hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Zheng Shao (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-6433) Add AsyncDiskService that is used in both hdfs and mapreduce
Date Mon, 14 Dec 2009 08:46:18 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-6433?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12790043#action_12790043
] 

Zheng Shao commented on HADOOP-6433:
------------------------------------

AsyncDiskService is designed to work with multiple disk volumes, to make sure we have a maximum
number of threads per volume.
Both the use cases in HDFS and Mapreduce are like that.

I don't think it will be used outside this area in the near future - for non-multi-volume
disk operations, people will probably use a single thread pool instead of AsyncDiskService
(which contains multiple thread pools)

So I feel it's good to name it AsyncDiskService instead of AsyncService.

> Add AsyncDiskService that is used in both hdfs and mapreduce
> ------------------------------------------------------------
>
>                 Key: HADOOP-6433
>                 URL: https://issues.apache.org/jira/browse/HADOOP-6433
>             Project: Hadoop Common
>          Issue Type: New Feature
>            Reporter: Zheng Shao
>            Assignee: Zheng Shao
>         Attachments: HADOOP-6433.1.patch, HADOOP-6433.2.patch, HADOOP-6433.3.patch
>
>
> Both MAPREDUCE-1213 and HDFS-611 are using a class called AsyncDiskService.
> The idea is to create a thread pool per disk volume, and use that for scheduling async
disk operations.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message