Reduce in memory queue limit by 16x #2455
Merged
+2
−2
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
This was previously across all partitions, but since 1.1 its per partition. And it is 350M per partition. Those entries are not initially used, but as you scale to 1m invocations per partition, all the memory pages in the queue's ring buffer are dirtied and contribute to RSS. This leads to 9G of usage on a 24 partition node. This PR reduces the limit by 16x to 21M per partition, or 562M on a 24 partition node, which it will reach after 1.5 million invocations. A more manageable figure, even if it still appears as a 'leak' until that amount is reached.
AhmedSoliman
approved these changes
Dec 23, 2024
There was a problem hiding this comment.
Great work investigating and proposing an improvement to this @jackkleeman. Changes look good to me.
jackkleeman
added a commit
that referenced
this pull request
Dec 23, 2024
This was previously across all partitions, but since 1.1 its per partition. And it is 350M per partition. Those entries are not initially used, but as you scale to 1m invocations per partition, all the memory pages in the queue's ring buffer are dirtied and contribute to RSS. This leads to 9G of usage on a 24 partition node. This PR reduces the limit by 16x to 21M per partition, or 562M on a 24 partition node, which it will reach after 1.5 million invocations. A more manageable figure, even if it still appears as a 'leak' until that amount is reached.
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Outdated suggestions cannot be applied.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.
This was previously across all partitions, but since 1.1 its per partition. And it is 350M per partition. Those entries are not initially used, but as you scale to 1m invocations per partition, all the memory pages in the queue's ring buffer are dirtied and contribute to RSS. This leads to 9G of usage on a 24 partition node.
This PR reduces the limit by 16x to 21M per partition, or 562M on a 24 partition node, which it will reach after 1.5 million invocations. A more manageable figure, even if it still appears as a 'leak' until that amount is reached.