Glossary

Cold start (serverless)

A cold start is the extra initialisation latency incurred when a serverless function is invoked on a new execution environment that must be provisioned from scratch. The runtime must download the package, start the language runtime, run initialisation code, and establish connections — all before handling the first request. Cold starts are invisible in load tests that keep functions warm, but appear as severe outliers in production latency distributions.

Formula: Typical: Node/Python 100–300 ms; JVM without SnapStart 500 ms–2 s; Go 50–150 ms (order-of-magnitude).

Last updated: March 2026