2021-03-29 14:14:38 +02:00
|
|
|
package sinks
|
|
|
|
|
|
|
|
import (
|
|
|
|
"bytes"
|
2022-02-04 18:12:24 +01:00
|
|
|
"encoding/json"
|
2021-05-18 15:16:10 +02:00
|
|
|
"errors"
|
2021-03-29 14:14:38 +02:00
|
|
|
"fmt"
|
2024-10-11 04:43:57 +02:00
|
|
|
"os"
|
2022-06-08 14:12:35 +02:00
|
|
|
"sync"
|
2022-02-04 18:12:24 +01:00
|
|
|
"time"
|
|
|
|
|
2022-10-10 11:53:11 +02:00
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
|
|
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
2022-01-25 15:37:43 +01:00
|
|
|
influx "github.com/influxdata/line-protocol"
|
2021-03-29 14:14:38 +02:00
|
|
|
nats "github.com/nats-io/nats.go"
|
|
|
|
)
|
|
|
|
|
2022-02-04 18:12:24 +01:00
|
|
|
type NatsSinkConfig struct {
|
|
|
|
defaultSinkConfig
|
2022-06-08 14:12:35 +02:00
|
|
|
Host string `json:"host,omitempty"`
|
|
|
|
Port string `json:"port,omitempty"`
|
|
|
|
Subject string `json:"subject,omitempty"`
|
|
|
|
User string `json:"user,omitempty"`
|
|
|
|
Password string `json:"password,omitempty"`
|
|
|
|
FlushDelay string `json:"flush_delay,omitempty"`
|
2024-10-11 04:43:57 +02:00
|
|
|
NkeyFile string `json:"nkey_file,omitempty"`
|
2022-02-04 18:12:24 +01:00
|
|
|
}
|
|
|
|
|
2021-03-29 14:14:38 +02:00
|
|
|
type NatsSink struct {
|
2022-01-25 15:37:43 +01:00
|
|
|
sink
|
2021-03-29 14:14:38 +02:00
|
|
|
client *nats.Conn
|
2022-01-25 15:37:43 +01:00
|
|
|
encoder *influx.Encoder
|
2021-03-29 14:14:38 +02:00
|
|
|
buffer *bytes.Buffer
|
2022-02-04 18:12:24 +01:00
|
|
|
config NatsSinkConfig
|
2022-06-08 14:12:35 +02:00
|
|
|
|
|
|
|
lock sync.Mutex
|
|
|
|
flushDelay time.Duration
|
|
|
|
flushTimer *time.Timer
|
2021-03-29 14:14:38 +02:00
|
|
|
}
|
|
|
|
|
2021-05-18 15:16:10 +02:00
|
|
|
func (s *NatsSink) connect() error {
|
2022-02-04 18:12:24 +01:00
|
|
|
var err error
|
|
|
|
var uinfo nats.Option = nil
|
|
|
|
var nc *nats.Conn
|
|
|
|
if len(s.config.User) > 0 && len(s.config.Password) > 0 {
|
|
|
|
uinfo = nats.UserInfo(s.config.User, s.config.Password)
|
2024-10-11 04:43:57 +02:00
|
|
|
} else if len(s.config.NkeyFile) > 0 {
|
|
|
|
if _, err := os.Stat(s.config.NkeyFile); err == nil {
|
|
|
|
uinfo = nats.UserCredentials(s.config.NkeyFile)
|
|
|
|
} else {
|
|
|
|
cclog.ComponentError(s.name, "NKEY file", s.config.NkeyFile, "does not exist: %v", err.Error())
|
|
|
|
return err
|
|
|
|
}
|
2022-02-04 18:12:24 +01:00
|
|
|
}
|
|
|
|
uri := fmt.Sprintf("nats://%s:%s", s.config.Host, s.config.Port)
|
|
|
|
cclog.ComponentDebug(s.name, "Connect to", uri)
|
2021-05-18 15:16:10 +02:00
|
|
|
s.client = nil
|
2022-02-04 18:12:24 +01:00
|
|
|
if uinfo != nil {
|
|
|
|
nc, err = nats.Connect(uri, uinfo)
|
|
|
|
} else {
|
|
|
|
nc, err = nats.Connect(uri)
|
|
|
|
}
|
2021-03-29 14:14:38 +02:00
|
|
|
if err != nil {
|
2022-02-04 18:12:24 +01:00
|
|
|
cclog.ComponentError(s.name, "Connect to", uri, "failed:", err.Error())
|
2021-03-29 14:14:38 +02:00
|
|
|
return err
|
|
|
|
}
|
|
|
|
s.client = nc
|
|
|
|
return nil
|
|
|
|
}
|
|
|
|
|
2022-02-08 11:23:19 +01:00
|
|
|
func (s *NatsSink) Write(m lp.CCMetric) error {
|
2022-06-08 14:12:35 +02:00
|
|
|
s.lock.Lock()
|
|
|
|
_, err := s.encoder.Encode(m.ToPoint(s.meta_as_tags))
|
|
|
|
s.lock.Unlock()
|
|
|
|
if err != nil {
|
|
|
|
cclog.ComponentError(s.name, "Write:", err.Error())
|
|
|
|
return err
|
2021-03-29 14:14:38 +02:00
|
|
|
}
|
2022-06-08 14:12:35 +02:00
|
|
|
|
|
|
|
if s.flushDelay == 0 {
|
|
|
|
s.Flush()
|
|
|
|
} else if s.flushTimer == nil {
|
|
|
|
s.flushTimer = time.AfterFunc(s.flushDelay, func() {
|
|
|
|
s.Flush()
|
|
|
|
})
|
|
|
|
} else {
|
|
|
|
s.flushTimer.Reset(s.flushDelay)
|
|
|
|
}
|
|
|
|
|
2021-03-29 14:14:38 +02:00
|
|
|
return nil
|
|
|
|
}
|
|
|
|
|
2021-10-12 13:43:58 +02:00
|
|
|
func (s *NatsSink) Flush() error {
|
2022-06-08 14:12:35 +02:00
|
|
|
s.lock.Lock()
|
|
|
|
buf := append([]byte{}, s.buffer.Bytes()...) // copy bytes
|
|
|
|
s.buffer.Reset()
|
|
|
|
s.lock.Unlock()
|
|
|
|
|
|
|
|
if len(buf) == 0 {
|
|
|
|
return nil
|
|
|
|
}
|
|
|
|
|
|
|
|
if err := s.client.Publish(s.config.Subject, buf); err != nil {
|
|
|
|
cclog.ComponentError(s.name, "Flush:", err.Error())
|
|
|
|
return err
|
2022-01-25 15:37:43 +01:00
|
|
|
}
|
2021-10-12 13:43:58 +02:00
|
|
|
return nil
|
|
|
|
}
|
|
|
|
|
2021-03-29 14:14:38 +02:00
|
|
|
func (s *NatsSink) Close() {
|
2022-06-08 14:12:35 +02:00
|
|
|
cclog.ComponentDebug(s.name, "Close")
|
|
|
|
s.client.Close()
|
2021-03-29 14:14:38 +02:00
|
|
|
}
|
2022-02-22 16:15:25 +01:00
|
|
|
|
|
|
|
func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
|
|
|
|
s := new(NatsSink)
|
2022-02-23 14:56:29 +01:00
|
|
|
s.name = fmt.Sprintf("NatsSink(%s)", name)
|
2022-06-08 14:12:35 +02:00
|
|
|
s.flushDelay = 10 * time.Second
|
2022-02-23 14:56:29 +01:00
|
|
|
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())
|
2022-02-23 14:56:29 +01:00
|
|
|
return nil, err
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if len(s.config.Host) == 0 ||
|
|
|
|
len(s.config.Port) == 0 ||
|
2022-06-08 14:12:35 +02:00
|
|
|
len(s.config.Subject) == 0 {
|
2022-02-23 14:56:29 +01:00
|
|
|
return nil, errors.New("not all configuration variables set required by NatsSink")
|
|
|
|
}
|
2022-03-15 16:16:26 +01:00
|
|
|
// 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
|
|
|
|
}
|
2022-02-23 14:56:29 +01:00
|
|
|
// Setup Influx line protocol
|
|
|
|
s.buffer = &bytes.Buffer{}
|
|
|
|
s.buffer.Grow(1025)
|
|
|
|
s.encoder = influx.NewEncoder(s.buffer)
|
|
|
|
s.encoder.SetPrecision(time.Second)
|
|
|
|
s.encoder.SetMaxLineBytes(1024)
|
|
|
|
// Setup infos for connection
|
|
|
|
if err := s.connect(); err != nil {
|
2022-03-15 16:16:26 +01:00
|
|
|
return nil, fmt.Errorf("unable to connect: %v", err)
|
2022-02-23 14:56:29 +01:00
|
|
|
}
|
2022-06-08 14:12:35 +02:00
|
|
|
|
|
|
|
s.flushTimer = nil
|
|
|
|
if len(s.config.FlushDelay) != 0 {
|
|
|
|
var err error
|
|
|
|
s.flushDelay, err = time.ParseDuration(s.config.FlushDelay)
|
|
|
|
if err != nil {
|
|
|
|
return nil, err
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-02-22 16:15:25 +01:00
|
|
|
return s, nil
|
|
|
|
}
|