cc-metric-collector/sinks/natsSink.go
Thomas Gruber 8d85bd53f1
Merge latest development changes to main branch (#79)
* Cleanup: Remove unused code

* Use Golang duration parser for 'interval' and 'duration'
 in main config

* Update handling of LIKWID headers. Download only if not already present in the system. Fixes #73

* Units with cc-units (#64)

* Add option to normalize units with cc-unit

* Add unit conversion to router

* Add option to change unit prefix in the router

* Add to MetricRouter README

* Add order of operations in router to README

* Use second add_tags/del_tags only if metric gets renamed

* Skip disks in DiskstatCollector that have size=0

* Check readability of sensor files in TempCollector

* Fix for --once option

* Rename `cpu` type to `hwthread` (#69)

* Rename 'cpu' type to 'hwthread' to avoid naming clashes with MetricStore and CC-Webfrontend

* Collectors in parallel (#74)

* Provide info to CollectorManager whether the collector can be executed in parallel with others

* Split serial and parallel collectors. Read in parallel first

* Update NvidiaCollector with new metrics, MIG and NvLink support (#75)

* CC topology module update (#76)

* Rename CPU to hardware thread, write some comments

* Do renaming in other parts

* Remove CpuList and SocketList function from metricCollector. Available in ccTopology

* Option to use MIG UUID as subtype-id in NvidiaCollector

* Option to use MIG slice name as subtype-id in NvidiaCollector

* MetricRouter: Fix JSON in README

* Fix for Github Action to really use the selected version

* Remove Ganglia installation in runonce Action and add Go 1.18

* Fix daemon options in init script

* Add separate go.mod files to use it with deprecated 1.16

* Minor updates for Makefiles

* fix string comparison

* AMD ROCm SMI collector (#77)

* Add collector for AMD ROCm SMI metrics

* Fix import path

* Fix imports

* Remove Board Number

* store GPU index explicitly

* Remove board number from description

* Use http instead of ftp to download likwid

* Fix serial number in rocmCollector

* Improved http sink (#78)

* automatic flush in NatsSink

* tweak default options of HttpSink

* shorter cirt. section and retries for HttpSink

* fix error handling

* Remove file added by mistake.

* Use http instead of ftp to download likwid

* Fix serial number in rocmCollector

Co-authored-by: Thomas Roehl <thomas.roehl@fau.de>

Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
Co-authored-by: Lou <lou.knauer@gmx.de>
2022-06-08 15:25:40 +02:00

149 lines
3.4 KiB
Go

package sinks
import (
"bytes"
"encoding/json"
"errors"
"fmt"
"sync"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
influx "github.com/influxdata/line-protocol"
nats "github.com/nats-io/nats.go"
)
type NatsSinkConfig struct {
defaultSinkConfig
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"`
}
type NatsSink struct {
sink
client *nats.Conn
encoder *influx.Encoder
buffer *bytes.Buffer
config NatsSinkConfig
lock sync.Mutex
flushDelay time.Duration
flushTimer *time.Timer
}
func (s *NatsSink) connect() error {
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)
}
uri := fmt.Sprintf("nats://%s:%s", s.config.Host, s.config.Port)
cclog.ComponentDebug(s.name, "Connect to", uri)
s.client = nil
if uinfo != nil {
nc, err = nats.Connect(uri, uinfo)
} else {
nc, err = nats.Connect(uri)
}
if err != nil {
cclog.ComponentError(s.name, "Connect to", uri, "failed:", err.Error())
return err
}
s.client = nc
return nil
}
func (s *NatsSink) Write(m lp.CCMetric) error {
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
}
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)
}
return nil
}
func (s *NatsSink) Flush() error {
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
}
return nil
}
func (s *NatsSink) Close() {
cclog.ComponentDebug(s.name, "Close")
s.client.Close()
}
func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
s := new(NatsSink)
s.name = fmt.Sprintf("NatsSink(%s)", name)
s.flushDelay = 10 * time.Second
if len(config) > 0 {
err := json.Unmarshal(config, &s.config)
if err != nil {
cclog.ComponentError(s.name, "Error reading config for", s.name, ":", err.Error())
return nil, err
}
}
if len(s.config.Host) == 0 ||
len(s.config.Port) == 0 ||
len(s.config.Subject) == 0 {
return nil, errors.New("not all configuration variables set required by NatsSink")
}
// 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
}
// 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 {
return nil, fmt.Errorf("unable to connect: %v", err)
}
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
}
}
return s, nil
}