Bump default value of max split count per task for FTE #22622
Merged
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
With limit of 256 splits per task it was possible to end up with very small tasks and possibly even reach limit of number of tasks per stage (2^^15). The problem appeared when splits were very small. Task sizing should be mostly done based on split size; max number of splits should be treated as extra limit to be reached only in rare situations. This PR bumps default value 8x to 2048.
|
I verified this PR with benchmarks and it does not seem to introduce any perf regression. The logic should not matter for common case where data files are reasonably sized and the splits limit is not effective |
wendigo
approved these changes
Jul 18, 2024
dekimir
approved these changes
Jul 18, 2024
|
This pull request has gone a while without any activity. Tagging the Trino developer relations team: @bitsondatadev @colebow @mosabua |
|
No I do not think so |
|
Thanks @losipiuk |
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Outdated suggestions cannot be applied.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.
With limit of 256 splits per task it was possible to end up with very small tasks and possibly even reach limit of number of tasks per stage (2^^15). The problem appeared when splits were very small. Task sizing should be mostly done based on split size; max number of splits should be treated as extra limit to be reached only in rare situations. This PR bumps default value 8x to 2048.
Description
Additional context and related issues
Release notes
(x) This is not user-visible or is docs only, and no release notes are required.
( ) Release notes are required. Please propose a release note for me.
( ) Release notes are required, with the following suggested text: