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-7837) Erasure Coding: allocate and persist striped blocks in NameNode
Date Sat, 28 Feb 2015 06:12:05 GMT

    [ https://issues.apache.org/jira/browse/HDFS-7837?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14341371#comment-14341371
] 

Zhe Zhang commented on HDFS-7837:
---------------------------------

Continued review:
# I read the code again and figured out {{BlocksMap#removeBlock}}; never mind. 
# One concern is that a large portion of added logic for {{BlockInfoStriped}} is around indexing
into {{triplets}}. The NN optimization work HDFS-6658 is likely to change the structure significantly.
We should probably start thinking about it..
# {{FSNamesystem}}: "TODO we need block placement policy for striped block groups", the JIRA
is HDFS-7613

The rest looks good. Thanks again for the good work!

> Erasure Coding: allocate and persist striped blocks in NameNode
> ---------------------------------------------------------------
>
>                 Key: HDFS-7837
>                 URL: https://issues.apache.org/jira/browse/HDFS-7837
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>            Reporter: Jing Zhao
>            Assignee: Jing Zhao
>         Attachments: HDFS-7837.000.patch
>
>
> Try to finish the remaining work from HDFS-7339 (except the ClientProtocol/DFSClient
part):
> # Allow FSNamesystem#getAdditionalBlock to create striped blocks and persist striped
blocks to editlog
> # Update FSImage for max allocated striped block ID
> # Update the block commit/complete logic in BlockManager



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

Mime
View raw message