Add documentation of the internal structure of the LikwidCollector to its documentation

Create lockfile if it does not exist
Merge branch 'develop' of github.com:ClusterCockpit/cc-metric-collector into develop
2025-07-19 19:31:41 +02:00 · 2024-04-25 17:26:18 +02:00 · 2024-04-25 17:25:53 +02:00 · 2024-04-10 19:57:54 +02:00 · 2024-04-10 19:57:46 +02:00 · 2024-03-06 15:14:44 +01:00
9 changed files with 400 additions and 187 deletions
--- a/.github/workflows/Release.yml
+++ b/.github/workflows/Release.yml
@@ -45,10 +45,10 @@ jobs:
    - name: Install build dependencies
      run: |
          dnf --assumeyes install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm

    - name: RPM build MetricCollector
      id: rpmbuild
@@ -115,10 +115,10 @@ jobs:
    - name: Install build dependencies
      run: |
          dnf --assumeyes --disableplugin=subscription-manager install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm

    - name: RPM build MetricCollector
      id: rpmbuild
--- a/.github/workflows/runonce.yml
+++ b/.github/workflows/runonce.yml
@@ -10,32 +10,6 @@ on:

 jobs:

-  #
-  # Job build-1-20
-  # Build on latest Ubuntu using golang version 1.20
-  #
-  build-1-20:
-    runs-on: ubuntu-latest
-    steps:
-    # See: https://github.com/marketplace/actions/checkout
-    # Checkout git repository and submodules
-    - name: Checkout
-      uses: actions/checkout@v4
-      with:
-        submodules: recursive
-
-    # See: https://github.com/marketplace/actions/setup-go-environment
-    - name: Setup Golang
-      uses: actions/setup-go@v4
-      with:
-        go-version: '1.20'
-
-    - name: Build MetricCollector
-      run: make
-
-    - name: Run MetricCollector once
-      run: ./cc-metric-collector --once --config .github/ci-config.json
-
  #
  # Job build-1-21
  # Build on latest Ubuntu using golang version 1.21
@@ -62,6 +36,32 @@ jobs:
    - name: Run MetricCollector once
      run: ./cc-metric-collector --once --config .github/ci-config.json

+  #
+  # Job build-1-22
+  # Build on latest Ubuntu using golang version 1.22
+  #
+  build-1-22:
+    runs-on: ubuntu-latest
+    steps:
+    # See: https://github.com/marketplace/actions/checkout
+    # Checkout git repository and submodules
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    - name: Setup Golang
+      uses: actions/setup-go@v4
+      with:
+        go-version: '1.22'
+
+    - name: Build MetricCollector
+      run: make
+
+    - name: Run MetricCollector once
+      run: ./cc-metric-collector --once --config .github/ci-config.json
+
  #
  # Build on AlmaLinux 8 using go-toolset
  #
@@ -92,10 +92,10 @@ jobs:
    - name: Install build dependencies
      run: |
          dnf --assumeyes install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm

    - name: RPM build MetricCollector
      id: rpmbuild
@@ -130,10 +130,10 @@ jobs:
    - name: Install build dependencies
      run: |
          dnf --assumeyes --disableplugin=subscription-manager install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm

    - name: RPM build MetricCollector
      id: rpmbuild
@@ -174,4 +174,4 @@ jobs:
      run: |
          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
-          make DEB
+          make DEB
--- a/collectors/customCmdMetric.go
+++ b/collectors/customCmdMetric.go
@@ -99,10 +99,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 				continue
 			}

-			y := lp.FromInfluxMetric(c)
-			if err == nil {
-				output <- y
-			}
+			output <- lp.FromInfluxMetric(c)
 		}
 	}
 	for _, file := range m.files {
@@ -121,10 +118,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 			if skip {
 				continue
 			}
-			y := lp.FromInfluxMetric(f)
-			if err == nil {
-				output <- y
-			}
+			output <- lp.FromInfluxMetric(f)
 		}
 	}
 }
--- a/collectors/likwidMetric.go
+++ b/collectors/likwidMetric.go
@@ -374,6 +374,14 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
 	}
 	defer watcher.Close()
 	if len(m.config.LockfilePath) > 0 {
+		if _, err := os.Stat(m.config.LockfilePath); os.IsNotExist(err) {
+			file, err := os.Create(m.config.LockfilePath)
+			if err != nil {
+				cclog.ComponentError(m.name, "Cannot create lockfile", m.config.LockfilePath, ":", err.Error())
+				return true, err
+			}
+			file.Close()
+		}
 		info, err := os.Stat(m.config.LockfilePath)
 		if err != nil {
 			return true, err
@@ -382,9 +390,9 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
 		if uid != uint32(os.Getuid()) {
 			usr, err := user.LookupId(fmt.Sprint(uid))
 			if err == nil {
-				return true, fmt.Errorf("Access to performance counters locked by %s", usr.Username)
+				return true, fmt.Errorf("access to performance counters locked by %s", usr.Username)
 			} else {
-				return true, fmt.Errorf("Access to performance counters locked by %d", uid)
+				return true, fmt.Errorf("access to performance counters locked by %d", uid)
 			}
 		}
 		err = watcher.Add(m.config.LockfilePath)
--- a/collectors/likwidMetric.md
+++ b/collectors/likwidMetric.md
@@ -267,3 +267,45 @@ IPC   PMC0/PMC1                  ->     {
 ```

 The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.
+
+### Internal structure
+
+This section describes the internal structure of the `likwid` collector. 
+
+#### At initialization
+
+After setting the defaults, the configuration is read.
+
+Based on the configuration, the library is searched using `dlopen` to see whether it makes sense to proceed.
+
+Next, the user-given metrics are tested to ensure they can be evaluated. For this, it creates a list of all user-given events/counters with the value `1.0` which is provided to the metric evaluator. The same is done for the global metrics by using the metric names with value `1.0`. If the evaluator does not fail, the metric can be evaluated and the collector initialization can proceed.
+
+A separate thread is started to do the measurement. This is not done using a common goroutine but a real application thread with full control. This is required because LIKWID's access system tracks the processes of the using application and the PID should not change between measurements because that would require teardown and reopening of the access system.
+
+With the separate thread, the access system is initialized by setting the user-given access mode and adding all hardware threads.
+
+LIKWID measures per hardware thread in general but only some HW threads read the counters available only e.g. per CPU socket (often memory traffic). For this, the collector gets the system topology through LIKWID and creates different mappings like 'hwthread to list offset' and others. With this, the hardware threads responsible for a topological entity can be determined because those read the counters of the per CPU socket units. These mappings are later used in the measurement phase.
+
+In the end, we read the base CPU frequency of the system. It may be used in the metric evaluation.
+
+#### Measurements
+
+The reading of events is done by the separate application thread.
+
+It traverses over all configured event sets, creates valid LIKWID eventstrings out of them and pass them to take a measurement. This could be done only once but when the LIKWID lock changes, LIKWID has to be completely reopened to provide access again. With this reopening, the already added event sets are gone.
+
+LIKWID has it's own locking mechanism using a lock file. But not the content of the file is of interest but the owner. In order to track changes of the file, a `fsnotify` watcher is installed on the file. If the file does not exist, it is created and consequently is owned by the same user as `cc-metric-collector`. The LikwidCollector has to watch the file on it's own because LIKWID does not provide proper error handling for this.
+
+Each call to the LIKWID library for loading the event set, setting up the counting facilities as well as starting and stopping of the counters is wrapped into lockfile checks to ensure no state change happens. If the file owner changed, the LikwidCollector cannot access the counters anymore, so no further operation can be done and measurment stops.
+
+Although start/stop would be sufficient, the LikwidCollector performs start, read, wait, read, `getLastResult`, stop. Reason might be "historic" but is not 100% clear anymore. The author failed to document ;)
+
+#### Metric evaluation
+
+After each meaurement, the metrics of the event set are directly evaluated. It updates the counter->result mapping with the new measurements, calls the evaluator and generates the `CCMetric` with the user-given settings if it should be published. Each metric name to result calculation is stored for the global metric evaluation, which is done as a final step.
+
+#### Shutdown
+
+Since each measurment involves a complete initialize to finalize cycle of the LIKWID library, only the topology module needs to be closed.
+
+Moreover, the separate application thread is stopped.
--- a/go.mod
+++ b/go.mod
@@ -1,6 +1,6 @@
 module github.com/ClusterCockpit/cc-metric-collector

-go 1.20
+go 1.21

 require (
 	github.com/ClusterCockpit/cc-units v0.4.0
@@ -12,30 +12,30 @@ require (
 	github.com/influxdata/influxdb-client-go/v2 v2.13.0
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
 	github.com/influxdata/line-protocol/v2 v2.2.1
-	github.com/nats-io/nats.go v1.32.0
-	github.com/prometheus/client_golang v1.18.0
+	github.com/nats-io/nats.go v1.33.1
+	github.com/prometheus/client_golang v1.19.0
 	github.com/stmcginnis/gofish v0.15.0
 	github.com/tklauser/go-sysconf v0.3.13
 	golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
-	golang.org/x/exp v0.0.0-20240119083558-1b970713d09a
-	golang.org/x/sys v0.16.0
+	golang.org/x/exp v0.0.0-20240222234643-814bf88cf225
+	golang.org/x/sys v0.18.0
 )

 require (
 	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.2.0 // indirect
-	github.com/google/uuid v1.5.0 // indirect
-	github.com/klauspost/compress v1.17.4 // indirect
+	github.com/google/uuid v1.6.0 // indirect
+	github.com/klauspost/compress v1.17.7 // indirect
 	github.com/nats-io/nkeys v0.4.7 // indirect
 	github.com/nats-io/nuid v1.0.1 // indirect
 	github.com/oapi-codegen/runtime v1.1.1 // indirect
-	github.com/prometheus/client_model v0.5.0 // indirect
-	github.com/prometheus/common v0.46.0 // indirect
+	github.com/prometheus/client_model v0.6.0 // indirect
+	github.com/prometheus/common v0.49.0 // indirect
 	github.com/prometheus/procfs v0.12.0 // indirect
 	github.com/shopspring/decimal v1.3.1 // indirect
 	github.com/tklauser/numcpus v0.7.0 // indirect
-	golang.org/x/crypto v0.18.0 // indirect
-	golang.org/x/net v0.20.0 // indirect
-	google.golang.org/protobuf v1.32.0 // indirect
+	golang.org/x/crypto v0.21.0 // indirect
+	golang.org/x/net v0.22.0 // indirect
+	google.golang.org/protobuf v1.33.0 // indirect
 )
--- a/go.sum
+++ b/go.sum
@@ -7,7 +7,6 @@ github.com/NVIDIA/go-nvml v0.12.0-2 h1:Sg239yy7jmopu/cuvYauoMj9fOpcGMngxVxxS1EBX
 github.com/NVIDIA/go-nvml v0.12.0-2/go.mod h1:7ruy85eOM73muOc/I37euONSwEyFqZsv5ED9AogD4G0=
 github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E=
 github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
-github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
 github.com/PaesslerAG/jsonpath v0.1.0/go.mod h1:4BzmtoM/PI8fPO4aQGIusjGxGir2BzcV0grWtFzq1Y8=
 github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
@@ -19,20 +18,16 @@ github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj
 github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
 github.com/frankban/quicktest v1.11.2/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
-github.com/frankban/quicktest v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
 github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU=
 github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
 github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
 github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
-github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
-github.com/google/uuid v1.5.0 h1:1p67kYwdtXjb0gL0BPiP1Av9wiZPo5A8z2cWkTZ+eyU=
-github.com/google/uuid v1.5.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
 github.com/gorilla/mux v1.8.1/go.mod h1:AKf9I4AEqPTmMytcMc0KkNouC66V3BtZ4qD5fmWSiMQ=
 github.com/influxdata/influxdb-client-go/v2 v2.13.0 h1:ioBbLmR5NMbAjP4UVA5r9b5xGjpABD7j65pI8kFphDM=
@@ -40,24 +35,20 @@ github.com/influxdata/influxdb-client-go/v2 v2.13.0/go.mod h1:k+spCbt9hcvqvUiz0s
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf h1:7JTmneyiNEwVBOHSjoMxiWAqB992atOeepeFYegn5RU=
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
 github.com/influxdata/line-protocol-corpus v0.0.0-20210519164801-ca6fa5da0184/go.mod h1:03nmhxzZ7Xk2pdG+lmMd7mHDfeVOYFyhOgwO61qWU98=
-github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937 h1:MHJNQ+p99hFATQm6ORoLmpUCF7ovjwEFshs/NHzAbig=
 github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937/go.mod h1:BKR9c0uHSmRgM/se9JhFHtTT7JTO67X23MtKMHtZcpo=
 github.com/influxdata/line-protocol/v2 v2.0.0-20210312151457-c52fdecb625a/go.mod h1:6+9Xt5Sq1rWx+glMgxhcg2c0DUaehK+5TDcPZ76GypY=
 github.com/influxdata/line-protocol/v2 v2.1.0/go.mod h1:QKw43hdUBg3GTk2iC3iyCxksNj7PX9aUSeYOYE/ceHY=
 github.com/influxdata/line-protocol/v2 v2.2.1 h1:EAPkqJ9Km4uAxtMRgUubJyqAr6zgWM0dznKMLRauQRE=
 github.com/influxdata/line-protocol/v2 v2.2.1/go.mod h1:DmB3Cnh+3oxmG6LOBIxce4oaL4CPj3OmMPgvauXh+tM=
 github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
-github.com/klauspost/compress v1.17.4 h1:Ej5ixsIri7BrIjBkRZLTo6ghwrEtHFk7ijlczPW4fZ4=
-github.com/klauspost/compress v1.17.4/go.mod h1:/dCuZOvVtNoHsyb+cuJD3itjs3NbnF6KH9zAO4BDxPM=
+github.com/klauspost/compress v1.17.7 h1:ehO88t2UGzQK66LMdE8tibEd1ErmzZjNEqWkjLAKQQg=
+github.com/klauspost/compress v1.17.7/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
-github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
-github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
-github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
-github.com/nats-io/nats.go v1.32.0 h1:Bx9BZS+aXYlxW08k8Gd3yR2s73pV5XSoAQUyp1Kwvp0=
-github.com/nats-io/nats.go v1.32.0/go.mod h1:Ubdu4Nh9exXdSz0RVWRFBbRfrbSxOYd26oF0wkWclB8=
+github.com/nats-io/nats.go v1.33.1 h1:8TxLZZ/seeEfR97qV0/Bl939tpDnt2Z2fK3HkPypj70=
+github.com/nats-io/nats.go v1.33.1/go.mod h1:Ubdu4Nh9exXdSz0RVWRFBbRfrbSxOYd26oF0wkWclB8=
 github.com/nats-io/nkeys v0.4.7 h1:RwNJbbIdYCoClSDNY7QVKZlyb/wfT6ugvFCiKy6vDvI=
 github.com/nats-io/nkeys v0.4.7/go.mod h1:kqXRgRDPlGy7nGaEDMuYzmiJCIAAWDK0IMBtDmGD0nc=
 github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
@@ -65,18 +56,15 @@ github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OS
 github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
 github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
 github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
-github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/prometheus/client_golang v1.18.0 h1:HzFfmkOzH5Q8L8G+kSJKUx5dtG87sewO+FoDDqP5Tbk=
-github.com/prometheus/client_golang v1.18.0/go.mod h1:T+GXkCk5wSJyOqMIzVgvvjFDlkOQntgjkJWKrN5txjA=
-github.com/prometheus/client_model v0.5.0 h1:VQw1hfvPvk3Uv6Qf29VrPF32JB6rtbgI6cYPYQjL0Qw=
-github.com/prometheus/client_model v0.5.0/go.mod h1:dTiFglRmd66nLR9Pv9f0mZi7B7fk5Pm3gvsjB5tr+kI=
-github.com/prometheus/common v0.46.0 h1:doXzt5ybi1HBKpsZOL0sSkaNHJJqkyfEWZGGqqScV0Y=
-github.com/prometheus/common v0.46.0/go.mod h1:Tp0qkxpb9Jsg54QMe+EAmqXkSV7Evdy1BTn+g2pa/hQ=
+github.com/prometheus/client_golang v1.19.0 h1:ygXvpU1AoN1MhdzckN+PyD9QJOSD4x7kmXYlnfbA6JU=
+github.com/prometheus/client_golang v1.19.0/go.mod h1:ZRM9uEAypZakd+q/x7+gmsvXdURP+DABIEIjnmDdp+k=
+github.com/prometheus/client_model v0.6.0 h1:k1v3CzpSRUTrKMppY35TLwPvxHqBu0bYgxZzqGIgaos=
+github.com/prometheus/client_model v0.6.0/go.mod h1:NTQHnmxFpouOD0DpvP4XujX3CdOAGQPoaGhyTchlyt8=
+github.com/prometheus/common v0.49.0 h1:ToNTdK4zSnPVJmh698mGFkDor9wBI/iGaJy5dbH1EgI=
+github.com/prometheus/common v0.49.0/go.mod h1:Kxm+EULxRbUkjGU6WFsQqo3ORzB4tyKvlWFOE9mB2sE=
 github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
 github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
-github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
-github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
 github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8=
 github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
 github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
@@ -88,7 +76,6 @@ github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpE
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/tklauser/go-sysconf v0.3.13 h1:GBUpcahXSpR2xN01jhkNAbTLRk2Yzgggk8IM08lq3r4=
 github.com/tklauser/go-sysconf v0.3.13/go.mod h1:zwleP4Q4OehZHGn4CYZDipCgg9usW5IJePewFCGVEa0=
@@ -96,21 +83,20 @@ github.com/tklauser/numcpus v0.7.0 h1:yjuerZP127QG9m5Zh/mSO4wqurYil27tHrqwRoRjpr
 github.com/tklauser/numcpus v0.7.0/go.mod h1:bb6dMVcj8A42tSE7i32fsIUCbQNllK5iDguyOZRUzAY=
 golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg=
 golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE=
-golang.org/x/crypto v0.18.0 h1:PGVlW0xEltQnzFZ55hkuX5+KLyrMYhHld1YHO4AKcdc=
-golang.org/x/crypto v0.18.0/go.mod h1:R0j02AL6hcrfOiy9T4ZYp/rcWeMxM3L6QYxlOuEG1mg=
-golang.org/x/exp v0.0.0-20240119083558-1b970713d09a h1:Q8/wZp0KX97QFTc2ywcOE0YRjZPVIx+MXInMzdvQqcA=
-golang.org/x/exp v0.0.0-20240119083558-1b970713d09a/go.mod h1:idGWGoKP1toJGkd5/ig9ZLuPcZBC3ewk7SzmH0uou08=
-golang.org/x/net v0.20.0 h1:aCL9BSgETF1k+blQaYUBx9hJ9LOGP3gAVemcZlf1Kpo=
-golang.org/x/net v0.20.0/go.mod h1:z8BVo6PvndSri0LbOE3hAn0apkU+1YvI6E70E9jsnvY=
+golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
+golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
+golang.org/x/exp v0.0.0-20240222234643-814bf88cf225 h1:LfspQV/FYTatPTr/3HzIcmiUFH7PGP+OQ6mgDYo3yuQ=
+golang.org/x/exp v0.0.0-20240222234643-814bf88cf225/go.mod h1:CxmFvTBINI24O/j8iY7H1xHzx2i4OsyguNBmN/uPtqc=
+golang.org/x/net v0.22.0 h1:9sGLhx7iRIHEiX0oAJ3MRZMUCElJgy7Br1nO+AMN3Tc=
+golang.org/x/net v0.22.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
 golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.16.0 h1:xWw16ngr6ZMtmxDyKyIgsE93KNKz5HKmMa3b8ALHidU=
-golang.org/x/sys v0.16.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
+golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-google.golang.org/protobuf v1.32.0 h1:pPC6BG5ex8PDFnkbrGU3EixyhKcQ2aDuBS36lqK/C7I=
-google.golang.org/protobuf v1.32.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
+google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI=
+google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
--- a/receivers/redfishReceiver.go
+++ b/receivers/redfishReceiver.go
@@ -6,6 +6,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"maps"
 	"net/http"
 	"strconv"
 	"strings"
@@ -32,10 +33,14 @@ type RedfishReceiverClientConfig struct {

 	doPowerMetric      bool
 	doProcessorMetrics bool
+	doSensors          bool
 	doThermalMetrics   bool

 	skipProcessorMetricsURL map[string]bool

+	// readSensorURLs stores for each chassis ID a list of sensor URLs to read
+	readSensorURLs map[string][]string
+
 	gofish gofish.ClientConfig
 }

@@ -56,7 +61,226 @@ type RedfishReceiver struct {
 	wg   sync.WaitGroup // wait group for redfish receiver
 }

+// deleteEmptyTags removes tags or meta data tags with empty value
+func deleteEmptyTags(tags map[string]string) {
+	maps.DeleteFunc(
+		tags,
+		func(key string, value string) bool {
+			return value == ""
+		},
+	)
+}
+
+// setMetricValue sets the value entry in the fields map
+func setMetricValue(value any) map[string]interface{} {
+	return map[string]interface{}{
+		"value": value,
+	}
+}
+
+// sendMetric sends the metric through the sink channel
+func (r *RedfishReceiver) sendMetric(name string, tags map[string]string, meta map[string]string, value any, timestamp time.Time) {
+
+	deleteEmptyTags(tags)
+	deleteEmptyTags(meta)
+	y, err := lp.New(name, tags, meta, setMetricValue(value), timestamp)
+	if err == nil {
+		r.sink <- y
+	}
+}
+
+// readSensors reads sensors from a redfish device
+// See: https://redfish.dmtf.org/schemas/v1/Sensor.json
+// Redfish URI: /redfish/v1/Chassis/{ChassisId}/Sensors/{SensorId}
+func (r *RedfishReceiver) readSensors(
+	clientConfig *RedfishReceiverClientConfig,
+	chassis *redfish.Chassis) error {
+
+	writeTemperatureSensor := func(sensor *redfish.Sensor) {
+		tags := map[string]string{
+			"hostname": clientConfig.Hostname,
+			"type":     "node",
+			// ChassisType shall indicate the physical form factor for the type of chassis
+			"chassis_typ": string(chassis.ChassisType),
+			// Chassis name
+			"chassis_name": chassis.Name,
+			// ID uniquely identifies the resource
+			"sensor_id": sensor.ID,
+			// The area or device to which this sensor measurement applies
+			"temperature_physical_context": string(sensor.PhysicalContext),
+			// Name
+			"temperature_name": sensor.Name,
+		}
+
+		// Set meta data tags
+		meta := map[string]string{
+			"source": r.name,
+			"group":  "Temperature",
+			"unit":   "degC",
+		}
+
+		r.sendMetric("temperature", tags, meta, sensor.Reading, time.Now())
+	}
+
+	writeFanSpeedSensor := func(sensor *redfish.Sensor) {
+		tags := map[string]string{
+			"hostname": clientConfig.Hostname,
+			"type":     "node",
+			// ChassisType shall indicate the physical form factor for the type of chassis
+			"chassis_typ": string(chassis.ChassisType),
+			// Chassis name
+			"chassis_name": chassis.Name,
+			// ID uniquely identifies the resource
+			"sensor_id": sensor.ID,
+			// The area or device to which this sensor measurement applies
+			"fan_physical_context": string(sensor.PhysicalContext),
+			// Name
+			"fan_name": sensor.Name,
+		}
+
+		// Set meta data tags
+		meta := map[string]string{
+			"source": r.name,
+			"group":  "FanSpeed",
+			"unit":   string(sensor.ReadingUnits),
+		}
+
+		r.sendMetric("fan_speed", tags, meta, sensor.Reading, time.Now())
+	}
+
+	writePowerSensor := func(sensor *redfish.Sensor) {
+		// Set tags
+		tags := map[string]string{
+			"hostname": clientConfig.Hostname,
+			"type":     "node",
+			// ChassisType shall indicate the physical form factor for the type of chassis
+			"chassis_typ": string(chassis.ChassisType),
+			// Chassis name
+			"chassis_name": chassis.Name,
+			// ID uniquely identifies the resource
+			"sensor_id": sensor.ID,
+			// The area or device to which this sensor measurement applies
+			"power_physical_context": string(sensor.PhysicalContext),
+			// Name
+			"power_name": sensor.Name,
+		}
+
+		// Set meta data tags
+		meta := map[string]string{
+			"source": r.name,
+			"group":  "Energy",
+			"unit":   "watts",
+		}
+
+		r.sendMetric("power", tags, meta, sensor.Reading, time.Now())
+	}
+
+	if _, ok := clientConfig.readSensorURLs[chassis.ID]; !ok {
+		// First time run of read sensors for this chassis
+
+		clientConfig.readSensorURLs[chassis.ID] = make([]string, 0)
+
+		// Get sensor information for this chassis
+		sensors, err := chassis.Sensors()
+		if err != nil {
+			return fmt.Errorf("readSensors: chassis.Sensors() failed: %v", err)
+		}
+
+		// Skip empty sensors information
+		if sensors == nil {
+			return nil
+		}
+
+		for _, sensor := range sensors {
+
+			// Skip all sensors which are not in enabled state or which are unhealthy
+			if sensor.Status.State != common.EnabledState || sensor.Status.Health != common.OKHealth {
+				continue
+			}
+
+			// Skip sensors with missing readings units or type
+			if sensor.ReadingUnits == "" || sensor.ReadingType == "" {
+				continue
+			}
+
+			// Power readings
+			if (sensor.ReadingType == redfish.PowerReadingType && sensor.ReadingUnits == "Watts") ||
+				(sensor.ReadingType == redfish.CurrentReadingType && sensor.ReadingUnits == "Watts") {
+				if clientConfig.isExcluded["power"] {
+					continue
+				}
+
+				clientConfig.readSensorURLs[chassis.ID] = append(clientConfig.readSensorURLs[chassis.ID], sensor.ODataID)
+				writePowerSensor(sensor)
+				continue
+			}
+
+			// Fan speed readings
+			if (sensor.ReadingType == redfish.AirFlowReadingType && sensor.ReadingUnits == "RPM") ||
+				(sensor.ReadingType == redfish.AirFlowReadingType && sensor.ReadingUnits == "Percent") {
+				// Skip, when fan_speed metric is excluded
+				if clientConfig.isExcluded["fan_speed"] {
+					continue
+				}
+
+				clientConfig.readSensorURLs[chassis.ID] = append(clientConfig.readSensorURLs[chassis.ID], sensor.ODataID)
+				writeFanSpeedSensor(sensor)
+			}
+
+			// Temperature readings
+			if sensor.ReadingType == redfish.TemperatureReadingType && sensor.ReadingUnits == "C" {
+				if clientConfig.isExcluded["temperature"] {
+					continue
+				}
+
+				clientConfig.readSensorURLs[chassis.ID] = append(clientConfig.readSensorURLs[chassis.ID], sensor.ODataID)
+				writeTemperatureSensor(sensor)
+				continue
+			}
+		}
+	} else {
+
+		common.CollectCollection(
+			func(uri string) {
+				sensor, err := redfish.GetSensor(chassis.GetClient(), uri)
+				if err != nil {
+					cclog.ComponentError(r.name, "redfish.GetSensor() for uri '", uri, "' failed")
+				}
+
+				// Power readings
+				if (sensor.ReadingType == redfish.PowerReadingType && sensor.ReadingUnits == "Watts") ||
+					(sensor.ReadingType == redfish.CurrentReadingType && sensor.ReadingUnits == "Watts") {
+
+					writePowerSensor(sensor)
+					return
+				}
+
+				// Fan speed readings
+				if (sensor.ReadingType == redfish.AirFlowReadingType && sensor.ReadingUnits == "RPM") ||
+					(sensor.ReadingType == redfish.AirFlowReadingType && sensor.ReadingUnits == "Percent") {
+
+					writeFanSpeedSensor(sensor)
+					return
+				}
+
+				// Temperature readings
+				if sensor.ReadingType == redfish.TemperatureReadingType && sensor.ReadingUnits == "C" {
+
+					writeTemperatureSensor(sensor)
+					return
+				}
+			},
+			clientConfig.readSensorURLs[chassis.ID])
+
+	}
+	return nil
+}
+
 // readThermalMetrics reads thermal metrics from a redfish device
+// See: https://redfish.dmtf.org/schemas/v1/Thermal.json
+// Redfish URI: /redfish/v1/Chassis/{ChassisId}/Thermal
+// -> deprecated in favor of the ThermalSubsystem schema
+// -> on Lenovo servers /redfish/v1/Chassis/{ChassisId}/ThermalSubsystem/ThermalMetrics links to /redfish/v1/Chassis/{ChassisId}/Sensors/{SensorId}
 func (r *RedfishReceiver) readThermalMetrics(
 	clientConfig *RedfishReceiverClientConfig,
 	chassis *redfish.Chassis) error {
@@ -106,13 +330,6 @@ func (r *RedfishReceiver) readThermalMetrics(
 			"temperature_name": temperature.Name,
 		}

-		// Delete empty tags
-		for key, value := range tags {
-			if value == "" {
-				delete(tags, key)
-			}
-		}
-
 		// Set meta data tags
 		meta := map[string]string{
 			"source": r.name,
@@ -123,14 +340,7 @@ func (r *RedfishReceiver) readThermalMetrics(
 		// ReadingCelsius shall be the current value of the temperature sensor's reading.
 		value := temperature.ReadingCelsius

-		y, err := lp.New("temperature", tags, meta,
-			map[string]interface{}{
-				"value": value,
-			},
-			timestamp)
-		if err == nil {
-			r.sink <- y
-		}
+		r.sendMetric("temperature", tags, meta, value, timestamp)
 	}

 	for _, fan := range thermal.Fans {
@@ -164,13 +374,6 @@ func (r *RedfishReceiver) readThermalMetrics(
 			"fan_name": fan.Name,
 		}

-		// Delete empty tags
-		for key, value := range tags {
-			if value == "" {
-				delete(tags, key)
-			}
-		}
-
 		// Set meta data tags
 		meta := map[string]string{
 			"source": r.name,
@@ -178,23 +381,16 @@ func (r *RedfishReceiver) readThermalMetrics(
 			"unit":   string(fan.ReadingUnits),
 		}

-		// Reading shall be the current value of the fan sensor's reading
-		value := fan.Reading
-
-		y, err := lp.New("fan_speed", tags, meta,
-			map[string]interface{}{
-				"value": value,
-			},
-			timestamp)
-		if err == nil {
-			r.sink <- y
-		}
+		r.sendMetric("fan_speed", tags, meta, fan.Reading, timestamp)
 	}

 	return nil
 }

 // readPowerMetrics reads power metrics from a redfish device
+// See: https://redfish.dmtf.org/schemas/v1/Power.json
+// Redfish URI: /redfish/v1/Chassis/{ChassisId}/Power
+// -> deprecated in favor of the PowerSubsystem schema
 func (r *RedfishReceiver) readPowerMetrics(
 	clientConfig *RedfishReceiverClientConfig,
 	chassis *redfish.Chassis) error {
@@ -274,13 +470,6 @@ func (r *RedfishReceiver) readPowerMetrics(
 			"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,
@@ -289,23 +478,8 @@ func (r *RedfishReceiver) readPowerMetrics(
 			"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
-			}
+			r.sendMetric(name, tags, meta, value, timestamp)
 		}
 	}

@@ -314,6 +488,7 @@ func (r *RedfishReceiver) readPowerMetrics(

 // readProcessorMetrics reads processor metrics from a redfish device
 // See: https://redfish.dmtf.org/schemas/v1/ProcessorMetrics.json
+// Redfish URI: /redfish/v1/Systems/{ComputerSystemId}/Processors/{ProcessorId}/ProcessorMetrics
 func (r *RedfishReceiver) readProcessorMetrics(
 	clientConfig *RedfishReceiverClientConfig,
 	processor *redfish.Processor) error {
@@ -374,13 +549,6 @@ func (r *RedfishReceiver) readProcessorMetrics(
 		"processor_id": processor.ID,
 	}

-	// Delete empty tags
-	for key, value := range tags {
-		if value == "" {
-			delete(tags, key)
-		}
-	}
-
 	// Set meta data tags
 	metaPower := map[string]string{
 		"source": r.name,
@@ -393,14 +561,7 @@ func (r *RedfishReceiver) readProcessorMetrics(
 	if !clientConfig.isExcluded[namePower] &&
 		// Some servers return "ConsumedPowerWatt":65535 instead of "ConsumedPowerWatt":null
 		processorMetrics.ConsumedPowerWatt != 65535 {
-		y, err := lp.New(namePower, tags, metaPower,
-			map[string]interface{}{
-				"value": processorMetrics.ConsumedPowerWatt,
-			},
-			timestamp)
-		if err == nil {
-			r.sink <- y
-		}
+		r.sendMetric(namePower, tags, metaPower, processorMetrics.ConsumedPowerWatt, timestamp)
 	}
 	// Set meta data tags
 	metaThermal := map[string]string{
@@ -412,14 +573,7 @@ func (r *RedfishReceiver) readProcessorMetrics(
 	nameThermal := "temperature"

 	if !clientConfig.isExcluded[nameThermal] {
-		y, err := lp.New(nameThermal, tags, metaThermal,
-			map[string]interface{}{
-				"value": processorMetrics.TemperatureCelsius,
-			},
-			timestamp)
-		if err == nil {
-			r.sink <- y
-		}
+		r.sendMetric(nameThermal, tags, metaThermal, processorMetrics.TemperatureCelsius, timestamp)
 	}
 	return nil
 }
@@ -452,7 +606,8 @@ func (r *RedfishReceiver) readMetrics(clientConfig *RedfishReceiverClientConfig)

 	// Get all chassis managed by this service
 	isChassisListRequired :=
-		clientConfig.doThermalMetrics ||
+		clientConfig.doSensors ||
+			clientConfig.doThermalMetrics ||
 			clientConfig.doPowerMetric
 	var chassisList []*redfish.Chassis
 	if isChassisListRequired {
@@ -472,6 +627,16 @@ func (r *RedfishReceiver) readMetrics(clientConfig *RedfishReceiverClientConfig)
 		}
 	}

+	// Read sensors
+	if clientConfig.doSensors {
+		for _, chassis := range chassisList {
+			err := r.readSensors(clientConfig, chassis)
+			if err != nil {
+				return err
+			}
+		}
+	}
+
 	// read thermal metrics
 	if clientConfig.doThermalMetrics {
 		for _, chassis := range chassisList {
@@ -636,6 +801,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
 		// Globally disable collection of power, processor or thermal metrics
 		DisablePowerMetrics     bool `json:"disable_power_metrics"`
 		DisableProcessorMetrics bool `json:"disable_processor_metrics"`
+		DisableSensors          bool `json:"disable_sensors"`
 		DisableThermalMetrics   bool `json:"disable_thermal_metrics"`

 		// Globally excluded metrics
@@ -650,6 +816,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
 			// Per client disable collection of power,processor or thermal metrics
 			DisablePowerMetrics     bool `json:"disable_power_metrics"`
 			DisableProcessorMetrics bool `json:"disable_processor_metrics"`
+			DisableSensors          bool `json:"disable_sensors"`
 			DisableThermalMetrics   bool `json:"disable_thermal_metrics"`

 			// Per client excluded metrics
@@ -766,6 +933,9 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
 		doProcessorMetrics :=
 			!(configJSON.DisableProcessorMetrics ||
 				clientConfigJSON.DisableProcessorMetrics)
+		doSensors :=
+			!(configJSON.DisableSensors ||
+				clientConfigJSON.DisableSensors)
 		doThermalMetrics :=
 			!(configJSON.DisableThermalMetrics ||
 				clientConfigJSON.DisableThermalMetrics)
@@ -798,8 +968,10 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
 					isExcluded:              isExcluded,
 					doPowerMetric:           doPowerMetric,
 					doProcessorMetrics:      doProcessorMetrics,
+					doSensors:               doSensors,
 					doThermalMetrics:        doThermalMetrics,
 					skipProcessorMetricsURL: make(map[string]bool),
+					readSensorURLs:          map[string][]string{},
 					gofish: gofish.ClientConfig{
 						Username:   username,
 						Password:   password,
--- a/receivers/redfishReceiver.md
+++ b/receivers/redfishReceiver.md
@@ -17,15 +17,17 @@ The Redfish receiver uses the [Redfish (specification)](https://www.dmtf.org/sta
                "host_list": "n[1,2-4]"
            },
            {
-                "host_list": "n5"
-                "disable_power_metrics": true
+                "host_list": "n5",
+                "disable_power_metrics": true,
+                "disable_processor_metrics": true,
+                "disable_thermal_metrics": true
            },
            {
                "host_list": "n6" ],
                "username": "<Username 2>",
                "password": "<Password 2>",
                "endpoint": "https://%h-BMC",
-                "disable_thermal_metrics": true
+                "disable_sensor_metrics": true
            }
        ]
    }
@@ -41,9 +43,18 @@ Global settings:

 Global and per redfish device settings (per redfish device settings overwrite the global settings):

- `disable_power_metrics`: disable collection of power metrics
- `disable_processor_metrics`: disable collection of processor metrics
- `disable_thermal_metrics`: disable collection of thermal metrics
+- `disable_power_metrics`:
+  disable collection of power metrics
+  (`/redfish/v1/Chassis/{ChassisId}/Power`)
+- `disable_processor_metrics`:
+  disable collection of processor metrics
+  (`/redfish/v1/Systems/{ComputerSystemId}/Processors/{ProcessorId}/ProcessorMetrics`)
+- `disable_sensors`:
+  disable collection of fan, power and thermal sensor metrics
+  (`/redfish/v1/Chassis/{ChassisId}/Sensors/{SensorId}`)
+- `disable_thermal_metrics`:
+  disable collection of thermal metrics
+  (`/redfish/v1/Chassis/{ChassisId}/Thermal`)
 - `exclude_metrics`: list of excluded metrics
 - `username`: User name to authenticate with
 - `password`: Password to use for authentication
Author	SHA1	Message	Date
Thomas Röhl	9ca73a9f50	Add documentation of the internal structure of the LikwidCollector to its documentation	2024-04-25 17:26:18 +02:00
Thomas Röhl	0186dce521	Create lockfile if it does not exist	2024-04-25 17:25:53 +02:00
Thomas Roehl	16c796a2b8	Merge branch 'develop' of github.com:ClusterCockpit/cc-metric-collector into develop	2024-04-10 19:57:54 +02:00
Thomas Roehl	b6c4769db3	Remove stray error check	2024-04-10 19:57:46 +02:00
Holger Obermaier	7bbee70c14	Update golang toolchain to 1.21	2024-03-06 15:14:44 +01:00
Holger Obermaier	902f4349b6	Read sensors through redfish	2024-03-06 14:59:47 +01:00