-
Notifications
You must be signed in to change notification settings - Fork 127
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fix: forward bench feature to test-fixtures crate #2201
Conversation
Previously `neqo-bin`, `neqo-transport` and `test-fixtures` would each define a `bench` feature. But enabling e.g. `bench` in `neqo-transport` would not enable `bench` in `test-fixtures`. Thus a benchmark in e.g. `neqo-transport` with `--features bench` would still be serializing qlog traces. This commit makes `neqo-bin` and `neqo-transport` forward their `bench` feature to `test-fixtures`.
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #2201 +/- ##
==========================================
- Coverage 95.39% 95.39% -0.01%
==========================================
Files 112 112
Lines 36447 36447
==========================================
- Hits 34768 34767 -1
- Misses 1679 1680 +1 ☔ View full report in Codecov by Sentry. |
Failed Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
All resultsSucceeded Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
Unsupported Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
|
Benchmark resultsPerformance differences relative to 67d5e7f. coalesce_acked_from_zero 1+1 entries: No change in performance detected.time: [98.981 ns 99.339 ns 99.740 ns] change: [-0.8757% -0.1824% +0.5352%] (p = 0.62 > 0.05) coalesce_acked_from_zero 3+1 entries: No change in performance detected.time: [116.92 ns 117.21 ns 117.55 ns] change: [-0.3735% -0.0175% +0.3178%] (p = 0.93 > 0.05) coalesce_acked_from_zero 10+1 entries: No change in performance detected.time: [116.73 ns 117.15 ns 117.65 ns] change: [-1.6623% -0.5590% +0.2241%] (p = 0.30 > 0.05) coalesce_acked_from_zero 1000+1 entries: No change in performance detected.time: [96.923 ns 97.072 ns 97.231 ns] change: [-1.3879% -0.5188% +0.3452%] (p = 0.25 > 0.05) RxStreamOrderer::inbound_frame(): Change within noise threshold.time: [111.53 ms 111.58 ms 111.64 ms] change: [-0.2660% -0.1857% -0.1088%] (p = 0.00 < 0.05) transfer/pacing-false/varying-seeds: No change in performance detected.time: [26.035 ms 26.982 ms 27.935 ms] change: [-8.8189% -3.9917% +0.9586%] (p = 0.12 > 0.05) transfer/pacing-true/varying-seeds: No change in performance detected.time: [36.274 ms 37.954 ms 39.645 ms] change: [-2.7305% +3.7705% +11.186%] (p = 0.28 > 0.05) transfer/pacing-false/same-seed: No change in performance detected.time: [26.122 ms 26.845 ms 27.576 ms] change: [-5.2476% -1.0531% +3.0684%] (p = 0.62 > 0.05) transfer/pacing-true/same-seed: No change in performance detected.time: [41.967 ms 44.049 ms 46.189 ms] change: [-8.6813% -2.0707% +4.3455%] (p = 0.56 > 0.05) 1-conn/1-100mb-resp/mtu-1500 (aka. Download)/client: 💚 Performance has improved.time: [865.37 ms 874.01 ms 882.88 ms] thrpt: [113.27 MiB/s 114.41 MiB/s 115.56 MiB/s] change: time: [-6.2488% -5.0093% -3.7593%] (p = 0.00 < 0.05) thrpt: [+3.9062% +5.2735% +6.6653%] 1-conn/10_000-parallel-1b-resp/mtu-1500 (aka. RPS)/client: No change in performance detected.time: [318.50 ms 321.37 ms 324.26 ms] thrpt: [30.839 Kelem/s 31.117 Kelem/s 31.397 Kelem/s] change: time: [-1.7032% -0.4378% +0.8317%] (p = 0.50 > 0.05) thrpt: [-0.8248% +0.4398% +1.7328%] 1-conn/1-1b-resp/mtu-1500 (aka. HPS)/client: No change in performance detected.time: [33.632 ms 33.798 ms 33.973 ms] thrpt: [29.435 elem/s 29.588 elem/s 29.734 elem/s] change: time: [-1.2767% -0.5763% +0.1168%] (p = 0.10 > 0.05) thrpt: [-0.1166% +0.5796% +1.2932%] 1-conn/1-100mb-resp/mtu-1500 (aka. Upload)/client: 💚 Performance has improved.time: [1.7787 s 1.7959 s 1.8132 s] thrpt: [55.150 MiB/s 55.681 MiB/s 56.221 MiB/s] change: time: [-4.1301% -2.8167% -1.4711%] (p = 0.00 < 0.05) thrpt: [+1.4931% +2.8983% +4.3080%] 1-conn/1-100mb-resp/mtu-65536 (aka. Download)/client: Change within noise threshold.time: [110.46 ms 110.73 ms 111.00 ms] thrpt: [900.88 MiB/s 903.08 MiB/s 905.28 MiB/s] change: time: [+0.3403% +0.6758% +1.0115%] (p = 0.00 < 0.05) thrpt: [-1.0014% -0.6712% -0.3391%] 1-conn/10_000-parallel-1b-resp/mtu-65536 (aka. RPS)/client: No change in performance detected.time: [311.10 ms 314.22 ms 317.38 ms] thrpt: [31.508 Kelem/s 31.825 Kelem/s 32.144 Kelem/s] change: time: [-2.0101% -0.5380% +0.9964%] (p = 0.48 > 0.05) thrpt: [-0.9866% +0.5409% +2.0514%] 1-conn/1-1b-resp/mtu-65536 (aka. HPS)/client: 💔 Performance has regressed.time: [34.424 ms 34.643 ms 34.881 ms] thrpt: [28.669 elem/s 28.866 elem/s 29.050 elem/s] change: time: [+1.3987% +2.3460% +3.2391%] (p = 0.00 < 0.05) thrpt: [-3.1375% -2.2922% -1.3794%] 1-conn/1-100mb-resp/mtu-65536 (aka. Upload)/client: No change in performance detected.time: [279.48 ms 315.37 ms 366.98 ms] thrpt: [272.49 MiB/s 317.09 MiB/s 357.81 MiB/s] change: time: [-8.8512% +8.1858% +30.009%] (p = 0.43 > 0.05) thrpt: [-23.082% -7.5664% +9.7107%] Client/server transfer resultsTransfer of 33554432 bytes over loopback.
|
Previously
neqo-bin
,neqo-transport
andtest-fixtures
would each define abench
feature. But enabling e.g.bench
inneqo-transport
would not enablebench
intest-fixtures
. Thus a benchmark in e.g.neqo-transport
with--features bench
would still be serializing qlog traces.This commit makes
neqo-bin
andneqo-transport
forward theirbench
feature totest-fixtures
.