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>
This commit is contained in:
Thomas Gruber
2024-12-19 23:00:14 +01:00
committed by GitHub
parent 21646e1edf
commit 7840de7b82
74 changed files with 1902 additions and 1017 deletions

View File

@@ -10,8 +10,9 @@ import (
"strings"
"sync"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
"github.com/gorilla/mux"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promhttp"
@@ -49,11 +50,13 @@ func intToFloat64(input interface{}) (float64, error) {
return float64(value), nil
case int64:
return float64(value), nil
case uint64:
return float64(value), nil
}
return 0, errors.New("cannot cast value to float64")
}
func getLabelValue(metric lp.CCMetric) []string {
func getLabelValue(metric lp.CCMessage) []string {
labelValues := []string{}
if tid, tidok := metric.GetTag("type-id"); tidok && metric.HasTag("type") {
labelValues = append(labelValues, tid)
@@ -66,7 +69,7 @@ func getLabelValue(metric lp.CCMetric) []string {
return labelValues
}
func getLabelNames(metric lp.CCMetric) []string {
func getLabelNames(metric lp.CCMessage) []string {
labelNames := []string{}
if t, tok := metric.GetTag("type"); tok && metric.HasTag("type-id") {
labelNames = append(labelNames, t)
@@ -79,7 +82,7 @@ func getLabelNames(metric lp.CCMetric) []string {
return labelNames
}
func (s *PrometheusSink) newMetric(metric lp.CCMetric) error {
func (s *PrometheusSink) newMetric(metric lp.CCMessage) error {
var value float64 = 0
name := metric.Name()
opts := prometheus.GaugeOpts{
@@ -117,7 +120,7 @@ func (s *PrometheusSink) newMetric(metric lp.CCMetric) error {
return nil
}
func (s *PrometheusSink) updateMetric(metric lp.CCMetric) error {
func (s *PrometheusSink) updateMetric(metric lp.CCMessage) error {
var value float64 = 0.0
name := metric.Name()
labelValues := getLabelValue(metric)
@@ -150,8 +153,12 @@ func (s *PrometheusSink) updateMetric(metric lp.CCMetric) error {
return nil
}
func (s *PrometheusSink) Write(m lp.CCMetric) error {
return s.updateMetric(m)
func (s *PrometheusSink) Write(m lp.CCMessage) error {
msg, err := s.mp.ProcessMessage(m)
if err == nil && msg != nil {
err = s.updateMetric(m)
}
return err
}
func (s *PrometheusSink) Flush() error {
@@ -180,6 +187,20 @@ func NewPrometheusSink(name string, config json.RawMessage) (Sink, error) {
cclog.ComponentError(s.name, err.Error())
return nil, err
}
p, err := mp.NewMessageProcessor()
if err != nil {
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
}
s.mp = p
if len(s.config.MessageProcessor) > 0 {
err = p.FromConfigJSON(s.config.MessageProcessor)
if err != nil {
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
}
}
for _, k := range s.config.MetaAsTags {
s.mp.AddMoveMetaToTags("true", k, k)
}
s.labelMetrics = make(map[string]*prometheus.GaugeVec)
s.nodeMetrics = make(map[string]prometheus.Gauge)
s.promWg.Add(1)