This repository has been archived by the owner on Feb 27, 2024. It is now read-only.
Use unbounded queue in the receiver #16
Merged
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
added 2 commits
November 28, 2017 11:39
Signed-off-by: Sebastian Wicki <swicki@inf.ethz.ch>
Since senders are currently also unbounded, there is not much point in having receivers use bounded queues. Signed-off-by: Sebastian Wicki <swicki@inf.ethz.ch>
|
I'm merging this, as @antiguru has reported that it increases the throughput of his test program from ~150MBit/s to ~800MBit/s (on an input rate of 1000MBit/s). |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
The
transport::Receiverinstrymon_communicationwas using a blocking (bounded) queue which turned out to severely cripple performance. This PR changes this such that is uses a non-blocking queue.The original intention of using a bounded queue in the receiver was to propagate back-pressure to the sender. However, the current publisher interface does not really have a good way of indicating back-pressure, which means the original motivation for using a bounded queue is void.
Additionally, this PR also uses a buffered stream for the receiver, which should reduce the number of required system calls when reading from the socket.