Debugging ClickHouse lock contention at petabyte scale

A Cloudflare billing outage traced to ClickHouse query-planner lock contention produced upstream patches for a petabyte-scale cluster

When a partitioning change to our petabyte-scale ClickHouse cluster caused critical billing jobs to stall, standard metrics showed no obvious errors. Here's how we identified severe lock contention in ClickHouse's query planner and built up

Ranked #1 on backlist 2026-05-14 (14 May 2026 UTC) · by @Cloudflare · view on X ↗

How it ranks: Backlist reads my Twitter/X timeline, scores every tweet for substance with an LLM rubric (not engagement), and publishes the daily top picks with a one-line takeaway. Curated by Surya Dantuluri.