Fix SqliteSink

.github/ci-config.json

@@ -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
 }

.github/ci-receivers.json

@@ -1 +1 @@
-{}
+[]

.github/ci-sinks.json

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

.github/workflows/Release.yml

@@ -1,187 +0,0 @@
-# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
-
-# Workflow name
-name: Release
-
-# Run on tag push
-on:
- push:
-  tags:
-  - '**'
-
-jobs:
-
-  #
-  # Build on AlmaLinux 8.5 using go-toolset
-  #
-  AlmaLinux-RPM-build:
-    runs-on: ubuntu-latest
-    # See: https://hub.docker.com/_/almalinux
-    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:
-      rpm : ${{steps.rpmrename.outputs.RPM}}
-      srpm : ${{steps.rpmrename.outputs.SRPM}}
-    steps:
-
-    # Use dnf to install development packages
-    - name: Install development packages
-      run: dnf --assumeyes group install "Development Tools" "RPM Development Tools"
-
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: |
-        dnf --assumeyes install 'dnf-command(builddep)'
-        dnf --assumeyes install which
-        dnf --assumeyes builddep scripts/cc-metric-collector.spec
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: make RPM
-
-    # AlmaLinux 8.5 is a derivate of RedHat Enterprise Linux 8 (UBI8),
-    # so the created RPM both contain the substring 'el8' in the RPM file names
-    # This step replaces the substring 'el8' to 'alma85'. It uses the move operation
-    # because it is unclear whether the default AlmaLinux 8.5 container contains the 
-    # 'rename' command. This way we also get the new names for output.
-    - name: Rename RPMs (s/el8/alma85/)
-      id: rpmrename
-      run: |
-        OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
-        OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
-        NEW_RPM="${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}"
-        echo "::set-output name=RPM::${NEW_RPM}"
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        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 8.5
-        path: ${{ steps.rpmrename.outputs.SRPM }}
-
-  #
-  # 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:8.5-226.1645809065
-    # The job outputs link to the outputs of the 'rpmbuild' step
-    outputs:
-      rpm : ${{steps.rpmbuild.outputs.RPM}}
-      srpm : ${{steps.rpmbuild.outputs.SRPM}}
-    steps:
-
-    # Use dnf to install development packages
-    - name: Install development packages
-      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros 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@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: dnf --assumeyes --disableplugin=subscription-manager builddep scripts/cc-metric-collector.spec
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: make RPM
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector RPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.RPM }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.SRPM }}
-
-  #
-  # Create release with fresh RPMs
-  #
-  Release:
-    runs-on: ubuntu-latest
-    # We need the RPMs, so add dependency
-    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build]
-
-    steps:
-    # See: https://github.com/actions/download-artifact
-    - name: Download AlmaLinux 8.5 RPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector RPM for AlmaLinux 8.5
-    - name: Download AlmaLinux 8.5 SRPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for AlmaLinux 8.5
-    
-    - name: Download UBI 8 RPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector RPM for UBI 8
-    - name: Download UBI 8 SRPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for UBI 8
-
-    # The download actions do not publish the name of the downloaded file,
-    # so we re-use the job outputs of the parent jobs. The files are all
-    # downloaded to the current folder.
-    # The gh-release action afterwards does not accept file lists but all
-    # files have to be listed at 'files'. The step creates one output per
-    # RPM package (2 per distro)
-    - name: Set RPM variables
-      id: files
-      run: |
-        ALMA_85_RPM=$(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 "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
-        echo "ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
-        echo "UBI_8_RPM::${UBI_8_RPM}"
-        echo "UBI_8_SRPM::${UBI_8_SRPM}"
-        echo "::set-output name=ALMA_85_RPM::${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::${UBI_8_SRPM}"
-
-    # See: https://github.com/softprops/action-gh-release
-    - name: Release
-      uses: softprops/action-gh-release@v1
-      if: startsWith(github.ref, 'refs/tags/')
-      with:
-        name: cc-metric-collector-${{github.ref_name}}
-        files: |
-         ${{ steps.files.outputs.ALMA_85_RPM }}
-         ${{ steps.files.outputs.ALMA_85_SRPM }}
-         ${{ steps.files.outputs.UBI_8_RPM }}
-         ${{ steps.files.outputs.UBI_8_SRPM }}

.github/workflows/rpmbuild.yml

@@ -0,0 +1,61 @@
+name: Run RPM Build
+on: push
+
+jobs:
+  build-centos8:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: TomTheBear/rpmbuild@master
+      id: rpm
+      name: Build RPM package on CentOS8
+      with:
+        spec_file: "./scripts/cc-metric-collector.spec"
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v1.0.0
+      with:
+        name: cc-metric-collector RPM CentOS8
+        path: ${{ steps.rpm.outputs.rpm_dir_path }}
+    - name: Save SRPM as artifact
+      uses: actions/upload-artifact@v1.0.0
+      with:
+        name: cc-metric-collector SRPM CentOS8
+        path: ${{ steps.rpm.outputs.source_rpm_path }}
+  build-centos-latest:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: TomTheBear/rpmbuild@centos_latest
+      id: rpm
+      name: Build RPM package on CentOS 'Latest'
+      with:
+        spec_file: "./scripts/cc-metric-collector.spec"
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v1.0.0
+      with:
+        name: cc-metric-collector RPM CentOS 'Latest'
+        path: ${{ steps.rpm.outputs.rpm_dir_path }}
+    - name: Save SRPM as artifact
+      uses: actions/upload-artifact@v1.0.0
+      with:
+        name: cc-metric-collector SRPM CentOS 'Latest'
+        path: ${{ steps.rpm.outputs.source_rpm_path }}
+  build-alma-8_5:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: TomTheBear/rpmbuild@alma8.5
+      id: rpm
+      name: Build RPM package on AlmaLinux 8.5
+      with:
+        spec_file: "./scripts/cc-metric-collector.spec"
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v1.0.0
+      with:
+        name: cc-metric-collector RPM AlmaLinux 8.5
+        path: ${{ steps.rpm.outputs.rpm_dir_path }}
+    - name: Save SRPM as artifact
+      uses: actions/upload-artifact@v1.0.0
+      with:
+        name: cc-metric-collector SRPM AlmaLinux 8.5
+        path: ${{ steps.rpm.outputs.source_rpm_path }}

.github/workflows/runonce.yml

@@ -1,86 +1,20 @@
-# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
-
-# Workflow name
 name: Run Test
-
-# Run on event push
 on: push
 
 jobs:
-  #
-  # Job build-1-18
-  # Build on latest Ubuntu using golang version 1.18
-  #
-  build-1-18:
+  build:
     runs-on: ubuntu-latest
     steps:
-    # See: https://github.com/marketplace/actions/checkout
-    # Checkout git repository and submodules
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
+    - uses: actions/checkout@v2
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v3
+      uses: actions/setup-go@v2.1.5
       with:
-        go-version: '1.18.2'
+        go-version: '^1.17.6'
 
     - name: Build MetricCollector
       run: make
 
-    - name: Run MetricCollector once
-      run: ./cc-metric-collector --once --config .github/ci-config.json
-
-  #
-  # Job build-1-17
-  # Build on latest Ubuntu using golang version 1.17 
-  #
-  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@v2
-      with:
-        submodules: recursive
-
-    # See: https://github.com/marketplace/actions/setup-go-environment
-    - name: Setup Golang
-      uses: actions/setup-go@v3
-      with:
-        go-version: '1.17.7'
-
-    - name: Build MetricCollector
-      run: make
-
-    - name: Run MetricCollector once
-      run: ./cc-metric-collector --once --config .github/ci-config.json
-
-  #
-  # Job build-1-16
-  # Build on latest Ubuntu using golang version 1.16
-  #
-  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@v2
-      with:
-        submodules: recursive
-
-    # See: https://github.com/marketplace/actions/setup-go-environment
-    - name: Setup Golang
-      uses: actions/setup-go@v3
-      with:
-        go-version: '1.16.7' # The version AlmaLinux 8.5 uses
-
-    - name: Build MetricCollector
-      run: make
-
-    - name: Run MetricCollector once
+    - name: Run MetricCollector
       run: ./cc-metric-collector --once --config .github/ci-config.json

.gitmodules

@@ -1,4 +0,0 @@
-[submodule ".github/actions/rpmbuild-centos8-golang"]
-	path = .github/actions/rpmbuild-centos8-golang
-	url = https://github.com/naveenrajm7/rpmbuild.git
-	branch = centos8

Makefile

@@ -1,135 +1,43 @@
 APP = cc-metric-collector
-GOSRC_APP        := cc-metric-collector.go
+GOSRC_APP        := metric-collector.go
 GOSRC_COLLECTORS := $(wildcard collectors/*.go)
 GOSRC_SINKS      := $(wildcard sinks/*.go)
 GOSRC_RECEIVERS  := $(wildcard receivers/*.go)
 GOSRC_INTERNAL   := $(wildcard internal/*/*.go)
 GOSRC            := $(GOSRC_APP) $(GOSRC_COLLECTORS) $(GOSRC_SINKS) $(GOSRC_RECEIVERS) $(GOSRC_INTERNAL)
-COMPONENT_DIRS   := collectors \
-			sinks \
-			receivers \
-			internal/metricRouter \
-			internal/ccMetric \
-			internal/metricAggregator \
-			internal/ccLogger \
-			internal/ccTopology \
-			internal/multiChanTicker
-
-BINDIR = bin
-GOBIN = $(shell which go)
 
 
 .PHONY: all
 all: $(APP)
 
 $(APP): $(GOSRC)
-	if [ "$(shell $(GOBIN) version | cut -d' ' -f 3 | cut -d '.' -f1-2)" = "go1.16" ]; then \
-		echo "1.16"; \
-		cp go.mod.1.16 go.mod; \
-	else \
-		echo "1.17+"; \
-		cp go.mod.1.17+ go.mod; \
-	fi
 	make -C collectors
-	$(GOBIN) get
-	$(GOBIN) build -o $(APP) $(GOSRC_APP)
-
-install: $(APP)
-	@WORKSPACE=$(PREFIX)
-	@if [ -z "$${WORKSPACE}" ]; then exit 1; fi
-	@mkdir --parents --verbose $${WORKSPACE}/usr/$(BINDIR)
-	@install -Dpm 755 $(APP) $${WORKSPACE}/usr/$(BINDIR)/$(APP)
-	@mkdir --parents --verbose $${WORKSPACE}/etc/cc-metric-collector $${WORKSPACE}/etc/default $${WORKSPACE}/etc/systemd/system $${WORKSPACE}/etc/init.d
-	@install -Dpm 600 config.json $${WORKSPACE}/etc/cc-metric-collector/cc-metric-collector.json
-	@sed -i -e s+"\"./"+"\"/etc/cc-metric-collector/"+g $${WORKSPACE}/etc/cc-metric-collector/cc-metric-collector.json
-	@install -Dpm 600 sinks.json $${WORKSPACE}/etc/cc-metric-collector/sinks.json
-	@install -Dpm 600 collectors.json $${WORKSPACE}/etc/cc-metric-collector/collectors.json
-	@install -Dpm 600 router.json $${WORKSPACE}/etc/cc-metric-collector/router.json
-	@install -Dpm 600 receivers.json $${WORKSPACE}/etc/cc-metric-collector/receivers.json
-	@install -Dpm 600 scripts/cc-metric-collector.config $${WORKSPACE}/etc/default/cc-metric-collector
-	@install -Dpm 644 scripts/cc-metric-collector.service $${WORKSPACE}/etc/systemd/system/cc-metric-collector.service
-	@install -Dpm 644 scripts/cc-metric-collector.init $${WORKSPACE}/etc/init.d/cc-metric-collector
-
+	go get
+	go build -o $(APP) $(GOSRC_APP)
 
 .PHONY: clean
-.ONESHELL:
 clean:
-	@for COMP in $(COMPONENT_DIRS); do if [ -e $$COMP/Makefile ]; then make -C $$COMP clean;  fi; done
+	make -C collectors clean
 	rm -f $(APP)
 
 .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
-	$$($(GOBIN) env GOPATH)/bin/staticcheck ./...
-
-.ONESHELL:
-.PHONY: RPM
-RPM: scripts/cc-metric-collector.spec
-	@WORKSPACE="$${PWD}"
-	@SPECFILE="$${WORKSPACE}/scripts/cc-metric-collector.spec"
-	# Setup RPM build tree
-	@eval $$(rpm --eval "ARCH='%{_arch}' RPMDIR='%{_rpmdir}' SOURCEDIR='%{_sourcedir}' SPECDIR='%{_specdir}' SRPMDIR='%{_srcrpmdir}' BUILDDIR='%{_builddir}'")
-	@mkdir --parents --verbose "$${RPMDIR}" "$${SOURCEDIR}" "$${SPECDIR}" "$${SRPMDIR}" "$${BUILDDIR}"
-	# Create source tarball
-	@COMMITISH="HEAD"
-	@VERS=$$(git describe --tags $${COMMITISH})
-	@VERS=$${VERS#v}
-	@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}-$${VERSION}"
-	@FORMAT="tar.gz"
-	@SRCFILE="$${SOURCEDIR}/$${PREFIX}.$${FORMAT}"
-	@git archive --verbose --format "$${FORMAT}" --prefix="$${PREFIX}/" --output="$${SRCFILE}" $${COMMITISH}
-	# Build RPM and SRPM
-	@rpmbuild -ba --define="VERS $${VERS}" --rmsource --clean "$${SPECFILE}"
-	# Report RPMs and SRPMs when in GitHub Workflow
-	@if [[ "$${GITHUB_ACTIONS}" == true ]]; then
-	@     RPMFILE="$${RPMDIR}/$${ARCH}/$${NVRA}.rpm"
-	@     SRPMFILE="$${SRPMDIR}/$${NVR}.src.rpm"
-	@     echo "RPM: $${RPMFILE}"
-	@     echo "SRPM: $${SRPMFILE}"
-	@     echo "::set-output name=SRPM::$${SRPMFILE}"
-	@     echo "::set-output name=RPM::$${RPMFILE}"
-	@fi
-
-.PHONY: DEB
-DEB: scripts/cc-metric-collector.deb.control $(APP)
-	@BASEDIR=$${PWD}
-	@WORKSPACE=$${PWD}/.dpkgbuild
-	@DEBIANDIR=$${WORKSPACE}/debian
-	@DEBIANBINDIR=$${WORKSPACE}/DEBIAN
-	@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})
-	@VERS=$${VERS#v}
-	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
-	@ARCH=$$(uname -m)
-	@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 $$CONTROLFILE > $${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"
-	@rm -r "$${WORKSPACE}"
+	go install honnef.co/go/tools/cmd/staticcheck@latest
+	$$(go env GOPATH)/bin/staticcheck ./...

README.md

@@ -39,15 +39,14 @@ See the component READMEs for their configuration:
 ```
 $ git clone git@github.com:ClusterCockpit/cc-metric-collector.git
 $ make (downloads LIKWID, builds it as static library with 'direct' accessmode and copies all required files for the collector)
-$ go get (requires at least golang 1.16)
-$ make
+$ go get (requires at least golang 1.13)
+$ go build metric-collector
 ```
 
-
 # Running
 
 ```
-$ ./cc-metric-collector --help
+$ ./metric-collector --help
 Usage of metric-collector:
   -config string
     	Path to configuration file (default "./config.json")
@@ -55,42 +54,10 @@ Usage of metric-collector:
     	Path for logfile (default "stderr")
   -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:
-
-```mermaid
-flowchart TD
-  subgraph a ["Cluster A"]
-  nodeA[NodeA with CC collector]
-  nodeB[NodeB with CC collector]
-  nodeC[NodeC with CC collector]
-  end
-  a --> db[(Database)]
-  db <--> ccweb("Webfrontend")
+  -pidfile string
+    	Path for PID file (default "/var/run/cc-metric-collector.pid")
 ```
 
-``` mermaid
-flowchart TD
-  subgraph a [ClusterA]
-  direction LR
-  nodeA[NodeA with CC collector]
-  nodeB[NodeB with CC collector]
-  nodeC[NodeC with CC collector]
-  end
-  subgraph b [ClusterB]
-  direction LR
-  nodeD[NodeD with CC collector]
-  nodeE[NodeE with CC collector]
-  nodeF[NodeF with CC collector]
-  end
-  a --> ccrecv{"CC collector as receiver"}
-  b --> ccrecv
-  ccrecv --> db[("Database1")]
-  ccrecv -.-> db2[("Database2")]
-  db <-.-> ccweb("Webfrontend")
-```
 
 # 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.

collectors.json

@@ -1,28 +1,5 @@
 {
-    "cpufreq": {},
-    "cpufreq_cpuinfo": {},
-    "gpfs": {
-        "exclude_filesystem": [
-            "test_fs"
-        ]
-    },
-    "ibstat": {},
-    "loadavg": {
-        "exclude_metrics": [
-            "proc_total"
-        ]
-    },
-    "netstat": {
-        "include_devices": [
-            "enp5s0"
-        ],
-        "send_derived_values": true
-    },
-    "numastats": {},
-    "nvidia": {},
     "tempstat": {
-        "report_max_temperature": true,
-        "report_critical_temperature": true,
       "tag_override": {
         "hwmon0" : {
             "type" : "socket",
@@ -34,4 +11,5 @@
         }
       }
     }
+    
 }

collectors/Makefile

@@ -1,31 +1,82 @@
-# LIKWID version
+# Use central installation
+CENTRAL_INSTALL = false
+# How to access hardware performance counters through LIKWID.
+# Recommended is 'direct' mode
+ACCESSMODE = direct
+
+#######################################################################
+# if CENTRAL_INSTALL == true
+#######################################################################
+# Path to central installation (if CENTRAL_INSTALL=true)
+LIKWID_BASE=/apps/likwid/5.2.1
+# LIKWID version (should be same major version as central installation, 5.2.x)
 LIKWID_VERSION = 5.2.1
-LIKWID_INSTALLED_FOLDER=$(shell dirname $(shell which likwid-topology 2>/dev/null) 2>/dev/null)
 
-LIKWID_FOLDER="$(shell pwd)/likwid"
-
-all: $(LIKWID_FOLDER)/likwid.h
-
-.ONESHELL:
-.PHONY: $(LIKWID_FOLDER)/likwid.h
-$(LIKWID_FOLDER)/likwid.h:
-	if [ "$(LIKWID_INSTALLED_FOLDER)" != "" ]; then \
-		BASE="$(LIKWID_INSTALLED_FOLDER)/../include"; \
-		mkdir -p $(LIKWID_FOLDER); \
-		cp $$BASE/*.h $(LIKWID_FOLDER); \
-	else \
-		BUILD_FOLDER="$${PWD}/likwidbuild"; \
-		if [ -d $(LIKWID_FOLDER) ]; then rm -r $(LIKWID_FOLDER); fi; \
-		mkdir --parents --verbose  $(LIKWID_FOLDER) $${BUILD_FOLDER}; \
-		wget -P "$${BUILD_FOLDER}" http://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 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h $(LIKWID_FOLDER)/; \
-		install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h $(LIKWID_FOLDER)/; \
-		rm -r $${BUILD_FOLDER}; \
-	fi
+#######################################################################
+# if CENTRAL_INSTALL == false and ACCESSMODE == accessdaemon
+#######################################################################
+# Where to install the accessdaemon
+DAEMON_INSTALLDIR = /usr/local
+# Which user to use for the accessdaemon
+DAEMON_USER = root
+# Which group to use for the accessdaemon
+DAEMON_GROUP = root
 
 
-clean:
+
+#################################################
+# No need to change anything below this line
+#################################################
+INSTALL_FOLDER = ./likwid
+BUILD_FOLDER = ./likwid/build
+
+ifneq ($(strip $(CENTRAL_INSTALL)),true)
+LIKWID_BASE := $(shell pwd)/$(INSTALL_FOLDER)
+DAEMON_BASE := $(LIKWID_BASE)
+GROUPS_BASE := $(LIKWID_BASE)/groups
+all: $(INSTALL_FOLDER)/liblikwid.a cleanup
+else
+DAEMON_BASE= $(LIKWID_BASE)/sbin
+all: $(INSTALL_FOLDER)/liblikwid.a cleanup
+endif
+
+
+
+$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz: $(BUILD_FOLDER)
+	wget -P $(BUILD_FOLDER) ftp://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz
+
+$(BUILD_FOLDER):
+	mkdir -p $(BUILD_FOLDER)
+
+$(INSTALL_FOLDER):
+	mkdir -p $(INSTALL_FOLDER)
+
+$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION): $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz
+	tar -C $(BUILD_FOLDER) -xf $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz
+
+$(INSTALL_FOLDER)/liblikwid.a: $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION) $(INSTALL_FOLDER)
+	sed -i -e s+"PREFIX ?= .*"+"PREFIX = $(LIKWID_BASE)"+g \
+		-e s+"SHARED_LIBRARY = .*"+"SHARED_LIBRARY = false"+g \
+		-e s+"ACCESSMODE = .*"+"ACCESSMODE = $(ACCESSMODE)"+g \
+		-e s+"INSTALLED_ACCESSDAEMON = .*"+"INSTALLED_ACCESSDAEMON = $(DAEMON_INSTALLDIR)/likwid-accessD"+g \
+		$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/config.mk
+	cd $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION) && make
+	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/liblikwid.a $(INSTALL_FOLDER)
+	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/ext/hwloc/liblikwid-hwloc.a $(INSTALL_FOLDER)
+	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h $(INSTALL_FOLDER)
+	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h $(INSTALL_FOLDER)
+
+$(DAEMON_INSTALLDIR)/likwid-accessD: $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/likwid-accessD
+	sudo -u $(DAEMON_USER) -g $(DAEMON_GROUP) install -m 4775 $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/likwid-accessD $(DAEMON_INSTALLDIR)/likwid-accessD
+
+prepare_collector: likwidMetric.go
+	cp likwidMetric.go likwidMetric.go.orig
+	sed -i -e s+"const GROUPPATH =.*"+"const GROUPPATH = \`$(GROUPS_BASE)\`"+g likwidMetric.go
+
+cleanup:
+	rm -rf $(BUILD_FOLDER)
+
+clean: cleanup
 	rm -rf likwid
 
 .PHONY: clean

collectors/README.md

@@ -18,31 +18,21 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 
 * [`cpustat`](./cpustatMetric.md)
 * [`memstat`](./memstatMetric.md)
-* [`iostat`](./iostatMetric.md)
 * [`diskstat`](./diskstatMetric.md)
 * [`loadavg`](./loadavgMetric.md)
 * [`netstat`](./netstatMetric.md)
 * [`ibstat`](./infinibandMetric.md)
-* [`ibstat_perfquery`](./infinibandPerfQueryMetric.md)
 * [`tempstat`](./tempMetric.md)
-* [`lustrestat`](./lustreMetric.md)
+* [`lustre`](./lustreMetric.md)
 * [`likwid`](./likwidMetric.md)
 * [`nvidia`](./nvidiaMetric.md)
 * [`customcmd`](./customCmdMetric.md)
 * [`ipmistat`](./ipmiMetric.md)
 * [`topprocs`](./topprocsMetric.md)
-* [`nfs3stat`](./nfs3Metric.md)
-* [`nfs4stat`](./nfs4Metric.md)
-* [`cpufreq`](./cpufreqMetric.md)
-* [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
-* [`numastat`](./numastatMetric.md)
-* [`gpfs`](./gpfsMetric.md)
-* [`beegfs_meta`](./beegfsmetaMetric.md)
-* [`beegfs_storage`](./beegfsstorageMetric.md)
-* [`rocm_smi`](./rocmsmiMetric.md)
 
 ## Todos
 
+* [ ] Exclude devices for `diskstat` collector
 * [ ] Aggreate metrics to higher topology entity (sum hwthread metrics to socket metric, ...). Needs to be configurable
 
 # Contributing own collectors
@@ -81,11 +71,6 @@ type SampleCollector struct {
 }
 
 func (m *SampleCollector) Init(config json.RawMessage) error {
-    // Check if already initialized
-    if m.init {
-        return nil
-    }
-
     m.name = "SampleCollector"
     m.setup()
     if len(config) > 0 {
@@ -106,15 +91,10 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric)
     }
     // tags for the metric, if type != node use proper type and type-id
     tags := map[string]string{"type" : "node"}
-
-    x, err := GetMetric()
-    if err != nil {
-        cclog.ComponentError(m.name, fmt.Sprintf("Read(): %v", err))
-    }
-
     // Each metric has exactly one field: value !
-    value := map[string]interface{}{"value": int64(x)}
-    if y, err := lp.New("sample_metric", tags, m.meta, value, time.Now()); err == nil {
+    value := map[string]interface{}{"value": int(x)}
+    y, err := lp.New("sample_metric", tags, m.meta, value, time.Now())
+    if err == nil {
         output <- y
     }
 }

collectors/beegfsmetaMetric.go

@@ -1,230 +0,0 @@
-package collectors
-
-import (
-	"bufio"
-	"bytes"
-	"encoding/json"
-	"fmt"
-	"io/ioutil"
-	"os"
-	"os/exec"
-	"os/user"
-	"regexp"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
-
-// Struct for the collector-specific JSON config
-type BeegfsMetaCollectorConfig struct {
-	Beegfs            string   `json:"beegfs_path"`
-	ExcludeMetrics    []string `json:"exclude_metrics,omitempty"`
-	ExcludeFilesystem []string `json:"exclude_filesystem"`
-}
-
-type BeegfsMetaCollector struct {
-	metricCollector
-	tags    map[string]string
-	matches map[string]string
-	config  BeegfsMetaCollectorConfig
-	skipFS  map[string]struct{}
-}
-
-func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-	// Metrics
-	var nodeMdstat_array = [39]string{
-		"sum", "ack", "close", "entInf",
-		"fndOwn", "mkdir", "create", "rddir",
-		"refrEn", "mdsInf", "rmdir", "rmLnk",
-		"mvDirIns", "mvFiIns", "open", "ren",
-		"sChDrct", "sAttr", "sDirPat", "stat",
-		"statfs", "trunc", "symlnk", "unlnk",
-		"lookLI", "statLI", "revalLI", "openLI",
-		"createLI", "hardlnk", "flckAp", "flckEn",
-		"flckRg", "dirparent", "listXA", "getXA",
-		"rmXA", "setXA", "mirror"}
-
-	m.name = "BeegfsMetaCollector"
-	m.setup()
-	m.parallel = true
-	// Set default beegfs-ctl binary
-
-	m.config.Beegfs = DEFAULT_BEEGFS_CMD
-
-	// Read JSON configuration
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &m.config)
-		if err != nil {
-			return err
-		}
-	}
-
-	//create map with possible variables
-	m.matches = make(map[string]string)
-	for _, value := range nodeMdstat_array {
-		_, skip := stringArrayContains(m.config.ExcludeMetrics, value)
-		if skip {
-			m.matches["other"] = "0"
-		} else {
-			m.matches["beegfs_cmeta_"+value] = "0"
-		}
-	}
-
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "BeegfsMeta",
-	}
-	m.tags = map[string]string{
-		"type":       "node",
-		"filesystem": "",
-	}
-	m.skipFS = make(map[string]struct{})
-	for _, fs := range m.config.ExcludeFilesystem {
-		m.skipFS[fs] = struct{}{}
-	}
-
-	// Beegfs file system statistics can only be queried by user root
-	user, err := user.Current()
-	if err != nil {
-		return fmt.Errorf("BeegfsMetaCollector.Init(): Failed to get current user: %v", err)
-	}
-	if user.Uid != "0" {
-		return fmt.Errorf("BeegfsMetaCollector.Init(): BeeGFS file system statistics can only be queried by user root")
-	}
-
-	// Check if beegfs-ctl is in executable search path
-	_, err = exec.LookPath(m.config.Beegfs)
-	if err != nil {
-		return fmt.Errorf("BeegfsMetaCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
-	}
-	m.init = true
-	return nil
-}
-
-func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
-	mounts := strings.Split(string(buffer), "\n")
-	var mountpoints []string
-	for _, line := range mounts {
-		if len(line) == 0 {
-			continue
-		}
-		f := strings.Fields(line)
-		if strings.Contains(f[0], "beegfs_ondemand") {
-			// Skip excluded filesystems
-			if _, skip := m.skipFS[f[1]]; skip {
-				continue
-			}
-			mountpoints = append(mountpoints, f[1])
-		}
-	}
-
-	if len(mountpoints) == 0 {
-		return
-	}
-
-	for _, mountpoint := range mountpoints {
-		m.tags["filesystem"] = mountpoint
-
-		// bwwgfs-ctl:
-		// --clientstats: Show client IO statistics.
-		// --nodetype=meta: The node type to query (meta, storage).
-		// --interval:
-		// --mount=/mnt/beeond/: Which mount point
-		//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
-		mountoption := "--mount=" + mountpoint
-		cmd := exec.Command(m.config.Beegfs, "--clientstats",
-			"--nodetype=meta", mountoption, "--allstats")
-		cmd.Stdin = strings.NewReader("\n")
-		cmdStdout := new(bytes.Buffer)
-		cmdStderr := new(bytes.Buffer)
-		cmd.Stdout = cmdStdout
-		cmd.Stderr = cmdStderr
-		err := cmd.Run()
-		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, _ := ioutil.ReadAll(cmdStderr)
-			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
-			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stdout: \"%s\"\n", string(data))
-			return
-		}
-		// Read I/O statistics
-		scanner := bufio.NewScanner(cmdStdout)
-
-		sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
-		//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
-		statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
-		singleSpacePattern := regexp.MustCompile(`\s+`)
-		removePattern := regexp.MustCompile(`[\[|\]]`)
-
-		for scanner.Scan() {
-			readLine := scanner.Text()
-			//fmt.Println(readLine)
-			// Jump few lines, we only want the I/O stats from nodes
-			if !sumLine.MatchString(readLine) {
-				continue
-			}
-
-			match := statsLine.FindStringSubmatch(readLine)
-			// nodeName = "Sum:" or would be nodes
-			// nodeName := match[1]
-			//Remove multiple whitespaces
-			dummy := removePattern.ReplaceAllString(match[2], " ")
-			metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
-			split := strings.Split(metaStats, " ")
-
-			// fill map with values
-			// split[i+1] = mdname
-			// split[i] = amount of md operations
-			for i := 0; i <= len(split)-1; i += 2 {
-				if _, ok := m.matches[split[i+1]]; ok {
-					m.matches["beegfs_cmeta_"+split[i+1]] = split[i]
-				} else {
-					f1, err := strconv.ParseFloat(m.matches["other"], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					f2, err := strconv.ParseFloat(split[i], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					//mdStat["other"] = fmt.Sprintf("%f", f1+f2)
-					m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)
-				}
-			}
-
-			for key, data := range m.matches {
-				value, _ := strconv.ParseFloat(data, 32)
-				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-	}
-}
-
-func (m *BeegfsMetaCollector) Close() {
-	m.init = false
-}

collectors/beegfsmetaMetric.md

@@ -1,75 +0,0 @@
-## `BeeGFS on Demand` collector
-This Collector is to collect BeeGFS on Demand (BeeOND) metadata clientstats.
-
-```json
-  "beegfs_meta": {
-	"beegfs_path": "/usr/bin/beegfs-ctl",
-    "exclude_filesystem": [
-      "/mnt/ignore_me"
-    ],
-    "exclude_metrics": [     
-          "ack",
-          "entInf",
-          "fndOwn"
-    ]
-  }
-```
-
-The `BeeGFS On Demand (BeeOND)` collector uses the `beegfs-ctl` command to read performance metrics for
-BeeGFS filesystems.
-
-The reported filesystems can be filtered with the `exclude_filesystem` option
-in the configuration.
-
-The path to the `beegfs-ctl` command can be configured with the `beegfs_path` option
-in the configuration.
-
-When using the `exclude_metrics` option, the excluded metrics are summed as `other`.
-
-Important: The metrics listed below, are similar to the naming of BeeGFS. The Collector prefixes these with `beegfs_cstorage`(beegfs client storage).
-
-For example beegfs metric `open`-> `beegfs_cstorage_open`
-
-Available Metrics:
-
-* sum
-* ack
-* close
-* entInf
-* fndOwn
-* mkdir
-* create
-* rddir
-* refrEnt
-* mdsInf
-* rmdir
-* rmLnk
-* mvDirIns
-* mvFiIns
-* open
-* ren
-* sChDrct
-* sAttr
-* sDirPat
-* stat
-* statfs
-* trunc
-* symlnk
-* unlnk
-* lookLI
-* statLI
-* revalLI
-* openLI
-* createLI
-* hardlnk
-* flckAp
-* flckEn
-* flckRg
-* dirparent
-* listXA
-* getXA
-* rmXA
-* setXA
-* mirror
-
-The collector adds a `filesystem` tag to all metrics

collectors/beegfsstorageMetric.go

@@ -1,222 +0,0 @@
-package collectors
-
-import (
-	"bufio"
-	"bytes"
-	"encoding/json"
-	"fmt"
-	"io/ioutil"
-	"os"
-	"os/exec"
-	"os/user"
-	"regexp"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-// Struct for the collector-specific JSON config
-type BeegfsStorageCollectorConfig struct {
-	Beegfs            string   `json:"beegfs_path"`
-	ExcludeMetrics    []string `json:"exclude_metrics,omitempty"`
-	ExcludeFilesystem []string `json:"exclude_filesystem"`
-}
-
-type BeegfsStorageCollector struct {
-	metricCollector
-	tags    map[string]string
-	matches map[string]string
-	config  BeegfsStorageCollectorConfig
-	skipFS  map[string]struct{}
-}
-
-func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-	// Metrics
-	var storageStat_array = [18]string{
-		"sum", "ack", "sChDrct", "getFSize",
-		"sAttr", "statfs", "trunc", "close",
-		"fsync", "ops-rd", "MiB-rd/s", "ops-wr",
-		"MiB-wr/s", "gendbg", "hrtbeat", "remNode",
-		"storInf", "unlnk"}
-
-	m.name = "BeegfsStorageCollector"
-	m.setup()
-	m.parallel = true
-	// Set default beegfs-ctl binary
-
-	m.config.Beegfs = DEFAULT_BEEGFS_CMD
-
-	// Read JSON configuration
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &m.config)
-		if err != nil {
-			return err
-		}
-	}
-	println(m.config.Beegfs)
-	//create map with possible variables
-	m.matches = make(map[string]string)
-	for _, value := range storageStat_array {
-		_, skip := stringArrayContains(m.config.ExcludeMetrics, value)
-		if skip {
-			m.matches["other"] = "0"
-		} else {
-			m.matches["beegfs_cstorage_"+value] = "0"
-		}
-	}
-
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "BeegfsStorage",
-	}
-	m.tags = map[string]string{
-		"type":       "node",
-		"filesystem": "",
-	}
-	m.skipFS = make(map[string]struct{})
-	for _, fs := range m.config.ExcludeFilesystem {
-		m.skipFS[fs] = struct{}{}
-	}
-
-	// Beegfs file system statistics can only be queried by user root
-	user, err := user.Current()
-	if err != nil {
-		return fmt.Errorf("BeegfsStorageCollector.Init(): Failed to get current user: %v", err)
-	}
-	if user.Uid != "0" {
-		return fmt.Errorf("BeegfsStorageCollector.Init(): BeeGFS file system statistics can only be queried by user root")
-	}
-
-	// Check if beegfs-ctl is in executable search path
-	_, err = exec.LookPath(m.config.Beegfs)
-	if err != nil {
-		return fmt.Errorf("BeegfsStorageCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
-	}
-	m.init = true
-	return nil
-}
-
-func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
-	mounts := strings.Split(string(buffer), "\n")
-	var mountpoints []string
-	for _, line := range mounts {
-		if len(line) == 0 {
-			continue
-		}
-		f := strings.Fields(line)
-		if strings.Contains(f[0], "beegfs_ondemand") {
-			// Skip excluded filesystems
-			if _, skip := m.skipFS[f[1]]; skip {
-				continue
-			}
-			mountpoints = append(mountpoints, f[1])
-		}
-	}
-	if len(mountpoints) == 0 {
-		return
-	}
-	// collects stats for each BeeGFS on Demand FS
-	for _, mountpoint := range mountpoints {
-		m.tags["filesystem"] = mountpoint
-
-		// bwwgfs-ctl:
-		// --clientstats: Show client IO statistics.
-		// --nodetype=meta: The node type to query (meta, storage).
-		// --interval:
-		// --mount=/mnt/beeond/: Which mount point
-		//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
-		mountoption := "--mount=" + mountpoint
-		cmd := exec.Command(m.config.Beegfs, "--clientstats",
-			"--nodetype=storage", mountoption, "--allstats")
-		cmd.Stdin = strings.NewReader("\n")
-		cmdStdout := new(bytes.Buffer)
-		cmdStderr := new(bytes.Buffer)
-		cmd.Stdout = cmdStdout
-		cmd.Stderr = cmdStderr
-		err := cmd.Run()
-		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, _ := ioutil.ReadAll(cmdStderr)
-			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
-			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stdout: \"%s\"\n", string(data))
-			return
-		}
-		// Read I/O statistics
-		scanner := bufio.NewScanner(cmdStdout)
-
-		sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
-		//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
-		statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
-		singleSpacePattern := regexp.MustCompile(`\s+`)
-		removePattern := regexp.MustCompile(`[\[|\]]`)
-
-		for scanner.Scan() {
-			readLine := scanner.Text()
-			//fmt.Println(readLine)
-			// Jump few lines, we only want the I/O stats from nodes
-			if !sumLine.MatchString(readLine) {
-				continue
-			}
-
-			match := statsLine.FindStringSubmatch(readLine)
-			// nodeName = "Sum:" or would be nodes
-			// nodeName := match[1]
-			//Remove multiple whitespaces
-			dummy := removePattern.ReplaceAllString(match[2], " ")
-			metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
-			split := strings.Split(metaStats, " ")
-
-			// fill map with values
-			// split[i+1] = mdname
-			// split[i] = amount of operations
-			for i := 0; i <= len(split)-1; i += 2 {
-				if _, ok := m.matches[split[i+1]]; ok {
-					m.matches["beegfs_cstorage_"+split[i+1]] = split[i]
-					//m.matches[split[i+1]] = split[i]
-				} else {
-					f1, err := strconv.ParseFloat(m.matches["other"], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					f2, err := strconv.ParseFloat(split[i], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)
-				}
-			}
-
-			for key, data := range m.matches {
-				value, _ := strconv.ParseFloat(data, 32)
-				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-	}
-}
-
-func (m *BeegfsStorageCollector) Close() {
-	m.init = false
-}

collectors/beegfsstorageMetric.md

@@ -1,55 +0,0 @@
-## `BeeGFS on Demand` collector
-This Collector is to collect BeeGFS on Demand (BeeOND) storage stats.
-
-```json
-  "beegfs_storage": {
-	"beegfs_path": "/usr/bin/beegfs-ctl",
-    "exclude_filesystem": [
-      "/mnt/ignore_me"
-    ],
-    "exclude_metrics": [     
-          "ack",
-		  "storInf",
-		  "unlnk"
-    ]
-  }
-```
-
-The `BeeGFS On Demand (BeeOND)` collector uses the `beegfs-ctl` command to read performance metrics for BeeGFS filesystems.
-
-The reported filesystems can be filtered with the `exclude_filesystem` option
-in the configuration.
-
-The path to the `beegfs-ctl` command can be configured with the `beegfs_path` option
-in the configuration.
-
-When using the `exclude_metrics` option, the excluded metrics are summed as `other`.
-
-Important: The metrics listed below, are similar to the naming of BeeGFS. The Collector prefixes these with `beegfs_cstorage_`(beegfs client meta).
-For example beegfs metric `open`-> `beegfs_cstorage_`
-
-Note: BeeGFS FS offers many Metadata Information. Probably it makes sense to exlcude most of them. Nevertheless, these excluded metrics will be summed as `beegfs_cstorage_other`. 
-
-Available Metrics:
-
-* "sum"
-* "ack"
-* "sChDrct" 
-* "getFSize"
-* "sAttr"
-* "statfs"
-* "trunc"
-* "close"
-* "fsync"
-* "ops-rd"
-* "MiB-rd/s" 
-* "ops-wr"
-* "MiB-wr/s" 
-* "endbg" 
-* "hrtbeat"
-* "remNode"
-* "storInf"
-* "unlnk"
-
-
-The collector adds a `filesystem` tag to all metrics

collectors/collectorManager.go

@@ -19,38 +19,30 @@ var AvailableCollectors = map[string]MetricCollector{
 	"memstat":          new(MemstatCollector),
 	"netstat":          new(NetstatCollector),
 	"ibstat":           new(InfinibandCollector),
+	"ibstat_perfquery": new(InfinibandPerfQueryCollector),
 	"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),
-	"rocm_smi":        new(RocmSmiCollector),
+	"nfsstat":          new(NfsCollector),
 }
 
 // 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
+	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
-	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
 }
 
 // Metric collector manager access functions
@@ -70,7 +62,6 @@ 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
@@ -105,11 +96,7 @@ 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)
-		}
 	}
 	return nil
 }
@@ -125,10 +112,6 @@ 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()
 			}
@@ -143,26 +126,7 @@ 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:

collectors/cpufreqCpuinfoMetric.go

@@ -5,13 +5,13 @@ import (
 	"encoding/json"
 
 	"fmt"
+	"log"
 	"os"
 	"strconv"
 	"strings"
 	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+
 )
 
 //
@@ -23,56 +23,45 @@ import (
 type CPUFreqCpuInfoCollectorTopology struct {
 	processor               string // logical processor number (continuous, starting at 0)
 	coreID                  string // socket local core ID
-	coreID_int              int64
+	coreID_int              int
 	physicalPackageID       string // socket / package ID
-	physicalPackageID_int   int64
+	physicalPackageID_int   int
 	numPhysicalPackages     string // number of  sockets / packages
-	numPhysicalPackages_int int64
+	numPhysicalPackages_int int
 	isHT                    bool
 	numNonHT                string // number of non hyperthreading processors
-	numNonHT_int            int64
+	numNonHT_int            int
 	tagSet                  map[string]string
 }
 
 type CPUFreqCpuInfoCollector struct {
 	metricCollector
-	topology []*CPUFreqCpuInfoCollectorTopology
+	topology []CPUFreqCpuInfoCollectorTopology
 }
 
 func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
-	m.setup()
-
 	m.name = "CPUFreqCpuInfoCollector"
-	m.parallel = true
 	m.meta = map[string]string{
 		"source": m.name,
-		"group":  "CPU",
-		"unit":   "MHz",
+		"group":  "cpufreq",
 	}
 
 	const cpuInfoFile = "/proc/cpuinfo"
 	file, err := os.Open(cpuInfoFile)
 	if err != nil {
-		return fmt.Errorf("failed to open file '%s': %v", cpuInfoFile, err)
+		return fmt.Errorf("Failed to open '%s': %v", cpuInfoFile, err)
 	}
 	defer file.Close()
 
 	// Collect topology information from file cpuinfo
 	foundFreq := false
 	processor := ""
-	var numNonHT_int int64 = 0
+	numNonHT_int := 0
 	coreID := ""
 	physicalPackageID := ""
-	var maxPhysicalPackageID int64 = 0
-	m.topology = make([]*CPUFreqCpuInfoCollectorTopology, 0)
+	maxPhysicalPackageID := 0
+	m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
 	coreSeenBefore := make(map[string]bool)
-
-	// Read cpuinfo file, line by line
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		lineSplit := strings.Split(scanner.Text(), ":")
@@ -98,41 +87,39 @@ 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)
+			coreID_int, err := strconv.Atoi(coreID)
 			if err != nil {
-				return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
+				return fmt.Errorf("Unable to convert coreID to int: %v", err)
 			}
-
-			// Physical package ID
-			topology.physicalPackageID = physicalPackageID
-			topology.physicalPackageID_int, err = strconv.ParseInt(physicalPackageID, 10, 64)
+			physicalPackageID_int, err := strconv.Atoi(physicalPackageID)
 			if err != nil {
-				return fmt.Errorf("unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
+				return fmt.Errorf("Unable to convert physicalPackageID to int: %v", err)
 			}
 
 			// increase maximun socket / package ID, when required
-			if topology.physicalPackageID_int > maxPhysicalPackageID {
-				maxPhysicalPackageID = topology.physicalPackageID_int
+			if physicalPackageID_int > maxPhysicalPackageID {
+				maxPhysicalPackageID = physicalPackageID_int
 			}
 
-			// is hyperthread?
 			globalID := physicalPackageID + ":" + coreID
-			topology.isHT = coreSeenBefore[globalID]
+			isHT := coreSeenBefore[globalID]
 			coreSeenBefore[globalID] = true
-			if !topology.isHT {
+			if !isHT {
 				// increase number on non hyper thread cores
 				numNonHT_int++
 			}
 
 			// store collected topology information
-			m.topology = append(m.topology, topology)
+			m.topology = append(
+				m.topology,
+				CPUFreqCpuInfoCollectorTopology{
+					processor:             processor,
+					coreID:                coreID,
+					coreID_int:            coreID_int,
+					physicalPackageID:     physicalPackageID,
+					physicalPackageID_int: physicalPackageID_int,
+					isHT:                  isHT,
+				})
 
 			// reset topology information
 			foundFreq = false
@@ -145,15 +132,18 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	numPhysicalPackageID_int := maxPhysicalPackageID + 1
 	numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
 	numNonHT := fmt.Sprint(numNonHT_int)
-	for _, t := range m.topology {
+	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":       "hwthread",
+			"type":        "cpu",
 			"type-id":     t.processor,
+			"num_core":    t.numNonHT,
 			"package_id":  t.physicalPackageID,
+			"num_package": t.numPhysicalPackages,
 		}
 	}
 
@@ -161,18 +151,15 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
+
 func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	// Check if already initialized
 	if !m.init {
 		return
 	}
-
 	const cpuInfoFile = "/proc/cpuinfo"
 	file, err := os.Open(cpuInfoFile)
 	if err != nil {
-		cclog.ComponentError(
-			m.name,
-			fmt.Sprintf("Read(): Failed to open file '%s': %v", cpuInfoFile, err))
+		log.Printf("Failed to open '%s': %v", cpuInfoFile, err)
 		return
 	}
 	defer file.Close()
@@ -187,16 +174,15 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
 
 			// frequency
 			if key == "cpu MHz" {
-				t := m.topology[processorCounter]
+				t := &m.topology[processorCounter]
 				if !t.isHT {
 					value, err := strconv.ParseFloat(strings.TrimSpace(lineSplit[1]), 64)
 					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err))
+						log.Printf("Failed to convert cpu MHz to float: %v", err)
 						return
 					}
-					if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
+					y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now)
+					if err == nil {
 						output <- y
 					}
 				}

collectors/cpufreqCpuinfoMetric.md

@@ -1,10 +0,0 @@
-
-## `cpufreq_cpuinfo` collector
-```json
-  "cpufreq_cpuinfo": {}
-```
-
-The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **hwthread** metrics.
-
-Metrics:
-* `cpufreq`

collectors/cpufreqMetric.go

@@ -1,30 +1,48 @@
 package collectors
 
 import (
+	"bufio"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"log"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	"golang.org/x/sys/unix"
 )
 
+//
+// readOneLine reads one line from a file.
+// It returns ok when file was successfully read.
+// In this case text contains the first line of the files contents.
+//
+func readOneLine(filename string) (text string, ok bool) {
+	file, err := os.Open(filename)
+	if err != nil {
+		return
+	}
+	defer file.Close()
+	scanner := bufio.NewScanner(file)
+	ok = scanner.Scan()
+	text = scanner.Text()
+	return
+}
+
 type CPUFreqCollectorTopology struct {
 	processor               string // logical processor number (continuous, starting at 0)
 	coreID                  string // socket local core ID
-	coreID_int              int64
+	coreID_int              int
 	physicalPackageID       string // socket / package ID
-	physicalPackageID_int   int64
+	physicalPackageID_int   int
 	numPhysicalPackages     string // number of  sockets / packages
-	numPhysicalPackages_int int64
+	numPhysicalPackages_int int
 	isHT                    bool
 	numNonHT                string // number of non hyperthreading processors
-	numNonHT_int            int64
+	numNonHT_int            int
 	scalingCurFreqFile      string
 	tagSet                  map[string]string
 }
@@ -46,14 +64,8 @@ type CPUFreqCollector struct {
 }
 
 func (m *CPUFreqCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
 	m.name = "CPUFreqCollector"
 	m.setup()
-	m.parallel = true
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -62,8 +74,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	}
 	m.meta = map[string]string{
 		"source": m.name,
-		"group":  "CPU",
-		"unit":   "MHz",
+		"group":  "CPU Frequency",
 	}
 
 	// Loop for all CPU directories
@@ -71,50 +82,48 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	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)
+		return fmt.Errorf("CPUFreqCollector.Init() 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)
+		return fmt.Errorf("CPUFreqCollector.Init() unable to find any files with pattern %s", globPattern)
 	}
 
 	// 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)
+		processor_int, err := strconv.Atoi(processor)
 		if err != nil {
-			return fmt.Errorf("unable to convert cpuID '%s' to int64: %v", processor, err)
+			return fmt.Errorf("CPUFreqCollector.Init() unable to convert cpuID to int: %v", 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, ok := readOneLine(physicalPackageIDFile)
+		if !ok {
+			return fmt.Errorf("CPUFreqCollector.Init() unable to read physical package ID from %s", physicalPackageIDFile)
 		}
-		physicalPackageID := strings.TrimSpace(string(line))
-		physicalPackageID_int, err := strconv.ParseInt(physicalPackageID, 10, 64)
+		physicalPackageID_int, err := strconv.Atoi(physicalPackageID)
 		if err != nil {
-			return fmt.Errorf("unable to convert packageID '%s' to int64: %v", physicalPackageID, err)
+			return fmt.Errorf("CPUFreqCollector.Init() unable to convert packageID to int: %v", 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, ok := readOneLine(coreIDFile)
+		if !ok {
+			return fmt.Errorf("CPUFreqCollector.Init() unable to read core ID from %s", coreIDFile)
 		}
-		coreID := strings.TrimSpace(string(line))
-		coreID_int, err := strconv.ParseInt(coreID, 10, 64)
+		coreID_int, err := strconv.Atoi(coreID)
 		if err != nil {
-			return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
+			return fmt.Errorf("CPUFreqCollector.Init() unable to convert coreID to int: %v", err)
 		}
 
 		// Check access to current frequency file
 		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)
+			return fmt.Errorf("CPUFreqCollector.Init() unable to access %s: %v", scalingCurFreqFile, err)
 		}
 
 		t := &m.topology[processor_int]
@@ -137,8 +146,8 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	}
 
 	// number of non hyper thread cores and packages / sockets
-	var numNonHT_int int64 = 0
-	var maxPhysicalPackageID int64 = 0
+	numNonHT_int := 0
+	maxPhysicalPackageID := 0
 	for i := range m.topology {
 		t := &m.topology[i]
 
@@ -162,9 +171,11 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 		t.numNonHT = numNonHT
 		t.numNonHT_int = numNonHT_int
 		t.tagSet = map[string]string{
-			"type":       "hwthread",
+			"type":        "cpu",
 			"type-id":     t.processor,
+			"num_core":    t.numNonHT,
 			"package_id":  t.physicalPackageID,
+			"num_package": t.numPhysicalPackages,
 		}
 	}
 
@@ -173,7 +184,6 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 }
 
 func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	// Check if already initialized
 	if !m.init {
 		return
 	}
@@ -188,22 +198,19 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		}
 
 		// Read current frequency
-		line, err := ioutil.ReadFile(t.scalingCurFreqFile)
-		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to read file '%s': %v", t.scalingCurFreqFile, err))
+		line, ok := readOneLine(t.scalingCurFreqFile)
+		if !ok {
+			log.Printf("CPUFreqCollector.Read(): Failed to read one line from file '%s'", t.scalingCurFreqFile)
 			continue
 		}
-		cpuFreq, err := strconv.ParseInt(strings.TrimSpace(string(line)), 10, 64)
+		cpuFreq, err := strconv.Atoi(line)
 		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert CPU frequency '%s' to int64: %v", line, err))
+			log.Printf("CPUFreqCollector.Read(): Failed to convert CPU frequency '%s': %v", line, err)
 			continue
 		}
 
-		if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
+		y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now)
+		if err == nil {
 			output <- y
 		}
 	}

collectors/cpufreqMetric.md

@@ -1,11 +0,0 @@
-## `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.
-
-Metrics:
-* `cpufreq`

collectors/cpustatMetric.go

@@ -1,15 +1,12 @@
 package collectors
 
 import (
-	"bufio"
 	"encoding/json"
 	"fmt"
-	"os"
+	"io/ioutil"
 	"strconv"
 	"strings"
 	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
@@ -22,127 +19,71 @@ type CpustatCollectorConfig struct {
 type CpustatCollector struct {
 	metricCollector
 	config CpustatCollectorConfig
-	matches  map[string]int
-	cputags  map[string]map[string]string
-	nodetags map[string]string
 }
 
 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"}
+	m.meta = map[string]string{"source": m.name, "group": "CPU"}
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	matches := map[string]int{
-		"cpu_user":       1,
-		"cpu_nice":       2,
-		"cpu_system":     3,
-		"cpu_idle":       4,
-		"cpu_iowait":     5,
-		"cpu_irq":        6,
-		"cpu_softirq":    7,
-		"cpu_steal":      8,
-		"cpu_guest":      9,
-		"cpu_guest_nice": 10,
-	}
-
-	m.matches = make(map[string]int)
-	for match, index := range matches {
-		doExclude := false
-		for _, exclude := range m.config.ExcludeMetrics {
-			if match == exclude {
-				doExclude = true
-				break
-			}
-		}
-		if !doExclude {
-			m.matches[match] = index
-		}
-	}
-
-	// Check input file
-	file, err := os.Open(string(CPUSTATFILE))
-	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)
-	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)
-			m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
-			num_cpus++
-		}
-	}
 	m.init = true
 	return nil
 }
 
-func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric) {
-	values := make(map[string]float64)
-	total := 0.0
-	for match, index := range m.matches {
-		if len(match) > 0 {
-			x, err := strconv.ParseInt(linefields[index], 0, 64)
+func (c *CpustatCollector) parseStatLine(line string, cpu int, exclude []string, output chan lp.CCMetric) {
+	ls := strings.Fields(line)
+	matches := []string{"", "cpu_user", "cpu_nice", "cpu_system", "cpu_idle", "cpu_iowait", "cpu_irq", "cpu_softirq", "cpu_steal", "cpu_guest", "cpu_guest_nice"}
+	for _, ex := range exclude {
+		matches, _ = RemoveFromStringList(matches, ex)
+	}
+
+	var tags map[string]string
+	if cpu < 0 {
+		tags = map[string]string{"type": "node"}
+	} else {
+		tags = map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", cpu)}
+	}
+	for i, m := range matches {
+		if len(m) > 0 {
+			x, err := strconv.ParseInt(ls[i], 0, 64)
 			if err == nil {
-				values[match] = float64(x)
-				total += values[match]
-			}
-		}
-	}
-	t := time.Now()
-	for name, value := range values {
-		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": (value * 100.0) / total}, t)
+				y, err := lp.New(m, tags, c.meta, map[string]interface{}{"value": int(x)}, time.Now())
 				if err == nil {
 					output <- y
 				}
 			}
 		}
+	}
+}
 
 func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
-	num_cpus := 0
-	file, err := os.Open(string(CPUSTATFILE))
+	buffer, err := ioutil.ReadFile(string(CPUSTATFILE))
+
 	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.Compare(linefields[0], "cpu") == 0 {
-			m.parseStatLine(linefields, m.nodetags, output)
-		} else if strings.HasPrefix(linefields[0], "cpu") {
-			m.parseStatLine(linefields, m.cputags[linefields[0]], output)
-			num_cpus++
-		}
+		return
 	}
 
-	num_cpus_metric, err := lp.New("num_cpus",
-		m.nodetags,
-		m.meta,
-		map[string]interface{}{"value": int(num_cpus)},
-		time.Now(),
-	)
-	if err == nil {
-		output <- num_cpus_metric
+	ll := strings.Split(string(buffer), "\n")
+	for _, line := range ll {
+		if len(line) == 0 {
+			continue
+		}
+		ls := strings.Fields(line)
+		if strings.Compare(ls[0], "cpu") == 0 {
+			m.parseStatLine(line, -1, m.config.ExcludeMetrics, output)
+		} else if strings.HasPrefix(ls[0], "cpu") {
+			cpustr := strings.TrimLeft(ls[0], "cpu")
+			cpu, _ := strconv.Atoi(cpustr)
+			m.parseStatLine(line, cpu, m.config.ExcludeMetrics, output)
+		}
 	}
 }
 

collectors/customCmdMetric.go

@@ -33,7 +33,6 @@ type CustomCmdCollector struct {
 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)
@@ -62,7 +61,7 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 		}
 	}
 	if len(m.files) == 0 && len(m.commands) == 0 {
-		return errors.New("no metrics to collect")
+		return errors.New("No metrics to collect")
 	}
 	m.handler = influx.NewMetricHandler()
 	m.parser = influx.NewParser(m.handler)
@@ -98,8 +97,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 			if skip {
 				continue
 			}
-
-			y := lp.FromInfluxMetric(c)
+			y, err := lp.New(c.Name(), Tags2Map(c), m.meta, Fields2Map(c), c.Time())
 			if err == nil {
 				output <- y
 			}
@@ -121,7 +119,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 			if skip {
 				continue
 			}
-			y := lp.FromInfluxMetric(f)
+			y, err := lp.New(f.Name(), Tags2Map(f), m.meta, Fields2Map(f), f.Time())
 			if err == nil {
 				output <- y
 			}

collectors/diskstatMetric.go

@@ -1,20 +1,18 @@
 package collectors
 
 import (
-	"bufio"
-	"encoding/json"
-	"os"
-	"strings"
-	"syscall"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	"io/ioutil"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	//	"log"
+	"encoding/json"
+	"errors"
+	"strconv"
+	"strings"
+	"time"
 )
 
-//	"log"
-
-const MOUNTFILE = `/proc/self/mounts`
+const DISKSTATFILE = `/proc/diskstats`
+const DISKSTAT_SYSFSPATH = `/sys/block`
 
 type DiskstatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
@@ -22,98 +20,93 @@ type DiskstatCollectorConfig struct {
 
 type DiskstatCollector struct {
 	metricCollector
-	//matches map[string]int
-	config IOstatCollectorConfig
-	//devices map[string]IOstatCollectorEntry
+	matches map[int]string
+	config  DiskstatCollectorConfig
 }
 
 func (m *DiskstatCollector) Init(config json.RawMessage) error {
+	var err error
 	m.name = "DiskstatCollector"
-	m.parallel = true
 	m.meta = map[string]string{"source": m.name, "group": "Disk"}
 	m.setup()
 	if len(config) > 0 {
-		err := json.Unmarshal(config, &m.config)
+		err = json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	file, err := os.Open(string(MOUNTFILE))
-	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
-		return err
+	// https://www.kernel.org/doc/html/latest/admin-guide/iostats.html
+	matches := map[int]string{
+		3:  "reads",
+		4:  "reads_merged",
+		5:  "read_sectors",
+		6:  "read_ms",
+		7:  "writes",
+		8:  "writes_merged",
+		9:  "writes_sectors",
+		10: "writes_ms",
+		11: "ioops",
+		12: "ioops_ms",
+		13: "ioops_weighted_ms",
+		14: "discards",
+		15: "discards_merged",
+		16: "discards_sectors",
+		17: "discards_ms",
+		18: "flushes",
+		19: "flushes_ms",
 	}
-	defer file.Close()
+	m.matches = make(map[int]string)
+	for k, v := range matches {
+		_, skip := stringArrayContains(m.config.ExcludeMetrics, v)
+		if !skip {
+			m.matches[k] = v
+		}
+	}
+	if len(m.matches) == 0 {
+		return errors.New("No metrics to collect")
+	}
+	_, err = ioutil.ReadFile(string(DISKSTATFILE))
+	if err == nil {
 		m.init = true
-	return nil
+	}
+	return err
 }
 
 func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	var lines []string
 	if !m.init {
 		return
 	}
 
-	file, err := os.Open(string(MOUNTFILE))
+	buffer, err := ioutil.ReadFile(string(DISKSTATFILE))
 	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
 		return
 	}
-	defer file.Close()
+	lines = strings.Split(string(buffer), "\n")
 
-	part_max_used := uint64(0)
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
+	for _, line := range lines {
 		if len(line) == 0 {
 			continue
 		}
-		if !strings.HasPrefix(line, "/dev") {
+		f := strings.Fields(line)
+		if strings.Contains(f[2], "loop") {
 			continue
 		}
-		linefields := strings.Fields(line)
-		if strings.Contains(linefields[0], "loop") {
-			continue
+		tags := map[string]string{
+			"device": f[2],
+			"type":   "node",
 		}
-		if strings.Contains(linefields[1], "boot") {
-			continue
-		}
-		path := strings.Replace(linefields[1], `\040`, " ", -1)
-		stat := syscall.Statfs_t{
-			Blocks: 0,
-			Bsize:  0,
-			Bfree:  0,
-		}
-		err := syscall.Statfs(path, &stat)
-		if err != nil {
-			continue
-		}
-		if stat.Blocks == 0 || stat.Bsize == 0 {
-			continue
-		}
-		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())
+		for idx, name := range m.matches {
+			if idx < len(f) {
+				x, err := strconv.ParseInt(f[idx], 0, 64)
+				if err == nil {
+					y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": int(x)}, time.Now())
 					if err == nil {
-			y.AddMeta("unit", "GBytes")
 						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")
-			output <- y
-		}
-		if total > 0 {
-			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")
-		output <- y
 	}
 }
 

collectors/diskstatMetric.md

@@ -4,18 +4,31 @@
 ```json
   "diskstat": {
     "exclude_metrics": [
-      "disk_total"
+      "read_ms"
     ],
   }
 ```
 
-The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
+The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
 
-Metrics per device (with `device` tag):
-* `disk_total` (unit `GBytes`)
-* `disk_free` (unit `GBytes`)
-
-Global metrics:
-* `part_max_used` (unit `percent`)
+Metrics:
+* `reads`
+* `reads_merged`
+* `read_sectors`
+* `read_ms`
+* `writes`
+* `writes_merged`
+* `writes_sectors`
+* `writes_ms`
+* `ioops`
+* `ioops_ms`
+* `ioops_weighted_ms`
+* `discards`
+* `discards_merged`
+* `discards_sectors`
+* `discards_ms`
+* `flushes`
+* `flushes_ms`
 
+The device name is added as tag `device`.
 

collectors/gpfsMetric.go

@@ -7,49 +7,31 @@ import (
 	"fmt"
 	"io/ioutil"
 	"log"
+	"os"
 	"os/exec"
 	"os/user"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const DEFAULT_GPFS_CMD = "mmpmon"
-
-type GpfsCollectorLastState struct {
-	bytesRead    int64
-	bytesWritten int64
-}
-
 type GpfsCollector struct {
 	metricCollector
 	tags   map[string]string
 	config struct {
-		Mmpmon            string   `json:"mmpmon_path,omitempty"`
-		ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
-		SendBandwidths    bool     `json:"send_bandwidths"`
+		Mmpmon string `json:"mmpmon"`
 	}
-	skipFS        map[string]struct{}
-	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
-	lastState     map[string]GpfsCollectorLastState
 }
 
 func (m *GpfsCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
 	var err error
 	m.name = "GpfsCollector"
 	m.setup()
-	m.parallel = true
 
 	// Set default mmpmon binary
-	m.config.Mmpmon = DEFAULT_GPFS_CMD
+	m.config.Mmpmon = "/usr/lpp/mmfs/bin/mmpmon"
 
 	// Read JSON configuration
 	if len(config) > 0 {
@@ -67,45 +49,31 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 		"type":       "node",
 		"filesystem": "",
 	}
-	m.skipFS = make(map[string]struct{})
-	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()
 	if err != nil {
-		return fmt.Errorf("failed to get current user: %v", err)
+		return fmt.Errorf("GpfsCollector.Init(): Failed to get current user: %v", err)
 	}
 	if user.Uid != "0" {
-		return fmt.Errorf("GPFS file system statistics can only be queried by user root")
+		return fmt.Errorf("GpfsCollector.Init(): GPFS file system statistics can only be queried by user root")
 	}
 
 	// Check if mmpmon is in executable search path
-	p, err := exec.LookPath(m.config.Mmpmon)
+	_, err = exec.LookPath(m.config.Mmpmon)
 	if err != nil {
-		return fmt.Errorf("failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
+		return fmt.Errorf("GpfsCollector.Init(): Failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
 	}
-	m.config.Mmpmon = p
 
 	m.init = true
 	return nil
 }
 
 func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	// Check if already initialized
 	if !m.init {
 		return
 	}
 
-	// Current time stamp
-	now := time.Now()
-	// time difference to last time stamp
-	timeDiff := now.Sub(m.lastTimestamp).Seconds()
-	// Save current timestamp
-	m.lastTimestamp = now
-
 	// mmpmon:
 	// -p: generate output that can be parsed
 	// -s: suppress the prompt on input
@@ -118,15 +86,12 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	cmd.Stderr = cmdStderr
 	err := cmd.Run()
 	if err != nil {
-		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),
-			fmt.Sprintf("Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode()),
-			fmt.Sprintf("Read(): command stderr: \"%s\"\n", string(dataStdErr)),
-			fmt.Sprintf("Read(): command stdout: \"%s\"\n", string(dataStdOut)),
-		)
+		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
+		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
+		data, _ := ioutil.ReadAll(cmdStderr)
+		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): command stderr: \"%s\"\n", string(data))
+		data, _ = ioutil.ReadAll(cmdStdout)
+		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): command stdout: \"%s\"\n", string(data))
 		return
 	}
 
@@ -134,12 +99,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	scanner := bufio.NewScanner(cmdStdout)
 	for scanner.Scan() {
 		lineSplit := strings.Fields(scanner.Text())
-
-		// Only process lines starting with _fs_io_s_
-		if lineSplit[0] != "_fs_io_s_" {
-			continue
-		}
-
+		if lineSplit[0] == "_fs_io_s_" {
 			key_value := make(map[string]string)
 			for i := 1; i < len(lineSplit); i += 2 {
 				key_value[lineSplit[i]] = lineSplit[i+1]
@@ -153,57 +113,35 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 			filesystem, ok := key_value["_fs_"]
 			if !ok {
-			cclog.ComponentError(
-				m.name,
-				"Read(): Failed to get filesystem name.")
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to get filesystem name.\n")
 				continue
 			}
 
-		// Skip excluded filesystems
-		if _, skip := m.skipFS[filesystem]; skip {
-			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,
-				}
-			}
-		}
-
 			// return code
 			rc, err := strconv.Atoi(key_value["_rc_"])
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert return code '%s' to int: %v", key_value["_rc_"], err))
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert return code: %s\n", err.Error())
 				continue
 			}
 			if rc != 0 {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Filesystem '%s' is not ok.", filesystem))
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Filesystem %s not ok.", filesystem)
 				continue
 			}
 
 			sec, err := strconv.ParseInt(key_value["_t_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert seconds '%s' to int64: %v", key_value["_t_"], err))
+				fmt.Fprintf(os.Stderr,
+					"GpfsCollector.Read(): Failed to convert seconds to int '%s': %v\n",
+					key_value["_t_"], err)
 				continue
 			}
 			msec, err := strconv.ParseInt(key_value["_tu_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert micro seconds '%s' to int64: %v", key_value["_tu_"], err))
+				fmt.Fprintf(os.Stderr,
+					"GpfsCollector.Read(): Failed to convert micro seconds to int '%s': %v\n",
+					key_value["_tu_"], err)
 				continue
 			}
 			timestamp := time.Unix(sec, msec*1000)
@@ -211,123 +149,101 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 			// bytes read
 			bytesRead, err := strconv.ParseInt(key_value["_br_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert bytes read '%s' to int64: %v", key_value["_br_"], err))
+				fmt.Fprintf(os.Stderr,
+					"GpfsCollector.Read(): Failed to convert bytes read '%s': %s\n",
+					key_value["_br_"], err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp); err == nil {
+
+			y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp)
+			if err == nil {
 				output <- y
 			}
-		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 {
-					output <- y
-				}
-			}
-		}
 
 			// bytes written
 			bytesWritten, err := strconv.ParseInt(key_value["_bw_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert bytes written '%s' to int64: %v", key_value["_bw_"], err))
+				fmt.Fprintf(os.Stderr,
+					"GpfsCollector.Read(): Failed to convert bytes written '%s': %s\n",
+					key_value["_bw_"], err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp); err == nil {
-			output <- y
-		}
-		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 {
-					output <- y
-				}
-			}
-		}
 
-		if m.config.SendBandwidths {
-			m.lastState[filesystem] = GpfsCollectorLastState{
-				bytesRead:    bytesRead,
-				bytesWritten: bytesWritten,
-			}
+			y, err = lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp)
+			if err == nil {
+				output <- y
 			}
 
 			// number of opens
 			numOpens, err := strconv.ParseInt(key_value["_oc_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert number of opens '%s' to int64: %v", key_value["_oc_"], err))
+				fmt.Fprintf(os.Stderr,
+					"GpfsCollector.Read(): Failed to convert number of opens '%s': %s\n",
+					key_value["_oc_"], err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
+			y, err = lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp)
+			if err == nil {
 				output <- y
 			}
 
 			// number of closes
 			numCloses, err := strconv.ParseInt(key_value["_cc_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert number of closes: '%s' to int64: %v", key_value["_cc_"], err))
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of closes: %s\n", err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
+			y, err = lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp)
+			if err == nil {
 				output <- y
 			}
 
 			// number of reads
 			numReads, err := strconv.ParseInt(key_value["_rdc_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert number of reads: '%s' to int64: %v", key_value["_rdc_"], err))
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of reads: %s\n", err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
+			y, err = lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp)
+			if err == nil {
 				output <- y
 			}
 
 			// number of writes
 			numWrites, err := strconv.ParseInt(key_value["_wc_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert number of writes: '%s' to int64: %v", key_value["_wc_"], err))
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of writes: %s\n", err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
+			y, err = lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp)
+			if err == nil {
 				output <- y
 			}
 
 			// number of read directories
 			numReaddirs, err := strconv.ParseInt(key_value["_dir_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert number of read directories: '%s' to int64: %v", key_value["_dir_"], err))
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of read directories: %s\n", err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
+			y, err = lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp)
+			if err == nil {
 				output <- y
 			}
 
 			// Number of inode updates
 			numInodeUpdates, err := strconv.ParseInt(key_value["_iu_"], 10, 64)
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert number of inode updates: '%s' to int: %v", key_value["_iu_"], err))
+				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert Number of inode updates: %s\n", err.Error())
 				continue
 			}
-		if y, err := lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
+			y, err = lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp)
+			if err == nil {
 				output <- y
 			}
 		}
 	}
+}
 
 func (m *GpfsCollector) Close() {
 	m.init = false

collectors/gpfsMetric.md

@@ -1,34 +0,0 @@
-## `gpfs` collector
-
-```json
-  "ibstat": {
-    "mmpmon_path": "/path/to/mmpmon",
-    "exclude_filesystem": [
-      "fs1"
-    ],
-    "send_bandwidths" : true
-  }
-```
-
-The `gpfs` collector uses the `mmpmon` command to read performance metrics for
-GPFS / IBM Spectrum Scale filesystems.
-
-The reported filesystems can be filtered with the `exclude_filesystem` option
-in the configuration.
-
-The path to the `mmpmon` command can be configured with the `mmpmon_path` option
-in the configuration. If nothing is set, the collector searches in `$PATH` for `mmpmon`.
-
-
-Metrics:
-* `gpfs_bytes_read`
-* `gpfs_bytes_written`
-* `gpfs_num_opens`
-* `gpfs_num_closes`
-* `gpfs_num_reads`
-* `gpfs_num_readdirs`
-* `gpfs_num_inode_updates`
-* `gpfs_bw_read` (if `send_bandwidths == true`)
-* `gpfs_bw_write` (if `send_bandwidths == true`)
-
-The collector adds a `filesystem` tag to all metrics

collectors/infinibandMetric.go

@@ -2,10 +2,8 @@ package collectors
 
 import (
 	"fmt"
-	"io/ioutil"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	"golang.org/x/sys/unix"
 
@@ -16,54 +14,51 @@ import (
 	"time"
 )
 
-const IB_BASEPATH = "/sys/class/infiniband/"
-
-type InfinibandCollectorMetric struct {
-	path string
-	unit string
-}
+const IB_BASEPATH = `/sys/class/infiniband/`
 
 type InfinibandCollectorInfo struct {
 	LID              string            // IB local Identifier (LID)
 	device           string            // IB device
 	port             string            // IB device port
-	portCounterFiles map[string]InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
+	portCounterFiles map[string]string // mapping counter name -> file
 	tagSet           map[string]string // corresponding tag list
-	lastState        map[string]int64                     // State from last measurement
 }
 
 type InfinibandCollector struct {
 	metricCollector
 	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
-		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
+}
+
+func (m *InfinibandCollector) Help() {
+	fmt.Println("This collector includes all devices that can be found below ", IB_BASEPATH)
+	fmt.Println("and where any of the ports provides a 'lid' file (glob ", IB_BASEPATH, "/<dev>/ports/<port>/lid).")
+	fmt.Println("The devices can be filtered with the 'exclude_devices' option in the configuration.")
+	fmt.Println("For each found LIDs the collector calls the 'perfquery' command")
+	fmt.Println("")
+	fmt.Println("Full configuration object:")
+	fmt.Println("\"ibstat\" : {")
+	fmt.Println("  \"exclude_devices\" : [\"dev1\"]")
+	fmt.Println("}")
+	fmt.Println("")
+	fmt.Println("Metrics:")
+	fmt.Println("- ib_recv")
+	fmt.Println("- ib_xmit")
+	fmt.Println("- ib_recv_pkts")
+	fmt.Println("- ib_xmit_pkts")
 }
 
 // Init initializes the Infiniband collector by walking through files below IB_BASEPATH
 func (m *InfinibandCollector) Init(config json.RawMessage) error {
-
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
 	var err error
 	m.name = "InfinibandCollector"
 	m.setup()
-	m.parallel = true
 	m.meta = map[string]string{
 		"source": m.name,
 		"group":  "Network",
 	}
-
-	// Set default configuration,
-	m.config.SendAbsoluteValues = true
-	m.config.SendDerivedValues = false
-	// Read configuration file, allow overwriting default config
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -75,21 +70,17 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	globPattern := filepath.Join(IB_BASEPATH, "*", "ports", "*")
 	ibDirs, err := filepath.Glob(globPattern)
 	if err != nil {
-		return fmt.Errorf("unable to glob files with pattern %s: %v", globPattern, err)
+		return fmt.Errorf("Unable to glob files with pattern %s: %v", globPattern, err)
 	}
 	if ibDirs == nil {
-		return fmt.Errorf("unable to find any directories with pattern %s", globPattern)
+		return fmt.Errorf("Unable to find any directories with pattern %s", globPattern)
 	}
 
 	for _, path := range ibDirs {
 
 		// Skip, when no LID is assigned
-		line, err := ioutil.ReadFile(filepath.Join(path, "lid"))
-		if err != nil {
-			continue
-		}
-		LID := strings.TrimSpace(string(line))
-		if LID == "0x0" {
+		LID, ok := readOneLine(path + "/lid")
+		if !ok || LID == "0x0" {
 			continue
 		}
 
@@ -112,27 +103,21 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 
 		// Check access to counter files
 		countersDir := filepath.Join(path, "counters")
-		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"},
+		portCounterFiles := map[string]string{
+			"ib_recv":      filepath.Join(countersDir, "port_rcv_data"),
+			"ib_xmit":      filepath.Join(countersDir, "port_xmit_data"),
+			"ib_recv_pkts": filepath.Join(countersDir, "port_rcv_packets"),
+			"ib_xmit_pkts": filepath.Join(countersDir, "port_xmit_packets"),
 		}
-		for _, counter := range portCounterFiles {
-			err := unix.Access(counter.path, unix.R_OK)
+		for _, counterFile := range portCounterFiles {
+			err := unix.Access(counterFile, unix.R_OK)
 			if err != nil {
-				return fmt.Errorf("unable to access %s: %v", counter.path, err)
+				return fmt.Errorf("Unable to access %s: %v", counterFile, err)
 			}
 		}
 
-		// 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,
@@ -143,12 +128,11 @@ 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")
+		return fmt.Errorf("Found no IB devices")
 	}
 
 	m.init = true
@@ -163,57 +147,20 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 		return
 	}
 
-	// Current time stamp
 	now := time.Now()
-	// time difference to last time stamp
-	timeDiff := now.Sub(m.lastTimestamp).Seconds()
-	// Save current timestamp
-	m.lastTimestamp = now
+	for i := range m.info {
 
-	for _, info := range m.info {
-		for counterName, counterDef := range info.portCounterFiles {
-
-			// Read counter file
-			line, err := ioutil.ReadFile(counterDef.path)
-			if err != nil {
-				cclog.ComponentError(
-					m.name,
-					fmt.Sprintf("Read(): Failed to read from file '%s': %v", counterDef.path, err))
-				continue
-			}
-			data := strings.TrimSpace(string(line))
-
-			// convert counter to int64
-			v, err := strconv.ParseInt(data, 10, 64)
-			if err != nil {
-				cclog.ComponentError(
-					m.name,
-					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
-				continue
-			}
-
-			// Send absolut values
-			if m.config.SendAbsoluteValues {
+		// device info
+		info := &m.info[i]
+		for counterName, counterFile := range info.portCounterFiles {
+			if data, ok := readOneLine(counterFile); ok {
+				if v, err := strconv.ParseInt(data, 10, 64); 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
 					}
 				}
-
-			// Send derived values
-			if m.config.SendDerivedValues {
-				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
 			}
 		}
-				// Save current state
-				info.lastState[counterName] = v
-			}
-		}
-
 	}
 }
 

collectors/infinibandMetric.md

@@ -3,30 +3,17 @@
 
 ```json
   "ibstat": {
+    "perfquery_path" : "<path to perfquery command>",
     "exclude_devices": [
       "mlx4"
-    ],
-    "send_abs_values": true,
-    "send_derived_values": true
+    ]
   }
 ```
 
-The `ibstat` collector includes all Infiniband devices that can be
-found below `/sys/class/infiniband/` and where any of the ports provides a
-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>`.
+The `ibstat` collector reads either data through the `perfquery` command or the sysfs files below `/sys/class/infiniband/<device>`.
 
 Metrics:
 * `ib_recv`
 * `ib_xmit`
-* `ib_recv_pkts`
-* `ib_xmit_pkts`
-* `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`)
-* `ib_xmit_pkts_bw` (if `send_derived_values == true`)
 
 The collector adds a `device` tag to all metrics

collectors/infinibandPerfQueryMetric.go

@@ -0,0 +1,250 @@
+package collectors
+
+import (
+	"fmt"
+	"io/ioutil"
+	"log"
+	"os/exec"
+
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+
+	//	"os"
+	"encoding/json"
+	"errors"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+)
+
+const PERFQUERY = `/usr/sbin/perfquery`
+
+type InfinibandPerfQueryCollector struct {
+	metricCollector
+	tags   map[string]string
+	lids   map[string]map[string]string
+	config struct {
+		ExcludeDevices []string `json:"exclude_devices,omitempty"`
+		PerfQueryPath  string   `json:"perfquery_path"`
+	}
+}
+
+func (m *InfinibandPerfQueryCollector) Help() {
+	fmt.Println("This collector includes all devices that can be found below ", IB_BASEPATH)
+	fmt.Println("and where any of the ports provides a 'lid' file (glob ", IB_BASEPATH, "/<dev>/ports/<port>/lid).")
+	fmt.Println("The devices can be filtered with the 'exclude_devices' option in the configuration.")
+	fmt.Println("For each found LIDs the collector calls the 'perfquery' command")
+	fmt.Println("The path to the 'perfquery' command can be configured with the 'perfquery_path' option")
+	fmt.Println("in the configuration")
+	fmt.Println("")
+	fmt.Println("Full configuration object:")
+	fmt.Println("\"ibstat\" : {")
+	fmt.Println("  \"perfquery_path\" : \"path/to/perfquery\"  # if omitted, it searches in $PATH")
+	fmt.Println("  \"exclude_devices\" : [\"dev1\"]")
+	fmt.Println("}")
+	fmt.Println("")
+	fmt.Println("Metrics:")
+	fmt.Println("- ib_recv")
+	fmt.Println("- ib_xmit")
+	fmt.Println("- ib_recv_pkts")
+	fmt.Println("- ib_xmit_pkts")
+}
+
+func (m *InfinibandPerfQueryCollector) Init(config json.RawMessage) error {
+	var err error
+	m.name = "InfinibandCollectorPerfQuery"
+	m.setup()
+	m.meta = map[string]string{"source": m.name, "group": "Network"}
+	m.tags = map[string]string{"type": "node"}
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			return err
+		}
+	}
+	if len(m.config.PerfQueryPath) == 0 {
+		path, err := exec.LookPath("perfquery")
+		if err == nil {
+			m.config.PerfQueryPath = path
+		}
+	}
+	m.lids = make(map[string]map[string]string)
+	p := fmt.Sprintf("%s/*/ports/*/lid", string(IB_BASEPATH))
+	files, err := filepath.Glob(p)
+	for _, f := range files {
+		lid, err := ioutil.ReadFile(f)
+		if err == nil {
+			plist := strings.Split(strings.Replace(f, string(IB_BASEPATH), "", -1), "/")
+			skip := false
+			for _, d := range m.config.ExcludeDevices {
+				if d == plist[0] {
+					skip = true
+				}
+			}
+			if !skip {
+				m.lids[plist[0]] = make(map[string]string)
+				m.lids[plist[0]][plist[2]] = string(lid)
+			}
+		}
+	}
+
+	for _, ports := range m.lids {
+		for port, lid := range ports {
+			args := fmt.Sprintf("-r %s %s 0xf000", lid, port)
+			command := exec.Command(m.config.PerfQueryPath, args)
+			command.Wait()
+			_, err := command.Output()
+			if err != nil {
+				return fmt.Errorf("Failed to execute %s: %v", m.config.PerfQueryPath, err)
+			}
+		}
+	}
+
+	if len(m.lids) == 0 {
+		return errors.New("No usable IB devices")
+	}
+
+	m.init = true
+	return nil
+}
+
+func (m *InfinibandPerfQueryCollector) doPerfQuery(cmd string, dev string, lid string, port string, tags map[string]string, output chan lp.CCMetric) error {
+
+	args := fmt.Sprintf("-r %s %s 0xf000", lid, port)
+	command := exec.Command(cmd, args)
+	command.Wait()
+	stdout, err := command.Output()
+	if err != nil {
+		log.Print(err)
+		return err
+	}
+	ll := strings.Split(string(stdout), "\n")
+
+	for _, line := range ll {
+		if strings.HasPrefix(line, "PortRcvData") || strings.HasPrefix(line, "RcvData") {
+			lv := strings.Fields(line)
+			v, err := strconv.ParseFloat(lv[1], 64)
+			if err == nil {
+				y, err := lp.New("ib_recv", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+		if strings.HasPrefix(line, "PortXmitData") || strings.HasPrefix(line, "XmtData") {
+			lv := strings.Fields(line)
+			v, err := strconv.ParseFloat(lv[1], 64)
+			if err == nil {
+				y, err := lp.New("ib_xmit", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+		if strings.HasPrefix(line, "PortRcvPkts") || strings.HasPrefix(line, "RcvPkts") {
+			lv := strings.Fields(line)
+			v, err := strconv.ParseFloat(lv[1], 64)
+			if err == nil {
+				y, err := lp.New("ib_recv_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+		if strings.HasPrefix(line, "PortXmitPkts") || strings.HasPrefix(line, "XmtPkts") {
+			lv := strings.Fields(line)
+			v, err := strconv.ParseFloat(lv[1], 64)
+			if err == nil {
+				y, err := lp.New("ib_xmit_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+		if strings.HasPrefix(line, "PortRcvPkts") || strings.HasPrefix(line, "RcvPkts") {
+			lv := strings.Fields(line)
+			v, err := strconv.ParseFloat(lv[1], 64)
+			if err == nil {
+				y, err := lp.New("ib_recv_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+		if strings.HasPrefix(line, "PortXmitPkts") || strings.HasPrefix(line, "XmtPkts") {
+			lv := strings.Fields(line)
+			v, err := strconv.ParseFloat(lv[1], 64)
+			if err == nil {
+				y, err := lp.New("ib_xmit_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+	}
+	return nil
+}
+
+func (m *InfinibandPerfQueryCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+
+	if m.init {
+		for dev, ports := range m.lids {
+			for port, lid := range ports {
+				tags := map[string]string{
+					"type":   "node",
+					"device": dev,
+					"port":   port,
+					"lid":    lid}
+				path := fmt.Sprintf("%s/%s/ports/%s/counters/", string(IB_BASEPATH), dev, port)
+				buffer, err := ioutil.ReadFile(fmt.Sprintf("%s/port_rcv_data", path))
+				if err == nil {
+					data := strings.Replace(string(buffer), "\n", "", -1)
+					v, err := strconv.ParseFloat(data, 64)
+					if err == nil {
+						y, err := lp.New("ib_recv", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
+				}
+				buffer, err = ioutil.ReadFile(fmt.Sprintf("%s/port_xmit_data", path))
+				if err == nil {
+					data := strings.Replace(string(buffer), "\n", "", -1)
+					v, err := strconv.ParseFloat(data, 64)
+					if err == nil {
+						y, err := lp.New("ib_xmit", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
+				}
+				buffer, err = ioutil.ReadFile(fmt.Sprintf("%s/port_rcv_packets", path))
+				if err == nil {
+					data := strings.Replace(string(buffer), "\n", "", -1)
+					v, err := strconv.ParseFloat(data, 64)
+					if err == nil {
+						y, err := lp.New("ib_recv_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
+				}
+				buffer, err = ioutil.ReadFile(fmt.Sprintf("%s/port_xmit_packets", path))
+				if err == nil {
+					data := strings.Replace(string(buffer), "\n", "", -1)
+					v, err := strconv.ParseFloat(data, 64)
+					if err == nil {
+						y, err := lp.New("ib_xmit_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
+				}
+			}
+		}
+	}
+}
+
+func (m *InfinibandPerfQueryCollector) Close() {
+	m.init = false
+}

collectors/iostatMetric.go

@@ -1,156 +0,0 @@
-package collectors
-
-import (
-	"bufio"
-	"os"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-
-	//	"log"
-	"encoding/json"
-	"errors"
-	"strconv"
-	"strings"
-	"time"
-)
-
-const IOSTATFILE = `/proc/diskstats`
-const IOSTAT_SYSFSPATH = `/sys/block`
-
-type IOstatCollectorConfig struct {
-	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-}
-
-type IOstatCollectorEntry struct {
-	lastValues map[string]int64
-	tags       map[string]string
-}
-
-type IOstatCollector struct {
-	metricCollector
-	matches map[string]int
-	config  IOstatCollectorConfig
-	devices map[string]IOstatCollectorEntry
-}
-
-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 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			return err
-		}
-	}
-	// https://www.kernel.org/doc/html/latest/admin-guide/iostats.html
-	matches := map[string]int{
-		"io_reads":             3,
-		"io_reads_merged":      4,
-		"io_read_sectors":      5,
-		"io_read_ms":           6,
-		"io_writes":            7,
-		"io_writes_merged":     8,
-		"io_writes_sectors":    9,
-		"io_writes_ms":         10,
-		"io_ioops":             11,
-		"io_ioops_ms":          12,
-		"io_ioops_weighted_ms": 13,
-		"io_discards":          14,
-		"io_discards_merged":   15,
-		"io_discards_sectors":  16,
-		"io_discards_ms":       17,
-		"io_flushes":           18,
-		"io_flushes_ms":        19,
-	}
-	m.devices = make(map[string]IOstatCollectorEntry)
-	m.matches = make(map[string]int)
-	for k, v := range matches {
-		if _, skip := stringArrayContains(m.config.ExcludeMetrics, k); !skip {
-			m.matches[k] = v
-		}
-	}
-	if len(m.matches) == 0 {
-		return errors.New("no metrics to collect")
-	}
-	file, err := os.Open(string(IOSTATFILE))
-	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-	defer file.Close()
-
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
-		linefields := strings.Fields(line)
-		device := linefields[2]
-		if strings.Contains(device, "loop") {
-			continue
-		}
-		values := make(map[string]int64)
-		for m := range m.matches {
-			values[m] = 0
-		}
-		m.devices[device] = IOstatCollectorEntry{
-			tags: map[string]string{
-				"device": linefields[2],
-				"type":   "node",
-			},
-			lastValues: values,
-		}
-	}
-	m.init = true
-	return err
-}
-
-func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-
-	file, err := os.Open(string(IOSTATFILE))
-	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
-		return
-	}
-	defer file.Close()
-
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
-		if len(line) == 0 {
-			continue
-		}
-		linefields := strings.Fields(line)
-		device := linefields[2]
-		if strings.Contains(device, "loop") {
-			continue
-		}
-		if _, ok := m.devices[device]; !ok {
-			continue
-		}
-		entry := m.devices[device]
-		for name, idx := range m.matches {
-			if idx < len(linefields) {
-				x, err := strconv.ParseInt(linefields[idx], 0, 64)
-				if err == nil {
-					diff := x - entry.lastValues[name]
-					y, err := lp.New(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
-					if err == nil {
-						output <- y
-					}
-				}
-				entry.lastValues[name] = x
-			}
-		}
-		m.devices[device] = entry
-	}
-}
-
-func (m *IOstatCollector) Close() {
-	m.init = false
-}

collectors/iostatMetric.md

@@ -1,34 +0,0 @@
-
-## `iostat` collector
-
-```json
-  "iostat": {
-    "exclude_metrics": [
-      "read_ms"
-    ],
-  }
-```
-
-The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
-
-Metrics:
-* `io_reads`
-* `io_reads_merged`
-* `io_read_sectors`
-* `io_read_ms`
-* `io_writes`
-* `io_writes_merged`
-* `io_writes_sectors`
-* `io_writes_ms`
-* `io_ioops`
-* `io_ioops_ms`
-* `io_ioops_weighted_ms`
-* `io_discards`
-* `io_discards_merged`
-* `io_discards_sectors`
-* `io_discards_ms`
-* `io_flushes`
-* `io_flushes_ms`
-
-The device name is added as tag `device`. For more details, see https://www.kernel.org/doc/html/latest/admin-guide/iostats.html
-

collectors/ipmiMetric.go

@@ -9,12 +9,11 @@ import (
 	"strconv"
 	"strings"
 	"time"
-
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const IPMITOOL_PATH = `ipmitool`
-const IPMISENSORS_PATH = `ipmi-sensors`
+const IPMITOOL_PATH = `/usr/bin/ipmitool`
+const IPMISENSORS_PATH = `/usr/sbin/ipmi-sensors`
 
 type IpmiCollectorConfig struct {
 	ExcludeDevices  []string `json:"exclude_devices"`
@@ -24,38 +23,31 @@ type IpmiCollectorConfig struct {
 
 type IpmiCollector struct {
 	metricCollector
-	//tags        map[string]string
-	//matches     map[string]string
+	tags    map[string]string
+	matches map[string]string
 	config  IpmiCollectorConfig
-	ipmitool    string
-	ipmisensors string
 }
 
 func (m *IpmiCollector) Init(config json.RawMessage) error {
 	m.name = "IpmiCollector"
 	m.setup()
-	m.parallel = true
 	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
 		}
 	}
-	p, err := exec.LookPath(m.config.IpmitoolPath)
-	if err == nil {
-		m.ipmitool = p
+	_, err1 := os.Stat(m.config.IpmitoolPath)
+	_, err2 := os.Stat(m.config.IpmisensorsPath)
+	if err1 != nil {
+		m.config.IpmitoolPath = ""
 	}
-	p, err = exec.LookPath(m.config.IpmisensorsPath)
-	if err == nil {
-		m.ipmisensors = p
+	if err2 != nil {
+		m.config.IpmisensorsPath = ""
 	}
-	if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
-		return errors.New("no IPMI reader found")
+	if err1 != nil && err2 != nil {
+		return errors.New("No IPMI reader found")
 	}
 	m.init = true
 	return nil

collectors/likwidMetric.go

@@ -2,7 +2,7 @@ package collectors
 
 /*
 #cgo CFLAGS: -I./likwid
-#cgo LDFLAGS: -Wl,--unresolved-symbols=ignore-in-object-files
+#cgo LDFLAGS: -L./likwid -llikwid -llikwid-hwloc -lm
 #include <stdlib.h>
 #include <likwid.h>
 */
@@ -13,36 +13,35 @@ import (
 	"errors"
 	"fmt"
 	"io/ioutil"
+	"log"
 	"math"
 	"os"
-	"os/signal"
-	"sort"
 	"strconv"
 	"strings"
-	"sync"
-	"syscall"
 	"time"
 	"unsafe"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
-	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	"github.com/NVIDIA/go-nvml/pkg/dl"
+	"gopkg.in/Knetic/govaluate.v2"
 )
 
+type MetricScope int
+
 const (
-	LIKWID_LIB_NAME       = "liblikwid.so"
-	LIKWID_LIB_DL_FLAGS   = dl.RTLD_LAZY | dl.RTLD_GLOBAL
-	LIKWID_DEF_ACCESSMODE = "direct"
+	METRIC_SCOPE_HWTHREAD = iota
+	METRIC_SCOPE_SOCKET
+	METRIC_SCOPE_NUMA
+	METRIC_SCOPE_NODE
 )
 
+func (ms MetricScope) String() string {
+	return []string{"Head", "Shoulder", "Knee", "Toe"}[ms]
+}
+
 type LikwidCollectorMetricConfig struct {
-	Name    string `json:"name"` // Name of the metric
-	Calc    string `json:"calc"` // Calculation for the metric using
-	Type    string `json:"type"` // Metric type (aka node, socket, cpu, ...)
+	Name    string      `json:"name"`
+	Calc    string      `json:"calc"`
+	Scope   MetricScope `json:"socket_scope"`
 	Publish bool        `json:"publish"`
-	Unit    string `json:"unit"` // Unit of metric if any
 }
 
 type LikwidCollectorEventsetConfig struct {
@@ -50,46 +49,30 @@ type LikwidCollectorEventsetConfig struct {
 	Metrics []LikwidCollectorMetricConfig `json:"metrics"`
 }
 
-type LikwidEventsetConfig struct {
-	internal int
-	gid      C.int
-	eorder   []*C.char
-	estr     *C.char
-	go_estr  string
-	results  map[int]map[string]interface{}
-	metrics  map[int]map[string]float64
-}
-
 type LikwidCollectorConfig struct {
 	Eventsets      []LikwidCollectorEventsetConfig `json:"eventsets"`
-	Metrics        []LikwidCollectorMetricConfig   `json:"globalmetrics,omitempty"`
-	ForceOverwrite bool                            `json:"force_overwrite,omitempty"`
-	InvalidToZero  bool                            `json:"invalid_to_zero,omitempty"`
-	AccessMode     string                          `json:"access_mode,omitempty"`
-	DaemonPath     string                          `json:"accessdaemon_path,omitempty"`
-	LibraryPath    string                          `json:"liblikwid_path,omitempty"`
+	Metrics        []LikwidCollectorMetricConfig   `json:"globalmetrics"`
+	ExcludeMetrics []string                        `json:"exclude_metrics"`
+	ForceOverwrite bool                            `json:"force_overwrite"`
 }
 
 type LikwidCollector struct {
 	metricCollector
 	cpulist   []C.int
-	cpu2tid      map[int]int
 	sock2tid  map[int]int
 	metrics   map[C.int]map[string]int
 	groups    []C.int
 	config    LikwidCollectorConfig
+	results   map[int]map[int]map[string]interface{}
+	mresults  map[int]map[int]map[string]float64
 	gmresults map[int]map[string]float64
 	basefreq  float64
-	running      bool
-	initialized  bool
-	likwidGroups map[C.int]LikwidEventsetConfig
-	lock         sync.Mutex
 }
 
 type LikwidMetric struct {
 	name         string
 	search       string
-	scope     string
+	socket_scope bool
 	group_idx    int
 }
 
@@ -101,475 +84,238 @@ func eventsToEventStr(events map[string]string) string {
 	return strings.Join(elist, ",")
 }
 
-func genLikwidEventSet(input LikwidCollectorEventsetConfig) LikwidEventsetConfig {
-	tmplist := make([]string, 0)
-	clist := make([]string, 0)
-	for k := range input.Events {
-		clist = append(clist, k)
-	}
-	sort.Strings(clist)
-	elist := make([]*C.char, 0)
-	for _, k := range clist {
-		v := input.Events[k]
-		tmplist = append(tmplist, fmt.Sprintf("%s:%s", v, k))
-		c_counter := C.CString(k)
-		elist = append(elist, c_counter)
-	}
-	estr := strings.Join(tmplist, ",")
-	res := make(map[int]map[string]interface{})
-	met := make(map[int]map[string]float64)
-	for _, i := range topo.CpuList() {
-		res[i] = make(map[string]interface{})
-		for k := range input.Events {
-			res[i][k] = 0.0
-		}
-		met[i] = make(map[string]float64)
-		for _, v := range input.Metrics {
-			res[i][v.Name] = 0.0
-		}
-	}
-	return LikwidEventsetConfig{
-		gid:     -1,
-		eorder:  elist,
-		estr:    C.CString(estr),
-		go_estr: estr,
-		results: res,
-		metrics: met,
-	}
-}
-
-func testLikwidMetricFormula(formula string, params []string) bool {
-	myparams := make(map[string]interface{})
-	for _, p := range params {
-		myparams[p] = float64(1.0)
-	}
-	_, err := agg.EvalFloat64Condition(formula, myparams)
-	return err == nil
-}
-
 func getBaseFreq() float64 {
-	files := []string{
-		"/sys/devices/system/cpu/cpu0/cpufreq/bios_limit",
-		"/sys/devices/system/cpu/cpu0/cpufreq/base_frequency",
-	}
 	var freq float64 = math.NaN()
-	for _, f := range files {
-		buffer, err := ioutil.ReadFile(f)
+	C.power_init(0)
+	info := C.get_powerInfo()
+	if float64(info.baseFrequency) != 0 {
+		freq = float64(info.baseFrequency)
+	} else {
+		buffer, err := ioutil.ReadFile("/sys/devices/system/cpu/cpu0/cpufreq/bios_limit")
 		if err == nil {
 			data := strings.Replace(string(buffer), "\n", "", -1)
 			x, err := strconv.ParseInt(data, 0, 64)
 			if err == nil {
-				freq = float64(x) * 1e6
+				freq = float64(x) * 1e3
 			}
 		}
 	}
-
-	if math.IsNaN(freq) {
-		C.power_init(0)
-		info := C.get_powerInfo()
-		if float64(info.baseFrequency) != 0 {
-			freq = float64(info.baseFrequency) * 1e6
-		}
-		C.power_finalize()
-	}
 	return freq
 }
 
+func getSocketCpus() map[C.int]int {
+	slist := SocketList()
+	var cpu C.int
+	outmap := make(map[C.int]int)
+	for _, s := range slist {
+		t := C.CString(fmt.Sprintf("S%d", s))
+		clen := C.cpustr_to_cpulist(t, &cpu, 1)
+		if int(clen) == 1 {
+			outmap[cpu] = s
+		}
+	}
+	return outmap
+}
+
 func (m *LikwidCollector) Init(config json.RawMessage) error {
+	var ret C.int
 	m.name = "LikwidCollector"
-	m.parallel = false
-	m.initialized = false
-	m.running = false
-	m.config.AccessMode = LIKWID_DEF_ACCESSMODE
-	m.config.LibraryPath = LIKWID_LIB_NAME
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	lib := dl.New(m.config.LibraryPath, LIKWID_LIB_DL_FLAGS)
-	if lib == nil {
-		return fmt.Errorf("error instantiating DynamicLibrary for %s", m.config.LibraryPath)
-	}
-	err := lib.Open()
-	if err != nil {
-		return fmt.Errorf("error opening %s: %v", m.config.LibraryPath, err)
-	}
-
-	if m.config.ForceOverwrite {
-		cclog.ComponentDebug(m.name, "Set LIKWID_FORCE=1")
-		os.Setenv("LIKWID_FORCE", "1")
-	}
 	m.setup()
-
-	m.meta = map[string]string{"group": "PerfCounter"}
-	cclog.ComponentDebug(m.name, "Get cpulist and init maps and lists")
-	cpulist := topo.HwthreadList()
+	m.meta = map[string]string{"source": m.name, "group": "PerfCounter"}
+	cpulist := CpuList()
 	m.cpulist = make([]C.int, len(cpulist))
-	m.cpu2tid = make(map[int]int)
+	slist := getSocketCpus()
+
+	m.sock2tid = make(map[int]int)
+	//	m.numa2tid = make(map[int]int)
 	for i, c := range cpulist {
 		m.cpulist[i] = C.int(c)
-		m.cpu2tid[c] = i
+		if sid, found := slist[m.cpulist[i]]; found {
+			m.sock2tid[sid] = i
+		}
+	}
+	m.results = make(map[int]map[int]map[string]interface{})
+	m.mresults = make(map[int]map[int]map[string]float64)
+	m.gmresults = make(map[int]map[string]float64)
+	ret = C.topology_init()
+	if ret != 0 {
+		return errors.New("Failed to initialize LIKWID topology")
+	}
+	if m.config.ForceOverwrite {
+		os.Setenv("LIKWID_FORCE", "1")
+	}
+	ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
+	if ret != 0 {
+		C.topology_finalize()
+		return errors.New("Failed to initialize LIKWID topology")
 	}
 
-	m.likwidGroups = make(map[C.int]LikwidEventsetConfig)
-
-	// m.results = make(map[int]map[int]map[string]interface{})
-	// m.mresults = make(map[int]map[int]map[string]float64)
-	m.gmresults = make(map[int]map[string]float64)
-	for _, tid := range m.cpu2tid {
+	for i, evset := range m.config.Eventsets {
+		estr := eventsToEventStr(evset.Events)
+		cstr := C.CString(estr)
+		gid := C.perfmon_addEventSet(cstr)
+		if gid >= 0 {
+			m.groups = append(m.groups, gid)
+		}
+		C.free(unsafe.Pointer(cstr))
+		m.results[i] = make(map[int]map[string]interface{})
+		m.mresults[i] = make(map[int]map[string]float64)
+		for tid := range m.cpulist {
+			m.results[i][tid] = make(map[string]interface{})
+			m.mresults[i][tid] = make(map[string]float64)
 			m.gmresults[tid] = make(map[string]float64)
 		}
-
-	// This is for the global metrics computation test
-	totalMetrics := 0
-	// Generate parameter list for the metric computing test
-	params := make([]string, 0)
-	params = append(params, "time", "inverseClock")
-	// Generate parameter list for the global metric computing test
-	globalParams := make([]string, 0)
-	globalParams = append(globalParams, "time", "inverseClock")
-	// We test the eventset metrics whether they can be computed at all
-	for _, evset := range m.config.Eventsets {
-		if len(evset.Events) > 0 {
-			params = params[:2]
-			for counter := range evset.Events {
-				params = append(params, counter)
-			}
-			for _, metric := range evset.Metrics {
-				// Try to evaluate the metric
-				if testLikwidMetricFormula(metric.Calc, params) {
-					// Add the computable metric to the parameter list for the global metrics
-					globalParams = append(globalParams, metric.Name)
-					totalMetrics++
-				} else {
-					metric.Calc = ""
-				}
-			}
-		} else {
-			cclog.ComponentError(m.name, "Invalid Likwid eventset config, no events given")
-			continue
-		}
-	}
-	for _, metric := range m.config.Metrics {
-		// Try to evaluate the global metric
-		if !testLikwidMetricFormula(metric.Calc, globalParams) {
-			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed")
-			metric.Calc = ""
-		} else {
-			totalMetrics++
-		}
 	}
 
-	// If no event set could be added, shut down LikwidCollector
-	if totalMetrics == 0 {
-		err := errors.New("no LIKWID eventset or metric usable")
-		cclog.ComponentError(m.name, err.Error())
-		return err
+	if len(m.groups) == 0 {
+		C.perfmon_finalize()
+		C.topology_finalize()
+		return errors.New("No LIKWID performance group initialized")
 	}
+	m.basefreq = getBaseFreq()
 	m.init = true
 	return nil
 }
 
-// take a measurement for 'interval' seconds of event set index 'group'
-func (m *LikwidCollector) takeMeasurement(evset LikwidEventsetConfig, interval time.Duration) (bool, error) {
-	var ret C.int
-	m.lock.Lock()
-	if m.initialized {
-		ret = C.perfmon_setupCounters(evset.gid)
-		if ret != 0 {
-			var err error = nil
-			var skip bool = false
-			if ret == -37 {
-				skip = true
-			} else {
-				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-			}
-			m.lock.Unlock()
-			return skip, err
-		}
-		ret = C.perfmon_startCounters()
-		if ret != 0 {
-			var err error = nil
-			var skip bool = false
-			if ret == -37 {
-				skip = true
-			} else {
-				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-			}
-			m.lock.Unlock()
-			return skip, err
-		}
-		m.running = true
-		time.Sleep(interval)
-		m.running = false
-		ret = C.perfmon_stopCounters()
-		if ret != 0 {
-			var err error = nil
-			var skip bool = false
-			if ret == -37 {
-				skip = true
-			} else {
-				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-			}
-			m.lock.Unlock()
-			return skip, err
-		}
-	}
-	m.lock.Unlock()
-	return false, nil
-}
-
-// Get all measurement results for an event set, derive the metric values out of the measurement results and send it
-func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
-	invClock := float64(1.0 / m.basefreq)
-
-	// Go over events and get the results
-	for eidx, counter := range evset.eorder {
-		gctr := C.GoString(counter)
-		for _, tid := range m.cpu2tid {
-			res := C.perfmon_getLastResult(evset.gid, C.int(eidx), C.int(tid))
-			fres := float64(res)
-			if m.config.InvalidToZero && (math.IsNaN(fres) || math.IsInf(fres, 0)) {
-				fres = 0.0
-			}
-			evset.results[tid][gctr] = fres
-			evset.results[tid]["time"] = interval.Seconds()
-			evset.results[tid]["inverseClock"] = invClock
-		}
-	}
-
-	// Go over the event set metrics, derive the value out of the event:counter values and send it
-	for _, metric := range m.config.Eventsets[evset.internal].Metrics {
-		// The metric scope is determined in the Init() function
-		// Get the map scope-id -> tids
-		scopemap := m.cpu2tid
-		if metric.Type == "socket" {
-			scopemap = m.sock2tid
-		}
-		for domain, tid := range scopemap {
-			if tid >= 0 && len(metric.Calc) > 0 {
-				value, err := agg.EvalFloat64Condition(metric.Calc, evset.results[tid])
-				if err != nil {
-					cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
-					value = 0.0
-				}
-				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
-					value = 0.0
-				}
-				evset.metrics[tid][metric.Name] = value
-				// Now we have the result, send it with the proper tags
-				if !math.IsNaN(value) {
-					if metric.Publish {
-						fields := map[string]interface{}{"value": value}
-						y, err := lp.New(metric.Name, map[string]string{"type": metric.Type}, m.meta, fields, time.Now())
-						if err == nil {
-							if metric.Type != "node" {
-								y.AddTag("type-id", fmt.Sprintf("%d", domain))
-							}
-							if len(metric.Unit) > 0 {
-								y.AddMeta("unit", metric.Unit)
-							}
-							output <- y
-						}
-					}
-				}
-			}
-		}
-	}
-
-	return nil
-}
-
-// Go over the global metrics, derive the value out of the event sets' metric values and send it
-func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan lp.CCMetric) error {
-	for _, metric := range m.config.Metrics {
-		scopemap := m.cpu2tid
-		if metric.Type == "socket" {
-			scopemap = m.sock2tid
-		}
-		for domain, tid := range scopemap {
-			if tid >= 0 {
-				// Here we generate parameter list
-				params := make(map[string]interface{})
-				for _, evset := range m.likwidGroups {
-					for mname, mres := range evset.metrics[tid] {
-						params[mname] = mres
-					}
-				}
-				// Evaluate the metric
-				value, err := agg.EvalFloat64Condition(metric.Calc, params)
-				if err != nil {
-					cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
-					value = 0.0
-				}
-				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
-					value = 0.0
-				}
-				m.gmresults[tid][metric.Name] = value
-				// Now we have the result, send it with the proper tags
-				if !math.IsNaN(value) {
-					if metric.Publish {
-						tags := map[string]string{"type": metric.Type}
-						fields := map[string]interface{}{"value": value}
-						y, err := lp.New(metric.Name, tags, m.meta, fields, time.Now())
-						if err == nil {
-							if metric.Type != "node" {
-								y.AddTag("type-id", fmt.Sprintf("%d", domain))
-							}
-							if len(metric.Unit) > 0 {
-								y.AddMeta("unit", metric.Unit)
-							}
-							output <- y
-						}
-					}
-				}
-			}
-		}
-	}
-	return nil
-}
-
-func (m *LikwidCollector) LateInit() error {
-	var ret C.int
-	if m.initialized {
-		return nil
-	}
-	switch m.config.AccessMode {
-	case "direct":
-		C.HPMmode(0)
-	case "accessdaemon":
-		if len(m.config.DaemonPath) > 0 {
-			p := os.Getenv("PATH")
-			os.Setenv("PATH", m.config.DaemonPath+":"+p)
-		}
-		C.HPMmode(1)
-	}
-	cclog.ComponentDebug(m.name, "initialize LIKWID topology")
-	ret = C.topology_init()
-	if ret != 0 {
-		err := errors.New("failed to initialize LIKWID topology")
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-
-	m.sock2tid = make(map[int]int)
-	tmp := make([]C.int, 1)
-	for _, sid := range topo.SocketList() {
-		cstr := C.CString(fmt.Sprintf("S%d:0", sid))
-		ret = C.cpustr_to_cpulist(cstr, &tmp[0], 1)
-		if ret > 0 {
-			m.sock2tid[sid] = m.cpu2tid[int(tmp[0])]
-		}
-		C.free(unsafe.Pointer(cstr))
-	}
-
-	m.basefreq = getBaseFreq()
-	cclog.ComponentDebug(m.name, "BaseFreq", m.basefreq)
-
-	cclog.ComponentDebug(m.name, "initialize LIKWID perfmon module")
-	ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
-	if ret != 0 {
-		var err error = nil
-		C.topology_finalize()
-		if ret != -22 {
-			err = errors.New("failed to initialize LIKWID perfmon")
-			cclog.ComponentError(m.name, err.Error())
-		} else {
-			err = errors.New("access to LIKWID perfmon locked")
-		}
-		return err
-	}
-
-	// While adding the events, we test the metrics whether they can be computed at all
-	for i, evset := range m.config.Eventsets {
-		var gid C.int
-		if len(evset.Events) > 0 {
-			skip := false
-			likwidGroup := genLikwidEventSet(evset)
-			for _, g := range m.likwidGroups {
-				if likwidGroup.go_estr == g.go_estr {
-					skip = true
-					break
-				}
-			}
-			if skip {
-				continue
-			}
-			// Now we add the list of events to likwid
-			gid = C.perfmon_addEventSet(likwidGroup.estr)
-			if gid >= 0 {
-				likwidGroup.gid = gid
-				likwidGroup.internal = i
-				m.likwidGroups[gid] = likwidGroup
-			}
-		} else {
-			cclog.ComponentError(m.name, "Invalid Likwid eventset config, no events given")
-			continue
-		}
-
-	}
-
-	// If no event set could be added, shut down LikwidCollector
-	if len(m.likwidGroups) == 0 {
-		C.perfmon_finalize()
-		C.topology_finalize()
-		err := errors.New("no LIKWID performance group initialized")
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-	sigchan := make(chan os.Signal, 1)
-	signal.Notify(sigchan, syscall.SIGCHLD)
-	signal.Notify(sigchan, os.Interrupt)
-	go func() {
-		<-sigchan
-
-		signal.Stop(sigchan)
-		m.initialized = false
-	}()
-	m.initialized = true
-	return nil
-}
-
-// main read function taking multiple measurement rounds, each 'interval' seconds long
 func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	var skip bool = false
-	var err error
 	if !m.init {
 		return
 	}
+	var ret C.int
 
-	if !m.initialized {
-		m.lock.Lock()
-		err = m.LateInit()
+	for i, gid := range m.groups {
+		evset := m.config.Eventsets[i]
+		ret = C.perfmon_setupCounters(gid)
+		if ret != 0 {
+			log.Print("Failed to setup performance group ", C.perfmon_getGroupName(gid))
+			continue
+		}
+		ret = C.perfmon_startCounters()
+		if ret != 0 {
+			log.Print("Failed to start performance group ", C.perfmon_getGroupName(gid))
+			continue
+		}
+		time.Sleep(interval)
+		ret = C.perfmon_stopCounters()
+		if ret != 0 {
+			log.Print("Failed to stop performance group ", C.perfmon_getGroupName(gid))
+			continue
+		}
+		var eidx C.int
+		for tid := range m.cpulist {
+			for eidx = 0; int(eidx) < len(evset.Events); eidx++ {
+				ctr := C.perfmon_getCounterName(gid, eidx)
+				gctr := C.GoString(ctr)
+				res := C.perfmon_getLastResult(gid, eidx, C.int(tid))
+				m.results[i][tid][gctr] = float64(res)
+			}
+			m.results[i][tid]["time"] = interval.Seconds()
+			m.results[i][tid]["inverseClock"] = float64(1.0 / m.basefreq)
+			for _, metric := range evset.Metrics {
+				expression, err := govaluate.NewEvaluableExpression(metric.Calc)
 				if err != nil {
-			m.lock.Unlock()
-			return
+					log.Print(err.Error())
+					continue
 				}
-		m.initialized = true
-		m.lock.Unlock()
-	}
-
-	if m.initialized && !skip {
-		for _, evset := range m.likwidGroups {
-			if !skip {
-				// measure event set 'i' for 'interval' seconds
-				skip, err = m.takeMeasurement(evset, interval)
+				result, err := expression.Evaluate(m.results[i][tid])
 				if err != nil {
-					cclog.ComponentError(m.name, err.Error())
-					return
+					log.Print(err.Error())
+					continue
+				}
+				m.mresults[i][tid][metric.Name] = float64(result.(float64))
+			}
 		}
 	}
 
-			if !skip {
-				// read measurements and derive event set metrics
-				m.calcEventsetMetrics(evset, interval, output)
+	for _, metric := range m.config.Metrics {
+		for tid := range m.cpulist {
+			var params map[string]interface{}
+			expression, err := govaluate.NewEvaluableExpression(metric.Calc)
+			if err != nil {
+				log.Print(err.Error())
+				continue
+			}
+			params = make(map[string]interface{})
+			for j := range m.groups {
+				for mname, mres := range m.mresults[j][tid] {
+					params[mname] = mres
+				}
+			}
+			result, err := expression.Evaluate(params)
+			if err != nil {
+				log.Print(err.Error())
+				continue
+			}
+			m.gmresults[tid][metric.Name] = float64(result.(float64))
+		}
+	}
+	for i := range m.groups {
+		evset := m.config.Eventsets[i]
+		for _, metric := range evset.Metrics {
+			_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
+			if metric.Publish && !skip {
+				if metric.Scope.String() == "socket" {
+					for sid, tid := range m.sock2tid {
+						y, err := lp.New(metric.Name,
+							map[string]string{"type": "socket",
+								"type-id": fmt.Sprintf("%d", int(sid))},
+							m.meta,
+							map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
+							time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
+				} else if metric.Scope.String() == "hwthread" {
+					for tid, cpu := range m.cpulist {
+						y, err := lp.New(metric.Name,
+							map[string]string{"type": "cpu",
+								"type-id": fmt.Sprintf("%d", int(cpu))},
+							m.meta,
+							map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
+							time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
+				}
+			}
+		}
+	}
+	for _, metric := range m.config.Metrics {
+		_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
+		if metric.Publish && !skip {
+			if metric.Scope.String() == "socket" {
+				for sid, tid := range m.sock2tid {
+					y, err := lp.New(metric.Name,
+						map[string]string{"type": "socket",
+							"type-id": fmt.Sprintf("%d", int(sid))},
+						m.meta,
+						map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
+						time.Now())
+					if err == nil {
+						output <- y
+					}
+				}
+			} else {
+				for tid, cpu := range m.cpulist {
+					y, err := lp.New(metric.Name,
+						map[string]string{"type": "cpu",
+							"type-id": fmt.Sprintf("%d", int(cpu))},
+						m.meta,
+						map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
+						time.Now())
+					if err == nil {
+						output <- y
+					}
 				}
 			}
-		if !skip {
-			// use the event set metrics to derive the global metrics
-			m.calcGlobalMetrics(interval, output)
 		}
 	}
 }
@@ -577,17 +323,7 @@ func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric)
 func (m *LikwidCollector) Close() {
 	if m.init {
 		m.init = false
-		cclog.ComponentDebug(m.name, "Closing ...")
-		m.lock.Lock()
-		if m.initialized {
-			cclog.ComponentDebug(m.name, "Finalize LIKWID perfmon module")
 		C.perfmon_finalize()
-			m.initialized = false
-		}
-		m.lock.Unlock()
-		cclog.ComponentDebug(m.name, "Finalize LIKWID topology module")
 		C.topology_finalize()
-
-		cclog.ComponentDebug(m.name, "Closing done")
 	}
 }

collectors/likwidMetric.md

@@ -1,134 +1,7 @@
 
 ## `likwid` collector
-
-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,
-    "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 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. 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.
-
-Additional options:
-- `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`
-
-### 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.
-
-- `hwthread` : One metric per CPU hardware thread with the tags `"type" : "hwthread"` and `"type-id" : "$hwthread_id"`
-- `socket` : One metric per CPU socket/package with the tags `"type" : "socket"` and `"type-id" : "$socket_id"`
-
-**Note:** You cannot specify `socket` scope for a metric that is measured at `hwthread` 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 scope `hwthread`
-- All counters names containing `BOX` have the scope `socket`
-- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `hwthread` 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
-[...]
-short name: ICX
-[...]
-$ likwid-perfctr -a
-[...]
-MEM_DP
-MEM
-FLOPS_SP
-CLOCK
-[...]
-$ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
-{
-  "events": {
-    "FIXC0": "INSTR_RETIRED_ANY",
-    "FIXC1": "CPU_CLK_UNHALTED_CORE",
-    "..." : "..."
-  },
-  "metrics" : [
-    {
-      "calc": "time",
-      "name": "Runtime (RDTSC) [s]",
-      "publish": true,
-      "unit": "seconds"
-      "scope": "hwthread"
-    },
-    {
-      "..." : "..."
-    }
-  ]
-}
-```
-
-You can copy this JSON and add it to the `eventsets` list. If you specify multiple event sets, you can add globally derived metrics in the extra `global_metrics` section with the metric names as variables.
-
-### Mixed usage between daemon and users
-
-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, ...)
-```
-$ chown $JOBUSER /var/run/likwid.lock
-```
-
-After (SLURM epilog, ...)
-```
-$ 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).
-
-
-### Example configuration
-
-#### AMD Zen3
-
-```json
-  "likwid": {
-    "force_overwrite" : false,
-    "invalid_to_zero" : false,
     "eventsets": [
       {
         "events": {
@@ -147,28 +20,25 @@ One might think this does not happen often but often used metrics in the world o
           {
             "name": "ipc",
             "calc": "PMC0/PMC1",
-            "type": "hwthread",
+            "socket_scope": false,
             "publish": true
           },
           {
             "name": "flops_any",
             "calc": "0.000001*PMC2/time",
-            "unit": "MFlops/s",
-            "type": "hwthread",
+            "socket_scope": false,
             "publish": true
           },
           {
-            "name": "clock",
+            "name": "clock_mhz",
             "calc": "0.000001*(FIXC1/FIXC2)/inverseClock",
-            "type": "hwthread",
-            "unit": "MHz",
+            "socket_scope": false,
             "publish": true
           },
           {
             "name": "mem1",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "unit": "Mbyte/s",
-            "type": "socket",
+            "socket_scope": true,
             "publish": false
           }
         ]
@@ -186,22 +56,19 @@ One might think this does not happen often but often used metrics in the world o
           {
             "name": "pwr_core",
             "calc": "PWR0/time",
-            "unit": "Watt"
-            "type": "socket",
+            "socket_scope": false,
             "publish": true
           },
           {
             "name": "pwr_pkg",
             "calc": "PWR1/time",
-            "type": "socket",
-            "unit": "Watt"
+            "socket_scope": true,
             "publish": true
           },
           {
             "name": "mem2",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "unit": "Mbyte/s",
-            "type": "socket",
+            "socket_scope": true,
             "publish": false
           }
         ]
@@ -211,15 +78,14 @@ One might think this does not happen often but often used metrics in the world o
       {
         "name": "mem_bw",
         "calc": "mem1+mem2",
-        "type": "socket",
-        "unit": "Mbyte/s",
+        "socket_scope": true,
         "publish": true
       }
     ]
   }
 ```
 
-### How to get the eventsets and metrics from LIKWID
+_Example config suitable for AMD Zen3_
 
 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.
 
@@ -242,10 +108,12 @@ METRICS                          ->   "metrics": [
 IPC   PMC0/PMC1                  ->     {
                                  ->       "name" : "IPC",
                                  ->       "calc" : "PMC0/PMC1",
-                                 ->       "scope": "hwthread",
+                                 ->       "socket_scope": false,
                                  ->       "publish": true
                                  ->     }
                                  ->   ]
 ```
 
-The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.
+The `socket_scope` option tells whether it is submitted per socket or per hwthread. If a metric is only used for internal calculations, you can set `publish = false`.
+
+Since some metrics can only be gathered in multiple measurements (like the memory bandwidth on AMD Zen3 chips), configure multiple eventsets like in the example config and use the `globalmetrics` section to combine them. **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.

collectors/loadavgMetric.go

@@ -2,41 +2,29 @@ package collectors
 
 import (
 	"encoding/json"
-	"fmt"
 	"io/ioutil"
 	"strconv"
 	"strings"
 	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-//
-// LoadavgCollector collects:
-// * load average of last 1, 5 & 15 minutes
-// * number of processes currently runnable
-// * total number of processes in system
-//
-// See: https://www.kernel.org/doc/html/latest/filesystems/proc.html
-//
-const LOADAVGFILE = "/proc/loadavg"
+const LOADAVGFILE = `/proc/loadavg`
+
+type LoadavgCollectorConfig struct {
+	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+}
 
 type LoadavgCollector struct {
 	metricCollector
 	tags         map[string]string
 	load_matches []string
-	load_skips   []bool
 	proc_matches []string
-	proc_skips   []bool
-	config       struct {
-		ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-	}
+	config       LoadavgCollectorConfig
 }
 
 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)
@@ -44,82 +32,46 @@ func (m *LoadavgCollector) Init(config json.RawMessage) error {
 			return err
 		}
 	}
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "LOAD"}
+	m.meta = map[string]string{"source": m.name, "group": "LOAD"}
 	m.tags = map[string]string{"type": "node"}
-	m.load_matches = []string{
-		"load_one",
-		"load_five",
-		"load_fifteen"}
-	m.load_skips = make([]bool, len(m.load_matches))
-	m.proc_matches = []string{
-		"proc_run",
-		"proc_total"}
-	m.proc_skips = make([]bool, len(m.proc_matches))
-
-	for i, name := range m.load_matches {
-		_, m.load_skips[i] = stringArrayContains(m.config.ExcludeMetrics, name)
-	}
-	for i, name := range m.proc_matches {
-		_, m.proc_skips[i] = stringArrayContains(m.config.ExcludeMetrics, name)
-	}
+	m.load_matches = []string{"load_one", "load_five", "load_fifteen"}
+	m.proc_matches = []string{"proc_run", "proc_total"}
 	m.init = true
 	return nil
 }
 
 func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	var skip bool
 	if !m.init {
 		return
 	}
-	buffer, err := ioutil.ReadFile(LOADAVGFILE)
+	buffer, err := ioutil.ReadFile(string(LOADAVGFILE))
+
 	if err != nil {
-		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
-		}
 		return
 	}
-	now := time.Now()
 
-	// Load metrics
 	ls := strings.Split(string(buffer), ` `)
 	for i, name := range m.load_matches {
 		x, err := strconv.ParseFloat(ls[i], 64)
-		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", ls[i], err))
-			continue
-		}
-		if m.load_skips[i] {
-			continue
-		}
-		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
 		if err == nil {
+			_, skip = stringArrayContains(m.config.ExcludeMetrics, name)
+			y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": float64(x)}, time.Now())
+			if err == nil && !skip {
 				output <- y
 			}
 		}
-
-	// Process metrics
+	}
 	lv := strings.Split(ls[3], `/`)
 	for i, name := range m.proc_matches {
-		x, err := strconv.ParseInt(lv[i], 10, 64)
-		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", lv[i], err))
-			continue
-		}
-		if m.proc_skips[i] {
-			continue
-		}
-		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
+		x, err := strconv.ParseFloat(lv[i], 64)
 		if err == nil {
+			_, skip = stringArrayContains(m.config.ExcludeMetrics, name)
+			y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": float64(x)}, time.Now())
+			if err == nil && !skip {
 				output <- y
 			}
-
+		}
 	}
 }
 

collectors/lustreMetric.go

@@ -3,292 +3,32 @@ package collectors
 import (
 	"encoding/json"
 	"errors"
-	"fmt"
-	"os/exec"
-	"os/user"
+	"io/ioutil"
+	"log"
 	"strconv"
 	"strings"
 	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const LUSTRE_SYSFS = `/sys/fs/lustre`
-const LCTL_CMD = `lctl`
-const LCTL_OPTION = `get_param`
+const LUSTREFILE = `/proc/fs/lustre/llite/lnec-XXXXXX/stats`
 
 type LustreCollectorConfig struct {
-	LCtlCommand        string   `json:"lctl_command,omitempty"`
-	ExcludeMetrics     []string `json:"exclude_metrics,omitempty"`
-	Sudo               bool     `json:"use_sudo,omitempty"`
-	SendAbsoluteValues bool     `json:"send_abs_values,omitempty"`
-	SendDerivedValues  bool     `json:"send_derived_values,omitempty"`
-	SendDiffValues     bool     `json:"send_diff_values,omitempty"`
-}
-
-type LustreMetricDefinition struct {
-	name       string
-	lineprefix string
-	lineoffset int
-	unit       string
-	calc       string
+	Procfiles      []string `json:"procfiles"`
+	ExcludeMetrics []string `json:"exclude_metrics"`
 }
 
 type LustreCollector struct {
 	metricCollector
 	tags    map[string]string
+	matches map[string]map[string]int
+	devices []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
-}
-
-func (m *LustreCollector) getDeviceDataCommand(device string) []string {
-	var command *exec.Cmd
-	statsfile := fmt.Sprintf("llite.%s.stats", device)
-	if m.config.Sudo {
-		command = exec.Command(m.sudoCmd, m.lctl, LCTL_OPTION, statsfile)
-	} else {
-		command = exec.Command(m.lctl, LCTL_OPTION, statsfile)
-	}
-	command.Wait()
-	stdout, _ := command.Output()
-	return strings.Split(string(stdout), "\n")
-}
-
-func (m *LustreCollector) getDevices() []string {
-	devices := make([]string, 0)
-
-	// //Version reading devices from sysfs
-	// globPattern := filepath.Join(LUSTRE_SYSFS, "llite/*/stats")
-	// files, err := filepath.Glob(globPattern)
-	// if err != nil {
-	// 	return devices
-	// }
-	// for _, f := range files {
-	// 	pathlist := strings.Split(f, "/")
-	// 	devices = append(devices, pathlist[4])
-	// }
-
-	data := m.getDeviceDataCommand("*")
-
-	for _, line := range data {
-		if strings.HasPrefix(line, "llite") {
-			linefields := strings.Split(line, ".")
-			if len(linefields) > 2 {
-				devices = append(devices, linefields[1])
-			}
-		}
-	}
-	return devices
-}
-
-func getMetricData(lines []string, prefix string, offset int) (int64, error) {
-	for _, line := range lines {
-		if strings.HasPrefix(line, prefix) {
-			lf := strings.Fields(line)
-			return strconv.ParseInt(lf[offset], 0, 64)
-		}
-	}
-	return 0, errors.New("no such line in data")
-}
-
-// //Version reading the stats data of a device from sysfs
-// func (m *LustreCollector) getDeviceDataSysfs(device string) []string {
-// 	llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
-// 	devdir := filepath.Join(llitedir, device)
-// 	statsfile := filepath.Join(devdir, "stats")
-// 	buffer, err := ioutil.ReadFile(statsfile)
-// 	if err != nil {
-// 		return make([]string, 0)
-// 	}
-// 	return strings.Split(string(buffer), "\n")
-// }
-
-var LustreAbsMetrics = []LustreMetricDefinition{
-	{
-		name:       "lustre_read_requests",
-		lineprefix: "read_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_write_requests",
-		lineprefix: "write_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_read_bytes",
-		lineprefix: "read_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_write_bytes",
-		lineprefix: "write_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_open",
-		lineprefix: "open",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_close",
-		lineprefix: "close",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_setattr",
-		lineprefix: "setattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_getattr",
-		lineprefix: "getattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_statfs",
-		lineprefix: "statfs",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_inode_permission",
-		lineprefix: "inode_permission",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-}
-
-var LustreDiffMetrics = []LustreMetricDefinition{
-	{
-		name:       "lustre_read_requests_diff",
-		lineprefix: "read_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_write_requests_diff",
-		lineprefix: "write_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_read_bytes_diff",
-		lineprefix: "read_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_write_bytes_diff",
-		lineprefix: "write_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_open_diff",
-		lineprefix: "open",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_close_diff",
-		lineprefix: "close",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_setattr_diff",
-		lineprefix: "setattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_getattr_diff",
-		lineprefix: "getattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_statfs_diff",
-		lineprefix: "statfs",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_inode_permission_diff",
-		lineprefix: "inode_permission",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-}
-
-var LustreDeriveMetrics = []LustreMetricDefinition{
-	{
-		name:       "lustre_read_requests_rate",
-		lineprefix: "read_bytes",
-		lineoffset: 1,
-		unit:       "requests/sec",
-		calc:       "derivative",
-	},
-	{
-		name:       "lustre_write_requests_rate",
-		lineprefix: "write_bytes",
-		lineoffset: 1,
-		unit:       "requests/sec",
-		calc:       "derivative",
-	},
-	{
-		name:       "lustre_read_bw",
-		lineprefix: "read_bytes",
-		lineoffset: 6,
-		unit:       "bytes/sec",
-		calc:       "derivative",
-	},
-	{
-		name:       "lustre_write_bw",
-		lineprefix: "write_bytes",
-		lineoffset: 6,
-		unit:       "bytes/sec",
-		calc:       "derivative",
-	},
 }
 
 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 {
@@ -298,81 +38,28 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
 	m.setup()
 	m.tags = map[string]string{"type": "node"}
 	m.meta = map[string]string{"source": m.name, "group": "Lustre"}
-
-	// Lustre file system statistics can only be queried by user root
-	// or with password-less sudo
-	if !m.config.Sudo {
-		user, err := user.Current()
-		if err != nil {
-			cclog.ComponentError(m.name, "Failed to get current user:", err.Error())
-			return err
-		}
-		if user.Uid != "0" {
-			cclog.ComponentError(m.name, "Lustre file system statistics can only be queried by user root")
-			return err
-		}
-	} else {
-		p, err := exec.LookPath("sudo")
-		if err != nil {
-			cclog.ComponentError(m.name, "Cannot find 'sudo'")
-			return err
-		}
-		m.sudoCmd = p
-	}
-
-	p, err := exec.LookPath(m.config.LCtlCommand)
-	if err != nil {
-		p, err = exec.LookPath(LCTL_CMD)
-		if err != nil {
-			return err
-		}
-	}
-	m.lctl = p
-
-	m.definitions = []LustreMetricDefinition{}
-	if m.config.SendAbsoluteValues {
-		for _, def := range LustreAbsMetrics {
-			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
-				m.definitions = append(m.definitions, def)
-			}
-		}
-	}
-	if m.config.SendDiffValues {
-		for _, def := range LustreDiffMetrics {
-			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
-				m.definitions = append(m.definitions, def)
-			}
-		}
-	}
-	if m.config.SendDerivedValues {
-		for _, def := range LustreDeriveMetrics {
-			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
-				m.definitions = append(m.definitions, def)
-			}
-		}
-	}
-	if len(m.definitions) == 0 {
-		return errors.New("no metrics to collect")
-	}
-
-	devices := m.getDevices()
-	if len(devices) == 0 {
-		return errors.New("no Lustre devices found")
-	}
-	m.stats = make(map[string]map[string]int64)
-	for _, d := range devices {
-		m.stats[d] = make(map[string]int64)
-		data := m.getDeviceDataCommand(d)
-		for _, def := range m.definitions {
-			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
+	m.matches = map[string]map[string]int{"read_bytes": {"read_bytes": 6, "read_requests": 1},
+		"write_bytes":      {"write_bytes": 6, "write_requests": 1},
+		"open":             {"open": 1},
+		"close":            {"close": 1},
+		"setattr":          {"setattr": 1},
+		"getattr":          {"getattr": 1},
+		"statfs":           {"statfs": 1},
+		"inode_permission": {"inode_permission": 1}}
+	m.devices = make([]string, 0)
+	for _, p := range m.config.Procfiles {
+		_, err := ioutil.ReadFile(p)
 		if err == nil {
-				m.stats[d][def.name] = x
+			m.devices = append(m.devices, p)
 		} else {
-				m.stats[d][def.name] = 0
+			log.Print(err.Error())
+			continue
 		}
 	}
+
+	if len(m.devices) == 0 {
+		return errors.New("No metrics to collect")
 	}
-	m.lastTimestamp = time.Now()
 	m.init = true
 	return nil
 }
@@ -381,49 +68,40 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
-	now := time.Now()
-	tdiff := now.Sub(m.lastTimestamp)
-	for device, devData := range m.stats {
-		data := m.getDeviceDataCommand(device)
-		for _, def := range m.definitions {
-			var use_x int64
-			var err error
-			var y lp.CCMetric
-			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
+	for _, p := range m.devices {
+		buffer, err := ioutil.ReadFile(p)
+
+		if err != nil {
+			log.Print(err)
+			return
+		}
+
+		for _, line := range strings.Split(string(buffer), "\n") {
+			lf := strings.Fields(line)
+			if len(lf) > 1 {
+				for match, fields := range m.matches {
+					if lf[0] == match {
+						for name, idx := range fields {
+							_, skip := stringArrayContains(m.config.ExcludeMetrics, name)
+							if skip {
+								continue
+							}
+							x, err := strconv.ParseInt(lf[idx], 0, 64)
 							if err == nil {
-				use_x = x
-			} else {
-				use_x = devData[def.name]
-			}
-			var value interface{}
-			switch def.calc {
-			case "none":
-				value = use_x
-				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-			case "difference":
-				value = use_x - devData[def.name]
-				if value.(int64) < 0 {
-					value = 0
-				}
-				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-			case "derivative":
-				value = float64(use_x-devData[def.name]) / tdiff.Seconds()
-				if value.(float64) < 0 {
-					value = 0
-				}
-				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-			}
+								y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, time.Now())
 								if err == nil {
-				y.AddTag("device", device)
-				if len(def.unit) > 0 {
-					y.AddMeta("unit", def.unit)
+									if strings.Contains(name, "byte") {
+										y.AddMeta("unit", "Byte")
 									}
 									output <- y
 								}
-			devData[def.name] = use_x
 							}
 						}
-	m.lastTimestamp = now
+					}
+				}
+			}
+		}
+	}
 }
 
 func (m *LustreCollector) Close() {

collectors/lustreMetric.md

@@ -3,44 +3,27 @@
 
 ```json
   "lustrestat": {
-    "lctl_command": "/path/to/lctl",
+    "procfiles" : [
+      "/proc/fs/lustre/llite/lnec-XXXXXX/stats"
+    ],
     "exclude_metrics": [
       "setattr",
       "getattr"
-    ],
-    "send_abs_values" : true,
-    "send_derived_values" : true,
-    "send_diff_values": true,
-    "use_sudo": false
+    ]
   }
 ```
 
-The `lustrestat` collector uses the `lctl` application with the `get_param` option to get all `llite` metrics (Lustre client). The `llite` metrics are only available for root users. If password-less sudo is configured, you can enable `sudo` in the configuration.
+The `lustrestat` collector reads from the procfs stat files for Lustre like `/proc/fs/lustre/llite/lnec-XXXXXX/stats`.
 
 Metrics:
-* `lustre_read_bytes` (unit `bytes`)
-* `lustre_read_requests` (unit `requests`)
-* `lustre_write_bytes` (unit `bytes`)
-* `lustre_write_requests` (unit `requests`)
-* `lustre_open`
-* `lustre_close`
-* `lustre_getattr`
-* `lustre_setattr`
-* `lustre_statfs`
-* `lustre_inode_permission`
-* `lustre_read_bw` (if `send_derived_values == true`, unit `bytes/sec`)
-* `lustre_write_bw` (if `send_derived_values == true`, unit `bytes/sec`)
-* `lustre_read_requests_rate` (if `send_derived_values == true`, unit `requests/sec`)
-* `lustre_write_requests_rate` (if `send_derived_values == true`, unit `requests/sec`)
-* `lustre_read_bytes_diff` (if `send_diff_values == true`, unit `bytes`)
-* `lustre_read_requests_diff` (if `send_diff_values == true`, unit `requests`)
-* `lustre_write_bytes_diff` (if `send_diff_values == true`, unit `bytes`)
-* `lustre_write_requests_diff` (if `send_diff_values == true`, unit `requests`)
-* `lustre_open_diff` (if `send_diff_values == true`)
-* `lustre_close_diff` (if `send_diff_values == true`)
-* `lustre_getattr_diff` (if `send_diff_values == true`)
-* `lustre_setattr_diff` (if `send_diff_values == true`)
-* `lustre_statfs_diff` (if `send_diff_values == true`)
-* `lustre_inode_permission_diff` (if `send_diff_values == true`)
+* `read_bytes`
+* `read_requests`
+* `write_bytes`
+* `write_requests`
+* `open`
+* `close`
+* `getattr`
+* `setattr`
+* `statfs`
+* `inode_permission`
 
-This collector adds an `device` tag.

collectors/memstatMetric.go

@@ -1,33 +1,22 @@
 package collectors
 
 import (
-	"bufio"
 	"encoding/json"
 	"errors"
 	"fmt"
-	"os"
-	"path/filepath"
-	"regexp"
+	"io/ioutil"
+	"log"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const MEMSTATFILE = "/proc/meminfo"
-const NUMA_MEMSTAT_BASE = "/sys/devices/system/node"
+const MEMSTATFILE = `/proc/meminfo`
 
 type MemstatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics"`
-	NodeStats      bool     `json:"node_stats,omitempty"`
-	NumaStats      bool     `json:"numa_stats,omitempty"`
-}
-
-type MemstatCollectorNode struct {
-	file string
-	tags map[string]string
 }
 
 type MemstatCollector struct {
@@ -36,66 +25,22 @@ type MemstatCollector struct {
 	tags    map[string]string
 	matches map[string]string
 	config  MemstatCollectorConfig
-	nodefiles   map[int]MemstatCollectorNode
-	sendMemUsed bool
-}
-
-type MemstatStats struct {
-	value float64
-	unit  string
-}
-
-func getStats(filename string) map[string]MemstatStats {
-	stats := make(map[string]MemstatStats)
-	file, err := os.Open(filename)
-	if err != nil {
-		cclog.Error(err.Error())
-	}
-	defer file.Close()
-
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
-		linefields := strings.Fields(line)
-		if len(linefields) == 3 {
-			v, err := strconv.ParseFloat(linefields[1], 64)
-			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
-					value: v,
-					unit:  linefields[2],
-				}
-			}
-		} else if len(linefields) == 5 {
-			v, err := strconv.ParseFloat(linefields[3], 64)
-			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
-					value: v,
-					unit:  linefields[4],
-				}
-			}
-		}
-	}
-	return stats
 }
 
 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 {
 		err = json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	m.meta = map[string]string{"source": m.name, "group": "Memory"}
+	m.meta = map[string]string{"source": m.name, "group": "Memory", "unit": "kByte"}
 	m.stats = make(map[string]int64)
 	m.matches = make(map[string]string)
 	m.tags = map[string]string{"type": "node"}
-	matches := map[string]string{
-		"MemTotal":     "mem_total",
+	matches := map[string]string{`MemTotal`: "mem_total",
 		"SwapTotal":    "swap_total",
 		"SReclaimable": "mem_sreclaimable",
 		"Slab":         "mem_slab",
@@ -103,126 +48,79 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 		"Buffers":      "mem_buffers",
 		"Cached":       "mem_cached",
 		"MemAvailable": "mem_available",
-		"SwapFree":     "swap_free",
-		"MemShared":    "mem_shared",
-	}
+		"SwapFree":     "swap_free"}
 	for k, v := range matches {
 		_, skip := stringArrayContains(m.config.ExcludeMetrics, k)
 		if !skip {
 			m.matches[k] = v
 		}
 	}
-	m.sendMemUsed = false
-	if _, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used"); !skip {
-		m.sendMemUsed = true
-	}
 	if len(m.matches) == 0 {
-		return errors.New("no metrics to collect")
+		return errors.New("No metrics to collect")
 	}
 	m.setup()
-
-	if m.config.NodeStats {
-		if stats := getStats(MEMSTATFILE); len(stats) == 0 {
-			return fmt.Errorf("cannot read data from file %s", MEMSTATFILE)
-		}
-	}
-
-	if m.config.NumaStats {
-		globPattern := filepath.Join(NUMA_MEMSTAT_BASE, "node[0-9]*", "meminfo")
-		regex := regexp.MustCompile(filepath.Join(NUMA_MEMSTAT_BASE, "node(\\d+)", "meminfo"))
-		files, err := filepath.Glob(globPattern)
+	_, err = ioutil.ReadFile(string(MEMSTATFILE))
 	if err == nil {
-			m.nodefiles = make(map[int]MemstatCollectorNode)
-			for _, f := range files {
-				if stats := getStats(f); len(stats) == 0 {
-					return fmt.Errorf("cannot read data from file %s", f)
-				}
-				rematch := regex.FindStringSubmatch(f)
-				if len(rematch) == 2 {
-					id, err := strconv.Atoi(rematch[1])
-					if err == nil {
-						f := MemstatCollectorNode{
-							file: f,
-							tags: map[string]string{
-								"type":    "memoryDomain",
-								"type-id": fmt.Sprintf("%d", id),
-							},
-						}
-						m.nodefiles[id] = f
-					}
-				}
-			}
-		}
-	}
 		m.init = true
+	}
 	return err
 }
 
 func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
-		cclog.ComponentPrint(m.name, "Here")
 		return
 	}
 
-	sendStats := func(stats map[string]MemstatStats, tags map[string]string) {
+	buffer, err := ioutil.ReadFile(string(MEMSTATFILE))
+	if err != nil {
+		log.Print(err)
+		return
+	}
+
+	ll := strings.Split(string(buffer), "\n")
+	for _, line := range ll {
+		ls := strings.Split(line, `:`)
+		if len(ls) > 1 {
+			lv := strings.Fields(ls[1])
+			m.stats[ls[0]], err = strconv.ParseInt(lv[0], 0, 64)
+		}
+	}
+
+	if _, exists := m.stats[`MemTotal`]; !exists {
+		err = errors.New("Parse error")
+		log.Print(err)
+		return
+	}
+
 	for match, name := range m.matches {
-			var value float64 = 0
-			var unit string = ""
-			if v, ok := stats[match]; ok {
-				value = v.value
-				if len(v.unit) > 0 {
-					unit = v.unit
+		if _, exists := m.stats[match]; !exists {
+			err = fmt.Errorf("Parse error for %s : %s", match, name)
+			log.Print(err)
+			continue
 		}
-			}
-
-			y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": int(float64(m.stats[match]) * 1.0e-3)}, time.Now())
 		if err == nil {
-				if len(unit) > 0 {
-					y.AddMeta("unit", unit)
-				}
 			output <- y
 		}
 	}
-		if m.sendMemUsed {
-			memUsed := 0.0
-			unit := ""
-			if totalVal, total := stats["MemTotal"]; total {
-				if freeVal, free := stats["MemFree"]; free {
-					if bufVal, buffers := stats["Buffers"]; buffers {
-						if cacheVal, cached := stats["Cached"]; cached {
-							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
-							}
-						}
-					}
-				}
-			}
-			y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
-			if err == nil {
-				if len(unit) > 0 {
-					y.AddMeta("unit", unit)
-				}
+
+	if _, free := m.stats[`MemFree`]; free {
+		if _, buffers := m.stats[`Buffers`]; buffers {
+			if _, cached := m.stats[`Cached`]; cached {
+				memUsed := m.stats[`MemTotal`] - (m.stats[`MemFree`] + m.stats[`Buffers`] + m.stats[`Cached`])
+				_, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used")
+				y, err := lp.New("mem_used", m.tags, m.meta, map[string]interface{}{"value": int(float64(memUsed) * 1.0e-3)}, time.Now())
+				if err == nil && !skip {
 					output <- y
 				}
 			}
 		}
-
-	if m.config.NodeStats {
-		nodestats := getStats(MEMSTATFILE)
-		sendStats(nodestats, m.tags)
 	}
-
-	if m.config.NumaStats {
-		for _, nodeConf := range m.nodefiles {
-			stats := getStats(nodeConf.file)
-			sendStats(stats, nodeConf.tags)
+	if _, found := m.stats[`MemShared`]; found {
+		_, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_shared")
+		y, err := lp.New("mem_shared", m.tags, m.meta, map[string]interface{}{"value": int(float64(m.stats[`MemShared`]) * 1.0e-3)}, time.Now())
+		if err == nil && !skip {
+			output <- y
 		}
 	}
 }

collectors/metricCollector.go

@@ -3,43 +3,40 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
+	"io/ioutil"
+	"log"
+	"strconv"
+	"strings"
 	"time"
 
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	influx "github.com/influxdata/line-protocol"
 )
 
 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
-	Read(duration time.Duration, output chan lp.CCMetric) // Read metrics from metric collector
-	Close()                                               // Close / finish metric collector
+	Name() string
+	Init(config json.RawMessage) error
+	Initialized() bool
+	Read(duration time.Duration, output chan lp.CCMetric)
+	Close()
 }
 
 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
+	init bool
+	meta map[string]string
 }
 
-// Name returns the name of the metric collector
+// Name() returns the name of the metric collector
 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
 }
 
-// Initialized indicates whether the metric collector has been initialized
+// Initialized() indicates whether the metric collector has been initialized.
 func (c *metricCollector) Initialized() bool {
 	return c.init
 }
@@ -68,13 +65,81 @@ func stringArrayContains(array []string, str string) (int, bool) {
 	return -1, false
 }
 
+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
+}
+
+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
+}
+
+// Tags2Map stores a InfluxDB list of tags in a map of key value pairs
+func Tags2Map(metric influx.Metric) map[string]string {
+	tags := make(map[string]string)
+	for _, t := range metric.TagList() {
+		tags[t.Key] = t.Value
+	}
+	return tags
+}
+
+// Fields2Map stores a InfluxDB list of fields in a map of key value pairs
+func Fields2Map(metric influx.Metric) map[string]interface{} {
+	fields := make(map[string]interface{})
+	for _, f := range metric.FieldList() {
+		fields[f.Key] = f.Value
+	}
+	return fields
+}
+
 // 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) {
-	for i := range s {
-		if r == s[i] {
+	for i, item := range s {
+		if r == item {
 			return append(s[:i], s[i+1:]...), nil
 		}
 	}
-	return s, fmt.Errorf("no such string in list")
+	return s, fmt.Errorf("No such string in list")
 }

collectors/netstatMetric.go

@@ -1,218 +1,92 @@
 package collectors
 
 import (
-	"bufio"
 	"encoding/json"
-	"errors"
-	"os"
+	"io/ioutil"
+	"log"
 	"strconv"
 	"strings"
 	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const NETSTATFILE = "/proc/net/dev"
+const NETSTATFILE = `/proc/net/dev`
 
 type NetstatCollectorConfig struct {
-	IncludeDevices     []string `json:"include_devices"`
-	SendAbsoluteValues bool     `json:"send_abs_values"`
-	SendDerivedValues  bool     `json:"send_derived_values"`
-}
-
-type NetstatCollectorMetric struct {
-	name       string
-	index      int
-	tags       map[string]string
-	meta       map[string]string
-	meta_rates map[string]string
-	lastValue  int64
+	ExcludeDevices []string `json:"exclude_devices"`
 }
 
 type NetstatCollector struct {
 	metricCollector
 	config  NetstatCollectorConfig
-	matches       map[string][]NetstatCollectorMetric
-	lastTimestamp time.Time
+	matches map[int]string
 }
 
 func (m *NetstatCollector) Init(config json.RawMessage) error {
 	m.name = "NetstatCollector"
-	m.parallel = true
 	m.setup()
-	m.lastTimestamp = time.Now()
-
-	const (
-		fieldInterface = iota
-		fieldReceiveBytes
-		fieldReceivePackets
-		fieldReceiveErrs
-		fieldReceiveDrop
-		fieldReceiveFifo
-		fieldReceiveFrame
-		fieldReceiveCompressed
-		fieldReceiveMulticast
-		fieldTransmitBytes
-		fieldTransmitPackets
-		fieldTransmitErrs
-		fieldTransmitDrop
-		fieldTransmitFifo
-		fieldTransmitColls
-		fieldTransmitCarrier
-		fieldTransmitCompressed
-	)
-
-	m.matches = make(map[string][]NetstatCollectorMetric)
-
-	// Set default configuration,
-	m.config.SendAbsoluteValues = true
-	m.config.SendDerivedValues = false
-	// Read configuration file, allow overwriting default config
+	m.meta = map[string]string{"source": m.name, "group": "Memory"}
+	m.matches = map[int]string{
+		1:  "bytes_in",
+		9:  "bytes_out",
+		2:  "pkts_in",
+		10: "pkts_out",
+	}
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
-			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			log.Print(err.Error())
 			return err
 		}
 	}
-
-	// Check access to net statistic file
-	file, err := os.Open(NETSTATFILE)
-	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-	defer file.Close()
-
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		l := scanner.Text()
-
-		// Skip lines with no net device entry
-		if !strings.Contains(l, ":") {
-			continue
-		}
-
-		// Split line into fields
-		f := strings.Fields(l)
-
-		// Get net device entry
-		dev := strings.Trim(f[0], ": ")
-
-		// Check if device is a included device
-		if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
-			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"}
-			meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"}
-
-			m.matches[dev] = []NetstatCollectorMetric{
-				{
-					name:       "net_bytes_in",
-					index:      fieldReceiveBytes,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_byte,
-					meta_rates: meta_unit_byte_per_sec,
-				},
-				{
-					name:       "net_pkts_in",
-					index:      fieldReceivePackets,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_pkts,
-					meta_rates: meta_unit_pkts_per_sec,
-				},
-				{
-					name:       "net_bytes_out",
-					index:      fieldTransmitBytes,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_byte,
-					meta_rates: meta_unit_byte_per_sec,
-				},
-				{
-					name:       "net_pkts_out",
-					index:      fieldTransmitPackets,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_pkts,
-					meta_rates: meta_unit_pkts_per_sec,
-				},
-			}
-		}
-
-	}
-
-	if len(m.matches) == 0 {
-		return errors.New("no devices to collector metrics found")
-	}
+	_, err := ioutil.ReadFile(string(NETSTATFILE))
+	if err == nil {
 		m.init = true
+	}
 	return nil
 }
 
 func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-	// Current time stamp
-	now := time.Now()
-	// time difference to last time stamp
-	timeDiff := now.Sub(m.lastTimestamp).Seconds()
-	// Save current timestamp
-	m.lastTimestamp = now
-
-	file, err := os.Open(string(NETSTATFILE))
+	data, err := ioutil.ReadFile(string(NETSTATFILE))
 	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
+		log.Print(err.Error())
 		return
 	}
-	defer file.Close()
 
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		l := scanner.Text()
-
-		// Skip lines with no net device entry
+	lines := strings.Split(string(data), "\n")
+	for _, l := range lines {
 		if !strings.Contains(l, ":") {
 			continue
 		}
-
-		// Split line into fields
 		f := strings.Fields(l)
-
-		// Get net device entry
-		dev := strings.Trim(f[0], ":")
-
-		// Check if device is a included device
-		if devmetrics, ok := m.matches[dev]; ok {
-			for i := range devmetrics {
-				metric := &devmetrics[i]
-
-				// Read value
-				v, err := strconv.ParseInt(f[metric.index], 10, 64)
-				if err != nil {
+		dev := f[0][0 : len(f[0])-1]
+		cont := false
+		for _, d := range m.config.ExcludeDevices {
+			if d == dev {
+				cont = true
+			}
+		}
+		if cont {
 			continue
 		}
-				if m.config.SendAbsoluteValues {
-					if y, err := lp.New(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
+		tags := map[string]string{"device": dev, "type": "node"}
+		for i, name := range m.matches {
+			v, err := strconv.ParseInt(f[i], 10, 0)
+			if err == nil {
+				y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": int(float64(v) * 1.0e-3)}, time.Now())
+				if err == nil {
+					switch {
+					case strings.Contains(name, "byte"):
+						y.AddMeta("unit", "Byte")
+					case strings.Contains(name, "pkt"):
+						y.AddMeta("unit", "Packets")
+					}
 					output <- y
 				}
 			}
-				if m.config.SendDerivedValues {
-					if metric.lastValue >= 0 {
-						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
-						}
-					}
-					metric.lastValue = v
-				}
-			}
 		}
 	}
+
 }
 
 func (m *NetstatCollector) Close() {

collectors/netstatMetric.md

@@ -3,25 +3,19 @@
 
 ```json
   "netstat": {
-    "include_devices": [
-      "eth0"
-    ],
-    "send_abs_values" : true,
-    "send_derived_values" : true
+    "exclude_devices": [
+      "lo"
+    ]
   }
 ```
 
-The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list.
+The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. If a device is not required, it can be excluded from forwarding it to the sink. Commonly the `lo` device should be excluded.
 
 Metrics:
-* `net_bytes_in` (`unit=bytes`)
-* `net_bytes_out` (`unit=bytes`)
-* `net_pkts_in` (`unit=packets`)
-* `net_pkts_out` (`unit=packets`)
-* `net_bytes_in_bw` (`unit=bytes/sec` if `send_derived_values == true`)
-* `net_bytes_out_bw` (`unit=bytes/sec` if `send_derived_values == true`)
-* `net_pkts_in_bw` (`unit=packets/sec` if `send_derived_values == true`)
-* `net_pkts_out_bw` (`unit=packets/sec` if `send_derived_values == true`)
+* `bytes_in`
+* `bytes_out`
+* `pkts_in`
+* `pkts_out`
 
 The device name is added as tag `device`.
 

collectors/nfs3Metric.md

@@ -1,39 +0,0 @@
-
-## `nfs3stat` collector
-
-```json
-  "nfs3stat": {
-    "nfsstat" : "/path/to/nfsstat",
-    "exclude_metrics": [
-      "nfs3_total"
-    ]
-  }
-```
-
-The `nfs3stat` collector reads data from `nfsstat` command and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink. There is currently no possibility to get the metrics per mount point.
-
-
-Metrics:
-* `nfs3_total` 
-* `nfs3_null` 
-* `nfs3_getattr` 
-* `nfs3_setattr` 
-* `nfs3_lookup` 
-* `nfs3_access` 
-* `nfs3_readlink` 
-* `nfs3_read` 
-* `nfs3_write` 
-* `nfs3_create` 
-* `nfs3_mkdir` 
-* `nfs3_symlink` 
-* `nfs3_remove` 
-* `nfs3_rmdir` 
-* `nfs3_rename` 
-* `nfs3_link` 
-* `nfs3_readdir` 
-* `nfs3_readdirplus` 
-* `nfs3_fsstat` 
-* `nfs3_fsinfo` 
-* `nfs3_pathconf` 
-* `nfs3_commit` 
-

collectors/nfs4Metric.md

@@ -1,62 +0,0 @@
-
-## `nfs4stat` collector
-
-```json
-  "nfs4stat": {
-    "nfsstat" : "/path/to/nfsstat",
-    "exclude_metrics": [
-      "nfs4_total"
-    ]
-  }
-```
-
-The `nfs4stat` collector reads data from `nfsstat` command and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink. There is currently no possibility to get the metrics per mount point.
-
-
-Metrics:
-* `nfs4_total` 
-* `nfs4_null` 
-* `nfs4_read` 
-* `nfs4_write` 
-* `nfs4_commit` 
-* `nfs4_open` 
-* `nfs4_open_conf` 
-* `nfs4_open_noat` 
-* `nfs4_open_dgrd` 
-* `nfs4_close` 
-* `nfs4_setattr` 
-* `nfs4_fsinfo` 
-* `nfs4_renew` 
-* `nfs4_setclntid` 
-* `nfs4_confirm` 
-* `nfs4_lock` 
-* `nfs4_lockt` 
-* `nfs4_locku` 
-* `nfs4_access` 
-* `nfs4_getattr` 
-* `nfs4_lookup` 
-* `nfs4_lookup_root` 
-* `nfs4_remove` 
-* `nfs4_rename` 
-* `nfs4_link` 
-* `nfs4_symlink` 
-* `nfs4_create` 
-* `nfs4_pathconf` 
-* `nfs4_statfs` 
-* `nfs4_readlink` 
-* `nfs4_readdir` 
-* `nfs4_server_caps` 
-* `nfs4_delegreturn` 
-* `nfs4_getacl` 
-* `nfs4_setacl` 
-* `nfs4_rel_lkowner` 
-* `nfs4_exchange_id` 
-* `nfs4_create_session` 
-* `nfs4_destroy_session` 
-* `nfs4_sequence` 
-* `nfs4_get_lease_time` 
-* `nfs4_reclaim_comp` 
-* `nfs4_secinfo_no` 
-* `nfs4_bind_conn_to_ses` 
-
-

collectors/nfsMetric.go

@@ -14,29 +14,23 @@ import (
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-// First part contains the code for the general NfsCollector.
-// Later, the general NfsCollector is more limited to Nfs3- and Nfs4Collector.
-
-const NFSSTAT_EXEC = `nfsstat`
-
 type NfsCollectorData struct {
 	current int64
 	last    int64
 }
 
-type nfsCollector struct {
+type NfsCollector struct {
 	metricCollector
 	tags   map[string]string
-	version string
 	config struct {
-		Nfsstats       string   `json:"nfsstat"`
+		Nfsutils       string   `json:"nfsutils"`
 		ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
 	}
-	data map[string]NfsCollectorData
+	data map[string]map[string]NfsCollectorData
 }
 
-func (m *nfsCollector) initStats() error {
-	cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
+func (m *NfsCollector) initStats() error {
+	cmd := exec.Command(m.config.Nfsutils, "-l")
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {
@@ -45,16 +39,17 @@ func (m *nfsCollector) initStats() error {
 			if len(lf) != 5 {
 				continue
 			}
-			if lf[1] == m.version {
+			if _, exist := m.data[lf[1]]; !exist {
+				m.data[lf[1]] = make(map[string]NfsCollectorData)
+			}
 			name := strings.Trim(lf[3], ":")
-				if _, exist := m.data[name]; !exist {
+			if _, exist := m.data[lf[1]][name]; !exist {
 				value, err := strconv.ParseInt(lf[4], 0, 64)
 				if err == nil {
-						x := m.data[name]
+					x := m.data[lf[1]][name]
 					x.current = value
-						x.last = value
-						m.data[name] = x
-					}
+					x.last = 0
+					m.data[lf[1]][name] = x
 				}
 			}
 		}
@@ -62,8 +57,8 @@ func (m *nfsCollector) initStats() error {
 	return err
 }
 
-func (m *nfsCollector) updateStats() error {
-	cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
+func (m *NfsCollector) updateStats() error {
+	cmd := exec.Command(m.config.Nfsutils, "-l")
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {
@@ -72,16 +67,17 @@ func (m *nfsCollector) updateStats() error {
 			if len(lf) != 5 {
 				continue
 			}
-			if lf[1] == m.version {
+			if _, exist := m.data[lf[1]]; !exist {
+				m.data[lf[1]] = make(map[string]NfsCollectorData)
+			}
 			name := strings.Trim(lf[3], ":")
-				if _, exist := m.data[name]; exist {
+			if _, exist := m.data[lf[1]][name]; exist {
 				value, err := strconv.ParseInt(lf[4], 0, 64)
 				if err == nil {
-						x := m.data[name]
+					x := m.data[lf[1]][name]
 					x.last = x.current
 					x.current = value
-						m.data[name] = x
-					}
+					m.data[lf[1]][name] = x
 				}
 			}
 		}
@@ -89,11 +85,17 @@ func (m *nfsCollector) updateStats() error {
 	return err
 }
 
-func (m *nfsCollector) MainInit(config json.RawMessage) error {
-	m.config.Nfsstats = string(NFSSTAT_EXEC)
+func (m *NfsCollector) Init(config json.RawMessage) error {
+	var err error
+	m.name = "NfsCollector"
+	m.setup()
+
+	// Set default mmpmon binary
+	m.config.Nfsutils = "/usr/sbin/nfsstat"
+
 	// Read JSON configuration
 	if len(config) > 0 {
-		err := json.Unmarshal(config, &m.config)
+		err = json.Unmarshal(config, &m.config)
 		if err != nil {
 			log.Print(err.Error())
 			return err
@@ -106,70 +108,40 @@ func (m *nfsCollector) MainInit(config json.RawMessage) error {
 	m.tags = map[string]string{
 		"type": "node",
 	}
-	// Check if nfsstat is in executable search path
-	_, err := exec.LookPath(m.config.Nfsstats)
+	// Check if mmpmon is in executable search path
+	_, err = exec.LookPath(m.config.Nfsutils)
 	if err != nil {
-		return fmt.Errorf("NfsCollector.Init(): Failed to find nfsstat binary '%s': %v", m.config.Nfsstats, err)
+		return fmt.Errorf("NfsCollector.Init(): Failed to find nfsstat binary '%s': %v", m.config.Nfsutils, err)
 	}
-	m.data = make(map[string]NfsCollectorData)
+	m.data = make(map[string]map[string]NfsCollectorData)
 	m.initStats()
 	m.init = true
-	m.parallel = true
 	return nil
 }
 
-func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *NfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
 	timestamp := time.Now()
 
 	m.updateStats()
-	prefix := ""
-	switch m.version {
-	case "v3":
-		prefix = "nfs3"
-	case "v4":
-		prefix = "nfs4"
-	default:
-		prefix = "nfs"
-	}
 
-	for name, data := range m.data {
+	for version, metrics := range m.data {
+		for name, data := range metrics {
 			if _, skip := stringArrayContains(m.config.ExcludeMetrics, name); skip {
 				continue
 			}
 			value := data.current - data.last
-		y, err := lp.New(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New(fmt.Sprintf("nfs_%s", name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
-			y.AddMeta("version", m.version)
+				y.AddMeta("version", version)
 				output <- y
 			}
 		}
 	}
+}
 
-func (m *nfsCollector) Close() {
+func (m *NfsCollector) Close() {
 	m.init = false
 }
-
-type Nfs3Collector struct {
-	nfsCollector
-}
-
-type Nfs4Collector struct {
-	nfsCollector
-}
-
-func (m *Nfs3Collector) Init(config json.RawMessage) error {
-	m.name = "Nfs3Collector"
-	m.version = `v3`
-	m.setup()
-	return m.MainInit(config)
-}
-
-func (m *Nfs4Collector) Init(config json.RawMessage) error {
-	m.name = "Nfs4Collector"
-	m.version = `v4`
-	m.setup()
-	return m.MainInit(config)
-}

collectors/numastatsMetric.go

@@ -1,140 +0,0 @@
-package collectors
-
-import (
-	"bufio"
-	"encoding/json"
-	"fmt"
-	"os"
-	"path/filepath"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-//
-// Numa policy hit/miss statistics
-//
-// numa_hit:
-//   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.
-// numa_foreign:
-//   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.
-// other_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.
-//
-// See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
-//
-type NUMAStatsCollectorTopolgy struct {
-	file   string
-	tagSet map[string]string
-}
-
-type NUMAStatsCollector struct {
-	metricCollector
-	topology []NUMAStatsCollectorTopolgy
-}
-
-func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
-	m.name = "NUMAStatsCollector"
-	m.parallel = true
-	m.setup()
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "NUMA",
-	}
-
-	// Loop for all NUMA node directories
-	base := "/sys/devices/system/node/node"
-	globPattern := base + "[0-9]*"
-	dirs, err := filepath.Glob(globPattern)
-	if err != nil {
-		return fmt.Errorf("unable to glob files with pattern '%s'", globPattern)
-	}
-	if dirs == nil {
-		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
-	}
-	m.topology = make([]NUMAStatsCollectorTopolgy, 0, len(dirs))
-	for _, dir := range dirs {
-		node := strings.TrimPrefix(dir, base)
-		file := filepath.Join(dir, "numastat")
-		m.topology = append(m.topology,
-			NUMAStatsCollectorTopolgy{
-				file:   file,
-				tagSet: map[string]string{"memoryDomain": node},
-			})
-	}
-
-	m.init = true
-	return nil
-}
-
-func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-
-	for i := range m.topology {
-		// Loop for all NUMA domains
-		t := &m.topology[i]
-
-		now := time.Now()
-		file, err := os.Open(t.file)
-		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to open file '%s': %v", t.file, err))
-			return
-		}
-		scanner := bufio.NewScanner(file)
-
-		// Read line by line
-		for scanner.Scan() {
-			split := strings.Fields(scanner.Text())
-			if len(split) != 2 {
-				continue
-			}
-			key := split[0]
-			value, err := strconv.ParseInt(split[1], 10, 64)
-			if err != nil {
-				cclog.ComponentError(
-					m.name,
-					fmt.Sprintf("Read(): Failed to convert %s='%s' to int64: %v", key, split[1], err))
-				continue
-			}
-			y, err := lp.New(
-				"numastats_"+key,
-				t.tagSet,
-				m.meta,
-				map[string]interface{}{"value": value},
-				now,
-			)
-			if err == nil {
-				output <- y
-			}
-		}
-
-		file.Close()
-	}
-}
-
-func (m *NUMAStatsCollector) Close() {
-	m.init = false
-}

collectors/numastatsMetric.md

@@ -1,15 +0,0 @@
-
-## `numastat` collector
-```json
-  "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
-
-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.

collectors/nvidiaMetric.md

@@ -4,73 +4,37 @@
 ```json
   "nvidia": {
     "exclude_devices" : [
-      "0","1", "0000000:ff:01.0"
+      "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>`
+

collectors/rocmsmiMetric.go

@@ -1,319 +0,0 @@
-package collectors
-
-import (
-	"encoding/json"
-	"errors"
-	"fmt"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/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
-}

collectors/rocmsmiMetric.md

@@ -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>`. 

collectors/sampleMetric.go

@@ -1,101 +0,0 @@
-package collectors
-
-import (
-	"encoding/json"
-	"time"
-
-	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
-type SampleCollectorConfig struct {
-	Interval string `json:"interval"`
-}
-
-// This contains all variables we need during execution and the variables
-// defined by metricCollector (name, init, ...)
-type SampleCollector struct {
-	metricCollector
-	config SampleTimerCollectorConfig // the configuration structure
-	meta   map[string]string          // default meta information
-	tags   map[string]string          // 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 *SampleCollector) Init(config json.RawMessage) error {
-	var err error = nil
-	// Always set the name early in Init() to use it in cclog.Component* functions
-	m.name = "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 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": "SAMPLE"}
-	// 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)
-	// 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)
-	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
-		}
-	}
-
-	// Set up everything that the collector requires during the Read() execution
-	// Check files required, test execution of some commands, create data structure
-	// for all topological entities (sockets, NUMA domains, ...)
-	// Return some useful error message in case of any failures
-
-	// 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 *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	// Create a sample metric
-	timestamp := time.Now()
-
-	value := 1.0
-	// If you want to measure something for a specific amount of time, use interval
-	// start := readState()
-	// time.Sleep(interval)
-	// stop := readState()
-	// value = (stop - start) / interval.Seconds()
-
-	y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
-	if err == nil {
-		// Send it to output channel
-		output <- y
-	}
-
-}
-
-// Close metric collector: close network connection, close files, close libraries, ...
-// Called once by the collector manager
-func (m *SampleCollector) Close() {
-	// Unset flag
-	m.init = false
-}

collectors/sampleTimerMetric.go

@@ -1,122 +0,0 @@
-package collectors
-
-import (
-	"encoding/json"
-	"sync"
-	"time"
-
-	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
-type SampleTimerCollectorConfig struct {
-	Interval string `json:"interval"`
-}
-
-// This contains all variables we need during execution and the variables
-// defined by metricCollector (name, init, ...)
-type SampleTimerCollector struct {
-	metricCollector
-	wg       sync.WaitGroup             // sync group for management
-	done     chan bool                  // channel for management
-	meta     map[string]string          // default meta information
-	tags     map[string]string          // default tags
-	config   SampleTimerCollectorConfig // the configuration structure
-	interval time.Duration              // the interval parsed from configuration
-	ticker   *time.Ticker               // own timer
-	output   chan lp.CCMetric           // own internal output channel
-}
-
-func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
-	var err error = nil
-	// Always set the name early in Init() to use it in cclog.Component* functions
-	m.name = "SampleTimerCollector"
-	// 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": "SAMPLE"}
-	// 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
-		}
-	}
-	// Parse the read interval duration
-	m.interval, err = time.ParseDuration(m.config.Interval)
-	if err != nil {
-		cclog.ComponentError(m.name, "Error parsing interval:", err.Error())
-		return err
-	}
-
-	// Storage for output channel
-	m.output = nil
-	// Mangement channel for the timer function.
-	m.done = make(chan bool)
-	// Create the own ticker
-	m.ticker = time.NewTicker(m.interval)
-
-	// Start the timer loop with return functionality by sending 'true' to the done channel
-	m.wg.Add(1)
-	go func() {
-		select {
-		case <-m.done:
-			// Exit the timer loop
-			cclog.ComponentDebug(m.name, "Closing...")
-			m.wg.Done()
-			return
-		case timestamp := <-m.ticker.C:
-			// This is executed every timer tick but we have to wait until the first
-			// Read() to get the output channel
-			if m.output != nil {
-				m.ReadMetrics(timestamp)
-			}
-		}
-	}()
-
-	// Set this flag only if everything is initialized properly, all required files exist, ...
-	m.init = true
-	return err
-}
-
-// This function is called at each interval timer tick
-func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
-	// Create a sample metric
-
-	value := 1.0
-
-	// If you want to measure something for a specific amout of time, use interval
-	// start := readState()
-	// time.Sleep(interval)
-	// stop := readState()
-	// value = (stop - start) / interval.Seconds()
-
-	y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
-	if err == nil && m.output != nil {
-		// Send it to output channel if we have a valid channel
-		m.output <- y
-	}
-}
-
-func (m *SampleTimerCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	// Capture output channel
-	m.output = output
-}
-
-func (m *SampleTimerCollector) Close() {
-	// Send signal to the timer loop to stop it
-	m.done <- true
-	// Wait until the timer loop is done
-	m.wg.Wait()
-	// Unset flag
-	m.init = false
-}

collectors/tempMetric.go

@@ -4,232 +4,110 @@ import (
 	"encoding/json"
 	"fmt"
 	"io/ioutil"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-// See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
-// /sys/class/hwmon/hwmon*/name -> coretemp
-// /sys/class/hwmon/hwmon*/temp*_label -> Core 0
-// /sys/class/hwmon/hwmon*/temp*_input -> 27800 = 27.8°C
-// /sys/class/hwmon/hwmon*/temp*_max -> 86000 = 86.0°C
-// /sys/class/hwmon/hwmon*/temp*_crit -> 100000 = 100.0°C
+const HWMON_PATH = `/sys/class/hwmon`
 
-type TempCollectorSensor struct {
-	name         string
-	label        string
-	metricName   string // Default: name_label
-	file         string
-	maxTempName  string
-	maxTemp      int64
-	critTempName string
-	critTemp     int64
-	tags         map[string]string
+type TempCollectorConfig struct {
+	ExcludeMetrics []string                     `json:"exclude_metrics"`
+	TagOverride    map[string]map[string]string `json:"tag_override"`
 }
 
 type TempCollector struct {
 	metricCollector
-	config struct {
-		ExcludeMetrics     []string                     `json:"exclude_metrics"`
-		TagOverride        map[string]map[string]string `json:"tag_override"`
-		ReportMaxTemp      bool                         `json:"report_max_temperature"`
-		ReportCriticalTemp bool                         `json:"report_critical_temperature"`
-	}
-	sensors []*TempCollectorSensor
+	config TempCollectorConfig
 }
 
 func (m *TempCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
 	m.name = "TempCollector"
-	m.parallel = true
 	m.setup()
+	m.meta = map[string]string{"source": m.name, "group": "IPMI", "unit": "degC"}
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "IPMI",
-		"unit":   "degC",
-	}
-
-	m.sensors = make([]*TempCollectorSensor, 0)
-
-	// Find all temperature sensor files
-	globPattern := filepath.Join("/sys/class/hwmon", "*", "temp*_input")
-	inputFiles, err := filepath.Glob(globPattern)
-	if err != nil {
-		return fmt.Errorf("unable to glob files with pattern '%s': %v", globPattern, err)
-	}
-	if inputFiles == nil {
-		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
-	}
-
-	// Get sensor name for each temperature sensor file
-	for _, file := range inputFiles {
-		sensor := new(TempCollectorSensor)
-
-		// sensor name
-		nameFile := filepath.Join(filepath.Dir(file), "name")
-		name, err := ioutil.ReadFile(nameFile)
-		if err == nil {
-			sensor.name = strings.TrimSpace(string(name))
-		}
-
-		// sensor label
-		labelFile := strings.TrimSuffix(file, "_input") + "_label"
-		label, err := ioutil.ReadFile(labelFile)
-		if err == nil {
-			sensor.label = strings.TrimSpace(string(label))
-		}
-
-		// sensor metric name
-		switch {
-		case len(sensor.name) == 0 && len(sensor.label) == 0:
-			continue
-		case sensor.name == "coretemp" && strings.HasPrefix(sensor.label, "Core ") ||
-			sensor.name == "coretemp" && strings.HasPrefix(sensor.label, "Package id "):
-			sensor.metricName = "temp_" + sensor.label
-		case len(sensor.name) != 0 && len(sensor.label) != 0:
-			sensor.metricName = sensor.name + "_" + sensor.label
-		case len(sensor.name) != 0:
-			sensor.metricName = sensor.name
-		case len(sensor.label) != 0:
-			sensor.metricName = sensor.label
-		}
-		sensor.metricName = strings.ToLower(sensor.metricName)
-		sensor.metricName = strings.Replace(sensor.metricName, " ", "_", -1)
-		// Add temperature prefix, if required
-		if !strings.Contains(sensor.metricName, "temp") {
-			sensor.metricName = "temp_" + sensor.metricName
-		}
-
-		// Sensor file
-		_, err = ioutil.ReadFile(file)
-		if err != nil {
-			continue
-		}
-		sensor.file = file
-
-		// Sensor tags
-		sensor.tags = map[string]string{
-			"type": "node",
-		}
-
-		// Apply tag override configuration
-		for key, newtags := range m.config.TagOverride {
-			if strings.Contains(sensor.file, key) {
-				sensor.tags = newtags
-				break
-			}
-		}
-
-		// max temperature
-		if m.config.ReportMaxTemp {
-			maxTempFile := strings.TrimSuffix(file, "_input") + "_max"
-			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
-				}
-			}
-		}
-
-		// critical temperature
-		if m.config.ReportCriticalTemp {
-			criticalTempFile := strings.TrimSuffix(file, "_input") + "_crit"
-			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
-				}
-			}
-		}
-
-		m.sensors = append(m.sensors, sensor)
-	}
-
-	// Empty sensors map
-	if len(m.sensors) == 0 {
-		return fmt.Errorf("no temperature sensors found")
-	}
-
-	// Finished initialization
 	m.init = true
 	return nil
 }
 
+func get_hwmon_sensors() (map[string]map[string]string, error) {
+	var folders []string
+	var sensors map[string]map[string]string
+	sensors = make(map[string]map[string]string)
+	err := filepath.Walk(HWMON_PATH, func(p string, info os.FileInfo, err error) error {
+		if info.IsDir() {
+			return nil
+		}
+		folders = append(folders, p)
+		return nil
+	})
+	if err != nil {
+		return sensors, err
+	}
+
+	for _, f := range folders {
+		sensors[f] = make(map[string]string)
+		myp := fmt.Sprintf("%s/", f)
+		err := filepath.Walk(myp, func(path string, info os.FileInfo, err error) error {
+			dir, fname := filepath.Split(path)
+			if strings.Contains(fname, "temp") && strings.Contains(fname, "_input") {
+				namefile := fmt.Sprintf("%s/%s", dir, strings.Replace(fname, "_input", "_label", -1))
+				name, ierr := ioutil.ReadFile(namefile)
+				if ierr == nil {
+					sensors[f][strings.Replace(string(name), "\n", "", -1)] = path
+				}
+			}
+			return nil
+		})
+		if err != nil {
+			continue
+		}
+	}
+	return sensors, nil
+}
+
 func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
-	for _, sensor := range m.sensors {
-		// Read sensor file
-		buffer, err := ioutil.ReadFile(sensor.file)
+	sensors, err := get_hwmon_sensors()
+	if err != nil {
+		return
+	}
+	for _, files := range sensors {
+		for name, file := range files {
+			tags := map[string]string{"type": "node"}
+			for key, newtags := range m.config.TagOverride {
+				if strings.Contains(file, key) {
+					tags = newtags
+					break
+				}
+			}
+			mname := strings.Replace(name, " ", "_", -1)
+			if !strings.Contains(mname, "temp") {
+				mname = fmt.Sprintf("temp_%s", mname)
+			}
+			buffer, err := ioutil.ReadFile(string(file))
 			if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to read file '%s': %v", sensor.file, err))
 				continue
 			}
-		x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64)
-		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to convert temperature '%s' to int64: %v", buffer, err))
-			continue
-		}
-		x /= 1000
-		y, err := lp.New(
-			sensor.metricName,
-			sensor.tags,
-			m.meta,
-			map[string]interface{}{"value": x},
-			time.Now(),
-		)
+			x, err := strconv.ParseInt(strings.Replace(string(buffer), "\n", "", -1), 0, 64)
 			if err == nil {
-			output <- y
-		}
-
-		// max temperature
-		if m.config.ReportMaxTemp && sensor.maxTemp != 0 {
-			y, err := lp.New(
-				sensor.maxTempName,
-				sensor.tags,
-				m.meta,
-				map[string]interface{}{"value": sensor.maxTemp},
-				time.Now(),
-			)
-			if err == nil {
-				output <- y
-			}
-		}
-
-		// critical temperature
-		if m.config.ReportCriticalTemp && sensor.critTemp != 0 {
-			y, err := lp.New(
-				sensor.critTempName,
-				sensor.tags,
-				m.meta,
-				map[string]interface{}{"value": sensor.critTemp},
-				time.Now(),
-			)
+				y, err := lp.New(strings.ToLower(mname), tags, m.meta, map[string]interface{}{"value": int(float64(x) / 1000)}, time.Now())
 				if err == nil {
+					cclog.ComponentDebug(m.name, y)
 					output <- y
 				}
 			}
 		}
-
+	}
 }
 
 func (m *TempCollector) Close() {

collectors/topprocsMetric.go

@@ -8,7 +8,6 @@ import (
 	"os/exec"
 	"strings"
 	"time"
-
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
@@ -28,7 +27,6 @@ type TopProcsCollector struct {
 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 {
@@ -40,14 +38,14 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
 		m.config.Num_procs = int(DEFAULT_NUM_PROCS)
 	}
 	if m.config.Num_procs <= 0 || m.config.Num_procs > MAX_NUM_PROCS {
-		return fmt.Errorf("num_procs option must be set in 'topprocs' config (range: 1-%d)", MAX_NUM_PROCS)
+		return errors.New(fmt.Sprintf("num_procs option must be set in 'topprocs' config (range: 1-%d)", MAX_NUM_PROCS))
 	}
 	m.setup()
 	command := exec.Command("ps", "-Ao", "comm", "--sort=-pcpu")
 	command.Wait()
 	_, err = command.Output()
 	if err != nil {
-		return errors.New("failed to execute command")
+		return errors.New("Failed to execute command")
 	}
 	m.init = true
 	return nil

config.json

@@ -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
 }

docs/configuration.md

@@ -1,189 +0,0 @@
-# Configuring the CC metric collector
-
-The configuration of the CC metric collector consists of five configuration files: one global file and four component related files.
-
-## Global configuration
-
-The global file contains the paths to the other four files and some global options. 
-
-```json
-{
-  "sinks": "sinks.json",
-  "collectors" : "collectors.json",
-  "receivers" : "receivers.json",
-  "router" : "router.json",
-  "interval": 10,
-  "duration": 1
-}
-```
-
-Be aware that the paths are relative to the execution folder of the cc-metric-collector binary, so it is recommended to use absolute paths.
-
-## Component configuration
-
-The others are mainly list of of subcomponents: the collectors, the receivers, the router and the sinks. Their role is best shown in a picture:
-
-```mermaid
-flowchart LR
-
-  subgraph col ["Collectors"]
-  direction TB
-  cpustat["cpustat"]
-  memstat["memstat"]
-  tempstat["tempstat"]
-  misc["..."]
-  end
-  
-  subgraph Receivers ["Receivers"]
-  direction TB
-  nats["NATS"]
-  httprecv["HTTP"]
-  miscrecv[...]
-  end
-
-  subgraph calc["Aggregator"]
-  direction LR
-  cache["Cache"]
-  agg["Calculator"]
-  end
-
-  subgraph sinks ["Sinks"]
-  direction RL
-  influx["InfluxDB"]
-  ganglia["Ganglia"]
-  logger["Logfile"]
-  miscsink["..."]
-  end
-
-  cpustat --> CollectorManager["CollectorManager"]
-  memstat --> CollectorManager
-  tempstat --> CollectorManager
-  misc --> CollectorManager
-
-  nats  --> ReceiverManager["ReceiverManager"]
-  httprecv --> ReceiverManager
-  miscrecv --> ReceiverManager
-
-  CollectorManager --> newrouter["Router"]
-  ReceiverManager -.-> newrouter
-  calc -.-> newrouter
-  newrouter --> SinkManager["SinkManager"]
-  newrouter -.-> calc
-
-  SinkManager --> influx
-  SinkManager --> ganglia
-  SinkManager --> logger
-  SinkManager --> miscsink
-
-
-```
-
-There are four parts:
-- The collectors read data from files, execute commands and call dynamically loaded library function and send it to the router
-- The router can process metrics by cacheing and evaluating functions and conditions on them
-- The sinks send the metrics to storage backends
-- The receivers can be used to receive metrics from other collectors and forward them to the router. They can be used to create a tree-like structure of collectors.
-
-(A maybe better differentiation between collectors and receivers is that the collectors are called periodically while the receivers have their own logic and submit metrics at any time)
-
-
-### Collectors configuration file
-
-The collectors configuration file tells which metrics should be queried from the system. The metric gathering is logically grouped in so called 'Collectors'. So there are Collectors to read CPU, memory or filesystem statistics. The collectors configuration file is a list of these collectors with collector-specific configurations:
-
-```json
-{
-  "cpustat" : {},
-  "diskstat": {
-    "exclude_metrics": [
-      "disk_total"
-    ]
-  }
-}
-```
-
-The first one is the CPU statistics collector without any collector-specific setting. The second one enables disk mount statistics but excludes the metric `disk_total`.
-
-All names and possible collector-specific configuration options can be found [here](../collectors/README.md).
-
-Some collectors might dynamically load shared libraries. In order to enable these collectors, make sure that the shared library path is part of the `LD_LIBRARY_PATH` environment variable.
-
-### Sinks configuration file
-
-The sinks define the output/sending of metrics. The metrics can be forwarded to multiple sinks, even to sinks of the same type. The sinks configuration file is a list of these sinks, each with an individual name.
-
-```json
-{
-  "myinflux" : {
-    "type" : "influxasync",
-    "host": "localhost",
-    "port": "8086",
-    "organization" : "testorga",
-    "database" : "testbucket",
-    "password" : "<my secret JWT>"
-  },
-  "companyinflux" : {
-    "type" : "influxasync",
-    "host": "companyhost",
-    "port": "8086",
-    "organization" : "company",
-    "database" : "main",
-    "password" : "<company's secret JWT>"
-  }
-}
-```
-
-The above example configuration file defines two sink, both ot type `influxasync`. They are differentiated internally by the names: `myinflux` and `companyinflux`.
-
-All types and possible sink-specific configuration options can be found [here](../sinks/README.md).
-
-Some sinks might dynamically load shared libraries. In order to enable these sinks, make sure that the shared library path is part of the `LD_LIBRARY_PATH` environment variable.
-
-### Router configuration file
-
-The collectors and the sinks are connected through the router. The router forwards the metrics to the sinks but enables some data processing. A common example is to tag all passing metrics like adding `cluster=mycluster`. But also aggregations like "take the average of all 'ipc' metrics" (ipc -> Instructions Per Cycle). Since the configurations of these aggregations can be quite complicated, we refer to the router's [README](../internal/metricRouter/README.md).
-
-A simple router configuration file to start with looks like this:
-
-```json
-{
-    "add_tags" : [
-        {
-            "key" : "cluster",
-            "value" : "mycluster",
-            "if" : "*"
-        }
-    ],
-    "interval_timestamp" : false,
-    "num_cache_intervals" : 0
-}
-```
-
-With the `add_tags` section, we tell to attach the `cluster=mycluster` tag to each (`*` metric). The `interval_timestamp` tell the router to not touch the timestamp of metrics. It is possible to send all metrics within an interval with a common time stamp to avoid later alignment issues. The `num_cache_intervals` diables the cache completely. The cache is only required if you want to do complex metric aggregations.
-
-All configuration options can be found [here](../internal/metricRouter/README.md).
-
-### Receivers configuration file
-
-The receivers are a special feature of the CC Metric Collector to enable simpler integration into exising setups. While collectors query data from the local system, the receivers commonly get data from other systems through some network technology like HTTP or NATS. The idea is keep the current setup but send it to a CC Metric Collector which forwards it to the the destination system (if a sink exists for it). For most setups, the receivers are not required and an the receiver config file should contain only an empty JSON map (`{}`). 
-
-```json
-{
-  "nats_rack0": {
-    "type": "nats",
-    "address" : "nats-server.example.org",
-    "port" : "4222",
-    "subject" : "rack0",
-  },
-  "nats_rack1": {
-    "type": "nats",
-    "address" : "nats-server.example.org",
-    "port" : "4222",
-    "subject" : "rack1",
-  }
-}
-```
-
-This example configuration creates two receivers with the names `nats_rack0` and `nats_rack1`. While one subscribes to metrics published with the `rack0` subject, the other one subscribes to the `rack0` subject. The NATS server is the same as it manages all subjects in a subnet. (As example, the router could add tags `rack=0` and `rack=1` respectively to the received metrics.)
-
-All types and possible receiver-specific configuration options can be found [here](../receivers/README.md).

go.mod

@@ -1,35 +1,20 @@
 module github.com/ClusterCockpit/cc-metric-collector
 
-go 1.17
+go 1.16
 
 require (
-	github.com/ClusterCockpit/cc-units v0.0.0-20220318130935-92a0c6442220
-	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/PaesslerAG/gval v1.1.2
-	github.com/gorilla/mux v1.8.0
-	github.com/influxdata/influxdb-client-go/v2 v2.8.1
+	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/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.13.0
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
+	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/beorn7/perks v1.0.1 // indirect
-	github.com/cespare/xxhash/v2 v2.1.2 // indirect
-	github.com/deepmap/oapi-codegen v1.8.2 // indirect
+	github.com/PaesslerAG/gval v1.1.2
 	github.com/golang/protobuf v1.5.2 // indirect
-	github.com/matttproud/golang_protobuf_extensions v1.0.1 // indirect
-	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nkeys v0.3.0 // indirect
-	github.com/nats-io/nuid v1.0.1 // indirect
-	github.com/pkg/errors v0.9.1 // indirect
-	github.com/prometheus/client_model v0.2.0 // indirect
-	github.com/prometheus/common v0.32.1 // indirect
-	github.com/prometheus/procfs v0.7.3 // indirect
-	golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce // indirect
-	golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2 // indirect
-	google.golang.org/protobuf v1.26.0 // indirect
-	gopkg.in/yaml.v2 v2.4.0 // indirect
+	github.com/mattn/go-sqlite3 v1.14.11
+	github.com/nats-io/nats-server/v2 v2.7.0 // indirect
+	google.golang.org/protobuf v1.27.1 // indirect
 )

go.mod.1.16

@@ -1,16 +0,0 @@
-module github.com/ClusterCockpit/cc-metric-collector
-
-go 1.16
-
-require (
-	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/PaesslerAG/gval v1.1.2
-	github.com/gorilla/mux v1.8.0
-	github.com/influxdata/influxdb-client-go/v2 v2.7.0
-	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.13.0
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
-)

go.mod.1.17+

@@ -1,16 +0,0 @@
-module github.com/ClusterCockpit/cc-metric-collector
-
-go 1.17
-
-require (
-	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/PaesslerAG/gval v1.1.2
-	github.com/gorilla/mux v1.8.0
-	github.com/influxdata/influxdb-client-go/v2 v2.8.1
-	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.13.0
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
-)

go.sum

@@ -54,6 +54,8 @@ github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope
 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/mattn/go-sqlite3 v1.14.11 h1:gt+cp9c0XGqe9S/wAHTL3n/7MqY+siPWgWJgqdsFrzQ=
+github.com/mattn/go-sqlite3 v1.14.11/go.mod h1:NyWgC/yNuGj7Q9rpYnZvas74GogHl5/Z4A/KQRfk6bU=
 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=

internal/ccMetric/ccMetric.go

@@ -2,187 +2,239 @@ package ccmetric
 
 import (
 	"fmt"
+	"sort"
 	"time"
 
-	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
-	write "github.com/influxdata/influxdb-client-go/v2/api/write"
 	lp "github.com/influxdata/line-protocol" // MIT license
 )
 
 // Most functions are derived from github.com/influxdata/line-protocol/metric.go
 // The metric type is extended with an extra meta information list re-using the Tag
 // type.
-//
-// See: https://docs.influxdata.com/influxdb/latest/reference/syntax/line-protocol/
+
 type ccMetric struct {
-	name   string                 // Measurement name
-	meta   map[string]string      // map of meta data tags
-	tags   map[string]string      // map of of tags
-	fields map[string]interface{} // map of of fields
-	tm     time.Time              // timestamp
+	name   string
+	tags   []*lp.Tag
+	fields []*lp.Field
+	tm     time.Time
+	meta   []*lp.Tag
 }
 
-// ccMetric access functions
 type CCMetric interface {
-	ToPoint(metaAsTags map[string]bool) *write.Point  // Generate influxDB point for data type ccMetric
-	ToLineProtocol(metaAsTags map[string]bool) string // Generate influxDB line protocol for data type ccMetric
-
-	Name() string        // Get metric name
-	SetName(name string) // Set metric name
-
-	Time() time.Time     // Get timestamp
-	SetTime(t time.Time) // Set timestamp
-
-	Tags() map[string]string                   // Map of tags
-	AddTag(key, value string)                  // Add a tag
-	GetTag(key string) (value string, ok bool) // Get a tag by its key
-	HasTag(key string) (ok bool)               // Check if a tag key is present
-	RemoveTag(key string)                      // Remove a tag by its key
-
-	Meta() map[string]string                    // Map of meta data tags
-	AddMeta(key, value string)                  // Add a meta data tag
-	GetMeta(key string) (value string, ok bool) // Get a meta data tab addressed by its key
-	HasMeta(key string) (ok bool)               // Check if a meta data key is present
-	RemoveMeta(key string)                      // Remove a meta data tag by its key
-
-	Fields() map[string]interface{}                   // Map of fields
-	AddField(key string, value interface{})           // Add a field
-	GetField(key string) (value interface{}, ok bool) // Get a field addressed by its key
-	HasField(key string) (ok bool)                    // Check if a field key is present
-	RemoveField(key string)                           // Remove a field addressed by its key
+	lp.MutableMetric
+	Name() string
+	AddTag(key, value string)
+	GetTag(key string) (string, bool)
+	HasTag(key string) bool
+	RemoveTag(key string)
+	Tags() map[string]string
+	TagList() []*lp.Tag
+	AddMeta(key, value string)
+	GetMeta(key string) (string, bool)
+	HasMeta(key string) bool
+	RemoveMeta(key string)
+	Meta() map[string]string
+	MetaList() []*lp.Tag
+	AddField(key string, value interface{})
+	GetField(key string) (interface{}, bool)
+	HasField(key string) bool
+	RemoveField(key string)
+	Fields() map[string]interface{}
+	FieldList() []*lp.Field
+	String() string
+	SetTime(t time.Time)
+}
+
+func (m *ccMetric) Meta() map[string]string {
+	meta := make(map[string]string, len(m.meta))
+	for _, m := range m.meta {
+		meta[m.Key] = m.Value
+	}
+	return meta
+}
+
+func (m *ccMetric) MetaList() []*lp.Tag {
+	return m.meta
 }
 
-// String implements the stringer interface for data type ccMetric
 func (m *ccMetric) String() string {
-	return fmt.Sprintf(
-		"Name: %s, Tags: %+v, Meta: %+v, fields: %+v, Timestamp: %d",
-		m.name, m.tags, m.meta, m.fields, m.tm.UnixNano(),
-	)
+	return fmt.Sprintf("%s %v %v %v %d", m.name, m.Tags(), m.Meta(), m.Fields(), m.tm.UnixNano())
 }
 
-// ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToPoint(metaAsTags map[string]bool) (p *write.Point) {
-	p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
-	for key, ok1 := range metaAsTags {
-		if val, ok2 := m.GetMeta(key); ok1 && ok2 {
-			p.AddTag(key, val)
-		}
-	}
-	return p
-}
-
-// ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToLineProtocol(metaAsTags map[string]bool) string {
-
-	return write.PointToLineProtocol(
-		m.ToPoint(metaAsTags),
-		time.Nanosecond,
-	)
-}
-
-// Name returns the measurement name
 func (m *ccMetric) Name() string {
 	return m.name
 }
 
-// SetName sets the measurement name
-func (m *ccMetric) SetName(name string) {
-	m.name = name
+func (m *ccMetric) Tags() map[string]string {
+	tags := make(map[string]string, len(m.tags))
+	for _, tag := range m.tags {
+		tags[tag.Key] = tag.Value
+	}
+	return tags
+}
+
+func (m *ccMetric) TagList() []*lp.Tag {
+	return m.tags
+}
+
+func (m *ccMetric) Fields() map[string]interface{} {
+	fields := make(map[string]interface{}, len(m.fields))
+	for _, field := range m.fields {
+		fields[field.Key] = field.Value
+	}
+
+	return fields
+}
+
+func (m *ccMetric) FieldList() []*lp.Field {
+	return m.fields
 }
 
-// Time returns timestamp
 func (m *ccMetric) Time() time.Time {
 	return m.tm
 }
 
-// SetTime sets the timestamp
 func (m *ccMetric) SetTime(t time.Time) {
 	m.tm = t
 }
 
-// Tags returns the the list of tags as key-value-mapping
-func (m *ccMetric) Tags() map[string]string {
-	return m.tags
-}
-
-// AddTag adds a tag (consisting of key and value) to the map of tags
-func (m *ccMetric) AddTag(key, value string) {
-	m.tags[key] = value
-}
-
-// GetTag returns the tag with tag's key equal to <key>
-func (m *ccMetric) GetTag(key string) (string, bool) {
-	value, ok := m.tags[key]
-	return value, ok
-}
-
-// HasTag checks if a tag with key equal to <key> is present in the list of tags
 func (m *ccMetric) HasTag(key string) bool {
-	_, ok := m.tags[key]
-	return ok
+	for _, tag := range m.tags {
+		if tag.Key == key {
+			return true
+		}
+	}
+	return false
+}
+
+func (m *ccMetric) GetTag(key string) (string, bool) {
+	for _, tag := range m.tags {
+		if tag.Key == key {
+			return tag.Value, true
+		}
+	}
+	return "", false
 }
 
-// RemoveTag removes the tag with tag's key equal to <key>
 func (m *ccMetric) RemoveTag(key string) {
-	delete(m.tags, key)
+	for i, tag := range m.tags {
+		if tag.Key == key {
+			copy(m.tags[i:], m.tags[i+1:])
+			m.tags[len(m.tags)-1] = nil
+			m.tags = m.tags[:len(m.tags)-1]
+			return
+		}
+	}
 }
 
-// Meta returns the meta data tags as key-value mapping
-func (m *ccMetric) Meta() map[string]string {
-	return m.meta
+func (m *ccMetric) AddTag(key, value string) {
+	for i, tag := range m.tags {
+		if key > tag.Key {
+			continue
 		}
 
-// AddMeta adds a meta data tag (consisting of key and value) to the map of meta data tags
-func (m *ccMetric) AddMeta(key, value string) {
-	m.meta[key] = value
+		if key == tag.Key {
+			tag.Value = value
+			return
 		}
 
-// GetMeta returns the meta data tag with meta data's key equal to <key>
-func (m *ccMetric) GetMeta(key string) (string, bool) {
-	value, ok := m.meta[key]
-	return value, ok
+		m.tags = append(m.tags, nil)
+		copy(m.tags[i+1:], m.tags[i:])
+		m.tags[i] = &lp.Tag{Key: key, Value: value}
+		return
+	}
+
+	m.tags = append(m.tags, &lp.Tag{Key: key, Value: value})
 }
 
-// HasMeta checks if a meta data tag with meta data's key equal to <key> is present in the map of meta data tags
 func (m *ccMetric) HasMeta(key string) bool {
-	_, ok := m.meta[key]
-	return ok
+	for _, tag := range m.meta {
+		if tag.Key == key {
+			return true
+		}
+	}
+	return false
+}
+
+func (m *ccMetric) GetMeta(key string) (string, bool) {
+	for _, tag := range m.meta {
+		if tag.Key == key {
+			return tag.Value, true
+		}
+	}
+	return "", false
 }
 
-// RemoveMeta removes the meta data tag with tag's key equal to <key>
 func (m *ccMetric) RemoveMeta(key string) {
-	delete(m.meta, key)
+	for i, tag := range m.meta {
+		if tag.Key == key {
+			copy(m.meta[i:], m.meta[i+1:])
+			m.meta[len(m.meta)-1] = nil
+			m.meta = m.meta[:len(m.meta)-1]
+			return
+		}
+	}
 }
 
-// Fields returns the list of fields as key-value-mapping
-func (m *ccMetric) Fields() map[string]interface{} {
-	return m.fields
+func (m *ccMetric) AddMeta(key, value string) {
+	for i, tag := range m.meta {
+		if key > tag.Key {
+			continue
+		}
+
+		if key == tag.Key {
+			tag.Value = value
+			return
+		}
+
+		m.meta = append(m.meta, nil)
+		copy(m.meta[i+1:], m.meta[i:])
+		m.meta[i] = &lp.Tag{Key: key, Value: value}
+		return
+	}
+
+	m.meta = append(m.meta, &lp.Tag{Key: key, Value: value})
 }
 
-// AddField adds a field (consisting of key and value) to the map of fields
 func (m *ccMetric) AddField(key string, value interface{}) {
-	m.fields[key] = value
+	for i, field := range m.fields {
+		if key == field.Key {
+			m.fields[i] = &lp.Field{Key: key, Value: convertField(value)}
+			return
+		}
+	}
+	m.fields = append(m.fields, &lp.Field{Key: key, Value: convertField(value)})
 }
 
-// GetField returns the field with field's key equal to <key>
 func (m *ccMetric) GetField(key string) (interface{}, bool) {
-	v, ok := m.fields[key]
-	return v, ok
+	for _, field := range m.fields {
+		if field.Key == key {
+			return field.Value, true
+		}
+	}
+	return "", false
 }
 
-// HasField checks if a field with field's key equal to <key> is present in the map of fields
 func (m *ccMetric) HasField(key string) bool {
-	_, ok := m.fields[key]
-	return ok
+	for _, field := range m.fields {
+		if field.Key == key {
+			return true
+		}
+	}
+	return false
 }
 
-// RemoveField removes the field with field's key equal to <key>
-// from the map of fields
 func (m *ccMetric) RemoveField(key string) {
-	delete(m.fields, key)
+	for i, field := range m.fields {
+		if field.Key == key {
+			copy(m.fields[i:], m.fields[i+1:])
+			m.fields[len(m.fields)-1] = nil
+			m.fields = m.fields[:len(m.fields)-1]
+			return
+		}
+	}
 }
 
-// New creates a new measurement point
 func New(
 	name string,
 	tags map[string]string,
@@ -192,79 +244,85 @@ func New(
 ) (CCMetric, error) {
 	m := &ccMetric{
 		name:   name,
-		tags:   make(map[string]string, len(tags)),
-		meta:   make(map[string]string, len(meta)),
-		fields: make(map[string]interface{}, len(fields)),
+		tags:   nil,
+		fields: nil,
 		tm:     tm,
+		meta:   nil,
 	}
 
-	// deep copy tags, meta data tags and fields
+	if len(tags) > 0 {
+		m.tags = make([]*lp.Tag, 0, len(tags))
 		for k, v := range tags {
-		m.tags[k] = v
+			m.tags = append(m.tags,
+				&lp.Tag{Key: k, Value: v})
 		}
+		sort.Slice(m.tags, func(i, j int) bool { return m.tags[i].Key < m.tags[j].Key })
+	}
+
+	if len(meta) > 0 {
+		m.meta = make([]*lp.Tag, 0, len(meta))
 		for k, v := range meta {
-		m.meta[k] = v
+			m.meta = append(m.meta,
+				&lp.Tag{Key: k, Value: v})
 		}
+		sort.Slice(m.meta, func(i, j int) bool { return m.meta[i].Key < m.meta[j].Key })
+	}
+
+	if len(fields) > 0 {
+		m.fields = make([]*lp.Field, 0, len(fields))
 		for k, v := range fields {
 			v := convertField(v)
 			if v == nil {
 				continue
 			}
-		m.fields[k] = v
+			m.AddField(k, v)
+		}
 	}
 
 	return m, nil
 }
 
-// FromMetric copies the metric <other>
-func FromMetric(other ccMetric) CCMetric {
+func FromMetric(other CCMetric) CCMetric {
 	m := &ccMetric{
 		name:   other.Name(),
-		tags:   make(map[string]string, len(other.tags)),
-		meta:   make(map[string]string, len(other.meta)),
-		fields: make(map[string]interface{}, len(other.fields)),
+		tags:   make([]*lp.Tag, len(other.TagList())),
+		fields: make([]*lp.Field, len(other.FieldList())),
+		meta:   make([]*lp.Tag, len(other.MetaList())),
 		tm:     other.Time(),
 	}
 
-	// deep copy tags, meta data tags and fields
-	for key, value := range other.tags {
-		m.tags[key] = value
+	for i, tag := range other.TagList() {
+		m.tags[i] = &lp.Tag{Key: tag.Key, Value: tag.Value}
 	}
-	for key, value := range other.meta {
-		m.meta[key] = value
+	for i, s := range other.MetaList() {
+		m.meta[i] = &lp.Tag{Key: s.Key, Value: s.Value}
 	}
-	for key, value := range other.fields {
-		m.fields[key] = value
+
+	for i, field := range other.FieldList() {
+		m.fields[i] = &lp.Field{Key: field.Key, Value: field.Value}
 	}
 	return m
 }
 
-// FromInfluxMetric copies the influxDB line protocol metric <other>
 func FromInfluxMetric(other lp.Metric) CCMetric {
 	m := &ccMetric{
 		name:   other.Name(),
-		tags:   make(map[string]string),
-		meta:   make(map[string]string),
-		fields: make(map[string]interface{}),
+		tags:   make([]*lp.Tag, len(other.TagList())),
+		fields: make([]*lp.Field, len(other.FieldList())),
+		meta:   make([]*lp.Tag, 0),
 		tm:     other.Time(),
 	}
 
-	// deep copy tags and fields
-	for _, otherTag := range other.TagList() {
-		m.tags[otherTag.Key] = otherTag.Value
+	for i, tag := range other.TagList() {
+		m.tags[i] = &lp.Tag{Key: tag.Key, Value: tag.Value}
 	}
-	for _, otherField := range other.FieldList() {
-		m.fields[otherField.Key] = otherField.Value
+
+	for i, field := range other.FieldList() {
+		m.fields[i] = &lp.Field{Key: field.Key, Value: field.Value}
 	}
 	return m
 }
 
-// convertField converts data types of fields by the following schemata:
-//                         *float32, *float64,                      float32, float64 -> float64
-//  *int,  *int8,  *int16,   *int32,   *int64,  int,  int8,  int16,   int32,   int64 ->   int64
-// *uint, *uint8, *uint16,  *uint32,  *uint64, uint, uint8, uint16,  uint32,  uint64 ->  uint64
-// *[]byte, *string,                           []byte, string                        -> string
-// *bool,                                      bool                                  -> bool
 func convertField(v interface{}) interface{} {
 	switch v := v.(type) {
 	case float64:

internal/ccTopology/ccTopology.go

@@ -6,17 +6,12 @@ import (
 	"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
@@ -29,34 +24,26 @@ func intArrayContains(array []int, str int) (int, bool) {
 	return -1, false
 }
 
-// Used internally for sysfs file reads
-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)
-}
+// stringArrayContains scans an array of strings 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 stringArrayContains(array []string, str string) (int, bool) {
+// 	for i, a := range array {
+// 		if a == str {
+// 			return i, true
+// 		}
+// 	}
+// 	return -1, false
+// }
 
-// Get list of CPU socket IDs
 func SocketList() []int {
-	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
+	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
 	if err != nil {
 		log.Print(err)
 		return nil
 	}
 	ll := strings.Split(string(buffer), "\n")
-	packs := make([]int, 0)
+	var packs []int
 	for _, line := range ll {
 		if strings.HasPrefix(line, "physical id") {
 			lv := strings.Fields(line)
@@ -74,15 +61,14 @@ func SocketList() []int {
 	return packs
 }
 
-// Get list of hardware thread IDs in the order of listing in /proc/cpuinfo
-func HwthreadList() []int {
-	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
+func CpuList() []int {
+	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
 	if err != nil {
 		log.Print(err)
 		return nil
 	}
 	ll := strings.Split(string(buffer), "\n")
-	cpulist := make([]int, 0)
+	var cpulist []int
 	for _, line := range ll {
 		if strings.HasPrefix(line, "processor") {
 			lv := strings.Fields(line)
@@ -100,114 +86,7 @@ func HwthreadList() []int {
 	return cpulist
 }
 
-// Get list of hardware thread IDs in the order of listing in /proc/cpuinfo
-// Deprecated! Use HwthreadList()
-func CpuList() []int {
-	return HwthreadList()
-}
-
-// Get list of CPU core IDs in the order of listing in /proc/cpuinfo
-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
-}
-
-// Get list of NUMA node IDs
-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
-}
-
-// Get list of CPU die IDs
-func DieList() []int {
-	cpulist := HwthreadList()
-	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()
-}
-
-// Get 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{}
-}
-
-// Structure holding all information about a hardware thread
-type HwthreadEntry struct {
+type CpuEntry struct {
 	Cpuid      int
 	SMT        int
 	Core       int
@@ -216,25 +95,25 @@ type HwthreadEntry struct {
 	Die        int
 }
 
-func CpuData() []HwthreadEntry {
+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)
-	// }
+	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))
 	}
@@ -250,14 +129,14 @@ func CpuData() []HwthreadEntry {
 	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())
+			log.Print(err)
 		}
 		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())
+				log.Print(err)
 			}
 			threadlist = append(threadlist, int(id))
 		}
@@ -270,114 +149,94 @@ func CpuData() []HwthreadEntry {
 	}
 
 	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)
+		files, err := filepath.Glob(fmt.Sprintf("%s/node*", basepath))
 		if err != nil {
-			cclogger.ComponentError("CCTopology", "CpuData:getNumaDomain", err.Error())
+			log.Print(err)
 		}
 		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 && (finfo.IsDir() || finfo.Mode()&os.ModeSymlink != 0) {
+				var id int
+				parts := strings.Split(f, "/")
+				_, err = fmt.Scanf("node%d", parts[len(parts)-1], &id)
 				if err == nil {
 					return id
 				}
 			}
 		}
-		}
 		return 0
 	}
 
-	clist := make([]HwthreadEntry, 0)
-	for _, c := range HwthreadList() {
-		clist = append(clist, HwthreadEntry{Cpuid: c})
+	clist := make([]CpuEntry, 0)
+	for _, c := range CpuList() {
+		clist = append(clist, CpuEntry{Cpuid: c})
 	}
-	for i, centry := range clist {
+	for _, 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")
+		base := fmt.Sprintf("/sys/devices/system/cpu/cpu%d/topology", centry.Cpuid)
 
 		// Lookup CPU core id
-		centry.Core = getCore(topoBase)
+		centry.Core = getCore(base)
 
 		// Lookup CPU socket id
-		centry.Socket = getSocket(topoBase)
+		centry.Socket = getSocket(base)
 
 		// Lookup CPU die id
-		centry.Die = getDie(topoBase)
-		if centry.Die < 0 {
-			centry.Die = centry.Socket
-		}
+		centry.Die = getDie(base)
 
 		// Lookup SMT thread id
-		centry.SMT = getSMT(centry.Cpuid, topoBase)
+		centry.SMT = getSMT(centry.Cpuid, base)
 
 		// Lookup NUMA domain id
 		centry.Numadomain = getNumaDomain(base)
 
-		// Update values in output list
-		clist[i] = centry
 	}
 	return clist
 }
 
-// Structure holding basic information about a CPU
 type CpuInformation struct {
 	NumHWthreads   int
 	SMTWidth       int
 	NumSockets     int
 	NumDies        int
-	NumCores       int
 	NumNumaDomains int
 }
 
-// Get basic information about the CPU
 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)
+	smt := 0
+	numa := 0
+	die := 0
+	socket := 0
 	cdata := CpuData()
 	for _, d := range cdata {
-		if _, ok := intArrayContains(smtList, d.SMT); !ok {
-			smtList = append(smtList, d.SMT)
+		if d.SMT > smt {
+			smt = d.SMT
 		}
-		if _, ok := intArrayContains(numaList, d.Numadomain); !ok {
-			numaList = append(numaList, d.Numadomain)
+		if d.Numadomain > numa {
+			numa = d.Numadomain
 		}
-		if _, ok := intArrayContains(dieList, d.Die); !ok {
-			dieList = append(dieList, d.Die)
+		if d.Die > die {
+			die = 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)
+		if d.Socket > socket {
+			socket = d.Socket
 		}
 	}
-	c.NumNumaDomains = len(numaList)
-	c.SMTWidth = len(smtList)
-	c.NumDies = len(dieList)
-	c.NumCores = len(coreList)
-	c.NumSockets = len(socketList)
+	c.NumNumaDomains = numa + 1
+	c.SMTWidth = smt + 1
+	c.NumDies = die + 1
+	c.NumSockets = socket + 1
 	c.NumHWthreads = len(cdata)
 	return c
 }
 
-// Get the CPU socket ID for a given hardware thread ID
-func GetHwthreadSocket(cpuid int) int {
+func GetCpuSocket(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -387,8 +246,7 @@ func GetHwthreadSocket(cpuid int) int {
 	return -1
 }
 
-// Get the NUMA node ID for a given hardware thread ID
-func GetHwthreadNumaDomain(cpuid int) int {
+func GetCpuNumaDomain(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -398,8 +256,7 @@ func GetHwthreadNumaDomain(cpuid int) int {
 	return -1
 }
 
-// Get the CPU die ID for a given hardware thread ID
-func GetHwthreadDie(cpuid int) int {
+func GetCpuDie(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -409,8 +266,7 @@ func GetHwthreadDie(cpuid int) int {
 	return -1
 }
 
-// Get the CPU core ID for a given hardware thread ID
-func GetHwthreadCore(cpuid int) int {
+func GetCpuCore(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -419,51 +275,3 @@ func GetHwthreadCore(cpuid int) int {
 	}
 	return -1
 }
-
-// Get the all hardware thread ID associated with a CPU socket
-func GetSocketHwthreads(socket int) []int {
-	all := CpuData()
-	cpulist := make([]int, 0)
-	for _, d := range all {
-		if d.Socket == socket {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}
-
-// Get the all hardware thread ID associated with a NUMA node
-func GetNumaDomainHwthreads(domain int) []int {
-	all := CpuData()
-	cpulist := make([]int, 0)
-	for _, d := range all {
-		if d.Numadomain == domain {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}
-
-// Get the all hardware thread ID associated with a CPU die
-func GetDieHwthreads(die int) []int {
-	all := CpuData()
-	cpulist := make([]int, 0)
-	for _, d := range all {
-		if d.Die == die {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}
-
-// Get the all hardware thread ID associated with a CPU core
-func GetCoreHwthreads(core int) []int {
-	all := CpuData()
-	cpulist := make([]int, 0)
-	for _, d := range all {
-		if d.Core == core {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}

internal/metricAggregator/README.md

@@ -1,38 +0,0 @@
-# The MetricAggregator
-
-In some cases, further combination of metrics or raw values is required. For that strings like `foo + 1` with runtime dependent `foo` need to be evaluated. The MetricAggregator relies on the [`gval`](https://github.com/PaesslerAG/gval) Golang package to perform all expression evaluation. The `gval` package provides the basic arithmetic operations but the MetricAggregator defines additional ones.
-
-**Note**: To get an impression which expressions can be handled by `gval`, see its [README](https://github.com/PaesslerAG/gval/blob/master/README.md)
-
-## Simple expression evaluation
-
-For simple expression evaluation, the MetricAggregator provides two function for different use-cases:
-- `EvalBoolCondition(expression string, params map[string]interface{}`: Used by the MetricRouter to match metrics like `metric.Name() == 'mymetric'`
-- `EvalFloat64Condition(expression string, params map[string]interface{})`: Used by the MetricRouter and LikwidCollector to derive new values like `(PMC0+PMC1)/PMC3`
-
-## MetricAggregator extensions for `gval`
-
-The MetricAggregator provides these functions additional to the `Full` language in `gval`:
-- `sum(array)`: Sum up values in an array like `sum(values)`
-- `min(array)`: Get the minimum value in an array like `min(values)`
-- `avg(array)`: Get the mean value in an array like `avg(values)`
-- `mean(array)`: Get the mean value in an array like `mean(values)`
-- `max(array)`: Get the maximum value in an array like `max(values)`
-- `len(array)`: Get the length of an array like `len(values)`
-- `median(array)`: Get the median value in an array like `mean(values)`
-- `in`: Check existence in an array like `0 in getCpuList()` to check whether there is an entry `0`. Also substring matching works like `temp in metric.Name()`
-- `match`: Regular-expression matching like `match('temp_cores_%d+', metric.Name())`. **Note** all `\` in an regex has to be replaced with `%`
-- `getCpuCore(cpuid)`: For a CPU id, the the corresponding CPU core id like `getCpuCore(0)`
-- `getCpuSocket(cpuid)`: For a CPU id, the the corresponding CPU socket id
-- `getCpuNuma(cpuid)`: For a CPU id, the the corresponding NUMA domain id
-- `getCpuDie(cpuid)`: For a CPU id, the the corresponding CPU die id
-- `getSockCpuList(sockid)`: For a given CPU socket id, the list of CPU ids is returned like the CPUs on socket 1 `getSockCpuList(1)`
-- `getNumaCpuList(numaid)`: For a given NUMA node id, the list of CPU ids is returned
-- `getDieCpuList(dieid)`: For a given CPU die id, the list of CPU ids is returned
-- `getCoreCpuList(coreid)`: For a given CPU core id, the list of CPU ids is returned
-- `getCpuList`: Get the list of all CPUs
-
-## Limitations
-
-- Since the metrics are written in JSON files which do not allow `""` without proper escaping inside of JSON strings, you have to use `''` for strings.
-- Since `\` is interpreted by JSON as escape character, it cannot be used in metrics. But it is required to write regular expressions. So instead of `/`, use `%` and the MetricAggregator replaces them after reading the JSON file.

internal/metricRouter/README.md

@@ -6,10 +6,6 @@ The CCMetric router sits in between the collectors and the sinks and can be used
 
 ```json
 {
-    "num_cache_intervals" : 1,
-    "interval_timestamp" : true,
-    "hostname_tag" : "hostname",
-    "max_forward" : 50,
     "add_tags" : [
         {
             "key" : "cluster",
@@ -29,85 +25,16 @@ The CCMetric router sits in between the collectors and the sinks and can be used
             "if" : "*"
         }
     ],
-    "interval_aggregates" : [
-        {
-            "name" : "temp_cores_avg",
-            "if" : "match('temp_core_%d+', metric.Name())",
-            "function" : "avg(values)",
-            "tags" : {
-                "type" : "node"
-            },
-            "meta" : {
-                "group": "IPMI",
-                "unit": "degC",
-                "source": "TempCollector"
-            }
-        }
-    ],
-    "drop_metrics" : [
-        "not_interesting_metric_at_all"
-    ],
-    "drop_metrics_if" : [
-        "match('temp_core_%d+', metric.Name())"
-    ],
-    "rename_metrics" : {
-        "metric_12345" : "mymetric"
-    },
-    "normalize_units" : true,
-    "change_unit_prefix" : {
-      "mem_used" : "G",
-      "mem_total" : "G"
-    }
+    "interval_timestamp" : true
 }
 ```
 
 There are three main options `add_tags`, `delete_tags` and `interval_timestamp`. `add_tags` and `delete_tags` are lists consisting of dicts with `key`, `value` and `if`. The `value` can be omitted in the `delete_tags` part as it only uses the `key` for removal. The `interval_timestamp` setting means that a unique timestamp is applied to all metrics traversing the router during an interval.
 
-# Processing order in the router
+# Conditional manipulation of tags
 
-- Add the `hostname_tag` tag (if sent by collectors or cache)
-- If `interval_timestamp == true`, change time of metrics
-- Check if metric should be dropped (`drop_metrics` and `drop_metrics_if`)
-- Add tags from `add_tags`
-- Delete tags from `del_tags`
-- Rename metric based on `rename_metrics` and store old name as `oldname` in meta information
-- Add tags from `add_tags` (if you used the new name in the `if` condition)
-- Delete tags from `del_tags` (if you used the new name in the `if` condition)
-- Send to sinks
-- Move to cache (if `num_cache_intervals > 0`)
+The `if` setting allows conditional testing of a single metric like in the example:
 
-# The `interval_timestamp` option
-
-The collectors' `Read()` functions are not called simultaneously and therefore the metrics gathered in an interval can have different timestamps. If you want to avoid that and have a common timestamp (the beginning of the interval), set this option to `true` and the MetricRouter sets the time.
-
-# The `num_cache_intervals` option
-
-If the MetricRouter should buffer metrics of intervals in a MetricCache, this option specifies the number of past intervals that should be kept. If `num_cache_intervals = 0`, the cache is disabled. With `num_cache_intervals = 1`, only the metrics of the last interval are buffered.
-
-A `num_cache_intervals > 0` is required to use the `interval_aggregates` option.
-
-# The `hostname_tag` option
-
-By default, the router tags metrics with the hostname for all locally created metrics. The default tag name is `hostname`, but it can be changed if your organization wants anything else
-
-# The `max_forward` option
-
-Every time the router receives a metric through any of the channels, it tries to directly read up to `max_forward` metrics from the same channel. This was done as the router thread would go to sleep and wake up with every arriving metric. The default are `50` metrics at once and `max_forward` needs to greater than `1`.
-
-# The `rename_metrics` option
-
-In the ClusterCockpit world we specified a set of standard metrics. Since some collectors determine the metric names based on files, execuables and libraries, they might change from system to system (or installation to installtion, OS to OS, ...). In order to get the common names, you can rename incoming metrics before sending them to the sink. If the metric name matches the `oldname`, it is changed to `newname`
-
-```json
-{
-  "oldname" : "newname",
-  "clock_mhz" : "clock"
-}
-```
-
-# Conditional manipulation of tags (`add_tags` and `del_tags`)
-
-Common config format:
 ```json
 {
     "key" : "test",
@@ -116,158 +43,8 @@ Common config format:
 }
 ```
 
-## The `del_tags` option
+If the CCMetric name is equal to 'temp_package_id_0', it adds an additional tag `test=testing` to the metric.
 
-The collectors are free to add whatever `key=value` pair to the metric tags (although the usage of tags should be minimized). If you want to delete a tag afterwards, you can do that. When the `if` condition matches on a metric, the `key` is removed from the metric's tags.
+In order to match all metrics, you can use `*`, so in order to add a flag per default, like the `cluster=testcluster` tag in the example.
 
-If you want to remove a tag for all metrics, use the condition wildcard `*`. The `value` field can be omitted in the `del_tags` case.
 
-Never delete tags:
-- `hostname`
-- `type`
-- `type-id`
-
-## The `add_tags` option
-
-In some cases, metrics should be tagged or an existing tag changed based on some condition. This can be done in the `add_tags` section. When the `if` condition evaluates to `true`, the tag `key` is added or gets changed to the new `value`.
-
-If the CCMetric name is equal to `temp_package_id_0`, it adds an additional tag `test=testing` to the metric.
-
-For this metric, a more useful example would be:
-
-```json
-[
-  {
-    "key" : "type",
-    "value" : "socket",
-    "if" : "name == 'temp_package_id_0'"
-  },
-  {
-    "key" : "type-id",
-    "value" : "0",
-    "if" : "name == 'temp_package_id_0'"
-  },
-]
-```
-
-The metric `temp_package_id_0` corresponds to the tempature of the first CPU socket (=package). With the above configuration, the tags would reflect that because commonly the [TempCollector](../../collectors/tempMetric.md) submits only `node` metrics.
-
-In order to match all metrics, you can use `*`, so in order to add a flag per default. This is useful to attached system-specific tags like `cluster=testcluster`:
-
-```json
-{
-    "key" : "cluster",
-    "value" : "testcluster",
-    "if" : "*"
-}
-```
-
-# Dropping metrics
-
-In some cases, you want to drop a metric and don't get it forwarded to the sinks. There are two options based on the required specification:
-- Based only on the metric name -> `drop_metrics` section
-- An evaluable condition with more overhead -> `drop_metrics_if` section
-
-## The `drop_metrics` section
-
-The argument is a list of metric names. No futher checks are performed, only a comparison of the metric name
-
-```json
-{
-  "drop_metrics" : [
-      "drop_metric_1",
-      "drop_metric_2"
-  ]
-}
-```
-
-The example drops all metrics with the name `drop_metric_1` and `drop_metric_2`.
-
-## The `drop_metrics_if` section
-
-This option takes a list of evaluable conditions and performs them one after the other on **all** metrics incoming from the collectors and the metric cache (aka `interval_aggregates`).
-
-```json
-{
-  "drop_metrics_if" : [
-      "match('drop_metric_%d+', name)",
-      "match('cpu', type) && type-id == 0"
-  ]
-}
-```
-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
-
-**Note:** `interval_aggregates` works only if `num_cache_intervals` > 0
-
-In some cases, you need to derive new metrics based on the metrics arriving during an interval. This can be done in the `interval_aggregates` section. The logic is similar to the other metric manipulation and filtering options. A cache stores all metrics that arrive during an interval. At the beginning of the *next* interval, the list of metrics is submitted to the MetricAggregator. It derives new metrics and submits them back to the MetricRouter, so they are sent in the next interval but have the timestamp of the previous interval beginning.
-
-```json
-"interval_aggregates" : [
-  {
-    "name" : "new_metric_name",
-    "if" : "match('sub_metric_%d+', metric.Name())",
-    "function" : "avg(values)",
-    "tags" : {
-      "key" : "value",
-      "type" : "node"
-    },
-    "meta" : {
-      "key" : "value",
-      "group": "IPMI",
-      "unit": "<copy>",
-    }
-  }
-]
-```
-
-The above configuration, collects all metric values for metrics evaluating `if` to `true`. Afterwards it calculates the average `avg` of the `values` (list of all metrics' field `value`) and creates a new CCMetric with the name `new_metric_name` and adds the tags in `tags` and the meta information in `meta`. The special value `<copy>` searches the input metrics and copies the value of the first match of `key` to the new CCMetric.
-
-If you are not interested in the input metrics `sub_metric_%d+` at all, you can add the same condition used here to the `drop_metrics_if` section to drop them.
-
-Use cases for `interval_aggregates`:
-- Combine multiple metrics of the a collector to a new one like the [MemstatCollector](../../collectors/memstatMetric.md) does it for `mem_used`)):
-```json
-  {
-    "name" : "mem_used",
-    "if" : "source == 'MemstatCollector'",
-    "function" : "sum(mem_total) - (sum(mem_free) + sum(mem_buffers) + sum(mem_cached))",
-    "tags" : {
-      "type" : "node"
-    },
-    "meta" : {
-      "group": "<copy>",
-      "unit": "<copy>",
-      "source": "<copy>"
-    }
-  }
-```
-
-# 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

internal/metricRouter/metricAggregator.go

@@ -1,12 +1,10 @@
-package metricAggregator
+package metricRouter
 
 import (
 	"context"
 	"fmt"
-	"math"
 	"os"
 	"strings"
-	"sync"
 	"time"
 
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
@@ -17,7 +15,7 @@ import (
 	"github.com/PaesslerAG/gval"
 )
 
-type MetricAggregatorIntervalConfig struct {
+type metricAggregatorIntervalConfig struct {
 	Name      string            `json:"name"`     // Metric name for the new metric
 	Function  string            `json:"function"` // Function to apply on the metric
 	Condition string            `json:"if"`       // Condition for applying function
@@ -28,7 +26,7 @@ type MetricAggregatorIntervalConfig struct {
 }
 
 type metricAggregator struct {
-	functions []*MetricAggregatorIntervalConfig
+	functions []*metricAggregatorIntervalConfig
 	constants map[string]interface{}
 	language  gval.Language
 	output    chan lp.CCMetric
@@ -63,20 +61,10 @@ var metricCacheLanguage = gval.NewLanguage(
 	gval.Function("getCpuList", getCpuListOfNode),
 	gval.Function("getCpuListOfType", getCpuListOfType),
 )
-var language gval.Language = gval.NewLanguage(
-	gval.Full(),
-	metricCacheLanguage,
-)
-var evaluables = struct {
-	mapping map[string]gval.Evaluable
-	mutex   sync.Mutex
-}{
-	mapping: make(map[string]gval.Evaluable),
-}
 
 func (c *metricAggregator) Init(output chan lp.CCMetric) error {
 	c.output = output
-	c.functions = make([]*MetricAggregatorIntervalConfig, 0)
+	c.functions = make([]*metricAggregatorIntervalConfig, 0)
 	c.constants = make(map[string]interface{})
 
 	// add constants like hostname, numSockets, ... to constants list
@@ -96,7 +84,7 @@ func (c *metricAggregator) Init(output chan lp.CCMetric) error {
 	c.constants["smtWidth"] = cinfo.SMTWidth
 
 	c.language = gval.NewLanguage(
-		gval.Full(),
+		gval.Base(),
 		metricCacheLanguage,
 	)
 
@@ -257,16 +245,15 @@ func (c *metricAggregator) AddAggregation(name, function, condition string, tags
 			return nil
 		}
 	}
-	agg := &MetricAggregatorIntervalConfig{
-		Name:      name,
-		Condition: newcond,
-		gvalCond:  gvalCond,
-		Function:  newfunc,
-		gvalFunc:  gvalFunc,
-		Tags:      tags,
-		Meta:      meta,
-	}
-	c.functions = append(c.functions, agg)
+	var agg metricAggregatorIntervalConfig
+	agg.Name = name
+	agg.Condition = newcond
+	agg.gvalCond = gvalCond
+	agg.Function = newfunc
+	agg.gvalFunc = gvalFunc
+	agg.Tags = tags
+	agg.Meta = meta
+	c.functions = append(c.functions, &agg)
 	return nil
 }
 
@@ -294,50 +281,6 @@ func (c *metricAggregator) AddFunction(name string, function func(args ...interf
 	c.language = gval.NewLanguage(c.language, gval.Function(name, function))
 }
 
-func EvalBoolCondition(condition string, params map[string]interface{}) (bool, error) {
-	evaluables.mutex.Lock()
-	evaluable, ok := evaluables.mapping[condition]
-	evaluables.mutex.Unlock()
-	if !ok {
-		newcond :=
-			strings.ReplaceAll(
-				strings.ReplaceAll(
-					condition, "'", "\""), "%", "\\")
-		var err error
-		evaluable, err = language.NewEvaluable(newcond)
-		if err != nil {
-			return false, err
-		}
-		evaluables.mutex.Lock()
-		evaluables.mapping[condition] = evaluable
-		evaluables.mutex.Unlock()
-	}
-	value, err := evaluable.EvalBool(context.Background(), params)
-	return value, err
-}
-
-func EvalFloat64Condition(condition string, params map[string]interface{}) (float64, error) {
-	evaluables.mutex.Lock()
-	evaluable, ok := evaluables.mapping[condition]
-	evaluables.mutex.Unlock()
-	if !ok {
-		newcond :=
-			strings.ReplaceAll(
-				strings.ReplaceAll(
-					condition, "'", "\""), "%", "\\")
-		var err error
-		evaluable, err = language.NewEvaluable(newcond)
-		if err != nil {
-			return math.NaN(), err
-		}
-		evaluables.mutex.Lock()
-		evaluables.mapping[condition] = evaluable
-		evaluables.mutex.Unlock()
-	}
-	value, err := evaluable.EvalFloat64(context.Background(), params)
-	return value, err
-}
-
 func NewAggregator(output chan lp.CCMetric) (MetricAggregator, error) {
 	a := new(metricAggregator)
 	err := a.Init(output)

internal/metricRouter/metricAggregatorFunctions.go

@@ -1,4 +1,4 @@
-package metricAggregator
+package metricRouter
 
 import (
 	"errors"
@@ -246,7 +246,7 @@ func matchfunc(args ...interface{}) (interface{}, error) {
 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")
 }
@@ -255,7 +255,7 @@ func getCpuCoreFunc(args ...interface{}) (interface{}, error) {
 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")
 }
@@ -264,7 +264,7 @@ func getCpuSocketFunc(args ...interface{}) (interface{}, error) {
 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")
 }
@@ -273,7 +273,7 @@ func getCpuNumaDomainFunc(args ...interface{}) (interface{}, error) {
 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")
 }
@@ -336,7 +336,7 @@ func getCpuListOfDieFunc(args ...interface{}) (interface{}, error) {
 
 // wrapper function to get a list of all cpuids of the node
 func getCpuListOfNode(args ...interface{}) (interface{}, error) {
-	return topo.HwthreadList(), nil
+	return topo.CpuList(), nil
 }
 
 // helper function to get the cpuid list for a CCMetric type tag set (type and type-id)
@@ -348,14 +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) {

internal/metricRouter/metricCache.go

@@ -7,7 +7,6 @@ import (
 	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"
 	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
 )
 
@@ -23,14 +22,13 @@ type metricCachePeriod struct {
 type metricCache struct {
 	numPeriods int
 	curPeriod  int
-	lock       sync.Mutex
 	intervals  []*metricCachePeriod
 	wg         *sync.WaitGroup
 	ticker     mct.MultiChanTicker
 	tickchan   chan time.Time
 	done       chan bool
 	output     chan lp.CCMetric
-	aggEngine  agg.MetricAggregator
+	aggEngine  MetricAggregator
 }
 
 type MetricCache interface {
@@ -61,7 +59,7 @@ func (c *metricCache) Init(output chan lp.CCMetric, ticker mct.MultiChanTicker,
 
 	// Create a new aggregation engine. No separate goroutine at the moment
 	// The code is executed by the MetricCache goroutine
-	c.aggEngine, err = agg.NewAggregator(c.output)
+	c.aggEngine, err = NewAggregator(c.output)
 	if err != nil {
 		cclog.ComponentError("MetricCache", "Cannot create aggregator")
 		return err
@@ -104,11 +102,9 @@ func (c *metricCache) Start() {
 				done()
 				return
 			case tick := <-c.tickchan:
-				c.lock.Lock()
 				old := rotate(tick)
 				// Get the last period and evaluate aggregation metrics
 				starttime, endtime, metrics := c.GetPeriod(old)
-				c.lock.Unlock()
 				if len(metrics) > 0 {
 					c.aggEngine.Eval(starttime, endtime, metrics)
 				} else {
@@ -126,7 +122,6 @@ func (c *metricCache) Start() {
 // to avoid reallocations
 func (c *metricCache) Add(metric lp.CCMetric) {
 	if c.curPeriod >= 0 && c.curPeriod < c.numPeriods {
-		c.lock.Lock()
 		p := c.intervals[c.curPeriod]
 		if p.numMetrics < p.sizeMetrics {
 			p.metrics[p.numMetrics] = metric
@@ -138,7 +133,6 @@ func (c *metricCache) Add(metric lp.CCMetric) {
 			p.sizeMetrics = p.sizeMetrics + 1
 			p.stopstamp = metric.Time()
 		}
-		c.lock.Unlock()
 	}
 }
 
@@ -154,26 +148,16 @@ func (c *metricCache) DeleteAggregation(name string) error {
 // is the current one, index=1 the last interval and so on. Returns and empty array if a wrong index
 // is given (negative index, index larger than configured number of total intervals, ...)
 func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric) {
-	var start time.Time = time.Now()
-	var stop time.Time = time.Now()
-	var metrics []lp.CCMetric
 	if index >= 0 && index < c.numPeriods {
 		pindex := c.curPeriod - index
 		if pindex < 0 {
 			pindex = c.numPeriods - pindex
 		}
 		if pindex >= 0 && pindex < c.numPeriods {
-			start = c.intervals[pindex].startstamp
-			stop = c.intervals[pindex].stopstamp
-			metrics = c.intervals[pindex].metrics
-			//return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
-		} else {
-			metrics = make([]lp.CCMetric, 0)
+			return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
 		}
-	} else {
-		metrics = make([]lp.CCMetric, 0)
 	}
-	return start, stop, metrics
+	return time.Now(), time.Now(), make([]lp.CCMetric, 0)
 }
 
 // Close finishes / stops the metric cache

internal/metricRouter/metricRouter.go

@@ -10,13 +10,10 @@ import (
 	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"
 	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
-	units "github.com/ClusterCockpit/cc-units"
+	"gopkg.in/Knetic/govaluate.v2"
 )
 
-const ROUTER_MAX_FORWARD = 50
-
 // Metric router tag configuration
 type metricRouterTagConfig struct {
 	Key       string `json:"key"`   // Tag name
@@ -26,19 +23,11 @@ type metricRouterTagConfig struct {
 
 // Metric router configuration
 type metricRouterConfig struct {
-	HostnameTagName   string                               `json:"hostname_tag"`        // Key name used when adding the hostname to a metric (default 'hostname')
 	AddTags           []metricRouterTagConfig          `json:"add_tags"`            // List of tags that are added when the condition is met
 	DelTags           []metricRouterTagConfig          `json:"delete_tags"`         // List of tags that are removed when the condition is met
-	IntervalAgg       []agg.MetricAggregatorIntervalConfig `json:"interval_aggregates"` // List of aggregation function processed at the end of an interval
-	DropMetrics       []string                             `json:"drop_metrics"`        // List of metric names to drop. For fine-grained dropping use drop_metrics_if
-	DropMetricsIf     []string                             `json:"drop_metrics_if"`     // List of evaluatable terms to drop metrics
-	RenameMetrics     map[string]string                    `json:"rename_metrics"`      // Map to rename metric name from key to value
+	IntervalAgg       []metricAggregatorIntervalConfig `json:"interval_aggregates"` // List of aggregation function processed at the end of an interval
 	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
@@ -51,11 +40,11 @@ type metricRouter struct {
 	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
 }
 
 // MetricRouter access functions
@@ -80,8 +69,6 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	r.cache_input = make(chan lp.CCMetric)
 	r.wg = wg
 	r.ticker = ticker
-	r.config.MaxForward = ROUTER_MAX_FORWARD
-	r.config.HostnameTagName = "hostname"
 
 	// Set hostname
 	hostname, err := os.Hostname()
@@ -105,12 +92,11 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 		cclog.ComponentError("MetricRouter", err.Error())
 		return err
 	}
-	r.maxForward = 1
-	if r.config.MaxForward > r.maxForward {
-		r.maxForward = r.config.MaxForward
+	numIntervals := r.config.NumCacheIntervals
+	if numIntervals <= 0 {
+		numIntervals = 1
 	}
-	if r.config.NumCacheIntervals > 0 {
-		r.cache, err = NewCache(r.cache_input, r.ticker, &r.cachewg, r.config.NumCacheIntervals)
+	r.cache, err = NewCache(r.cache_input, r.ticker, &r.cachewg, numIntervals)
 	if err != nil {
 		cclog.ComponentError("MetricRouter", "MetricCache initialization failed:", err.Error())
 		return err
@@ -118,42 +104,73 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	for _, agg := range r.config.IntervalAgg {
 		r.cache.AddAggregation(agg.Name, agg.Function, agg.Condition, agg.Tags, agg.Meta)
 	}
-	}
-	r.config.dropMetrics = make(map[string]bool)
-	for _, mname := range r.config.DropMetrics {
-		r.config.dropMetrics[mname] = true
-	}
 	return nil
 }
 
-func getParamMap(point lp.CCMetric) map[string]interface{} {
+// 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:
+				r.timestamp = t
+			}
+		}
+	}()
+	cclog.ComponentDebug("MetricRouter", "TIMER START")
+}
+
+// EvalCondition evaluates condition cond for metric data from point
+func (r *metricRouter) EvalCondition(cond string, point lp.CCMetric) (bool, error) {
+	expression, err := govaluate.NewEvaluableExpression(cond)
+	if err != nil {
+		cclog.ComponentDebug("MetricRouter", cond, " = ", err.Error())
+		return false, err
+	}
+
+	// Add metric name, tags, meta data, fields and timestamp to the parameter list
 	params := make(map[string]interface{})
-	params["metric"] = point
 	params["name"] = point.Name()
-	for key, value := range point.Tags() {
-		params[key] = value
+	for _, t := range point.TagList() {
+		params[t.Key] = t.Value
 	}
-	for key, value := range point.Meta() {
-		params[key] = value
+	for _, m := range point.MetaList() {
+		params[m.Key] = m.Value
 	}
-	for key, value := range point.Fields() {
-		params[key] = value
+	for _, f := range point.FieldList() {
+		params[f.Key] = f.Value
 	}
 	params["timestamp"] = point.Time()
-	return params
+
+	// evaluate condition
+	result, err := expression.Evaluate(params)
+	if err != nil {
+		cclog.ComponentDebug("MetricRouter", cond, " = ", err.Error())
+		return false, err
+	}
+	return bool(result.(bool)), err
 }
 
 // DoAddTags adds a tag when condition is fullfiled
 func (r *metricRouter) DoAddTags(point lp.CCMetric) {
-	var conditionMatches bool
 	for _, m := range r.config.AddTags {
+		var conditionMatches bool
+
 		if m.Condition == "*" {
-			// Condition is always matched
 			conditionMatches = true
 		} else {
-			// Evaluate condition
 			var err error
-			conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
+			conditionMatches, err = r.EvalCondition(m.Condition, point)
 			if err != nil {
 				cclog.ComponentError("MetricRouter", err.Error())
 				conditionMatches = false
@@ -167,15 +184,14 @@ func (r *metricRouter) DoAddTags(point lp.CCMetric) {
 
 // DoDelTags removes a tag when condition is fullfiled
 func (r *metricRouter) DoDelTags(point lp.CCMetric) {
-	var conditionMatches bool
 	for _, m := range r.config.DelTags {
+		var conditionMatches bool
+
 		if m.Condition == "*" {
-			// Condition is always matched
 			conditionMatches = true
 		} else {
-			// Evaluate condition
 			var err error
-			conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
+			conditionMatches, err = r.EvalCondition(m.Condition, point)
 			if err != nil {
 				cclog.ComponentError("MetricRouter", err.Error())
 				conditionMatches = false
@@ -187,68 +203,13 @@ func (r *metricRouter) DoDelTags(point lp.CCMetric) {
 	}
 }
 
-// Conditional test whether a metric should be dropped
-func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
-	// Simple drop check
-	if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
-		return conditionMatches
-	}
-
-	// Checking the dropping conditions
-	for _, m := range r.config.DropMetricsIf {
-		conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point))
-		if err != nil {
-			cclog.ComponentError("MetricRouter", err.Error())
-			conditionMatches = false
-		}
-		if conditionMatches {
-			return conditionMatches
-		}
-	}
-
-	// No dropping condition met
-	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
@@ -263,94 +224,43 @@ func (r *metricRouter) Start() {
 		cclog.ComponentDebug("MetricRouter", "FORWARD", point)
 		r.DoAddTags(point)
 		r.DoDelTags(point)
-		name := point.Name()
-		if new, ok := r.config.RenameMetrics[name]; ok {
-			point.SetName(new)
-			point.AddMeta("oldname", name)
-			r.DoAddTags(point)
-			r.DoDelTags(point)
-		}
-
-		r.prepareUnit(point)
-
 		for _, o := range r.outputs {
 			o <- point
 		}
 	}
 
-	// Foward message received from collector channel
-	coll_forward := func(p lp.CCMetric) {
-		// receive from metric collector
-		p.AddTag(r.config.HostnameTagName, r.hostname)
-		if r.config.IntervalStamp {
-			p.SetTime(r.timestamp)
-		}
-		if !r.dropMetric(p) {
-			forward(p)
-		}
-		// even if the metric is dropped, it is stored in the cache for
-		// aggregations
-		if r.config.NumCacheIntervals > 0 {
-			r.cache.Add(p)
-		}
-	}
-
-	// Forward message received from receivers channel
-	recv_forward := func(p lp.CCMetric) {
-		// receive from receive manager
-		if r.config.IntervalStamp {
-			p.SetTime(r.timestamp)
-		}
-		if !r.dropMetric(p) {
-			forward(p)
-		}
-	}
-
-	// Forward message received from cache channel
-	cache_forward := func(p lp.CCMetric) {
-		// receive from metric collector
-		if !r.dropMetric(p) {
-			p.AddTag(r.config.HostnameTagName, r.hostname)
-			forward(p)
-		}
-	}
-
 	// Start Metric Cache
-	if r.config.NumCacheIntervals > 0 {
 	r.cache.Start()
-	}
 
 	r.wg.Add(1)
 	go func() {
 		defer r.wg.Done()
-
 		for {
 			select {
 			case <-r.done:
 				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++ {
-					coll_forward(<-r.coll_input)
+				// receive from metric collector
+				p.AddTag("hostname", r.hostname)
+				if r.config.IntervalStamp {
+					p.SetTime(r.timestamp)
 				}
+				forward(p)
+				r.cache.Add(p)
 
 			case p := <-r.recv_input:
-				recv_forward(p)
-				for i := 0; len(r.recv_input) > 0 && i < (r.maxForward-1); i++ {
-					recv_forward(<-r.recv_input)
+				// receive from receive manager
+				if r.config.IntervalStamp {
+					p.SetTime(r.timestamp)
 				}
+				forward(p)
 
 			case p := <-r.cache_input:
-				cache_forward(p)
-				for i := 0; len(r.cache_input) > 0 && i < (r.maxForward-1); i++ {
-					cache_forward(<-r.cache_input)
-				}
+				// receive from metric collector
+				p.AddTag("hostname", r.hostname)
+				forward(p)
 			}
 		}
 	}()
@@ -378,14 +288,15 @@ func (r *metricRouter) Close() {
 	r.done <- true
 	// wait for close of channel r.done
 	<-r.done
-
-	// stop metric cache
-	if r.config.NumCacheIntervals > 0 {
-		cclog.ComponentDebug("MetricRouter", "CACHE CLOSE")
+	if r.config.IntervalStamp {
+		cclog.ComponentDebug("MetricRouter", "TIMER CLOSE")
+		r.timerdone <- true
+		// wait for close of channel r.timerdone
+		<-r.timerdone
+	}
 	r.cache.Close()
 	r.cachewg.Wait()
 }
-}
 
 // New creates a new initialized metric router
 func New(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) (MetricRouter, error) {

metric-collector.go

@@ -22,8 +22,9 @@ import (
 )
 
 type CentralConfigFile struct {
-	Interval            string `json:"interval"`
-	Duration            string `json:"duration"`
+	Interval            int    `json:"interval"`
+	Duration            int    `json:"duration"`
+	Pidfile             string `json:"pidfile,omitempty"`
 	CollectorConfigFile string `json:"collectors"`
 	RouterConfigFile    string `json:"router"`
 	SinkConfigFile      string `json:"sinks"`
@@ -86,12 +87,14 @@ func ReadCli() map[string]string {
 	var m map[string]string
 	cfg := flag.String("config", "./config.json", "Path to configuration file")
 	logfile := flag.String("log", "stderr", "Path for logfile")
+	pidfile := flag.String("pidfile", "/var/run/cc-metric-collector.pid", "Path for PID file")
 	once := flag.Bool("once", false, "Run all collectors only once")
 	debug := flag.Bool("debug", false, "Activate debug output")
 	flag.Parse()
 	m = make(map[string]string)
 	m["configfile"] = *cfg
 	m["logfile"] = *logfile
+	m["pidfile"] = *pidfile
 	if *once {
 		m["once"] = "true"
 	} else {
@@ -122,6 +125,25 @@ func ReadCli() map[string]string {
 //	return nil
 //}
 
+//func CreatePidfile(pidfile string) error {
+//	file, err := os.OpenFile(pidfile, os.O_CREATE|os.O_RDWR, 0600)
+//	if err != nil {
+//		log.Print(err)
+//		return err
+//	}
+//	file.Write([]byte(fmt.Sprintf("%d", os.Getpid())))
+//	file.Close()
+//	return nil
+//}
+
+//func RemovePidfile(pidfile string) error {
+//	info, err := os.Stat(pidfile)
+//	if !os.IsNotExist(err) && !info.IsDir() {
+//		os.Remove(pidfile)
+//	}
+//	return nil
+//}
+
 // General shutdownHandler function that gets executed in case of interrupt or graceful shutdownHandler
 func shutdownHandler(config *RuntimeConfig, shutdownSignal chan os.Signal) {
 	defer config.Sync.Done()
@@ -152,6 +174,11 @@ func shutdownHandler(config *RuntimeConfig, shutdownSignal chan os.Signal) {
 		cclog.Debug("Shutdown SinkManager...")
 		config.SinkManager.Close()
 	}
+
+	//	pidfile := config.ConfigFile.Pidfile
+	//	RemovePidfile(pidfile)
+	//	pidfile = config.CliArgs["pidfile"]
+	//	RemovePidfile(pidfile)
 }
 
 func mainFunc() int {
@@ -173,36 +200,16 @@ 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 {
+	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
 	}
-	}
-
-	// 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 {
+	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
 	}
-	}
-	if rcfg.Duration > rcfg.Interval {
-		cclog.Error("The interval should be greater than duration")
-		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")
@@ -219,6 +226,8 @@ func mainFunc() int {
 		return 1
 	}
 
+	//	err = CreatePidfile(rcfg.CliArgs["pidfile"])
+
 	// Set log file
 	if logfile := rcfg.CliArgs["logfile"]; logfile != "stderr" {
 		cclog.SetOutput(logfile)
@@ -291,7 +300,7 @@ 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
 	}

receivers.json

@@ -1,25 +1,8 @@
+[
     {
-    "natsrecv" : {
         "type": "nats",
         "address": "nats://my-url",
         "port" : "4222",
         "database": "testcluster"
-    },
-    "redfish_recv": {
-        "type": "redfish",
-        "client_config": [
-            {
-                "hostname": "my-host-1",
-                "username": "username-1",
-                "password": "password-1",
-                "endpoint": "https://my-endpoint-1"
-            },
-            {
-                "hostname": "my-host-2",
-                "username": "username-2",
-                "password": "password-2",
-                "endpoint": "https://my-endpoint-2"
     }
 ]
-    }
-}

receivers/README.md

@@ -7,23 +7,38 @@ This folder contains the ReceiveManager and receiver implementations for the cc-
 The configuration file for the receivers is a list of configurations. The `type` field in each specifies which receiver to initialize.
 
 ```json
+[
   {
-  "myreceivername" : {
-    "type": "receiver-type",
-    <receiver-specific configuration>
+    "type": "nats",
+    "address": "nats://my-url",
+    "port" : "4222",
+    "database": "testcluster"
   }
+]
+```
+
+
+## Type `nats`
+
+```json
+{
+  "type": "nats",
+  "address": "<nats-URI or hostname>",
+  "port" : "<portnumber>",
+  "database": "<subscribe topic>"
 }
 ```
 
-This allows to specify
-
-## Available receivers
-
-- [`nats`](./natsReceiver.md): Receive metrics from the NATS network
-- [`prometheus`](./prometheusReceiver.md): Scrape data from a Prometheus client
-- [`http`](./httpReceiver.md): Listen for HTTP Post requests transporting metrics in InfluxDB line protocol
+The `nats` receiver subscribes to the topic `database` and listens on `address` and `port` for metrics in the InfluxDB line protocol.
 
 # Contributing own receivers
-A receiver contains a few functions and is derived from the type `Receiver` (in `metricReceiver.go`):
+A receiver contains three functions and is derived from the type `Receiver` (in `metricReceiver.go`):
+* `Init(config ReceiverConfig) error`
+* `Start() error`
+* `Close()`
+* `Name() string`
+* `SetSink(sink chan ccMetric.CCMetric)`
 
-For an example, check the [sample receiver](./sampleReceiver.go)
+The data structures should be set up in `Init()` like opening a file or server connection. The `Start()` function should either start a go routine or issue some other asynchronous mechanism for receiving metrics. The `Close()` function should tear down anything created in `Init()`.
+
+Finally, the receiver needs to be registered in the `receiveManager.go`. There is a list of receivers called `AvailableReceivers` which is a map (`receiver_type_string` -> `pointer to Receiver interface`). Add a new entry with a descriptive name and the new receiver.

receivers/httpReceiver.go

@@ -1,118 +0,0 @@
-package receivers
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io/ioutil"
-	"net/http"
-	"strings"
-	"sync"
-
-	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"
-
-type HttpReceiverConfig struct {
-	Type string `json:"type"`
-	Addr string `json:"address"`
-	Port string `json:"port"`
-	Path string `json:"path"`
-}
-
-type HttpReceiver struct {
-	receiver
-	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)
-	r.config.Port = HTTP_RECEIVER_PORT
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &r.config)
-		if err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return err
-		}
-	}
-	if len(r.config.Port) == 0 {
-		return errors.New("not all configuration variables set required by HttpReceiver")
-	}
-	r.meta = map[string]string{"source": r.name}
-	p := r.config.Path
-	if !strings.HasPrefix(p, "/") {
-		p = "/" + p
-	}
-	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
-}
-
-func (r *HttpReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-	r.wg.Add(1)
-	go func() {
-		err := r.server.ListenAndServe()
-		if err != nil && err.Error() != "http: Server closed" {
-			cclog.ComponentError(r.name, err.Error())
-		}
-		r.wg.Done()
-	}()
-}
-
-func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
-	if req.Method != http.MethodPost {
-		http.Error(w, "Method Not Allowed", http.StatusMethodNotAllowed)
-		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)
-	}
-
-	for _, m := range metrics {
-		y := lp.FromInfluxMetric(m)
-		for k, v := range r.meta {
-			y.AddMeta(k, v)
-		}
-		if r.sink != nil {
-			r.sink <- y
-		}
-	}
-
-	w.WriteHeader(http.StatusOK)
-}
-
-func (r *HttpReceiver) Close() {
-	r.server.Shutdown(context.Background())
-}
-
-func NewHttpReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(HttpReceiver)
-	err := r.Init(name, config)
-	return r, err
-}

receivers/httpReceiver.md

@@ -1,23 +0,0 @@
-## `http` receiver
-
-The `http` receiver can be used receive metrics through HTTP POST requests.
-
-### Configuration structure
-
-```json
-{
-  "<name>": {
-    "type": "http",
-    "address" : "",
-    "port" : "8080",
-    "path" : "/write"
-  }
-}
-```
-
-- `type`: makes the receiver a `http` receiver
-- `address`: Listen address
-- `port`: Listen port
-- `path`: URL path for the write endpoint
-
-The HTTP endpoint listens to `http://<address>:<port>/<path>`

receivers/metricReceiver.go

@@ -1,14 +1,11 @@
 package receivers
 
 import (
+	//	"time"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	influx "github.com/influxdata/line-protocol"
 )
 
-type defaultReceiverConfig struct {
-	Type string `json:"type"`
-}
-
-// Receiver configuration: Listen address, port
 type ReceiverConfig struct {
 	Addr         string `json:"address"`
 	Port         string `json:"port"`
@@ -19,22 +16,41 @@ type ReceiverConfig struct {
 
 type receiver struct {
 	name         string
+	addr         string
+	port         string
+	database     string
+	organization string
 	sink         chan lp.CCMetric
 }
 
 type Receiver interface {
+	Init(config ReceiverConfig) error
 	Start()
-	Close()                        // Close / finish metric receiver
-	Name() string                  // Name of the metric receiver
-	SetSink(sink chan lp.CCMetric) // Set sink channel
+	Close()
+	Name() string
+	SetSink(sink chan lp.CCMetric)
 }
 
-// Name returns the name of the metric receiver
 func (r *receiver) Name() string {
 	return r.name
 }
 
-// SetSink set the sink channel
 func (r *receiver) SetSink(sink chan lp.CCMetric) {
 	r.sink = sink
 }
+
+func Tags2Map(metric influx.Metric) map[string]string {
+	tags := make(map[string]string)
+	for _, t := range metric.TagList() {
+		tags[t.Key] = t.Value
+	}
+	return tags
+}
+
+func Fields2Map(metric influx.Metric) map[string]interface{} {
+	fields := make(map[string]interface{})
+	for _, f := range metric.FieldList() {
+		fields[f.Key] = f.Value
+	}
+	return fields
+}

receivers/natsReceiver.go

@@ -1,22 +1,19 @@
 package receivers
 
 import (
-	"encoding/json"
 	"errors"
 	"fmt"
-	"time"
-
-	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"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	"time"
 )
 
 type NatsReceiverConfig struct {
-	Type    string `json:"type"`
 	Addr     string `json:"address"`
 	Port     string `json:"port"`
-	Subject string `json:"subject"`
+	Database string `json:"database"`
 }
 
 type NatsReceiver struct {
@@ -25,16 +22,49 @@ type NatsReceiver struct {
 	handler *influx.MetricHandler
 	parser  *influx.Parser
 	meta    map[string]string
-	config  NatsReceiverConfig
+	config  ReceiverConfig
 }
 
 var DefaultTime = func() time.Time {
 	return time.Unix(42, 0)
 }
 
+func (r *NatsReceiver) Init(config ReceiverConfig) error {
+	r.name = "NatsReceiver"
+	r.config = config
+	if len(r.config.Addr) == 0 ||
+		len(r.config.Port) == 0 ||
+		len(r.config.Database) == 0 {
+		return errors.New("Not all configuration variables set required by NatsReceiver")
+	}
+	r.meta = map[string]string{"source": r.name}
+	r.addr = r.config.Addr
+	if len(r.addr) == 0 {
+		r.addr = nats.DefaultURL
+	}
+	r.port = r.config.Port
+	if len(r.port) == 0 {
+		r.port = "4222"
+	}
+	uri := fmt.Sprintf("%s:%s", r.addr, r.port)
+	cclog.ComponentDebug("NatsReceiver", "INIT", uri)
+	nc, err := nats.Connect(uri)
+	if err == nil {
+		r.database = r.config.Database
+		r.nc = nc
+	} else {
+		r.nc = nil
+		return err
+	}
+	r.handler = influx.NewMetricHandler()
+	r.parser = influx.NewParser(r.handler)
+	r.parser.SetTimeFunc(DefaultTime)
+	return err
+}
+
 func (r *NatsReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-	r.nc.Subscribe(r.config.Subject, r._NatsReceive)
+	cclog.ComponentDebug("NatsReceiver", "START")
+	r.nc.Subscribe(r.database, r._NatsReceive)
 }
 
 func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
@@ -54,39 +84,7 @@ func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
 
 func (r *NatsReceiver) Close() {
 	if r.nc != nil {
-		cclog.ComponentDebug(r.name, "CLOSE")
+		cclog.ComponentDebug("NatsReceiver", "CLOSE")
 		r.nc.Close()
 	}
 }
-
-func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(NatsReceiver)
-	r.name = fmt.Sprintf("NatsReceiver(%s)", name)
-	r.config.Addr = nats.DefaultURL
-	r.config.Port = "4222"
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &r.config)
-		if err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return nil, err
-		}
-	}
-	if len(r.config.Addr) == 0 ||
-		len(r.config.Port) == 0 ||
-		len(r.config.Subject) == 0 {
-		return nil, errors.New("not all configuration variables set required by NatsReceiver")
-	}
-	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
-}

receivers/natsReceiver.md

@@ -1,21 +0,0 @@
-## `nats` receiver
-
-The `nats` receiver can be used receive metrics from the NATS network. The `nats` receiver subscribes to the topic `database` and listens on `address` and `port` for metrics in the InfluxDB line protocol.
-
-### Configuration structure
-
-```json
-{
-  "<name>": {
-    "type": "nats",
-    "address" : "nats-server.example.org",
-    "port" : "4222",
-    "subject" : "subject"
-  }
-}
-```
-
-- `type`: makes the receiver a `nats` receiver
-- `address`: Address of the NATS control server
-- `port`: Port of the NATS control server
-- `subject`: Subscribes to this subject and receive metrics

receivers/prometheusReceiver.go

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

receivers/prometheusReceiver.md

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

receivers/receiveManager.go

@@ -9,31 +9,32 @@ import (
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
-	"nats":    NewNatsReceiver,
-	"redfish": NewRedfishReceiver,
+var AvailableReceivers = map[string]Receiver{
+	"nats": &NatsReceiver{},
 }
 
 type receiveManager struct {
 	inputs []Receiver
 	output chan lp.CCMetric
-	config []json.RawMessage
+	done   chan bool
+	wg     *sync.WaitGroup
+	config []ReceiverConfig
 }
 
 type ReceiveManager interface {
 	Init(wg *sync.WaitGroup, receiverConfigFile string) error
-	AddInput(name string, rawConfig json.RawMessage) error
+	AddInput(rawConfig json.RawMessage) error
 	AddOutput(output chan lp.CCMetric)
 	Start()
 	Close()
 }
 
 func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) error {
-	// Initialize struct fields
 	rm.inputs = make([]Receiver, 0)
 	rm.output = nil
-	rm.config = make([]json.RawMessage, 0)
-
+	rm.done = make(chan bool)
+	rm.wg = wg
+	rm.config = make([]ReceiverConfig, 0)
 	configFile, err := os.Open(receiverConfigFile)
 	if err != nil {
 		cclog.ComponentError("ReceiveManager", err.Error())
@@ -41,21 +42,20 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
 	}
 	defer configFile.Close()
 	jsonParser := json.NewDecoder(configFile)
-	var rawConfigs map[string]json.RawMessage
+	var rawConfigs []json.RawMessage
 	err = jsonParser.Decode(&rawConfigs)
 	if err != nil {
 		cclog.ComponentError("ReceiveManager", err.Error())
 		return err
 	}
-	for name, raw := range rawConfigs {
-		rm.AddInput(name, raw)
+	for _, raw := range rawConfigs {
+		rm.AddInput(raw)
 	}
-
 	return nil
 }
 
 func (rm *receiveManager) Start() {
-	cclog.ComponentDebug("ReceiveManager", "START")
+	rm.wg.Add(1)
 
 	for _, r := range rm.inputs {
 		cclog.ComponentDebug("ReceiveManager", "START", r.Name())
@@ -64,8 +64,8 @@ func (rm *receiveManager) Start() {
 	cclog.ComponentDebug("ReceiveManager", "STARTED")
 }
 
-func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error {
-	var config defaultReceiverConfig
+func (rm *receiveManager) AddInput(rawConfig json.RawMessage) error {
+	var config ReceiverConfig
 	err := json.Unmarshal(rawConfig, &config)
 	if err != nil {
 		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "JSON config error:", err.Error())
@@ -75,13 +75,14 @@ func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error
 		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "unknown receiver:", err.Error())
 		return err
 	}
-	r, err := AvailableReceivers[config.Type](name, rawConfig)
+	r := AvailableReceivers[config.Type]
+	err = r.Init(config)
 	if err != nil {
-		cclog.ComponentError("ReceiveManager", "SKIP", name, "initialization failed:", err.Error())
+		cclog.ComponentError("ReceiveManager", "SKIP", r.Name(), "initialization failed:", err.Error())
 		return err
 	}
 	rm.inputs = append(rm.inputs, r)
-	rm.config = append(rm.config, rawConfig)
+	rm.config = append(rm.config, config)
 	cclog.ComponentDebug("ReceiveManager", "ADD RECEIVER", r.Name())
 	return nil
 }
@@ -94,19 +95,16 @@ 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

receivers/redfishReceiver.go

@@ -1,324 +0,0 @@
-package receivers
-
-import (
-	"encoding/json"
-	"fmt"
-	"strconv"
-	"sync"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-
-	// See: https://pkg.go.dev/github.com/stmcginnis/gofish
-	"github.com/stmcginnis/gofish"
-)
-
-// RedfishReceiver configuration:
-type RedfishReceiver struct {
-	receiver
-	config struct {
-		Type     string `json:"type"`
-		Fanout   int    `json:"fanout,omitempty"`   // Default fanout: 64
-		Interval int    `json:"interval,omitempty"` // Default interval: 30s
-
-		// Client config for each redfish service
-		ClientConfigs []struct {
-			Hostname       *string  `json:"hostname"`
-			Username       *string  `json:"username"`
-			Password       *string  `json:"password"`
-			Endpoint       *string  `json:"endpoint"`
-			Insecure       *bool    `json:"insecure,omitempty"`
-			ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-			gofish         gofish.ClientConfig
-		} `json:"client_config"`
-	}
-
-	done chan bool      // channel to finish / stop redfish receiver
-	wg   sync.WaitGroup // wait group for redfish receiver
-}
-
-// Start starts the redfish receiver
-func (r *RedfishReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-
-	// readPowerMetric reads readfish power metric from the endpoint configured in conf
-	readPowerMetric := func(clientConfigIndex int) error {
-
-		clientConfig := &r.config.ClientConfigs[clientConfigIndex]
-
-		// Connect to redfish service
-		c, err := gofish.Connect(clientConfig.gofish)
-		if err != nil {
-			c := struct {
-				Username  string
-				Endpoint  string
-				BasicAuth bool
-				Insecure  bool
-			}{
-				Username:  clientConfig.gofish.Username,
-				Endpoint:  clientConfig.gofish.Endpoint,
-				BasicAuth: clientConfig.gofish.BasicAuth,
-				Insecure:  clientConfig.gofish.Insecure,
-			}
-			return fmt.Errorf("readPowerMetric: gofish.Connect(%+v) failed: %v", c, err)
-		}
-		defer c.Logout()
-
-		// Get all chassis managed by this service
-		chassis_list, err := c.Service.Chassis()
-		if err != nil {
-			return fmt.Errorf("readPowerMetric: c.Service.Chassis() failed: %v", err)
-		}
-
-		for _, chassis := range chassis_list {
-			timestamp := time.Now()
-
-			// Get power information for each chassis
-			power, err := chassis.Power()
-			if err != nil {
-				return fmt.Errorf("readPowerMetric: chassis.Power() failed: %v", err)
-			}
-			if power == nil {
-				continue
-			}
-
-			// Read min, max and average consumed watts for each power control
-			for _, pc := range power.PowerControl {
-
-				// Map of collected metrics
-				metrics := map[string]float32{
-					// PowerConsumedWatts shall represent the actual power being consumed (in
-					// Watts) by the chassis
-					"consumed_watts": pc.PowerConsumedWatts,
-					// AverageConsumedWatts shall represent the
-					// average power level that occurred averaged over the last IntervalInMin
-					// minutes.
-					"average_consumed_watts": pc.PowerMetrics.AverageConsumedWatts,
-					// MinConsumedWatts shall represent the
-					// minimum power level in watts that occurred within the last
-					// IntervalInMin minutes.
-					"min_consumed_watts": pc.PowerMetrics.MinConsumedWatts,
-					// MaxConsumedWatts shall represent the
-					// maximum power level in watts that occurred within the last
-					// IntervalInMin minutes
-					"max_consumed_watts": pc.PowerMetrics.MaxConsumedWatts,
-				}
-				intervalInMin := strconv.FormatFloat(float64(pc.PowerMetrics.IntervalInMin), 'f', -1, 32)
-
-				// Metrics to exclude
-				for _, key := range clientConfig.ExcludeMetrics {
-					delete(metrics, key)
-				}
-
-				// Set tags
-				tags := map[string]string{
-					"hostname": *clientConfig.Hostname,
-					"type":     "node",
-					// ID uniquely identifies the resource
-					"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.
-					"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.
-					"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
-	}
-
-	// doReadPowerMetric read power metrics for all configure redfish services.
-	// To compensate latencies of the Redfish services a fanout is used.
-	doReadPowerMetric := func() {
-
-		// Compute fanout to use
-		realFanout := r.config.Fanout
-		if len(r.config.ClientConfigs) < realFanout {
-			realFanout = len(r.config.ClientConfigs)
-		}
-
-		// Create wait group and input channel for workers
-		var workerWaitGroup sync.WaitGroup
-		workerInput := make(chan int, realFanout)
-
-		// Create worker go routines
-		for i := 0; i < realFanout; 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 clientConfigIndex := range workerInput {
-					err := readPowerMetric(clientConfigIndex)
-					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 <- 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 redfish receiver
-	r.wg.Add(1)
-	go func() {
-		defer r.wg.Done()
-
-		// Create ticker
-		ticker := time.NewTicker(time.Duration(r.config.Interval) * time.Second)
-		defer ticker.Stop()
-
-		for {
-			doReadPowerMetric()
-
-			select {
-			case <-ticker.C:
-				// process ticker event -> continue
-				continue
-			case <-r.done:
-				// process done event
-				return
-			}
-		}
-	}()
-
-	cclog.ComponentDebug(r.name, "STARTED")
-}
-
-// Close 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")
-}
-
-// 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 NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(RedfishReceiver)
-
-	// Set name
-	r.name = fmt.Sprintf("RedfishReceiver(%s)", name)
-
-	// Create done channel
-	r.done = make(chan bool)
-
-	// Set defaults in r.config
-	// Allow overwriting these defaults by reading config JSON
-	r.config.Fanout = 64
-	r.config.Interval = 30
-
-	// Read the redfish 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
-		}
-	}
-
-	// Create gofish client config
-	for i := range r.config.ClientConfigs {
-		clientConfig := &r.config.ClientConfigs[i]
-		gofishConfig := &clientConfig.gofish
-
-		if clientConfig.Hostname == nil {
-			err := fmt.Errorf("client config number %v requires hostname", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		if clientConfig.Endpoint == nil {
-			err := fmt.Errorf("client config number %v requires endpoint", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Endpoint = *clientConfig.Endpoint
-
-		if clientConfig.Username == nil {
-			err := fmt.Errorf("client config number %v requires username", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Username = *clientConfig.Username
-
-		if clientConfig.Password == nil {
-			err := fmt.Errorf("client config number %v requires password", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Password = *clientConfig.Password
-
-		gofishConfig.Insecure = true
-		if clientConfig.Insecure != nil {
-			gofishConfig.Insecure = *clientConfig.Insecure
-		}
-	}
-
-	return r, nil
-}

receivers/sampleReceiver.go

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

scripts/cc-metric-collector.config

@@ -16,8 +16,5 @@ 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
+# Only used on systemd systems
+PID_FILE_DIR=/var/run

scripts/cc-metric-collector.deb.control

@@ -1,12 +0,0 @@
-Package: cc-metric-collector
-Version: {VERSION}
-Installed-Size: {INSTALLED_SIZE}
-Architecture: {ARCH}
-Maintainer: thomas.gruber@fau.de
-Depends: libc6 (>= 2.2.1)
-Build-Depends: debhelper-compat (= 13), git, golang-go
-Description: Metric collection daemon from the ClusterCockpit suite
-Homepage: https://github.com/ClusterCockpit/cc-metric-collector
-Source: cc-metric-collector
-Rules-Requires-Root: no
-

scripts/cc-metric-collector.init

@@ -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

scripts/cc-metric-collector.service

@@ -14,7 +14,11 @@ Restart=on-failure
 WorkingDirectory=/tmp
 RuntimeDirectory=cc-metric-collector
 RuntimeDirectoryMode=0750
-ExecStart=/usr/sbin/cc-metric-collector --config=${CONF_FILE}
+ExecStart=/usr/sbin/cc-metric-collector                                             \
+                            --config=${CONF_FILE}                                   \
+                            --pidfile=${PID_FILE_DIR}/cc-metric-collector.pid
+
+
 LimitNOFILE=10000
 TimeoutStopSec=20
 UMask=0027

scripts/cc-metric-collector.spec

@@ -1,5 +1,5 @@
 Name:           cc-metric-collector
-Version:        %{VERS}
+Version:        0.1
 Release:        1%{?dist}
 Summary:        Metric collection daemon from the ClusterCockpit suite
 
@@ -7,9 +7,8 @@ License:        MIT
 Source0:        %{name}-%{version}.tar.gz
 
 BuildRequires:  go-toolset
-BuildRequires:  systemd-rpm-macros
-# for header downloads
-BuildRequires:  wget
+# for internal LIKWID installation
+BuildRequires:  wget perl-Data-Dumper
 
 Provides:       %{name} = %{version}
 
@@ -27,23 +26,15 @@ make
 
 
 %install
-install -Dpm 0750 %{name} %{buildroot}%{_sbindir}/%{name}
+install -Dpm 0755 %{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
-install -Dpm 0600 receivers.json %{buildroot}%{_sysconfdir}/%{name}/receivers.json
-install -Dpm 0600 router.json %{buildroot}%{_sysconfdir}/%{name}/router.json
-install -Dpm 0644 scripts/%{name}.service %{buildroot}%{_unitdir}/%{name}.service
-install -Dpm 0600 scripts/%{name}.config %{buildroot}%{_sysconfdir}/default/%{name}
-install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.conf
+install -Dpm 644 scripts/%{name}.service %{buildroot}%{_unitdir}/%{name}.service
+install -Dpm 600 scripts/%{name}.config %{buildroot}%{_sysconfdir}/default/%{name}
 
 
 %check
 # go test should be here... :)
 
-%pre
-%sysusers_create_package scripts/%{name}.sysusers
-
 %post
 %systemd_post %{name}.service
 
@@ -51,25 +42,13 @@ install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.c
 %systemd_preun %{name}.service
 
 %files
-# Binary
-%attr(-,clustercockpit,clustercockpit) %{_sbindir}/%{name}
-# Config
 %dir %{_sysconfdir}/%{name}
-%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/%{name}.json
-%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/collectors.json
-%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/sinks.json
-%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/receivers.json
-%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/router.json
-# Systemd
+%{_sbindir}/%{name}
 %{_unitdir}/%{name}.service
 %{_sysconfdir}/default/%{name}
-%{_sysusersdir}/%{name}.conf
+%config(noreplace) %{_sysconfdir}/%{name}/%{name}.json
+
 
 %changelog
-* Thu Mar 03 2022 Thomas Gruber - 0.3
-- Add clustercockpit user installation
-* Mon Feb 14 2022 Thomas Gruber - 0.2
-- Add component specific configuration files
-- Add %attr to config files
 * Mon Nov 22 2021 Thomas Gruber - 0.1
 - Initial spec file

scripts/cc-metric-collector.sysusers

@@ -1,2 +0,0 @@
-#Type Name           ID GECOS                     Home directory           Shell
-u     clustercockpit -  "User for ClusterCockpit" /run/cc-metric-collector /sbin/nologin

scripts/likwid_perfgroup_to_cc_config.py

@@ -1,83 +0,0 @@
-#!/usr/bin/env python3
-
-import os, os.path, sys, getopt, re, json
-
-def which(cmd):
-    ospath = os.environ.get("PATH", "")
-    for p in ospath.split(":"):
-        testcmd = os.path.join(p, cmd)
-        if os.access(testcmd, os.X_OK):
-            return testcmd
-    return None
-
-def group_to_json(groupfile):
-    gdata = []
-    with open(groupfile, "r") as fp:
-        gdata = fp.read().strip().split("\n")
-    events = {}
-    metrics = []
-    parse_events = False
-    parse_metrics = False
-    for line in gdata:
-        if line == "EVENTSET":
-            parse_events = True
-            parse_metrics = False
-            continue
-        if line == "METRICS":
-            parse_events = False
-            parse_metrics = True
-            continue
-        if len(line) == 0 or line.startswith("SHORT") or line == "LONG":
-            parse_events = False
-            parse_metrics = False
-            continue
-        if parse_events:
-            m = re.match("([\w\d]+)\s+([\w\d_]+)", line)
-            if m:
-                events[m.group(1)] = m.group(2)
-        if parse_metrics:
-            llist = re.split("\s+", line)
-            calc = llist[-1]
-            metric = " ".join(llist[:-1])
-            scope = "hwthread"
-            if "BOX" in calc:
-                scope = "socket"
-            if "PWR" in calc:
-                scope = "socket"
-
-            m = {"name" : metric, "calc": calc, "scope" : scope, "publish" : True}
-            metrics.append(m)
-    return {"events" : events, "metrics" : metrics}
-
-if len(sys.argv) != 3:
-    print("Usage: $0 <likwid-arch> <group-name>")
-    sys.exit(1)
-
-
-arch = sys.argv[1]
-group = sys.argv[2]
-
-ltopo = which("likwid-topology")
-if not ltopo:
-    print("Cannot find LIKWID installation. Please add LIKWID bin folder to your PATH.")
-    sys.exit(1)
-
-bindir = os.path.dirname(ltopo)
-
-groupdir = os.path.normpath(os.path.join(bindir, "../share/likwid/perfgroups"))
-if not os.path.exists(groupdir):
-    print("Cannot find LIKWID performance groups in default install location")
-    sys.exit(1)
-
-archdir = os.path.join(groupdir, arch)
-if not os.path.exists(archdir):
-    print("Cannot find LIKWID performance groups for architecture {}".format(arch))
-    sys.exit(1)
-
-groupfile = os.path.join(archdir, "{}.txt".format(group))
-if not os.path.exists(groupfile):
-    print("Cannot find LIKWID performance group {} for architecture {}".format(group, arch))
-    sys.exit(1)
-
-gdata = group_to_json(groupfile)
-print(json.dumps(gdata, sort_keys=True, indent=2))

sinks.json

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

sinks/README.md

@@ -2,27 +2,17 @@
 
 This folder contains the SinkManager and sink implementations for the cc-metric-collector.
 
-# Available sinks:
-- [`stdout`](./stdoutSink.md): Print all metrics to `stdout`, `stderr` or a file
-- [`http`](./httpSink.md): Send metrics to an HTTP server as POST requests
-- [`influxdb`](./influxSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database
-- [`influxasync`](./influxAsyncSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database with non-blocking write API
-- [`nats`](./natsSink.md): Publish metrics to the [NATS](https://nats.io/) network overlay system
-- [`ganglia`](./gangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) using the `gmetric` CLI tool
-- [`libganglia`](./libgangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) directly using `libganglia.so`
-- [`prometeus`](./prometheusSink.md): Publish metrics for the [Prometheus Monitoring System](https://prometheus.io/)
-
 # Configuration
 
 The configuration file for the sinks is a list of configurations. The `type` field in each specifies which sink to initialize.
 
 ```json
 [
-  "mystdout" : {
+  {
     "type" : "stdout",
     "meta_as_tags" : false
   },
-  "metricstore" : {
+  {
     "type" : "http",
     "host" : "localhost",
     "port" : "4123",
@@ -32,75 +22,78 @@ The configuration file for the sinks is a list of configurations. The `type` fie
 ]
 ```
 
+This example initializes two sinks, the `stdout` sink printing all metrics to the STDOUT and the `http` sink with the given `host`, `port`, `database` and `password`.
+
+If `meta_as_tags` is set, all meta information attached to CCMetric are printed out as tags.
+
+## Type `stdout`
+
+```json
+{
+  "type" : "stdout",
+  "meta_as_tags" : <true|false>
+}
+```
+
+The `stdout` sink dumps all metrics to the STDOUT.
+
+## Type `http`
+
+```json
+{
+  "type" : "http",
+  "host" : "<hostname>",
+  "port" : "<portnumber>",
+  "database" : "<database name>",
+  "password" : "<jwt token>",
+  "meta_as_tags" : <true|false>
+}
+```
+The sink uses POST requests to send metrics to `http://<host>:<port>/<database>` using the JWT token as a JWT in the 'Authorization' header.
+
+## Type `nats`
+
+```json
+{
+  "type" : "nats",
+  "host" : "<hostname>",
+  "port" : "<portnumber>",
+  "user" : "<username>",
+  "password" : "<password>",
+  "database" : "<database name>"
+  "meta_as_tags" : <true|false>
+}
+```
+
+This sink publishes the CCMetric in a NATS environment using `host`, `port`, `user` and `password` for connecting. The metrics are published using the topic `database`. 
+
+## Type `influxdb`
+
+```json
+{
+  "type" : "influxdb",
+  "host" : "<hostname>",
+  "port" : "<portnumber>",
+  "user" : "<username>",
+  "password" : "<password or API key>",
+  "database" : "<database name>"
+  "organization": "<InfluxDB v2 organization>",
+  "ssl" : <true|false>,
+  "meta_as_tags" : <true|false>
+}
+```
+
+This sink submits the CCMetrics to an InfluxDB time-series database. It uses `host`, `port` and `ssl` for connecting. For authentification, it uses either `user:password` if `user` is set and only `password` as API key. The `organization` and `database` are used for writing to the correct database.
 
 
 
 # Contributing own sinks
-A sink contains five functions and is derived from the type `sink`:
-* `Init(name string, config json.RawMessage) error`
+A sink contains three functions and is derived from the type `Sink`:
+* `Init(config SinkConfig) error`
 * `Write(point CCMetric) error`
 * `Flush() error`
 * `Close()`
-* `New<Typename>(name string, config json.RawMessage) (Sink, error)` (calls the `Init()` function)
 
 The data structures should be set up in `Init()` like opening a file or server connection. The `Write()` function writes/sends the data. For non-blocking sinks, the `Flush()` method tells the sink to drain its internal buffers. The `Close()` function should tear down anything created in `Init()`.
 
 Finally, the sink needs to be registered in the `sinkManager.go`. There is a list of sinks called `AvailableSinks` which is a map (`sink_type_string` -> `pointer to sink interface`). Add a new entry with a descriptive name and the new sink.
-
-## Sample sink
-
-```go
-package sinks
-
-import (
-	"encoding/json"
-	"log"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-type SampleSinkConfig struct {
-	defaultSinkConfig  // defines JSON tags for 'name' and 'meta_as_tags'
-}
-
-type SampleSink struct {
-	sink              // declarate 'name' and 'meta_as_tags'
-	config StdoutSinkConfig // entry point to the SampleSinkConfig
-}
-
-// Initialize the sink by giving it a name and reading in the config JSON
-func (s *SampleSink) Init(name string, config json.RawMessage) error {
-	s.name = fmt.Sprintf("SampleSink(%s)", name)   // Always specify a name here
-  // Read in the config JSON
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &s.config)
-		if err != nil {
-			return err
-		}
-	}
-	return nil
-}
-
-// Code to submit a single CCMetric to the sink
-func (s *SampleSink) Write(point lp.CCMetric) error {
-	log.Print(point)
-	return nil
-}
-
-// If the sink uses batched sends internally, you can tell to flush its buffers
-func (s *SampleSink) Flush() error {
-	return nil
-}
-
-
-// Close sink: close network connection, close files, close libraries, ...
-func (s *SampleSink) Close() {}
-
-
-// New function to create a new instance of the sink
-func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
-	s := new(SampleSink)
-	err := s.Init(name, config)
-	return s, err
-}
-
-```

sinks/gangliaCommon.go

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

sinks/gangliaSink.go

@@ -1,83 +1,76 @@
 package sinks
 
 import (
-	"encoding/json"
-	"errors"
 	"fmt"
+	"log"
 	"strings"
 
 	//	"time"
 	"os/exec"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const GMETRIC_EXEC = `gmetric`
-const GMETRIC_CONFIG = `/etc/ganglia/gmond.conf`
-
-type GangliaSinkConfig struct {
-	defaultSinkConfig
-	GmetricPath     string `json:"gmetric_path,omitempty"`
-	GmetricConfig   string `json:"gmetric_config,omitempty"`
-	AddGangliaGroup bool   `json:"add_ganglia_group,omitempty"`
-	AddTagsAsDesc   bool   `json:"add_tags_as_desc,omitempty"`
-	ClusterName     string `json:"cluster_name,omitempty"`
-	AddTypeToName   bool   `json:"add_type_to_name,omitempty"`
-	AddUnits        bool   `json:"add_units,omitempty"`
-}
 
 type GangliaSink struct {
-	sink
+	Sink
 	gmetric_path string
-	gmetric_config string
-	config         GangliaSinkConfig
+}
+
+func (s *GangliaSink) Init(config sinkConfig) error {
+	p, err := exec.LookPath(string(GMETRIC_EXEC))
+	if err == nil {
+		s.gmetric_path = p
+	}
+	return err
 }
 
 func (s *GangliaSink) Write(point lp.CCMetric) error {
 	var err error = nil
-	//var tagsstr []string
+	var tagsstr []string
 	var argstr []string
-
-	// Get metric config (type, value, ... in suitable format)
-	conf := GetCommonGangliaConfig(point)
-	if len(conf.Type) == 0 {
-		conf = GetGangliaConfig(point)
+	for _, t := range point.TagList() {
+		switch t.Key {
+		case "cluster":
+			argstr = append(argstr, fmt.Sprintf("--cluster=%s", t.Value))
+		case "unit":
+			argstr = append(argstr, fmt.Sprintf("--units=%s", t.Value))
+		case "group":
+			argstr = append(argstr, fmt.Sprintf("--group=%s", t.Value))
+		default:
+			tagsstr = append(tagsstr, fmt.Sprintf("%s=%s", t.Key, t.Value))
 		}
-	if len(conf.Type) == 0 {
-		return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
 	}
-
-	if s.config.AddGangliaGroup {
-		argstr = append(argstr, fmt.Sprintf("--group=%s", conf.Group))
+	if len(tagsstr) > 0 {
+		argstr = append(argstr, fmt.Sprintf("--desc=%q", strings.Join(tagsstr, ",")))
 	}
-	if s.config.AddUnits && len(conf.Unit) > 0 {
-		argstr = append(argstr, fmt.Sprintf("--units=%s", conf.Unit))
+	argstr = append(argstr, fmt.Sprintf("--name=%s", point.Name()))
+	for _, f := range point.FieldList() {
+		if f.Key == "value" {
+			switch f.Value.(type) {
+			case float64:
+				argstr = append(argstr, fmt.Sprintf("--value=%v", f.Value.(float64)))
+				argstr = append(argstr, "--type=double")
+			case float32:
+				argstr = append(argstr, fmt.Sprintf("--value=%v", f.Value.(float32)))
+				argstr = append(argstr, "--type=float")
+			case int:
+				argstr = append(argstr, fmt.Sprintf("--value=%d", f.Value.(int)))
+				argstr = append(argstr, "--type=int32")
+			case int64:
+				argstr = append(argstr, fmt.Sprintf("--value=%d", f.Value.(int64)))
+				argstr = append(argstr, "--type=int32")
+			case string:
+				argstr = append(argstr, fmt.Sprintf("--value=%q", f.Value.(string)))
+				argstr = append(argstr, "--type=string")
 			}
-
-	if len(s.config.ClusterName) > 0 {
-		argstr = append(argstr, fmt.Sprintf("--cluster=%s", s.config.ClusterName))
 		}
-	// if s.config.AddTagsAsDesc && len(tagsstr) > 0 {
-	// 	argstr = append(argstr, fmt.Sprintf("--desc=%q", strings.Join(tagsstr, ",")))
-	// }
-	if len(s.gmetric_config) > 0 {
-		argstr = append(argstr, fmt.Sprintf("--conf=%s", s.gmetric_config))
 	}
-	if s.config.AddTypeToName {
-		argstr = append(argstr, fmt.Sprintf("--name=%s", GangliaMetricName(point)))
-	} else {
-		argstr = append(argstr, fmt.Sprintf("--name=%s", conf.Name))
-	}
-	argstr = append(argstr, fmt.Sprintf("--slope=%s", conf.Slope))
-	argstr = append(argstr, fmt.Sprintf("--value=%s", conf.Value))
-	argstr = append(argstr, fmt.Sprintf("--type=%s", conf.Type))
-	argstr = append(argstr, fmt.Sprintf("--tmax=%d", conf.Tmax))
-
-	cclog.ComponentDebug(s.name, s.gmetric_path, strings.Join(argstr, " "))
-	command := exec.Command(s.gmetric_path, argstr...)
-	command.Wait()
-	_, err = command.Output()
+	log.Print(s.gmetric_path, " ", strings.Join(argstr, " "))
+	//	command := exec.Command(string(GMETRIC_EXEC), strings.Join(argstr, " "))
+	//	command.Wait()
+	//	_, err := command.Output()
 	return err
 }
 
@@ -87,38 +80,3 @@ func (s *GangliaSink) Flush() error {
 
 func (s *GangliaSink) Close() {
 }
-
-func NewGangliaSink(name string, config json.RawMessage) (Sink, error) {
-	s := new(GangliaSink)
-	s.name = fmt.Sprintf("GangliaSink(%s)", name)
-	s.config.AddTagsAsDesc = false
-	s.config.AddGangliaGroup = false
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &s.config)
-		if err != nil {
-			cclog.ComponentError(s.name, "Error reading config for", s.name, ":", err.Error())
-			return nil, err
-		}
-	}
-	s.gmetric_path = ""
-	s.gmetric_config = ""
-	if len(s.config.GmetricPath) > 0 {
-		p, err := exec.LookPath(s.config.GmetricPath)
-		if err == nil {
-			s.gmetric_path = p
-		}
-	}
-	if len(s.gmetric_path) == 0 {
-		p, err := exec.LookPath(string(GMETRIC_EXEC))
-		if err == nil {
-			s.gmetric_path = p
-		}
-	}
-	if len(s.gmetric_path) == 0 {
-		return nil, errors.New("cannot find executable 'gmetric'")
-	}
-	if len(s.config.GmetricConfig) > 0 {
-		s.gmetric_config = s.config.GmetricConfig
-	}
-	return s, nil
-}

sinks/gangliaSink.md

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

sinks/httpSink.go

@@ -2,179 +2,69 @@ package sinks
 
 import (
 	"bytes"
-	"encoding/json"
 	"errors"
 	"fmt"
 	"net/http"
-	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 
-type HttpSinkConfig struct {
-	defaultSinkConfig
-	URL             string `json:"url,omitempty"`
-	JWT             string `json:"jwt,omitempty"`
-	Timeout         string `json:"timeout,omitempty"`
-	IdleConnTimeout string `json:"idle_connection_timeout,omitempty"`
-	FlushDelay      string `json:"flush_delay,omitempty"`
-	MaxRetries      int    `json:"max_retries,omitempty"`
-}
-
 type HttpSink struct {
 	sink
 	client   *http.Client
+	url, jwt string
 	encoder  *influx.Encoder
-	lock            sync.Mutex // Flush() runs in another goroutine, so this lock has to protect the buffer
 	buffer   *bytes.Buffer
-	flushTimer      *time.Timer
-	config          HttpSinkConfig
-	idleConnTimeout time.Duration
-	timeout         time.Duration
-	flushDelay      time.Duration
 }
 
-func (s *HttpSink) Write(m lp.CCMetric) error {
-	p := m.ToPoint(s.meta_as_tags)
-	s.lock.Lock()
-	firstWriteOfBatch := s.buffer.Len() == 0
-	_, err := s.encoder.Encode(p)
-	s.lock.Unlock()
-	if err != nil {
-		cclog.ComponentError(s.name, "encoding failed:", err.Error())
-		return err
+func (s *HttpSink) Init(config sinkConfig) error {
+	s.name = "HttpSink"
+	if len(config.Host) == 0 || len(config.Port) == 0 || len(config.Database) == 0 {
+		return errors.New("`host`, `port` and `database` config options required for TCP sink")
 	}
 
-	if s.flushDelay == 0 {
-		return s.Flush()
-	}
-
-	if firstWriteOfBatch {
-		if s.flushTimer == nil {
-			s.flushTimer = time.AfterFunc(s.flushDelay, func() {
-				if err := s.Flush(); err != nil {
-					cclog.ComponentError(s.name, "flush failed:", err.Error())
-				}
-			})
-		} else {
-			s.flushTimer.Reset(s.flushDelay)
-		}
-	}
+	s.client = &http.Client{}
+	s.url = fmt.Sprintf("http://%s:%s/%s", config.Host, config.Port, config.Database)
+	s.port = config.Port
+	s.jwt = config.Password
+	s.buffer = &bytes.Buffer{}
+	s.encoder = influx.NewEncoder(s.buffer)
+	s.encoder.SetPrecision(time.Second)
 
 	return nil
 }
 
+func (s *HttpSink) Write(point lp.CCMetric) error {
+	_, err := s.encoder.Encode(point)
+	return err
+}
+
 func (s *HttpSink) Flush() error {
-	// Own lock for as short as possible: the time it takes to copy the buffer.
-	s.lock.Lock()
-	buf := make([]byte, s.buffer.Len())
-	copy(buf, s.buffer.Bytes())
+	req, err := http.NewRequest(http.MethodPost, s.url, s.buffer)
+	if err != nil {
+		return err
+	}
+
+	if len(s.jwt) != 0 {
+		req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", s.jwt))
+	}
+
+	res, err := s.client.Do(req)
 	s.buffer.Reset()
-	s.lock.Unlock()
-	if len(buf) == 0 {
-		return nil
-	}
 
-	var res *http.Response
-	for i := 0; i < s.config.MaxRetries; i++ {
-		// Create new request to send buffer
-		req, err := http.NewRequest(http.MethodPost, s.config.URL, bytes.NewReader(buf))
 	if err != nil {
-			cclog.ComponentError(s.name, "failed to create request:", err.Error())
 		return err
 	}
 
-		// Set authorization header
-		if len(s.config.JWT) != 0 {
-			req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", s.config.JWT))
-		}
-
-		// Do request
-		res, err = s.client.Do(req)
-		if err != nil {
-			cclog.ComponentError(s.name, "transport/tcp error:", err.Error())
-			// Wait between retries
-			time.Sleep(time.Duration(i+1) * (time.Second / 2))
-			continue
-		}
-
-		break
-	}
-
-	if res == nil {
-		return errors.New("flush failed due to repeated errors")
-	}
-
-	// Handle application errors
-	if res.StatusCode != http.StatusOK {
-		err := errors.New(res.Status)
-		cclog.ComponentError(s.name, "application error:", err.Error())
-		return err
+	if res.StatusCode != 200 {
+		return errors.New(res.Status)
 	}
 
 	return nil
 }
 
 func (s *HttpSink) Close() {
-	s.flushTimer.Stop()
-	if err := s.Flush(); err != nil {
-		cclog.ComponentError(s.name, "flush failed:", err.Error())
-	}
 	s.client.CloseIdleConnections()
 }
-
-func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
-	s := new(HttpSink)
-	// Set default values
-	s.name = fmt.Sprintf("HttpSink(%s)", name)
-	s.config.IdleConnTimeout = "120s" // should be larger than the measurement interval.
-	s.config.Timeout = "5s"
-	s.config.FlushDelay = "5s"
-	s.config.MaxRetries = 3
-
-	// Read config
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &s.config)
-		if err != nil {
-			return nil, err
-		}
-	}
-	if len(s.config.URL) == 0 {
-		return nil, errors.New("`url` config option is required for HTTP sink")
-	}
-	if len(s.config.IdleConnTimeout) > 0 {
-		t, err := time.ParseDuration(s.config.IdleConnTimeout)
-		if err == nil {
-			s.idleConnTimeout = t
-		}
-	}
-	if len(s.config.Timeout) > 0 {
-		t, err := time.ParseDuration(s.config.Timeout)
-		if err == nil {
-			s.timeout = t
-		}
-	}
-	if len(s.config.FlushDelay) > 0 {
-		t, err := time.ParseDuration(s.config.FlushDelay)
-		if err == nil {
-			s.flushDelay = t
-		}
-	}
-	// Create lookup map to use meta infos as tags in the output metric
-	s.meta_as_tags = make(map[string]bool)
-	for _, k := range s.config.MetaAsTags {
-		s.meta_as_tags[k] = true
-	}
-	tr := &http.Transport{
-		MaxIdleConns:    1, // We will only ever talk to one host.
-		IdleConnTimeout: s.idleConnTimeout,
-	}
-	s.client = &http.Client{Transport: tr, Timeout: s.timeout}
-	s.buffer = &bytes.Buffer{}
-	s.encoder = influx.NewEncoder(s.buffer)
-	s.encoder.SetPrecision(time.Second)
-	return s, nil
-}

sinks/httpSink.md

@@ -1,29 +0,0 @@
-## `http` sink
-
-The `http` sink uses POST requests to a HTTP server to submit the metrics in the InfluxDB line-protocol format. It uses JSON web tokens for authentification. The sink creates batches of metrics before sending, to reduce the HTTP traffic.
-
-### Configuration structure
-
-```json
-{
-  "<name>": {
-    "type": "http",
-    "meta_as_tags" : true,
-    "url" : "https://my-monitoring.example.com:1234/api/write",
-    "jwt" : "blabla.blabla.blabla",
-    "timeout": "5s",
-    "max_idle_connections" : 10,
-    "idle_connection_timeout" : "5s",
-    "flush_delay": "2s",
-  }
-}
-```
-
-- `type`: makes the sink an `http` sink
-- `meta_as_tags`: print all meta information as tags in the output (optional)
-- `url`: The full URL of the endpoint
-- `jwt`: JSON web tokens for authentification (Using the *Bearer* scheme)
-- `timeout`: General timeout for the HTTP client (default '5s')
-- `max_idle_connections`: Maximally idle connections (default 10)
-- `idle_connection_timeout`: Timeout for idle connections (default '5s')
-- `flush_delay`: Batch all writes arriving in during this duration (default '1s', batching can be disabled by setting it to 0)

sinks/influxAsyncSink.go

@@ -1,239 +0,0 @@
-package sinks
-
-import (
-	"context"
-	"crypto/tls"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
-	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
-	influxdb2ApiHttp "github.com/influxdata/influxdb-client-go/v2/api/http"
-)
-
-type InfluxAsyncSinkConfig struct {
-	defaultSinkConfig
-	Host         string `json:"host,omitempty"`
-	Port         string `json:"port,omitempty"`
-	Database     string `json:"database,omitempty"`
-	User         string `json:"user,omitempty"`
-	Password     string `json:"password,omitempty"`
-	Organization string `json:"organization,omitempty"`
-	SSL          bool   `json:"ssl,omitempty"`
-	// Maximum number of points sent to server in single request. Default 5000
-	BatchSize uint `json:"batch_size,omitempty"`
-	// Interval, in ms, in which is buffer flushed if it has not been already written (by reaching batch size) . Default 1000ms
-	FlushInterval         uint   `json:"flush_interval,omitempty"`
-	InfluxRetryInterval   string `json:"retry_interval,omitempty"`
-	InfluxExponentialBase uint   `json:"retry_exponential_base,omitempty"`
-	InfluxMaxRetries      uint   `json:"max_retries,omitempty"`
-	InfluxMaxRetryTime    string `json:"max_retry_time,omitempty"`
-	CustomFlushInterval   string `json:"custom_flush_interval,omitempty"`
-	MaxRetryAttempts      uint   `json:"max_retry_attempts,omitempty"`
-}
-
-type InfluxAsyncSink struct {
-	sink
-	client              influxdb2.Client
-	writeApi            influxdb2Api.WriteAPI
-	errors              <-chan error
-	config              InfluxAsyncSinkConfig
-	influxRetryInterval uint
-	influxMaxRetryTime  uint
-	customFlushInterval time.Duration
-	flushTimer          *time.Timer
-}
-
-func (s *InfluxAsyncSink) connect() error {
-	var auth string
-	var uri string
-	if s.config.SSL {
-		uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
-	} else {
-		uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
-	}
-	if len(s.config.User) == 0 {
-		auth = s.config.Password
-	} else {
-		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
-	}
-	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
-	clientOptions := influxdb2.DefaultOptions()
-	if s.config.BatchSize != 0 {
-		cclog.ComponentDebug(s.name, "Batch size", s.config.BatchSize)
-		clientOptions.SetBatchSize(s.config.BatchSize)
-	}
-	if s.config.FlushInterval != 0 {
-		cclog.ComponentDebug(s.name, "Flush interval", s.config.FlushInterval)
-		clientOptions.SetFlushInterval(s.config.FlushInterval)
-	}
-	if s.influxRetryInterval != 0 {
-		cclog.ComponentDebug(s.name, "MaxRetryInterval", s.influxRetryInterval)
-		clientOptions.SetMaxRetryInterval(s.influxRetryInterval)
-	}
-	if s.influxMaxRetryTime != 0 {
-		cclog.ComponentDebug(s.name, "MaxRetryTime", s.influxMaxRetryTime)
-		clientOptions.SetMaxRetryTime(s.influxMaxRetryTime)
-	}
-	if s.config.InfluxExponentialBase != 0 {
-		cclog.ComponentDebug(s.name, "Exponential Base", s.config.InfluxExponentialBase)
-		clientOptions.SetExponentialBase(s.config.InfluxExponentialBase)
-	}
-	if s.config.InfluxMaxRetries != 0 {
-		cclog.ComponentDebug(s.name, "Max Retries", s.config.InfluxMaxRetries)
-		clientOptions.SetMaxRetries(s.config.InfluxMaxRetries)
-	}
-	clientOptions.SetTLSConfig(
-		&tls.Config{
-			InsecureSkipVerify: true,
-		},
-	).SetPrecision(time.Second)
-
-	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
-	s.writeApi = s.client.WriteAPI(s.config.Organization, s.config.Database)
-	ok, err := s.client.Ping(context.Background())
-	if err != nil {
-		return err
-	}
-	if !ok {
-		return fmt.Errorf("connection to %s not healthy", uri)
-	}
-	s.writeApi.SetWriteFailedCallback(func(batch string, err influxdb2ApiHttp.Error, retryAttempts uint) bool {
-		mlist := strings.Split(batch, "\n")
-		cclog.ComponentError(s.name, fmt.Sprintf("Failed to write batch with %d metrics %d times (max: %d): %s", len(mlist), retryAttempts, s.config.MaxRetryAttempts, err.Error()))
-		return retryAttempts <= s.config.MaxRetryAttempts
-	})
-	return nil
-}
-
-func (s *InfluxAsyncSink) Write(m lp.CCMetric) error {
-	if s.customFlushInterval != 0 && s.flushTimer == nil {
-		// Run a batched flush for all lines that have arrived in the defined interval
-		s.flushTimer = time.AfterFunc(s.customFlushInterval, func() {
-			if err := s.Flush(); err != nil {
-				cclog.ComponentError(s.name, "flush failed:", err.Error())
-			}
-		})
-	}
-	s.writeApi.WritePoint(
-		m.ToPoint(s.meta_as_tags),
-	)
-	return nil
-}
-
-func (s *InfluxAsyncSink) Flush() error {
-	cclog.ComponentDebug(s.name, "Flushing")
-	s.writeApi.Flush()
-	if s.customFlushInterval != 0 && s.flushTimer != nil {
-		s.flushTimer = nil
-	}
-	return nil
-}
-
-func (s *InfluxAsyncSink) Close() {
-	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
-	s.writeApi.Flush()
-	s.client.Close()
-}
-
-func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
-	s := new(InfluxAsyncSink)
-	s.name = fmt.Sprintf("InfluxSink(%s)", name)
-
-	// Set default for maximum number of points sent to server in single request.
-	s.config.BatchSize = 0
-	s.influxRetryInterval = 0
-	//s.config.InfluxRetryInterval = "1s"
-	s.influxMaxRetryTime = 0
-	//s.config.InfluxMaxRetryTime = "168h"
-	s.config.InfluxMaxRetries = 0
-	s.config.InfluxExponentialBase = 0
-	s.config.FlushInterval = 0
-	s.config.CustomFlushInterval = ""
-	s.customFlushInterval = time.Duration(0)
-	s.config.MaxRetryAttempts = 1
-
-	// Default retry intervals (in seconds)
-	// 1 2
-	// 2 4
-	// 4 8
-	// 8 16
-	// 16 32
-	// 32 64
-	// 64 128
-	// 128 256
-	// 256 512
-	// 512 1024
-	// 1024 2048
-	// 2048 4096
-	// 4096 8192
-	// 8192 16384
-	// 16384 32768
-	// 32768 65536
-	// 65536 131072
-	// 131072 262144
-	// 262144 524288
-
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &s.config)
-		if err != nil {
-			return nil, err
-		}
-	}
-	if len(s.config.Port) == 0 {
-		return nil, errors.New("Missing port configuration required by InfluxSink")
-	}
-	if len(s.config.Database) == 0 {
-		return nil, errors.New("Missing database configuration required by InfluxSink")
-	}
-	if len(s.config.Organization) == 0 {
-		return nil, errors.New("Missing organization configuration required by InfluxSink")
-	}
-	if len(s.config.Password) == 0 {
-		return nil, errors.New("Missing password configuration required by InfluxSink")
-	}
-	// Create lookup map to use meta infos as tags in the output metric
-	s.meta_as_tags = make(map[string]bool)
-	for _, k := range s.config.MetaAsTags {
-		s.meta_as_tags[k] = true
-	}
-
-	toUint := func(duration string, def uint) uint {
-		t, err := time.ParseDuration(duration)
-		if err == nil {
-			return uint(t.Milliseconds())
-		}
-		return def
-	}
-	s.influxRetryInterval = toUint(s.config.InfluxRetryInterval, s.influxRetryInterval)
-	s.influxMaxRetryTime = toUint(s.config.InfluxMaxRetryTime, s.influxMaxRetryTime)
-
-	// Use a own timer for calling Flush()
-	if len(s.config.CustomFlushInterval) > 0 {
-		t, err := time.ParseDuration(s.config.CustomFlushInterval)
-		if err != nil {
-			return nil, fmt.Errorf("invalid duration in 'custom_flush_interval': %v", err)
-		}
-		s.customFlushInterval = t
-	}
-
-	// Connect to InfluxDB server
-	if err := s.connect(); err != nil {
-		return nil, fmt.Errorf("unable to connect: %v", err)
-	}
-
-	// Start background: Read from error channel
-	s.errors = s.writeApi.Errors()
-	go func() {
-		for err := range s.errors {
-			cclog.ComponentError(s.name, err.Error())
-		}
-	}()
-
-	return s, nil
-}

sinks/influxAsyncSink.md

@@ -1,44 +0,0 @@
-## `influxasync` sink
-
-The `influxasync` sink uses the official [InfluxDB golang client](https://pkg.go.dev/github.com/influxdata/influxdb-client-go/v2) to write the metrics to an InfluxDB database in a **non-blocking** fashion. It provides only support for V2 write endpoints (InfluxDB 1.8.0 or later).
-
-
-### Configuration structure
-
-```json
-{
-  "<name>": {
-    "type": "influxasync",
-    "meta_as_tags" : true,
-    "database" : "mymetrics",
-    "host": "dbhost.example.com",
-    "port": "4222",
-    "user": "exampleuser",
-    "password" : "examplepw",
-    "organization": "myorg",
-    "ssl": true,
-    "batch_size": 200,
-    "retry_interval" : "1s",
-    "retry_exponential_base" : 2,
-    "max_retries": 20,
-    "max_retry_time" : "168h"
-  }
-}
-```
-
-- `type`: makes the sink an `influxdb` sink
-- `meta_as_tags`: print all meta information as tags in the output (optional)
-- `database`: All metrics are written to this bucket 
-- `host`: Hostname of the InfluxDB database server
-- `port`: Portnumber (as string) of the InfluxDB database server
-- `user`: Username for basic authentification
-- `password`: Password for basic authentification
-- `organization`: Organization in the InfluxDB
-- `ssl`: Use SSL connection
-- `batch_size`: batch up metrics internally, default 100
-- `retry_interval`: Base retry interval for failed write requests, default 1s
-- `retry_exponential_base`: The retry interval is exponentially increased with this base, default 2
-- `max_retries`: Maximal number of retry attempts
-- `max_retry_time`: Maximal time to retry failed writes, default 168h (one week)
-
-For information about the calculation of the retry interval settings, see [offical influxdb-client-go documentation](https://github.com/influxdata/influxdb-client-go#handling-of-failed-async-writes)

sinks/influxSink.go

@@ -3,219 +3,85 @@ package sinks
 import (
 	"context"
 	"crypto/tls"
-	"encoding/json"
 	"errors"
 	"fmt"
-	"sync"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
 	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
-	"github.com/influxdata/influxdb-client-go/v2/api/write"
+	"log"
 )
 
 type InfluxSink struct {
 	sink
 	client    influxdb2.Client
 	writeApi  influxdb2Api.WriteAPIBlocking
-	config   struct {
-		defaultSinkConfig
-		Host         string `json:"host,omitempty"`
-		Port         string `json:"port,omitempty"`
-		Database     string `json:"database,omitempty"`
-		User         string `json:"user,omitempty"`
-		Password     string `json:"password,omitempty"`
-		Organization string `json:"organization,omitempty"`
-		SSL          bool   `json:"ssl,omitempty"`
-		// Maximum number of points sent to server in single request. Default 100
-		BatchSize int `json:"batch_size,omitempty"`
-		// Interval, in which is buffer flushed if it has not been already written (by reaching batch size). Default 1s
-		FlushInterval string `json:"flush_delay,omitempty"`
-	}
-	batch      []*write.Point
-	flushTimer *time.Timer
-	flushDelay time.Duration
-	lock       sync.Mutex // Flush() runs in another goroutine, so this lock has to protect the buffer
+	retPolicy string
 }
 
-// connect connects to the InfluxDB server
 func (s *InfluxSink) connect() error {
-
-	// URI options:
-	// * http://host:port
-	// * https://host:port
-	var uri string
-	if s.config.SSL {
-		uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
-	} else {
-		uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
-	}
-
-	// Authentication options:
-	// * token
-	// * username:password
 	var auth string
-	if len(s.config.User) == 0 {
-		auth = s.config.Password
+	var uri string
+	if s.ssl {
+		uri = fmt.Sprintf("https://%s:%s", s.host, s.port)
 	} else {
-		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
+		uri = fmt.Sprintf("http://%s:%s", s.host, s.port)
+	}
+	if len(s.user) == 0 {
+		auth = s.password
+	} else {
+		auth = fmt.Sprintf("%s:%s", s.user, s.password)
+	}
+	log.Print("Using URI ", uri, " Org ", s.organization, " Bucket ", s.database)
+	s.client = influxdb2.NewClientWithOptions(uri, auth,
+		influxdb2.DefaultOptions().SetTLSConfig(&tls.Config{InsecureSkipVerify: true}))
+	s.writeApi = s.client.WriteAPIBlocking(s.organization, s.database)
+	return nil
 }
-	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
 
-	// Set influxDB client options
-	clientOptions := influxdb2.DefaultOptions()
+func (s *InfluxSink) Init(config sinkConfig) error {
+	s.name = "InfluxSink"
+	if len(config.Host) == 0 ||
+		len(config.Port) == 0 ||
+		len(config.Database) == 0 ||
+		len(config.Organization) == 0 ||
+		len(config.Password) == 0 {
+		return errors.New("Not all configuration variables set required by InfluxSink")
+	}
+	s.host = config.Host
+	s.port = config.Port
+	s.database = config.Database
+	s.organization = config.Organization
+	s.user = config.User
+	s.password = config.Password
+	s.ssl = config.SSL
+	s.meta_as_tags = config.MetaAsTags
+	return s.connect()
+}
 
-	// Do not check InfluxDB certificate
-	clientOptions.SetTLSConfig(
-		&tls.Config{
-			InsecureSkipVerify: true,
-		},
-	)
-
-	clientOptions.SetPrecision(time.Second)
-
-	// Create new writeAPI
-	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
-	s.writeApi = s.client.WriteAPIBlocking(s.config.Organization, s.config.Database)
-
-	// Check InfluxDB server accessibility
-	ok, err := s.client.Ping(context.Background())
-	if err != nil {
+func (s *InfluxSink) Write(point lp.CCMetric) error {
+	tags := map[string]string{}
+	fields := map[string]interface{}{}
+	for _, t := range point.TagList() {
+		tags[t.Key] = t.Value
+	}
+	if s.meta_as_tags {
+		for _, m := range point.MetaList() {
+			tags[m.Key] = m.Value
+		}
+	}
+	for _, f := range point.FieldList() {
+		fields[f.Key] = f.Value
+	}
+	p := influxdb2.NewPoint(point.Name(), tags, fields, point.Time())
+	err := s.writeApi.WritePoint(context.Background(), p)
 	return err
 }
-	if !ok {
-		return fmt.Errorf("connection to %s not healthy", uri)
-	}
-	return nil
-}
 
-func (s *InfluxSink) Write(m lp.CCMetric) error {
-
-	if len(s.batch) == 0 && s.flushDelay != 0 {
-		// This is the first write since the last flush, start the flushTimer!
-		if s.flushTimer != nil && s.flushTimer.Stop() {
-			cclog.ComponentDebug(s.name, "unexpected: the flushTimer was already running?")
-		}
-
-		// Run a batched flush for all lines that have arrived in the last flush delay interval
-		s.flushTimer = time.AfterFunc(
-			s.flushDelay,
-			func() {
-				if err := s.Flush(); err != nil {
-					cclog.ComponentError(s.name, "flush failed:", err.Error())
-				}
-			})
-	}
-
-	// Append metric to batch slice
-	p := m.ToPoint(s.meta_as_tags)
-	s.lock.Lock()
-	s.batch = append(s.batch, p)
-	s.lock.Unlock()
-
-	// Flush synchronously if "flush_delay" is zero
-	if s.flushDelay == 0 {
-		return s.Flush()
-	}
-
-	// Flush if batch size is reached
-	if len(s.batch) == s.config.BatchSize {
-		return s.Flush()
-	}
-
-	return nil
-}
-
-// Flush sends all metrics buffered in batch slice to InfluxDB server
 func (s *InfluxSink) Flush() error {
-
-	// Lock access to batch slice
-	s.lock.Lock()
-	defer s.lock.Unlock()
-
-	// Nothing to do, batch slice is empty
-	if len(s.batch) == 0 {
-		return nil
-	}
-
-	// Send metrics from batch slice
-	err := s.writeApi.WritePoint(context.Background(), s.batch...)
-	if err != nil {
-		cclog.ComponentError(s.name, "flush failed:", err.Error())
-		return err
-	}
-
-	// Clear batch slice
-	for i := range s.batch {
-		s.batch[i] = nil
-	}
-	s.batch = s.batch[:0]
-
 	return nil
 }
 
 func (s *InfluxSink) Close() {
-	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
-	s.flushTimer.Stop()
-	s.Flush()
+	log.Print("Closing InfluxDB connection")
 	s.client.Close()
 }
-
-// NewInfluxSink create a new InfluxDB sink
-func NewInfluxSink(name string, config json.RawMessage) (Sink, error) {
-	s := new(InfluxSink)
-	s.name = fmt.Sprintf("InfluxSink(%s)", name)
-
-	// Set config default values
-	s.config.BatchSize = 100
-	s.config.FlushInterval = "1s"
-
-	// Read config
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &s.config)
-		if err != nil {
-			return nil, err
-		}
-	}
-
-	if len(s.config.Host) == 0 {
-		return nil, errors.New("Missing host configuration required by InfluxSink")
-	}
-	if len(s.config.Port) == 0 {
-		return nil, errors.New("Missing port configuration required by InfluxSink")
-	}
-	if len(s.config.Database) == 0 {
-		return nil, errors.New("Missing database configuration required by InfluxSink")
-	}
-	if len(s.config.Organization) == 0 {
-		return nil, errors.New("Missing organization configuration required by InfluxSink")
-	}
-	if len(s.config.Password) == 0 {
-		return nil, errors.New("Missing password configuration required by InfluxSink")
-	}
-
-	// Create lookup map to use meta infos as tags in the output metric
-	s.meta_as_tags = make(map[string]bool)
-	for _, k := range s.config.MetaAsTags {
-		s.meta_as_tags[k] = true
-	}
-
-	// Configure flush delay duration
-	if len(s.config.FlushInterval) > 0 {
-		t, err := time.ParseDuration(s.config.FlushInterval)
-		if err == nil {
-			s.flushDelay = t
-		}
-	}
-
-	// allocate batch slice
-	s.batch = make([]*write.Point, 0, s.config.BatchSize)
-
-	// Connect to InfluxDB server
-	if err := s.connect(); err != nil {
-		return nil, fmt.Errorf("unable to connect: %v", err)
-	}
-	return s, nil
-}

sinks/influxSink.md

@@ -1,37 +0,0 @@
-## `influxdb` sink
-
-The `influxdb` sink uses the official [InfluxDB golang client](https://pkg.go.dev/github.com/influxdata/influxdb-client-go/v2) to write the metrics to an InfluxDB database in a **blocking** fashion. It provides only support for V2 write endpoints (InfluxDB 1.8.0 or later).
-
-
-### Configuration structure
-
-```json
-{
-  "<name>": {
-    "type": "influxdb",
-    "meta_as_tags" : true,
-    "database" : "mymetrics",
-    "host": "dbhost.example.com",
-    "port": "4222",
-    "user": "exampleuser",
-    "password" : "examplepw",
-    "organization": "myorg",
-    "ssl": true,
-    "flush_delay" : "1s",
-    "batch_size" : 100
-  }
-}
-```
-
-- `type`: makes the sink an `influxdb` sink
-- `meta_as_tags`: print all meta information as tags in the output (optional)
-- `database`: All metrics are written to this bucket 
-- `host`: Hostname of the InfluxDB database server
-- `port`: Portnumber (as string) of the InfluxDB database server
-- `user`: Username for basic authentification
-- `password`: Password for basic authentification
-- `organization`: Organization in the InfluxDB
-- `ssl`: Use SSL connection
-- `flush_delay`: Group metrics coming in to a single batch
-- `batch_size`: Maximal batch size
-