Mailing-List: contact hdfs-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hdfs-issues@hadoop.apache.org
Message-ID: <2107445523.422541269306807278.JavaMail.jira@brutus.apache.org>
Date: Tue, 23 Mar 2010 01:13:27 +0000 (UTC)
From: "Bharath Mundlapudi (JIRA)" <jira@apache.org>
To: hdfs-issues@hadoop.apache.org
Subject: [jira] Commented: (HDFS-1061) Memory footprint optimization for
 INodeFile object.
In-Reply-To: <680844895.417801269297689033.JavaMail.jira@brutus.apache.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/HDFS-1061?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12848486#action_12848486 ] 

Bharath Mundlapudi commented on HDFS-1061:
------------------------------------------

At present, The shallow size of INodeFile object consumes 80 bytes on a 64bit JVM. There are couple of objects in NameNode which are in critical path for scalability of number of files. One of them is INodeFile object. Also, INodeFile objects are long lived and placed in tenure generation and as these objects grow in number can put more pressure on Garbage Collector.  So reducing the size of INodeFile object has good number of benefits.

> Memory footprint optimization for INodeFile object. 
> ----------------------------------------------------
>
>                 Key: HDFS-1061
>                 URL: https://issues.apache.org/jira/browse/HDFS-1061
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: name-node
>    Affects Versions: 0.22.0
>            Reporter: Bharath Mundlapudi
>            Priority: Minor
>             Fix For: 0.22.0
>
>
> I am proposing a footprint optimization to merge blockReplication and preferredBlockSize fields into one 'long header' field in INodeFile class. This saves 8 bytes per INodeFile object on a 64 bit JVM. This memory optimization is transparent and changes are very minimal.

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