[
https://issues.apache.org/jira/browse/HDFS-2243?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13082646#comment-13082646
]
Todd Lipcon commented on HDFS-2243:
-----------------------------------
BTW, you may want to also look into SocketIOWithTimeout - I think we're doing
some dumb things with the way we use epoll, etc. I've tried to hack it out but
couldn't quite get the NIO magic right. Do you see epoll_wait taking a lot of
systime?
> DataXceiver per accept seems to be a bottleneck in HBase/YCSB test
> ------------------------------------------------------------------
>
> Key: HDFS-2243
> URL: https://issues.apache.org/jira/browse/HDFS-2243
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: data-node
> Affects Versions: 0.23.0
> Environment: Using Fedora 14 on a quad core phenom system
> Reporter: Eric Caspole
> Priority: Minor
>
> I am running the YCSB benchmark against HBase, sometimes against a single
> node, sometimes against a cluster of 6 systems. As the load increases into
> thousands of TPS, especially on the single node, I can see that the datanode
> runs very high system time and seems to be bottlenecked by how fast it can
> create the threads to handle the new connections in DataXceiverServer.run. By
> "perf top" I can see the process spends about 12% of all its time in
> pthread_create, and in hprof profiles I can see there are tens of thousands
> of threads created in just a few minutes of test execution.
> Does anyone else observe this bottleneck? Is there a major challenge to using
> a thread pool of DataXceivers in this situation?
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
