-
Notifications
You must be signed in to change notification settings - Fork 48
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
Hashing query performance improvements (1.5-2x faster on benchmarks) #114
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
Benchmark Results
|
Benchmark Results
|
Benchmark Results
|
Benchmark Results
|
Benchmark Results
|
Benchmark Results
|
Benchmark Results
|
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Outdated suggestions cannot be applied.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.
Rewrote custom hashing query (
MatchHashesAndScoreQuery
) in Java.This doesn't necessarily make it faster, rather less likely that you introduce an expensive scala abstraction.
Also easier to get help from Lucene users.
Made match counting faster by using an array instead of a map.
This works because each counter only deals with the consecutive doc ids in a single segment.
So instead of a Map from doc id to count, you have an array where the index is the doc id and value is the count.
Made candidate identification faster using a similar construct.
Since you know the highest possible count is the number of terms, you can us an array to build a histogram of the counts,
then traverse from the end of the array to find the kth largest count.
Still need to understand how the
PrefixCodedTerms
work and if there's any possible optimization.Specific timing improvements (p90 benchmark times):