[ 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: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org