[ https://issues.apache.org/jira/browse/MAPREDUCE-4049?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13413700#comment-13413700 ]
Avner BenHanoch commented on MAPREDUCE-4049: -------------------------------------------- Hi Arun, Thanks for your comperhensive review. I accept all your comments, and I'll provide new patch soon. I'll be happy to submit a corresponding patch for hadoop-2. Is it possible to start with hadoop-1 patch in order to have it on time for 1.1.0? - I'll be eager to do the hadoop-2 patch immediately after it. 1. We use taskDone/jobDone as optional messages to the plugin. We have experimental variant of the plugin that uses these messages for optimizing cache handling. 2. ok 3. I'll include mapred-default.xml in the patch. I'll use default values for the the new config. Thank you for working with me on it, Avner > plugin for generic shuffle service > ---------------------------------- > > Key: MAPREDUCE-4049 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-4049 > Project: Hadoop Map/Reduce > Issue Type: Improvement > Components: performance, task, tasktracker > Affects Versions: 1.0.3, 1.1.0, 2.0.0-alpha, 3.0.0 > Reporter: Avner BenHanoch > Labels: merge, plugin, rdma, shuffle > Attachments: HADOOP-1.0.2.patch, HADOOP-1.0.x.patch, > HADOOP-1.1.patch, HADOOP-1.x.y-review-oriented.patch, Hadoop Shuffle Consumer > Plugin TLD.rtf, Hadoop Shuffle Provider Plugin TLD.rtf, mapred-site.xml > > > Support generic shuffle service as set of two plugins: ShuffleProvider & > ShuffleConsumer. > This will satisfy the following needs: > # Better shuffle and merge performance. For example: we are working on > shuffle plugin that performs shuffle over RDMA in fast networks (10gE, 40gE, > or Infiniband) instead of using the current HTTP shuffle. Based on the fast > RDMA shuffle, the plugin can also utilize a suitable merge approach during > the intermediate merges. Hence, getting much better performance. > # Satisfy MAPREDUCE-3060 - generic shuffle service for avoiding hidden > dependency of NodeManager with a specific version of mapreduce shuffle > (currently targeted to 0.24.0). > References: > # Hadoop Acceleration through Network Levitated Merging, by Prof. Weikuan Yu > from Auburn University with others, > [http://pasl.eng.auburn.edu/pubs/sc11-netlev.pdf] > # I am attaching 2 documents with suggested Top Level Design for both plugins > (currently, based on 1.0 branch) -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira