capacity
The most work a component or fleet can handle while still meeting its latency target.
In more detail
Capacity should be measured, not guessed, and measured at the latency target rather than at the point of collapse. Capacity for stateless throughput can be added in seconds, while capacity for stored state needs copying and catching up first.
Related terms
- per node capacity — The throughput one server or node sustains while staying inside its latency target, found by a load test.
- headroom — Capacity kept free above the expected peak, so the system survives deployments, spikes and failures.
- capacity planning — Estimating how much computing capacity a system will need and when, so it is there before the load arrives.
- utilization — The fraction of time a resource is busy.
Taught in
- Back Of The Envelope Estimation: Traffic And Throughput — Scalable System Design & Distributed Architecture
- Back Of The Envelope Estimation: Storage And Bandwidth — Scalable System Design & Distributed Architecture
- The Storage Decision: Relational Versus Document — Scalable System Design & Distributed Architecture
- Partitioning, Sharding And Hot Keys — Scalable System Design & Distributed Architecture
- Queues, Events And Asynchronous Work — Scalable System Design & Distributed Architecture
- Load Balancing And The Failure Modes It Introduces — Scalable System Design & Distributed Architecture
- Timeouts, And Avoiding Cascaded Failure — Scalable System Design & Distributed Architecture
- Circuit Breakers — Scalable System Design & Distributed Architecture
- Backpressure And Load Shedding — Scalable System Design & Distributed Architecture
- Monolith Versus Services: The Honest Trade Offs — Scalable System Design & Distributed Architecture
- Capacity Planning As A Design Input — Scalable System Design & Distributed Architecture
- Worked Design One: Scaling The Ticket Booking System — Scalable System Design & Distributed Architecture
- Worked Design Two: Scaling Chat Fan Out — Scalable System Design & Distributed Architecture
- Worked Design Three: A Metrics Ingestion Pipeline — Scalable System Design & Distributed Architecture
- Worked Design Three: Scaling The Metrics Pipeline — Scalable System Design & Distributed Architecture