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>
176 lines
3.6 KiB
Go
176 lines
3.6 KiB
Go
package collectors
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"log"
|
|
|
|
// "os"
|
|
"os/exec"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
|
)
|
|
|
|
// First part contains the code for the general NfsCollector.
|
|
// Later, the general NfsCollector is more limited to Nfs3- and Nfs4Collector.
|
|
|
|
const NFSSTAT_EXEC = `nfsstat`
|
|
|
|
type NfsCollectorData struct {
|
|
current int64
|
|
last int64
|
|
}
|
|
|
|
type nfsCollector struct {
|
|
metricCollector
|
|
tags map[string]string
|
|
version string
|
|
config struct {
|
|
Nfsstats string `json:"nfsstat"`
|
|
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
|
|
}
|
|
data map[string]NfsCollectorData
|
|
}
|
|
|
|
func (m *nfsCollector) initStats() error {
|
|
cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
|
|
cmd.Wait()
|
|
buffer, err := cmd.Output()
|
|
if err == nil {
|
|
for _, line := range strings.Split(string(buffer), "\n") {
|
|
lf := strings.Fields(line)
|
|
if len(lf) != 5 {
|
|
continue
|
|
}
|
|
if lf[1] == m.version {
|
|
name := strings.Trim(lf[3], ":")
|
|
if _, exist := m.data[name]; !exist {
|
|
value, err := strconv.ParseInt(lf[4], 0, 64)
|
|
if err == nil {
|
|
x := m.data[name]
|
|
x.current = value
|
|
x.last = value
|
|
m.data[name] = x
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return err
|
|
}
|
|
|
|
func (m *nfsCollector) updateStats() error {
|
|
cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
|
|
cmd.Wait()
|
|
buffer, err := cmd.Output()
|
|
if err == nil {
|
|
for _, line := range strings.Split(string(buffer), "\n") {
|
|
lf := strings.Fields(line)
|
|
if len(lf) != 5 {
|
|
continue
|
|
}
|
|
if lf[1] == m.version {
|
|
name := strings.Trim(lf[3], ":")
|
|
if _, exist := m.data[name]; exist {
|
|
value, err := strconv.ParseInt(lf[4], 0, 64)
|
|
if err == nil {
|
|
x := m.data[name]
|
|
x.last = x.current
|
|
x.current = value
|
|
m.data[name] = x
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return err
|
|
}
|
|
|
|
func (m *nfsCollector) MainInit(config json.RawMessage) error {
|
|
m.config.Nfsstats = string(NFSSTAT_EXEC)
|
|
// Read JSON configuration
|
|
if len(config) > 0 {
|
|
err := json.Unmarshal(config, &m.config)
|
|
if err != nil {
|
|
log.Print(err.Error())
|
|
return err
|
|
}
|
|
}
|
|
m.meta = map[string]string{
|
|
"source": m.name,
|
|
"group": "NFS",
|
|
}
|
|
m.tags = map[string]string{
|
|
"type": "node",
|
|
}
|
|
// Check if nfsstat is in executable search path
|
|
_, err := exec.LookPath(m.config.Nfsstats)
|
|
if err != nil {
|
|
return fmt.Errorf("NfsCollector.Init(): Failed to find nfsstat binary '%s': %v", m.config.Nfsstats, err)
|
|
}
|
|
m.data = make(map[string]NfsCollectorData)
|
|
m.initStats()
|
|
m.init = true
|
|
m.parallel = true
|
|
return nil
|
|
}
|
|
|
|
func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
|
|
if !m.init {
|
|
return
|
|
}
|
|
timestamp := time.Now()
|
|
|
|
m.updateStats()
|
|
prefix := ""
|
|
switch m.version {
|
|
case "v3":
|
|
prefix = "nfs3"
|
|
case "v4":
|
|
prefix = "nfs4"
|
|
default:
|
|
prefix = "nfs"
|
|
}
|
|
|
|
for name, data := range m.data {
|
|
if _, skip := stringArrayContains(m.config.ExcludeMetrics, name); skip {
|
|
continue
|
|
}
|
|
value := data.current - data.last
|
|
y, err := lp.NewMessage(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("version", m.version)
|
|
output <- y
|
|
}
|
|
}
|
|
}
|
|
|
|
func (m *nfsCollector) Close() {
|
|
m.init = false
|
|
}
|
|
|
|
type Nfs3Collector struct {
|
|
nfsCollector
|
|
}
|
|
|
|
type Nfs4Collector struct {
|
|
nfsCollector
|
|
}
|
|
|
|
func (m *Nfs3Collector) Init(config json.RawMessage) error {
|
|
m.name = "Nfs3Collector"
|
|
m.version = `v3`
|
|
m.setup()
|
|
return m.MainInit(config)
|
|
}
|
|
|
|
func (m *Nfs4Collector) Init(config json.RawMessage) error {
|
|
m.name = "Nfs4Collector"
|
|
m.version = `v4`
|
|
m.setup()
|
|
return m.MainInit(config)
|
|
}
|