ClickHouse Aggregates In Order and Stops Reading Early
If your table is sorted by the GROUP BY key, ClickHouse can skip the hash table entirely: it counts each contiguous run of equal keys and emits it.
Performance
ClickHouse Decides Which Parts to Merge: A Cost Model for Write Amplification
ClickHouse picks merge candidates with a tiny, explicit cost model: score each contiguous range as sum_size / (count - 1.9), pick the cheapest admissible one, and only ever…
ClickHouse Evaluates IN with Hash Sets: Build Once, Probe Once Per Row
ClickHouse picks one of thirteen hash-table shapes for IN based on the key type, then spills the set to disk behind per-block Bloom filters when it outgrows RAM.
ClickHouse JIT-Compiles Scalar Expressions with LLVM
ClickHouse compiles hot scalar expressions to native code with LLVM.
ClickHouse Marks Empty Hash Table Cells With Zeroed Memory
ClickHouse’s hash table has no occupancy bit, no tombstone, and no sentinel pointer.