[
https://issues.apache.org/jira/browse/HDFS-8668?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15339708#comment-15339708
]
Liran Oz commented on HDFS-8668:
--------------------------------
Hi Kai,
I tried to use the native EC coder with hadoop-3.0.0-alpha1. so i applied the
relevant patch from HADOOP-11540 but i have noticed that every encode/decode
operation requires additional copy because the byteBuffer were not direct.
As i understand, HDFS-8668 patch should allocate direct ByteBuffers for the
native coder - but i did not managed to apply it.
Thank you for your response.
Liran.
> Erasure Coding: revisit buffer used for encoding and decoding.
> --------------------------------------------------------------
>
> Key: HDFS-8668
> URL: https://issues.apache.org/jira/browse/HDFS-8668
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Reporter: Yi Liu
> Assignee: Kai Zheng
> Attachments: HDFS-8668-v1.patch, HDFS-8668-v2.patch
>
>
> For encoding and decoding buffers, currently some places use java heap
> ByteBuffer, some use direct byteBUffer, and some use java byte array. If
> the coder implementation is native, we should use direct ByteBuffer. This
> jira is to revisit all encoding/decoding buffers and improve them.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
