mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2024-12-16 00:41:24 +01:00
22c1e29284
The caller of ParseStream then can generate HTTP 503 responses for non-nil errors occured in callbacks when processing incoming requests. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/896
175 lines
4.0 KiB
Go
175 lines
4.0 KiB
Go
package vmimport
|
|
|
|
import (
|
|
"bufio"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"runtime"
|
|
"sync"
|
|
|
|
"github.com/VictoriaMetrics/VictoriaMetrics/lib/bytesutil"
|
|
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
|
|
"github.com/VictoriaMetrics/VictoriaMetrics/lib/protoparser/common"
|
|
"github.com/VictoriaMetrics/metrics"
|
|
)
|
|
|
|
var maxLineLen = flagutil.NewBytes("import.maxLineLen", 100*1024*1024, "The maximum length in bytes of a single line accepted by /api/v1/import; "+
|
|
"the line length can be limited with `max_rows_per_line` query arg passed to /api/v1/export")
|
|
|
|
// ParseStream parses /api/v1/import lines from req and calls callback for the parsed rows.
|
|
//
|
|
// The callback can be called concurrently multiple times for streamed data from req.
|
|
//
|
|
// callback shouldn't hold rows after returning.
|
|
func ParseStream(req *http.Request, callback func(rows []Row) error) error {
|
|
r := req.Body
|
|
if req.Header.Get("Content-Encoding") == "gzip" {
|
|
zr, err := common.GetGzipReader(r)
|
|
if err != nil {
|
|
return fmt.Errorf("cannot read gzipped vmimport data: %w", err)
|
|
}
|
|
defer common.PutGzipReader(zr)
|
|
r = zr
|
|
}
|
|
ctx := getStreamContext(r)
|
|
defer putStreamContext(ctx)
|
|
for ctx.Read() {
|
|
uw := getUnmarshalWork()
|
|
uw.callback = func(rows []Row) {
|
|
if err := callback(rows); err != nil {
|
|
ctx.callbackErrLock.Lock()
|
|
if ctx.callbackErr == nil {
|
|
ctx.callbackErr = fmt.Errorf("error when processing imported data: %w", err)
|
|
}
|
|
ctx.callbackErrLock.Unlock()
|
|
}
|
|
ctx.wg.Done()
|
|
}
|
|
uw.reqBuf, ctx.reqBuf = ctx.reqBuf, uw.reqBuf
|
|
ctx.wg.Add(1)
|
|
common.ScheduleUnmarshalWork(uw)
|
|
}
|
|
ctx.wg.Wait()
|
|
if err := ctx.Error(); err != nil {
|
|
return err
|
|
}
|
|
return ctx.callbackErr
|
|
}
|
|
|
|
func (ctx *streamContext) Read() bool {
|
|
readCalls.Inc()
|
|
if ctx.err != nil {
|
|
return false
|
|
}
|
|
ctx.reqBuf, ctx.tailBuf, ctx.err = common.ReadLinesBlockExt(ctx.br, ctx.reqBuf, ctx.tailBuf, maxLineLen.N)
|
|
if ctx.err != nil {
|
|
if ctx.err != io.EOF {
|
|
readErrors.Inc()
|
|
ctx.err = fmt.Errorf("cannot read vmimport data: %w", ctx.err)
|
|
}
|
|
return false
|
|
}
|
|
return true
|
|
}
|
|
|
|
var (
|
|
readCalls = metrics.NewCounter(`vm_protoparser_read_calls_total{type="vmimport"}`)
|
|
readErrors = metrics.NewCounter(`vm_protoparser_read_errors_total{type="vmimport"}`)
|
|
rowsRead = metrics.NewCounter(`vm_protoparser_rows_read_total{type="vmimport"}`)
|
|
)
|
|
|
|
type streamContext struct {
|
|
br *bufio.Reader
|
|
reqBuf []byte
|
|
tailBuf []byte
|
|
err error
|
|
|
|
wg sync.WaitGroup
|
|
callbackErrLock sync.Mutex
|
|
callbackErr 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
|
|
ctx.callbackErr = nil
|
|
}
|
|
|
|
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)
|
|
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
|
|
for i := range rows {
|
|
row := &rows[i]
|
|
rowsRead.Add(len(row.Timestamps))
|
|
}
|
|
uw.callback(rows)
|
|
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
|