[
https://issues.apache.org/jira/browse/HDFS-8901?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15438489#comment-15438489
]
SammiChen commented on HDFS-8901:
---------------------------------
Hi Zhe,
Thanks for your great effort to review the patch. Very good suggestions. Here
is my thoughts.
1. the piece of code will be moved to BlockReaderUtil, create a new readAll
function for it.
2. will be handled.
3. Yes. we are planning to add a ByteBuffer version read API
4. good question, I'm double checking the code. And will share my finding later.
5. will be handled.
6. Every StripingChunk will have either a ChunkByteBuffer or a ByteBuffer to
track different buffer source. ChunkByteBuffer will be used when reusing user
input buffer as the striping read buffer during positional read. And ByteBuffer
will be used when read using stateful strip reader.
7. the memory copy is avoid in case chunk.useChunkBuffer is not true, that's an
improvement.
> 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, 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: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
