Ensure TCP_NODELAY is disabled by fixing namespacing #187
Conversation
This file contains 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
michaelklishin
added a commit
that referenced
this pull request
Feb 14, 2014
Ensure TCP_NODELAY is disabled by fixing namespacing
michaelklishin
added a commit
to michaelklishin/sneakers
that referenced
this pull request
Feb 15, 2014
[Significantly lower latency](ruby-amqp/bunny#187) for workloads that involve frequently sent small messages.
michaelklishin
pushed a commit
to ruby-amqp/hutch
that referenced
this pull request
Feb 15, 2014
[Lower latency](ruby-amqp/bunny#187), you see.
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Outdated suggestions cannot be applied.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.
While using bunny-1.1.0, we discovered an unacceptable latency for publishing messages with confirmation. Between a Bunny client and broker, both running Ubuntu Precise, this latency converges to 40ms for the case of many small messages. After some head-scratching, a packet capture revealed the true cause:
Although both frames are sent in a tight loop, the client machine waits for an ACK before sending the payload. This suggests that Bunny isn't disabling Nagle's algorithm as a read through implies it ought to. After some poking, I discovered the bug:
By monkey-patching the implementation, I was able to achieve the desired result: