[
https://issues.apache.org/jira/browse/HDFS-7782?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14381430#comment-14381430
]
Zhe Zhang commented on HDFS-7782:
---------------------------------
bq. I guess in the end we do not need the serial read?
I agree. If the pread request spans multiple cells we should always read in
parallel. Do you think we should limit the number of parallel read threads?
Maybe at this stage we can simply have a thread pool sized at {{groupSize}} for
each input stream. Later we can decide if we want to move the pool to DFSClient
and limit the pool size.
> Read a striping layout file from client side
> --------------------------------------------
>
> Key: HDFS-7782
> URL: https://issues.apache.org/jira/browse/HDFS-7782
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Reporter: Li Bo
> Assignee: Zhe Zhang
> Attachments: HDFS-7782-000.patch, HDFS-7782-001.patch,
> HDFS-7782-002.patch, HDFS-7782-003.patch, HDFS-7782-004.patch
>
>
> If client wants to read a file, he is not necessary to know and handle what
> layout the file is. This sub task adds logic to DFSInputStream to support
> reading striping layout files.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
