omansfeld:spurious_undo - Branch - mozilla/neqo - CodSpeed

Blog Docs Changelog

feat(transport/cc): spurious congestion event recovery

Comparing

omansfeld:spurious_undo

(

b0b5b43

) with

main

(

e74f986

)

-7%

Improvements: 1

Regressions: 4

Untouched: 18

No successful run was found on main ( 3b011a3) during the generation of this report, so e74f986 was used instead as the comparison base. There might be some changes unrelated to this pull request in this report.

Benchmarks

Failed

coalesce_acked_from_zero 1+1 entries

neqo-transport/benches/range_tracker.rs::benches::benchmark_coalesce

Regression

-4%

2.9 µs3 µs

coalesce_acked_from_zero 10+1 entries

neqo-transport/benches/range_tracker.rs::benches::benchmark_coalesce

Regression

-4%

3 µs3.1 µs

coalesce_acked_from_zero 1000+1 entries

neqo-transport/benches/range_tracker.rs::benches::benchmark_coalesce

Regression

-7%

2.6 µs2.8 µs

coalesce_acked_from_zero 3+1 entries

neqo-transport/benches/range_tracker.rs::benches::benchmark_coalesce

Regression

-4%

3 µs3.1 µs

Improved

client

neqo-bin/benches/main.rs::benches::transfer::1-conn/1-100mb-resp (aka. Download)

+3%

816.2 ms790.1 ms

Passed

run

neqo-transport/benches/transfer.rs::transfer::benchmark_transfer_fixed::transfer/pacing-true/same-seed/wallclock-time

0%

156.8 ms156.7 ms

decode 4096 bytes, mask 7f

neqo-common/benches/decoder.rs::benches::benchmark_decoder

0%

38.6 µs38.6 µs

decode 4096 bytes, mask 3f

neqo-common/benches/decoder.rs::benches::benchmark_decoder

0%

46.6 µs46.5 µs

decode 1048576 bytes, mask 7f

neqo-common/benches/decoder.rs::benches::benchmark_decoder

0%

9.8 ms9.8 ms

decode 1048576 bytes, mask 3f

neqo-common/benches/decoder.rs::benches::benchmark_decoder

0%

11.8 ms11.8 ms

decode 1048576 bytes, mask ff

neqo-common/benches/decoder.rs::benches::benchmark_decoder

0%

6.8 ms6.8 ms

decode 4096 bytes, mask ff

neqo-common/benches/decoder.rs::benches::benchmark_decoder

0%

27 µs27 µs

take_ranges

neqo-transport/benches/sent_packets.rs::benches::take_ranges::sent::Packets

0%

30 µs30 µs

inbound_frame()

neqo-transport/benches/rx_stream_orderer.rs::benches::criterion_benchmark::RxStreamOrderer

0%

125.6 ms125.6 ms

client

neqo-bin/benches/main.rs::benches::transfer::1-conn/10_000-parallel-1b-resp (aka. RPS)

0%

366.6 ms366.6 ms

wallclock-time

neqo-http3/benches/streams.rs::benches::criterion_benchmark::1000-streams/each-1-bytes

0%

32.3 ms32.3 ms

run

neqo-transport/benches/transfer.rs::transfer::benchmark_transfer_variable::transfer/pacing-false/varying-seeds/wallclock-time

0%

157.9 ms158.2 ms

run

neqo-transport/benches/transfer.rs::transfer::benchmark_transfer_fixed::transfer/pacing-false/same-seed/wallclock-time

0%

156.8 ms157.1 ms

client

neqo-bin/benches/main.rs::benches::transfer::1-conn/1-1b-resp (aka. HPS)

-1%

15.1 ms15.2 ms

client

neqo-bin/benches/main.rs::benches::transfer::1-conn/1-100mb-req (aka. Upload)

-1%

891.3 ms902.6 ms

run

neqo-transport/benches/transfer.rs::transfer::benchmark_transfer_variable::transfer/pacing-true/varying-seeds/wallclock-time

-2%

155.4 ms158.1 ms

wallclock-time

neqo-http3/benches/streams.rs::benches::criterion_benchmark::1000-streams/each-1000-bytes

-2%

121.7 ms124.4 ms

wallclock-time

neqo-http3/benches/streams.rs::benches::criterion_benchmark::1-streams/each-1000-bytes

-3%

1 ms1.1 ms

Commits

Click on a commit to change the comparison range

Base

main

e74f986

-7.32%

More updates: - renaming `State` to `Phase` - renaming `Parameters` to `State` - adding `State::new()` - using `derive_more::Display` - docs

e2dd590

5 hours ago

by omansfeld

0%

fix clippy

b0b5b43

3 hours ago

by omansfeld

© 2026 CodSpeed Technology

Home Terms Privacy Docs