How the ClickHouse Log Engine Stores Rows in Append-Only Files with a Marks Index
Log stores one .bin per column stream plus a __marks.mrk file of (rows, offset) pairs, and truncates files back to a recorded size after a crash.
Posts
All posts published on this site.
Everything published here, newest first.
ClickHouse Batches Distributed Inserts into Files on Disk
ClickHouse turns a Distributed INSERT into files on disk and ships them in the background.
ClickHouse Buffers I/O with a pos()/end() Invariant
ClickHouse replaces iostreams with ReadBuffer/WriteBuffer: one cursor, one virtual refill, and a memcpy fast path.
ClickHouse Caches Remote Objects as Local File Segments
ClickHouse’s filesystem cache stores remote objects as size-encoded local segment files ordered by an in-memory LRU.
ClickHouse Compiles a Date Format String into a Program
formatDateTime compiles its format string into an instruction vector and a byte template.