clickhouse
https://github.com/yandex/clickhouse
C++
ClickHouse is a free analytic DBMS for big data.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
C++ not yet supported66 Subscribers
Add a CodeTriage badge to clickhouse
Help out
- Issues
- Bump `mariadb-connector-c` from v3.4.10 to v3.4.11
- Bump `librdkafka` from 2.15.1 to 2.16.0
- Query condition cache: keep the rows a PREWHERE selects, so a repeated query does not evaluate the condition again (repeated ClickBench Q41 -36%, Q40 -36%, Q42 -30%, Q38 -24%, Q30 -22%)
- Iceberg REST catalog tables load their whole snapshot history on every query, costing about 150-330 ms per query at 10,000 snapshots
- COUNT(DISTINCT) with GROUP BY over few groups: deduplicate the (key, value) pairs by radix partitioning, also next to other aggregates (ClickBench Q8 -38%, Q9 -24% over current master)
- Improve PREWHERE reordering on compact parts
- Migrate from `SimSIMD` to `NumKong`
- `DeltaLake` table keeps one object storage connection per `_delta_log` commit in each cached snapshot, so connections grow linearly with `INSERT`s
- Read Parquet files with data pages that have no values
- Add `snapshot_loading_mode` to load only referenced snapshots from Iceberg REST catalogs
- Docs
- C++ not yet supported