[ 
https://issues.apache.org/jira/browse/HDFS-3702?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14220259#comment-14220259
 ] 

stack commented on HDFS-3702:
-----------------------------

Nice. Thanks for picking this up [~eddyxu] again.

nit: why have the temporary tempExcluded variable in below?

1369              DatanodeInfo[] tempExcluded = ObjectArrays.concat(
1370                  excluded, excludedLocalNodes, DatanodeInfo.class);
1371              excluded = tempExcluded;

Would be coolio if at least a trace logging I could enable for a few seconds to 
ensure this feature was working properly when enabled?

Are there other cases in the codebase that you know of where the DN 
NetUtils.getHostname() works as a key for finding the datanode info in the NN?

As I read it, we are doing an extra trip to the NN when we open a DFSOS with 
AVOID_LOCAL_COPY set? No means of doing doing this once only or once every so 
often rather than on each time (not a blocker for the hbase case I'd say but 
would be good to avoid or mitigate if possible).

Thanks again for working on this one.



> Add an option for NOT writing the blocks locally if there is a datanode on 
> the same box as the client
> -----------------------------------------------------------------------------------------------------
>
>                 Key: HDFS-3702
>                 URL: https://issues.apache.org/jira/browse/HDFS-3702
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: hdfs-client
>    Affects Versions: 2.5.1
>            Reporter: Nicolas Liochon
>            Assignee: Lei (Eddy) Xu
>            Priority: Minor
>         Attachments: HDFS-3702.000.patch, HDFS-3702.001.patch
>
>
> This is useful for Write-Ahead-Logs: these files are writen for recovery 
> only, and are not read when there are no failures.
> Taking HBase as an example, these files will be read only if the process that 
> wrote them (the 'HBase regionserver') dies. This will likely come from a 
> hardware failure, hence the corresponding datanode will be dead as well. So 
> we're writing 3 replicas, but in reality only 2 of them are really useful.



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

Reply via email to