Received: from localhost (unknown [200.46.204.183]) by postgresql.org (Postfix) with ESMTP id 39FDC2E00AA for ; Fri, 28 Mar 2008 06:43:41 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.183]) (amavisd-maia, port 10024) with ESMTP id 61604-03-2 for ; Fri, 28 Mar 2008 06:43:35 -0300 (ADT) X-Greylist: from auto-whitelisted by SQLgrey-1.7.5 Received: from outmail136059.authsmtp.com (outmail136059.authsmtp.com [62.13.136.59]) by postgresql.org (Postfix) with ESMTP id 93DB82E0094 for ; Fri, 28 Mar 2008 06:43:33 -0300 (ADT) Received: from squirrel.dmpriest.net.uk (squirrel.dmpriest.net.uk [62.13.128.25]) by punt2.authsmtp.com (8.13.8/8.13.8/Kp) with ESMTP id m2S9hTdn026414; Fri, 28 Mar 2008 09:43:29 GMT Received: from [192.168.0.3] (85-211-64-98.dyn.gotadsl.co.uk [85.211.64.98]) (authenticated bits=0) by mail.authsmtp.com (8.14.2/8.14.2/Kp) with ESMTP id m2S9hTkd046001; Fri, 28 Mar 2008 09:43:29 GMT Subject: Re: Commitfest patches From: Simon Riggs To: Gregory Stark Cc: Pg Hackers In-Reply-To: <87wsnnz046.fsf@oxford.xeocode.com> References: <87wsnnz046.fsf@oxford.xeocode.com> Content-Type: text/plain Date: Fri, 28 Mar 2008 09:44:42 +0000 Message-Id: <1206697482.4285.1518.camel@ebony.site> Mime-Version: 1.0 X-Mailer: Evolution 2.8.2 Content-Transfer-Encoding: 7bit X-Server-Quench: 6c08a041-fcab-11dc-b66f-001871e930f4 X-AuthRoute: OCdxZQATClZOTQEd DAteCiNZVAwpPBRK HVkIKg5MJUcNSQVJ NksadBtFag1bYFhD HGQLW1xEUFR7XWB/ aQMfZQBDYEtPQQNu TkFBXVBXCwUmXB5i D0Z6CU1ycwNGeH8+ ZEJkXz5dD0RyJEZ5 Q1MCRjxUeGZhPDMC AkZeIR5UcAJCeR4Q Y1N/AndDAzANdhEY NiQQEgoKCH10LyFQ Qx0DIEkOCV4CAjU8 Sgtq X-Authentic-SMTP: 61633235383639.cat.dmpriest.net.uk:787/Kp X-Report-SPAM: If SPAM / abuse - report it at: http://www.authsmtp.com/abuse X-Virus-Status: No virus detected - but ensure you scan with your own anti-virus system! X-Virus-Scanned: Maia Mailguard 1.0.1 X-Archive-Number: 200803/1158 X-Sequence-Number: 115959 On Fri, 2008-03-28 at 09:08 +0000, Gregory Stark wrote: > A more invasive form of this patch would be to assign and pin a buffer when > the preread is done. That would men subsequently we would have a pinned buffer > ready to go and not need to go back to the buffer manager a second time. We > would instead just "complete" the i/o by issuing a normal read call. So if posix_fadvise did nothing or there was a longer than optimal delay, this would be a net loss. You'd need reasonable evidence that the posix_fadvise facility was a win on all platforms and recent release levels before we could agree with that. I think we need a more thorough examination of this area before we commit anything. Maybe you've done this, but I haven't seen the analysis. Can you say more, please? Or at least say what you don't know, so other experts listening can fill in the blanks. -- Simon Riggs 2ndQuadrant http://www.2ndQuadrant.com PostgreSQL UK 2008 Conference: http://www.postgresql.org.uk