[ https://issues.apache.org/jira/browse/YARN-2314?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14170026#comment-14170026 ]
Wangda Tan commented on YARN-2314: ---------------------------------- Hi [~jlowe], Looking at this issue recently. I think it will be not easy to change the under layer of RPC. One question, according to the patch you mentioned in https://issues.apache.org/jira/browse/YARN-2314?focusedCommentId=14131901&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-14131901, do you have any data about is there any performance downgrade of this patch in your environment? I'm wondering if we can just disable the cache and make the timeout to 0 as the standard behavior. Thanks, Wangda > ContainerManagementProtocolProxy can create thousands of threads for a large > cluster > ------------------------------------------------------------------------------------ > > Key: YARN-2314 > URL: https://issues.apache.org/jira/browse/YARN-2314 > Project: Hadoop YARN > Issue Type: Bug > Components: client > Affects Versions: 2.1.0-beta > Reporter: Jason Lowe > Priority: Critical > Attachments: disable-cm-proxy-cache.patch, > nmproxycachefix.prototype.patch > > > ContainerManagementProtocolProxy has a cache of NM proxies, and the size of > this cache is configurable. However the cache can grow far beyond the > configured size when running on a large cluster and blow AM address/container > limits. More details in the first comment. -- This message was sent by Atlassian JIRA (v6.3.4#6332)