Compactor tweaks: Fix pool leak when iter exhausted and async pages for better throughput #3579
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
mdisibio
requested review from
joe-elliott,
annanay25,
mapno,
kvrhdn,
zalegrala,
electron0zero,
ie-pham and
stoewer
as code owners
stoewer
added a commit
to stoewer/tempo
that referenced
this pull request
Apr 19, 2024
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Outdated suggestions cannot be applied.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.
What this PR does:
Two small improvements to compactors that I noticed in #3537 . Bringing them forward since it is currently paused for a bit, and the changes are very small.
Async pages improves throughput by ~40% in our internal cluster. Below are screenshots showing total output traces and data rate. Benchmarks don't show this since there is no latency like object storage. (Aside, the benchmarks could use some work but skipping for now).
The pooling leak is mentioned here It only happens when compacting blocks of different trace counts. The benchmarks are also lacking this (they compact blocks of identical counts). Small but useful reduction in memory.
Which issue(s) this PR fixes:
Fixes #
Checklist
CHANGELOG.mdupdated - the order of entries should be[CHANGE],[FEATURE],[ENHANCEMENT],[BUGFIX]