mirror of
https://github.com/prometheus/prometheus.git
synced 2024-12-26 06:04:05 -08:00
c5b3f0221f
* Make WAL replay benchmark more representative Signed-off-by: Chris Marchbanks <csmarchbanks@gmail.com> * Move decoding records from the WAL into goroutine Decoding the WAL records accounts for a significant amount of time on startup, and can be done in parallel with creating series/samples to speed up startup. However, records still must be handled in order, so only a single goroutine can do the decoding. benchmark old ns/op new ns/op delta BenchmarkLoadWAL/batches=10,seriesPerBatch=100,samplesPerSeries=7200-8 481607033 391971490 -18.61% BenchmarkLoadWAL/batches=10,seriesPerBatch=10000,samplesPerSeries=50-8 836394378 629067006 -24.79% BenchmarkLoadWAL/batches=10,seriesPerBatch=1000,samplesPerSeries=480-8 348238658 234218667 -32.74% Signed-off-by: Chris Marchbanks <csmarchbanks@gmail.com> |
||
|---|---|---|
| .. | ||
| chunkenc | ||
| chunks | ||
| cmd/tsdb | ||
| docs/format | ||
| encoding | ||
| errors | ||
| fileutil | ||
| goversion | ||
| index | ||
| labels | ||
| record | ||
| test | ||
| testdata | ||
| tombstones | ||
| tsdbutil | ||
| wal | ||
| .gitignore | ||
| block.go | ||
| block_test.go | ||
| CHANGELOG.md | ||
| compact.go | ||
| compact_test.go | ||
| db.go | ||
| db_test.go | ||
| head.go | ||
| head_bench_test.go | ||
| head_test.go | ||
| mocks_test.go | ||
| querier.go | ||
| querier_test.go | ||
| README.md | ||
| repair.go | ||
| repair_test.go | ||
| wal.go | ||
| wal_test.go | ||
TSDB
This repository contains the Prometheus storage layer that is used in its 2.x releases.
A writeup of its design can be found here.
Based on the Gorilla TSDB white papers.
Video: Storing 16 Bytes at Scale from PromCon 2017.
See also the format documentation.