X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by svr1.postgresql.org (Postfix) with ESMTP id A9EEDD6EF7 for ; Wed, 7 Sep 2005 09:02:11 -0300 (ADT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 01493-07 for ; Wed, 7 Sep 2005 12:02:06 +0000 (GMT) Received: from mercure-1.sigma.fr (mercure-2.sigma.fr [195.25.81.10]) by svr1.postgresql.org (Postfix) with ESMTP id 34171D6E87 for ; Wed, 7 Sep 2005 09:02:05 -0300 (ADT) Received: from localhost (localhost [127.0.0.1]) by mercure-1.sigma.fr (Postfix) with ESMTP id 65CFB1B8; Wed, 7 Sep 2005 14:02:05 +0200 (CEST) Received: from mercure-1.sigma.fr ([127.0.0.1]) by localhost (mercure-2 [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 10598-10; Wed, 7 Sep 2005 14:02:05 +0200 (CEST) Received: from delpiv3000-124l (unknown [89.195.0.5]) by mercure-1.sigma.fr (Postfix) with ESMTP id 310D11B5; Wed, 7 Sep 2005 14:02:05 +0200 (CEST) From: Marc Cousin Organization: Sigma Informatique To: pgsql-performance@postgresql.org Subject: Re: insert performance for win32 Date: Wed, 7 Sep 2005 14:02:02 +0200 User-Agent: KMail/1.8.2 Cc: "Merlin Moncure" References: <6EE64EF3AB31D5448D0007DD34EEB3417DD281@Herge.rcsinc.local> In-Reply-To: <6EE64EF3AB31D5448D0007DD34EEB3417DD281@Herge.rcsinc.local> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200509071402.02402.mcousin@sigma.fr> X-Virus-Scanned: by amavisd-new-20030616-p10 (Debian) at sigma.fr X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0 required=5 tests=[none] X-Spam-Level: X-Archive-Number: 200509/105 X-Sequence-Number: 14413 On Tuesday 06 September 2005 19:11, Merlin Moncure wrote: > > This makes me wonder if we are looking in the wrong place. Maybe the > > problem is coming from psql? More results to follow. > > problem is not coming from psql. > > One thing I did notice that in a 250k insert transaction the insert time > grows with #recs inserted. Time to insert first 50k recs is about 27 > sec and last 50 k recs is 77 sec. I also confimed that size of table is > not playing a role here. > > Marc, can you do select timeofday() every 50k recs from linux? Also a > gprof trace from linux would be helpful. > Here's the timeofday ... i'll do the gprof as soon as I can. Every 50000 rows... Wed Sep 07 13:58:13.860378 2005 CEST Wed Sep 07 13:58:20.926983 2005 CEST Wed Sep 07 13:58:27.928385 2005 CEST Wed Sep 07 13:58:35.472813 2005 CEST Wed Sep 07 13:58:42.825709 2005 CEST Wed Sep 07 13:58:50.789486 2005 CEST Wed Sep 07 13:58:57.553869 2005 CEST Wed Sep 07 13:59:04.298136 2005 CEST Wed Sep 07 13:59:11.066059 2005 CEST Wed Sep 07 13:59:19.368694 2005 CEST > Merlin > > ---------------------------(end of broadcast)--------------------------- > TIP 9: In versions below 8.0, the planner will ignore your desire to > choose an index scan if your joining column's datatypes do not > match