-
Notifications
You must be signed in to change notification settings - Fork 1.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Request for Comment: Native TopK
Operator
#7250
Closed
Closed
Changes from all commits
Commits
Show all changes
15 commits
Select commit
Hold shift + click to select a range
524af05
Prototype TopK operator
alamb d4c09f2
Avoid use of Row
alamb 6c85247
Merge remote-tracking branch 'apache/main' into alamb/topk
alamb 948c1a2
start working on compaction
alamb 354d687
checkpoint
alamb afea7d3
update
alamb 69b86ab
checkpoint
alamb c8b415c
fmt
alamb 0337e31
Fix compaction
alamb db196fb
add location for re-encoding
alamb f123075
Start sketching dictionary interleave
alamb 157379a
checkpoint
alamb 682127a
initial specialized dictionary
alamb a1ea62e
finish initial special interleave
alamb 5e65130
Complete dictionary order
alamb File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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 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
Oops, something went wrong.
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Outdated suggestions cannot be applied.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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In this prototype I simply used the
TopK
implementation forSortExec
when there was a fetch as it produces the same output.However, longer term I think we should make a real
TopKExec
ExecutionPlan
so that the optimizers know about it and can avoid repartitioning / trying to do anything else fancyThere was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I wonder if there is some threshold at which the fetch is large enough that sorting is the better approach, certainly if the fetch is large enough that we need to spill
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
One possible approach for starters (i.e. prior to
TopKExec
) could be to run the newTopK
whenfetch
isSome
and there was no memory limits set (i.e.RuntimeEnv
usesUnboundedMemoryPool
), given that theExternalSorter
does a relatively good job of obeying the memory limits (though it will use it all up in this scenario).There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you @tustvold and @gruuya -- these are good ideas.
Maybe we can figure out how to switch between sort and TopK dynamically -- like if TopK exceeds some memory threshold revert back to the normal ExternalSorter. Let me think about this 🤔