Repository navigation
fix: keep PTOs within the anti-amplification limit - #4098
Open
larseggert wants to merge 2 commits into
Open
larseggert wants to merge 2 commits into
larseggert wants to merge 2 commits into
Conversation
larseggert
requested review from
KershawChang,
martinthomson,
mxinden and
omansfeld
as code owners
October 19, 2026 12:05
larseggert
added this pull request to stack #4100
October 19, 2026 12:05
Contributor
There was a problem hiding this comment.
🟢 Approval recommended
The focused guards reuse existing budget semantics, and the regression test covers exhaustion with no blocking issues identified.
No open issues 🎉
What changed in this PR
This PR keeps QUIC probe sends within the anti-amplification limit by requiring enough budget for a full MTU.
Changes:
- Apply the existing budget check to timeout and recovery probes.
- Add a regression test covering partial-budget exhaustion.
| File | Description |
|---|---|
neqo-transport/src/recovery/mod.rs |
Guard both probe paths with the budget check. |
neqo-transport/src/connection/tests/handshake.rs |
Test server probe behavior as the amplification budget runs out. |
Review effort: Balanced
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #4098 +/- ##
==========================================
- Coverage 97.19% 97.04% -0.15%
==========================================
Files 113 118 +5
Lines 41835 42182 +347
Branches 41835 42182 +347
==========================================
+ Hits 40662 40936 +274
- Misses 1159 1222 +63
- Partials 14 24 +10
Flags with carried forward coverage won't be shown. Click here to find out more.
|
Contributor
Merging this PR will degrade performance by 2.84%
|
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ❌ | Walltime | 1-conn/10_000-parallel-1b-resp (aka. RPS) |
80.4 ms | 85.3 ms | -5.77% |
| ❌ | Walltime | walltime/1000-streams/each-1-bytes |
4.4 ms | 4.6 ms | -4.53% |
| ❌ | Walltime | walltime/10-streams/each-1048576-bytes |
34 ms | 35.2 ms | -3.48% |
| ❌ | CPU Simulation | simulated/pacing-true/same-seed |
58.2 ms | 60.2 ms | -3.22% |
| ❌ | Walltime | walltime/pacing-true/same-seed |
4.3 ms | 4.4 ms | -3.07% |
| ❌ | Walltime | walltime/1-streams/each-4194304-bytes |
12.7 ms | 13 ms | -2.58% |
| ⚡ | Walltime | 1-conn/1-100mb-req (aka. Upload) |
60 ms | 58.3 ms | +3% |
Tip
Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.
Comparing fix-pto-amplification (4c9b93f) with main (0a535c2)
A PTO datagram is sent only if a full MTU still fits.
larseggert
force-pushed
the
fix-pto-amplification
branch
from
October 21, 2026 06:29
1ceee6d to
4c9b93f
Compare
Contributor
Failed Interop TestsQUIC Interop Runner, client vs. server, differences relative to
All resultsSucceeded Interop TestsQUIC Interop Runner, client vs. server neqo-pr as client
neqo-pr as server
Unsupported Interop TestsQUIC Interop Runner, client vs. server neqo-pr as client
neqo-pr as server
|
Contributor
Benchmark resultsNo significant performance differences relative to a8809b4. All resultstransfer/1-conn/1-100mb-req (aka. Upload)/mtu-1500 time: [59.216 ms 59.263 ms 59.312 ms]
thrpt: [1.6465 GiB/s 1.6478 GiB/s 1.6492 GiB/s]
Found 4 outliers among 100 measurements (4.00%)
1 (1.00%) low mild
2 (2.00%) high mild
1 (1.00%) high severetransfer/1-conn/1-100mb-resp (aka. Download)/mtu-1500 time: [59.358 ms 59.406 ms 59.456 ms]
thrpt: [1.6425 GiB/s 1.6439 GiB/s 1.6452 GiB/s]
Found 2 outliers among 100 measurements (2.00%)
2 (2.00%) high mildtransfer/1-conn/1-1b-resp (aka. HPS)/mtu-1500 time: [3.5433 ms 3.5443 ms 3.5452 ms]
thrpt: [282.07 B/s 282.15 B/s 282.22 B/s]
Found 4 outliers among 100 measurements (4.00%)
1 (1.00%) low mild
2 (2.00%) high mild
1 (1.00%) high severetransfer/1-conn/10_000-parallel-1b-resp (aka. RPS)/mtu-1500 time: [80.884 ms 81.019 ms 81.161 ms]
thrpt: [123.21 Kelem/s 123.43 Kelem/s 123.63 Kelem/s]
Found 4 outliers among 100 measurements (4.00%)
1 (1.00%) low mild
2 (2.00%) high mild
1 (1.00%) high severestreams-flow-controlled/walltime/1-streams/each-4194304-bytes time: [12.485 ms 12.489 ms 12.494 ms]
thrpt: [320.15 MiB/s 320.27 MiB/s 320.40 MiB/s]streams-flow-controlled/walltime/10-streams/each-1048576-bytes time: [34.250 ms 34.265 ms 34.280 ms]
thrpt: [291.72 MiB/s 291.84 MiB/s 291.97 MiB/s]streams/walltime/1-streams/each-1000-bytes time: [156.61 µs 157.22 µs 158.02 µs]
thrpt: [6.0350 MiB/s 6.0657 MiB/s 6.0896 MiB/s]
Found 2 outliers among 100 measurements (2.00%)
2 (2.00%) high mildstreams/walltime/1000-streams/each-1-bytes time: [4.4693 ms 4.4751 ms 4.4806 ms]
thrpt: [217.95 KiB/s 218.22 KiB/s 218.50 KiB/s]
Found 4 outliers among 100 measurements (4.00%)
4 (4.00%) low mildstreams/walltime/1000-streams/each-1000-bytes time: [14.743 ms 14.755 ms 14.768 ms]
thrpt: [64.576 MiB/s 64.632 MiB/s 64.688 MiB/s]
Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) high mildtransfer/walltime/pacing-false/same-seed time: [3.9392 ms 3.9418 ms 3.9443 ms]
thrpt: [1014.1 MiB/s 1014.8 MiB/s 1015.4 MiB/s]transfer/walltime/pacing-false/varying-seeds time: [3.8176 ms 3.8192 ms 3.8212 ms]
thrpt: [1.0223 GiB/s 1.0228 GiB/s 1.0232 GiB/s]
Found 1 outliers among 100 measurements (1.00%)
1 (1.00%) high mildtransfer/walltime/pacing-true/same-seed time: [4.1131 ms 4.1163 ms 4.1201 ms]
thrpt: [970.85 MiB/s 971.76 MiB/s 972.51 MiB/s]transfer/walltime/pacing-true/varying-seeds time: [4.2189 ms 4.2225 ms 4.2269 ms]
thrpt: [946.33 MiB/s 947.32 MiB/s 948.12 MiB/s]Instructions per cycleCriterion reported no significant timing changes. All benchmarks
Profiles for profiler.firefox.com (64)
Download data for |
Contributor
Client/server transfer resultsPerformance differences relative to a8809b4. Transfer of 33554432 bytes over loopback, min. 100 runs. All unit-less numbers are in milliseconds.
Table above only shows statistically significant changes. See all results below. All resultsTransfer of 33554432 bytes over loopback, min. 100 runs. All unit-less numbers are in milliseconds.
Download data for |
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A PTO datagram is sent only if a full MTU still fits.
Stack created with GitHub Stacks CLI • Give Feedback 💬