Connection pooling + tune batch size to eliminate stragglers #38
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
samkumar
approved these changes
Jan 9, 2022
There was a problem hiding this comment.
Based on my reading of the code, it looks like the connection isn't persistent --- the destination port is left listening, but a separate connection is still used for each batch of chunks.
I'm approving since it improves bandwidth, but I still think that keeping the TCP connection itself alive for a long time is good, to avoid ramping up congestion control each time.
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Outdated suggestions cannot be applied.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.
Fixes #36
Connections now transfer 2-3x faster (from ~600Mbps to ~1.4Gbps for us-west-1 to us-east-1). By tuning batch sizes used when writing back to disk, the stragglers seem to no longer be a problem.