Principles for Fast Tokio Applications

Automated excerpt

Beware global resources The Tokio runtime schedules work on workers: dedicated threads that poll ready tasks. You rarely need every core for Tokio, and reserving cores for other work tends to improve latency. In both cases, stealing work takes longer. Many network services have both latency-sensitive work and lower-priority background work. Tokio runs N workers, usually one per available core.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.