From owner-freebsd-current@FreeBSD.ORG Sat Jan 5 18:35:31 2013 Return-Path: Delivered-To: freebsd-current@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by hub.freebsd.org (Postfix) with ESMTP id EB37C8E8 for ; Sat, 5 Jan 2013 18:35:31 +0000 (UTC) (envelope-from theraven@FreeBSD.org) Received: from theravensnest.org (theraven.freebsd.your.org [216.14.102.27]) by mx1.freebsd.org (Postfix) with ESMTP id C1211C39 for ; Sat, 5 Jan 2013 18:35:31 +0000 (UTC) Received: from [192.168.0.2] (cpc10-cmbg15-2-0-cust123.5-4.cable.virginmedia.com [86.30.246.124]) (authenticated bits=0) by theravensnest.org (8.14.5/8.14.5) with ESMTP id r05IZPqJ028428 (version=TLSv1/SSLv3 cipher=DHE-DSS-AES128-SHA bits=128 verify=NO); Sat, 5 Jan 2013 18:35:27 GMT (envelope-from theraven@FreeBSD.org) Subject: Re: ZFS/RAIDZ and SAMBA: abyssimal performance Mime-Version: 1.0 (Apple Message framework v1278) Content-Type: text/plain; charset=us-ascii From: David Chisnall In-Reply-To: <157811899.1684695.1357331955066.JavaMail.root@erie.cs.uoguelph.ca> Date: Sat, 5 Jan 2013 18:35:22 +0000 Content-Transfer-Encoding: quoted-printable Message-Id: <6CE7D306-86B8-40D7-9F0C-2964D6D5BB04@FreeBSD.org> References: <157811899.1684695.1357331955066.JavaMail.root@erie.cs.uoguelph.ca> To: Rick Macklem X-Mailer: Apple Mail (2.1278) Cc: freebsd-current@FreeBSD.org X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 05 Jan 2013 18:35:32 -0000 On 4 Jan 2013, at 20:39, Rick Macklem wrote: > What about capturing a few examples, like this one for a system with > 16Gb of Ram. Basically cases of: > - this is my hardware config and here's what works well for me > It's pretty easy for people to choose the example closest to their > setup as a starting point. This would be very helpful. One of the longer-term goals for the = storage stack is to make all of these things self-tuning, and some = well-tested data points showing system configuration, workload, and = performance would be a good starting point for this. David=