[jira] Commented: (HADOOP-1707) Remove the DFS Client disk-based cache

["Mukund Madhugiri (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HADOOP-1707?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12558041#action_12558041 ] 

Mukund Madhugiri commented on HADOOP-1707:
------------------------------------------

Running on a 100 node cluster, with the patch clientDiskBuffer19.patch, the sort benchmark showed these results:

|*100 nodes*|*trunk*|*trunk + patch*|
|randomWriter (hrs)|0.44|0.45|
|sort (hrs)|1.03|1|
|sortValidation (hrs)|0.39|0.3|

> Remove the DFS Client disk-based cache
> --------------------------------------
>
>                 Key: HADOOP-1707
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1707
>             Project: Hadoop
>          Issue Type: Improvement
>          Components: dfs
>            Reporter: dhruba borthakur
>            Assignee: dhruba borthakur
>             Fix For: 0.16.0
>
>         Attachments: clientDiskBuffer.patch, clientDiskBuffer10.patch, clientDiskBuffer11.patch, clientDiskBuffer12.patch, clientDiskBuffer14.patch, clientDiskBuffer15.patch, clientDiskBuffer16.patch, clientDiskBuffer17.patch, clientDiskBuffer18.patch, clientDiskBuffer19.patch, clientDiskBuffer2.patch, clientDiskBuffer6.patch, clientDiskBuffer7.patch, clientDiskBuffer8.patch, clientDiskBuffer9.patch, DataTransferProtocol.doc, DataTransferProtocol.html
>
>
> The DFS client currently uses a staging file on local disk to cache all user-writes to a file. When the staging file accumulates 1 block worth of data, its contents are flushed to a HDFS datanode. These operations occur sequentially.
> A simple optimization of allowing the user to write to another staging file while simultaneously uploading the contents of the first staging file to HDFS will improve file-upload performance.

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