This article explains why a tenant in OceanBase may experience frequent mini compactions, shows how to locate the responsible DML statements by querying merge info and tablet IDs, demonstrates the process with test tables, and provides conclusions and references for further investigation.
This article explains how to verify whether OceanBase's freeze mechanism and memstore dump processes are functioning correctly by querying internal tables, inspecting logs, and checking related metrics such as active_memstore_used, major_freeze_trigger, and MemTable reference counts.
This article presents a detailed performance test of HBase 2.x write throughput on a five‑node SSD cluster, identifies latency spikes caused by MemStore flush and ConcurrentSkipListMap size() overhead, and demonstrates how fixing the bug and applying in‑memory compaction dramatically reduces P999 and P9999 latency while preserving throughput.
The article systematically explains how HBase's MemStore uses a SkipList‑based model and introduces successive memory‑management optimizations—MemStoreLAB, ChunkPool, off‑heap chunks, CompactingMemStore and the CCSMap data structure—to reduce object overhead, GC pressure and improve throughput.
