fix: restore mtu probe promotion#287
Open
marcus-pousette-hp wants to merge 1 commit into
Open
Conversation
f346121 to
2b71491
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This fixes MTU probe promotion after 1302a45, which replaced
assert(wanted_size > pkt->size)with an early return. That condition is the normal in-band probe case: the packet is smaller than the target MTU and should be padded up to the probe size.The fix removes that inverted return and rejects invalid padding after computing it. Negative padding means the packet is already larger than the target probe size; padding above 255 cannot fit in the header field.
I added a regression test that transfers 8 MiB over loopback and asserts that successful probes promote the sender from
UDX_MTU_BASEtoUDX_MTU_MAX.I also tested this through
udx-native@1.20.6against a remote blind relay. Both peers ran locally and were forced through the remote relay; the remote host was only the relay. Each run transferred 8 MiB.Verified with
ctest --test-dir build-debug --output-on-failure: 30/30 passed, with the existing perf test disabled.Co-written with AI