ClusterCockpit/cc-metric-collector
1
0
Fork 0
mirror of https://github.com/ClusterCockpit/cc-metric-collector.git synced 2026-02-17 16:31:46 +01:00
Code Issues Packages Projects Releases Wiki Activity

Format with gofumpt

Browse Source
This commit is contained in:
Holger Obermaier
2026-02-16 14:16:03 +01:00
parent 9bb21b807a
commit 539581f952
28 changed files with 294 additions and 310 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
collectors/beegfsmetaMetric.go
View File

@@ -50,7 +50,7 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
return nil
}
// Metrics
var nodeMdstat_array = [39]string{
nodeMdstat_array := [39]string{
"sum", "ack", "close", "entInf",
"fndOwn", "mkdir", "create", "rddir",
"refrEn", "mdsInf", "rmdir", "rmLnk",
@@ -60,7 +60,8 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
"lookLI", "statLI", "revalLI", "openLI",
"createLI", "hardlnk", "flckAp", "flckEn",
"flckRg", "dirparent", "listXA", "getXA",
"rmXA", "setXA", "mirror"}
"rmXA", "setXA", "mirror",
}
m.name = "BeegfsMetaCollector"
if err := m.setup(); err != nil {
@@ -154,7 +155,6 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
// --nodetype=meta: The node type to query (meta, storage).
// --interval:
// --mount=/mnt/beeond/: Which mount point
//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
mountoption := "--mount=" + mountpoint
cmd := exec.Command(m.config.Beegfs, "--clientstats",
"--nodetype=meta", mountoption, "--allstats")
@@ -180,14 +180,12 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
scanner := bufio.NewScanner(cmdStdout)
sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
singleSpacePattern := regexp.MustCompile(`\s+`)
removePattern := regexp.MustCompile(`[\[|\]]`)
for scanner.Scan() {
readLine := scanner.Text()
//fmt.Println(readLine)
// Jump few lines, we only want the I/O stats from nodes
if !sumLine.MatchString(readLine) {
continue
@@ -196,7 +194,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
match := statsLine.FindStringSubmatch(readLine)
// nodeName = "Sum:" or would be nodes
// nodeName := match[1]
//Remove multiple whitespaces
// Remove multiple whitespaces
dummy := removePattern.ReplaceAllString(match[2], " ")
metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
split := strings.Split(metaStats, " ")
@@ -222,7 +220,6 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
continue
}
//mdStat["other"] = fmt.Sprintf("%f", f1+f2)
m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)
}
}

19
collectors/beegfsstorageMetric.go
View File

@@ -48,12 +48,13 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
return nil
}
// Metrics
var storageStat_array = [18]string{
storageStat_array := [18]string{
"sum", "ack", "sChDrct", "getFSize",
"sAttr", "statfs", "trunc", "close",
"fsync", "ops-rd", "MiB-rd/s", "ops-wr",
"MiB-wr/s", "gendbg", "hrtbeat", "remNode",
"storInf", "unlnk"}
"storInf", "unlnk",
}
m.name = "BeegfsStorageCollector"
if err := m.setup(); err != nil {
@@ -72,7 +73,7 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
}
}
//create map with possible variables
// Create map with possible variables
m.matches = make(map[string]string)
for _, value := range storageStat_array {
if slices.Contains(m.config.ExcludeMetrics, value) {
@@ -117,11 +118,10 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
if !m.init {
return
}
//get mounpoint
buffer, _ := os.ReadFile(string("/proc/mounts"))
mounts := strings.Split(string(buffer), "\n")
// Get mounpoint
buffer, _ := os.ReadFile("/proc/mounts")
var mountpoints []string
for _, line := range mounts {
for line := range strings.Lines(string(buffer)) {
if len(line) == 0 {
continue
}
@@ -146,7 +146,6 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
// --nodetype=meta: The node type to query (meta, storage).
// --interval:
// --mount=/mnt/beeond/: Which mount point
//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
mountoption := "--mount=" + mountpoint
cmd := exec.Command(m.config.Beegfs, "--clientstats",
"--nodetype=storage", mountoption, "--allstats")
@@ -172,7 +171,6 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
scanner := bufio.NewScanner(cmdStdout)
sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
singleSpacePattern := regexp.MustCompile(`\s+`)
removePattern := regexp.MustCompile(`[\[|\]]`)
@@ -187,7 +185,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
match := statsLine.FindStringSubmatch(readLine)
// nodeName = "Sum:" or would be nodes
// nodeName := match[1]
//Remove multiple whitespaces
// Remove multiple whitespaces
dummy := removePattern.ReplaceAllString(match[2], " ")
metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
split := strings.Split(metaStats, " ")
@@ -198,7 +196,6 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
for i := 0; i <= len(split)-1; i += 2 {
if _, ok := m.matches[split[i+1]]; ok {
m.matches["beegfs_cstorage_"+split[i+1]] = split[i]
//m.matches[split[i+1]] = split[i]
} else {
f1, err := strconv.ParseFloat(m.matches["other"], 32)
if err != nil {

1
collectors/collectorManager.go
View File

@@ -20,7 +20,6 @@ import (
// Map of all available metric collectors
var AvailableCollectors = map[string]MetricCollector{
"likwid": new(LikwidCollector),
"loadavg": new(LoadavgCollector),
"memstat": new(MemstatCollector),

1
collectors/cpufreqCpuinfoMetric.go
View File

@@ -10,7 +10,6 @@ package collectors
import (
"bufio"
"encoding/json"
"fmt"
"os"
"strconv"

3
collectors/cpustatMetric.go
View File

@@ -111,7 +111,8 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
cpu, _ := strconv.Atoi(cpustr)
m.cputags[linefields[0]] = map[string]string{
"type": "hwthread",
"type-id": strconv.Itoa(cpu)}
"type-id": strconv.Itoa(cpu),
}
m.olddata[linefields[0]] = make(map[string]int64)
for k, v := range m.matches {
m.olddata[linefields[0]][k], _ = strconv.ParseInt(linefields[v], 0, 64)

16
collectors/diskstatMetric.go
View File

@@ -123,28 +123,30 @@ mountLoop:
continue
}
tags := map[string]string{"type": "node", "device": linefields[0]}
total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
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},
"value": total,
},
time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
output <- y
}
}
free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
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},
"value": free,
},
time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
@@ -162,10 +164,12 @@ mountLoop:
y, err := lp.NewMessage(
"part_max_used",
map[string]string{
"type": "node"},
"type": "node",
},
m.meta,
map[string]any{
"value": int(part_max_used)},
"value": int(part_max_used),
},
time.Now())
if err == nil {
y.AddMeta("unit", "percent")

81
collectors/infinibandMetric.go
View File

@@ -8,19 +8,18 @@
package collectors
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"slices"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
"golang.org/x/sys/unix"
"encoding/json"
"path/filepath"
"strconv"
"strings"
"time"
)
const IB_BASEPATH = "/sys/class/infiniband/"
@@ -59,7 +58,6 @@ type InfinibandCollector struct {
// Init initializes the Infiniband collector by walking through files below IB_BASEPATH
func (m *InfinibandCollector) Init(config json.RawMessage) error {
// Check if already initialized
if m.init {
return nil
@@ -187,7 +185,6 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
// Read reads Infiniband counter files below IB_BASEPATH
func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// Check if already initialized
if !m.init {
return
@@ -233,15 +230,14 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
// 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.NewMessage(
counterDef.name,
info.tagSet,
m.meta,
map[string]any{
"value": counterDef.currentState,
},
now); err == nil {
y.AddMeta("unit", counterDef.unit)
output <- y
}
@@ -251,15 +247,14 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
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 {
if y, err := lp.NewMessage(
counterDef.name+"_bw",
info.tagSet,
m.meta,
map[string]any{
"value": rate,
},
now); err == nil {
y.AddMeta("unit", counterDef.unit+"/sec")
output <- y
@@ -281,28 +276,26 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
// 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.NewMessage(
"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(
"ib_total_pkts",
info.tagSet,
m.meta,
map[string]any{
"value": ib_total_pkts,
},
now); err == nil {
if y, err := lp.NewMessage(
"ib_total_pkts",
info.tagSet,
m.meta,
map[string]any{
"value": ib_total_pkts,
},
now); err == nil {
y.AddMeta("unit", "packets")
output <- y
}

4
collectors/ipmiMetric.go
View File

@@ -93,7 +93,6 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
}
func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
// Setup ipmitool command
command := exec.Command(cmd, "sensor")
stdout, _ := command.StdoutPipe()
@@ -152,7 +151,6 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
}
func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
// Setup ipmisensors command
command := exec.Command(cmd, "--comma-separated-output", "--sdr-cache-recreate")
stdout, _ := command.StdoutPipe()
@@ -197,11 +195,9 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
cclog.ComponentError(m.name, fmt.Sprintf("readIpmiSensors(): command stderr: \"%s\"\n", strings.TrimSpace(string(errMsg))))
return
}
}
func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// Check if already initialized
if !m.init {
return

119
collectors/likwidMetric.go
View File

@@ -609,18 +609,17 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
evset.metrics[tid][metric.Name] = value
// Now we have the result, send it with the proper tags
if !math.IsNaN(value) && metric.Publish {
y, err :=
lp.NewMessage(
metric.Name,
map[string]string{
"type": metric.Type,
},
m.meta,
map[string]any{
"value": value,
},
now,
)
y, err := lp.NewMessage(
metric.Name,
map[string]string{
"type": metric.Type,
},
m.meta,
map[string]any{
"value": value,
},
now,
)
if err == nil {
if metric.Type != "node" {
y.AddTag("type-id", strconv.Itoa(domain))
@@ -648,19 +647,18 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
}
for coreID, value := range totalCoreValues {
y, err :=
lp.NewMessage(
metric.Name,
map[string]string{
"type": "core",
"type-id": strconv.Itoa(coreID),
},
m.meta,
map[string]any{
"value": value,
},
now,
)
y, err := lp.NewMessage(
metric.Name,
map[string]string{
"type": "core",
"type-id": strconv.Itoa(coreID),
},
m.meta,
map[string]any{
"value": value,
},
now,
)
if err != nil {
continue
}
@@ -685,19 +683,18 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
}
for socketID, value := range totalSocketValues {
y, err :=
lp.NewMessage(
metric.Name,
map[string]string{
"type": "socket",
"type-id": strconv.Itoa(socketID),
},
m.meta,
map[string]any{
"value": value,
},
now,
)
y, err := lp.NewMessage(
metric.Name,
map[string]string{
"type": "socket",
"type-id": strconv.Itoa(socketID),
},
m.meta,
map[string]any{
"value": value,
},
now,
)
if err != nil {
continue
}
@@ -720,18 +717,17 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
}
}
y, err :=
lp.NewMessage(
metric.Name,
map[string]string{
"type": "node",
},
m.meta,
map[string]any{
"value": totalNodeValue,
},
now,
)
y, err := lp.NewMessage(
metric.Name,
map[string]string{
"type": "node",
},
m.meta,
map[string]any{
"value": totalNodeValue,
},
now,
)
if err != nil {
continue
}
@@ -778,18 +774,17 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
// Now we have the result, send it with the proper tags
if !math.IsNaN(value) {
if metric.Publish {
y, err :=
lp.NewMessage(
metric.Name,
map[string]string{
"type": metric.Type,
},
m.meta,
map[string]any{
"value": value,
},
now,
)
y, err := lp.NewMessage(
metric.Name,
map[string]string{
"type": metric.Type,
},
m.meta,
map[string]any{
"value": value,
},
now,
)
if err == nil {
if metric.Type != "node" {
y.AddTag("type-id", strconv.Itoa(domain))

9
collectors/loadavgMetric.go
View File

@@ -55,16 +55,19 @@ func (m *LoadavgCollector) Init(config json.RawMessage) error {
}
m.meta = map[string]string{
"source": m.name,
"group": "LOAD"}
"group": "LOAD",
}
m.tags = map[string]string{"type": "node"}
m.load_matches = []string{
"load_one",
"load_five",
"load_fifteen"}
"load_fifteen",
}
m.load_skips = make([]bool, len(m.load_matches))
m.proc_matches = []string{
"proc_run",
"proc_total"}
"proc_total",
}
m.proc_skips = make([]bool, len(m.proc_matches))
for i, name := range m.load_matches {

8
collectors/lustreMetric.go
View File

@@ -22,9 +22,11 @@ import (
lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
)
const LUSTRE_SYSFS = `/sys/fs/lustre`
const LCTL_CMD = `lctl`
const LCTL_OPTION = `get_param`
const (
LUSTRE_SYSFS = `/sys/fs/lustre`
LCTL_CMD = `lctl`
LCTL_OPTION = `get_param`
)
type LustreCollectorConfig struct {
LCtlCommand string `json:"lctl_command,omitempty"`

6
collectors/memstatMetric.go
View File

@@ -24,8 +24,10 @@ import (
lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
)
const MEMSTATFILE = "/proc/meminfo"
const NUMA_MEMSTAT_BASE = "/sys/devices/system/node"
const (
MEMSTATFILE = "/proc/meminfo"
NUMA_MEMSTAT_BASE = "/sys/devices/system/node"
)
type MemstatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics"`

9
collectors/nfsiostatMetric.go
View File

@@ -43,8 +43,10 @@ type NfsIOStatCollector struct {
lastTimestamp time.Time
}
var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
var bytesRegex = regexp.MustCompile(`\s+bytes:\s+(?P<nread>[^ ]+) (?P<nwrite>[^ ]+) (?P<dread>[^ ]+) (?P<dwrite>[^ ]+) (?P<nfsread>[^ ]+) (?P<nfswrite>[^ ]+) (?P<pageread>[^ ]+) (?P<pagewrite>[^ ]+)`)
var (
deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
bytesRegex = regexp.MustCompile(`\s+bytes:\s+(?P<nread>[^ ]+) (?P<nwrite>[^ ]+) (?P<dread>[^ ]+) (?P<dwrite>[^ ]+) (?P<nfsread>[^ ]+) (?P<nfswrite>[^ ]+) (?P<pageread>[^ ]+) (?P<pagewrite>[^ ]+)`)
)
func resolve_regex_fields(s string, regex *regexp.Regexp) map[string]string {
fields := make(map[string]string)
@@ -149,7 +151,8 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
m.tags,
m.meta,
map[string]any{
"value": newVal},
"value": newVal,
},
now)
if err == nil {
msg.AddTag("stype", "filesystem")

2
collectors/nvidiaMetric.go
View File

@@ -1226,7 +1226,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
}
// Actual read loop over all attached Nvidia GPUs
for i := 0; i < m.num_gpus; i++ {
for i := range m.num_gpus {
readAll(&m.gpus[i], output)

83
collectors/raplMetric.go
View File

@@ -49,7 +49,6 @@ type RAPLCollector struct {
// Init initializes the running average power limit (RAPL) collector
func (m *RAPLCollector) Init(config json.RawMessage) error {
// Check if already initialized
if m.init {
return nil
@@ -91,19 +90,20 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// readZoneInfo reads RAPL monitoring attributes for a zone given by zonePath
// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
readZoneInfo := func(zonePath string) (z struct {
name string // zones name e.g. psys, dram, core, uncore, package-0
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
ok bool // Are all information available?
}) {
readZoneInfo := func(zonePath string) (
z struct {
name string // zones name e.g. psys, dram, core, uncore, package-0
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
ok bool // Are all information available?
},
) {
// zones name e.g. psys, dram, core, uncore, package-0
foundName := false
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "name")); err == nil {
if v, err := os.ReadFile(
filepath.Join(zonePath, "name")); err == nil {
foundName = true
z.name = strings.TrimSpace(string(v))
}
@@ -124,9 +124,8 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// Range of the above energy counter in micro-joules
foundMaxEnergyRange := false
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
if v, err := os.ReadFile(
filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
foundMaxEnergyRange = true
z.maxEnergyRange = i
@@ -158,19 +157,18 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
!isNameExcluded[z.name] {
// Add RAPL monitoring attributes for a zone
m.RAPLZoneInfo =
append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID,
"zone_name": z.name,
},
energyFilepath: z.energyFilepath,
energy: z.energy,
energyTimestamp: z.energyTimestamp,
maxEnergyRange: z.maxEnergyRange,
})
m.RAPLZoneInfo = append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID,
"zone_name": z.name,
},
energyFilepath: z.energyFilepath,
energy: z.energy,
energyTimestamp: z.energyTimestamp,
maxEnergyRange: z.maxEnergyRange,
})
}
// find all sub zones for the given zone
@@ -187,27 +185,25 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
sz.ok &&
!isIDExcluded[zoneID+":"+subZoneID] &&
!isNameExcluded[sz.name] {
m.RAPLZoneInfo =
append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID + ":" + subZoneID,
"zone_name": z.name,
"sub_zone_name": sz.name,
},
energyFilepath: sz.energyFilepath,
energy: sz.energy,
energyTimestamp: sz.energyTimestamp,
maxEnergyRange: sz.maxEnergyRange,
})
m.RAPLZoneInfo = append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID + ":" + subZoneID,
"zone_name": z.name,
"sub_zone_name": sz.name,
},
energyFilepath: sz.energyFilepath,
energy: sz.energy,
energyTimestamp: sz.energyTimestamp,
maxEnergyRange: sz.maxEnergyRange,
})
}
}
}
if m.RAPLZoneInfo == nil {
return fmt.Errorf("no running average power limit (RAPL) device found in %s", controlTypePath)
}
// Initialized
@@ -224,7 +220,6 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// Read reads running average power limit (RAPL) monitoring attributes for all initialized zones
// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMessage) {
for i := range m.RAPLZoneInfo {
p := &m.RAPLZoneInfo[i]

10
collectors/rocmsmiMetric.go
View File

@@ -58,15 +58,6 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
if err := m.setup(); err != nil {
return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err)
}
// Define meta information sent with each metric
// (Can also be dynamic or this is the basic set with extension through AddMeta())
//m.meta = map[string]string{"source": m.name, "group": "AMD"}
// Define tags sent with each metric
// The 'type' tag is always needed, it defines the granulatity of the metric
// node -> whole system
// socket -> CPU socket (requires socket ID as 'type-id' tag)
// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
//m.tags = map[string]string{"type": "node"}
// Read in the JSON configuration
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
@@ -305,7 +296,6 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
}
}
}
}
// Close metric collector: close network connection, close files, close libraries, ...

1
collectors/sampleMetric.go
View File

@@ -101,7 +101,6 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMessage)
// Send it to output channel
output <- y
}
}
// Close metric collector: close network connection, close files, close libraries, ...

3
collectors/schedstatMetric.go
View File

@@ -138,7 +138,7 @@ func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMessa
return
}
//timestamps
// timestamps
now := time.Now()
tsdelta := now.Sub(m.lastTimestamp)
@@ -166,7 +166,6 @@ func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMessa
}
m.lastTimestamp = now
}
// Close metric collector: close network connection, close files, close libraries, ...

30
collectors/slurmCgroupMetric.go
View File

@@ -110,9 +110,11 @@ func (m *SlurmCgroupCollector) Init(config json.RawMessage) error {
m.parallel = true
m.meta = map[string]string{
"source": m.name,
"group": "SLURM"}
"group": "SLURM",
}
m.tags = map[string]string{
"type": "hwthread"}
"type": "hwthread",
}
m.cpuUsed = make(map[int]bool)
m.cgroupBase = defaultCgroupBase
@@ -265,7 +267,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": memPerCore},
"value": memPerCore,
},
timestamp); err == nil {
y.AddMeta("unit", "Bytes")
output <- y
@@ -279,7 +282,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": maxMemPerCore},
"value": maxMemPerCore,
},
timestamp); err == nil {
y.AddMeta("unit", "Bytes")
output <- y
@@ -293,7 +297,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": limitPerCore},
"value": limitPerCore,
},
timestamp); err == nil {
y.AddMeta("unit", "Bytes")
output <- y
@@ -307,7 +312,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": cpuUserPerCore},
"value": cpuUserPerCore,
},
timestamp); err == nil {
y.AddMeta("unit", "%")
output <- y
@@ -321,7 +327,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": cpuSysPerCore},
"value": cpuSysPerCore,
},
timestamp); err == nil {
y.AddMeta("unit", "%")
output <- y
@@ -346,7 +353,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": 0},
"value": 0,
},
timestamp); err == nil {
y.AddMeta("unit", "Bytes")
output <- y
@@ -359,7 +367,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": 0},
"value": 0,
},
timestamp); err == nil {
y.AddMeta("unit", "Bytes")
output <- y
@@ -372,7 +381,8 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
coreTags,
m.meta,
map[string]any{
"value": 0},
"value": 0,
},
timestamp); err == nil {
y.AddMeta("unit", "Bytes")
output <- y

2
collectors/tempMetric.go
View File

@@ -182,7 +182,6 @@ func (m *TempCollector) Init(config json.RawMessage) error {
}
func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
for _, sensor := range m.sensors {
// Read sensor file
buffer, err := os.ReadFile(sensor.file)
@@ -239,7 +238,6 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
}
}
}
}
func (m *TempCollector) Close() {

9
collectors/topprocsMetric.go
View File

@@ -18,8 +18,10 @@ import (
lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
)
const MAX_NUM_PROCS = 10
const DEFAULT_NUM_PROCS = 2
const (
MAX_NUM_PROCS = 10
DEFAULT_NUM_PROCS = 2
)
type TopProcsCollectorConfig struct {
Num_procs int `json:"num_procs"`
@@ -87,7 +89,8 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessag
m.tags,
m.meta,
map[string]any{
"value": lines[i]},
"value": lines[i],
},
time.Now())
if err == nil {
output <- y