mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-26 15:29:04 +01:00
200af84c54
* Use channels, add a metric router, split up configuration and use extended version of Influx line protocol internally * Use central timer for collectors and router. Add expressions to router * Add expression to router config * Update entry points * Start with README * Update README for CCMetric * Formatting * Update README.md * Add README for MultiChanTicker * Add README for MultiChanTicker * Update README.md * Add README to metric router * Update main README * Remove SinkEntity type * Update README for sinks * Update go files * Update README for receivers * Update collectors README * Update collectors README * Use seperate page per collector * Fix for tempstat page * Add docs for customcmd collector * Add docs for ipmistat collector * Add docs for topprocs collector * Update customCmdMetric.md * Use seconds when calculating LIKWID metrics * Add IB metrics ib_recv_pkts and ib_xmit_pkts * Drop domain part of host name * Updated to latest stable version of likwid * Define source code dependencies in Makefile * Add GPFS / IBM Spectrum Scale collector * Add vet and staticcheck make targets * Add vet and staticcheck make targets * Avoid go vet warning: struct field tag `json:"..., omitempty"` not compatible with reflect.StructTag.Get: suspicious space in struct tag value struct field tag `json:"...", omitempty` not compatible with reflect.StructTag.Get: key:"value" pairs not separated by spaces * Add sample collector to README.md * Add CPU frequency collector * Avoid staticcheck warning: redundant return statement * Avoid staticcheck warning: unnecessary assignment to the blank identifier * Simplified code * Add CPUFreqCollectorCpuinfo a metric collector to measure the current frequency of the CPUs as obtained from /proc/cpuinfo Only measure on the first hyperthread * Add collector for NFS clients * Move publication of metrics into Flush() for NatsSink * Update GitHub actions * Refactoring * Avoid vet warning: Println arg list ends with redundant newline * Avoid vet warning struct field commands has json tag but is not exported * Avoid vet warning: return copies lock value. * Corrected typo * Refactoring * Add go sources in internal/... * Bad separator in Makefile * Fix Infiniband collector Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
198 lines
4.9 KiB
Go
198 lines
4.9 KiB
Go
package collectors
|
|
|
|
import (
|
|
"bufio"
|
|
"encoding/json"
|
|
|
|
"fmt"
|
|
"log"
|
|
"os"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
|
|
|
|
)
|
|
|
|
//
|
|
// CPUFreqCollector
|
|
// a metric collector to measure the current frequency of the CPUs
|
|
// as obtained from /proc/cpuinfo
|
|
// Only measure on the first hyperthread
|
|
//
|
|
type CPUFreqCpuInfoCollectorTopology struct {
|
|
processor string // logical processor number (continuous, starting at 0)
|
|
coreID string // socket local core ID
|
|
coreID_int int
|
|
physicalPackageID string // socket / package ID
|
|
physicalPackageID_int int
|
|
numPhysicalPackages string // number of sockets / packages
|
|
numPhysicalPackages_int int
|
|
isHT bool
|
|
numNonHT string // number of non hyperthreading processors
|
|
numNonHT_int int
|
|
tagSet map[string]string
|
|
}
|
|
|
|
type CPUFreqCpuInfoCollector struct {
|
|
metricCollector
|
|
topology []CPUFreqCpuInfoCollectorTopology
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
|
|
m.name = "CPUFreqCpuInfoCollector"
|
|
m.meta = map[string]string{
|
|
"source": m.name,
|
|
"group": "cpufreq",
|
|
}
|
|
|
|
const cpuInfoFile = "/proc/cpuinfo"
|
|
file, err := os.Open(cpuInfoFile)
|
|
if err != nil {
|
|
return fmt.Errorf("Failed to open '%s': %v", cpuInfoFile, err)
|
|
}
|
|
defer file.Close()
|
|
|
|
// Collect topology information from file cpuinfo
|
|
foundFreq := false
|
|
processor := ""
|
|
numNonHT_int := 0
|
|
coreID := ""
|
|
physicalPackageID := ""
|
|
maxPhysicalPackageID := 0
|
|
m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
|
|
coreSeenBefore := make(map[string]bool)
|
|
scanner := bufio.NewScanner(file)
|
|
for scanner.Scan() {
|
|
lineSplit := strings.Split(scanner.Text(), ":")
|
|
if len(lineSplit) == 2 {
|
|
key := strings.TrimSpace(lineSplit[0])
|
|
value := strings.TrimSpace(lineSplit[1])
|
|
switch key {
|
|
case "cpu MHz":
|
|
// frequency
|
|
foundFreq = true
|
|
case "processor":
|
|
processor = value
|
|
case "core id":
|
|
coreID = value
|
|
case "physical id":
|
|
physicalPackageID = value
|
|
}
|
|
}
|
|
|
|
// were all topology information collected?
|
|
if foundFreq &&
|
|
len(processor) > 0 &&
|
|
len(coreID) > 0 &&
|
|
len(physicalPackageID) > 0 {
|
|
|
|
coreID_int, err := strconv.Atoi(coreID)
|
|
if err != nil {
|
|
return fmt.Errorf("Unable to convert coreID to int: %v", err)
|
|
}
|
|
physicalPackageID_int, err := strconv.Atoi(physicalPackageID)
|
|
if err != nil {
|
|
return fmt.Errorf("Unable to convert physicalPackageID to int: %v", err)
|
|
}
|
|
|
|
// increase maximun socket / package ID, when required
|
|
if physicalPackageID_int > maxPhysicalPackageID {
|
|
maxPhysicalPackageID = physicalPackageID_int
|
|
}
|
|
|
|
globalID := physicalPackageID + ":" + coreID
|
|
isHT := coreSeenBefore[globalID]
|
|
coreSeenBefore[globalID] = true
|
|
if !isHT {
|
|
// increase number on non hyper thread cores
|
|
numNonHT_int++
|
|
}
|
|
|
|
// store collected topology information
|
|
m.topology = append(
|
|
m.topology,
|
|
CPUFreqCpuInfoCollectorTopology{
|
|
processor: processor,
|
|
coreID: coreID,
|
|
coreID_int: coreID_int,
|
|
physicalPackageID: physicalPackageID,
|
|
physicalPackageID_int: physicalPackageID_int,
|
|
isHT: isHT,
|
|
})
|
|
|
|
// reset topology information
|
|
foundFreq = false
|
|
processor = ""
|
|
coreID = ""
|
|
physicalPackageID = ""
|
|
}
|
|
}
|
|
|
|
numPhysicalPackageID_int := maxPhysicalPackageID + 1
|
|
numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
|
|
numNonHT := fmt.Sprint(numNonHT_int)
|
|
for i := range m.topology {
|
|
t := &m.topology[i]
|
|
t.numPhysicalPackages = numPhysicalPackageID
|
|
t.numPhysicalPackages_int = numPhysicalPackageID_int
|
|
t.numNonHT = numNonHT
|
|
t.numNonHT_int = numNonHT_int
|
|
t.tagSet = map[string]string{
|
|
"type": "cpu",
|
|
"type-id": t.processor,
|
|
"num_core": t.numNonHT,
|
|
"package_id": t.physicalPackageID,
|
|
"num_package": t.numPhysicalPackages,
|
|
}
|
|
}
|
|
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMetric) {
|
|
if !m.init {
|
|
return
|
|
}
|
|
const cpuInfoFile = "/proc/cpuinfo"
|
|
file, err := os.Open(cpuInfoFile)
|
|
if err != nil {
|
|
log.Printf("Failed to open '%s': %v", cpuInfoFile, err)
|
|
return
|
|
}
|
|
defer file.Close()
|
|
|
|
processorCounter := 0
|
|
now := time.Now()
|
|
scanner := bufio.NewScanner(file)
|
|
for scanner.Scan() {
|
|
lineSplit := strings.Split(scanner.Text(), ":")
|
|
if len(lineSplit) == 2 {
|
|
key := strings.TrimSpace(lineSplit[0])
|
|
|
|
// frequency
|
|
if key == "cpu MHz" {
|
|
t := &m.topology[processorCounter]
|
|
if !t.isHT {
|
|
value, err := strconv.ParseFloat(strings.TrimSpace(lineSplit[1]), 64)
|
|
if err != nil {
|
|
log.Printf("Failed to convert cpu MHz to float: %v", err)
|
|
return
|
|
}
|
|
y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
processorCounter++
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Close() {
|
|
m.init = false
|
|
}
|