mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-11-10 04:27:25 +01:00
162cce0fda
* InfiniBandCollector: Scale raw readings from octets to bytes * Fix clock frequency coming from LikwidCollector and update docs * Build DEB package for Ubuntu 20.04 for releases * Fix memstat collector with numa_stats option * Remove useless prints from MemstatCollector * Replace ioutils with os and io (#87) * Use lower case for error strings in RocmSmiCollector * move maybe-usable-by-other-cc-components to pkg. Fix all files to use the new paths (#88) * Add collector for monitoring the execution of cc-metric-collector itself (#81) * Add collector to monitor execution of cc-metric-collector itself * Register SelfCollector * Fix import paths for moved packages * Check if at least one CPU with frequency information was detected * Correct type: /proc/stats -> /proc/stat * Update README.md * Run ipmitool asynchron. Improved error handling. * Corrected some typos * Add running average power limit (RAPL) metric collector * Add running average power limit (RAPL) metric collector * Do not mess up with the orignal configuration * * Corrected json config in numastatsMetric.md * Added some debug output to numastatsMetric.go * Fixed computing number of physical packages for non continous physical package IDs (e.g. on Ampere Altra Q80-30) * Fix kernel panic for receiver config with missing receiver type * Add receiver to gather remote IPMI sensor metrics * Added config option to add ipmi-sensors command line options * Add documentaion for IPMI receiver * Update to latest version of included go modules * Add go.mod to App dependency * Try to use common metric tags across hardware vendors * Add IPMI metric: current * remove prefix enumeration like 01-... * Add IPMI receiver example configuration to receivers.json * Minimal formating changes * Add hostlist package * Added tests for hostlist Expand() * Use package hostlist to expand a host list * Use package hostlist to expand a host list * Some servers return "ConsumedPowerWatt":65535 instead of "ConsumedPowerWatt":null * Updated to latest package versions * Do not allow unknown fields in JSON configuration file * Add workflow to customize packages to docs * NFS I/O Stats Collector (#91) * Initial version * Delete values for vanished mount points and comments * Fix for Likwid collector (#95) * Run LIKWID in separate thread and check metric type * Change LIKWID collector documentation to use 'type' instead of 'scope' * Re-initialize LIKWID after one read is missing due to lock toggle * Register cc-metric-collector at Zenodo (#93) * Add initial version of Zenodo project file * Orcid ID added * Update .zenodo.json Co-authored-by: Holger Obermaier <holger.obermaier@kit.edu> * Update ipmiMetric.go Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
175 lines
4.0 KiB
Go
175 lines
4.0 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-metric-collector/pkg/ccMetric"
|
|
)
|
|
|
|
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 {
|
|
m.ipmitool = p
|
|
}
|
|
p, err = exec.LookPath(m.config.IpmisensorsPath)
|
|
if err == nil {
|
|
m.ipmisensors = p
|
|
}
|
|
if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
|
|
return errors.New("no IPMI reader found")
|
|
}
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
|
|
|
|
// 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.New(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),
|
|
fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", string(errMsg)),
|
|
)
|
|
return
|
|
}
|
|
}
|
|
|
|
func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
|
|
|
|
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.New(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.CCMetric) {
|
|
|
|
// 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
|
|
}
|