[
https://issues.apache.org/jira/browse/HDFS-16113?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
JiangHua Zhu reassigned HDFS-16113:
-----------------------------------
Assignee: (was: JiangHua Zhu)
> Improve CallQueueManager#swapQueue() execution performance
> ----------------------------------------------------------
>
> Key: HDFS-16113
> URL: https://issues.apache.org/jira/browse/HDFS-16113
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: JiangHua Zhu
> Priority: Minor
>
> In CallQueueManager#swapQueue(), there are some codes:
> CallQueueManager#swapQueue() {
> ......
> while (!queueIsReallyEmpty(oldQ)) {}
> ......
> }
> In queueIsReallyEmpty():
> ......
> for (int i = 0; i <CHECKPOINT_NUM; i++) {}
> ...
> We found that this implementation has certain performance hindrances in real
> clusters.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
