hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Zhe Zhang (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-7613) Block placement policy for erasure coding groups
Date Tue, 12 May 2015 19:25:01 GMT

    [ https://issues.apache.org/jira/browse/HDFS-7613?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14540539#comment-14540539

Zhe Zhang commented on HDFS-7613:

Thanks for the feedback [~djp] and sorry about getting to this late.

bq. not sure if BlockPlacementPolicyDefault can meet all cases that BlockPlacementPolicyEC
should be there.
As discussed under HDFS-7891, EC has a higher requirement on rack-aware distribution, which
{{BlockPlacementPolicyDefault}} doesn't quite satisfy.

bq. Also, I see BlockPlacementPolicyEC support rack layer only, do we have plan to support
NodeGroup layer as well? It would be great to make EC can be suitable for broader scenarios.
[~walter.k.su] might be able to provide more insights. ASAIK we haven't implemented logic
for NodeGroup yet. I think it will be an interesting addition.

Right now we are still focusing on the EC-specific algorithm, and will revisit the multi-policy
proposal a little later.

> Block placement policy for erasure coding groups
> ------------------------------------------------
>                 Key: HDFS-7613
>                 URL: https://issues.apache.org/jira/browse/HDFS-7613
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>            Reporter: Zhe Zhang
>            Assignee: Walter Su
>         Attachments: HDFS-7613.001.patch
> Blocks in an erasure coding group should be placed in different failure domains -- different
DataNodes at the minimum, and different racks ideally.

This message was sent by Atlassian JIRA

View raw message