[
https://issues.apache.org/jira/browse/HADOOP-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12483325
]
Raghu Angadi commented on HADOOP-1134:
--------------------------------------
I think thinner and more detached the client is, better in long term. DFSClient
is not part of DFS cluster, because it is not expected to be up and running
when cluster is running. Tighter the coupling, more difficult it will be to
implement new features in future.
I don't think the issue is just about where the checksums are stored. I
interpreted as: DFS (excluding the DFSClient) will be aware of and in complete
control of how data is stored and its integrity is maintained. To me it does
not sound right if DFS can't change how its data is maintained in future. Of
course DFS still needs to be able to serve data it is supposed to serve.. thats
its fundamental duty.
Just my thoughts.. will ask more issue specific questions soon.
> 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
> Assigned To: Raghu Angadi
>
> 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.
