Return-Path: X-Original-To: apmail-hadoop-mapreduce-user-archive@minotaur.apache.org Delivered-To: apmail-hadoop-mapreduce-user-archive@minotaur.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 1B22195B1 for ; Wed, 21 Mar 2012 01:20:29 +0000 (UTC) Received: (qmail 29228 invoked by uid 500); 21 Mar 2012 01:20:23 -0000 Delivered-To: apmail-hadoop-mapreduce-user-archive@hadoop.apache.org Received: (qmail 28120 invoked by uid 500); 21 Mar 2012 01:20:22 -0000 Mailing-List: contact mapreduce-user-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: mapreduce-user@hadoop.apache.org Delivered-To: mailing list mapreduce-user@hadoop.apache.org Received: (qmail 28033 invoked by uid 99); 21 Mar 2012 01:20:22 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 21 Mar 2012 01:20:22 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (nike.apache.org: domain of ramon_wang@hotmail.com designates 65.54.190.35 as permitted sender) Received: from [65.54.190.35] (HELO bay0-omc1-s24.bay0.hotmail.com) (65.54.190.35) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 21 Mar 2012 01:20:12 +0000 Received: from BAY170-W71 ([65.54.190.61]) by bay0-omc1-s24.bay0.hotmail.com with Microsoft SMTPSVC(6.0.3790.4675); Tue, 20 Mar 2012 18:19:51 -0700 Message-ID: Content-Type: multipart/alternative; boundary="_693a0015-eb55-4d3e-925c-5b559c336c86_" X-Originating-IP: [114.242.126.130] From: WangRamon To: , , Subject: Fair Share Scheduler not worked as expected Date: Wed, 21 Mar 2012 09:19:50 +0800 Importance: Normal MIME-Version: 1.0 X-OriginalArrivalTime: 21 Mar 2012 01:19:51.0607 (UTC) FILETIME=[B70CB470:01CD0700] X-Virus-Checked: Checked by ClamAV on apache.org --_693a0015-eb55-4d3e-925c-5b559c336c86_ Content-Type: text/plain; charset="gb2312" Content-Transfer-Encoding: 8bit Hi All I noticed there is something strange in my Fair Share Scheduler monitor GUI, the SUMof the Faire Share Value is always about 30 even there is only one M/R Job is running, so I don't know whether the value is about the usage percentage, if it was the percentage, that explains why all my jobs cannot use all the slots configured, here is my configuration file: 42 42 1.0 100 I have 42 map slots and 42 reduce slots, i want the search pool (search is the hadoop user, it's the only one user) to use all my configured resource, but it seems all the jobs can only use 30% of my configured resource, not sure did i miss something, thanks for your help. Cheers Ramon --_693a0015-eb55-4d3e-925c-5b559c336c86_ Content-Type: text/html; charset="gb2312" Content-Transfer-Encoding: 8bit

Hi All

I noticed there is something strange in my Fair Share Scheduler monitor GUI, the SUMof the Faire Share Value is always about 30 even there is only one M/R Job is running, so I don't know whether the value is about the usage percentage, if it was the percentage, that explains why all my jobs cannot use all the slots configured, here is my configuration file:

<allocations>
        <pool name="search">
                <minMaps>42</minMaps>
                <minReduces>42</minReduces>
                <weight>1.0</weight>
        </pool>
        <userMaxJobsD efault>100</userMaxJobsDefault>
</allocations>

I have 42 map slots and 42 reduce slots, i want the search pool (search is the hadoop user, it's the only one user) to use all my configured resource, but it seems all the jobs can only use 30% of my configured resource, not sure did i miss something, thanks for your help.

Cheers
Ramon

--_693a0015-eb55-4d3e-925c-5b559c336c86_--