Mailing-List: contact hbase-dev-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hbase-dev@hadoop.apache.org
Message-ID: <668726402.1216689031851.JavaMail.jira@brutus>
Date: Mon, 21 Jul 2008 18:10:31 -0700 (PDT)
From: "Billy Pearson (JIRA)" <jira@apache.org>
To: hbase-dev@hadoop.apache.org
Subject: [jira] Commented: (HBASE-745) scaling of one regionserver,
 improving memory and cpu usage
In-Reply-To: <5532016.1216108771834.JavaMail.jira@brutus>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/HBASE-745?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12615487#action_12615487 ] 

Billy Pearson commented on HBASE-745:
-------------------------------------

now that I thank about it I thank I tryed a older version of trunk my mistake it applys to trunk.
When do you thank we can see this committed?

> scaling of one regionserver, improving memory and cpu usage
> -----------------------------------------------------------
>
>                 Key: HBASE-745
>                 URL: https://issues.apache.org/jira/browse/HBASE-745
>             Project: Hadoop HBase
>          Issue Type: Improvement
>          Components: regionserver
>    Affects Versions: 0.1.3, 0.2.0
>         Environment: hadoop 0.17.1
>            Reporter: LN
>            Priority: Minor
>         Attachments: hbase-745-for-0.2.patch, HBASE-745.compact.patch
>
>
> after weeks testing hbase 0.1.3 and hadoop(0.16.4, 0.17.1), i found there are many works to do,  before a particular regionserver can handle data about 100G, or even more. i'd share my opions here with stack, and other developers.
> first, the easiest way improving scalability of regionserver is upgrading hardware, use 64bit os and 8G memory for the regionserver process, and speed up disk io. 
> besides hardware, following are software bottlenecks i found in regionserver:
> 1. as data increasing, compaction was eating cpu(with io) times, the total compaction time is basicly linear relative to whole data size, even worse, sometimes square relavtive to that size.
> 2. memory usage are depends on opened mapfiles
> 3. network connection are depends on opened mapfiles, see HADOOP-2341 and HBASE-24. 

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