Add barrier tests + Change queue timeout #123
Merged
Conversation
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
csegarragonz
added
mpi
Shillaker
approved these changes
Jun 23, 2021
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Outdated suggestions cannot be applied.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.
After #118, dequeuing has a timeout of 500 ms. Unfortunately, there is an MPI test in faasm (the barrier test) that blocks for 1s dequeuing (note that the 1s timeout is enforced through
sleepcalls). Thus we either:faabriclarger (in this PR, happy to revert)MPI_QUEUE_TIMEOUT(originally opted for this, but given how controversial timeout values are, I doubt adding more will solve anything)clients/cppIn favour of changing the timeout value here is that there may be occasions in which we deliberately block on a
send/recvas a fake synchronization point, hence 500 ms may be a bit short.In the process of debugging this issue, I've realised we weren't testing the barrier at all in
faabricso added a couple tests for that.Lastly, after this gets merged in I will bump the faabric dependency in faasm. It's cumbersome to do so often, but helps catching this sort of bugs early.