[
https://issues.apache.org/jira/browse/HADOOP-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12484545
]
Raghu Angadi commented on HADOOP-1134:
--------------------------------------
>> 64KB is only for new blocks.
> I thought we'd benchmark before we changed any parameters, no? I'd vote to
> keep this at 512 until we benchmark.
I am fine with keeping it at 512. default config will not change then. Bigger
motivation for me to run good benchmarks :-)
> This sounds like another change we should benchmark before we make.
I think this is as much a policy decision as it is a performance decision. Do
we ever want datanode to ship corrupted data? If the benchmarks don't show any
negative effect of double checksum on real clusters, would that be enough?
If source datanode does not check for errors, how would you propose we handle
CRC errors while transferring to another datanode? I guess, destination
datanode should report the problem.
> 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.
