Improve wal entries encoding. (#3153)

Little trick to avoid memory allocation with regards to bytes slice and string. benchmp: ``` ❯ benchcmp before.txt after.txt benchmark old ns/op new ns/op delta Benchmark_EncodeEntries-16 1699362 1055627 -37.88% benchmark old allocs new allocs delta Benchmark_EncodeEntries-16 20025 25 -99.88% benchmark old bytes new bytes delta Benchmark_EncodeEntries-16 5625393 4665376 -17.07% ``` This originated from an investigation on CPU usage of ingester. Signed-off-by: Cyril Tovena <[email protected]>
grafana · Jan 11, 2021 · 2a90c4c · 2a90c4c
1 parent cfbc5f8
commit 2a90c4c
Show file tree

Hide file tree

Showing 2 changed files with 35 additions and 9 deletions.
diff --git a/pkg/ingester/encoding.go b/pkg/ingester/encoding.go
@@ -113,14 +113,11 @@ outer:
 
 		for _, s := range ref.Entries {
 			buf.PutVarint64(s.Timestamp.UnixNano() - first)
-			// denote line length
-			byteLine := []byte(s.Line)
-			buf.PutUvarint(len(byteLine))
-			buf.PutBytes(byteLine)
+			buf.PutUvarint(len(s.Line))
+			buf.PutString(s.Line)
 		}
 	}
 	return buf.Get()
-
 }
 
 func decodeEntries(b []byte, rec *WALRecord) error {
@@ -164,7 +161,6 @@ func decodeEntries(b []byte, rec *WALRecord) error {
 		return errors.Errorf("unexpected %d bytes left in entry", len(dec.B))
 	}
 	return nil
-
 }
 
 func decodeWALRecord(b []byte, walRec *WALRecord) (err error) {
@@ -205,15 +201,14 @@ func decodeWALRecord(b []byte, walRec *WALRecord) (err error) {
 func EncWith(b []byte) (res Encbuf) {
 	res.B = b
 	return res
-
 }
 
 // Encbuf extends encoding.Encbuf with support for multi byte encoding
 type Encbuf struct {
 	encoding.Encbuf
 }
 
-func (e *Encbuf) PutBytes(c []byte) { e.B = append(e.B, c...) }
+func (e *Encbuf) PutString(s string) { e.B = append(e.B, s...) }
 
 func DecWith(b []byte) (res Decbuf) {
 	res.B = b

diff --git a/pkg/ingester/encoding_test.go b/pkg/ingester/encoding_test.go
@@ -88,6 +88,38 @@ func Test_Encoding_Entries(t *testing.T) {
 	require.Equal(t, record, decoded)
 }
 
+func Benchmark_EncodeEntries(b *testing.B) {
+	var entries []logproto.Entry
+	for i := int64(0); i < 10000; i++ {
+		entries = append(entries, logproto.Entry{
+			Timestamp: time.Unix(0, i),
+			Line:      fmt.Sprintf("long line with a lot of data like a log %d", i),
+		})
+	}
+	record := &WALRecord{
+		entryIndexMap: make(map[uint64]int),
+		UserID:        "123",
+		RefEntries: []RefEntries{
+			{
+				Ref:     456,
+				Entries: entries,
+			},
+			{
+				Ref:     789,
+				Entries: entries,
+			},
+		},
+	}
+	b.ReportAllocs()
+	b.ResetTimer()
+	buf := recordPool.GetBytes()[:0]
+	defer recordPool.PutBytes(buf)
+
+	for n := 0; n < b.N; n++ {
+		record.encodeEntries(buf)
+	}
+}
+
 func fillChunk(t *testing.T, c chunkenc.Chunk) int64 {
 	t.Helper()
 	var i, inserted int64
@@ -115,7 +147,6 @@ func dummyConf() *Config {
 }
 
 func Test_EncodingChunks(t *testing.T) {
-
 	conf := dummyConf()
 	c := chunkenc.NewMemChunk(chunkenc.EncGZIP, conf.BlockSize, conf.TargetChunkSize)
 	fillChunk(t, c)