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 A20F8D6E40 for ; Tue, 6 Sep 2005 11:12:32 -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 73191-06 for ; Tue, 6 Sep 2005 14:12:27 +0000 (GMT) Received: from mercure-1.sigma.fr (mercure-2.sigma.fr [195.25.81.10]) by svr1.postgresql.org (Postfix) with ESMTP id 189C9D6D8A for ; Tue, 6 Sep 2005 11:12:26 -0300 (ADT) Received: from localhost (localhost [127.0.0.1]) by mercure-1.sigma.fr (Postfix) with ESMTP id 5B64C214 for ; Tue, 6 Sep 2005 16:12:29 +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 09338-06 for ; Tue, 6 Sep 2005 16:12:29 +0200 (CEST) Received: from delpiv3000-124l (unknown [89.195.0.5]) by mercure-1.sigma.fr (Postfix) with ESMTP id 2A86E21D for ; Tue, 6 Sep 2005 16:12:29 +0200 (CEST) From: Marc Cousin Organization: Sigma Informatique To: pgsql-performance@postgresql.org Subject: insert performance for win32 Date: Tue, 6 Sep 2005 16:12:27 +0200 User-Agent: KMail/1.8.2 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200509061612.27746.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: 200509/87 X-Sequence-Number: 14395 Hi, I usually use PostgreSQL coupled with Linux, but I have to use Windows for a perticular project. So I wanted to do some tests to know if the performance will be acceptable (I don't need PostgreSQL to be as fast with windows as with linux, but it has to be usable...). I started with trying to do lots of inserts, and I'm quite astonished by the catastrophics results ... The test : The computer was the same (my workstation, a PIV Dell with SATA disk), dual boot The windows OS is XP. Both Oses are PostgreSQL 8.0.3 Both PostgreSQL clusters (windows and linux) have the same tuning (shared_buffers=20000, wal_buffers=128, checkpoint_segments=10) Before each test, the clusters are vacuum analyzed, and the test database is recreated. The script is quite dumb : BEGIN; CREATE TABLE test (col1 serial, col2 text); INSERT INTO test (col2) values ('test'); INSERT INTO test (col2) values ('test'); INSERT INTO test (col2) values ('test'); INSERT INTO test (col2) values ('test'); INSERT INTO test (col2) values ('test'); ...... 500,000 times Then COMMIT. I know it isn't realistic, but I needed to start with something :) The results are as follows : Linux : 1'9'' Windows : 9'38'' What I've tried to solve, and didn't work : - Deactivate antivirus on windows - fsync=no - raise the checkpoint_segments value (32) - remove hyperthreading (who knows...) I don't know what could cause this (I'm not a windows admin...at all). All I see is a very high kernel load during the execution of this script, but I can't determine where it comes from. I'd like to know if this is a know problem, if there is something I can do, etc... Thanks a lot.