[
https://issues.apache.org/jira/browse/HADOOP-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12486492
]
Raghu Angadi commented on HADOOP-1134:
--------------------------------------
Not generating missing CRCs sounds fine and in the initial release datanode
will not delete any blocks for checksum reasons.
> That assumes that the checksum is validated, doesn't it? And we're not yet
> validating checksums except in the client,
Please confirm the desired behaviour in normal operation (after upgrade) : Two
options I have seen till now:
1) Datanode does not verify any checksums anytime. This might or might not
change in future.
2) Datanode also verifies checksums while receiving and sending data. It closes
the client connection if checksum does not match while receiving from client.
In short term, it at most prints a warning for checksum errors while sending
data and does not report the error.
Doug, I guess you are proposing (1). Though I prefer (2), I am ok with (1). If
this is not true I would like to know what the desired behavior is.
> 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.
