2022-02-25 14:33:20 +01:00
|
|
|
package sinks
|
|
|
|
|
|
|
|
import (
|
Merge develop into main (#109)
* Add cpu_used (all-cpu_idle) to CpustatCollector
* Update to line-protocol/v2
* Update runonce.yml with Golang 1.20
* Update fsnotify in LIKWID Collector
* Use not a pointer to line-protocol.Encoder
* Simplify Makefile
* Use only as many arguments as required
* Allow sum function to handle non float types
* Allow values to be a slice of type float64, float32, int, int64, int32, bool
* Use generic function to simplify code
* Add missing case for type []int32
* Use generic function to compute minimum
* Use generic function to compute maximum
* Use generic function to compute average
* Add error value to sumAnyType
* Use generic function to compute median
* For older versions of go slices is not part of the installation
* Remove old entries from go.sum
* Use simpler sort function
* Compute metrics ib_total and ib_total_pkts
* Add aggregated metrics.
Add missing units
* Update likwidMetric.go
Fixes a potential bug when `fsnotify.NewWatcher()` fails with an error
* Completly avoid memory allocations in infinibandMetric read()
* Fixed initialization: Initalization and measurements should run in the same thread
* Add safe.directory to Release action
* Fix path after installation to /usr/bin after installation
* ioutil.ReadFile is deprecated: As of Go 1.16, this function simply calls os.ReadFile
* Switch to package slices from the golang 1.21 default library
* Read file line by line
* Read file line by line
* Read file line by line
* Use CamelCase
* Use CamelCase
* Fix function getNumaDomain, it always returned 0
* Avoid type conversion by using Atoi
Avoid copying structs by using pointer access
Increase readability with CamelCase variable names
* Add caching
* Cache CpuData
* Cleanup
* Use init function to initalize cache structure to avoid multi threading problems
* Reuse information from /proc/cpuinfo
* Avoid slice cloning. Directly use the cache
* Add DieList
* Add NumaDomainList and SMTList
* Cleanup
* Add comment
* Lookup core ID from /sys/devices/system/cpu, /proc/cpuinfo is not portable
* Lookup all information from /sys/devices/system/cpu, /proc/cpuinfo is not portable
* Correctly handle lists from /sys
* Add Simultaneous Multithreading siblings
* Replace deprecated thread_siblings_list by core_cpus_list
* Reduce number of required slices
* Allow to send total values per core, socket and node
* Send all metrics with same time stamp
calcEventsetMetrics does only computiation, counter measurement is done before
* Input parameters should be float64 when evaluating to float64
* Send all metrics with same time stamp
calcGlobalMetrics does only computiation, counter measurement is done before
* Remove unused variable gmresults
* Add comments
* Updated go packages
* Add build with golang 1.21
* Switch to checkout action version 4
* Switch to setup-go action version 4
* Add workflow_dispatch to allow manual run of workflow
* Add workflow_dispatch to allow manual run of workflow
* Add release build jobs to runonce.yml
* Switch to golang 1.20 for RHEL based distributions
* Use dnf to download golang
* Remove golang versions before 1.20
* Upgrade Ubuntu focal -> jammy
* Pipe golang tar package directly to tar
* Update golang version
* Fix Ubuntu version number
* Add links to ipmi and redfish receivers
* Fix http server addr format
* github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol
* Corrected spelling
* Add some comments
* github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol
* Allow other fields not only field "value"
* Add some basic debugging documentation
* Add some basic debugging documentation
* Use a lock for the flush timer
* Add tags in lexical order as required by AddTag()
* Only access meta data, when it gets used as tag
* Use slice to store lexialicly orderd key value pairs
* Increase golang version requirement to 1.20.
* Avoid package cmp to allow builds with golang v1.20
* Fix: Error NVML library not found did crash
cc-metric-collector with "SIGSEGV: segmentation violation"
* Add config option idle_timeout
* Add basic authentication support
* Add basic authentication support
* Avoid unneccessary memory allocations
* Add documentation for send_*_total values
* Use generic package maps to clone maps
* Reuse flush timer
* Add Influx client options
* Reuse ccTopology functionality
* Do not store unused topology information
* Add batch_size config
* Cleanup
* Use stype and stype-id for the NIC in NetstatCollector
* Wait for concurrent flush operations to finish
* Be more verbose in error messages
* Reverted previous changes.
Made the code to complex without much advantages
* Use line protocol encoder
* Go pkg update
* Stop flush timer, when immediatelly flushing
* Fix: Corrected unlock access to batch slice
* Add config option to specify whether to use GZip compression in influx write requests
* Add asynchron send of encoder metrics
* Use DefaultServeMux instead of github.com/gorilla/mux
* Add config option for HTTP keep-alives
* Be more strict, when parsing json
* Add config option for HTTP request timeout and Retry interval
* Allow more then one background send operation
* Fix %sysusers_create_package args (#108)
%sysusers_create_package requires two arguments. See: https://github.com/systemd/systemd/blob/main/src/rpm/macros.systemd.in#L165
* Add nfsiostat to list of collectors
---------
Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
Co-authored-by: Holger Obermaier <holgerob@gmx.de>
Co-authored-by: Obihörnchen <obihoernchende@gmail.com>
2023-12-04 12:21:26 +01:00
|
|
|
"bytes"
|
2022-02-25 14:33:20 +01:00
|
|
|
"context"
|
|
|
|
"encoding/json"
|
|
|
|
"errors"
|
|
|
|
"fmt"
|
|
|
|
"net/http"
|
|
|
|
"strings"
|
|
|
|
"sync"
|
|
|
|
|
2024-12-19 23:00:14 +01:00
|
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
2022-10-10 11:53:11 +02:00
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
2024-12-19 23:00:14 +01:00
|
|
|
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
|
2022-02-25 14:33:20 +01:00
|
|
|
"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
|
2024-12-19 23:00:14 +01:00
|
|
|
case uint64:
|
|
|
|
return float64(value), nil
|
2022-02-25 14:33:20 +01:00
|
|
|
}
|
|
|
|
return 0, errors.New("cannot cast value to float64")
|
|
|
|
}
|
|
|
|
|
2024-12-19 23:00:14 +01:00
|
|
|
func getLabelValue(metric lp.CCMessage) []string {
|
2022-02-25 14:33:20 +01:00
|
|
|
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
|
|
|
|
}
|
|
|
|
|
2024-12-19 23:00:14 +01:00
|
|
|
func getLabelNames(metric lp.CCMessage) []string {
|
2022-02-25 14:33:20 +01:00
|
|
|
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
|
|
|
|
}
|
|
|
|
|
2024-12-19 23:00:14 +01:00
|
|
|
func (s *PrometheusSink) newMetric(metric lp.CCMessage) error {
|
2022-02-25 14:33:20 +01:00
|
|
|
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
|
|
|
|
}
|
|
|
|
|
2024-12-19 23:00:14 +01:00
|
|
|
func (s *PrometheusSink) updateMetric(metric lp.CCMessage) error {
|
2022-02-25 14:33:20 +01:00
|
|
|
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
|
|
|
|
}
|
|
|
|
|
2024-12-19 23:00:14 +01:00
|
|
|
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
|
2022-02-25 14:33:20 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
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 {
|
Merge develop into main (#109)
* Add cpu_used (all-cpu_idle) to CpustatCollector
* Update to line-protocol/v2
* Update runonce.yml with Golang 1.20
* Update fsnotify in LIKWID Collector
* Use not a pointer to line-protocol.Encoder
* Simplify Makefile
* Use only as many arguments as required
* Allow sum function to handle non float types
* Allow values to be a slice of type float64, float32, int, int64, int32, bool
* Use generic function to simplify code
* Add missing case for type []int32
* Use generic function to compute minimum
* Use generic function to compute maximum
* Use generic function to compute average
* Add error value to sumAnyType
* Use generic function to compute median
* For older versions of go slices is not part of the installation
* Remove old entries from go.sum
* Use simpler sort function
* Compute metrics ib_total and ib_total_pkts
* Add aggregated metrics.
Add missing units
* Update likwidMetric.go
Fixes a potential bug when `fsnotify.NewWatcher()` fails with an error
* Completly avoid memory allocations in infinibandMetric read()
* Fixed initialization: Initalization and measurements should run in the same thread
* Add safe.directory to Release action
* Fix path after installation to /usr/bin after installation
* ioutil.ReadFile is deprecated: As of Go 1.16, this function simply calls os.ReadFile
* Switch to package slices from the golang 1.21 default library
* Read file line by line
* Read file line by line
* Read file line by line
* Use CamelCase
* Use CamelCase
* Fix function getNumaDomain, it always returned 0
* Avoid type conversion by using Atoi
Avoid copying structs by using pointer access
Increase readability with CamelCase variable names
* Add caching
* Cache CpuData
* Cleanup
* Use init function to initalize cache structure to avoid multi threading problems
* Reuse information from /proc/cpuinfo
* Avoid slice cloning. Directly use the cache
* Add DieList
* Add NumaDomainList and SMTList
* Cleanup
* Add comment
* Lookup core ID from /sys/devices/system/cpu, /proc/cpuinfo is not portable
* Lookup all information from /sys/devices/system/cpu, /proc/cpuinfo is not portable
* Correctly handle lists from /sys
* Add Simultaneous Multithreading siblings
* Replace deprecated thread_siblings_list by core_cpus_list
* Reduce number of required slices
* Allow to send total values per core, socket and node
* Send all metrics with same time stamp
calcEventsetMetrics does only computiation, counter measurement is done before
* Input parameters should be float64 when evaluating to float64
* Send all metrics with same time stamp
calcGlobalMetrics does only computiation, counter measurement is done before
* Remove unused variable gmresults
* Add comments
* Updated go packages
* Add build with golang 1.21
* Switch to checkout action version 4
* Switch to setup-go action version 4
* Add workflow_dispatch to allow manual run of workflow
* Add workflow_dispatch to allow manual run of workflow
* Add release build jobs to runonce.yml
* Switch to golang 1.20 for RHEL based distributions
* Use dnf to download golang
* Remove golang versions before 1.20
* Upgrade Ubuntu focal -> jammy
* Pipe golang tar package directly to tar
* Update golang version
* Fix Ubuntu version number
* Add links to ipmi and redfish receivers
* Fix http server addr format
* github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol
* Corrected spelling
* Add some comments
* github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol
* Allow other fields not only field "value"
* Add some basic debugging documentation
* Add some basic debugging documentation
* Use a lock for the flush timer
* Add tags in lexical order as required by AddTag()
* Only access meta data, when it gets used as tag
* Use slice to store lexialicly orderd key value pairs
* Increase golang version requirement to 1.20.
* Avoid package cmp to allow builds with golang v1.20
* Fix: Error NVML library not found did crash
cc-metric-collector with "SIGSEGV: segmentation violation"
* Add config option idle_timeout
* Add basic authentication support
* Add basic authentication support
* Avoid unneccessary memory allocations
* Add documentation for send_*_total values
* Use generic package maps to clone maps
* Reuse flush timer
* Add Influx client options
* Reuse ccTopology functionality
* Do not store unused topology information
* Add batch_size config
* Cleanup
* Use stype and stype-id for the NIC in NetstatCollector
* Wait for concurrent flush operations to finish
* Be more verbose in error messages
* Reverted previous changes.
Made the code to complex without much advantages
* Use line protocol encoder
* Go pkg update
* Stop flush timer, when immediatelly flushing
* Fix: Corrected unlock access to batch slice
* Add config option to specify whether to use GZip compression in influx write requests
* Add asynchron send of encoder metrics
* Use DefaultServeMux instead of github.com/gorilla/mux
* Add config option for HTTP keep-alives
* Be more strict, when parsing json
* Add config option for HTTP request timeout and Retry interval
* Allow more then one background send operation
* Fix %sysusers_create_package args (#108)
%sysusers_create_package requires two arguments. See: https://github.com/systemd/systemd/blob/main/src/rpm/macros.systemd.in#L165
* Add nfsiostat to list of collectors
---------
Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
Co-authored-by: Holger Obermaier <holgerob@gmx.de>
Co-authored-by: Obihörnchen <obihoernchende@gmail.com>
2023-12-04 12:21:26 +01:00
|
|
|
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())
|
2022-02-25 14:33:20 +01:00
|
|
|
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
|
|
|
|
}
|
2024-12-19 23:00:14 +01:00
|
|
|
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)
|
|
|
|
}
|
2022-02-25 14:33:20 +01:00
|
|
|
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
|
|
|
|
}
|