[ https://issues.apache.org/jira/browse/YARN-5025?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15551451#comment-15551451 ]
ASF GitHub Bot commented on YARN-5025: -------------------------------------- GitHub user szape opened a pull request: https://github.com/apache/hadoop/pull/134 YARN-5025. Container move (relocation) between nodes Support for relocating containers has become a must-have requirement for most multi-service applications, since the inevitable concept-drifts make SLAs hard to be satisfied. The relocation and co-location of services (long running containers) can help to reduce bottlenecks in a multi-service cluster, especially where data-intensive, streaming applications interfere. You can merge this pull request into a Git repository by running: $ git pull https://github.com/szape/hadoop YARN-5025 Alternatively you can review and apply these changes as the patch at: https://github.com/apache/hadoop/pull/134.patch To close this pull request, make a commit to your master/trunk branch with (at least) the following in the commit message: This closes #134 ---- commit 5ada9ce8141265713d79f6c846d3aeb5d964fff5 Author: szape <nemderogator...@gmail.com> Date: 2016-09-15T09:48:19Z YARN-5025. Added container relocation logic to FifoScheduler commit ff1bdfd8e88e9f40db3109e9e3aa77d5264c4f3b Author: szape <nemderogator...@gmail.com> Date: 2016-09-16T10:15:17Z YARN-5025. Integrated container relocation feature into AMRMClient commit 260530caf17866a4fac3057406e4d5047080f4b4 Author: szape <nemderogator...@gmail.com> Date: 2016-09-19T09:50:55Z YARN-5025. Added and updated container management protocols for container relocation ---- > Container move (relocation) between nodes > ----------------------------------------- > > Key: YARN-5025 > URL: https://issues.apache.org/jira/browse/YARN-5025 > Project: Hadoop YARN > Issue Type: New Feature > Components: nodemanager, resourcemanager, yarn > Reporter: Zoltán Zvara > Attachments: YARN-Container-Move-(Relocation)-Between-Nodes.pdf > > > Support for relocating containers has become a must-have requirement for most > multi-service applications, since the inevitable concept-drifts make SLAs > hard to be satisfied. The relocation and co-location of services (long > running containers) can help to reduce bottlenecks in a multi-service > cluster, especially where data-intensive, streaming applications interfere. > See the high-level implementation details in the attached design document. -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org