --start -b --chdir "$WORK_DIR" --user "$CC_USER" -c "$CC_USER" --pidfile "$PID_FILE" --exec $DAEMON -- $CC_OPTS
start-stop-daemon --start -b --chdir "$WORK_DIR" --user "$CC_USER" -c "$CC_USER" --pidfile "$PID_FILE" --exec $DAEMON -- $DAEMON_OPTS
return=$?
if [ $return -eq 0 ]
then

View File

@@ -3,6 +3,7 @@ Description=ClusterCockpit metric collector
Documentation=https://github.com/ClusterCockpit/cc-metric-collector
Wants=network-online.target
After=network-online.target
After=postgresql.service mariadb.service mysql.service
[Service]
EnvironmentFile=/etc/default/cc-metric-collector
@@ -13,7 +14,7 @@ Restart=on-failure
WorkingDirectory=/tmp
RuntimeDirectory=cc-metric-collector
RuntimeDirectoryMode=0750
ExecStart=/usr/bin/cc-metric-collector --config=${CONF_FILE}
ExecStart=/usr/sbin/cc-metric-collector --config=${CONF_FILE}
LimitNOFILE=10000
TimeoutStopSec=20
UMask=0027

View File

@@ -10,8 +10,6 @@ BuildRequires: go-toolset
BuildRequires: systemd-rpm-macros
# for header downloads
BuildRequires: wget
# Recommended when using the sysusers_create_package macro
Requires(pre): /usr/bin/systemd-sysusers
Provides: %{name} = %{version}
@@ -29,7 +27,7 @@ make
%install
install -Dpm 0750 %{name} %{buildroot}%{_bindir}/%{name}
install -Dpm 0750 %{name} %{buildroot}%{_sbindir}/%{name}
install -Dpm 0600 config.json %{buildroot}%{_sysconfdir}/%{name}/%{name}.json
install -Dpm 0600 collectors.json %{buildroot}%{_sysconfdir}/%{name}/collectors.json
install -Dpm 0600 sinks.json %{buildroot}%{_sysconfdir}/%{name}/sinks.json
@@ -44,7 +42,7 @@ install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.c
# go test should be here... :)
%pre
%sysusers_create_package %{name} scripts/%{name}.sysusers
%sysusers_create_package scripts/%{name}.sysusers
%post
%systemd_post %{name}.service
@@ -54,7 +52,7 @@ install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.c
%files
# Binary
%attr(-,clustercockpit,clustercockpit) %{_bindir}/%{name}
%attr(-,clustercockpit,clustercockpit) %{_sbindir}/%{name}
# Config
%dir %{_sysconfdir}/%{name}
%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/%{name}.json

View File

@@ -39,13 +39,13 @@ def group_to_json(groupfile):
llist = re.split("\s+", line)
calc = llist[-1]
metric = " ".join(llist[:-1])
scope = "hwthread"
scope = "cpu"
if "BOX" in calc:
scope = "socket"
if "PWR" in calc:
scope = "socket"
m = {"name" : metric, "calc": calc, "type" : scope, "publish" : True}
m = {"name" : metric, "calc": calc, "scope" : scope, "publish" : True}
metrics.append(m)
return {"events" : events, "metrics" : metrics}

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