Mailing-List: contact chukwa-dev-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: chukwa-dev@hadoop.apache.org
Message-ID: <426499983.29081262642334466.JavaMail.jira@brutus.apache.org>
Date: Mon, 4 Jan 2010 21:58:54 +0000 (UTC)
From: "Ari Rabkin (JIRA)" <jira@apache.org>
To: chukwa-dev@hadoop.apache.org
Subject: [jira] Commented: (CHUKWA-433) file-per-post writer
In-Reply-To: <61393823.1261367418767.JavaMail.jira@brutus>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/CHUKWA-433?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12796375#action_12796375 ] 

Ari Rabkin commented on CHUKWA-433:
-----------------------------------

Did the experiment, didn't get interesting results. For my setup, the namenode was able to keep up with one file per post, and I didn't observe a latency penalty.

> file-per-post writer
> --------------------
>
>                 Key: CHUKWA-433
>                 URL: https://issues.apache.org/jira/browse/CHUKWA-433
>             Project: Hadoop Chukwa
>          Issue Type: New Feature
>          Components: data collection
>            Reporter: Ari Rabkin
>            Assignee: Ari Rabkin
>         Attachments: CHUKWA-433.patch
>
>
> I want to add a writer that outputs a separate HDFS file for each post. The use case is performance testing. It's almost certainly useless for any production purpose.

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