You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hbase.apache.org by "stack (JIRA)" <ji...@apache.org> on 2016/06/03 00:37:59 UTC
[jira] [Commented] (HBASE-15948) Port "HADOOP-9956 RPC listener
inefficiently assigns connections to readers"
[ https://issues.apache.org/jira/browse/HBASE-15948?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15313402#comment-15313402 ]
stack commented on HBASE-15948:
-------------------------------
002 is after review of current state of hadoop Server... looks like it changed again since HADOOP-9956 using a LinkedBlockingQueue instead of ConcurrentLinkedQueue. Adds new "ipc.server.read.connection-queue.size" config for how many items to queue per Reader instance (this is distinct from "hbase.ipc.server.listen.queue.size" which is how many calls to queue on the socket)
> Port "HADOOP-9956 RPC listener inefficiently assigns connections to readers"
> -----------------------------------------------------------------------------
>
> Key: HBASE-15948
> URL: https://issues.apache.org/jira/browse/HBASE-15948
> Project: HBase
> Issue Type: Sub-task
> Components: IPC/RPC
> Reporter: stack
> Assignee: stack
> Attachments: HBASE-15948.master.001.patch, HBASE-15948.master.002.patch
>
>
> Esteban noticed we were missing this upstream issue. Seems to make no difference in profiling but here is the patch anyways.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)