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 8BCF7D7115 for ; Thu, 3 Nov 2005 03:11:46 -0400 (AST) 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 36890-07 for ; Thu, 3 Nov 2005 07:11:44 +0000 (GMT) Received: from cliff.cs.toronto.edu (cliff.cs.toronto.edu [128.100.3.120]) by svr1.postgresql.org (Postfix) with ESMTP id 237E2D7101 for ; Thu, 3 Nov 2005 03:11:44 -0400 (AST) Received: from eon.cs (eon.cs.toronto.edu [128.100.3.15]) by cliff.cs.toronto.edu (Postfix) with ESMTP id 197A85FD0C; Thu, 3 Nov 2005 02:11:43 -0500 (EST) Received: by eon.cs (Postfix, from userid 1300) id 281EF7E9; Thu, 3 Nov 2005 02:11:43 -0500 (EST) Received: from localhost (localhost [127.0.0.1]) by eon.cs (Postfix) with ESMTP id 1AE3F544; Thu, 3 Nov 2005 02:11:43 -0500 (EST) Date: Thu, 3 Nov 2005 02:11:43 -0500 (EST) From: Qingqing Zhou X-X-Sender: zhouqq@eon.cs To: Merlin Moncure Cc: Marc Cousin , pgsql-performance@postgresql.org Subject: Re: insert performance for win32 In-Reply-To: <6EE64EF3AB31D5448D0007DD34EEB3417DD76C@Herge.rcsinc.local> Message-ID: References: <6EE64EF3AB31D5448D0007DD34EEB3417DD76C@Herge.rcsinc.local> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.363 required=5 tests=[AWL=-0.116, DNS_FROM_RFC_ABUSE=0.479] X-Spam-Score: 0.363 X-Spam-Level: X-Archive-Number: 200511/40 X-Sequence-Number: 15297 On Wed, 2 Nov 2005, Merlin Moncure wrote: > > > > By the way, we've tried to insert into the windows database from a > > linux psql client, via the network. In this configuration, inserting > > is only about 2 times slower than inserting locally (the linux client > > had a slower CPU 1700Mhz agains 3000). Could it be related to a > > problem in the windows psql client ? > > If you put client/server on the same machine, then we don't know how the CPU is splitted. Can you take a look at the approximate number by observing the task manager data while running? If communication code is the suspect, can we measure the difference if we disable the redefinition of recv()/send() etc in port/win32.h (may require change related code a little bit as well). In this way, the socket will not be able to pickup signals, but let see if there is any performance difference first. Regards, Qingqing > > [OK, I'm bringing this back on-list, and bringing it to QingQing's > attention, who I secretly hope is the right person to be looking at this > problem :)] > P.s. You scared me ;-)