[
https://issues.apache.org/jira/browse/HADOOP-13426?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15405980#comment-15405980
]
Kihwal Lee commented on HADOOP-13426:
-------------------------------------
+1 lgtm.
> More efficiently build IPC responses
> ------------------------------------
>
> Key: HADOOP-13426
> URL: https://issues.apache.org/jira/browse/HADOOP-13426
> Project: Hadoop Common
> Issue Type: Sub-task
> Reporter: Daryn Sharp
> Assignee: Daryn Sharp
> Attachments: HADOOP-13426.1.patch, HADOOP-13426.patch
>
>
> The call response buffer is allowed to dynamically grow until a max size is
> reached. Often times the full size of the response can be known in advance
> which avoids copies. This is very advantageous for large responses.
> Automatic framing of the response buffer will also prevent unnecessary
> allocations and copies when the size is/isn't known.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
