[ https://issues.apache.org/jira/browse/HDFS-941?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13050609#comment-13050609 ]
Konstantin Shvachko commented on HDFS-941: ------------------------------------------ > I think it is reasonable to run tests against the latest patch and make sure > there is no regression in performance. This is exactly what I asked. That is to run DFSIO on 5-node cluster with and without the *new* patch. Here is the command I propose to run for 5 nodes (should have nrFile <= nrNodes). {code} TestDFSIO -read -fileSize 10GB -nrFiles 5 {code} You can run -write first to generate data. I think this will be representative enough. > it failed to reject the null hypothesis Great analysis Todd, I am truly impressed. Does everything run on one node? Is there any inter-DN communication then? Also with 128 MB file everything is in RAM, not sure what it measures. > Uncommitting now may do more harm than good. If my concerns can be addressed without uncommitting then I can hold on to that. Please confirm somebody is doing it. > Datanode xceiver protocol should allow reuse of a connection > ------------------------------------------------------------ > > Key: HDFS-941 > URL: https://issues.apache.org/jira/browse/HDFS-941 > Project: Hadoop HDFS > Issue Type: Improvement > Components: data-node, hdfs client > Affects Versions: 0.22.0 > Reporter: Todd Lipcon > Assignee: bc Wong > Fix For: 0.22.0 > > Attachments: 941.22.txt, 941.22.txt, 941.22.v2.txt, 941.22.v3.txt, > HDFS-941-1.patch, HDFS-941-2.patch, HDFS-941-3.patch, HDFS-941-3.patch, > HDFS-941-4.patch, HDFS-941-5.patch, HDFS-941-6.22.patch, HDFS-941-6.patch, > HDFS-941-6.patch, HDFS-941-6.patch, fix-close-delta.txt, hdfs-941.txt, > hdfs-941.txt, hdfs-941.txt, hdfs-941.txt, hdfs941-1.png > > > Right now each connection into the datanode xceiver only processes one > operation. > In the case that an operation leaves the stream in a well-defined state (eg a > client reads to the end of a block successfully) the same connection could be > reused for a second operation. This should improve random read performance > significantly. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira