cc-metric-collector/collectors/cpufreqMetric.go
Thomas Gruber 7840de7b82
Merge develop branch into main (#123)
* 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>
2024-12-19 23:00:14 +01:00

129 lines
3.0 KiB
Go

package collectors
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
"github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
"golang.org/x/sys/unix"
)
type CPUFreqCollectorTopology struct {
scalingCurFreqFile string
tagSet map[string]string
}
// CPUFreqCollector
// a metric collector to measure the current frequency of the CPUs
// as obtained from the hardware (in KHz)
// Only measure on the first hyper-thread
//
// See: https://www.kernel.org/doc/html/latest/admin-guide/pm/cpufreq.html
type CPUFreqCollector struct {
metricCollector
topology []CPUFreqCollectorTopology
config struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
}
}
func (m *CPUFreqCollector) Init(config json.RawMessage) error {
// Check if already initialized
if m.init {
return nil
}
m.name = "CPUFreqCollector"
m.setup()
m.parallel = true
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
if err != nil {
return err
}
}
m.meta = map[string]string{
"source": m.name,
"group": "CPU",
"unit": "Hz",
}
m.topology = make([]CPUFreqCollectorTopology, 0)
for _, c := range ccTopology.CpuData() {
// Skip hyper threading CPUs
if c.CpuID != c.CoreCPUsList[0] {
continue
}
// Check access to current frequency file
scalingCurFreqFile := filepath.Join("/sys/devices/system/cpu", fmt.Sprintf("cpu%d", c.CpuID), "cpufreq/scaling_cur_freq")
err := unix.Access(scalingCurFreqFile, unix.R_OK)
if err != nil {
return fmt.Errorf("unable to access file '%s': %v", scalingCurFreqFile, err)
}
m.topology = append(m.topology,
CPUFreqCollectorTopology{
tagSet: map[string]string{
"type": "hwthread",
"type-id": fmt.Sprint(c.CpuID),
"package_id": fmt.Sprint(c.Socket),
},
scalingCurFreqFile: scalingCurFreqFile,
},
)
}
// Initialized
cclog.ComponentDebug(
m.name,
"initialized",
len(m.topology), "non-hyper-threading CPUs")
m.init = true
return nil
}
func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// Check if already initialized
if !m.init {
return
}
now := time.Now()
for i := range m.topology {
t := &m.topology[i]
// Read current frequency
line, err := os.ReadFile(t.scalingCurFreqFile)
if err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to read file '%s': %v", t.scalingCurFreqFile, err))
continue
}
cpuFreq, err := strconv.ParseInt(strings.TrimSpace(string(line)), 10, 64)
if err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to convert CPU frequency '%s' to int64: %v", line, err))
continue
}
if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
output <- y
}
}
}
func (m *CPUFreqCollector) Close() {
m.init = false
}