Mailing-List: contact hadoop-dev-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hadoop-dev@lucene.apache.org
Message-ID: <25075847.1146707957014.JavaMail.jira@brutus>
Date: Thu, 4 May 2006 01:59:17 +0000 (GMT+00:00)
From: "Konstantin Shvachko (JIRA)" <jira@apache.org>
To: hadoop-dev@lucene.apache.org
Subject: [jira] Created: (HADOOP-193) DFS i/o benchmark.
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit

DFS i/o benchmark.
------------------

         Key: HADOOP-193
         URL: http://issues.apache.org/jira/browse/HADOOP-193
     Project: Hadoop
        Type: Test

  Components: fs  
    Reporter: Konstantin Shvachko
 Attachments: IOBenchmark.patch

DFS i/o benchmark is a map-reduce based test that measures performance of the cluster for reads and writes.
This is an evolved version of HADOOP-72, and HADOOP-95 test.

This test writes into or reads from a specified number of files.
File size is specified as a parameter to the test.
Each file is processed in a separate map task.
The unique reducer then collects stats.
Finally, the following information is displayed

# read or write test
# date and time the test finished
# number of files processed
# total number of bytes processed
# throughput in mb/sec (total number of bytes / sum of processing times)
# average i/o rate in mb/sec per file
# standard i/o rate deviation

I  included the test into the AllTestDriver.

-- 
This message is automatically generated by JIRA.
-
If you think it was sent incorrectly contact one of the administrators:
   http://issues.apache.org/jira/secure/Administrators.jspa
-
For more information on JIRA, see:
   http://www.atlassian.com/software/jira