Choose cheapest aggregated path as base for chunk-wise aggregation #7025
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
Currently we use the cheapest path before final aggregation for this (i.e. Append over individual chunks), but it does not consider the cost of a Sort that might be required before aggregation. To account for this, use instead the child path of the cheapest final aggregated path.
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #7025 +/- ##
==========================================
+ Coverage 80.06% 82.16% +2.09%
==========================================
Files 190 230 +40
Lines 37181 43219 +6038
Branches 9450 10875 +1425
==========================================
+ Hits 29770 35512 +5742
- Misses 2997 3385 +388
+ Partials 4414 4322 -92 ☔ View full report in Codecov by Sentry. |
This is important for the common case of grouping by time_bucket(). In this case, under AggPath there is a ProjectionPath above the Append node for all the chunks. When we make a chunkwise aggregation plan, we have to put a similar ProjectionPath under each per-chunk AggPath.
13 tasks
…nion_view-* cagg_watermark-* continuous_aggs-* transparent_decompression-*
…union_view-* cagg_watermark-* continuous_aggs-* transparent_decompression-*
… transparent_decompression-*
…* transparent_decompression-*
|
@fabriziomello, @antekresic: please review this pull request.
|
svenklemm
approved these changes
Dec 9, 2024
fabriziomello
approved these changes
Dec 9, 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Outdated suggestions cannot be applied.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.
Currently we use the cheapest path before final aggregation for this (i.e. Append over individual chunks), but it does not consider the cost of a Sort that might be required before aggregation. To account for this, use instead the child path of the cheapest final aggregated path. Remove duplicate handling of parallel paths, because the cheapest path is either parallel or not, and we don't need to handle both together.
This is mostly needed for PR #6879 , where we introduce the unsorted DecompressChunk paths into consideration, and they are wrongly chosen as a basis for partial aggregation without regard for the cost of Sort over Append.
Disable-check: force-changelog-file