VictoriaMetrics/lib/protoparser/opentsdb/streamparser.go
Aliaksandr Valialkin 8df33bd5c1 app/{vminsert,vmagent}: improve data ingestion speed over a single connection
Process data obtianed from a single connection on all the available CPU cores.
2020-09-28 04:14:51 +03:00

175 lines
3.9 KiB
Go

package opentsdb
import (
"bufio"
"flag"
"fmt"
"io"
"runtime"
"sync"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fasttime"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
"github.com/VictoriaMetrics/metrics"
)
var (
trimTimestamp = flag.Duration("opentsdbTrimTimestamp", time.Second, "Trim timestamps for OpenTSDB 'telnet put' data to this duration. "+
"Minimum practical duration is 1s. Higher duration (i.e. 1m) may be used for reducing disk space usage for timestamp data")
)
// ParseStream parses OpenTSDB lines from r and calls callback for the parsed rows.
//
// The callback can be called multiple times for streamed data from r.
//
// callback shouldn't hold rows after returning.
func ParseStream(r io.Reader, callback func(rows []Row) error) error {
ctx := getStreamContext(r)
defer putStreamContext(ctx)
for ctx.Read() {
uw := getUnmarshalWork()
uw.callback = callback
uw.reqBuf = append(uw.reqBuf[:0], ctx.reqBuf...)
common.ScheduleUnmarshalWork(uw)
}
return ctx.Error()
}
func (ctx *streamContext) Read() bool {
readCalls.Inc()
if ctx.err != nil {
return false
}
ctx.reqBuf, ctx.tailBuf, ctx.err = common.ReadLinesBlock(ctx.br, ctx.reqBuf, ctx.tailBuf)
if ctx.err != nil {
if ctx.err != io.EOF {
readErrors.Inc()
ctx.err = fmt.Errorf("cannot read OpenTSDB put protocol data: %w", ctx.err)
}
return false
}
return true
}
type streamContext struct {
br *bufio.Reader
reqBuf []byte
tailBuf []byte
err error
}
func (ctx *streamContext) Error() error {
if ctx.err == io.EOF {
return nil
}
return ctx.err
}
func (ctx *streamContext) reset() {
ctx.br.Reset(nil)
ctx.reqBuf = ctx.reqBuf[:0]
ctx.tailBuf = ctx.tailBuf[:0]
ctx.err = nil
}
var (
readCalls = metrics.NewCounter(`vm_protoparser_read_calls_total{type="opentsdb"}`)
readErrors = metrics.NewCounter(`vm_protoparser_read_errors_total{type="opentsdb"}`)
rowsRead = metrics.NewCounter(`vm_protoparser_rows_read_total{type="opentsdb"}`)
)
func getStreamContext(r io.Reader) *streamContext {
select {
case ctx := <-streamContextPoolCh:
ctx.br.Reset(r)
return ctx
default:
if v := streamContextPool.Get(); v != nil {
ctx := v.(*streamContext)
ctx.br.Reset(r)
return ctx
}
return &streamContext{
br: bufio.NewReaderSize(r, 64*1024),
}
}
}
func putStreamContext(ctx *streamContext) {
ctx.reset()
select {
case streamContextPoolCh <- ctx:
default:
streamContextPool.Put(ctx)
}
}
var streamContextPool sync.Pool
var streamContextPoolCh = make(chan *streamContext, runtime.GOMAXPROCS(-1))
type unmarshalWork struct {
rows Rows
callback func(rows []Row) error
reqBuf []byte
}
func (uw *unmarshalWork) reset() {
uw.rows.Reset()
uw.callback = nil
uw.reqBuf = uw.reqBuf[:0]
}
// Unmarshal implements common.UnmarshalWork
func (uw *unmarshalWork) Unmarshal() {
uw.rows.Unmarshal(bytesutil.ToUnsafeString(uw.reqBuf))
rows := uw.rows.Rows
rowsRead.Add(len(rows))
// Fill in missing timestamps
currentTimestamp := int64(fasttime.UnixTimestamp())
for i := range rows {
r := &rows[i]
if r.Timestamp == 0 {
r.Timestamp = currentTimestamp
}
}
// Convert timestamps from seconds to milliseconds
for i := range rows {
rows[i].Timestamp *= 1e3
}
// Trim timestamps if required.
if tsTrim := trimTimestamp.Milliseconds(); tsTrim > 1000 {
for i := range rows {
row := &rows[i]
row.Timestamp -= row.Timestamp % tsTrim
}
}
if err := uw.callback(rows); err != nil {
logger.Errorf("error when processing imported data: %s", err)
putUnmarshalWork(uw)
return
}
putUnmarshalWork(uw)
}
func getUnmarshalWork() *unmarshalWork {
v := unmarshalWorkPool.Get()
if v == nil {
return &unmarshalWork{}
}
return v.(*unmarshalWork)
}
func putUnmarshalWork(uw *unmarshalWork) {
uw.reset()
unmarshalWorkPool.Put(uw)
}
var unmarshalWorkPool sync.Pool