-
Notifications
You must be signed in to change notification settings - Fork 734
24-3: Fix excessive read latency during and after shard splits #11061
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
24-3: Fix excessive read latency during and after shard splits #11061
Conversation
|
⚪
🟢
*please be aware that the difference is based on comparing your commit and the last completed build from the post-commit, check comparation |
|
⚪
🟢
*please be aware that the difference is based on comparing your commit and the last completed build from the post-commit, check comparation |
|
По зафейлившимся тестам, посмотрел более ранние PR в 24-3, там те же тесты фейлятся. |
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.