[
https://issues.apache.org/jira/browse/HADOOP-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12483297
]
Raghu Angadi commented on HADOOP-1134:
--------------------------------------
I think I need a little bit more clarification : There are multiple tasks:
Client :
--------
a) It needs confidence DFS stores the data it writes and gets back the same
data when it reads.
1) For client to be _absolutely_ sure of this, we need the current .crc
files i.e. client is assuming the responsibility of maintaining checksums
2) current proposal slightly relaxes this and expects the clients to
trust DFS to maintain data to best of its ability and try client's best to
verify it. ie, trusts that DN verifies checksum that client calculates while
writing, and maintains it after that etc.
If (2) is not acceptable, then probably we don't need block level checksums.
> 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.
