ClickHouse Skips Data: Granules, Marks, and Bit-Packed Indexes
A MergeTree scan isn’t a full scan. Parts are cut into granules, each granule gets a bit-packed mark, and the primary key index stores one key value per granule — so…
Posts
All posts published on this site.
Everything published here, newest first.
ClickHouse Sorts in Parallel: Partial Sort, Merge Sorted Streams and External Sort
ClickHouse never sorts the whole dataset at once. It sorts each chunk, throws away rows that can’t make the top-N, merges the sorted streams, and spills runs to disk when…
ClickHouse Splits GROUP BY into 256 Buckets for Parallel Merges
A GROUP BY needs a serial merge at the end — and that’s where the memory high-water mark lives.
ClickHouse's LowCardinality Column Shares One Dictionary Across Millions of Rows
LowCardinality(T) stores a dictionary of distinct values once and keeps a 1–8 byte index per row.
ClickHouse's Query Condition Cache: Skip Granules You Don't Need to Read
ClickHouse caches the granules a predicate emptied, so a dashboard that runs the same query every 30 seconds stops paying for index analysis and skipped data.