Move example configurations and update docs. Fixed #150

Bumps [github.com/ClusterCockpit/cc-lib](https://github.com/ClusterCockpit/cc-lib) from 0.9.1 to 0.10.1.
- [Release notes](https://github.com/ClusterCockpit/cc-lib/releases)
- [Commits](https://github.com/ClusterCockpit/cc-lib/compare/v0.9.1...v0.10.1)

---
updated-dependencies:
- dependency-name: github.com/ClusterCockpit/cc-lib
  dependency-version: 0.10.1
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "gomod"
+    directory: "/"
+    schedule:
+      interval: "weekly"

README.md

@@ -32,12 +32,14 @@ There is a main configuration file with basic settings that point to the other c
 
 ``` json
 {
-  "sinks": "sinks.json",
-  "collectors" : "collectors.json",
-  "receivers" : "receivers.json",
-  "router" : "router.json",
-  "interval": "10s",
-  "duration": "1s"
+  "sinks-file": "sinks.json",
+  "collectors-file" : "collectors.json",
+  "receivers-file" : "receivers.json",
+  "router-file" : "router.json",
+  "main": {
+    "interval": "10s",
+    "duration": "1s"
+  }
 }
 ```
 

collectors/README.md

@@ -52,6 +52,7 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 * [`beegfs_meta`](./beegfsmetaMetric.md)
 * [`beegfs_storage`](./beegfsstorageMetric.md)
 * [`rocm_smi`](./rocmsmiMetric.md)
+* [`slurm_cgroup`](./slurmCgroupMetric.md)
 
 ## Todos
 

collectors/collectorManager.go

@@ -47,6 +47,7 @@ var AvailableCollectors = map[string]MetricCollector{
 	"self":            new(SelfCollector),
 	"schedstat":       new(SchedstatCollector),
 	"nfsiostat":       new(NfsIOStatCollector),
+	"slurm_cgroup":    new(SlurmCgroupCollector),
 }
 
 // Metric collector manager data structure

collectors/gpfsMetric.go

@@ -11,6 +11,7 @@ import (
 	"bufio"
 	"bytes"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"io"
 	"log"
@@ -18,6 +19,7 @@ import (
 	"os/user"
 	"strconv"
 	"strings"
+	"syscall"
 	"time"
 
 	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
@@ -27,8 +29,17 @@ import (
 const DEFAULT_GPFS_CMD = "mmpmon"
 
 type GpfsCollectorLastState struct {
-	bytesRead    int64
-	bytesWritten int64
+	numOpens    	int64
+	numCloses 		int64
+	numReads		int64
+	numWrites		int64
+	numReaddirs		int64
+	numInodeUpdates int64
+	bytesRead    	int64
+	bytesWritten 	int64
+	bytesTotal		int64
+	iops			int64
+	metaops			int64
 }
 
 type GpfsCollector struct {
@@ -37,9 +48,12 @@ type GpfsCollector struct {
 	config struct {
 		Mmpmon            string   `json:"mmpmon_path,omitempty"`
 		ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
+		Sudo              bool     `json:"use_sudo,omitempty"`
 		SendBandwidths    bool     `json:"send_bandwidths"`
 		SendTotalValues   bool     `json:"send_total_values"`
+		SendDerivedValues bool     `json:"send_derived_values"`
 	}
+	sudoCmd       string
 	skipFS        map[string]struct{}
 	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
 	lastState     map[string]GpfsCollectorLastState
@@ -82,18 +96,43 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 	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)
-	}
-	if user.Uid != "0" {
-		return fmt.Errorf("GPFS file system statistics can only be queried by user root")
+	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, "GPFS 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
 	}
 
+	// when using sudo, the full path of mmpmon must be specified because
+	// exec.LookPath will not work as mmpmon is not executable as user
+	if m.config.Sudo && !strings.HasPrefix(m.config.Mmpmon, "/") {
+		return fmt.Errorf("when using sudo, mmpmon_path must be provided and an absolute path: %s", m.config.Mmpmon)
+	}
+	
 	// Check if mmpmon is in executable search path
 	p, err := exec.LookPath(m.config.Mmpmon)
 	if err != nil {
-		return fmt.Errorf("failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
+		// if using sudo, exec.lookPath will return EACCES (file mode r-x------), this can be ignored
+		if m.config.Sudo && errors.Is(err, syscall.EACCES) {
+			cclog.ComponentWarn(m.name, fmt.Sprintf("got error looking for mmpmon binary '%s': %v . This is expected when using sudo, continuing.", m.config.Mmpmon, err))
+			// the file was given in the config, use it
+			p = m.config.Mmpmon
+		} else {
+			cclog.ComponentError(m.name, fmt.Sprintf("failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err))
+			return fmt.Errorf("failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
+		}
 	}
 	m.config.Mmpmon = p
 
@@ -118,7 +157,13 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// -p: generate output that can be parsed
 	// -s: suppress the prompt on input
 	// fs_io_s: Displays I/O statistics per mounted file system
-	cmd := exec.Command(m.config.Mmpmon, "-p", "-s")
+	var cmd *exec.Cmd
+	if m.config.Sudo {
+		cmd = exec.Command(m.sudoCmd, m.config.Mmpmon, "-p", "-s")
+	} else {
+		cmd = exec.Command(m.config.Mmpmon, "-p", "-s")
+	}
+	
 	cmd.Stdin = strings.NewReader("once fs_io_s\n")
 	cmdStdout := new(bytes.Buffer)
 	cmdStderr := new(bytes.Buffer)
@@ -185,6 +230,22 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			}
 		}
 
+		if m.config.SendDerivedValues {
+			if _, ok := m.lastState[filesystem]; !ok {
+				m.lastState[filesystem] = GpfsCollectorLastState{
+					numReads:    -1,
+					numWrites: -1,
+					numOpens: -1,
+					numCloses: -1,
+					numReaddirs: -1,
+					numInodeUpdates: -1,
+					bytesTotal: -1,
+					iops: -1,
+					metaops: -1,
+				}
+			}		
+		}
+
 		// return code
 		rc, err := strconv.Atoi(key_value["_rc_"])
 		if err != nil {
@@ -278,7 +339,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			output <- y
 		}
 		if m.config.SendBandwidths {
-			if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
+			if lastBytesWritten := m.lastState[filesystem].bytesWritten; lastBytesWritten >= 0 {
 				bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
 				if y, err :=
 					lp.NewMessage(
@@ -296,13 +357,6 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			}
 		}
 
-		if m.config.SendBandwidths {
-			m.lastState[filesystem] = GpfsCollectorLastState{
-				bytesRead:    bytesRead,
-				bytesWritten: bytesWritten,
-			}
-		}
-
 		// number of opens
 		numOpens, err := strconv.ParseInt(key_value["_oc_"], 10, 64)
 		if err != nil {
@@ -314,6 +368,24 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		if y, err := lp.NewMessage("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendDerivedValues {
+			if lastNumOpens := m.lastState[filesystem].numOpens; lastNumOpens >= 0 {
+				opensRate := float64(numOpens-lastNumOpens) / timeDiff
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_opens_rate",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": opensRate,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "requests/sec")
+					output <- y
+				}
+			}
+		}
 
 		// number of closes
 		numCloses, err := strconv.ParseInt(key_value["_cc_"], 10, 64)
@@ -326,6 +398,24 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		if y, err := lp.NewMessage("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendDerivedValues {
+			if lastNumCloses := m.lastState[filesystem].numCloses; lastNumCloses >= 0 {
+				closesRate := float64(numCloses-lastNumCloses) / timeDiff
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_closes_rate",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": closesRate,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "requests/sec")
+					output <- y
+				}
+			}
+		}
 
 		// number of reads
 		numReads, err := strconv.ParseInt(key_value["_rdc_"], 10, 64)
@@ -338,6 +428,24 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		if y, err := lp.NewMessage("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendDerivedValues {
+			if lastNumReads := m.lastState[filesystem].numReads; lastNumReads >= 0 {
+				readsRate := float64(numReads-lastNumReads) / timeDiff
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_reads_rate",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": readsRate,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "requests/sec")
+					output <- y
+				}
+			}
+		}
 
 		// number of writes
 		numWrites, err := strconv.ParseInt(key_value["_wc_"], 10, 64)
@@ -350,6 +458,24 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		if y, err := lp.NewMessage("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendDerivedValues {
+			if lastNumWrites := m.lastState[filesystem].numWrites; lastNumWrites >= 0 {
+				writesRate := float64(numWrites-lastNumWrites) / timeDiff
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_writes_rate",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": writesRate,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "requests/sec")
+					output <- y
+				}
+			}
+		}
 
 		// number of read directories
 		numReaddirs, err := strconv.ParseInt(key_value["_dir_"], 10, 64)
@@ -362,6 +488,24 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		if y, err := lp.NewMessage("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendDerivedValues {
+			if lastNumReaddirs := m.lastState[filesystem].numReaddirs; lastNumReaddirs >= 0 {
+				readdirsRate := float64(numReaddirs-lastNumReaddirs) / timeDiff
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_readdirs_rate",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": readdirsRate,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "requests/sec")
+					output <- y
+				}
+			}
+		}
 
 		// Number of inode updates
 		numInodeUpdates, err := strconv.ParseInt(key_value["_iu_"], 10, 64)
@@ -374,10 +518,31 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		if y, err := lp.NewMessage("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendDerivedValues {
+			if lastNumInodeUpdates := m.lastState[filesystem].numInodeUpdates; lastNumInodeUpdates >= 0 {
+				inodeUpdatesRate := float64(numInodeUpdates-lastNumInodeUpdates) / timeDiff
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_inode_updates_rate",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": inodeUpdatesRate,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "requests/sec")
+					output <- y
+				}
+			}
+		}
 
 		// Total values
+		bytesTotal := int64(-1);
+		iops := int64(-1);
+		metaops := int64(-1);
 		if m.config.SendTotalValues {
-			bytesTotal := bytesRead + bytesWritten
+			bytesTotal = bytesRead + bytesWritten
 			if y, err :=
 				lp.NewMessage("gpfs_bytes_total",
 					m.tags,
@@ -390,7 +555,26 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				y.AddMeta("unit", "bytes")
 				output <- y
 			}
-			iops := numReads + numWrites
+			if m.config.SendBandwidths {
+				if lastBytesTotal := m.lastState[filesystem].bytesTotal; lastBytesTotal >= 0 {
+					bwTotal := float64(bytesTotal-lastBytesTotal) / timeDiff
+					if y, err :=
+						lp.NewMessage(
+							"gpfs_bw_total",
+							m.tags,
+							m.meta,
+							map[string]interface{}{
+								"value": bwTotal,
+							},
+							timestamp,
+						); err == nil {
+						y.AddMeta("unit", "bytes/sec")
+						output <- y
+					}
+				}
+			}
+
+			iops = numReads + numWrites
 			if y, err :=
 				lp.NewMessage("gpfs_iops",
 					m.tags,
@@ -402,7 +586,26 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				); err == nil {
 				output <- y
 			}
-			metaops := numInodeUpdates + numCloses + numOpens + numReaddirs
+			if m.config.SendDerivedValues {
+				if lastIops := m.lastState[filesystem].iops; lastIops >= 0 {
+					iopsRate := float64(iops-lastIops) / timeDiff
+					if y, err :=
+						lp.NewMessage(
+							"gpfs_iops_rate",
+							m.tags,
+							m.meta,
+							map[string]interface{}{
+								"value": iopsRate,
+							},
+							timestamp,
+						); err == nil {
+						y.AddMeta("unit", "requests/sec")
+						output <- y
+					}
+				}
+			}
+	
+			metaops = numInodeUpdates + numCloses + numOpens + numReaddirs
 			if y, err :=
 				lp.NewMessage("gpfs_metaops",
 					m.tags,
@@ -414,7 +617,41 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				); err == nil {
 				output <- y
 			}
+			if m.config.SendDerivedValues {
+				if lastMetaops := m.lastState[filesystem].metaops; lastMetaops >= 0 {
+					metaopsRate := float64(metaops-lastMetaops) / timeDiff
+					if y, err :=
+						lp.NewMessage(
+							"gpfs_metaops_rate",
+							m.tags,
+							m.meta,
+							map[string]interface{}{
+								"value": metaopsRate,
+							},
+							timestamp,
+						); err == nil {
+						y.AddMeta("unit", "requests/sec")
+						output <- y
+					}
+				}
+			}
 		}
+
+		// Save last state
+		m.lastState[filesystem] = GpfsCollectorLastState{
+			bytesRead:    bytesRead,
+			bytesWritten: bytesWritten,
+			numOpens: numOpens,
+			numCloses: numCloses,
+			numReads: numReads,
+			numWrites: numWrites,
+			numReaddirs: numReaddirs,
+			numInodeUpdates: numInodeUpdates,
+			bytesTotal: bytesTotal,
+			iops: iops,
+			metaops: metaops,
+		}
+
 	}
 }
 

collectors/gpfsMetric.md

@@ -14,11 +14,13 @@ hugo_path: docs/reference/cc-metric-collector/collectors/gpfs.md
 ```json
   "gpfs": {
     "mmpmon_path": "/path/to/mmpmon",
+    "use_sudo": "true",
     "exclude_filesystem": [
       "fs1"
     ],
     "send_bandwidths": true,
-    "send_total_values": true
+    "send_total_values": true,
+    "send_derived_values": true
   }
 ```
 
@@ -31,6 +33,11 @@ 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`.
 
+If cc-metric-collector is run as non-root, `sudo` can be enabled with `use_sudo`. 
+Because `mmpmon` is by default only executable as root, the Go procedure to
+search for it in `$PATH` will fail. If you use `sudo`, you must specify the
+complete path for `mmpmon` using the parameter `mmpmon_path`.
+
 
 Metrics:
 * `gpfs_bytes_read`
@@ -41,10 +48,19 @@ Metrics:
 * `gpfs_num_writes`
 * `gpfs_num_readdirs`
 * `gpfs_num_inode_updates`
+* `gpfs_opens_rate` (if `send_derived_values == true`)
+* `gpfs_closes_rate` (if `send_derived_values == true`)
+* `gpfs_reads_rate` (if `send_derived_values == true`)
+* `gpfs_writes_rate` (if `send_derived_values == true`)
+* `gpfs_readdirs_rate` (if `send_derived_values == true`)
+* `gpfs_inode_updates_rate` (if `send_derived_values == true`)
 * `gpfs_bytes_total = gpfs_bytes_read + gpfs_bytes_written` (if `send_total_values == true`)
 * `gpfs_iops = gpfs_num_reads + gpfs_num_writes` (if `send_total_values == true`)
+* `gpfs_iops_rate` (if `send_total_values == true` and `send_derived_values == true`)
 * `gpfs_metaops = gpfs_num_inode_updates + gpfs_num_closes + gpfs_num_opens + gpfs_num_readdirs` (if `send_total_values == true`)
+* `gpfs_metaops_rate` (if `send_total_values == true` and `send_derived_values == true`)
 * `gpfs_bw_read` (if `send_bandwidths == true`)
 * `gpfs_bw_write` (if `send_bandwidths == true`)
+* `gpfs_bw_total` (if `send_bandwidths == true` and `send_total_values == true`)
 
 The collector adds a `filesystem` tag to all metrics

collectors/iostatMetric.go

@@ -20,18 +20,17 @@ import (
 	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
-// Konstante für den Pfad zu /proc/diskstats
 const IOSTATFILE = `/proc/diskstats`
 
 type IOstatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-	// Neues Feld zum Ausschließen von Devices per JSON-Konfiguration
 	ExcludeDevices []string `json:"exclude_devices,omitempty"`
 }
 
 type IOstatCollectorEntry struct {
-	lastValues map[string]int64
-	tags       map[string]string
+	currentValues map[string]int64
+	lastValues    map[string]int64
+	tags          map[string]string
 }
 
 type IOstatCollector struct {
@@ -105,16 +104,27 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 		if _, skip := stringArrayContains(m.config.ExcludeDevices, device); skip {
 			continue
 		}
-		values := make(map[string]int64)
+		currentValues := make(map[string]int64)
+		lastValues := make(map[string]int64)
 		for m := range m.matches {
-			values[m] = 0
+			currentValues[m] = 0
+			lastValues[m] = 0
+		}
+		for name, idx := range m.matches {
+			if idx < len(linefields) {
+				if value, err := strconv.ParseInt(linefields[idx], 0, 64); err == nil {
+					currentValues[name] = value
+					lastValues[name] = value // Set last to current for first read
+				}
+			}
 		}
 		m.devices[device] = IOstatCollectorEntry{
 			tags: map[string]string{
 				"device": device,
 				"type":   "node",
 			},
-			lastValues: values,
+			currentValues: currentValues,
+			lastValues:    lastValues,
 		}
 	}
 	m.init = true
@@ -153,18 +163,22 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
 		if _, ok := m.devices[device]; !ok {
 			continue
 		}
+		// Update current and last values
 		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.NewMessage(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
+					// Calculate difference using previous current and new value
+					diff := x - entry.currentValues[name]
+					y, err := lp.NewMetric(name, entry.tags, m.meta, int(diff), time.Now())
 					if err == nil {
 						output <- y
 					}
+					// Update last to previous current, and current to new value
+					entry.lastValues[name] = entry.currentValues[name]
+					entry.currentValues[name] = x
 				}
-				entry.lastValues[name] = x
 			}
 		}
 		m.devices[device] = entry

collectors/numastatsMetric.go

@@ -102,8 +102,11 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
 		file := filepath.Join(dir, "numastat")
 		m.topology = append(m.topology,
 			NUMAStatsCollectorTopolgy{
-				file:           file,
-				tagSet:         map[string]string{"memoryDomain": node},
+				file: file,
+				tagSet: map[string]string{
+					"type":    "memoryDomain",
+					"type-id": node,
+				},
 				previousValues: make(map[string]int64),
 			})
 	}

collectors/nvidiaMetric.go

@@ -589,7 +589,7 @@ func readMaxClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) erro
 	if !device.excludeMetrics["nv_max_graphics_clock"] {
 		max_gclk, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_GRAPHICS)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_max_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now())
+			y, err := lp.NewMetric("nv_max_graphics_clock", device.tags, device.meta, float64(max_gclk), time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -598,9 +598,9 @@ func readMaxClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) erro
 	}
 
 	if !device.excludeMetrics["nv_max_sm_clock"] {
-		maxSmClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
+		maxSmClock, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_SM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_max_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxSmClock)}, time.Now())
+			y, err := lp.NewMetric("nv_max_sm_clock", device.tags, device.meta, float64(maxSmClock), time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -609,9 +609,9 @@ func readMaxClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) erro
 	}
 
 	if !device.excludeMetrics["nv_max_mem_clock"] {
-		maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
+		maxMemClock, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_MEM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_max_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
+			y, err := lp.NewMetric("nv_max_mem_clock", device.tags, device.meta, float64(maxMemClock), time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -620,9 +620,9 @@ func readMaxClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) erro
 	}
 
 	if !device.excludeMetrics["nv_max_video_clock"] {
-		maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
+		maxVideoClock, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_VIDEO)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_max_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
+			y, err := lp.NewMetric("nv_max_video_clock", device.tags, device.meta, float64(maxVideoClock), time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y

collectors/slurmCgroupMetric.go

@@ -0,0 +1,349 @@
+package collectors
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"os/exec"
+	"os/user"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+)
+
+type SlurmJobData struct {
+	MemoryUsage      float64
+	MaxMemoryUsage   float64
+	LimitMemoryUsage float64
+	CpuUsageUser     float64
+	CpuUsageSys      float64
+	CpuSet           []int
+}
+
+type SlurmCgroupsConfig struct {
+	CgroupBase     string   `json:"cgroup_base"`
+	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+	UseSudo        bool     `json:"use_sudo,omitempty"`
+}
+
+type SlurmCgroupCollector struct {
+	metricCollector
+	config         SlurmCgroupsConfig
+	meta           map[string]string
+	tags           map[string]string
+	allCPUs        []int
+	cpuUsed        map[int]bool
+	cgroupBase     string
+	excludeMetrics map[string]struct{}
+	useSudo        bool
+}
+
+const defaultCgroupBase = "/sys/fs/cgroup/system.slice/slurmstepd.scope"
+
+func ParseCPUs(cpuset string) ([]int, error) {
+	var result []int
+	if cpuset == "" {
+		return result, nil
+	}
+
+	ranges := strings.Split(cpuset, ",")
+	for _, r := range ranges {
+		if strings.Contains(r, "-") {
+			parts := strings.Split(r, "-")
+			if len(parts) != 2 {
+				return nil, fmt.Errorf("invalid CPU range: %s", r)
+			}
+			start, err := strconv.Atoi(strings.TrimSpace(parts[0]))
+			if err != nil {
+				return nil, fmt.Errorf("invalid CPU range start: %s", parts[0])
+			}
+			end, err := strconv.Atoi(strings.TrimSpace(parts[1]))
+			if err != nil {
+				return nil, fmt.Errorf("invalid CPU range end: %s", parts[1])
+			}
+			for i := start; i <= end; i++ {
+				result = append(result, i)
+			}
+		} else {
+			cpu, err := strconv.Atoi(strings.TrimSpace(r))
+			if err != nil {
+				return nil, fmt.Errorf("invalid CPU ID: %s", r)
+			}
+			result = append(result, cpu)
+		}
+	}
+	return result, nil
+}
+
+func GetAllCPUs() ([]int, error) {
+	data, err := os.ReadFile("/sys/devices/system/cpu/online")
+	if err != nil {
+		return nil, fmt.Errorf("failed to read /sys/devices/system/cpu/online: %v", err)
+	}
+	return ParseCPUs(strings.TrimSpace(string(data)))
+}
+
+func (m *SlurmCgroupCollector) isExcluded(metric string) bool {
+	_, found := m.excludeMetrics[metric]
+	return found
+}
+
+func (m *SlurmCgroupCollector) readFile(path string) ([]byte, error) {
+	if m.useSudo {
+		cmd := exec.Command("sudo", "cat", path)
+		return cmd.Output()
+	}
+	return os.ReadFile(path)
+}
+
+func (m *SlurmCgroupCollector) Init(config json.RawMessage) error {
+	var err error
+	m.name = "SlurmCgroupCollector"
+	m.setup()
+	m.parallel = true
+	m.meta = map[string]string{"source": m.name, "group": "SLURM"}
+	m.tags = map[string]string{"type": "hwthread"}
+	m.cpuUsed = make(map[int]bool)
+	m.cgroupBase = defaultCgroupBase
+
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			return err
+		}
+		m.excludeMetrics = make(map[string]struct{})
+		for _, metric := range m.config.ExcludeMetrics {
+			m.excludeMetrics[metric] = struct{}{}
+		}
+		if m.config.CgroupBase != "" {
+			m.cgroupBase = m.config.CgroupBase
+		}
+	}
+
+	m.useSudo = m.config.UseSudo
+	if !m.useSudo {
+		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, "Reading cgroup files requires root privileges (or enable use_sudo in config)")
+			return fmt.Errorf("not root")
+		}
+	}
+
+	m.allCPUs, err = GetAllCPUs()
+	if err != nil {
+		cclog.ComponentError(m.name, "Error reading online CPUs:", err.Error())
+		return err
+	}
+
+	m.init = true
+	return nil
+}
+
+func (m *SlurmCgroupCollector) ReadJobData(jobdir string) (SlurmJobData, error) {
+	jobdata := SlurmJobData{
+		MemoryUsage:      0,
+		MaxMemoryUsage:   0,
+		LimitMemoryUsage: 0,
+		CpuUsageUser:     0,
+		CpuUsageSys:      0,
+		CpuSet:           []int{},
+	}
+
+	cg := func(f string) string { return filepath.Join(m.cgroupBase, jobdir, f) }
+
+	memUsage, err := m.readFile(cg("memory.current"))
+	if err == nil {
+		x, err := strconv.ParseFloat(strings.TrimSpace(string(memUsage)), 64)
+		if err == nil {
+			jobdata.MemoryUsage = x
+		}
+	}
+
+	maxMem, err := m.readFile(cg("memory.peak"))
+	if err == nil {
+		x, err := strconv.ParseFloat(strings.TrimSpace(string(maxMem)), 64)
+		if err == nil {
+			jobdata.MaxMemoryUsage = x
+		}
+	}
+
+	limitMem, err := m.readFile(cg("memory.max"))
+	if err == nil {
+		x, err := strconv.ParseFloat(strings.TrimSpace(string(limitMem)), 64)
+		if err == nil {
+			jobdata.LimitMemoryUsage = x
+		}
+	}
+
+	cpuStat, err := m.readFile(cg("cpu.stat"))
+	if err == nil {
+		lines := strings.Split(strings.TrimSpace(string(cpuStat)), "\n")
+		var usageUsec, userUsec, systemUsec float64
+		for _, line := range lines {
+			fields := strings.Fields(line)
+			if len(fields) < 2 {
+				continue
+			}
+			value, err := strconv.ParseFloat(fields[1], 64)
+			if err != nil {
+				continue
+			}
+			switch fields[0] {
+			case "usage_usec":
+				usageUsec = value
+			case "user_usec":
+				userUsec = value
+			case "system_usec":
+				systemUsec = value
+			}
+		}
+		if usageUsec > 0 {
+			jobdata.CpuUsageUser = (userUsec * 100 / usageUsec)
+			jobdata.CpuUsageSys = (systemUsec * 100 / usageUsec)
+		}
+	}
+
+	cpuSet, err := m.readFile(cg("cpuset.cpus"))
+	if err == nil {
+		cpus, err := ParseCPUs(strings.TrimSpace(string(cpuSet)))
+		if err == nil {
+			jobdata.CpuSet = cpus
+		}
+	}
+
+	return jobdata, nil
+}
+
+func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+	timestamp := time.Now()
+
+	for k := range m.cpuUsed {
+		delete(m.cpuUsed, k)
+	}
+
+	globPattern := filepath.Join(m.cgroupBase, "job_*")
+	jobDirs, err := filepath.Glob(globPattern)
+	if err != nil {
+		cclog.ComponentError(m.name, "Error globbing job directories:", err.Error())
+		return
+	}
+
+	for _, jdir := range jobDirs {
+		jKey := filepath.Base(jdir)
+
+		jobdata, err := m.ReadJobData(jKey)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading job data for", jKey, ":", err.Error())
+			continue
+		}
+
+		if len(jobdata.CpuSet) > 0 {
+			coreCount := float64(len(jobdata.CpuSet))
+			for _, cpu := range jobdata.CpuSet {
+				coreTags := map[string]string{
+					"type":    "hwthread",
+					"type-id": fmt.Sprintf("%d", cpu),
+				}
+
+				if coreCount > 0 && !m.isExcluded("job_mem_used") {
+					memPerCore := jobdata.MemoryUsage / coreCount
+					if y, err := lp.NewMessage("job_mem_used", coreTags, m.meta, map[string]interface{}{"value": memPerCore}, timestamp); err == nil {
+						y.AddMeta("unit", "Bytes")
+						output <- y
+					}
+				}
+
+				if coreCount > 0 && !m.isExcluded("job_max_mem_used") {
+					maxMemPerCore := jobdata.MaxMemoryUsage / coreCount
+					if y, err := lp.NewMessage("job_max_mem_used", coreTags, m.meta, map[string]interface{}{"value": maxMemPerCore}, timestamp); err == nil {
+						y.AddMeta("unit", "Bytes")
+						output <- y
+					}
+				}
+
+				if coreCount > 0 && !m.isExcluded("job_mem_limit") {
+					limitPerCore := jobdata.LimitMemoryUsage / coreCount
+					if y, err := lp.NewMessage("job_mem_limit", coreTags, m.meta, map[string]interface{}{"value": limitPerCore}, timestamp); err == nil {
+						y.AddMeta("unit", "Bytes")
+						output <- y
+					}
+				}
+
+				if coreCount > 0 && !m.isExcluded("job_user_cpu") {
+					cpuUserPerCore := jobdata.CpuUsageUser / coreCount
+					if y, err := lp.NewMessage("job_user_cpu", coreTags, m.meta, map[string]interface{}{"value": cpuUserPerCore}, timestamp); err == nil {
+						y.AddMeta("unit", "%")
+						output <- y
+					}
+				}
+
+				if coreCount > 0 && !m.isExcluded("job_sys_cpu") {
+					cpuSysPerCore := jobdata.CpuUsageSys / coreCount
+					if y, err := lp.NewMessage("job_sys_cpu", coreTags, m.meta, map[string]interface{}{"value": cpuSysPerCore}, timestamp); err == nil {
+						y.AddMeta("unit", "%")
+						output <- y
+					}
+				}
+
+				m.cpuUsed[cpu] = true
+			}
+		}
+	}
+
+	for _, cpu := range m.allCPUs {
+		if !m.cpuUsed[cpu] {
+			coreTags := map[string]string{
+				"type":    "hwthread",
+				"type-id": fmt.Sprintf("%d", cpu),
+			}
+
+			if !m.isExcluded("job_mem_used") {
+				if y, err := lp.NewMessage("job_mem_used", coreTags, m.meta, map[string]interface{}{"value": 0}, timestamp); err == nil {
+					y.AddMeta("unit", "Bytes")
+					output <- y
+				}
+			}
+
+			if !m.isExcluded("job_max_mem_used") {
+				if y, err := lp.NewMessage("job_max_mem_used", coreTags, m.meta, map[string]interface{}{"value": 0}, timestamp); err == nil {
+					y.AddMeta("unit", "Bytes")
+					output <- y
+				}
+			}
+
+			if !m.isExcluded("job_mem_limit") {
+				if y, err := lp.NewMessage("job_mem_limit", coreTags, m.meta, map[string]interface{}{"value": 0}, timestamp); err == nil {
+					y.AddMeta("unit", "Bytes")
+					output <- y
+				}
+			}
+
+			if !m.isExcluded("job_user_cpu") {
+				if y, err := lp.NewMessage("job_user_cpu", coreTags, m.meta, map[string]interface{}{"value": 0}, timestamp); err == nil {
+					y.AddMeta("unit", "%")
+					output <- y
+				}
+			}
+
+			if !m.isExcluded("job_sys_cpu") {
+				if y, err := lp.NewMessage("job_sys_cpu", coreTags, m.meta, map[string]interface{}{"value": 0}, timestamp); err == nil {
+					y.AddMeta("unit", "%")
+					output <- y
+				}
+			}
+		}
+	}
+}
+
+func (m *SlurmCgroupCollector) Close() {
+	m.init = false
+}

collectors/slurmCgroupMetric.md

@@ -0,0 +1,50 @@
+<!--
+---
+title: Slurm cgroup metric collector
+description: Collect per-core memory and CPU usage for SLURM jobs from cgroup v2
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 3
+hugo_path: docs/reference/cc-metric-collector/collectors/slurm_cgroup.md
+---
+-->
+
+## `slurm_cgroup` collector
+
+The `slurm_cgroup` collector reads job-specific resource metrics from the cgroup v2 filesystem and provides **hwthread** metrics for memory and CPU usage of running SLURM jobs.  
+
+### Example configuration
+
+```json
+"slurm_cgroup": {
+  "cgroup_base": "/sys/fs/cgroup/system.slice/slurmstepd.scope",
+  "exclude_metrics": [
+    "job_sys_cpu",
+    "job_mem_limit"
+  ],
+  "use_sudo": false
+}
+```
+
+* The `cgroup_base` parameter (optional) can be set to specify the root path to SLURM job cgroups. The default is `/sys/fs/cgroup/system.slice/slurmstepd.scope`.
+* The `exclude_metrics` array can be used to suppress individual metrics from being sent to the sink.
+* The cgroups metrics are only available for root users. If password-less sudo is configured, you can enable sudo in the configuration.
+
+### Reported metrics
+
+All metrics are available **per hardware thread** :
+
+* `job_mem_used` (`unit=Bytes`): Current memory usage of the job
+* `job_max_mem_used` (`unit=Bytes`): Peak memory usage
+* `job_mem_limit` (`unit=Bytes`): Cgroup memory limit
+* `job_user_cpu` (`unit=%`): User CPU utilization percentage
+* `job_sys_cpu` (`unit=%`): System CPU utilization percentage
+
+Each metric has tags:
+
+* `type=hwthread`
+* `type-id=<core_id>`
+
+### Limitations
+
+* **cgroups v2 required:** This collector only supports systems running with cgroups v2 (unified hierarchy).

docs/configuration.md

@@ -4,7 +4,7 @@ The configuration of the CC metric collector consists of five configuration file
 
 ## Global configuration
 
-The global file contains the paths to the other four files and some global options. 
+The global file contains the paths to the other four files and some global options. You can find examples in `example_configs`.
 
 ```json
 {

go.mod

@@ -1,46 +1,45 @@
 module github.com/ClusterCockpit/cc-metric-collector
 
-go 1.23.4
-
-toolchain go1.23.7
+go 1.24.0
 
 require (
-	github.com/ClusterCockpit/cc-lib v0.2.0
+	github.com/ClusterCockpit/cc-lib v0.10.1
 	github.com/ClusterCockpit/go-rocm-smi v0.3.0
-	github.com/NVIDIA/go-nvml v0.12.4-1
-	github.com/PaesslerAG/gval v1.2.2
-	github.com/fsnotify/fsnotify v1.7.0
+	github.com/NVIDIA/go-nvml v0.13.0-1
+	github.com/PaesslerAG/gval v1.2.4
+	github.com/fsnotify/fsnotify v1.9.0
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/tklauser/go-sysconf v0.3.13
+	github.com/tklauser/go-sysconf v0.3.15
 	golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
-	golang.org/x/exp v0.0.0-20250408133849-7e4ce0ab07d0
-	golang.org/x/sys v0.32.0
+	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b
+	golang.org/x/sys v0.37.0
 )
 
 require (
 	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
-	github.com/expr-lang/expr v1.17.2 // indirect
+	github.com/expr-lang/expr v1.17.6 // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/gorilla/mux v1.8.1 // indirect
 	github.com/influxdata/influxdb-client-go/v2 v2.14.0 // indirect
 	github.com/influxdata/line-protocol/v2 v2.2.1 // indirect
 	github.com/klauspost/compress v1.18.0 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
-	github.com/nats-io/nats.go v1.41.2 // indirect
+	github.com/nats-io/nats.go v1.46.1 // indirect
 	github.com/nats-io/nkeys v0.4.11 // indirect
 	github.com/nats-io/nuid v1.0.1 // indirect
 	github.com/oapi-codegen/runtime v1.1.1 // indirect
-	github.com/prometheus/client_golang v1.22.0 // indirect
+	github.com/prometheus/client_golang v1.23.2 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
-	github.com/prometheus/common v0.63.0 // indirect
+	github.com/prometheus/common v0.66.1 // indirect
 	github.com/prometheus/procfs v0.16.1 // indirect
 	github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 // indirect
 	github.com/shopspring/decimal v1.3.1 // indirect
 	github.com/stmcginnis/gofish v0.20.0 // indirect
-	github.com/tklauser/numcpus v0.7.0 // indirect
-	golang.org/x/crypto v0.37.0 // indirect
-	golang.org/x/net v0.39.0 // indirect
-	google.golang.org/protobuf v1.36.6 // indirect
+	github.com/tklauser/numcpus v0.10.0 // indirect
+	go.yaml.in/yaml/v2 v2.4.2 // indirect
+	golang.org/x/crypto v0.42.0 // indirect
+	golang.org/x/net v0.43.0 // indirect
+	google.golang.org/protobuf v1.36.8 // indirect
 )

go.sum

@@ -1,15 +1,17 @@
-github.com/ClusterCockpit/cc-lib v0.2.0 h1:4mEpppqWXkjS3PCHYSOxF3NisrKsbPjg17ftsFhEKPk=
-github.com/ClusterCockpit/cc-lib v0.2.0/go.mod h1:S6oZNtejBHu+ewmGRKYFqJmlrRReXv8J4D2UP8hmu50=
+github.com/ClusterCockpit/cc-lib v0.10.1 h1:tjGEH8mFGgznYxO8BKLiiar0eZR1Oytk8x5iIQHZR5s=
+github.com/ClusterCockpit/cc-lib v0.10.1/go.mod h1:nvTZuxFCTwlos8I1rL5O1RPab7vRtkU8E/PGiaF6pQA=
 github.com/ClusterCockpit/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8=
 github.com/ClusterCockpit/go-rocm-smi v0.3.0/go.mod h1:+I3UMeX3OlizXDf1WpGD43W4KGZZGVSGmny6rTeOnWA=
 github.com/NVIDIA/go-nvml v0.11.6-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
-github.com/NVIDIA/go-nvml v0.12.4-1 h1:WKUvqshhWSNTfm47ETRhv0A0zJyr1ncCuHiXwoTrBEc=
-github.com/NVIDIA/go-nvml v0.12.4-1/go.mod h1:8Llmj+1Rr+9VGGwZuRer5N/aCjxGuR5nPb/9ebBiIEQ=
-github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E=
-github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
+github.com/NVIDIA/go-nvml v0.13.0-1 h1:OLX8Jq3dONuPOQPC7rndB6+iDmDakw0XTYgzMxObkEw=
+github.com/NVIDIA/go-nvml v0.13.0-1/go.mod h1:+KNA7c7gIBH7SKSJ1ntlwkfN80zdx8ovl4hrK3LmPt4=
+github.com/PaesslerAG/gval v1.2.4 h1:rhX7MpjJlcxYwL2eTTYIOBUyEKZ+A96T9vQySWkVUiU=
+github.com/PaesslerAG/gval v1.2.4/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/antithesishq/antithesis-sdk-go v0.4.3-default-no-op h1:+OSa/t11TFhqfrX0EOSqQBDJ0YlpmK0rDSiB19dg9M0=
+github.com/antithesishq/antithesis-sdk-go v0.4.3-default-no-op/go.mod h1:IUpT2DPAKh6i/YhSbt6Gl3v2yvUZjmKncl7U91fup7E=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
@@ -21,18 +23,20 @@ github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ3
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/expr-lang/expr v1.17.2 h1:o0A99O/Px+/DTjEnQiodAgOIK9PPxL8DtXhBRKC+Iso=
-github.com/expr-lang/expr v1.17.2/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
+github.com/expr-lang/expr v1.17.6 h1:1h6i8ONk9cexhDmowO/A64VPxHScu7qfSl2k8OlINec=
+github.com/expr-lang/expr v1.17.6/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
 github.com/frankban/quicktest v1.11.2/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
 github.com/frankban/quicktest v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
 github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU=
-github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
-github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
+github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=
+github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
 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 v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
+github.com/google/go-tpm v0.9.5 h1:ocUmnDebX54dnW+MQWGQRbdaAcJELsa6PqZhJ48KwVU=
+github.com/google/go-tpm v0.9.5/go.mod h1:h9jEsEECg7gtLis0upRBQU+GhYVH6jMjrFxI8u6bVUY=
 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=
@@ -60,10 +64,16 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
 github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
+github.com/minio/highwayhash v1.0.3 h1:kbnuUMoHYyVl7szWjSxJnxw11k2U709jqFPPmIUyD6Q=
+github.com/minio/highwayhash v1.0.3/go.mod h1:GGYsuwP/fPD6Y9hMiXuapVvlIUEhFhMTh0rxU3ik1LQ=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
-github.com/nats-io/nats.go v1.41.2 h1:5UkfLAtu/036s99AhFRlyNDI1Ieylb36qbGjJzHixos=
-github.com/nats-io/nats.go v1.41.2/go.mod h1:iRWIPokVIFbVijxuMQq4y9ttaBTMe0SFdlZfMDd+33g=
+github.com/nats-io/jwt/v2 v2.8.0 h1:K7uzyz50+yGZDO5o772eRE7atlcSEENpL7P+b74JV1g=
+github.com/nats-io/jwt/v2 v2.8.0/go.mod h1:me11pOkwObtcBNR8AiMrUbtVOUGkqYjMQZ6jnSdVUIA=
+github.com/nats-io/nats-server/v2 v2.12.0 h1:OIwe8jZUqJFrh+hhiyKu8snNib66qsx806OslqJuo74=
+github.com/nats-io/nats-server/v2 v2.12.0/go.mod h1:nr8dhzqkP5E/lDwmn+A2CvQPMd1yDKXQI7iGg3lAvww=
+github.com/nats-io/nats.go v1.46.1 h1:bqQ2ZcxVd2lpYI97xYASeRTY3I5boe/IVmuUDPitHfo=
+github.com/nats-io/nats.go v1.46.1/go.mod h1:iRWIPokVIFbVijxuMQq4y9ttaBTMe0SFdlZfMDd+33g=
 github.com/nats-io/nkeys v0.4.11 h1:q44qGV008kYd9W1b1nEBkNzvnWxtRSQ7A8BoqRrcfa0=
 github.com/nats-io/nkeys v0.4.11/go.mod h1:szDimtgmfOi9n25JpfIdGw12tZFYXqhGxjhVxsatHVE=
 github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
@@ -73,12 +83,12 @@ github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmt
 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 v1.22.0 h1:rb93p9lokFEsctTys46VnV1kLCDpVZ0a/Y92Vm0Zc6Q=
-github.com/prometheus/client_golang v1.22.0/go.mod h1:R7ljNsLXhuQXYZYtw6GAE9AZg8Y7vEW5scdCXrWRXC0=
+github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o=
+github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg=
 github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
 github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
-github.com/prometheus/common v0.63.0 h1:YR/EIY1o3mEFP/kZCD7iDMnLPlGyuU2Gb3HIcXnA98k=
-github.com/prometheus/common v0.63.0/go.mod h1:VVFF/fBIoToEnWRVkYoXEkq3R3paCoxG9PXP74SnV18=
+github.com/prometheus/common v0.66.1 h1:h5E0h5/Y8niHc5DlaLlWLArTQI7tMrsfQjHV+d9ZoGs=
+github.com/prometheus/common v0.66.1/go.mod h1:gcaUsgf3KfRSwHY4dIMXLPV0K/Wg1oZ8+SbZk/HH/dA=
 github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
 github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
 github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
@@ -92,28 +102,36 @@ github.com/stmcginnis/gofish v0.20.0 h1:hH2V2Qe898F2wWT1loApnkDUrXXiLKqbSlMaH3Y1
 github.com/stmcginnis/gofish v0.20.0/go.mod h1:PzF5i8ecRG9A2ol8XT64npKUunyraJ+7t0kYMpQAtqU=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
-github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
-github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
-github.com/tklauser/go-sysconf v0.3.13 h1:GBUpcahXSpR2xN01jhkNAbTLRk2Yzgggk8IM08lq3r4=
-github.com/tklauser/go-sysconf v0.3.13/go.mod h1:zwleP4Q4OehZHGn4CYZDipCgg9usW5IJePewFCGVEa0=
-github.com/tklauser/numcpus v0.7.0 h1:yjuerZP127QG9m5Zh/mSO4wqurYil27tHrqwRoRjpr4=
-github.com/tklauser/numcpus v0.7.0/go.mod h1:bb6dMVcj8A42tSE7i32fsIUCbQNllK5iDguyOZRUzAY=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+github.com/tklauser/go-sysconf v0.3.15 h1:VE89k0criAymJ/Os65CSn1IXaol+1wrsFHEB8Ol49K4=
+github.com/tklauser/go-sysconf v0.3.15/go.mod h1:Dmjwr6tYFIseJw7a3dRLJfsHAMXZ3nEnL/aZY+0IuI4=
+github.com/tklauser/numcpus v0.10.0 h1:18njr6LDBk1zuna922MgdjQuJFjrdppsZG60sHGfjso=
+github.com/tklauser/numcpus v0.10.0/go.mod h1:BiTKazU708GQTYF4mB+cmlpT2Is1gLk7XVuEeem8LsQ=
+go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
+go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
+go.yaml.in/yaml/v2 v2.4.2 h1:DzmwEr2rDGHl7lsFgAHxmNz/1NlQ7xLIrlN2h5d1eGI=
+go.yaml.in/yaml/v2 v2.4.2/go.mod h1:081UH+NErpNdqlCXm3TtEran0rJZGxAYx9hb/ELlsPU=
 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 v0.37.0 h1:kJNSjF/Xp7kU0iB2Z+9viTPMW4EqqsrywMXLJOOsXSE=
-golang.org/x/crypto v0.37.0/go.mod h1:vg+k43peMZ0pUMhYmVAWysMK35e6ioLh3wB8ZCAfbVc=
-golang.org/x/exp v0.0.0-20250408133849-7e4ce0ab07d0 h1:R84qjqJb5nVJMxqWYb3np9L5ZsaDtB+a39EqjV0JSUM=
-golang.org/x/exp v0.0.0-20250408133849-7e4ce0ab07d0/go.mod h1:S9Xr4PYopiDyqSyp5NjCrhFrqg6A5zA2E/iPHPhqnS8=
-golang.org/x/net v0.39.0 h1:ZCu7HMWDxpXpaiKdhzIfaltL9Lp31x/3fCP11bc6/fY=
-golang.org/x/net v0.39.0/go.mod h1:X7NRbYVEA+ewNkCNyJ513WmMdQ3BineSwVtN2zD/d+E=
+golang.org/x/crypto v0.42.0 h1:chiH31gIWm57EkTXpwnqf8qeuMUi0yekh6mT2AvFlqI=
+golang.org/x/crypto v0.42.0/go.mod h1:4+rDnOTJhQCx2q7/j6rAN5XDw8kPjeaXEUR2eL94ix8=
+golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=
+golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
+golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE=
+golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg=
 golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.32.0 h1:s77OFDvIQeibCmezSnk/q6iAfkdiQaJi4VzroCFrN20=
-golang.org/x/sys v0.32.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/sys v0.37.0 h1:fdNQudmxPjkdUTPnLn5mdQv7Zwvbvpaxqs831goi9kQ=
+golang.org/x/sys v0.37.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
+golang.org/x/time v0.13.0 h1:eUlYslOIt32DgYD6utsuUeHs4d7AsEYLuIAdg7FlYgI=
+golang.org/x/time v0.13.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
-google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
+google.golang.org/protobuf v1.36.8 h1:xHScyCOEuuwZEc6UtSOvPbAT4zRh0xcNRYekJwfqyMc=
+google.golang.org/protobuf v1.36.8/go.mod h1:fuxRtAxBytpl4zzqUh6/eyUujkJdNiuEkXntxiD/uRU=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 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=

scripts/cc-metric-collector.deb.control

@@ -1,4 +1,6 @@
 Package: cc-metric-collector
+Section: misc
+Priority: optional
 Version: {VERSION}
 Installed-Size: {INSTALLED_SIZE}
 Architecture: {ARCH}

scripts/likwid_perfgroup_to_cc_config.py

@@ -44,6 +44,8 @@ def group_to_json(groupfile):
                 scope = "socket"
             if "PWR" in calc:
                 scope = "socket"
+            if "UMC" in calc:
+                scope = "socket"
 
             m = {"name" : metric, "calc": calc, "type" : scope, "publish" : True}
             metrics.append(m)