Received: from maia.hub.org (maia-2.hub.org [200.46.204.251]) by mail.postgresql.org (Postfix) with ESMTP id A99EAB5DBE8 for ; Fri, 27 May 2011 08:09:54 -0300 (ADT) Received: from mail.postgresql.org ([200.46.204.86]) by maia.hub.org (mx1.hub.org [200.46.204.251]) (amavisd-maia, port 10024) with ESMTP id 25098-08 for ; Fri, 27 May 2011 11:09:47 +0000 (UTC) X-Greylist: delayed 00:15:05.885196 by SQLgrey-1.7.6 Received: from lo.gmane.org (lo.gmane.org [80.91.229.12]) by mail.postgresql.org (Postfix) with ESMTP id 821A5B5D944 for ; Fri, 27 May 2011 08:09:47 -0300 (ADT) Received: from list by lo.gmane.org with local (Exim 4.69) (envelope-from ) id 1QPugg-0001ZS-Vo for pgsql-performance@postgresql.org; Fri, 27 May 2011 12:54:38 +0200 Received: from lara.cc.fer.hr ([161.53.72.113]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 27 May 2011 12:54:38 +0200 Received: from ivoras by lara.cc.fer.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 27 May 2011 12:54:38 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: pgsql-performance@postgresql.org From: Ivan Voras Subject: Re: Performance block size. Date: Fri, 27 May 2011 12:54:27 +0200 Lines: 22 Message-ID: References: Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@dough.gmane.org X-Gmane-NNTP-Posting-Host: lara.cc.fer.hr User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.9.2.12) Gecko/20101102 Thunderbird/3.1.6 In-Reply-To: X-Enigmail-Version: 1.1.2 X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=-1.91 tagged_above=-10 required=5 tests=BAYES_00=-1.9, T_RP_MATCHES_RCVD=-0.01 X-Spam-Level: X-Archive-Number: 201105/396 X-Sequence-Number: 43905 On 27/05/2011 00:34, Tory M Blue wrote: > Working on some optimization as well as finally getting off my > backside and moving us to 64bit (32gb+memory). > > I was reading and at some point it appears on freeBSD the Postgres > block size was upped to 16kb, from 8kb. And on my fedora systems I > believe the default build is 8kb. This happened some years ago but it was quickly reverted. There were some apparent gains with the larger block size, especially since FreeBSD's UFS uses 16 KiB blocks by default (going to 32 KiB really soon now; note that this has no impact on small files because of the concept of "block fragments"), but it was concluded that the stock installation should follow the defaults set by the developers, not porters. YMMV. > Trying to gain some performance and wondered if any of this tuning > even is something I should bother with. Please do some benchmarks and report results.