Skip to content

chore: Bump MSRV to 1.82 #2456

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 5 commits into from
Feb 27, 2025
Merged

chore: Bump MSRV to 1.82 #2456

merged 5 commits into from
Feb 27, 2025

Conversation

larseggert
Copy link
Collaborator

And address some TODOs that were enabled by the new MSRV.

@codecov Codecov
Copy link

codecov bot commented Feb 26, 2025 •
edited
Loading

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 95.41%. Comparing base (0e41954) to head (9d8cf0a).
Report is 2 commits behind head on main.

Additional details and impacted files 
@@            Coverage Diff             @@
##             main    #2456      +/-   ##
==========================================
+ Coverage   95.39%   95.41%   +0.02%     
==========================================
  Files         115      115              
  Lines       36982    36996      +14     
  Branches    36982    36996      +14     
==========================================
+ Hits        35280    35301      +21     
+ Misses       1696     1689       -7     
  Partials        6        6
Components Coverage Δ
neqo-common 97.17% <100.00%> (+<0.01%) ⬆️
neqo-crypto 90.44% <100.00%> (+0.36%) ⬆️
neqo-http3 94.50% <100.00%> (-0.01%) ⬇️
neqo-qpack 96.29% <100.00%> (+<0.01%) ⬆️
neqo-transport 96.24% <100.00%> (+<0.01%) ⬆️
neqo-udp 95.29% <ø> (ø)

@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 26, 2025 •
edited
Loading

Failed Interop Tests

QUIC Interop Runner, client vs. server, differences relative to 0e41954.

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

@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 26, 2025 •
edited
Loading

Benchmark results

Performance differences relative to 0e41954.

decode 4096 bytes, mask ff: 💚 Performance has improved.
       time:   [11.389 µs 11.433 µs 11.482 µs]
       change: [-7.5298% -7.1092% -6.6185%] (p = 0.00 < 0.05)

Found 14 outliers among 100 measurements (14.00%)

2 (2.00%) low severe

1 (1.00%) low mild

11 (11.00%) high severe

decode 1048576 bytes, mask ff: 💔 Performance has regressed.
       time:   [3.1771 ms 3.1862 ms 3.1970 ms]
       change: [+11.858% +12.397% +12.930%] (p = 0.00 < 0.05)

Found 8 outliers among 100 measurements (8.00%)

8 (8.00%) high severe

decode 4096 bytes, mask 7f: 💚 Performance has improved.
       time:   [17.481 µs 17.519 µs 17.562 µs]
       change: [-16.000% -15.750% -15.499%] (p = 0.00 < 0.05)

Found 9 outliers among 100 measurements (9.00%)

1 (1.00%) low mild

1 (1.00%) high mild

7 (7.00%) high severe

decode 1048576 bytes, mask 7f: 💔 Performance has regressed.
       time:   [5.5200 ms 5.5316 ms 5.5447 ms]
       change: [+21.499% +21.926% +22.348%] (p = 0.00 < 0.05)

Found 14 outliers among 100 measurements (14.00%)

14 (14.00%) high severe

decode 4096 bytes, mask 3f: 💚 Performance has improved.
       time:   [6.7027 µs 6.7227 µs 6.7453 µs]
       change: [-21.161% -20.149% -19.242%] (p = 0.00 < 0.05)

Found 5 outliers among 100 measurements (5.00%)

3 (3.00%) high mild

2 (2.00%) high severe

decode 1048576 bytes, mask 3f: 💔 Performance has regressed.
       time:   [2.1064 ms 2.1134 ms 2.1217 ms]
       change: [+32.201% +32.927% +33.656%] (p = 0.00 < 0.05)

Found 10 outliers among 100 measurements (10.00%)

10 (10.00%) high severe

1 streams of 1 bytes/multistream: No change in performance detected.
       time:   [65.341 µs 65.460 µs 65.582 µs]
       change: [-1.2800% +0.2159% +1.1037%] (p = 0.82 > 0.05)

Found 3 outliers among 100 measurements (3.00%)

3 (3.00%) high mild

1000 streams of 1 bytes/multistream: 💚 Performance has improved.
       time:   [23.550 ms 23.590 ms 23.631 ms]
       change: [-2.1019% -1.8885% -1.6932%] (p = 0.00 < 0.05)

Found 1 outliers among 100 measurements (1.00%)

1 (1.00%) high mild

10000 streams of 1 bytes/multistream: Change within noise threshold.
       time:   [1.6248 s 1.6267 s 1.6286 s]
       change: [-0.9119% -0.7613% -0.6048%] (p = 0.00 < 0.05)

Found 24 outliers among 100 measurements (24.00%)

2 (2.00%) low severe

10 (10.00%) low mild

12 (12.00%) high severe

1 streams of 1000 bytes/multistream: Change within noise threshold.
       time:   [66.632 µs 67.176 µs 68.156 µs]
       change: [+0.6698% +1.5586% +3.0151%] (p = 0.01 < 0.05)

Found 3 outliers among 100 measurements (3.00%)

2 (2.00%) high mild

1 (1.00%) high severe

100 streams of 1000 bytes/multistream: Change within noise threshold.
       time:   [3.1455 ms 3.1521 ms 3.1595 ms]
       change: [-1.6232% -1.3101% -0.9918%] (p = 0.00 < 0.05)

Found 19 outliers among 100 measurements (19.00%)

19 (19.00%) high severe

1000 streams of 1000 bytes/multistream: Change within noise threshold.
       time:   [137.50 ms 137.58 ms 137.66 ms]
       change: [-1.0645% -0.9882% -0.9093%] (p = 0.00 < 0.05)

Found 3 outliers among 100 measurements (3.00%)

3 (3.00%) high mild

coalesce_acked_from_zero 1+1 entries: No change in performance detected.
       time:   [89.554 ns 89.890 ns 90.222 ns]
       change: [-0.3403% +0.0547% +0.4627%] (p = 0.79 > 0.05)

Found 12 outliers among 100 measurements (12.00%)

9 (9.00%) high mild

3 (3.00%) high severe

coalesce_acked_from_zero 3+1 entries: No change in performance detected.
       time:   [106.83 ns 107.13 ns 107.47 ns]
       change: [-0.7116% -0.1216% +0.4877%] (p = 0.69 > 0.05)

Found 13 outliers among 100 measurements (13.00%)

1 (1.00%) low mild

2 (2.00%) high mild

10 (10.00%) high severe

coalesce_acked_from_zero 10+1 entries: No change in performance detected.
       time:   [106.46 ns 106.81 ns 107.26 ns]
       change: [-0.8755% -0.3134% +0.2893%] (p = 0.28 > 0.05)

Found 8 outliers among 100 measurements (8.00%)

3 (3.00%) low mild

5 (5.00%) high severe

coalesce_acked_from_zero 1000+1 entries: No change in performance detected.
       time:   [89.696 ns 93.329 ns 101.67 ns]
       change: [+0.1075% +3.7663% +12.694%] (p = 0.22 > 0.05)

Found 15 outliers among 100 measurements (15.00%)

6 (6.00%) high mild

9 (9.00%) high severe

RxStreamOrderer::inbound_frame(): Change within noise threshold.
       time:   [116.29 ms 116.34 ms 116.39 ms]
       change: [-0.2026% -0.1422% -0.0795%] (p = 0.00 < 0.05)

Found 18 outliers among 100 measurements (18.00%)

4 (4.00%) low severe

3 (3.00%) low mild

2 (2.00%) high mild

9 (9.00%) high severe

SentPackets::take_ranges: No change in performance detected.
       time:   [5.2284 µs 5.3803 µs 5.5444 µs]
       change: [-2.1200% +0.6572% +3.2403%] (p = 0.65 > 0.05)

Found 6 outliers among 100 measurements (6.00%)

5 (5.00%) high mild

1 (1.00%) high severe

transfer/pacing-false/varying-seeds: Change within noise threshold.
       time:   [34.477 ms 34.546 ms 34.615 ms]
       change: [+2.4398% +2.6990% +2.9822%] (p = 0.00 < 0.05)

Found 1 outliers among 100 measurements (1.00%)

1 (1.00%) low mild

transfer/pacing-true/varying-seeds: Change within noise threshold.
       time:   [34.240 ms 34.297 ms 34.355 ms]
       change: [+1.8472% +2.0687% +2.2939%] (p = 0.00 < 0.05)

Found 2 outliers among 100 measurements (2.00%)

2 (2.00%) high mild

transfer/pacing-false/same-seed: Change within noise threshold.
       time:   [34.343 ms 34.394 ms 34.444 ms]
       change: [+2.3576% +2.5718% +2.7846%] (p = 0.00 < 0.05)
transfer/pacing-true/same-seed: Change within noise threshold.
       time:   [34.616 ms 34.668 ms 34.721 ms]
       change: [+2.5479% +2.7383% +2.9517%] (p = 0.00 < 0.05)

Found 1 outliers among 100 measurements (1.00%)

1 (1.00%) high mild

1-conn/1-100mb-resp/mtu-1504 (aka. Download)/client: No change in performance detected.
       time:   [2.1850 s 2.1923 s 2.1995 s]
       thrpt:  [45.465 MiB/s 45.614 MiB/s 45.767 MiB/s]
change:
       time:   [-0.2834% +0.2752% +0.8165%] (p = 0.34 > 0.05)
       thrpt:  [-0.8099% -0.2745% +0.2842%]
1-conn/10_000-parallel-1b-resp/mtu-1504 (aka. RPS)/client: No change in performance detected.
       time:   [385.30 ms 387.49 ms 389.75 ms]
       thrpt:  [25.657 Kelem/s 25.807 Kelem/s 25.954 Kelem/s]
change:
       time:   [-0.1619% +0.6417% +1.3917%] (p = 0.11 > 0.05)
       thrpt:  [-1.3726% -0.6376% +0.1621%]

Found 1 outliers among 100 measurements (1.00%)

1 (1.00%) high mild

1-conn/1-1b-resp/mtu-1504 (aka. HPS)/client: Change within noise threshold.
       time:   [26.837 ms 27.470 ms 28.120 ms]
       thrpt:  [35.562  elem/s 36.404  elem/s 37.263  elem/s]
change:
       time:   [-7.5397% -4.3026% -0.9183%] (p = 0.01 < 0.05)
       thrpt:  [+0.9268% +4.4960% +8.1545%]
1-conn/1-100mb-resp/mtu-1504 (aka. Upload)/client: No change in performance detected.
       time:   [3.1557 s 3.1733 s 3.1910 s]
       thrpt:  [31.338 MiB/s 31.513 MiB/s 31.689 MiB/s]
change:
       time:   [-1.6277% -0.6445% +0.3377%] (p = 0.21 > 0.05)
       thrpt:  [-0.3365% +0.6487% +1.6547%]

Client/server transfer results

Performance differences relative to 0e41954.

Transfer of 33554432 bytes over loopback, 30 runs. All unit-less numbers are in milliseconds.

Client Server CC Pacing Mean ± σ Min Max Δ main Δ main
neqo neqo reno on 482.7 ± 23.3 442.8 538.6 💚 -22.9 -1.2%
neqo neqo reno 519.3 ± 124.4 448.4 1073.8 -10.0 -0.5%
neqo neqo cubic on 507.4 ± 25.1 468.1 569.5 -8.6 -0.4%
neqo neqo cubic 501.5 ± 39.3 454.7 675.2 -25.8 -1.3%
google neqo reno on 907.6 ± 99.6 652.0 1039.1 7.1 0.2%
google neqo reno 904.5 ± 98.2 662.0 1029.5 5.0 0.1%
google neqo cubic on 903.8 ± 104.2 648.9 1133.8 5.6 0.2%
google neqo cubic 897.4 ± 93.9 662.0 997.6 -4.1 -0.1%
google google 549.2 ± 10.4 530.6 579.0 8.7 0.4%
neqo msquic reno on 223.7 ± 16.3 204.9 267.6 -6.1 -0.7%
neqo msquic reno 222.7 ± 23.8 197.6 324.4 -3.3 -0.4%
neqo msquic cubic on 226.0 ± 23.3 202.9 317.5 -1.6 -0.2%
neqo msquic cubic 233.7 ± 85.6 201.7 683.7 1.9 0.2%
msquic msquic 120.3 ± 26.4 99.8 234.6 -1.0 -0.2%

⬇️ Download logs

@martinthomson
Copy link
Member

What is going on with those benchmarks? I'm seeing huge swings. Have you landed that CPU pinning change? I would have thought that we would be less exposed to noise with that.

@martinthomson
Copy link
Member

The failure here looks legit. We're doing a sign erasure cast. The problem I see is that we already suppress the lint, so I don't know what is going on there.

@larseggert
Copy link
Collaborator Author

What is going on with those benchmarks? I'm seeing huge swings. Have you landed that CPU pinning change? I would have thought that we would be less exposed to noise with that.

So did I. I need to do some more debugging to understand and fix why it is (still) doing that. One weird aspect is that the isolated cores report a clock speed of 800MHz (vs. 3Ghz). That might be due to the way the isolation was done (via cmdline); if so there is a newer cpuset-based approach that I can try. Or the report is just wrong, since the benchmark speed difference is not that large...

@larseggert
Copy link
Collaborator Author

The failure here looks legit. We're doing a sign erasure cast. The problem I see is that we already suppress the lint, so I don't know what is going on there.

We didn't suppress clippy::cast_sign_loss, which only fires on Windows. Should be fixed now.

@larseggert larseggert mentioned this pull request Feb 27, 2025
Open
@larseggert larseggert added this pull request to the merge queue Feb 27, 2025
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to failed status checks Feb 27, 2025
@larseggert larseggert added this pull request to the merge queue Feb 27, 2025
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to failed status checks Feb 27, 2025
@larseggert larseggert merged commit 8d27458 into mozilla:main Feb 27, 2025
74 of 75 checks passed
@larseggert larseggert deleted the chore-msrv-1.82 branch February 27, 2025 18:22
@omansfeld omansfeld mentioned this pull request Apr 3, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@martinthomson martinthomson martinthomson left review comments

@mxinden mxinden mxinden approved these changes

@KershawChang KershawChang Awaiting requested review from KershawChang KershawChang is a code owner

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@larseggert @martinthomson @mxinden