[ http://issues.apache.org/jira/browse/HADOOP-195?page=comments#action_12378340 ]
paul sutter commented on HADOOP-195: ------------------------------------ Owen, Mike Ovsiannikov had a great suggestion. Can you check netstat for TIME_WAIT sessions during the slowdown? Maybe the system is running out of sockets (ports), 64,000 connects per reducer is a lot of connections. If you are accumulating zillions of TIME_WAIT sessions, you might want to try to experiment with the following: net.ipv4.tcp_tw_reuse net.ipv4.tcp_tw_recycle That histogram that you have.. can you show that as a time-series? Does it go really fast at first, and then bog down? It might also be good to instrument the time it takes to connect versus transfer versus close, etc. Paul > transfer map output transfer with http instead of rpc > ----------------------------------------------------- > > Key: HADOOP-195 > URL: http://issues.apache.org/jira/browse/HADOOP-195 > Project: Hadoop > Type: Improvement > Components: mapred > Versions: 0.2 > Reporter: Owen O'Malley > Assignee: Owen O'Malley > Fix For: 0.3 > > The data transfer of the map output should be transfered via http instead > rpc, because rpc is very slow for this application and the timeout behavior > is suboptimal. (server sends data and client ignores it because it took more > than 10 seconds to be received.) -- This message is automatically generated by JIRA. - If you think it was sent incorrectly contact one of the administrators: http://issues.apache.org/jira/secure/Administrators.jspa - For more information on JIRA, see: http://www.atlassian.com/software/jira
