Received: by oss.sgi.com id ; Mon, 3 Apr 2000 12:50:36 -0700 Received: from deliverator.sgi.com ([204.94.214.10]:64571 "EHLO deliverator.sgi.com") by oss.sgi.com with ESMTP id ; Mon, 3 Apr 2000 12:50:29 -0700 Received: from ledzep.cray.com (ledzep.cray.com [137.38.226.97]) by deliverator.sgi.com (980309.SGI.8.8.8-aspam-6.2/980310.SGI-aspam) via ESMTP id MAA01363 for ; Mon, 3 Apr 2000 12:45:47 -0700 (PDT) mail_from (mostek@sgi.com) Received: from ironwood-e185.americas.sgi.com (ironwood.cray.com [128.162.185.212]) by ledzep.cray.com (SGI-SGI-8.9.3/craymail-smart-nospam1.0) with ESMTP id OAA80072; Mon, 3 Apr 2000 14:47:56 -0500 (CDT) Received: from fsgi344.americas.sgi.com (fsgi344.americas.sgi.com [128.162.184.15]) by ironwood-e185.americas.sgi.com (8.8.4/SGI-ironwood-e1.4) with ESMTP id OAA24466; Mon, 3 Apr 2000 14:47:48 -0500 (CDT) From: Jim Mostek Received: by fsgi344.americas.sgi.com (980427.SGI.8.8.8/SGI-client.1.6) id OAA30522; Mon, 3 Apr 2000 14:47:54 -0500 (CDT) Message-Id: <200004031947.OAA30522@fsgi344.americas.sgi.com> Subject: Re: XFS architecture ? To: fredrik@air2.net (Fredrik =?iso-8859-1?Q?Win=E4s?=) Date: Mon, 3 Apr 2000 14:47:53 -0500 (CDT) Cc: linux-xfs@oss.sgi.com (Linux XFS mailinglista) In-Reply-To: <38E8F210.A0A3D92A@air2.net> from "Fredrik =?iso-8859-1?Q?Win=E4s?=" at Apr 03, 2000 09:33:36 PM X-Mailer: ELM [version 2.5 PL2] MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-linux-xfs@oss.sgi.com Precedence: bulk Return-Path: X-Orcpt: rfc822;linux-xfs-outgoing This has to do with the on disk format. All IRIX XFS implementations are MIPS Big Endian. The current pre-alpha Linux XFS implementation is IA32 Little Endian. We have an effort underway to allow the Linux implementation to run with different on disk formats (i.e. machine architectures): MIPS or Native (IA32, ...) or ... Multi means that the system can read/write multiple formats. The same machine could have different file systems each with different formats. This work is in development. The first step is to give the code the ability to read multiple formats. The second step is to see what the overhead is of always having MIPS big endian format. I hope this is the last step. If so, these selections will go away. If the overhead is too much, we will need to have Native and Multi so that we can have multiple endian on disk formats. Jim >Hi > >What is the difference between > > ( ) MIPS > (X) Native > ( ) Multi > >? > > > >Thanks