[ https://issues.apache.org/jira/browse/HDFS-13274?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17114997#comment-17114997 ]
Janus Chow commented on HDFS-13274: ----------------------------------- By "full stack of the NN", you mean the thread dump? Since there is no error where it happens. Some statics: 1. Max pool size on routers: 500. 2. Router count: 16. 3. NumConnections on NN: 30K. 4 Connections on Router: Above 2K. [~elgoiri] Do you have some best practice on the setting of max-pool size for routers? We set it to 500 because there is a very large "ProxyAvg" from the metrics, about hundreds of milliseconds. > RBF: Extend RouterRpcClient to use multiple sockets > --------------------------------------------------- > > Key: HDFS-13274 > URL: https://issues.apache.org/jira/browse/HDFS-13274 > Project: Hadoop HDFS > Issue Type: Sub-task > Reporter: Íñigo Goiri > Assignee: Íñigo Goiri > Priority: Major > > HADOOP-13144 introduces the ability to create multiple connections for the > same user and use different sockets. The RouterRpcClient should use this > approach to get a better throughput. -- 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