cc-metric-collector/sinks/prometheusSink.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

223 lines
6.0 KiB
Go

package sinks
import (
"bytes"
"context"
"encoding/json"
"errors"
"fmt"
"net/http"
"strings"
"sync"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
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"
)
type PrometheusSinkConfig struct {
defaultSinkConfig
Host string `json:"host,omitempty"`
Port string `json:"port"`
Path string `json:"path,omitempty"`
GroupAsNameSpace bool `json:"group_as_namespace,omitempty"`
// User string `json:"user,omitempty"`
// Password string `json:"password,omitempty"`
// FlushDelay string `json:"flush_delay,omitempty"`
}
type PrometheusSink struct {
sink
config PrometheusSinkConfig
labelMetrics map[string]*prometheus.GaugeVec
nodeMetrics map[string]prometheus.Gauge
promWg sync.WaitGroup
promServer *http.Server
}
func intToFloat64(input interface{}) (float64, error) {
switch value := input.(type) {
case float64:
return value, nil
case float32:
return float64(value), nil
case int:
return float64(value), nil
case int32:
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.CCMessage) []string {
labelValues := []string{}
if tid, tidok := metric.GetTag("type-id"); tidok && metric.HasTag("type") {
labelValues = append(labelValues, tid)
}
if d, ok := metric.GetTag("device"); ok {
labelValues = append(labelValues, d)
} else if d, ok := metric.GetMeta("device"); ok {
labelValues = append(labelValues, d)
}
return labelValues
}
func getLabelNames(metric lp.CCMessage) []string {
labelNames := []string{}
if t, tok := metric.GetTag("type"); tok && metric.HasTag("type-id") {
labelNames = append(labelNames, t)
}
if _, ok := metric.GetTag("device"); ok {
labelNames = append(labelNames, "device")
} else if _, ok := metric.GetMeta("device"); ok {
labelNames = append(labelNames, "device")
}
return labelNames
}
func (s *PrometheusSink) newMetric(metric lp.CCMessage) error {
var value float64 = 0
name := metric.Name()
opts := prometheus.GaugeOpts{
Name: name,
}
labels := getLabelNames(metric)
labelValues := getLabelValue(metric)
if len(labels) > 0 && len(labels) != len(labelValues) {
return fmt.Errorf("cannot detect metric labels for metric %s", name)
}
if metricValue, ok := metric.GetField("value"); ok {
if floatValue, err := intToFloat64(metricValue); err == nil {
value = floatValue
} else {
return fmt.Errorf("metric %s with value '%v' cannot be casted to float64", name, metricValue)
}
}
if s.config.GroupAsNameSpace && metric.HasMeta("group") {
g, _ := metric.GetMeta("group")
opts.Namespace = strings.ToLower(g)
}
if len(labels) > 0 {
new := prometheus.NewGaugeVec(opts, labels)
new.WithLabelValues(labelValues...).Set(value)
s.labelMetrics[name] = new
prometheus.Register(new)
} else {
new := prometheus.NewGauge(opts)
new.Set(value)
s.nodeMetrics[name] = new
prometheus.Register(new)
}
return nil
}
func (s *PrometheusSink) updateMetric(metric lp.CCMessage) error {
var value float64 = 0.0
name := metric.Name()
labelValues := getLabelValue(metric)
if metricValue, ok := metric.GetField("value"); ok {
if floatValue, err := intToFloat64(metricValue); err == nil {
value = floatValue
} else {
return fmt.Errorf("metric %s with value '%v' cannot be casted to float64", name, metricValue)
}
}
if len(labelValues) > 0 {
if _, ok := s.labelMetrics[name]; !ok {
err := s.newMetric(metric)
if err != nil {
return err
}
}
s.labelMetrics[name].WithLabelValues(labelValues...).Set(value)
} else {
if _, ok := s.labelMetrics[name]; !ok {
err := s.newMetric(metric)
if err != nil {
return err
}
}
s.nodeMetrics[name].Set(value)
}
return nil
}
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 {
return nil
}
func (s *PrometheusSink) Close() {
cclog.ComponentDebug(s.name, "CLOSE")
s.promServer.Shutdown(context.Background())
s.promWg.Wait()
}
func NewPrometheusSink(name string, config json.RawMessage) (Sink, error) {
s := new(PrometheusSink)
s.name = "PrometheusSink"
if len(config) > 0 {
d := json.NewDecoder(bytes.NewReader(config))
d.DisallowUnknownFields()
if err := d.Decode(&s.config); err != nil {
cclog.ComponentError(s.name, "Error reading config:", err.Error())
return nil, err
}
}
if len(s.config.Port) == 0 {
err := errors.New("not all configuration variables set required by PrometheusSink")
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)
go func() {
router := mux.NewRouter()
// Prometheus endpoint
router.Path("/" + s.config.Path).Handler(promhttp.Handler())
url := fmt.Sprintf("%s:%s", s.config.Host, s.config.Port)
cclog.ComponentDebug(s.name, "Serving Prometheus metrics at", fmt.Sprintf("%s:%s/%s", s.config.Host, s.config.Port, s.config.Path))
s.promServer = &http.Server{Addr: url, Handler: router}
err := s.promServer.ListenAndServe()
if err != nil && err.Error() != "http: Server closed" {
cclog.ComponentError(s.name, err.Error())
}
s.promWg.Done()
}()
return s, nil
}