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] Commented: (HADOOP-1134) Block level CRCs in HDFS
Date Fri, 01 Jun 2007 18:21:16 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-1134?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12500795
] 

Raghu Angadi commented on HADOOP-1134:
--------------------------------------


bq. It's a minor point, but if we write async-io daemons for this protocol then the easier
it is to parse the total packet length the easier it will be to write these daemons. So placing
the total packet length in a fixed position at the front of the packet so that it may be generically
accessed without having to determine what kind of a packet it is, will simplify things.

Agreed. Btw, these are not really packets in any sense. These are streams with typical lengths
of  100s of MB. Of course each DATA_CHUNK is like packet and it does include a length. Though
using Vints negates simplicity of Async reading. In fact, knowing lengths for DATA_CHUNK helps
even non-async processing and new code uses the length heavily.

We might even get rid of Initial length (or set it to -1) for OP_WRITE_BLOCK if we want to
move to streaming block to DN in parallel to client's writes (instead of transferring the
whole block inside endBlock()).


> 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: bc-no-upgrade-05302007.patch, DfsBlockCrcDesign-05305007.htm
>
>
> 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