Speed up top_metrics on hot shards (backport of #70579) #70691
Merged
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
This moves `top_metrics` from global ordinals to segment ordinals which should should speed it up a ton on shards receiving a lot of writes at the cost of a little speed on shards that aren't receiving many writes. The rally tests on hot shards so the performance cost is between .5% and 5%: ``` | | before | after | diff | | | 50th percentile service time | 706.406 | 716.434 | 10.0277 | ms | | 90th percentile service time | 738.705 | 742.636 | 3.9311 | ms | | 100th percentile service time | 773.643 | 812.476 | 38.8331 | ms | ``` That seems worth it for 0 startup cost on hot shards. Closes elastic#70453
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 moves
top_metricsfrom global ordinals to segment ordinals whichshould should speed it up a ton on shards receiving a lot of writes at
the cost of a little speed on shards that aren't receiving many writes.
The rally tests on hot shards so the performance cost is between .5% and
5%:
That seems worth it for 0 startup cost on hot shards.
Closes #70453