hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Raghu Angadi (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HADOOP-1134) Block level CRCs in HDFS
Date Sat, 07 Jul 2007 01:14:04 GMT

     [ https://issues.apache.org/jira/browse/HADOOP-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Raghu Angadi updated HADOOP-1134:
---------------------------------

    Attachment: BlockLevelCrc-07062007.patch

Attaching the latest patch (07062007) for weekend perusal :)

This one extends FSInputChecker for BlockReader class in DFSClient.

This does not use FSOutputSummer.

Doug, I don't think it is really necessary for my application. It probably removes 5 lines
and adds whatever is required for using the inteface. Also, for writes smaller than bytesPerChecksum,
FSOutputSummer buffers once more. This extra buffering is sort of required for InputChecker
but not really required while writing, since writing is very simple. I hope that is ok. I
wonder how big are map-reduce writes?

> Block level CRCs in HDFS
> ------------------------
>
>                 Key: HADOOP-1134
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1134
>             Project: Hadoop
>          Issue Type: New Feature
>          Components: dfs
>            Reporter: Raghu Angadi
>            Assignee: Raghu Angadi
>         Attachments: BlockLevelCrc-07032007.patch, BlockLevelCrc-07052007.patch, BlockLevelCrc-07062007.patch,
BlockLevelCrc-07062007.patch, DfsBlockCrcDesign-05305007.htm, readBuffer.java
>
>
> Currently CRCs are handled at FileSystem level and are transparent to core HDFS. See
recent improvement HADOOP-928 ( that can add checksums to a given filesystem ) regd more about
it. Though this served us well there a few disadvantages :
> 1) This doubles namespace in HDFS ( or other filesystem implementations ). In many cases,
it nearly doubles the number of blocks. Taking namenode out of CRCs would nearly double namespace
performance both in terms of CPU and memory.
> 2) Since CRCs are transparent to HDFS, it can not actively detect corrupted blocks. With
block level CRCs, Datanode can periodically verify the checksums and report corruptions to
namnode such that name replicas can be created.
> We propose to have CRCs maintained for all HDFS data in much the same way as in GFS.
I will update the jira with detailed requirements and design. This will include same guarantees
provided by current implementation and will include a upgrade of current data.
>  

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


Mime
View raw message