Re-enable use_doc_values_skipper and add specialized lucene query for @timestamp field filtering.
#127260
Conversation
This file contains hidden or 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
martijnvg
added
>non-issue
:StorageEngine/Mapping
7 tasks
martijnvg
force-pushed
the
enable_use_doc_values_skipper_take_two
branch
from
d5bd0d1 to
21075f1
Compare
martijnvg
force-pushed
the
enable_use_doc_values_skipper_take_two
branch
from
506cbfc to
d2cf578
Compare
Member
Author
|
Elastic/logs run comparing main (baseline) to this branch (contender): The |
Member
Author
|
Looks the large regression are not caused by range queries on timestamp field ( A lot of time is spent at I suspect some specialization needs to be build for |
Additionally, updated the filter-by-filter optimization to make use of the new TimestampQuery.
iverase
reviewed
May 21, 2025
| return doc = target; | ||
| case MAYBE: | ||
| if (target > innerApproximation.docID()) { | ||
| target = innerApproximation.advance(target); |
Contributor
There was a problem hiding this comment.
I would expect to advance here the timestamps iterator instead of the innerApproximation.
Contributor
There was a problem hiding this comment.
I see now that it is equivalent. Would it make sense to make innerApproximation a NumericDocValues and remove the reference from the parent class?
iverase
reviewed
May 21, 2025
| case YES -> true; | ||
| case MAYBE -> { | ||
| final long value = timestamps.longValue(); | ||
| yield value >= minTimestamp && value <= maxTimestamp; |
Contributor
There was a problem hiding this comment.
if value < minTimestamp, we know we will not be matching any more documents, maybe we can move approximation.match to NO?
Contributor
There was a problem hiding this comment.
Although this is only true if we are always in the same primary sort.
Contributor
There was a problem hiding this comment.
I wonder if we should have two MAYBE options, one that we know we are always in the same primary sort and another one with mixed primary sort. In that case we can apply the optimization in the first case (which should be the common case).
Member
Author
There was a problem hiding this comment.
Interesting, let me take a look at this.
Contributor
|
fwiw: apache/lucene#14672 |
remove timestamp field from TimestampTwoPhaseIterator
martijnvg
force-pushed
the
enable_use_doc_values_skipper_take_two
branch
from
c4dcd96 to
7ca9a34
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Relates to #127263