[jira] [Resolved] (HDFS-6934) Move checksum computation off the hot path when writing to RAM disk

["Chris Nauroth (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/HDFS-6934?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Chris Nauroth resolved HDFS-6934.
---------------------------------
       Resolution: Fixed
    Fix Version/s: 2.6.0

I have committed this to trunk, branch-2 and branch-2.6.  Xiaoyu and Nicholas, thank you for the code reviews.

bq. In such case, we should cherry-pick the trunk commit and resolve the merge manually.

Yes, this is how I handled it, so you'll see it show up in the branch-2.6 commit log as a cherry-pick.  The merge conflict was just enough that I thought it would be best to seek another +1 before pushing it up.  Thanks again!

> Move checksum computation off the hot path when writing to RAM disk
> -------------------------------------------------------------------
>
>                 Key: HDFS-6934
>                 URL: https://issues.apache.org/jira/browse/HDFS-6934
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>          Components: datanode, hdfs-client
>            Reporter: Arpit Agarwal
>            Assignee: Chris Nauroth
>             Fix For: 2.6.0
>
>         Attachments: HDFS-6934-branch-2.6.5.patch, HDFS-6934.3.patch, HDFS-6934.4.patch, HDFS-6934.5.patch, h6934_20141003b.patch, h6934_20141005.patch
>
>
> Since local RAM is considered reliable we can avoid writing checksums on the hot path when replicas are being written to a local RAM disk.
> The checksum can be computed by the lazy writer when moving replicas to disk.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)