From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from daytona.panasas.com ([67.152.220.89]:35119 "EHLO daytona.panasas.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753620Ab1BWEqI (ORCPT ); Tue, 22 Feb 2011 23:46:08 -0500 Message-ID: <4D64910E.1030202@panasas.com> Date: Tue, 22 Feb 2011 20:46:06 -0800 From: Boaz Harrosh To: Jim Rees CC: linux-nfs@vger.kernel.org, peter honeyman Subject: Re: stripe definitions References: <20110222200558.GC7545@merit.edu> In-Reply-To: <20110222200558.GC7545@merit.edu> Content-Type: text/plain; charset=UTF-8 Sender: linux-nfs-owner@vger.kernel.org List-ID: MIME-Version: 1.0 On 02/22/2011 12:05 PM, Jim Rees wrote: > There's an inconsistency in rfc5663 that had me a bit confused: > > /// struct pnfs_block_stripe_volume_info4 { > /// length4 bsv_stripe_unit; /* size of stripe in bytes */ > > The comment "size of stripe in bytes" fits the definition of "stripe width" > from rfc5661 section 13.2, but that's not what's meant here. The field > name, "stripe_unit", is correct. > -- > To unsubscribe from this list: send the line "unsubscribe linux-nfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html You are right stripe_unit is the the bytes to write to a single device before advancing to the next device. The comment is wrong the "size of stripe in bytes" is stripe_unit * num_of_devices. The same name used in the OSD and files layout and has the same meaning. Cheers Boaz