Skip to content
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

ci: Try and speed up QNS docker build #2092

Merged
merged 2 commits into from
Sep 9, 2024

Conversation

larseggert
Copy link
Collaborator

Copy link

github-actions bot commented Sep 6, 2024

Firefox builds for this PR

The following builds are available for testing. Crossed-out builds did not succeed.

@larseggert larseggert marked this pull request as ready for review September 6, 2024 13:41
Copy link

github-actions bot commented Sep 6, 2024

Failed Interop Tests

QUIC Interop Runner, client vs. server

neqo-latest as client

neqo-latest as server

All results

Succeeded Interop Tests

QUIC Interop Runner, client vs. server

neqo-latest as client

neqo-latest as server

Unsupported Interop Tests

QUIC Interop Runner, client vs. server

neqo-latest as client

neqo-latest as server

Copy link

codecov bot commented Sep 6, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 95.30%. Comparing base (28f60bd) to head (60910da).
Report is 2 commits behind head on main.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #2092      +/-   ##
==========================================
- Coverage   95.36%   95.30%   -0.07%     
==========================================
  Files         112      112              
  Lines       36559    36300     -259     
==========================================
- Hits        34866    34596     -270     
- Misses       1693     1704      +11     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Copy link

github-actions bot commented Sep 9, 2024

Benchmark results

Performance differences relative to 28f60bd.

coalesce_acked_from_zero 1+1 entries: No change in performance detected.
       time:   [99.501 ns 99.825 ns 100.15 ns]
       change: [-0.0318% +0.9025% +2.0566%] (p = 0.08 > 0.05)

Found 13 outliers among 100 measurements (13.00%)
8 (8.00%) high mild
5 (5.00%) high severe

coalesce_acked_from_zero 3+1 entries: Change within noise threshold.
       time:   [117.55 ns 117.86 ns 118.21 ns]
       change: [+0.0609% +0.5464% +1.0336%] (p = 0.03 < 0.05)

Found 15 outliers among 100 measurements (15.00%)
2 (2.00%) low mild
1 (1.00%) high mild
12 (12.00%) high severe

coalesce_acked_from_zero 10+1 entries: No change in performance detected.
       time:   [117.10 ns 117.53 ns 118.05 ns]
       change: [-0.3541% +0.2385% +0.7407%] (p = 0.42 > 0.05)

Found 8 outliers among 100 measurements (8.00%)
2 (2.00%) low severe
1 (1.00%) low mild
1 (1.00%) high mild
4 (4.00%) high severe

coalesce_acked_from_zero 1000+1 entries: No change in performance detected.
       time:   [97.359 ns 97.485 ns 97.624 ns]
       change: [-0.9854% -0.1336% +0.7523%] (p = 0.78 > 0.05)

Found 11 outliers among 100 measurements (11.00%)
4 (4.00%) high mild
7 (7.00%) high severe

RxStreamOrderer::inbound_frame(): 💔 Performance has regressed.
       time:   [114.34 ms 114.48 ms 114.70 ms]
       change: [+1.8791% +2.0130% +2.2322%] (p = 0.00 < 0.05)

Found 7 outliers among 100 measurements (7.00%)
5 (5.00%) low mild
1 (1.00%) high mild
1 (1.00%) high severe

transfer/pacing-false/varying-seeds: No change in performance detected.
       time:   [27.657 ms 28.766 ms 29.879 ms]
       change: [-1.7747% +4.0209% +9.9170%] (p = 0.16 > 0.05)

Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) low mild

transfer/pacing-true/varying-seeds: No change in performance detected.
       time:   [35.027 ms 36.914 ms 38.829 ms]
       change: [-9.6250% -3.3887% +3.1849%] (p = 0.33 > 0.05)

Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) high mild

transfer/pacing-false/same-seed: No change in performance detected.
       time:   [32.401 ms 33.126 ms 33.832 ms]
       change: [-3.6098% -0.6507% +2.2954%] (p = 0.67 > 0.05)

Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) low mild

transfer/pacing-true/same-seed: No change in performance detected.
       time:   [43.101 ms 46.435 ms 49.763 ms]
       change: [-5.2877% +4.0434% +13.706%] (p = 0.42 > 0.05)
1-conn/1-100mb-resp (aka. Download)/client: 💚 Performance has improved.
       time:   [112.43 ms 112.92 ms 113.39 ms]
       thrpt:  [881.91 MiB/s 885.55 MiB/s 889.42 MiB/s]
change:
       time:   [-2.7566% -2.1719% -1.5715%] (p = 0.00 < 0.05)
       thrpt:  [+1.5966% +2.2202% +2.8347%]

Found 6 outliers among 100 measurements (6.00%)
1 (1.00%) low severe
4 (4.00%) low mild
1 (1.00%) high mild

1-conn/10_000-parallel-1b-resp (aka. RPS)/client: No change in performance detected.
       time:   [314.75 ms 318.35 ms 321.87 ms]
       thrpt:  [31.069 Kelem/s 31.412 Kelem/s 31.771 Kelem/s]
change:
       time:   [-2.2649% -0.8060% +0.7471%] (p = 0.30 > 0.05)
       thrpt:  [-0.7416% +0.8125% +2.3174%]
1-conn/1-1b-resp (aka. HPS)/client: No change in performance detected.
       time:   [32.357 ms 32.536 ms 32.728 ms]
       thrpt:  [30.555  elem/s 30.735  elem/s 30.905  elem/s]
change:
       time:   [-0.5576% +0.0954% +0.8360%] (p = 0.78 > 0.05)
       thrpt:  [-0.8291% -0.0953% +0.5607%]

Found 9 outliers among 100 measurements (9.00%)
3 (3.00%) low mild
2 (2.00%) high mild
4 (4.00%) high severe

Client/server transfer results

Transfer of 33554432 bytes over loopback.

Client Server CC Pacing Mean [ms] Min [ms] Max [ms] Relative
msquic msquic 106.0 ± 26.8 84.0 174.2 1.00
neqo msquic reno on 220.2 ± 13.0 204.4 243.5 1.00
neqo msquic reno 227.5 ± 12.9 207.2 246.3 1.00
neqo msquic cubic on 228.4 ± 16.3 205.1 263.2 1.00
neqo msquic cubic 218.5 ± 15.1 205.3 252.5 1.00
msquic neqo reno on 93.9 ± 22.8 75.3 177.7 1.00
msquic neqo reno 94.5 ± 23.7 76.4 163.0 1.00
msquic neqo cubic on 88.2 ± 20.8 75.0 179.1 1.00
msquic neqo cubic 91.3 ± 27.2 75.5 229.2 1.00
neqo neqo reno on 163.3 ± 54.8 128.7 352.3 1.00
neqo neqo reno 150.7 ± 21.1 126.3 198.4 1.00
neqo neqo cubic on 174.4 ± 43.8 133.1 315.6 1.00
neqo neqo cubic 217.4 ± 107.7 134.9 407.8 1.00

⬇️ Download logs

Copy link
Collaborator

@mxinden mxinden left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I have had good experience both (1) with manually copying the Cargo.toml and an empty main.rs to build dependencies as a cachable layer and (2) with cargo-chef.

Of the two, in favor of cargo-chef.

qns/Dockerfile Outdated Show resolved Hide resolved
Co-authored-by: Max Inden <mail@max-inden.de>
Signed-off-by: Lars Eggert <lars@eggert.org>
@larseggert larseggert added this pull request to the merge queue Sep 9, 2024
Merged via the queue into mozilla:main with commit b1b0da3 Sep 9, 2024
52 of 56 checks passed
@larseggert larseggert deleted the ci-qns-faster-docker-build branch September 9, 2024 09:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants