mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-07 05:22:56 +00:00
9da67c4f19
Stacked atop https://github.com/neondatabase/neon/pull/5557 Prep work for https://github.com/neondatabase/neon/pull/5560 These changes have a 2% impact on `bench_walredo`. That's likely because of the `block_on() in the innermost piece of benchmark-only code. So, it doesn't affect production code. The use of closures in the benchmarking code prevents a straightforward conversion of the whole benchmarking code to async. before: ``` $ cargo bench --features testing --bench bench_walredo Compiling pageserver v0.1.0 (/home/cs/src/neon/pageserver) Finished bench [optimized + debuginfo] target(s) in 2m 11s Running benches/bench_walredo.rs (target/release/deps/bench_walredo-d99a324337dead70) Gnuplot not found, using plotters backend short/short/1 time: [26.363 µs 27.451 µs 28.573 µs] Found 1 outliers among 100 measurements (1.00%) 1 (1.00%) high mild short/short/2 time: [64.340 µs 64.927 µs 65.485 µs] Found 2 outliers among 100 measurements (2.00%) 2 (2.00%) low mild short/short/4 time: [101.98 µs 104.06 µs 106.13 µs] short/short/8 time: [151.42 µs 152.74 µs 154.03 µs] short/short/16 time: [296.30 µs 297.53 µs 298.88 µs] Found 14 outliers among 100 measurements (14.00%) 10 (10.00%) high mild 4 (4.00%) high severe medium/medium/1 time: [225.12 µs 225.90 µs 226.66 µs] Found 1 outliers among 100 measurements (1.00%) 1 (1.00%) low mild medium/medium/2 time: [490.80 µs 491.64 µs 492.49 µs] Found 1 outliers among 100 measurements (1.00%) 1 (1.00%) low mild medium/medium/4 time: [934.47 µs 936.49 µs 938.52 µs] Found 5 outliers among 100 measurements (5.00%) 3 (3.00%) low mild 1 (1.00%) high mild 1 (1.00%) high severe medium/medium/8 time: [1.8364 ms 1.8412 ms 1.8463 ms] Found 4 outliers among 100 measurements (4.00%) 4 (4.00%) high mild medium/medium/16 time: [3.6694 ms 3.6896 ms 3.7104 ms] ``` after: ``` $ cargo bench --features testing --bench bench_walredo Compiling pageserver v0.1.0 (/home/cs/src/neon/pageserver) Finished bench [optimized + debuginfo] target(s) in 2m 11s Running benches/bench_walredo.rs (target/release/deps/bench_walredo-d99a324337dead70) Gnuplot not found, using plotters backend short/short/1 time: [28.345 µs 28.529 µs 28.699 µs] change: [-0.2201% +3.9276% +8.2451%] (p = 0.07 > 0.05) No change in performance detected. Found 17 outliers among 100 measurements (17.00%) 4 (4.00%) low severe 5 (5.00%) high mild 8 (8.00%) high severe short/short/2 time: [66.145 µs 66.719 µs 67.274 µs] change: [+1.5467% +2.7605% +3.9927%] (p = 0.00 < 0.05) Performance has regressed. Found 5 outliers among 100 measurements (5.00%) 5 (5.00%) low mild short/short/4 time: [105.51 µs 107.52 µs 109.49 µs] change: [+0.5023% +3.3196% +6.1986%] (p = 0.02 < 0.05) Change within noise threshold. short/short/8 time: [151.90 µs 153.16 µs 154.41 µs] change: [-1.0001% +0.2779% +1.4221%] (p = 0.65 > 0.05) No change in performance detected. short/short/16 time: [297.38 µs 298.26 µs 299.20 µs] change: [-0.2953% +0.2462% +0.7763%] (p = 0.37 > 0.05) No change in performance detected. Found 2 outliers among 100 measurements (2.00%) 2 (2.00%) high mild medium/medium/1 time: [229.76 µs 230.72 µs 231.69 µs] change: [+1.5804% +2.1354% +2.6635%] (p = 0.00 < 0.05) Performance has regressed. medium/medium/2 time: [501.14 µs 502.31 µs 503.64 µs] change: [+1.8730% +2.1709% +2.5199%] (p = 0.00 < 0.05) Performance has regressed. Found 7 outliers among 100 measurements (7.00%) 1 (1.00%) low mild 1 (1.00%) high mild 5 (5.00%) high severe medium/medium/4 time: [954.15 µs 956.74 µs 959.33 µs] change: [+1.7962% +2.1627% +2.4905%] (p = 0.00 < 0.05) Performance has regressed. medium/medium/8 time: [1.8726 ms 1.8785 ms 1.8848 ms] change: [+1.5858% +2.0240% +2.4626%] (p = 0.00 < 0.05) Performance has regressed. Found 6 outliers among 100 measurements (6.00%) 1 (1.00%) low mild 3 (3.00%) high mild 2 (2.00%) high severe medium/medium/16 time: [3.7565 ms 3.7746 ms 3.7934 ms] change: [+1.5503% +2.3044% +3.0818%] (p = 0.00 < 0.05) Performance has regressed. Found 3 outliers among 100 measurements (3.00%) 3 (3.00%) high mild ```