[
https://issues.apache.org/jira/browse/HADOOP-11514?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14296323#comment-14296323
]
Kai Zheng commented on HADOOP-11514:
------------------------------------
Hi [~anu],
Thanks for you question.
bq. how does it know if the ECBlock (or ECChunk) is valid ?
In high level constructs like ECManager, it will check EC blocks are healthy or
not (like lost at all due to DataNode failure or corrupt by block checksum
detected), if some block is found in question then the erasure codec framework
will play in the work and this *RawErasureCoder* will be involved. The bad
block will be marked as isErasred being true and the codec/coder will know
which block in a ECGroup or BlockGroup is to be recovered, and then ECChunks
will be extracted for decoding.
> Raw Erasure Coder API for concrete encoding and decoding
> --------------------------------------------------------
>
> Key: HADOOP-11514
> URL: https://issues.apache.org/jira/browse/HADOOP-11514
> Project: Hadoop Common
> Issue Type: Sub-task
> Affects Versions: HDFS-EC
> Reporter: Kai Zheng
> Assignee: Kai Zheng
> Attachments: HDFS-7353-v1.patch, HDFS-7353-v2.patch,
> HDFS-7353-v3.patch, HDFS-7353-v4.patch, HDFS-7353-v5.patch,
> HDFS-7353-v6.patch, HDFS-7353-v7.patch
>
>
> This is to abstract and define raw erasure coder API across different codes
> algorithms like RS, XOR and etc. Such API can be implemented by utilizing
> various library support, such as Intel ISA library and Jerasure library.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
