lordcheng10 opened a new pull request #2973: URL: https://github.com/apache/bookkeeper/pull/2973
### Motivation When checkAllLedgers is scheduled periodically, because it will try to read almost all entry data, it may cause the bookkeeper to time out and cause the entry to be incorrectly marked with markLedgerUnderreplicatedAsync. In our cluster, the execution cycle of checkAllLedgers is 1 week. Then we found that a large number of ledger will be marked markLedgerUnderreplicatedAsync each time it is executed. Analyzing the log found that there are some reading bookkeeper timeouts:   Due to too many read requests, the cluster pressure is too high, and the latency of pulsar's write time continues to soar until the recovery is completed.：  -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
