Better fsync tracking. #13204
Labels
area/docdb
YugabyteDB core features
jira-originated
kind/enhancement
This is an enhancement of an existing feature
priority/medium
Medium priority issue
Jira Link: DB-2876
I see the following log 400k/h on one cluster.
This seems recessive. Maybe we can cap this log to at most once per second?
A better way to track this would be a distribution metric for fsync latency. This would give us better visibility and greatly reduce the cost of tracking that data.
The text was updated successfully, but these errors were encountered: