X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.144]) by svr1.postgresql.org (Postfix) with ESMTP id 390A0D1B1AB for ; Sun, 11 Jul 2004 11:14:10 -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 29912-04 for ; Sun, 11 Jul 2004 14:14:14 +0000 (GMT) Received: from smtp104.mail.sc5.yahoo.com (smtp104.mail.sc5.yahoo.com [66.163.169.223]) by svr1.postgresql.org (Postfix) with SMTP id 7CC45D1B174 for ; Sun, 11 Jul 2004 11:14:05 -0300 (ADT) Received: from unknown (HELO jupiter.black-lion.info) (janwieck@68.80.245.191 with login) by smtp104.mail.sc5.yahoo.com with SMTP; 11 Jul 2004 14:14:14 -0000 Received: from Yahoo.com (ganymed.black-lion.info [192.168.192.100]) (authenticated bits=0) by jupiter.black-lion.info (8.12.10/8.12.9) with ESMTP id i6BEE23v004406; Sun, 11 Jul 2004 10:14:08 -0400 (EDT) (envelope-from JanWieck@Yahoo.com) Message-ID: <40F14ADE.4080402@Yahoo.com> Date: Sun, 11 Jul 2004 10:12:46 -0400 From: Jan Wieck User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.0; en-US; rv:1.4) Gecko/20030624 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Merlin Moncure Cc: Andy Ballingall , pgsql-performance@postgresql.org Subject: Re: Working on huge RAM based datasets References: <6EE64EF3AB31D5448D0007DD34EEB34101AEC2@Herge.rcsinc.local> In-Reply-To: <6EE64EF3AB31D5448D0007DD34EEB34101AEC2@Herge.rcsinc.local> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.1 tagged_above=0.0 required=5.0 tests=RCVD_IN_SORBS X-Spam-Level: X-Archive-Number: 200407/59 X-Sequence-Number: 7450 On 7/9/2004 10:16 AM, Merlin Moncure wrote: >> What is it about the buffer cache that makes it so unhappy being able > to >> hold everything? I don't want to be seen as a cache hit fascist, but > isn't >> it just better if the data is just *there*, available in the > postmaster's >> address space ready for each backend process to access it, rather than >> expecting the Linux cache mechanism, optimised as it may be, to have > to do >> the caching? > > The disk cache on most operating systems is optimized. Plus, keeping > shared buffers low gives you more room to bump up the sort memory, which > will make your big queries run faster. Plus, the situation will change dramatically with 7.5 where the disk cache will have less information than the PG shared buffers, which will become sequential scan resistant and will know that a block was pulled in on behalf of vacuum and not because the regular database access pattern required it. Jan -- #======================================================================# # It's easier to get forgiveness for being wrong than for being right. # # Let's break this rule - forgive me. # #================================================== JanWieck@Yahoo.com #