[
https://issues.apache.org/jira/browse/HDFS-8901?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15438885#comment-15438885
]
SammiChen commented on HDFS-8901:
---------------------------------
For question 4, why flip is not needed before? The reason is previously,
positional reader use a byte array wrapped buffer as read buffer. Then later
code use byte array to access the fetched data. And for stateful reader,
previously it has already reset the buffer position by {{
decodeInputs[i].position(0) }} before decoding.
And one complement for question 6. ByteBuffer is also used in decode function
in positional reader, to hold parity content.
> 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: SammiChen
> Attachments: HDFS-8901-v10.patch, HDFS-8901-v2.patch,
> HDFS-8901-v3.patch, HDFS-8901-v4.patch, HDFS-8901-v5.patch,
> HDFS-8901-v6.patch, HDFS-8901-v7.patch, HDFS-8901-v8.patch,
> HDFS-8901-v9.patch, HDFS-8901.v11.patch, HDFS-8901.v12.patch,
> HDFS-8901.v13.patch, HDFS-8901.v14.patch, HDFS-8901.v15.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)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
