X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id EA3399DCB96 for ; Sat, 3 Dec 2005 12:41:44 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 76857-03 for ; Sat, 3 Dec 2005 12:41:42 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from floppy.pyrenet.fr (news.pyrenet.fr [194.116.145.2]) by postgresql.org (Postfix) with ESMTP id 62B729DCB83 for ; Sat, 3 Dec 2005 12:41:42 -0400 (AST) Received: by floppy.pyrenet.fr (Postfix, from userid 106) id E168A3093A; Sat, 3 Dec 2005 17:41:41 +0100 (MET) From: Michael Riess X-Newsgroups: pgsql.performance Subject: Re: 15,000 tables - next step Date: Sat, 03 Dec 2005 17:41:42 +0100 Organization: Hub.Org Networking Services Lines: 24 Message-ID: References: <4391BF0F.9000208@Yahoo.com> <20051203162642.GA29022@surnet.cl> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@news.hub.org User-Agent: Thunderbird 1.5 (Windows/20051025) In-Reply-To: <20051203162642.GA29022@surnet.cl> To: pgsql-performance@postgresql.org X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0 required=5 tests=[none] X-Spam-Score: 0 X-Spam-Level: X-Archive-Number: 200512/100 X-Sequence-Number: 15921 Alvaro Herrera schrieb: > Michael Riess wrote: > >> Shared memory ... I currently use 1500 buffers for 50 connections, and >> performance really suffered when I used 3000 buffers. The problem is >> that it is a 1GB machine, and Apache + Tomcat need about 400MB. > > Well, I'd think that's were your problem is. Not only you have a > (relatively speaking) small server -- you also share it with other > very-memory-hungry services! That's not a situation I'd like to be in. > Try putting Apache and Tomcat elsewhere, and leave the bulk of the 1GB > to Postgres. No can do. I can try to switch to a 2GB machine, but I will not use several machines. Not for a 5GB database. ;-) > With 1500 shared buffers you are not really going > anywhere -- you should have ten times that at the very least. > Like I said - I tried to double the buffers and the performance did not improve in the least. And I also tried this on a 2GB machine, and swapping was not a problem. If I used 10x more buffers, I would in essence remove the OS buffers.