PlanetScale architecture: how PlanetScale scaled (2 case studies)
We track 2 public engineering write-ups by PlanetScale, published between 2022 and 2026. Techniques that come up more than once: benchmarking (2) and horizontal sharding (2). Stack mentioned: AWS r8g.16xlarge, MySQL, Neki, PostgreSQL and Vitess. 2 of the 2 state concrete scale numbers, for example "118.5M QPS sustained for 16 minutes". Each card below links to our short summary and the original post.
118 million queries per second on Neki
PlanetScale benchmarked Neki, its sharded Postgres, with single-shard primary-key point selects. Targeting about 200K QPS per shard, it went from 5 shards (about 1M QPS) to 50 (9.9M QPS, per-shard rate within 0.8%) to 512 shards and 480 routers, sustaining 118.5M QPS for 16 minutes over 1.22 PiB with a p99 of 6.06 ms at the router and about one error per 1.8 million queries. PlanetScale notes the run was read-only, primary-only with no replicas, and had no failover during the measured window.
One million queries per second with MySQL
PlanetScale benchmarked a horizontally sharded Vitess cluster up to one million QPS.