Optimize numeric sort on match_all queries #49717
Closed
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 is a follow up of elastic#48804 where we rewrite numeric sort to use the DistanceFeatureQuery. This change adds another optimization if the query is a `match_all` that instead of using a distance feature query will simply extract the documents directly from the indexed point and early terminate as soon as enough docs have been collected. This optimization has a constant cost so it can be considerably faster than the other optimization since it only needs to visit the BKD-tree of a field and can early terminate as soon as it collected the number of requested hits. Note that this optimization can only work when the query is a match_all and the numeric sort order is not reversed. The pr is in WIP state, it needs more tests and some cleanup but I wanted to open it early in order to discuss whether we should pursue this path or not.
jimczi
added
>enhancement
WIP
:Search/Search
|
Pinging @elastic/es-search (:Search/Search) |
This was referenced Feb 3, 2020
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Outdated suggestions cannot be applied.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 is a follow up of #48804 where we rewrite numeric sort to use the DistanceFeatureQuery.
This change adds another optimization if the query is a
match_allthat instead of using a distance feature query will simply extract the documents directly from the indexed point and early terminate as soon as enough docs have been collected. This optimization has a constant cost so it can be considerably faster than the other optimization since it only needs to visit the BKD-tree of a field and can early terminate as soon as it collected the number of requested hits. Note that this optimization can only work when the query is a match_all and the numeric sort order is not reversed.The pr is in WIP state, it needs more tests and some cleanup but I wanted to open it early in order to discuss whether we should pursue this path or not.