cc-metric-collector/collectors/ipmiMetric.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

191 lines
4.4 KiB
Go

package collectors
import (
"bufio"
"bytes"
"encoding/json"
"errors"
"fmt"
"io"
"log"
"os/exec"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
)
const IPMISENSORS_PATH = `ipmi-sensors`
type IpmiCollector struct {
metricCollector
config struct {
ExcludeDevices []string `json:"exclude_devices"`
IpmitoolPath string `json:"ipmitool_path"`
IpmisensorsPath string `json:"ipmisensors_path"`
}
ipmitool string
ipmisensors string
}
func (m *IpmiCollector) Init(config json.RawMessage) error {
// Check if already initialized
if m.init {
return nil
}
m.name = "IpmiCollector"
m.setup()
m.parallel = true
m.meta = map[string]string{
"source": m.name,
"group": "IPMI",
}
// default path to IPMI tools
m.config.IpmitoolPath = "ipmitool"
m.config.IpmisensorsPath = "ipmi-sensors"
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
if err != nil {
return err
}
}
// Check if executables ipmitool or ipmisensors are found
p, err := exec.LookPath(m.config.IpmitoolPath)
if err == nil {
command := exec.Command(p)
err := command.Run()
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Failed to execute %s: %v", p, err.Error()))
m.ipmitool = ""
} else {
m.ipmitool = p
}
}
p, err = exec.LookPath(m.config.IpmisensorsPath)
if err == nil {
command := exec.Command(p)
err := command.Run()
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Failed to execute %s: %v", p, err.Error()))
m.ipmisensors = ""
} else {
m.ipmisensors = p
}
}
if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
return errors.New("no usable IPMI reader found")
}
m.init = true
return nil
}
func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
// Setup ipmitool command
command := exec.Command(cmd, "sensor")
stdout, _ := command.StdoutPipe()
errBuf := new(bytes.Buffer)
command.Stderr = errBuf
// start command
if err := command.Start(); err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("readIpmiTool(): Failed to start command \"%s\": %v", command.String(), err),
)
return
}
// Read command output
scanner := bufio.NewScanner(stdout)
for scanner.Scan() {
lv := strings.Split(scanner.Text(), "|")
if len(lv) < 3 {
continue
}
v, err := strconv.ParseFloat(strings.TrimSpace(lv[1]), 64)
if err == nil {
name := strings.ToLower(strings.Replace(strings.TrimSpace(lv[0]), " ", "_", -1))
unit := strings.TrimSpace(lv[2])
if unit == "Volts" {
unit = "Volts"
} else if unit == "degrees C" {
unit = "degC"
} else if unit == "degrees F" {
unit = "degF"
} else if unit == "Watts" {
unit = "Watts"
}
y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
if err == nil {
y.AddMeta("unit", unit)
output <- y
}
}
}
// Wait for command end
if err := command.Wait(); err != nil {
errMsg, _ := io.ReadAll(errBuf)
cclog.ComponentError(
m.name,
fmt.Sprintf("readIpmiTool(): Failed to wait for the end of command \"%s\": %v\n", command.String(), err),
)
cclog.ComponentError(m.name, fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", strings.TrimSpace(string(errMsg))))
return
}
}
func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
command := exec.Command(cmd, "--comma-separated-output", "--sdr-cache-recreate")
command.Wait()
stdout, err := command.Output()
if err != nil {
log.Print(err)
return
}
ll := strings.Split(string(stdout), "\n")
for _, line := range ll {
lv := strings.Split(line, ",")
if len(lv) > 3 {
v, err := strconv.ParseFloat(lv[3], 64)
if err == nil {
name := strings.ToLower(strings.Replace(lv[1], " ", "_", -1))
y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
if err == nil {
if len(lv) > 4 {
y.AddMeta("unit", lv[4])
}
output <- y
}
}
}
}
}
func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// Check if already initialized
if !m.init {
return
}
if len(m.config.IpmitoolPath) > 0 {
m.readIpmiTool(m.config.IpmitoolPath, output)
} else if len(m.config.IpmisensorsPath) > 0 {
m.readIpmiSensors(m.config.IpmisensorsPath, output)
}
}
func (m *IpmiCollector) Close() {
m.init = false
}