X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.2]) by svr1.postgresql.org (Postfix) with ESMTP id 43A33D1D086 for ; Mon, 19 Apr 2004 04:27:59 -0300 (ADT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (neptune.hub.org [200.46.204.2]) (amavisd-new, port 10024) with ESMTP id 90727-08 for ; Mon, 19 Apr 2004 04:27:59 -0300 (ADT) Received: from mail2.aeccom.com (port-212-202-101-158.reverse.qsc.de [212.202.101.158]) by svr1.postgresql.org (Postfix) with ESMTP id F21BCD1D096 for ; Mon, 19 Apr 2004 04:27:56 -0300 (ADT) Received: from aeccom.com (cayambe.core.aeccom.com [192.168.2.12]) by mail2.aeccom.com (Postfix) with ESMTP id 1E91F34; Mon, 19 Apr 2004 09:27:57 +0200 (CEST) Message-ID: <40837F7D.9050102@aeccom.com> Date: Mon, 19 Apr 2004 09:27:57 +0200 From: =?ISO-8859-1?Q?Dirk_Lutzeb=E4ck?= Organization: AEC/communications GmbH, Berlin User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.5) Gecko/20031016 X-Accept-Language: de, en MIME-Version: 1.0 To: josh@agliodbs.com Cc: Tom Lane , pgsql-performance@postgresql.org Subject: Re: RESOLVED: Re: Wierd context-switching issue on Xeon References: <200311251419.36771.josh@agliodbs.com> <407FAF0F.2070304@aeccom.com> <407FD9A0.6040608@aeccom.com> <200404160958.14902.josh@agliodbs.com> In-Reply-To: <200404160958.14902.josh@agliodbs.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200404/262 X-Sequence-Number: 6562 Josh, I cannot reproduce the excessive semop() on a Dual XEON DP on a non-bigmem kernel, HT on. Interesting to know if the problem is related to XEON MP (as Tom wrote) or bigmem. Josh Berkus wrote: >Dirk, > > > >>I'm not sure if this semop() problem is still an issue but the database >>behaves a bit out of bounds in this situation, i.e. consuming system >>resources with semop() calls 95% while tables are locked very often and >>longer. >> >> > >It would be helpful to us if you could test this with the indexes disabled on >the non-Bigmem system. I'd like to eliminate Bigmem as a factor, if >possible. > > >