rocksdb-write-stall · shipping · also write stall (RocksDB)

RocksDB write stall

A RocksDB write stall is backpressure that delays or stops foreground writes when configured resource or background-work limits are reached.

The project uses stall for both slowdown and full stop; it does not mean a device has failed. A trigger in one column family can affect writes across that database. [1] The v10.10.1 decision code evaluates stop conditions before slowdown conditions, and disabling automatic compactions bypasses its L0 and pending-compaction triggers but not its memtable triggers. [2] WriteOptions::no_slowdown can return Incomplete for a recognized stall; it does not make the entire write path nonblocking. [3]

Relations

related

rocksdb-write-slowdown, pending-compaction-bytes, rocksdb-column-family, memtable, compaction, rocksdb-write-buffer-manager

Citations

1. RocksDB project. Write Stalls: causes, scope and admission behavior. (accessed 2026-10-15)
2. RocksDB v10.10.1. ColumnFamilyData::GetWriteStallConditionAndCause. (accessed 2026-10-15)
3. RocksDB v10.10.1. DelayWrite and write preprocessing. (accessed 2026-10-15)
4. RocksDB: a WAL sync is not a memtable flush; write backpressure boundaries. (accessed 2026-10-15)

JSON: /data/terms/rocksdb-write-stall.json