-
Notifications
You must be signed in to change notification settings - Fork 735
Fix excessive read latency during and after shard splits #11059
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
|
⚪ Test history | Ya make output | Test bloat
⚪ Test history | Ya make output | Test bloat | Test bloat
🟢
*please be aware that the difference is based on comparing your commit and the last completed build from the post-commit, check comparation |
|
⚪ Test history | Ya make output | Test bloat
🟢
*please be aware that the difference is based on comparing your commit and the last completed build from the post-commit, check comparation |
Changelog entry
Fixed excessive read latency during and after some shard splits.
Changelog category
Additional information
It was observed that reads sometimes take seconds during frequent shard splits. Turns out shards replied with an
OVERLOADEDstatus even after split has already finished, which caused KQP to retry reads repeatedly with an exponential backoff, until eventually a guard condition (after multiple seconds) would cause read actor to finally re-resolve the table again. A correctNOT_FOUNDstatus (which indicates the table no longer exists) fixes this problem.Fixes #11036.