Received: from localhost (unknown [200.46.204.187]) by postgresql.org (Postfix) with ESMTP id 8CDEF2E006E for ; Tue, 15 Jan 2008 08:09:35 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.187]) (amavisd-maia, port 10024) with ESMTP id 06799-09 for ; Tue, 15 Jan 2008 08:09:26 -0400 (AST) Received: from mx.comgate.cz (mx.comgate.cz [193.165.185.50]) by postgresql.org (Postfix) with ESMTP id A74382E1FFA for ; Tue, 15 Jan 2008 08:09:30 -0400 (AST) Received: from alibaba ([127.0.0.1] helo=[10.1.0.53] ident=root) by mx.comgate.cz with asmtp (Exim 3.35 #1 (Debian)) id 1JEkbZ-0004Bj-00; Tue, 15 Jan 2008 13:09:21 +0100 Message-ID: <478CA26E.9040105@comgate.cz> Date: Tue, 15 Jan 2008 13:09:18 +0100 From: Jakub Ouhrabka User-Agent: Thunderbird 2.0.0.9 (Windows/20071031) MIME-Version: 1.0 To: Tom Lane CC: pgsql-performance@postgresql.org Subject: Re: Linux/PostgreSQL scalability issue - problem with 8 cores References: <7083.1199379570@sss.pgh.pa.us> <477D1D59.7050002@comgate.cz> <4782063C.7070105@comgate.cz> <26502.1199745090@sss.pgh.pa.us> <4782AB4D.8010009@comgate.cz> <27655.1199750492@sss.pgh.pa.us> <47836A4C.5080707@comgate.cz> <10713.1199813111@sss.pgh.pa.us> <47874EE8.2050406@comgate.cz> <12997.1200063940@sss.pgh.pa.us> <478B4BB9.4030208@comgate.cz> <13894.1200324134@sss.pgh.pa.us> In-Reply-To: <13894.1200324134@sss.pgh.pa.us> Content-Type: text/plain; charset=windows-1250; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: Maia Mailguard 1.0.1 X-Archive-Number: 200801/123 X-Sequence-Number: 28362 Hi Tom, > I can think of three things that might be producing this: we've found it: TRUNCATE We'll try to eliminate use of TRUNCATE and the periodical spikes should go off. There will still be possibility of spikes because of database creation etc - we'll try to handle this by issuing trivial commands from idle backeds and in longer run to decrease the number of backends/databases running. This is the way to go, right? One more question: is it ok to do mass regexp update of pg_proc.prosrc changing TRUNCATEs to DELETEs? Anything we should be aware of? Sure we'll do our own testing but in case you see any obvious downsides... Many thanks for your guidance! Kuba