From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Martin K. Petersen" Subject: Re: [PATCH 1/2] block: add support for discard limits Date: Mon, 02 Nov 2009 13:18:16 -0500 Message-ID: References: <20091029150830.497006534@bombadil.infradead.org> <20091029151127.257902381@bombadil.infradead.org> <20091030050558.GC17714@infradead.org> <4AEF02B0.2060506@panasas.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from rcsinet12.oracle.com ([148.87.113.124]:60689 "EHLO rgminet12.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756134AbZKBSTT (ORCPT ); Mon, 2 Nov 2009 13:19:19 -0500 In-Reply-To: <4AEF02B0.2060506@panasas.com> (Boaz Harrosh's message of "Mon, 02 Nov 2009 18:02:56 +0200") Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Boaz Harrosh Cc: "Martin K. Petersen" , Christoph Hellwig , linux-scsi@vger.kernel.org, axboe@kernel.dk, matthew@wil.cx >>>>> "Boaz" == Boaz Harrosh writes: Boaz> On 11/02/2009 03:29 PM, Martin K. Petersen wrote: >> >> With heterogeneous md and dm devices there may not be a meaningful >> value to put in the discard granularity field. Then what? >> Boaz> These alignment masks may only be base-2, no? Nope. Could be the good old sector 63 offset vs. naturally aligned. Boaz> If so then the max alignment of all devices will work for any Boaz> device. But even then we'd waste space on the array with smaller granularity. -- Martin K. Petersen Oracle Linux Engineering