This repository has been archived by the owner on Sep 18, 2023. It is now read-only.
[NSE-569] CPU overhead on fine grain / concurrent off-heap acquire operations #590
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
zhouyuan
reviewed
Nov 30, 2021
| @@ -20,24 +20,55 @@ | |||
| import org.apache.arrow.memory.AllocationListener; | |||
|
|
|||
| public class SparkManagedAllocationListener implements AllocationListener { | |||
| public static long BLOCK_SIZE = 8L * 1024 * 1024; // 8MB per block | |||
There was a problem hiding this comment.
how about make this configurable?
There was a problem hiding this comment.
That's a good idea.
Although at this time I think a fixed size is enough for most cases: say 8M can already reduce Spark acquire calls by 99%, in my own measurement.
Also the similar logic was applied to C++ Arrow code so it might require further thinking to unify them somehow. On the whole I think we can open a individual topic for the suggestion. :)
|
Benchmarked: Able to speed up TPC-DS SF1000 by ~5% |
|
CI UTs were failing and should be fixed by this PR also cc @rui-mo |
zhouyuan
approved these changes
Dec 1, 2021
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Outdated suggestions cannot be applied.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.
What changes were proposed in this pull request?
To fix #569
How was this patch tested?
TPC-H benchmark on Jenkins