mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-25 23:19:06 +01:00
7840de7b82
* Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Update README.md Use right JSON type in configuration * Update sink's README * Test whether ipmitool or ipmi-sensors can be executed without errors * Little fixes to the prometheus sink (#115) * Add uint64 to float64 cast option * Add prometheus sink to the list of available sinks * Add aggregated counters by gpu for nvlink errors --------- Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de> * Ccmessage migration (#119) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Switch to CCMessage for all files. --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Switch to ccmessage also for latest additions in nvidiaMetric * New Message processor (#118) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * New message processor to check whether a message should be dropped or manipulate it in flight * Create a copy of message before manipulation --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Update collector's Makefile and go.mod/sum files * Use message processor in router, all sinks and all receivers * Add support for credential file (NKEY) to NATS sink and receiver * Fix JSON keys in message processor configuration * Update docs for message processor, router and the default router config file * Add link to expr syntax and fix regex matching docs * Update sample collectors * Minor style change in collector manager * Some helpers for ccTopology * LIKWID collector: write log owner change only once * Fix for metrics without units and reduce debugging messages for messageProcessor * Use shorted hostname for hostname added by router * Define default port for NATS * CPUstat collector: only add unit for applicable metrics * Add precision option to all sinks using Influx's encoder * Add message processor to all sink documentation * Add units to documentation of cpustat collector --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: oscarminus <me@oscarminus.de> Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>
170 lines
3.8 KiB
Go
170 lines
3.8 KiB
Go
package collectors
|
|
|
|
import (
|
|
"bufio"
|
|
"encoding/json"
|
|
|
|
"fmt"
|
|
"os"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
)
|
|
|
|
// 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 {
|
|
isHT bool
|
|
tagSet map[string]string
|
|
}
|
|
|
|
type CPUFreqCpuInfoCollector struct {
|
|
metricCollector
|
|
topology []CPUFreqCpuInfoCollectorTopology
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
|
|
// Check if already initialized
|
|
if m.init {
|
|
return nil
|
|
}
|
|
|
|
m.setup()
|
|
|
|
m.name = "CPUFreqCpuInfoCollector"
|
|
m.parallel = true
|
|
m.meta = map[string]string{
|
|
"source": m.name,
|
|
"group": "CPU",
|
|
"unit": "MHz",
|
|
}
|
|
|
|
const cpuInfoFile = "/proc/cpuinfo"
|
|
file, err := os.Open(cpuInfoFile)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to open file '%s': %v", cpuInfoFile, err)
|
|
}
|
|
defer file.Close()
|
|
|
|
// Collect topology information from file cpuinfo
|
|
foundFreq := false
|
|
processor := ""
|
|
coreID := ""
|
|
physicalPackageID := ""
|
|
m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
|
|
coreSeenBefore := make(map[string]bool)
|
|
|
|
// Read cpuinfo file, line by line
|
|
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 {
|
|
|
|
globalID := physicalPackageID + ":" + coreID
|
|
|
|
// store collected topology information
|
|
m.topology = append(m.topology,
|
|
CPUFreqCpuInfoCollectorTopology{
|
|
isHT: coreSeenBefore[globalID],
|
|
tagSet: map[string]string{
|
|
"type": "hwthread",
|
|
"type-id": processor,
|
|
"package_id": physicalPackageID,
|
|
},
|
|
},
|
|
)
|
|
|
|
// mark core as seen before
|
|
coreSeenBefore[globalID] = true
|
|
|
|
// reset topology information
|
|
foundFreq = false
|
|
processor = ""
|
|
coreID = ""
|
|
physicalPackageID = ""
|
|
}
|
|
}
|
|
|
|
// Check if at least one CPU with frequency information was detected
|
|
if len(m.topology) == 0 {
|
|
return fmt.Errorf("no CPU frequency info found in %s", cpuInfoFile)
|
|
}
|
|
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMessage) {
|
|
// Check if already initialized
|
|
if !m.init {
|
|
return
|
|
}
|
|
|
|
const cpuInfoFile = "/proc/cpuinfo"
|
|
file, err := os.Open(cpuInfoFile)
|
|
if err != nil {
|
|
cclog.ComponentError(
|
|
m.name,
|
|
fmt.Sprintf("Read(): Failed to open file '%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 {
|
|
cclog.ComponentError(
|
|
m.name,
|
|
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]interface{}{"value": value}, now); err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
processorCounter++
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Close() {
|
|
m.init = false
|
|
}
|