Received: from localhost (mx1.hub.org [200.46.208.251]) by postgresql.org (Postfix) with ESMTP id BD8469F9F45 for ; Sun, 24 Sep 2006 10:30:06 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.208.251]) (amavisd-new, port 10024) with ESMTP id 29889-06 for ; Sun, 24 Sep 2006 10:29:56 -0300 (ADT) X-Greylist: from auto-whitelisted by SQLgrey- Received: from floppy.pyrenet.fr (floppy.pyrenet.fr [194.116.145.2]) by postgresql.org (Postfix) with ESMTP id 0286E9F9F96 for ; Sun, 24 Sep 2006 10:29:54 -0300 (ADT) Received: by floppy.pyrenet.fr (Postfix, from userid 106) id D72AB30E1A; Sun, 24 Sep 2006 15:29:51 +0200 (MET DST) From: Ron Mayer X-Newsgroups: pgsql.performance Subject: Re: Large tables (was: RAID 0 not as fast as Date: Sun, 24 Sep 2006 06:29:50 -0700 Organization: Hub.Org Networking Services Lines: 18 Message-ID: <4516884E.6070308@cheapcomplexdevices.com> References: <20060922034037.GB2820@mark.mielke.cc> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@news.hub.org To: Luke Lonergan User-Agent: Thunderbird 1.5.0.5 (X11/20060812) In-Reply-To: X-Enigmail-Version: 0.94.0.0 To: pgsql-performance@postgresql.org X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=0.048 tagged_above=0 required=5 tests=AWL X-Spam-Level: X-Archive-Number: 200609/322 X-Sequence-Number: 21008 Luke Lonergan wrote: > > I think the topic is similar to "cache bypass", used in cache capable vector > processors (Cray, Convex, Multiflow, etc) in the 90's. When you are > scanning through something larger than the cache, it should be marked > "non-cacheable" and bypass caching altogether. This avoids a copy, and > keeps the cache available for things that can benefit from it. And 'course some file systems do this automatically when they detect a sequential scan[1] though it can have unexpected (to some) negative side effects[2]. For file systems that support freebehind as a configurable parameter, it might be easier to experiment with the idea there. [1] http://www.ediaudit.com/doc_sol10/Solaris_10_Doc/common/SUNWaadm/reloc/sun_docs/C/solaris_10/SUNWaadm/SOLTUNEPARAMREF/p18.html [2] http://bugs.opensolaris.org/bugdatabase/view_bug.do?bug_id=6207772