hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "dhruba borthakur (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-2780) Socket receive buffer size on datanode too large
Date Fri, 08 Feb 2008 06:47:08 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-2780?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12566936#action_12566936

dhruba borthakur commented on HADOOP-2780:

This is a "performance improvement" fix rather than a bug fix. I do not expect to have a unit
test for this one (unless anybody in QA thinks otherwise). 

> Socket receive buffer size on datanode too large
> ------------------------------------------------
>                 Key: HADOOP-2780
>                 URL: https://issues.apache.org/jira/browse/HADOOP-2780
>             Project: Hadoop Core
>          Issue Type: Bug
>          Components: dfs
>            Reporter: dhruba borthakur
>            Assignee: dhruba borthakur
>             Fix For: 0.16.1
>         Attachments: socketBufferSize.patch
> HADOOP-1707 introduced code that created the socket receive buffer size to be 1MB by
default. This should be changed back to 128K.

This message is automatically generated by JIRA.
You can reply to this email to add a comment to the issue online.

View raw message