Compare commits

..

6 Commits

Author SHA1 Message Date
Holger Obermaier
656ea73d12 Fix: num_cpus could not be excluded 2026-05-07 14:47:23 +02:00
Holger Obermaier
330f923596 Fixed exclude_metrics and check for used metrics 2026-05-07 12:25:07 +02:00
Holger Obermaier
8e58072ff6 Use NewMetric to create a new metric 2026-05-06 13:22:02 +02:00
Holger Obermaier
0f6fee9db4 Do not save current state of infiniband counters, only last state is required 2026-05-06 10:42:06 +02:00
Holger Obermaier
7585ee7289 Add bandwidth metrics for ib_total and ib_total_pkts 2026-05-05 14:13:38 +02:00
Michael Panzlaff
30b2eb69dd Merge pull request #213 from ClusterCockpit/fix/libdrm-ubuntu-deb
CI: Install libdrm-dev for building (required on Ubuntu)
2026-05-04 14:30:44 +02:00
18 changed files with 108 additions and 189 deletions

View File

@@ -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 err == nil {
if y, err := lp.NewMetric(key, m.tags, m.meta, value, time.Now()); err == nil {
output <- y
}
}

View File

@@ -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 err == nil {
if y, err := lp.NewMetric(key, m.tags, m.meta, value, time.Now()); err == nil {
output <- y
}
}

View File

@@ -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
}
}

View File

@@ -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
}
}

View File

@@ -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
@@ -191,15 +195,11 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage
}
}
num_cpus_metric, err := lp.NewMessage("num_cpus",
m.nodetags,
m.meta,
map[string]any{"value": num_cpus},
now,
)
if err == nil {
if !m.config.excludeNumCPUs {
if num_cpus_metric, err := lp.NewMetric("num_cpus", m.nodetags, m.meta, num_cpus, now); err == nil {
output <- num_cpus_metric
}
}
m.lastTimestamp = now
}

View File

@@ -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(
"disk_total",
tags,
m.meta,
map[string]any{
"value": total,
},
time.Now())
if err == nil {
if y, err := lp.NewMetric("disk_total", tags, m.meta, total, time.Now()); 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(
"disk_free",
tags,
m.meta,
map[string]any{
"value": free,
},
time.Now())
if err == nil {
if y, err := lp.NewMetric("disk_free", tags, m.meta, free, time.Now()); err == nil {
y.AddMeta("unit", "GBytes")
output <- y
}
@@ -164,16 +148,7 @@ mountLoop:
}
}
if m.allowedMetrics["part_max_used"] {
y, err := lp.NewMessage(
"part_max_used",
map[string]string{
"type": "node",
},
m.meta,
map[string]any{
"value": int(part_max_used),
},
time.Now())
y, err := lp.NewMetric("part_max_used", map[string]string{"type": "node"}, m.meta, int(part_max_used), time.Now())
if err == nil {
y.AddMeta("unit", "percent")
output <- y

View File

@@ -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(
counterDef.name,
info.tagSet,
m.meta,
map[string]any{
"value": counterDef.currentState,
},
now); err == nil {
if y, err := lp.NewMetric(counterDef.name, info.tagSet, m.meta, v, 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
if y, err := lp.NewMessage(
counterDef.name+"_bw",
info.tagSet,
m.meta,
map[string]any{
"value": rate,
},
now); err == nil {
rate := float64((v - counterDef.lastState)) / timeDiff
if y, err := lp.NewMetric(counterDef.name+"_bw", info.tagSet, m.meta, 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(
"ib_total",
info.tagSet,
m.meta,
map[string]any{
"value": ib_total,
},
now); err == nil {
if y, err := lp.NewMetric("ib_total", info.tagSet, m.meta, ib_total, now); err == nil {
y.AddMeta("unit", "bytes")
output <- y
}
if y, err := lp.NewMessage(
"ib_total_pkts",
info.tagSet,
m.meta,
map[string]any{
"value": ib_total_pkts,
},
now); err == nil {
if y, err := lp.NewMetric("ib_total_pkts", info.tagSet, m.meta, 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
}
}
}
}
}

View File

@@ -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

View File

@@ -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

View File

@@ -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
}

View File

@@ -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)

View File

@@ -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
}
}

View File

@@ -146,17 +146,16 @@ 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
}
y, err := lp.NewMessage(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, valueMap, timestamp)
value := data.current - data.last
y, err := lp.NewMetric(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, value, timestamp)
if err == nil {
y.AddMeta("version", m.version)
output <- y
}
}
}
}
func (m *nfsCollector) Close() {
m.init = false

View File

@@ -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(
"nfsio_"+name,
m.tags,
m.meta,
map[string]any{
"value": newVal,
},
now)
msg, err := lp.NewMetric("nfsio_"+name, m.tags, m.meta, 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")

View File

@@ -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(
"rapl_average_power",
p.tags,
m.meta,
map[string]any{"value": averagePower},
energyTimestamp)
y, err := lp.NewMetric("rapl_average_power", p.tags, m.meta, averagePower, energyTimestamp)
if err == nil {
output <- y
}

View File

@@ -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 err == nil {
if y, err := lp.NewMetric("rocm_gfx_util", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_umc_util", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_mm_util", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_avg_power", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_temp_mem", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_temp_hotspot", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_temp_edge", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_temp_vrgfx", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_temp_vrsoc", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_temp_vrmem", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_gfx_clock", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_soc_clock", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_u_clock", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_v0_clock", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_v1_clock", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_d0_clock", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_d1_clock", dev.tags, dev.meta, value, timestamp); 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 err == nil {
if y, err := lp.NewMetric("rocm_temp_hbm", dev.tags, dev.meta, value, timestamp); err == nil {
y.AddTag("stype", "device")
y.AddTag("stype-id", strconv.Itoa(i))
output <- y

View File

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

View File

@@ -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(
name,
m.tags,
m.meta,
map[string]any{
"value": lines[i],
},
time.Now())
if err == nil {
if y, err := lp.NewMetric(name, m.tags, m.meta, lines[i], time.Now()); err == nil {
output <- y
}
}