Versioned performance evidence

Rust edge performance you can audit before sizing servers.

Immutable benchmark snapshots tie every published result to a Webship release, test environment, and measurement date.

Benchmark version

Webship 1.1.0Current

Measured August 23, 2026. This URL is pinned to an immutable benchmark snapshot.

Test platform
Debian GNU/Linux 12 · Intel Xeon Gold 5115
Accepted samples
5 × at least 20 seconds
Reported unit
Median requests per second

This 1.1.0 snapshot contains Webship-only measurements; use 1.0.0 for the retained contemporaneous competitor comparison. Reverse H1 TLS uses a 4/3/3 frontend/origin/client physical-core partition because the standard 4/4/2 run saturated its two-core TLS client. Other reverse TCP/TLS protocols use 4/4/2, and H3 uses 4/2/4.

Direct static response

Median requests per second. Higher is better.

ServerHTTP/1.1HTTP/1.1 TLSh2cHTTP/2 TLSHTTP/3 TLS
Webship415,735.58312,069.331,041,848.3937,318.6307,727

Reverse proxy

Median requests per second. Higher is better.

ServerHTTP/1.1HTTP/1.1 TLSh2cHTTP/2 TLSHTTP/3 TLS
Webship164,919.51120,834.25127,965.65112,687.298,897

Reproducible method

Each supported result is the median of five accepted samples. TCP and TLS workloads include warm-up; HTTP/3 includes a calibrated prime.

Server and load-generator processes ran on disjoint physical cores. Reverse-proxy runs also isolated the static origin.

Every accepted sample passed zero-error correctness gates and the published stability limits. Failed samples are never silently included.

A published snapshot is immutable. New Webship releases receive new benchmark versions instead of replacing historical results.