Received: from localhost (maia-4.hub.org [200.46.204.183]) by postgresql.org (Postfix) with ESMTP id C17D79FB6E9 for ; Fri, 27 Jul 2007 06:14:31 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.183]) (amavisd-maia, port 10024) with ESMTP id 73867-01 for ; Fri, 27 Jul 2007 06:14:27 -0300 (ADT) X-Greylist: from auto-whitelisted by SQLgrey-1.7.5 Received: from mail01.enterprisedb.com (mail01.enterprisedb.com [63.246.7.168]) by postgresql.org (Postfix) with ESMTP id B94CB9FB6C8 for ; Fri, 27 Jul 2007 06:14:27 -0300 (ADT) thread-index: AcfQLo/ybuE0yH6nR1S9hlz8EB52dg== Received: from [172.24.32.57] ([62.232.55.118]) by mail01.enterprisedb.com with Microsoft SMTPSVC(6.0.3790.3959); Fri, 27 Jul 2007 05:14:39 -0400 Content-Class: urn:content-classes:message Importance: normal X-MimeOLE: Produced By Microsoft MimeOLE V6.00.3790.4073 Subject: Re: User concurrency thresholding: where do I look? From: "Simon Riggs" To: "Alvaro Herrera" Cc: "Jignesh K. Shah" , "Tom Lane" , "Josh Berkus" , In-Reply-To: <20070727085805.GF2550@alvh.no-ip.org> References: <1545.1185214760@sss.pgh.pa.us> <46A7D5AD.9000706@sun.com> <13162.1185405865@sss.pgh.pa.us> <46A8AFDF.3050804@sun.com> <26825.1185460816@sss.pgh.pa.us> <46A8BD62.2080904@sun.com> <1185465076.4190.87.camel@ebony.site> <46A8F9AA.4040507@sun.com> <1185480291.5510.22.camel@ebony.site> <46A90F83.8050401@sun.com> <20070727085805.GF2550@alvh.no-ip.org> Content-Type: text/plain; charset="iso-8859-1" Date: Fri, 27 Jul 2007 10:15:13 +0100 Message-ID: <1185527713.4191.20.camel@ebony.site> MIME-Version: 1.0 X-Mailer: Evolution 2.8.2 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 27 Jul 2007 09:14:39.0859 (UTC) FILETIME=[8F89BC30:01C7D02E] X-Virus-Scanned: Maia Mailguard 1.0.1 X-Archive-Number: 200707/383 X-Sequence-Number: 26067 On Fri, 2007-07-27 at 04:58 -0400, Alvaro Herrera wrote: > Jignesh K. Shah wrote: > > > Top Wait time seems to come from the following code path for > > ProcArrayLock: > > > > Lock Id Mode Count > > ProcArrayLock Exclusive 21 > > > > Lock Id Combined Time (ns) > > ProcArrayLock 5255937500 > > > > Lock Id Combined Time (ns) > > > > > > postgres`LWLockAcquire+0x1f0 > > postgres`CommitTransaction+0x104 > > Yeah, ProcArrayLock is pretty contended. I think it would be kinda neat > if we could split it up in partitions. This lock is quite particular > though. Maybe, if we did we should set the partitions according to numbers of users, so lower numbers of users are all in one partition. -- Simon Riggs EnterpriseDB http://www.enterprisedb.com