f2064c7987
promql, tsdb (histograms): Do not re-use spans between histograms When multiple points exist with the same native histogram schemas they share their spans. This causes a problem when a native histogram (NH) schema is modified (for example, during a Sum) then the other NH's with the same spans are also modified. As such, we should create a new Span for each NH. This will ensure NH's interfaces are safe to use without considering the effect on other histograms. At the moment this doesn't present itself as a problem because in all aggregations and functions operating on native histograms they are copied by the promql query engine first. Signed-off-by: Joshua Hesketh <josh@nitrotech.org> --------- Signed-off-by: Joshua Hesketh <josh@nitrotech.org> |
||
|---|---|---|
| .. | ||
| agent | ||
| chunkenc | ||
| chunks | ||
| docs | ||
| encoding | ||
| errors | ||
| fileutil | ||
| goversion | ||
| index | ||
| record | ||
| testdata | ||
| tombstones | ||
| tsdbutil | ||
| wlog | ||
| .gitignore | ||
| CHANGELOG.md | ||
| README.md | ||
| block.go | ||
| block_test.go | ||
| blockwriter.go | ||
| blockwriter_test.go | ||
| compact.go | ||
| compact_test.go | ||
| db.go | ||
| db_test.go | ||
| example_test.go | ||
| exemplar.go | ||
| exemplar_test.go | ||
| head.go | ||
| head_append.go | ||
| head_bench_test.go | ||
| head_dedupelabels.go | ||
| head_other.go | ||
| head_read.go | ||
| head_read_test.go | ||
| head_test.go | ||
| head_wal.go | ||
| isolation.go | ||
| isolation_test.go | ||
| mocks_test.go | ||
| ooo_head.go | ||
| ooo_head_read.go | ||
| ooo_head_read_test.go | ||
| ooo_head_test.go | ||
| ooo_isolation.go | ||
| ooo_isolation_test.go | ||
| querier.go | ||
| querier_bench_test.go | ||
| querier_test.go | ||
| repair.go | ||
| repair_test.go | ||
| testutil.go | ||
| tsdbblockutil.go | ||
README.md
TSDB
This directory contains the Prometheus TSDB (Time Series DataBase) library, which handles storage and querying of all Prometheus v2 data.
Documentation
External resources
- A writeup of the original design can be found here.
- Video: Storing 16 Bytes at Scale from PromCon 2017.
- Compression is based on the Gorilla TSDB white paper.
A series of blog posts explaining different components of TSDB: