Skip to content

store: fix deduplication in proxy heap for series with multiple chunks #6663

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
MichaHoffmann wants to merge 3 commits into
base: main
Choose a base branch
from
Open

store: fix deduplication in proxy heap for series with multiple chunks #6663

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4d50e46
store: fix deduplication in proxy heap for series with multiple chunks
MichaHoffmann Aug 26, 2023
2f9024a
Merge branch 'main' into mhoffm-fix-dedup-heap-multiple-chunks
MichaHoffmann Aug 28, 2023
c883a30
Merge branch 'main' into mhoffm-fix-dedup-heap-multiple-chunks
MichaHoffmann Mar 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion pkg/store/prometheus.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -480,7 +480,6 @@ func (p *PrometheusStore) chunkSamples(series *prompb.TimeSeries, maxSamplesPerC

samples = samples[chunkSize:]
}

return chks, nil
}

Expand Down
32 changes: 20 additions & 12 deletions pkg/store/proxy_heap.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,9 @@ package store
import (
"container/heap"
"context"
"encoding/binary"
"fmt"
"hash"
"io"
"sort"
"sync"
Expand Down Expand Up @@ -111,24 +113,30 @@ func (d *dedupResponseHeap) Next() bool {
func chainSeriesAndRemIdenticalChunks(series []*storepb.SeriesResponse) *storepb.SeriesResponse {
chunkDedupMap := map[uint64]*storepb.AggrChunk{}

buf := make([]byte, 8)
hasher := hashPool.Get().(hash.Hash64)
defer hashPool.Put(hasher)

for _, s := range series {
for _, chk := range s.GetSeries().Chunks {
hasher.Reset()
for _, field := range []*storepb.Chunk{
chk.Raw, chk.Count, chk.Max, chk.Min, chk.Sum, chk.Counter,
} {
if field == nil {
continue
}
hash := field.Hash
if hash == 0 {
hash = xxhash.Sum64(field.Data)
}

if _, ok := chunkDedupMap[hash]; !ok {
chk := chk
chunkDedupMap[hash] = &chk
break
switch {
case field == nil:
binary.BigEndian.PutUint64(buf, 0)
case field.Hash != 0:
binary.BigEndian.PutUint64(buf, field.Hash)
default:
binary.BigEndian.PutUint64(buf, xxhash.Sum64(field.Data))
}
_, _ = hasher.Write(buf)
}
aggrChunkHash := hasher.Sum64()
Copy link
Contributor

@eharcevs eharcevs Aug 28, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do I get it right, that this actually calculates a hash of hashes of all the fields?
I wonder how it differs from calculating the hash of all the fields data in terms of possible hash collisions...

Copy link
Contributor Author

@MichaHoffmann MichaHoffmann Aug 28, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Its the hash of field hashes ( mainly to reuse the field.Hash ).

if _, ok := chunkDedupMap[aggrChunkHash]; !ok {
chk := chk
chunkDedupMap[aggrChunkHash] = &chk
}
}
}
Expand Down
49 changes: 49 additions & 0 deletions pkg/store/proxy_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2197,6 +2197,55 @@ func TestDedupRespHeap_Deduplication(t *testing.T) {
testFn func(responses []*storepb.SeriesResponse, h *dedupResponseHeap)
tname string
}{
{
tname: "dedups identical series with multiple chunks",
responses: []*storepb.SeriesResponse{
{
Result: &storepb.SeriesResponse_Series{
Series: &storepb.Series{
Labels: labelpb.ZLabelsFromPromLabels(labels.FromStrings("foo", "bar")),
Chunks: []storepb.AggrChunk{
{
Count: &storepb.Chunk{
Type: storepb.Chunk_XOR,
Data: []byte(`count`),
},
Sum: &storepb.Chunk{
Type: storepb.Chunk_XOR,
Data: []byte(`sum`),
},
},
},
},
},
},
{
Result: &storepb.SeriesResponse_Series{
Series: &storepb.Series{
Labels: labelpb.ZLabelsFromPromLabels(labels.FromStrings("foo", "bar")),
Chunks: []storepb.AggrChunk{
{
Count: &storepb.Chunk{
Type: storepb.Chunk_XOR,
Data: []byte(`count`),
},
Sum: &storepb.Chunk{
Type: storepb.Chunk_XOR,
Data: []byte(`sum`),
},
},
},
},
},
},
},
testFn: func(responses []*storepb.SeriesResponse, h *dedupResponseHeap) {
testutil.Equals(t, true, h.Next())
resp := h.At()
testutil.Equals(t, responses[0], resp)
testutil.Equals(t, false, h.Next())
},
},
{
tname: "edge case with zero responses",
responses: []*storepb.SeriesResponse{},
Expand Down