[jira] Commented: (HADOOP-1702) Reduce buffer copies when data is written to DFS

["Hairong Kuang (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HADOOP-1702?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12594735#action_12594735 ] 

Hairong Kuang commented on HADOOP-1702:
---------------------------------------

A few initial comments:
1. Once Packet.getBuffer() is called, no more data can be written to packet. This is not obvious to code readers. Better add this restriction to the comment.
2. packetSize/writePacketSize in DFSClient don't include the size of the packet header. I think it is better to rename them to packetPayloadSize/writePacketPayloadSize.
3. The packet size guess calculation in DataNode should match the calculation in DFSClient.

> Reduce buffer copies when data is written to DFS
> ------------------------------------------------
>
>                 Key: HADOOP-1702
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1702
>             Project: Hadoop Core
>          Issue Type: Bug
>          Components: dfs
>    Affects Versions: 0.14.0
>            Reporter: Raghu Angadi
>            Assignee: Raghu Angadi
>             Fix For: 0.18.0
>
>         Attachments: HADOOP-1702.patch, HADOOP-1702.patch, HADOOP-1702.patch, HADOOP-1702.patch, HADOOP-1702.patch
>
>
> HADOOP-1649 adds extra buffering to improve write performance.  The following diagram shows buffers as pointed by (numbers). Each eatra buffer adds an extra copy since most of our read()/write()s match the io.bytes.per.checksum, which is much smaller than buffer size.
> {noformat}
>        (1)                 (2)          (3)                 (5)
>    +---||----[ CLIENT ]---||----<>-----||---[ DATANODE ]---||--<>-> to Mirror  
>    | (buffer)                  (socket)           |  (4)
>    |                                              +--||--+
>  =====                                                    |
>  =====                                                  =====
>  (disk)                                                 =====
> {noformat}
> Currently loops that read and write block data, handle one checksum chunk at a time. By reading multiple chunks at a time, we can remove buffers (1), (2), (3), and (5). 
> Similarly some copies can be reduced when clients read data from the DFS.

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