From owner-freebsd-geom@FreeBSD.ORG Sun Feb 3 03:33:41 2008 Return-Path: Delivered-To: freebsd-geom@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 942AC16A46B for ; Sun, 3 Feb 2008 03:33:41 +0000 (UTC) (envelope-from fbsd06+SY=10e1635e@mlists.homeunix.com) Received: from turtle-out.mxes.net (turtle-out.mxes.net [216.86.168.191]) by mx1.freebsd.org (Postfix) with ESMTP id 676E713C455 for ; Sun, 3 Feb 2008 03:33:41 +0000 (UTC) (envelope-from fbsd06+SY=10e1635e@mlists.homeunix.com) Received: from mxout-03.mxes.net (mxout-03.mxes.net [216.86.168.178]) by turtle-in.mxes.net (Postfix) with ESMTP id ADA61163DF0 for ; Sat, 2 Feb 2008 22:01:40 -0500 (EST) Received: from gumby.homeunix.com. (unknown [87.81.140.128]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by smtp.mxes.net (Postfix) with ESMTP id 2120623E3E8 for ; Sat, 2 Feb 2008 22:01:35 -0500 (EST) Date: Sun, 3 Feb 2008 03:01:29 +0000 From: RW To: freebsd-geom@freebsd.org Message-ID: <20080203030129.18e1d940@gumby.homeunix.com.> In-Reply-To: References: X-Mailer: Claws Mail 3.0.2 (GTK+ 2.12.5; i386-portbld-freebsd7.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Re: Geli sector size > 8192 completely breaks. X-BeenThere: freebsd-geom@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: GEOM-specific discussions and implementations List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 03 Feb 2008 03:33:41 -0000 On Sat, 2 Feb 2008 10:51:19 +0000 Andrew B wrote: > > I've been trying to get GELI working in a number of ways, and it > seems whenever I change the sector size to 16384 or higher, I can't > run newfs on the resultant encrypted volume. Bill Moran, in the questions list, said he got panics at 8k. > Using dd with sector size 16384 gives me the greatest performance for > the sector size I'm willing to have. I did some tests like that, but I wondered how well that translates to actual performance. dd shows the benefit of fewer IV initialisations, but that could be wiped-out if larger sectors lead to more work for the cipher.