Concurrency vs. Throughput: why more parallelism can make databases slower

T1Covered by 1 source · first reported by Databricks / ClickHouse / DuckDB / Supabase / Neon / PlanetScale at 07 Aug, 00:00 UTC

Increasing throughput sometimes requires reducing parallelism. A look into why this is the case for Vitess + MySQL databases

Sources

• T1Concurrency vs. Throughput: why more parallelism can make databases slowerDatabricks / ClickHouse / DuckDB / Supabase / Neon / PlanetScale07 Aug, 00:00