Skip to content
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

Jump to bottom

Add series population to tokenizer #11070

Merged
merged 3 commits into from
Nov 1, 2023
Merged

Add series population to tokenizer #11070

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
b9701f9
Add series population to tokenizer
poyzannur Oct 27, 2023
91f6737
Update testing lib to use new function signature
paul1r Oct 27, 2023
29ba897
Merge branch 'main' into poyzannur/change-tokenizer-to-work-with-seri…
poyzannur Nov 1, 2023
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
18 changes: 14 additions & 4 deletions pkg/storage/bloom/v1/bloom_tokenizer.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@ import (
"github.com/grafana/loki/pkg/chunkenc"
"github.com/grafana/loki/pkg/logproto"
"github.com/grafana/loki/pkg/logql/log"
"github.com/grafana/loki/pkg/storage/bloom/v1/filter"
"github.com/grafana/loki/pkg/storage/chunk"
util_log "github.com/grafana/loki/pkg/util/log"
//"github.com/grafana/loki/tools/tsdb/helpers"
Expand Down Expand Up @@ -69,20 +68,26 @@ func clearCache(cache map[string]interface{}) {
}
}

func (bt *BloomTokenizer) PopulateSBF(sbf *filter.ScalableBloomFilter, chunks []chunk.Chunk) {
func (bt *BloomTokenizer) PopulateSeriesWithBloom(seriesWithBloom *SeriesWithBloom, chunks []chunk.Chunk) {
clearCache(bt.cache)
for idx := range chunks {
lc := chunks[idx].Data.(*chunkenc.Facade).LokiChunk()
bt.chunkIDTokenizer.Reinit(chunks[idx].ChunkRef)

// TODO: error handling
itr, _ := lc.Iterator(
itr, err := lc.Iterator(
context.Background(),
time.Unix(0, 0), // TODO: Parameterize/better handle the timestamps?
time.Unix(0, math.MaxInt64),
logproto.FORWARD,
log.NewNoopPipeline().ForStream(chunks[idx].Metric),
)
if err != nil {
level.Info(util_log.Logger).Log("chunk iterator cannot be created")
return
}

defer itr.Close()

for itr.Next() && itr.Error() == nil {
toks := bt.chunkIDTokenizer.Tokens(itr.Entry().Line)
Expand All @@ -94,7 +99,7 @@ func (bt *BloomTokenizer) PopulateSBF(sbf *filter.ScalableBloomFilter, chunks []
if !found {
bt.cache[str] = nil

sbf.TestAndAdd(tok.Key)
seriesWithBloom.Bloom.ScalableBloomFilter.TestAndAdd(tok.Key)

if len(bt.cache) > 150000 { // While crude, this has proven efficient in performance testing. This speaks to the similarity in log lines near each other
clearCache(bt.cache)
Expand All @@ -103,6 +108,11 @@ func (bt *BloomTokenizer) PopulateSBF(sbf *filter.ScalableBloomFilter, chunks []
}
}
}
seriesWithBloom.Series.Chunks = append(seriesWithBloom.Series.Chunks, ChunkRef{
Start: chunks[idx].From,
End: chunks[idx].Through,
Checksum: chunks[idx].Checksum,
})
} // for each chunk
}

Expand Down
14 changes: 12 additions & 2 deletions tools/tsdb/bloom-tester/lib.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -350,7 +350,17 @@ func analyze(metrics *Metrics, sampler Sampler, indexShipper indexshipper.IndexS
startTime := time.Now().UnixMilli()

sbf := experiment.bloom()
bloomTokenizer.PopulateSBF(sbf, got)
bloom := bt.Bloom{
ScalableBloomFilter: *sbf,
}
series := bt.Series{
Fingerprint: fp,
}
swb := bt.SeriesWithBloom{
Bloom: &bloom,
Series: &series,
}
bloomTokenizer.PopulateSeriesWithBloom(&swb, got)

endTime := time.Now().UnixMilli()
if len(got) > 0 {
Expand All @@ -361,7 +371,7 @@ func analyze(metrics *Metrics, sampler Sampler, indexShipper indexshipper.IndexS
float64(estimatedCount(sbf.Capacity(), sbf.FillRatio())),
)

writeSBF(sbf,
writeSBF(&swb.Bloom.ScalableBloomFilter,
os.Getenv("DIR"),
fmt.Sprint(bucketPrefix, experiment.name),
os.Getenv("BUCKET"),
Expand Down
Loading