ozone
ozone copied to clipboard
HDDS-6775. Add more performance logs to DataNode disk/container operations
What changes were proposed in this pull request?
Log warnings if any DataNode request handler spends more than 300ms, or if any block read/write takes more than 300ms.
What is the link to the Apache JIRA
https://issues.apache.org/jira/browse/HDDS-6775
How was this patch tested?
Tested on a standalone cluster that has severe disk latency problem.
cc @duongnguyen0
LGTM.