[
https://issues.apache.org/jira/browse/HDFS-8901?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15010163#comment-15010163
]
Kai Zheng commented on HDFS-8901:
---------------------------------
bq. If that's the plan, ...
Yeah, it was planned and the patch worked the way.
bq. we can remove PositionStripeReader, and use StatefulStripeReader for pread.
StatefulStripeReader is good at reading stripe by stripe.
It's a good idea and same thought with me :). In fact I did it in HDFS-8957,
where I combined the two into a same path around that place. That patch is
relying on this one and ready for review. Maybe you could also take a look?
Thanks.
> Use ByteBuffer in striping positional read
> ------------------------------------------
>
> Key: HDFS-8901
> URL: https://issues.apache.org/jira/browse/HDFS-8901
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Reporter: Kai Zheng
> Assignee: Kai Zheng
> Attachments: HDFS-8901-v2.patch, initial-poc.patch
>
>
> Native erasure coder prefers to direct ByteBuffer for performance
> consideration. To prepare for it, this change uses ByteBuffer through the
> codes in implementing striping position read. It will also fix avoiding
> unnecessary data copying between striping read chunk buffers and decode input
> buffers.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
