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: Only show performance improvements and regressions details #1906

Merged
merged 2 commits into from
May 21, 2024

Conversation

larseggert
Copy link
Collaborator

@larseggert larseggert commented May 16, 2024

By default. Makes the perf PR comment a bit more concise. See below.

By default. Makes the perf PR comment a bit more concise.
Copy link

github-actions bot commented May 16, 2024

Failed Interop Tests

QUIC Interop Runner, client vs. server

All results

Succeeded Interop Tests

QUIC Interop Runner, client vs. server

Unsupported Interop Tests

QUIC Interop Runner, client vs. server

Copy link

codecov bot commented May 16, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 93.20%. Comparing base (a71e43d) to head (f4fe9df).
Report is 1 commits behind head on main.

Additional details and impacted files
@@           Coverage Diff           @@
##             main    #1906   +/-   ##
=======================================
  Coverage   93.19%   93.20%           
=======================================
  Files         110      110           
  Lines       35760    35763    +3     
=======================================
+ Hits        33328    33333    +5     
+ Misses       2432     2430    -2     

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

Copy link

github-actions bot commented May 16, 2024

Benchmark results

Performance differences relative to a71e43d.

coalesce_acked_from_zero 1+1 entries: No change in performance detected.
       time:   [196.68 ns 197.13 ns 197.60 ns]
       change: [-0.6399% -0.2900% +0.0383%] (p = 0.10 > 0.05)
Found 19 outliers among 100 measurements (19.00%)
  1 (1.00%) low mild
  8 (8.00%) high mild
  10 (10.00%) high severe
coalesce_acked_from_zero 3+1 entries: Change within noise threshold.
       time:   [238.72 ns 239.32 ns 239.96 ns]
       change: [-0.7943% -0.4757% -0.1402%] (p = 0.00 < 0.05)
Found 14 outliers among 100 measurements (14.00%)
  14 (14.00%) high severe
coalesce_acked_from_zero 10+1 entries: Change within noise threshold.
       time:   [237.80 ns 238.56 ns 239.48 ns]
       change: [-3.2300% -1.5488% -0.4040%] (p = 0.02 < 0.05)
Found 7 outliers among 100 measurements (7.00%)
  1 (1.00%) high mild
  6 (6.00%) high severe
coalesce_acked_from_zero 1000+1 entries: No change in performance detected.
       time:   [216.92 ns 217.08 ns 217.25 ns]
       change: [-8.2607% -2.7045% +0.6362%] (p = 0.46 > 0.05)
Found 9 outliers among 100 measurements (9.00%)
  2 (2.00%) high mild
  7 (7.00%) high severe
RxStreamOrderer::inbound_frame(): 💚 Performance has improved.
       time:   [118.48 ms 118.59 ms 118.71 ms]
       change: [-1.7180% -1.5080% -1.3439%] (p = 0.00 < 0.05)
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild
transfer/Run multiple transfers with varying seeds: Change within noise threshold.
       time:   [119.15 ms 119.41 ms 119.67 ms]
       thrpt:  [33.424 MiB/s 33.498 MiB/s 33.572 MiB/s]
change:
       time:   [-0.9970% -0.6654% -0.3279%] (p = 0.00 < 0.05)
       thrpt:  [+0.3290% +0.6699% +1.0070%]
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild
transfer/Run multiple transfers with the same seed: Change within noise threshold.
       time:   [119.32 ms 119.53 ms 119.74 ms]
       thrpt:  [33.406 MiB/s 33.464 MiB/s 33.524 MiB/s]
change:
       time:   [-0.7724% -0.4782% -0.1806%] (p = 0.00 < 0.05)
       thrpt:  [+0.1810% +0.4805% +0.7785%]
Found 3 outliers among 100 measurements (3.00%)
  2 (2.00%) low mild
  1 (1.00%) high mild
1-conn/1-100mb-resp (aka. Download)/client: Change within noise threshold.
       time:   [1.1250 s 1.1379 s 1.1524 s]
       thrpt:  [86.773 MiB/s 87.880 MiB/s 88.886 MiB/s]
change:
       time:   [+0.6213% +3.9938% +7.2745%] (p = 0.04 < 0.05)
       thrpt:  [-6.7812% -3.8404% -0.6175%]
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) high mild
1-conn/10_000-parallel-1b-resp (aka. RPS)/client: No change in performance detected.
       time:   [391.35 ms 394.70 ms 398.11 ms]
       thrpt:  [25.118 Kelem/s 25.335 Kelem/s 25.552 Kelem/s]
change:
       time:   [-0.7719% +0.3353% +1.5493%] (p = 0.57 > 0.05)
       thrpt:  [-1.5257% -0.3342% +0.7779%]

1-conn/1-1b-resp (aka. HPS)/client
time: [42.118 ms 42.296 ms 42.513 ms]
thrpt: [23.522 elem/s 23.643 elem/s 23.743 elem/s]
change:
time: [+0.4930% +1.0330% +1.6455%] (p = 0.00 < 0.05)
thrpt: [-1.6188% -1.0224% -0.4906%]
Change within noise threshold.
Found 5 outliers among 100 measurements (5.00%)
5 (5.00%) high severe

Client/server transfer results

Transfer of 134217728 bytes over loopback.

Client Server CC Pacing Mean [ms] Min [ms] Max [ms] Relative
msquic msquic 668.5 ± 211.7 435.1 1162.3 1.00
neqo msquic reno on 953.6 ± 120.3 805.4 1141.7 1.00
neqo msquic reno 908.3 ± 268.2 693.8 1642.0 1.00
neqo msquic cubic on 905.2 ± 183.1 759.7 1293.6 1.00
neqo msquic cubic 871.2 ± 192.2 747.7 1377.1 1.00
msquic neqo reno on 4360.4 ± 236.5 4180.8 4818.9 1.00
msquic neqo reno 4142.9 ± 75.0 3994.7 4290.5 1.00
msquic neqo cubic on 4064.5 ± 197.9 3940.7 4584.6 1.00
msquic neqo cubic 3952.8 ± 57.4 3798.8 4004.4 1.00
neqo neqo reno on 3452.7 ± 179.7 3156.8 3675.9 1.00
neqo neqo reno 3250.6 ± 222.5 2971.2 3626.5 1.00
neqo neqo cubic on 3651.5 ± 133.8 3432.3 3826.4 1.00
neqo neqo cubic 3569.4 ± 151.9 3361.8 3758.4 1.00

⬇️ Download logs

Copy link

github-actions bot commented May 16, 2024

Firefox builds for this PR

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

@larseggert larseggert enabled auto-merge May 16, 2024 13:30
Copy link
Member

@martinthomson martinthomson left a comment

Choose a reason for hiding this comment

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

This is mostly fine, but I want to encourage you more strongly not to write perl code.

.github/workflows/bench.yml Show resolved Hide resolved
@larseggert larseggert added this pull request to the merge queue May 21, 2024
Merged via the queue into mozilla:main with commit 4162cd8 May 21, 2024
55 checks passed
@larseggert larseggert deleted the ci-bench-only-show-diff branch May 21, 2024 06:44
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