mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-27 07:39:05 +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>
243 lines
7.5 KiB
Go
243 lines
7.5 KiB
Go
package sinks
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"crypto/tls"
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
|
influxdb2 "github.com/influxdata/influxdb-client-go/v2"
|
|
influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
|
|
influxdb2ApiHttp "github.com/influxdata/influxdb-client-go/v2/api/http"
|
|
)
|
|
|
|
type InfluxAsyncSinkConfig struct {
|
|
defaultSinkConfig
|
|
Host string `json:"host,omitempty"`
|
|
Port string `json:"port,omitempty"`
|
|
Database string `json:"database,omitempty"`
|
|
User string `json:"user,omitempty"`
|
|
Password string `json:"password,omitempty"`
|
|
Organization string `json:"organization,omitempty"`
|
|
SSL bool `json:"ssl,omitempty"`
|
|
// Maximum number of points sent to server in single request. Default 5000
|
|
BatchSize uint `json:"batch_size,omitempty"`
|
|
// Interval, in ms, in which is buffer flushed if it has not been already written (by reaching batch size) . Default 1000ms
|
|
FlushInterval uint `json:"flush_interval,omitempty"`
|
|
InfluxRetryInterval string `json:"retry_interval,omitempty"`
|
|
InfluxExponentialBase uint `json:"retry_exponential_base,omitempty"`
|
|
InfluxMaxRetries uint `json:"max_retries,omitempty"`
|
|
InfluxMaxRetryTime string `json:"max_retry_time,omitempty"`
|
|
CustomFlushInterval string `json:"custom_flush_interval,omitempty"`
|
|
MaxRetryAttempts uint `json:"max_retry_attempts,omitempty"`
|
|
}
|
|
|
|
type InfluxAsyncSink struct {
|
|
sink
|
|
client influxdb2.Client
|
|
writeApi influxdb2Api.WriteAPI
|
|
errors <-chan error
|
|
config InfluxAsyncSinkConfig
|
|
influxRetryInterval uint
|
|
influxMaxRetryTime uint
|
|
customFlushInterval time.Duration
|
|
flushTimer *time.Timer
|
|
}
|
|
|
|
func (s *InfluxAsyncSink) connect() error {
|
|
var auth string
|
|
var uri string
|
|
if s.config.SSL {
|
|
uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
|
|
} else {
|
|
uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
|
|
}
|
|
if len(s.config.User) == 0 {
|
|
auth = s.config.Password
|
|
} else {
|
|
auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
|
|
}
|
|
cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
|
|
clientOptions := influxdb2.DefaultOptions()
|
|
if s.config.BatchSize != 0 {
|
|
cclog.ComponentDebug(s.name, "Batch size", s.config.BatchSize)
|
|
clientOptions.SetBatchSize(s.config.BatchSize)
|
|
}
|
|
if s.config.FlushInterval != 0 {
|
|
cclog.ComponentDebug(s.name, "Flush interval", s.config.FlushInterval)
|
|
clientOptions.SetFlushInterval(s.config.FlushInterval)
|
|
}
|
|
if s.influxRetryInterval != 0 {
|
|
cclog.ComponentDebug(s.name, "MaxRetryInterval", s.influxRetryInterval)
|
|
clientOptions.SetMaxRetryInterval(s.influxRetryInterval)
|
|
}
|
|
if s.influxMaxRetryTime != 0 {
|
|
cclog.ComponentDebug(s.name, "MaxRetryTime", s.influxMaxRetryTime)
|
|
clientOptions.SetMaxRetryTime(s.influxMaxRetryTime)
|
|
}
|
|
if s.config.InfluxExponentialBase != 0 {
|
|
cclog.ComponentDebug(s.name, "Exponential Base", s.config.InfluxExponentialBase)
|
|
clientOptions.SetExponentialBase(s.config.InfluxExponentialBase)
|
|
}
|
|
if s.config.InfluxMaxRetries != 0 {
|
|
cclog.ComponentDebug(s.name, "Max Retries", s.config.InfluxMaxRetries)
|
|
clientOptions.SetMaxRetries(s.config.InfluxMaxRetries)
|
|
}
|
|
clientOptions.SetTLSConfig(
|
|
&tls.Config{
|
|
InsecureSkipVerify: true,
|
|
},
|
|
).SetPrecision(time.Second)
|
|
|
|
s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
|
|
s.writeApi = s.client.WriteAPI(s.config.Organization, s.config.Database)
|
|
ok, err := s.client.Ping(context.Background())
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if !ok {
|
|
return fmt.Errorf("connection to %s not healthy", uri)
|
|
}
|
|
s.writeApi.SetWriteFailedCallback(func(batch string, err influxdb2ApiHttp.Error, retryAttempts uint) bool {
|
|
mlist := strings.Split(batch, "\n")
|
|
cclog.ComponentError(s.name, fmt.Sprintf("Failed to write batch with %d metrics %d times (max: %d): %s", len(mlist), retryAttempts, s.config.MaxRetryAttempts, err.Error()))
|
|
return retryAttempts <= s.config.MaxRetryAttempts
|
|
})
|
|
return nil
|
|
}
|
|
|
|
func (s *InfluxAsyncSink) Write(m lp.CCMetric) error {
|
|
if s.customFlushInterval != 0 && s.flushTimer == nil {
|
|
// Run a batched flush for all lines that have arrived in the defined interval
|
|
s.flushTimer = time.AfterFunc(s.customFlushInterval, func() {
|
|
if err := s.Flush(); err != nil {
|
|
cclog.ComponentError(s.name, "flush failed:", err.Error())
|
|
}
|
|
})
|
|
}
|
|
s.writeApi.WritePoint(
|
|
m.ToPoint(s.meta_as_tags),
|
|
)
|
|
return nil
|
|
}
|
|
|
|
func (s *InfluxAsyncSink) Flush() error {
|
|
cclog.ComponentDebug(s.name, "Flushing")
|
|
s.writeApi.Flush()
|
|
if s.customFlushInterval != 0 && s.flushTimer != nil {
|
|
s.flushTimer = nil
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (s *InfluxAsyncSink) Close() {
|
|
cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
|
|
s.writeApi.Flush()
|
|
s.client.Close()
|
|
}
|
|
|
|
func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
|
|
s := new(InfluxAsyncSink)
|
|
s.name = fmt.Sprintf("InfluxSink(%s)", name)
|
|
|
|
// Set default for maximum number of points sent to server in single request.
|
|
s.config.BatchSize = 0
|
|
s.influxRetryInterval = 0
|
|
//s.config.InfluxRetryInterval = "1s"
|
|
s.influxMaxRetryTime = 0
|
|
//s.config.InfluxMaxRetryTime = "168h"
|
|
s.config.InfluxMaxRetries = 0
|
|
s.config.InfluxExponentialBase = 0
|
|
s.config.FlushInterval = 0
|
|
s.config.CustomFlushInterval = ""
|
|
s.customFlushInterval = time.Duration(0)
|
|
s.config.MaxRetryAttempts = 1
|
|
|
|
// Default retry intervals (in seconds)
|
|
// 1 2
|
|
// 2 4
|
|
// 4 8
|
|
// 8 16
|
|
// 16 32
|
|
// 32 64
|
|
// 64 128
|
|
// 128 256
|
|
// 256 512
|
|
// 512 1024
|
|
// 1024 2048
|
|
// 2048 4096
|
|
// 4096 8192
|
|
// 8192 16384
|
|
// 16384 32768
|
|
// 32768 65536
|
|
// 65536 131072
|
|
// 131072 262144
|
|
// 262144 524288
|
|
|
|
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 {
|
|
return nil, errors.New("missing port configuration required by InfluxSink")
|
|
}
|
|
if len(s.config.Database) == 0 {
|
|
return nil, errors.New("missing database configuration required by InfluxSink")
|
|
}
|
|
if len(s.config.Organization) == 0 {
|
|
return nil, errors.New("missing organization configuration required by InfluxSink")
|
|
}
|
|
if len(s.config.Password) == 0 {
|
|
return nil, errors.New("missing password configuration required by InfluxSink")
|
|
}
|
|
// Create lookup map to use meta infos as tags in the output metric
|
|
s.meta_as_tags = make(map[string]bool)
|
|
for _, k := range s.config.MetaAsTags {
|
|
s.meta_as_tags[k] = true
|
|
}
|
|
|
|
toUint := func(duration string, def uint) uint {
|
|
t, err := time.ParseDuration(duration)
|
|
if err == nil {
|
|
return uint(t.Milliseconds())
|
|
}
|
|
return def
|
|
}
|
|
s.influxRetryInterval = toUint(s.config.InfluxRetryInterval, s.influxRetryInterval)
|
|
s.influxMaxRetryTime = toUint(s.config.InfluxMaxRetryTime, s.influxMaxRetryTime)
|
|
|
|
// Use a own timer for calling Flush()
|
|
if len(s.config.CustomFlushInterval) > 0 {
|
|
t, err := time.ParseDuration(s.config.CustomFlushInterval)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("invalid duration in 'custom_flush_interval': %v", err)
|
|
}
|
|
s.customFlushInterval = t
|
|
}
|
|
|
|
// Connect to InfluxDB server
|
|
if err := s.connect(); err != nil {
|
|
return nil, fmt.Errorf("unable to connect: %v", err)
|
|
}
|
|
|
|
// Start background: Read from error channel
|
|
s.errors = s.writeApi.Errors()
|
|
go func() {
|
|
for err := range s.errors {
|
|
cclog.ComponentError(s.name, err.Error())
|
|
}
|
|
}()
|
|
|
|
return s, nil
|
|
}
|