mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-26 15:29:04 +01:00
6ab45dd3ec
* 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>
185 lines
4.5 KiB
Go
185 lines
4.5 KiB
Go
package sinks
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"os"
|
|
"sync"
|
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
|
)
|
|
|
|
const SINK_MAX_FORWARD = 50
|
|
|
|
// Map of all available sinks
|
|
var AvailableSinks = map[string]func(name string, config json.RawMessage) (Sink, error){
|
|
"ganglia": NewGangliaSink,
|
|
"libganglia": NewLibgangliaSink,
|
|
"stdout": NewStdoutSink,
|
|
"nats": NewNatsSink,
|
|
"influxdb": NewInfluxSink,
|
|
"influxasync": NewInfluxAsyncSink,
|
|
"http": NewHttpSink,
|
|
}
|
|
|
|
// Metric collector manager data structure
|
|
type sinkManager struct {
|
|
input chan lp.CCMetric // input channel
|
|
done chan bool // channel to finish / stop metric sink manager
|
|
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
|
|
sinks map[string]Sink // Mapping sink name to sink
|
|
maxForward int // number of metrics to write maximally in one iteration
|
|
}
|
|
|
|
// Sink manager access functions
|
|
type SinkManager interface {
|
|
Init(wg *sync.WaitGroup, sinkConfigFile string) error
|
|
AddInput(input chan lp.CCMetric)
|
|
AddOutput(name string, config json.RawMessage) error
|
|
Start()
|
|
Close()
|
|
}
|
|
|
|
// Init initializes the sink manager by:
|
|
// * Reading its configuration file
|
|
// * Adding the configured sinks and providing them with the corresponding config
|
|
func (sm *sinkManager) Init(wg *sync.WaitGroup, sinkConfigFile string) error {
|
|
sm.input = nil
|
|
sm.done = make(chan bool)
|
|
sm.wg = wg
|
|
sm.sinks = make(map[string]Sink, 0)
|
|
sm.maxForward = SINK_MAX_FORWARD
|
|
|
|
if len(sinkConfigFile) == 0 {
|
|
return nil
|
|
}
|
|
|
|
// Read sink config file
|
|
configFile, err := os.Open(sinkConfigFile)
|
|
if err != nil {
|
|
cclog.ComponentError("SinkManager", err.Error())
|
|
return err
|
|
}
|
|
defer configFile.Close()
|
|
|
|
// Parse config
|
|
jsonParser := json.NewDecoder(configFile)
|
|
var rawConfigs map[string]json.RawMessage
|
|
err = jsonParser.Decode(&rawConfigs)
|
|
if err != nil {
|
|
cclog.ComponentError("SinkManager", err.Error())
|
|
return err
|
|
}
|
|
|
|
// Start sinks
|
|
for name, raw := range rawConfigs {
|
|
err = sm.AddOutput(name, raw)
|
|
if err != nil {
|
|
cclog.ComponentError("SinkManager", err)
|
|
continue
|
|
}
|
|
}
|
|
|
|
// Check that at least one sink is running
|
|
if !(len(sm.sinks) > 0) {
|
|
cclog.ComponentError("SinkManager", "Found no usable sinks")
|
|
return fmt.Errorf("found no usable sinks")
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
// Start starts the sink managers background task, which
|
|
// distributes received metrics to the sinks
|
|
func (sm *sinkManager) Start() {
|
|
sm.wg.Add(1)
|
|
go func() {
|
|
defer sm.wg.Done()
|
|
|
|
// Sink manager is done
|
|
done := func() {
|
|
for _, s := range sm.sinks {
|
|
s.Close()
|
|
}
|
|
|
|
close(sm.done)
|
|
cclog.ComponentDebug("SinkManager", "DONE")
|
|
}
|
|
|
|
toTheSinks := func(p lp.CCMetric) {
|
|
// Send received metric to all outputs
|
|
cclog.ComponentDebug("SinkManager", "WRITE", p)
|
|
for _, s := range sm.sinks {
|
|
if err := s.Write(p); err != nil {
|
|
cclog.ComponentError("SinkManager", "WRITE", s.Name(), "write failed:", err.Error())
|
|
}
|
|
}
|
|
}
|
|
|
|
for {
|
|
select {
|
|
case <-sm.done:
|
|
done()
|
|
return
|
|
|
|
case p := <-sm.input:
|
|
toTheSinks(p)
|
|
for i := 0; len(sm.input) > 0 && i < sm.maxForward; i++ {
|
|
p := <-sm.input
|
|
toTheSinks(p)
|
|
}
|
|
}
|
|
}
|
|
}()
|
|
|
|
// Sink manager is started
|
|
cclog.ComponentDebug("SinkManager", "STARTED")
|
|
}
|
|
|
|
// AddInput adds the input channel to the sink manager
|
|
func (sm *sinkManager) AddInput(input chan lp.CCMetric) {
|
|
sm.input = input
|
|
}
|
|
|
|
func (sm *sinkManager) AddOutput(name string, rawConfig json.RawMessage) error {
|
|
var err error
|
|
var sinkConfig defaultSinkConfig
|
|
if len(rawConfig) > 0 {
|
|
err := json.Unmarshal(rawConfig, &sinkConfig)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
if _, found := AvailableSinks[sinkConfig.Type]; !found {
|
|
cclog.ComponentError("SinkManager", "SKIP", name, "unknown sink:", sinkConfig.Type)
|
|
return err
|
|
}
|
|
s, err := AvailableSinks[sinkConfig.Type](name, rawConfig)
|
|
if err != nil {
|
|
cclog.ComponentError("SinkManager", "SKIP", name, "initialization failed:", err.Error())
|
|
return err
|
|
}
|
|
sm.sinks[name] = s
|
|
cclog.ComponentDebug("SinkManager", "ADD SINK", s.Name(), "with name", fmt.Sprintf("'%s'", name))
|
|
return nil
|
|
}
|
|
|
|
// Close finishes / stops the sink manager
|
|
func (sm *sinkManager) Close() {
|
|
cclog.ComponentDebug("SinkManager", "CLOSE")
|
|
sm.done <- true
|
|
// wait for close of channel sm.done
|
|
<-sm.done
|
|
}
|
|
|
|
// New creates a new initialized sink manager
|
|
func New(wg *sync.WaitGroup, sinkConfigFile string) (SinkManager, error) {
|
|
sm := new(sinkManager)
|
|
err := sm.Init(wg, sinkConfigFile)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
return sm, err
|
|
}
|