Fix lint errors

Bumps [github.com/tklauser/go-sysconf](https://github.com/tklauser/go-sysconf) from 0.3.16 to 0.4.0.
- [Release notes](https://github.com/tklauser/go-sysconf/releases)
- [Commits](https://github.com/tklauser/go-sysconf/compare/v0.3.16...v0.4.0)

---
updated-dependencies:
- dependency-name: github.com/tklauser/go-sysconf
  dependency-version: 0.4.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

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

collectors/beegfsmetaMetric.go

@@ -227,8 +227,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
 
 			for key, data := range m.matches {
 				value, _ := strconv.ParseFloat(data, 32)
-				y, err := lp.NewMessage(key, m.tags, m.meta, map[string]any{"value": value}, time.Now())
+				if y, err := lp.NewMetric(key, m.tags, m.meta, value, time.Now()); err == nil {
-				if err == nil {
 					output <- y
 				}
 			}

collectors/beegfsstorageMetric.go

@@ -218,8 +218,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
 
 			for key, data := range m.matches {
 				value, _ := strconv.ParseFloat(data, 32)
-				y, err := lp.NewMessage(key, m.tags, m.meta, map[string]any{"value": value}, time.Now())
+				if y, err := lp.NewMetric(key, m.tags, m.meta, value, time.Now()); err == nil {
-				if err == nil {
 					output <- y
 				}
 			}

collectors/collectorManager.go

@@ -50,6 +50,7 @@ var AvailableCollectors = map[string]MetricCollector{
 	"nfsiostat":       new(NfsIOStatCollector),
 	"slurm_cgroup":    new(SlurmCgroupCollector),
 	"smartmon":        new(SmartMonCollector),
+	"nvidia_gpm":      new(NvidiaGPMCollector),
 }
 
 // Metric collector manager data structure
@@ -99,17 +100,17 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
 	// Initialize configured collectors
 	for collectorName, collectorCfg := range cm.config {
 		if _, found := AvailableCollectors[collectorName]; !found {
-			cclog.ComponentError("CollectorManager", "SKIP unknown collector", collectorName)
+			cclog.ComponentErrorf("CollectorManager", "SKIP unknown collector %s", collectorName)
 			continue
 		}
 		collector := AvailableCollectors[collectorName]
 
 		err := collector.Init(collectorCfg)
 		if err != nil {
-			cclog.ComponentError("CollectorManager", fmt.Sprintf("Collector %s initialization failed: %v", collectorName, err))
+			cclog.ComponentErrorf("CollectorManager", "Collector %s initialization failed: %v", collectorName, err)
 			continue
 		}
-		cclog.ComponentDebug("CollectorManager", "ADD COLLECTOR", collector.Name())
+		cclog.ComponentDebugf("CollectorManager", "ADD COLLECTOR %s", collector.Name())
 		if collector.Parallel() {
 			cm.collectors = append(cm.collectors, collector)
 		} else {
@@ -155,7 +156,7 @@ func (cm *collectorManager) Start() {
 						return
 					default:
 						// Read metrics from collector c via goroutine
-						cclog.ComponentDebug("CollectorManager", c.Name(), t)
+						cclog.ComponentDebugf("CollectorManager: Read %s at %v", c.Name(), t)
 						cm.collector_wg.Add(1)
 						go func(myc MetricCollector) {
 							myc.Read(cm.duration, cm.output)
@@ -173,7 +174,7 @@ func (cm *collectorManager) Start() {
 						return
 					default:
 						// Read metrics from collector c
-						cclog.ComponentDebug("CollectorManager", c.Name(), t)
+						cclog.ComponentDebugf("CollectorManager: Read %s at %v", c.Name(), t)
 						c.Read(cm.duration, cm.output)
 					}
 				}

collectors/cpufreqCpuinfoMetric.go

@@ -171,7 +171,7 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
 							fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err))
 						return
 					}
-					if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]any{"value": value}, now); err == nil {
+					if y, err := lp.NewMetric("cpufreq", t.tagSet, m.meta, value, now); err == nil {
 						output <- y
 					}
 				}

collectors/cpufreqMetric.go

@@ -129,7 +129,7 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage
 			continue
 		}
 
-		if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]any{"value": cpuFreq}, now); err == nil {
+		if y, err := lp.NewMetric("cpufreq", t.tagSet, m.meta, cpuFreq, now); err == nil {
 			output <- y
 		}
 	}

collectors/cpustatMetric.go

@@ -27,6 +27,7 @@ const CPUSTATFILE = `/proc/stat`
 
 type CpustatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+	excludeNumCPUs bool
 }
 
 type CpustatCollector struct {
@@ -79,6 +80,7 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 			m.matches[match] = index
 		}
 	}
+	m.config.excludeNumCPUs = slices.Contains(m.config.ExcludeMetrics, "num_cpus")
 
 	// Check input file
 	file, err := os.Open(CPUSTATFILE)
@@ -95,11 +97,13 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 		line := scanner.Text()
 		linefields := strings.Fields(line)
 		if strings.Compare(linefields[0], "cpu") == 0 {
+			// Kernel system statistics for all CPUs
 			m.olddata["cpu"] = make(map[string]int64)
 			for k, v := range m.matches {
 				m.olddata["cpu"][k], _ = strconv.ParseInt(linefields[v], 0, 64)
 			}
 		} else if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
+			// Kernel system statistics per CPU
 			cpustr := strings.TrimLeft(linefields[0], "cpu")
 			cpu, _ := strconv.Atoi(cpustr)
 			m.cputags[linefields[0]] = map[string]string{
@@ -141,7 +145,7 @@ func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]st
 	sum := float64(0)
 	for name, value := range values {
 		sum += value
-		y, err := lp.NewMessage(name, tags, m.meta, map[string]any{"value": value * 100}, now)
+		y, err := lp.NewMetric(name, tags, m.meta, value*100, now)
 		if err == nil {
 			y.AddTag("unit", "Percent")
 			output <- y
@@ -149,7 +153,7 @@ func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]st
 	}
 	if v, ok := values["cpu_idle"]; ok {
 		sum -= v
-		y, err := lp.NewMessage("cpu_used", tags, m.meta, map[string]any{"value": sum * 100}, now)
+		y, err := lp.NewMetric("cpu_used", tags, m.meta, sum*100, now)
 		if err == nil {
 			y.AddTag("unit", "Percent")
 			output <- y
@@ -191,14 +195,10 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage
 		}
 	}
 
-	num_cpus_metric, err := lp.NewMessage("num_cpus",
+	if !m.config.excludeNumCPUs {
-		m.nodetags,
+		if num_cpus_metric, err := lp.NewMetric("num_cpus", m.nodetags, m.meta, num_cpus, now); err == nil {
-		m.meta,
+			output <- num_cpus_metric
-		map[string]any{"value": num_cpus},
+		}
-		now,
-	)
-	if err == nil {
-		output <- num_cpus_metric
 	}
 
 	m.lastTimestamp = now

collectors/diskstatMetric.go

@@ -128,30 +128,14 @@ mountLoop:
 		tags := map[string]string{"type": "node", "device": linefields[0]}
 		total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000_000_000)
 		if m.allowedMetrics["disk_total"] {
-			y, err := lp.NewMessage(
+			if y, err := lp.NewMetric("disk_total", tags, m.meta, total, time.Now()); err == nil {
-				"disk_total",
-				tags,
-				m.meta,
-				map[string]any{
-					"value": total,
-				},
-				time.Now())
-			if err == nil {
 				y.AddMeta("unit", "GBytes")
 				output <- y
 			}
 		}
 		free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000_000_000)
 		if m.allowedMetrics["disk_free"] {
-			y, err := lp.NewMessage(
+			if y, err := lp.NewMetric("disk_free", tags, m.meta, free, time.Now()); err == nil {
-				"disk_free",
-				tags,
-				m.meta,
-				map[string]any{
-					"value": free,
-				},
-				time.Now())
-			if err == nil {
 				y.AddMeta("unit", "GBytes")
 				output <- y
 			}
@@ -164,16 +148,7 @@ mountLoop:
 		}
 	}
 	if m.allowedMetrics["part_max_used"] {
-		y, err := lp.NewMessage(
+		y, err := lp.NewMetric("part_max_used", map[string]string{"type": "node"}, m.meta, int(part_max_used), time.Now())
-			"part_max_used",
-			map[string]string{
-				"type": "node",
-			},
-			m.meta,
-			map[string]any{
-				"value": int(part_max_used),
-			},
-			time.Now())
 		if err == nil {
 			y.AddMeta("unit", "percent")
 			output <- y

collectors/infinibandMetric.go

@@ -32,7 +32,6 @@ type InfinibandCollectorMetric struct {
 	scale            int64
 	addToIBTotal     bool
 	addToIBTotalPkgs bool
-	currentState     int64
 	lastState        int64
 }
 
@@ -202,7 +201,9 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 	for i := range m.info {
 		info := &m.info[i]
 
-		var ib_total, ib_total_pkts int64
+		var ib_total, ib_total_last_state,
+			ib_total_pkts, ib_total_pkts_last_state int64
+		var ib_total_last_state_available, ib_total_pkts_last_state_available bool
 		for i := range info.portCounterFiles {
 			counterDef := &info.portCounterFiles[i]
 
@@ -227,19 +228,9 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 			// Scale raw value
 			v *= counterDef.scale
 
-			// Save current state
-			counterDef.currentState = v
-
 			// Send absolut values
 			if m.config.SendAbsoluteValues {
-				if y, err := lp.NewMessage(
+				if y, err := lp.NewMetric(counterDef.name, info.tagSet, m.meta, v, now); err == nil {
-					counterDef.name,
-					info.tagSet,
-					m.meta,
-					map[string]any{
-						"value": counterDef.currentState,
-					},
-					now); err == nil {
 					y.AddMeta("unit", counterDef.unit)
 					output <- y
 				}
@@ -248,59 +239,65 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 			// Send derived values
 			if m.config.SendDerivedValues {
 				if counterDef.lastState >= 0 {
-					rate := float64((counterDef.currentState - counterDef.lastState)) / timeDiff
+					rate := float64((v - counterDef.lastState)) / timeDiff
-					if y, err := lp.NewMessage(
+					if y, err := lp.NewMetric(counterDef.name+"_bw", info.tagSet, m.meta, rate, now); err == nil {
-						counterDef.name+"_bw",
-						info.tagSet,
-						m.meta,
-						map[string]any{
-							"value": rate,
-						},
-						now); err == nil {
 						y.AddMeta("unit", counterDef.unit+"/sec")
 						output <- y
+					}
 
+					// Sum up total values of last state
+					if m.config.SendTotalValues {
+						switch {
+						case counterDef.addToIBTotal:
+							ib_total_last_state += counterDef.lastState
+							ib_total_last_state_available = true
+						case counterDef.addToIBTotalPkgs:
+							ib_total_pkts_last_state += counterDef.lastState
+							ib_total_pkts_last_state_available = true
+						}
 					}
 				}
-				counterDef.lastState = counterDef.currentState
+				counterDef.lastState = v
 			}
 
 			// Sum up total values
 			if m.config.SendTotalValues {
 				switch {
 				case counterDef.addToIBTotal:
-					ib_total += counterDef.currentState
+					ib_total += v
 				case counterDef.addToIBTotalPkgs:
-					ib_total_pkts += counterDef.currentState
+					ib_total_pkts += v
 				}
 			}
 		}
 
 		// Send total values
 		if m.config.SendTotalValues {
-			if y, err := lp.NewMessage(
+			if y, err := lp.NewMetric("ib_total", info.tagSet, m.meta, ib_total, now); err == nil {
-				"ib_total",
-				info.tagSet,
-				m.meta,
-				map[string]any{
-					"value": ib_total,
-				},
-				now); err == nil {
 				y.AddMeta("unit", "bytes")
 				output <- y
 			}
 
-			if y, err := lp.NewMessage(
+			if y, err := lp.NewMetric("ib_total_pkts", info.tagSet, m.meta, ib_total_pkts, now); err == nil {
-				"ib_total_pkts",
-				info.tagSet,
-				m.meta,
-				map[string]any{
-					"value": ib_total_pkts,
-				},
-				now); err == nil {
 				y.AddMeta("unit", "packets")
 				output <- y
 			}
+
+			if m.config.SendDerivedValues && ib_total_last_state_available {
+				rate := float64((ib_total - ib_total_last_state)) / timeDiff
+				if y, err := lp.NewMetric("ib_total_bw", info.tagSet, m.meta, rate, now); err == nil {
+					y.AddMeta("unit", "bytes/sec")
+					output <- y
+				}
+			}
+
+			if m.config.SendDerivedValues && ib_total_pkts_last_state_available {
+				rate := float64((ib_total_pkts - ib_total_pkts_last_state)) / timeDiff
+				if y, err := lp.NewMetric("ib_total_pkts_bw", info.tagSet, m.meta, rate, now); err == nil {
+					y.AddMeta("unit", "packets/sec")
+					output <- y
+				}
+			}
 		}
 	}
 }

collectors/infinibandMetric.md

@@ -41,5 +41,7 @@ Metrics:
 * `ib_xmit_bw` (if `send_derived_values == true`)
 * `ib_recv_pkts_bw` (if `send_derived_values == true`)
 * `ib_xmit_pkts_bw` (if `send_derived_values == true`)
+* `ib_total_bw` (if `send_total_values == true` and `send_derived_values == true`)
+* `ib_total_pkts_bw` (if `send_total_values == true` and `send_derived_values == true`)
 
 The collector adds a `device` tag to all metrics

collectors/ipmiMetric.go

@@ -28,9 +28,9 @@ type IpmiCollector struct {
 	metricCollector
 
 	config struct {
-		IpmitoolPath    string   `json:"ipmitool_path"`
+		IpmitoolPath    string `json:"ipmitool_path"`
-		IpmisensorsPath string   `json:"ipmisensors_path"`
+		IpmisensorsPath string `json:"ipmisensors_path"`
-		Sudo            bool     `json:"use_sudo"`
+		Sudo            bool   `json:"use_sudo"`
 	}
 
 	ipmitool    string
@@ -157,7 +157,7 @@ func (m *IpmiCollector) readIpmiTool(output chan lp.CCMessage) error {
 			unit = "Watts"
 		}
 
-		y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]any{"value": v}, time.Now())
+		y, err := lp.NewMetric(name, map[string]string{"type": "node"}, m.meta, v, time.Now())
 		if err != nil {
 			cclog.ComponentErrorf(m.name, "Failed to create message: %v", err)
 			continue
@@ -209,7 +209,7 @@ func (m *IpmiCollector) readIpmiSensors(output chan lp.CCMessage) error {
 			continue
 		}
 		name := strings.ToLower(strings.ReplaceAll(lv[1], " ", "_"))
-		y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]any{"value": v}, time.Now())
+		y, err := lp.NewMetric(name, map[string]string{"type": "node"}, m.meta, v, time.Now())
 		if err != nil {
 			cclog.ComponentErrorf(m.name, "Failed to create message: %v", err)
 			continue

collectors/loadavgMetric.go

@@ -109,7 +109,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
 		if m.load_skips[i] {
 			continue
 		}
-		y, err := lp.NewMessage(name, m.tags, m.meta, map[string]any{"value": x}, now)
+		y, err := lp.NewMetric(name, m.tags, m.meta, x, now)
 		if err == nil {
 			output <- y
 		}
@@ -128,7 +128,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
 		if m.proc_skips[i] {
 			continue
 		}
-		y, err := lp.NewMessage(name, m.tags, m.meta, map[string]any{"value": x}, now)
+		y, err := lp.NewMetric(name, m.tags, m.meta, x, now)
 		if err == nil {
 			output <- y
 		}

collectors/memstatMetric.go

@@ -72,7 +72,8 @@ func getStats(filename string) map[string]MemstatStats {
 	for scanner.Scan() {
 		line := scanner.Text()
 		linefields := strings.Fields(line)
-		if len(linefields) == 3 {
+		switch len(linefields) {
+		case 3:
 			v, err := strconv.ParseFloat(linefields[1], 64)
 			if err == nil {
 				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
@@ -80,7 +81,7 @@ func getStats(filename string) map[string]MemstatStats {
 					unit:  linefields[2],
 				}
 			}
-		} else if len(linefields) == 5 {
+		case 5:
 			v, err := strconv.ParseFloat(linefields[3], 64)
 			if err == nil {
 				cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
@@ -106,7 +107,10 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 			return fmt.Errorf("%s Init(): Error decoding JSON config: %w", m.name, err)
 		}
 	}
-	m.meta = map[string]string{"source": m.name, "group": "Memory"}
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "Memory",
+	}
 	m.stats = make(map[string]int64)
 	m.matches = make(map[string]string)
 	m.tags = map[string]string{"type": "node"}
@@ -145,7 +149,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 		"KernelStack":     "mem_kernelstack",
 	}
 	for k, v := range matches {
-		if !slices.Contains(m.config.ExcludeMetrics, k) {
+		if !slices.Contains(m.config.ExcludeMetrics, v) {
 			m.matches[k] = v
 		}
 	}
@@ -153,7 +157,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 	if !slices.Contains(m.config.ExcludeMetrics, "mem_used") {
 		m.sendMemUsed = true
 	}
-	if len(m.matches) == 0 {
+	if len(m.matches) == 0 && !m.sendMemUsed {
 		return fmt.Errorf("%s Init(): no metrics to collect", m.name)
 	}
 	if err := m.setup(); err != nil {
@@ -213,7 +217,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 				}
 			}
 
-			y, err := lp.NewMessage(name, tags, m.meta, map[string]any{"value": value}, time.Now())
+			y, err := lp.NewMetric(name, tags, m.meta, value, time.Now())
 			if err == nil {
 				if len(unit) > 0 {
 					y.AddMeta("unit", unit)
@@ -252,7 +256,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 					}
 				}
 			}
-			y, err := lp.NewMessage("mem_used", tags, m.meta, map[string]any{"value": memUsed}, time.Now())
+			y, err := lp.NewMetric("mem_used", tags, m.meta, memUsed, time.Now())
 			if err == nil {
 				if len(unit) > 0 {
 					y.AddMeta("unit", unit)

collectors/netstatMetric.go

@@ -262,14 +262,14 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 					continue
 				}
 				if m.config.SendAbsoluteValues {
-					if y, err := lp.NewMessage(metric.name, metric.tags, metric.meta, map[string]any{"value": v}, now); err == nil {
+					if y, err := lp.NewMetric(metric.name, metric.tags, metric.meta, v, now); err == nil {
 						output <- y
 					}
 				}
 				if m.config.SendDerivedValues {
 					if metric.lastValue >= 0 {
 						rate := float64(v-metric.lastValue) / timeDiff
-						if y, err := lp.NewMessage(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]any{"value": rate}, now); err == nil {
+						if y, err := lp.NewMetric(metric.name+"_bw", metric.tags, metric.meta_rates, rate, now); err == nil {
 							output <- y
 						}
 					}

collectors/nfsMetric.go

@@ -146,14 +146,13 @@ func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			continue
 		}
 
-		valueMap := make(map[string]any)
 		if data.current >= 0 && data.last >= 0 {
-			valueMap["value"] = data.current - data.last
+			value := data.current - data.last
-		}
+			y, err := lp.NewMetric(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, value, timestamp)
-		y, err := lp.NewMessage(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, valueMap, timestamp)
+			if err == nil {
-		if err == nil {
+				y.AddMeta("version", m.version)
-			y.AddMeta("version", m.version)
+				output <- y
-			output <- y
+			}
 		}
 	}
 }

collectors/nfsiostatMetric.go

@@ -145,14 +145,7 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
 		if old, ok := m.data[mntpoint]; ok {
 			for name, newVal := range values {
 				if m.config.SendAbsoluteValues {
-					msg, err := lp.NewMessage(
+					msg, err := lp.NewMetric("nfsio_"+name, m.tags, m.meta, newVal, now)
-						"nfsio_"+name,
-						m.tags,
-						m.meta,
-						map[string]any{
-							"value": newVal,
-						},
-						now)
 					if err == nil {
 						msg.AddTag("stype", "filesystem")
 						msg.AddTag("stype-id", mntpoint)
@@ -161,7 +154,7 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
 				}
 				if m.config.SendDerivedValues {
 					rate := float64(newVal-old[name]) / timeDiff
-					msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s_bw", name), m.tags, m.meta, map[string]any{"value": rate}, now)
+					msg, err := lp.NewMetric(fmt.Sprintf("nfsio_%s_bw", name), m.tags, m.meta, rate, now)
 					if err == nil {
 						if strings.HasPrefix(name, "page") {
 							msg.AddMeta("unit", "4K_pages/s")

collectors/nvidiaGPMMetric.go

@@ -0,0 +1,396 @@
+package collectors
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"slices"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
+	"github.com/NVIDIA/go-nvml/pkg/nvml"
+)
+
+type NvidiaGPMMetricDef struct {
+	name    string
+	outname string
+	id      nvml.GpmMetricId
+	unit    string
+}
+
+var NvidiaGPMMetrics []NvidiaGPMMetricDef = []NvidiaGPMMetricDef{
+	{
+		name:    "GRAPHICS_UTIL",
+		outname: "nv_gpm_graphics_util",
+		id:      nvml.GPM_METRIC_GRAPHICS_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "SM_UTIL",
+		outname: "nv_gpm_sm_util",
+		id:      nvml.GPM_METRIC_SM_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "SM_OCCUPANCY",
+		outname: "nv_gpm_sm_occupancy",
+		id:      nvml.GPM_METRIC_SM_OCCUPANCY,
+		unit:    "%",
+	},
+	{
+		name:    "INTEGER_UTIL",
+		outname: "nv_gpm_integer_util",
+		id:      nvml.GPM_METRIC_INTEGER_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "ANY_TENSOR_UTIL",
+		outname: "nv_gpm_any_tensor_util",
+		id:      nvml.GPM_METRIC_ANY_TENSOR_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "DFMA_TENSOR_UTIL",
+		outname: "nv_gpm_dfma_tensor_util",
+		id:      nvml.GPM_METRIC_DFMA_TENSOR_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "HMMA_TENSOR_UTIL",
+		outname: "nv_gpm_hmma_tensor_util",
+		id:      nvml.GPM_METRIC_HMMA_TENSOR_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "IMMA_TENSOR_UTIL",
+		outname: "nv_gpm_imma_tensor_util",
+		id:      nvml.GPM_METRIC_IMMA_TENSOR_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "DRAM_BW_UTIL",
+		outname: "nv_gpm_dram_bw_util",
+		id:      nvml.GPM_METRIC_DRAM_BW_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "FP64_UTIL",
+		outname: "nv_gpm_fp64_util",
+		id:      nvml.GPM_METRIC_FP64_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "FP32_UTIL",
+		outname: "nv_gpm_fp32_util",
+		id:      nvml.GPM_METRIC_FP32_UTIL,
+		unit:    "%",
+	},
+	{
+		name:    "FP16_UTIL",
+		outname: "nv_gpm_fp16_util",
+		id:      nvml.GPM_METRIC_FP16_UTIL,
+		unit:    "%",
+	},
+}
+
+type NvidiaGPMCollectorConfig struct {
+	Metrics               []string `json:"metrics,omitempty"`
+	ExcludeDevices        []string `json:"exclude_devices,omitempty"`
+	AddPciInfoTag         bool     `json:"add_pci_info_tag,omitempty"`
+	UsePciInfoAsTypeId    bool     `json:"use_pci_info_as_type_id,omitempty"`
+	AddUuidMeta           bool     `json:"add_uuid_meta,omitempty"`
+	AddBoardNumberMeta    bool     `json:"add_board_number_meta,omitempty"`
+	AddSerialMeta         bool     `json:"add_serial_meta,omitempty"`
+	ProcessMigDevices     bool     `json:"process_mig_devices,omitempty"`
+	UseUuidForMigDevices  bool     `json:"use_uuid_for_mig_device,omitempty"`
+	UseSliceForMigDevices bool     `json:"use_slice_for_mig_device,omitempty"`
+}
+
+type NvidiaGPMCollectorDevice struct {
+	device        nvml.Device
+	tags          map[string]string
+	meta          map[string]string
+	startTime     time.Time
+	endTime       time.Time
+	measurement   nvml.GpmMetricsGetType
+	metricsLookup map[int]NvidiaGPMMetricDef
+}
+
+type NvidiaGPMCollector struct {
+	metricCollector
+
+	config   NvidiaGPMCollectorConfig
+	gpus     []NvidiaGPMCollectorDevice
+	num_gpus int
+}
+
+func (m *NvidiaGPMCollector) Init(config json.RawMessage) error {
+	var err error = nil
+	m.name = "NvidiaGPMCollector"
+	m.parallel = true
+	if err := m.setup(); err != nil {
+		return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err)
+	}
+	if len(config) > 0 {
+		d := json.NewDecoder(strings.NewReader(string(config)))
+		d.DisallowUnknownFields()
+		if err = d.Decode(&m.config); err != nil {
+			return fmt.Errorf("%s Init(): Error decoding JSON config: %w", m.name, err)
+		}
+	}
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "NvidiaGPM",
+	}
+
+	// Initialize NVIDIA Management Library (NVML)
+	ret := nvml.Init()
+
+	// Error: NVML library not found
+	// (nvml.ErrorString can not be used in this case)
+	if ret == nvml.ERROR_LIBRARY_NOT_FOUND {
+		return fmt.Errorf("%s Init(): NVML library not found", m.name)
+	}
+	if ret != nvml.SUCCESS {
+		err = errors.New(nvml.ErrorString(ret))
+		return fmt.Errorf("%s Init(): Unable to initialize NVML: %w", m.name, err)
+	}
+
+	// Number of NVIDIA GPUs
+	num_gpus, ret := nvml.DeviceGetCount()
+	if ret != nvml.SUCCESS {
+		err = errors.New(nvml.ErrorString(ret))
+		return fmt.Errorf("%s Init(): Unable to get device count: %w", m.name, err)
+	}
+
+	// For all GPUs
+	m.gpus = make([]NvidiaGPMCollectorDevice, 0, num_gpus)
+	for i := range num_gpus {
+
+		// Skip excluded devices by ID
+		str_i := strconv.Itoa(i)
+		if slices.Contains(m.config.ExcludeDevices, str_i) {
+			cclog.ComponentDebugf(m.name, "Skipping excluded device %s", str_i)
+			continue
+		}
+
+		// Get device handle
+		device, ret := nvml.DeviceGetHandleByIndex(i)
+		if ret != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(ret))
+			cclog.ComponentErrorf(m.name, "Unable to get device at index %d: %s", i, err.Error())
+			continue
+		}
+
+		supportInfo, ret := nvml.GpmQueryDeviceSupport(device)
+		if ret != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(ret))
+			cclog.ComponentErrorf(m.name, "Unable to query GPM support for device at index %d: %s", i, err.Error())
+			continue
+		} else {
+			if supportInfo.IsSupportedDevice == uint32(nvml.FEATURE_DISABLED) {
+				cclog.ComponentErrorf(m.name, "Device at index %d does not support GPM metrics", i)
+				continue
+			}
+		}
+
+		stream, ret := nvml.GpmQueryIfStreamingEnabled(device)
+		if ret != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(ret))
+			cclog.ComponentErrorf(m.name, "Unable to query GPM streaming for device at index %d: %s", i, err.Error())
+			continue
+		} else {
+			if stream == uint32(nvml.FEATURE_DISABLED) {
+				ret = nvml.GpmSetStreamingEnabled(device, uint32(nvml.FEATURE_ENABLED))
+				if ret != nvml.SUCCESS {
+					err = errors.New(nvml.ErrorString(ret))
+					cclog.ComponentErrorf(m.name, "Unable to set streaming mode for device at index %d: %s", i, err.Error())
+				}
+			}
+		}
+
+		// Get device's PCI info
+		pciInfo, ret := nvml.DeviceGetPciInfo(device)
+		if ret != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(ret))
+			cclog.ComponentErrorf(m.name, "Unable to get PCI info for device at index %d: %s", i, err.Error())
+			continue
+		}
+		// Create PCI ID in the common format used by the NVML.
+		pci_id := fmt.Sprintf(
+			nvml.DEVICE_PCI_BUS_ID_FMT,
+			pciInfo.Domain,
+			pciInfo.Bus,
+			pciInfo.Device)
+
+		// Skip excluded devices specified by PCI ID
+		if slices.Contains(m.config.ExcludeDevices, pci_id) {
+			cclog.ComponentDebugf(m.name, "Skipping excluded device %s", pci_id)
+			continue
+		}
+		ss, nvmlErr := nvml.GpmSampleAlloc()
+		if nvmlErr != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(ret))
+			cclog.ComponentErrorf(m.name, "Failed to allocate GPM sample for device %d: %s", i, err.Error())
+			continue
+		}
+		es, nvmlErr := nvml.GpmSampleAlloc()
+		if nvmlErr != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(ret))
+			cclog.ComponentErrorf(m.name, "Failed to allocate GPM sample for device %d: %s", i, err.Error())
+			continue
+		}
+
+		// Select which value to use as 'type-id'.
+		// The PCI ID is commonly required in SLURM environments because the
+		// numberic IDs used by SLURM and the ones used by NVML might differ
+		// depending on the job type. The PCI ID is more reliable but is commonly
+		// not recorded for a job, so it must be added manually in prologue or epilogue
+		// e.g. to the comment field
+		tid := str_i
+		if m.config.UsePciInfoAsTypeId {
+			tid = pci_id
+		}
+
+		// Now we got all infos together, populate the device list
+		g := NvidiaGPMCollectorDevice{}
+
+		// Add device handle
+		g.device = device
+
+		// Add tags
+		g.tags = map[string]string{
+			"type":    "accelerator",
+			"type-id": tid,
+		}
+
+		// Add PCI info as tag if not already used as 'type-id'
+		if m.config.AddPciInfoTag && !m.config.UsePciInfoAsTypeId {
+			g.tags["pci_identifier"] = pci_id
+		}
+
+		g.meta = map[string]string{
+			"source": m.name,
+			"group":  "Nvidia",
+		}
+
+		if m.config.AddBoardNumberMeta {
+			board, ret := nvml.DeviceGetBoardPartNumber(device)
+			if ret != nvml.SUCCESS {
+				err = errors.New(nvml.ErrorString(ret))
+				cclog.ComponentError(m.name, "Unable to get boart part number for device at index", i, ":", err.Error())
+			} else {
+				g.meta["board_number"] = board
+			}
+		}
+		if m.config.AddSerialMeta {
+			serial, ret := nvml.DeviceGetSerial(device)
+			if ret != nvml.SUCCESS {
+				err = errors.New(nvml.ErrorString(ret))
+				cclog.ComponentError(m.name, "Unable to get serial number for device at index", i, ":", err.Error())
+			} else {
+				g.meta["serial"] = serial
+			}
+		}
+		if m.config.AddUuidMeta {
+			uuid, ret := nvml.DeviceGetUUID(device)
+			if ret != nvml.SUCCESS {
+				err = errors.New(nvml.ErrorString(ret))
+				cclog.ComponentError(m.name, "Unable to get UUID for device at index", i, ":", err.Error())
+			} else {
+				g.meta["uuid"] = uuid
+			}
+		}
+
+		g.measurement.Sample1 = ss
+		g.measurement.Sample2 = es
+		g.measurement.Version = nvml.GPM_METRICS_GET_VERSION
+		g.metricsLookup = make(map[int]NvidiaGPMMetricDef)
+		metIdx := 0
+		for _, inmetric := range m.config.Metrics {
+			for _, defmetric := range NvidiaGPMMetrics {
+				if inmetric == defmetric.outname || inmetric == defmetric.name {
+					g.measurement.Metrics[metIdx] = nvml.GpmMetric{
+						MetricId: uint32(defmetric.id),
+					}
+					g.metricsLookup[metIdx] = defmetric
+					metIdx += 1
+				}
+			}
+		}
+		g.measurement.NumMetrics = uint32(metIdx)
+		m.gpus = append(m.gpus, g)
+	}
+	cclog.ComponentDebugf(m.name, "Found %d Nvidia GPUs with GPM support", len(m.gpus))
+	m.num_gpus = len(m.gpus)
+	m.init = true
+	return err
+}
+
+func (m *NvidiaGPMCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+	var err error
+	if !m.init {
+		return
+	}
+	for i, gpu := range m.gpus {
+		gpu.startTime = time.Now()
+		nvmlErr := gpu.measurement.Sample1.Get(gpu.device)
+		if nvmlErr != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(nvmlErr))
+			cclog.ComponentError(m.name, "Unable to get start GPM sample for device at index", i, ":", err.Error())
+			continue
+		}
+	}
+	time.Sleep(interval)
+
+	for i, gpu := range m.gpus {
+		gpu.endTime = time.Now()
+		nvmlErr := gpu.measurement.Sample2.Get(gpu.device)
+		if nvmlErr != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(nvmlErr))
+			cclog.ComponentError(m.name, "Unable to get stop GPM sample for device at index", i, ":", err.Error())
+			continue
+		}
+	}
+
+	for i, gpu := range m.gpus {
+		nvmlErr := nvml.GpmMetricsGet(&gpu.measurement)
+		if nvmlErr != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(nvmlErr))
+			cclog.ComponentError(m.name, "Unable to get evaluate GPM sample for device at index", i, ":", err.Error())
+			continue
+		}
+		for idx, metricDef := range gpu.metricsLookup {
+			y, err := lp.NewMetric(metricDef.outname, gpu.tags, gpu.meta, gpu.measurement.Metrics[idx].Value, time.Now())
+			if err == nil {
+				y.AddMeta("unit", metricDef.unit)
+				output <- y
+			}
+		}
+	}
+
+}
+
+func (m *NvidiaGPMCollector) Close() {
+	if m.init {
+		for i, gpu := range m.gpus {
+			ret := gpu.measurement.Sample1.Free()
+			if ret != nvml.SUCCESS {
+				err := errors.New(nvml.ErrorString(ret))
+				cclog.ComponentErrorf(m.name, "Unable to free start sample for device at index %d: %s", i, err.Error())
+			}
+			ret = gpu.measurement.Sample2.Free()
+			if ret != nvml.SUCCESS {
+				err := errors.New(nvml.ErrorString(ret))
+				cclog.ComponentErrorf(m.name, "Unable to free stop sample for device at index %d: %s", i, err.Error())
+			}
+		}
+		if ret := nvml.Shutdown(); ret != nvml.SUCCESS {
+			cclog.ComponentError(m.name, "nvml.Shutdown() not successful")
+		}
+		m.init = false
+	}
+}

collectors/nvidiaGPMMetric.md

@@ -0,0 +1,54 @@
+<!--
+---
+title: "Nvidia NVML GPM metric collector"
+description: Collect metrics for Nvidia GPUs using the NVML GPM interface
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/nvidiaGPM.md
+---
+-->
+
+## `nvidiaGPM` collector
+
+```json
+  "nvidia_gpm": {
+    "metrics": [
+      "nv_fb_mem_used",
+      "nv_fan"
+    ],
+    "exclude_devices": [
+      "0","1", "0000000:ff:01.0"
+    ],
+    
+    "process_mig_devices": false,
+    "use_pci_info_as_type_id": true,
+    "add_pci_info_tag": false,
+    "add_uuid_meta": false,
+    "add_board_number_meta": false,
+    "add_serial_meta": false,
+    "use_uuid_for_mig_device": false,
+    "use_slice_for_mig_device": false
+  }
+```
+
+The `nvidia_gpm` collector can be configured to leave out specific devices with the `exclude_devices` option. It takes IDs as supplied to the NVML with `nvmlDeviceGetHandleByIndex()` or the PCI address in NVML format (`%08X:%02X:%02X.0`). Commonly only the physical GPUs are monitored. If MIG devices should be analyzed as well, set `process_mig_devices` (adds `stype=mig,stype-id=<mig_index>`). With the options `use_uuid_for_mig_device` and `use_slice_for_mig_device`, the `<mig_index>` can be replaced with the UUID (e.g. `MIG-6a9f7cc8-6d5b-5ce0-92de-750edc4d8849`) or the MIG slice name (e.g. `1g.5gb`).
+
+The metrics sent by the `nvidia_gpm` collector use `accelerator` as `type` tag. For the `type-id`, it uses the device handle index by default. With the `use_pci_info_as_type_id` option, the PCI ID is used instead. If both values should be added as tags, activate the `add_pci_info_tag` option. It uses the device handle index as `type-id` and adds the PCI ID as separate `pci_identifier` tag.
+
+Optionally, it is possible to add the UUID, the board part number and the serial to the meta informations. They are not sent to the sinks (if not configured otherwise).
+
+
+Available Metrics:
+* `nv_gpm_graphics_util`
+* `nv_gpm_sm_util`
+* `nv_gpm_sm_occupancy`
+* `nv_gpm_integer_util`
+* `nv_gpm_any_tensor_util`
+* `nv_gpm_dfma_tensor_util`
+* `nv_gpm_hmma_tensor_util`
+* `nv_gpm_imma_tensor_util`
+* `nv_gpm_dram_bw_util`
+* `nv_gpm_fp64_util`
+* `nv_gpm_fp32_util`
+* `nv_gpm_fp16_util`

collectors/raplMetric.go

@@ -242,12 +242,7 @@ func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				timeDiff := energyTimestamp.Sub(p.energyTimestamp)
 				averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
 
-				y, err := lp.NewMessage(
+				y, err := lp.NewMetric("rapl_average_power", p.tags, m.meta, averagePower, energyTimestamp)
-					"rapl_average_power",
-					p.tags,
-					m.meta,
-					map[string]any{"value": averagePower},
-					energyTimestamp)
 				if err == nil {
 					output <- y
 				}

collectors/rocmsmiMetric.go

@@ -158,128 +158,110 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
 
 		if !dev.excludeMetrics["rocm_gfx_util"] {
 			value := metrics.Average_gfx_activity
-			y, err := lp.NewMessage("rocm_gfx_util", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_gfx_util", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_umc_util"] {
 			value := metrics.Average_umc_activity
-			y, err := lp.NewMessage("rocm_umc_util", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_umc_util", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_mm_util"] {
 			value := metrics.Average_mm_activity
-			y, err := lp.NewMessage("rocm_mm_util", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_mm_util", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_avg_power"] {
 			value := metrics.Average_socket_power
-			y, err := lp.NewMessage("rocm_avg_power", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_avg_power", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_mem"] {
 			value := metrics.Temperature_mem
-			y, err := lp.NewMessage("rocm_temp_mem", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_temp_mem", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_hotspot"] {
 			value := metrics.Temperature_hotspot
-			y, err := lp.NewMessage("rocm_temp_hotspot", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_temp_hotspot", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_edge"] {
 			value := metrics.Temperature_edge
-			y, err := lp.NewMessage("rocm_temp_edge", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_temp_edge", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_vrgfx"] {
 			value := metrics.Temperature_vrgfx
-			y, err := lp.NewMessage("rocm_temp_vrgfx", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_temp_vrgfx", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_vrsoc"] {
 			value := metrics.Temperature_vrsoc
-			y, err := lp.NewMessage("rocm_temp_vrsoc", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_temp_vrsoc", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_vrmem"] {
 			value := metrics.Temperature_vrmem
-			y, err := lp.NewMessage("rocm_temp_vrmem", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_temp_vrmem", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_gfx_clock"] {
 			value := metrics.Average_gfxclk_frequency
-			y, err := lp.NewMessage("rocm_gfx_clock", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_gfx_clock", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_soc_clock"] {
 			value := metrics.Average_socclk_frequency
-			y, err := lp.NewMessage("rocm_soc_clock", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_soc_clock", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_u_clock"] {
 			value := metrics.Average_uclk_frequency
-			y, err := lp.NewMessage("rocm_u_clock", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_u_clock", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_v0_clock"] {
 			value := metrics.Average_vclk0_frequency
-			y, err := lp.NewMessage("rocm_v0_clock", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_v0_clock", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_v1_clock"] {
 			value := metrics.Average_vclk1_frequency
-			y, err := lp.NewMessage("rocm_v1_clock", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_v1_clock", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_d0_clock"] {
 			value := metrics.Average_dclk0_frequency
-			y, err := lp.NewMessage("rocm_d0_clock", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_d0_clock", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_d1_clock"] {
 			value := metrics.Average_dclk1_frequency
-			y, err := lp.NewMessage("rocm_d1_clock", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+			if y, err := lp.NewMetric("rocm_d1_clock", dev.tags, dev.meta, value, timestamp); err == nil {
-			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_hbm"] {
 			for i := range rocm_smi.NUM_HBM_INSTANCES {
 				value := metrics.Temperature_hbm[i]
-				y, err := lp.NewMessage("rocm_temp_hbm", dev.tags, dev.meta, map[string]any{"value": value}, timestamp)
+				if y, err := lp.NewMetric("rocm_temp_hbm", dev.tags, dev.meta, value, timestamp); err == nil {
-				if err == nil {
 					y.AddTag("stype", "device")
 					y.AddTag("stype-id", strconv.Itoa(i))
 					output <- y

collectors/tempMetric.go

@@ -201,26 +201,14 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			continue
 		}
 		x /= 1000
-		y, err := lp.NewMessage(
+		y, err := lp.NewMetric(sensor.metricName, sensor.tags, m.meta, x, time.Now())
-			sensor.metricName,
-			sensor.tags,
-			m.meta,
-			map[string]any{"value": x},
-			time.Now(),
-		)
 		if err == nil {
 			output <- y
 		}
 
 		// max temperature
 		if m.config.ReportMaxTemp && sensor.maxTemp != 0 {
-			y, err := lp.NewMessage(
+			y, err := lp.NewMetric(sensor.maxTempName, sensor.tags, m.meta, sensor.maxTemp, time.Now())
-				sensor.maxTempName,
-				sensor.tags,
-				m.meta,
-				map[string]any{"value": sensor.maxTemp},
-				time.Now(),
-			)
 			if err == nil {
 				output <- y
 			}
@@ -228,13 +216,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 
 		// critical temperature
 		if m.config.ReportCriticalTemp && sensor.critTemp != 0 {
-			y, err := lp.NewMessage(
+			y, err := lp.NewMetric(sensor.critTempName, sensor.tags, m.meta, sensor.critTemp, time.Now())
-				sensor.critTempName,
-				sensor.tags,
-				m.meta,
-				map[string]any{"value": sensor.critTemp},
-				time.Now(),
-			)
 			if err == nil {
 				output <- y
 			}

collectors/topprocsMetric.go

@@ -86,15 +86,7 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessag
 	lines := strings.Split(string(stdout), "\n")
 	for i := 1; i < m.config.Num_procs+1; i++ {
 		name := fmt.Sprintf("topproc%d", i)
-		y, err := lp.NewMessage(
+		if y, err := lp.NewMetric(name, m.tags, m.meta, lines[i], time.Now()); err == nil {
-			name,
-			m.tags,
-			m.meta,
-			map[string]any{
-				"value": lines[i],
-			},
-			time.Now())
-		if err == nil {
 			output <- y
 		}
 	}

go.mod

@@ -7,10 +7,10 @@ require (
 	github.com/ClusterCockpit/go-rocm-smi v0.4.0
 	github.com/NVIDIA/go-nvml v0.13.0-1
 	github.com/PaesslerAG/gval v1.2.4
-	github.com/fsnotify/fsnotify v1.10.0
+	github.com/fsnotify/fsnotify v1.10.1
-	github.com/tklauser/go-sysconf v0.3.16
+	github.com/tklauser/go-sysconf v0.4.0
 	golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
-	golang.org/x/sys v0.43.0
+	golang.org/x/sys v0.45.0
 )
 
 require (
@@ -38,7 +38,7 @@ require (
 	github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 // indirect
 	github.com/shopspring/decimal v1.4.0 // indirect
 	github.com/stmcginnis/gofish v0.21.6 // indirect
-	github.com/tklauser/numcpus v0.11.0 // indirect
+	github.com/tklauser/numcpus v0.12.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.4 // indirect
 	golang.org/x/crypto v0.50.0 // indirect
 	golang.org/x/net v0.53.0 // indirect

go.sum

@@ -53,8 +53,8 @@ github.com/expr-lang/expr v1.17.8 h1:W1loDTT+0PQf5YteHSTpju2qfUfNoBt4yw9+wOEU9VM
 github.com/expr-lang/expr v1.17.8/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 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 v1.10.0 h1:Xx/5Ydg9CeBDX/wi4VJqStNtohYjitZhhlHt4h3St1M=
+github.com/fsnotify/fsnotify v1.10.1 h1:b0/UzAf9yR5rhf3RPm9gf3ehBPpf0oZKIjtpKrx59Ho=
-github.com/fsnotify/fsnotify v1.10.0/go.mod h1:TLheqan6HD6GBK6PrDWyDPBaEV8LspOxvPSjC+bVfgo=
+github.com/fsnotify/fsnotify v1.10.1/go.mod h1:TLheqan6HD6GBK6PrDWyDPBaEV8LspOxvPSjC+bVfgo=
 github.com/go-ole/go-ole v1.3.0 h1:Dt6ye7+vXGIKZ7Xtk4s6/xVdGDQynvom7xCFEdWr6uE=
 github.com/go-ole/go-ole v1.3.0/go.mod h1:5LS6F96DhAwUc7C+1HLexzMXY1xGRSryjyPPKW6zv78=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
@@ -163,10 +163,10 @@ github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu
 github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
 github.com/testcontainers/testcontainers-go v0.26.0 h1:uqcYdoOHBy1ca7gKODfBd9uTHVK3a7UL848z09MVZ0c=
 github.com/testcontainers/testcontainers-go v0.26.0/go.mod h1:ICriE9bLX5CLxL9OFQ2N+2N+f+803LNJ1utJb1+Inx0=
-github.com/tklauser/go-sysconf v0.3.16 h1:frioLaCQSsF5Cy1jgRBrzr6t502KIIwQ0MArYICU0nA=
+github.com/tklauser/go-sysconf v0.4.0 h1:7H0uAN+7RkwWRaxhYXDLqa5V3LPrJeV8wmD9dRUgPQU=
-github.com/tklauser/go-sysconf v0.3.16/go.mod h1:/qNL9xxDhc7tx3HSRsLWNnuzbVfh3e7gh/BmM179nYI=
+github.com/tklauser/go-sysconf v0.4.0/go.mod h1:8mTNWyog7H+MpKijp4VmKJAd2bbYQ2zuUwkYRbUArPI=
-github.com/tklauser/numcpus v0.11.0 h1:nSTwhKH5e1dMNsCdVBukSZrURJRoHbSEQjdEbY+9RXw=
+github.com/tklauser/numcpus v0.12.0 h1:NR85qdvHA9pFse3x3weVZ0r0ST8R6l5RHbZrlRaqob4=
-github.com/tklauser/numcpus v0.11.0/go.mod h1:z+LwcLq54uWZTX0u/bGobaV34u6V7KNlTZejzM6/3MQ=
+github.com/tklauser/numcpus v0.12.0/go.mod h1:ABHeXzJnr/qqwguhClkZKT1/8VABcYrsyUiUGobwWJg=
 github.com/yusufpapurcu/wmi v1.2.3 h1:E1ctvB7uKFMOJw3fdOW32DwGE9I7t++CRUEMKvFoFiw=
 github.com/yusufpapurcu/wmi v1.2.3/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
@@ -184,8 +184,8 @@ golang.org/x/mod v0.13.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA=
 golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs=
 golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI=
+golang.org/x/sys v0.45.0 h1:dO4czNzziLiiXplLQgBCEpCvXQ3dnkn0SdaZSYdQ+FY=
-golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
+golang.org/x/sys v0.45.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
 golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
 golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
 golang.org/x/tools v0.14.0 h1:jvNa2pY0M4r62jkRQ6RwEZZyPcymeL9XZMLBbV7U2nc=