-
Notifications
You must be signed in to change notification settings - Fork 742
scheduler: fix anticount and improving the Robustness of Hotspot Statistics #3928
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
Conversation
[REVIEW NOTIFICATION] This pull request has been approved by:
To complete the pull request process, please ask the reviewers in the list to review by filling The full list of commands accepted by this bot can be found here. Reviewer can indicate their review by submitting an approval review. |
Codecov Report
@@ Coverage Diff @@
## master #3928 +/- ##
==========================================
+ Coverage 74.55% 74.68% +0.13%
==========================================
Files 246 246
Lines 25064 25068 +4
==========================================
+ Hits 18686 18722 +36
+ Misses 4713 4695 -18
+ Partials 1665 1651 -14
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
/merge |
@nolouch: It seems you want to merge this PR, I will help you trigger all the tests: /run-all-tests Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the ti-community-infra/tichi repository. |
This pull request has been accepted and is ready to merge. Commit hash: aaeaab9
|
…istics (tikv#3928) * update Signed-off-by: lhy1024 <admin@liudos.us> * fix test Signed-off-by: lhy1024 <admin@liudos.us> Co-authored-by: Ti Chi Robot <ti-community-prow-bot@tidb.io>
Signed-off-by: lhy1024 admin@liudos.us
What problem does this PR solve?
it is similiar with #3707, After getting the hot read peer information from store heartbeat, a region that previously took two minutes to get cold will take only 20 seconds to get cold, so that the balance leader scheduler will go to the balance hotspot for a more variable load.
for read-peer/write-peer/write-store, the period of filter is 5, but it is 3 for read store.
What is changed and how it works?
Check List
Tests
Release note