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
- `mapValues` `bloom_filter` throws `BAD_GET`: constant not cast to value type
- Parquet over S3 at default settings waits a full round trip for each separately read row group; reading the next one ahead makes ClickBench S3 queries 20-27% faster
- Parquet: per-value PREWHERE on a dictionary column scans and renumbers all indexes of every block to drop unused values; marking them while decoding makes ClickBench Q11 and Q12 13-16% faster
- MergeTree index analysis builds a condition for every skip index on each filtered query: skip indexes the filter does not read (ClickBench Q41 -33%, Q42 -29% with min-max indexes on all numeric and date columns)
- Report a missing file instead of an unknown table for a URL database
- Do not build the conditions of minmax skip indexes the filter cannot use
- Parquet and Iceberg reads run JOIN runtime filters after weak PREWHERE conditions; running the more selective one first makes TPC-DS q37 and q82 2.1-2.3x faster
- Iceberg: struct subcolumn `st.x` fails with `NOT_FOUND_COLUMN_IN_BLOCK` on data files written before any schema change
- Bump `StringZilla` from v5.0.5 to v5.3.2
- Show hardware counters for changed queries in the perf report
- Docs
- C++ not yet supported