From owner-freebsd-fs Mon Jul 13 13:38:20 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id NAA00509 for freebsd-fs-outgoing; Mon, 13 Jul 1998 13:38:20 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewaya.anheuser-busch.com (gatewaya.anheuser-busch.com [151.145.250.252]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id NAA00474; Mon, 13 Jul 1998 13:38:15 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewaya.anheuser-busch.com; id PAA23160; Mon, 13 Jul 1998 15:35:42 -0500 Received: from stlabcexg004.anheuser-busch.com(unknown 151.145.101.160) by gatewaya via smap (V2.1) id xma023109; Mon, 13 Jul 98 15:35:30 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id <3QYWQRAT>; Mon, 13 Jul 1998 21:38:39 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF90177660A@STLABCEXG011> From: "Alton, Matthew" To: "'Hackers@FreeBSD.ORG'" , "'FreeBSD-fs@FreeBSD.ORG'" Subject: Software RAID Date: Mon, 13 Jul 1998 21:38:37 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Is anybody working on software RAID? Matthew Alton Computer Services - UNIX Systems Administration (314)632-6644 matthew.alton@anheuser-busch.com alton@plantnet.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Jul 13 14:47:47 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA15356 for freebsd-fs-outgoing; Mon, 13 Jul 1998 14:47:47 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from pluto.plutotech.com (mail.plutotech.com [206.168.67.137]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id OAA15351; Mon, 13 Jul 1998 14:47:46 -0700 (PDT) (envelope-from gibbs@plutotech.com) Received: from narnia.plutotech.com (narnia.plutotech.com [206.168.67.130]) by pluto.plutotech.com (8.8.7/8.8.5) with ESMTP id PAA06102; Mon, 13 Jul 1998 15:46:35 -0600 (MDT) Message-Id: <199807132146.PAA06102@pluto.plutotech.com> X-Mailer: exmh version 2.0.2 2/24/98 To: "Alton, Matthew" cc: "'Hackers@FreeBSD.ORG'" , "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: Software RAID In-reply-to: Your message of "Mon, 13 Jul 1998 21:38:37 BST." <31B3F0BF1C40D11192A700805FD48BF90177660A@STLABCEXG011> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 13 Jul 1998 15:41:23 -0600 From: "Justin T. Gibbs" Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >Is anybody working on software RAID? There is supposedly some work being done in the NetBSD environment to pull RaidFrame into their kernel. You may want to get involved with that effort. -- Justin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Jul 13 15:17:41 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id PAA21124 for freebsd-fs-outgoing; Mon, 13 Jul 1998 15:17:41 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from freefall.pipeline.ch (intranet.pipeline.ch [195.134.128.66]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA21102; Mon, 13 Jul 1998 15:17:28 -0700 (PDT) (envelope-from andre@pipeline.ch) Received: from pipeline.ch ([195.134.128.41]) by freefall.pipeline.ch (Netscape Mail Server v2.02) with ESMTP id AAA412; Tue, 14 Jul 1998 00:15:39 +0200 Message-ID: <35AA872E.3D07CE1D@pipeline.ch> Date: Tue, 14 Jul 1998 00:16:14 +0200 From: "IBS / Andre Oppermann" Organization: Internet Business Solutions Ltd. (AG) X-Mailer: Mozilla 4.03 [en] (WinNT; U) MIME-Version: 1.0 To: "Justin T. Gibbs" CC: "Alton, Matthew" , "'Hackers@FreeBSD.ORG'" , "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: Software RAID References: <199807132146.PAA06102@pluto.plutotech.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Justin T. Gibbs wrote: > > >Is anybody working on software RAID? > > There is supposedly some work being done in the NetBSD environment to > pull RaidFrame into their kernel. You may want to get involved with > that effort. Terry did that already for FreeBSD: http://www.freebsd.org/~terry -- Andre Oppermann CEO / Geschaeftsfuehrer Internet Business Solutions Ltd. (AG) Hardstrasse 235, 8005 Zurich, Switzerland Fon +41 1 277 75 75 / Fax +41 1 277 75 77 http://www.pipeline.ch ibs@pipeline.ch To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Jul 13 15:19:37 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id PAA21699 for freebsd-fs-outgoing; Mon, 13 Jul 1998 15:19:37 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from pluto.plutotech.com (mail.plutotech.com [206.168.67.137]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA21686; Mon, 13 Jul 1998 15:19:35 -0700 (PDT) (envelope-from gibbs@plutotech.com) Received: from narnia.plutotech.com (narnia.plutotech.com [206.168.67.130]) by pluto.plutotech.com (8.8.7/8.8.5) with ESMTP id QAA07976; Mon, 13 Jul 1998 16:19:26 -0600 (MDT) Message-Id: <199807132219.QAA07976@pluto.plutotech.com> X-Mailer: exmh version 2.0.2 2/24/98 To: "IBS / Andre Oppermann" cc: "Justin T. Gibbs" , "Alton, Matthew" , "'Hackers@FreeBSD.ORG'" , "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: Software RAID In-reply-to: Your message of "Tue, 14 Jul 1998 00:16:14 +0200." <35AA872E.3D07CE1D@pipeline.ch> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Mon, 13 Jul 1998 16:14:14 -0600 From: "Justin T. Gibbs" Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >> There is supposedly some work being done in the NetBSD environment to >> pull RaidFrame into their kernel. You may want to get involved with >> that effort. > >Terry did that already for FreeBSD: http://www.freebsd.org/~terry Last I heard, Terry had ported the userland implementation to FreeBSD, not the kernel one. The kernel stuff would actually give reasonable performance since the userland code doesn't have "real threads" to rely on. -- Justin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Jul 13 15:46:31 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id PAA26341 for freebsd-fs-outgoing; Mon, 13 Jul 1998 15:46:31 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id PAA26330; Mon, 13 Jul 1998 15:46:26 -0700 (PDT) (envelope-from michaelh@cet.co.jp) Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.8.8/CET-v2.2) with SMTP id WAA12655; Mon, 13 Jul 1998 22:43:41 GMT Date: Tue, 14 Jul 1998 07:43:40 +0900 (JST) From: Michael Hancock To: "Alton, Matthew" cc: "'Hackers@FreeBSD.ORG'" , "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: Software RAID In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF90177660A@STLABCEXG011> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org http://www.lemis.com/vinum.html On Mon, 13 Jul 1998, Alton, Matthew wrote: > Is anybody working on software RAID? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Jul 13 16:07:26 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA29608 for freebsd-fs-outgoing; Mon, 13 Jul 1998 16:07:26 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from bb.cc.wa.us (chris@bb.cc.wa.us [134.39.181.3]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id QAA29602; Mon, 13 Jul 1998 16:07:24 -0700 (PDT) (envelope-from chris@bb.cc.wa.us) Received: from localhost (chris@localhost) by bb.cc.wa.us (8.8.8/8.6.9) with SMTP id XAA02434; Mon, 13 Jul 1998 23:02:08 GMT Date: Mon, 13 Jul 1998 16:02:08 -0700 (PDT) From: Chris Coleman To: "Alton, Matthew" cc: "'Hackers@FreeBSD.ORG'" , "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: Software RAID In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF90177660A@STLABCEXG011> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Isn't vinum that Greg Lehey working on supposed to do RAID. At least RAID0 now and RAID5 soon. Christopher J. Coleman (whyareyou@lookingforme.com) Computer Support Analyst I (509)-762-6341 FreeBSD Book Project: http://www.vmunix.com/fbsd-book/ On Mon, 13 Jul 1998, Alton, Matthew wrote: > Is anybody working on software RAID? > > Matthew Alton > Computer Services - UNIX Systems Administration > (314)632-6644 matthew.alton@anheuser-busch.com > alton@plantnet.com > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-hackers" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Jul 13 16:31:37 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA04190 for freebsd-fs-outgoing; Mon, 13 Jul 1998 16:31:37 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from smtp02.primenet.com (daemon@smtp02.primenet.com [206.165.6.132]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id QAA04171; Mon, 13 Jul 1998 16:31:34 -0700 (PDT) (envelope-from tlambert@usr08.primenet.com) Received: (from daemon@localhost) by smtp02.primenet.com (8.8.8/8.8.8) id QAA05632; Mon, 13 Jul 1998 16:31:28 -0700 (MST) Received: from usr08.primenet.com(206.165.6.208) via SMTP by smtp02.primenet.com, id smtpd005560; Mon Jul 13 16:31:22 1998 Received: (from tlambert@localhost) by usr08.primenet.com (8.8.5/8.8.5) id QAA15175; Mon, 13 Jul 1998 16:31:08 -0700 (MST) From: Terry Lambert Message-Id: <199807132331.QAA15175@usr08.primenet.com> Subject: Re: Software RAID To: gibbs@plutotech.com (Justin T. Gibbs) Date: Mon, 13 Jul 1998 23:31:08 +0000 (GMT) Cc: andre@pipeline.ch, gibbs@plutotech.com, Matthew.Alton@anheuser-busch.com, Hackers@FreeBSD.ORG, FreeBSD-fs@FreeBSD.ORG In-Reply-To: <199807132219.QAA07976@pluto.plutotech.com> from "Justin T. Gibbs" at Jul 13, 98 04:14:14 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > >> There is supposedly some work being done in the NetBSD environment to > >> pull RaidFrame into their kernel. You may want to get involved with > >> that effort. > > > >Terry did that already for FreeBSD: http://www.freebsd.org/~terry > > Last I heard, Terry had ported the userland implementation to FreeBSD, > not the kernel one. This is correct. I did the userspace port, and I sent the patches back to the maintainer; in theory it should work "out of the box". Which begs the question: "who is going through all the ports and sending those patches back to the maintainers so FreeBSD is supported out of the box?". > The kernel stuff would actually give reasonable > performance since the userland code doesn't have "real threads" to rely > on. I think the value of quote-unquote "real threads" has been greatly exaggerated; kernel threads result in SMP scalability and higher context switch overhead and more interleaved I/O, and that's presuming something has been done about scheduler and processor affinity (I have yet to see John Dyson's patches for this committed, however, even though Elvind and other have copies). The biggest overhead in a software RAID 5 is the software instead of hardware checksum calculation, and that's going to be a much higher penalty than non-interleaved I/O (IMO; writes are typically interleaved, and where you care about reads, you will be set to trigger read-ahead). Software RAID is a data integrity issue, not a performance one, and I think making the performance argument for whatever reason (protection domain crossing, interleaved I/O, SMP scalability, etc.) is a strawman at best. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Mon Jul 13 18:29:57 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id SAA23702 for freebsd-fs-outgoing; Mon, 13 Jul 1998 18:29:57 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from freebie.lemis.com (freebie.lemis.com [139.130.136.133]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id SAA23662; Mon, 13 Jul 1998 18:29:51 -0700 (PDT) (envelope-from grog@freebie.lemis.com) Received: (from grog@localhost) by freebie.lemis.com (8.9.0/8.9.0) id KAA13777; Tue, 14 Jul 1998 10:59:44 +0930 (CST) Message-ID: <19980714105944.C754@freebie.lemis.com> Date: Tue, 14 Jul 1998 10:59:44 +0930 From: Greg Lehey To: Matthew Alton , Hackers@FreeBSD.ORG, FreeBSD-fs@FreeBSD.ORG Subject: Re: Software RAID References: <31B3F0BF1C40D11192A700805FD48BF90177660A@STLABCEXG011> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF90177660A@STLABCEXG011>; from Alton, Matthew on Mon, Jul 13, 1998 at 09:38:37PM +0100 WWW-Home-Page: http://www.lemis.com/~grog Organization: LEMIS, PO Box 460, Echunga SA 5153, Australia Phone: +61-8-8388-8286 Fax: +61-8-8388-8725 Mobile: +61-41-739-7062 Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Monday, 13 July 1998 at 21:38:37 +0100, Alton, Matthew wrote: > Is anybody working on software RAID? Yes, I am. I see you've already followed up the URL (http://www.lemis.com/vinum.html; thanks, Chris). Greg -- See complete headers for address and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Tue Jul 14 01:25:59 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id BAA06379 for freebsd-fs-outgoing; Tue, 14 Jul 1998 01:25:59 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from publica.ub.mng.net (publica.ub.mng.net [202.179.0.80]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id BAA06374 for ; Tue, 14 Jul 1998 01:25:54 -0700 (PDT) (envelope-from balgaa@mtcone.net) Received: from dev ([202.179.0.113]) by publica.ub.mng.net (8.8.7/8.8.7) with SMTP id QAA07433 for ; Tue, 14 Jul 1998 16:29:45 +0800 (CST) Message-ID: <35AB1067.2C67@mtcone.net> Date: Tue, 14 Jul 1998 17:01:43 +0900 From: "Balgansuren.B" Organization: Mongolia Telecom X-Mailer: Mozilla 3.01SGoldC-SGI (X11; I; IRIX 6.3 IP32) MIME-Version: 1.0 To: freebsd-fs@FreeBSD.ORG Subject: I want to mount NTFS Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hello, I am new user of FreeBSD. i am using FreeBSD 2.2.6 and i want to mount NTFS disks on the my FreeBSD system. Anyone have some experience on this issue. Please, send me help information or advice? Thanks Balgansuren To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Tue Jul 14 14:03:07 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA14764 for freebsd-fs-outgoing; Tue, 14 Jul 1998 14:03:07 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewaya.anheuser-busch.com (gatewaya.anheuser-busch.com [151.145.250.252]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id OAA14756 for ; Tue, 14 Jul 1998 14:03:04 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewaya.anheuser-busch.com; id QAA27086; Tue, 14 Jul 1998 16:00:36 -0500 Received: from stlabcexg004.anheuser-busch.com(stlabcexg004 151.145.101.160) by gatewaya via smap (V2.1) id xma027068; Tue, 14 Jul 98 16:00:32 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id <3QYWQX9X>; Tue, 14 Jul 1998 22:03:41 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF90177660D@STLABCEXG011> From: "Alton, Matthew" To: "'FreeBSD-fs@FreeBSD.ORG'" Subject: LFS Hacking Date: Tue, 14 Jul 1998 22:03:55 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org OK people, I'm hip-deep in LFS code and the vfs/vnode interface and all the other goodies we need to make LFS happen. Are there any wish-list type requests or design deltas or anything before I move into the 'you should have said something earlier' phase? Right now, I'm just trying to stabilize the existing code. Once this done, I'll apply lessons learned to logging metadata only to make a journaling filesystem. Matthew Alton Computer Services - UNIX Systems Administration (314)632-6644 matthew.alton@anheuser-busch.com alton@plantnet.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Tue Jul 14 22:56:13 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id WAA23724 for freebsd-fs-outgoing; Tue, 14 Jul 1998 22:56:13 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id WAA23706 for ; Tue, 14 Jul 1998 22:56:03 -0700 (PDT) (envelope-from michaelh@cet.co.jp) Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.8.8/CET-v2.2) with SMTP id FAA23027; Wed, 15 Jul 1998 05:53:46 GMT Date: Wed, 15 Jul 1998 14:53:45 +0900 (JST) From: Michael Hancock To: "Alton, Matthew" cc: '" >" Subject: Re: LFS Hacking In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF90177660D@STLABCEXG011> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Tue, 14 Jul 1998, Alton, Matthew wrote: > OK people, I'm hip-deep in LFS code and the vfs/vnode interface > and all the other goodies we need to make LFS happen. Are there > any wish-list type requests or design deltas or anything before I > move into the 'you should have said something earlier' phase? > Right now, I'm just trying to stabilize the existing code. Once this > done, I'll apply lessons learned to logging metadata only to make > a journaling filesystem. Just go to it. If you get LFS working that'd be excellent. You do understand that a log structured filesystem is quite a different kettle of fish than a meta-data journaling filesystem, right? Regards, Mike Hancock To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Wed Jul 15 08:45:37 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA05455 for freebsd-fs-outgoing; Wed, 15 Jul 1998 08:45:37 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewaya.anheuser-busch.com (gatewaya.anheuser-busch.com [151.145.250.252]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id IAA05449 for ; Wed, 15 Jul 1998 08:45:36 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewaya.anheuser-busch.com; id KAA05575; Wed, 15 Jul 1998 10:43:09 -0500 Received: from stlabcexg004.anheuser-busch.com(stlabcexg004 151.145.101.160) by gatewaya via smap (V2.1) id xma005567; Wed, 15 Jul 98 10:42:42 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id <3851V181>; Wed, 15 Jul 1998 16:45:50 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF90177660E@STLABCEXG011> From: "Alton, Matthew" To: "Hancock, Michael (Internet)" Cc: "'FreeBSD-fs@FreeBSD.ORG'" Subject: RE: LFS Hacking Date: Wed, 15 Jul 1998 16:46:13 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > -----Original Message----- > From: Hancock, Michael (Internet) > Sent: Wednesday, July 15, 1998 12:54 AM > To: Alton, Matthew > Cc: 'FreeBSD-fs@FreeBSD.ORG' > Subject: Re: LFS Hacking > > On Tue, 14 Jul 1998, Alton, Matthew wrote: > > > OK people, I'm hip-deep in LFS code and the vfs/vnode interface > > and all the other goodies we need to make LFS happen. Are there > > any wish-list type requests or design deltas or anything before I > > move into the 'you should have said something earlier' phase? > > Right now, I'm just trying to stabilize the existing code. Once > this > > done, I'll apply lessons learned to logging metadata only to make > > a journaling filesystem. > > Just go to it. If you get LFS working that'd be excellent. > > You do understand that a log structured filesystem is quite a > different > kettle of fish than a meta-data journaling filesystem, right? [Alton, Matthew] Yupper. For the metadata-only one I would like to use ufs-style fixed-position inodes in conjunction with asyncronous I/O and do pending/commit flags in a IBM-JFS type fixed-size log. The 'lessons learned' will be general vfs-oid techniques &etc. I'm still not overly happy with the vfs/vnode structure but the chapter from Vahalla's _UNIX Internals_ has shed considerable light on the subject. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Wed Jul 15 09:29:49 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA11334 for freebsd-fs-outgoing; Wed, 15 Jul 1998 09:29:49 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewayb.anheuser-busch.com (gatewayb.anheuser-busch.com [151.145.250.253]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id JAA11325 for ; Wed, 15 Jul 1998 09:29:45 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewayb.anheuser-busch.com; id LAA21857; Wed, 15 Jul 1998 11:27:05 -0500 Received: from stlabcexg004.anheuser-busch.com( 151.145.101.160) by gatewayb via smap (V2.1) id xma021507; Wed, 15 Jul 98 11:26:53 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id <3851VFZS>; Wed, 15 Jul 1998 17:29:52 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF90177660F@STLABCEXG011> From: "Alton, Matthew" To: "'FreeBSD-fs@FreeBSD.ORG'" Subject: LFS & soft updates Date: Wed, 15 Jul 1998 17:30:16 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Just for fun - are lfs and Kirk McKusick's Ganger-Patt soft update scheme necessarily mutually exclusive? I don't know anything about soft updates yet. Just wondered if I should look at the GP papers before designing LFS v.2. Matthew Alton Computer Services - UNIX Systems Administration (314)632-6644 matthew.alton@anheuser-busch.com alton@plantnet.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Wed Jul 15 14:10:10 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA16589 for freebsd-fs-outgoing; Wed, 15 Jul 1998 14:10:10 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from smtp03.primenet.com (daemon@smtp03.primenet.com [206.165.6.133]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id OAA16584 for ; Wed, 15 Jul 1998 14:10:07 -0700 (PDT) (envelope-from tlambert@usr08.primenet.com) Received: (from daemon@localhost) by smtp03.primenet.com (8.8.8/8.8.8) id OAA19911; Wed, 15 Jul 1998 14:09:58 -0700 (MST) Received: from usr08.primenet.com(206.165.6.208) via SMTP by smtp03.primenet.com, id smtpd019897; Wed Jul 15 14:09:56 1998 Received: (from tlambert@localhost) by usr08.primenet.com (8.8.5/8.8.5) id OAA19937; Wed, 15 Jul 1998 14:09:54 -0700 (MST) From: Terry Lambert Message-Id: <199807152109.OAA19937@usr08.primenet.com> Subject: Re: LFS & soft updates To: Matthew.Alton@anheuser-busch.com (Alton, Matthew) Date: Wed, 15 Jul 1998 21:09:54 +0000 (GMT) Cc: FreeBSD-fs@FreeBSD.ORG In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF90177660F@STLABCEXG011> from "Alton, Matthew" at Jul 15, 98 05:30:16 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > Just for fun - are lfs and Kirk McKusick's Ganger-Patt soft update > scheme necessarily mutually exclusive? I don't know anything > about soft updates yet. Just wondered if I should look at the > GP papers before designing LFS v.2. Note: Doing this work would be a good Master's Thesis project; solving the general problem such that you could stack FS layers arbitrarily using the same underlying graph code would probably be worth a PhD Dissertation. LFS and soft updates are not mutually exclusive, but in order to optimize the representational geometry (how the structures are laid out, what they imply, precalculation instead of postcalculation of some dependency related issues, etc., etc.), the FFS soft dependency code as implemented is very depndent on the FFS architecture itself. It is possible to take a non-traditional view of an FS, and look at it as a series of events and actors. Each event/actor relationship is what the soft updates code represents, and the ordering of the actors operations as a result of the events is what a dependency models. Effectively, the code embodies the result of a Warshall's Algorithm run on the dependency graph generated from looking at the FS as events: transitive closure over the dependency graph. The work Julian, Kirk, and anyone else who has submitted patches have been engaged in is removing redundant OpenBSD and/or BSDI dependency nodes, and adding FreeBSD/unified VM dependency nodes. In addition, they have resolved some problems that are still issues for OpenBSD and BSDI (hopefully, both will benefit from the efforts). This work would have been a hell of a lot easier if the FFS and its interaction with the rest of the kernel and I/O subsystem had been documented in terms of event/actor relationships. If this had been done, one would need only to "diff" the graphs, and they would be, for all practical purposes, asking "will the code that needs to be changed please stand up". I personally would have preferred an implementation that registered a graph and computed the Warshal's at the time an FS was instanced (an O(3) algorithm, which is extermely cheap in graph theory terms), and pre-calculated the Hamiltonian cycles across the graph to allow people to stick new edges in later with a minimal recalculation cost. This would have allowed the soft updates mechanism to be extensible, at the cost of a full linear node traversal -- O(1) -- for each new nodal relationship (ie: stacking FS layers, export of a transactioning system to user space, etc.). This would have cost memory, as Kirk points out, but I don't think it would have cost as much memory as he seems to believe it would have cost, since you could still encode the dependency data as Kirk has done; the penalty would be serializing dependencies at the VFS/VFS boundry. The memory costs would be for inter-VFSOP dependency resoloution, seperate from the integration of this code into the FFS code within the ops themselves. If you want soft updates in the LFS code, which might make *some* sense, in terms of reducing the work for the cleaner, and adding implicit write gathering, and similar benefits to LFS, then you should do this: 1) Model the current FFS code in terms of event/actor relationships. Now that the soft updates code seems to be working fairly completely, this should be rather easy; just go through the code, and everywhere there is an incusrion of the soft udates code, that is an event/actor dependency relationship. 2) Now do the same for LFS. For the UFS code, which both LFS and FFS depend upon, this should be rather trivial, since it is already done. For the LFS code, you will have to specifically identify the points in the model where each event/actor relationship occurs. 3) Implement the dependency resoloution code that will be executed off of the slotted soft clock that is the syncd to resolve each of these relationships; both queuing of dependencies when the events occur, and conflicts on queued data changes which may occur between the new actors and the existing ones. This is not a trivial undertaking; mostly it is tedious detail work requiring a lot of academic rigor. A failure in rigor will result in a system that fails to operate as expected. As with the FFS soft updates code, a single missed dependency will result in a system that is, in certain circumstances, no better than async mounts (the degradation case is a system that is as unreliable as an async mount, and which fails to make the integrity guarantees that were the reason you expended the effort in the first place). I don't think I'm exagerating either the difficulty or the value of the resulting work. The original Ganger/Patt work was at this level of difficulty, and Kirk McKusick is definitely no slouch as a Computer Scientist, and he did not implement the code over night. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Wed Jul 15 14:43:38 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA21021 for freebsd-fs-outgoing; Wed, 15 Jul 1998 14:43:38 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewaya.anheuser-busch.com (gatewaya.anheuser-busch.com [151.145.250.252]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id OAA21013 for ; Wed, 15 Jul 1998 14:43:35 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewaya.anheuser-busch.com; id QAA03837; Wed, 15 Jul 1998 16:41:02 -0500 Received: from stlabcexg004.anheuser-busch.com(stlabcexg004 151.145.101.160) by gatewaya via smap (V2.1) id xma003816; Wed, 15 Jul 98 16:40:52 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id <3851VLPY>; Wed, 15 Jul 1998 22:44:02 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF901776611@STLABCEXG011> From: "Alton, Matthew" To: "'Terry Lambert'" Cc: FreeBSD-fs@FreeBSD.ORG Subject: RE: LFS & soft updates Date: Wed, 15 Jul 1998 22:44:29 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > -----Original Message----- > From: Terry Lambert [SMTP:tlambert@primenet.com] > Sent: Wednesday, July 15, 1998 4:10 PM > To: Alton, Matthew > Cc: FreeBSD-fs@FreeBSD.ORG > Subject: Re: LFS & soft updates > > > Just for fun - are lfs and Kirk McKusick's Ganger-Patt soft update > > scheme necessarily mutually exclusive? I don't know anything > > about soft updates yet. Just wondered if I should look at the > > GP papers before designing LFS v.2. > > Note: Doing this work would be a good Master's Thesis project; > solving the general problem such that you could stack FS layers > arbitrarily using the same underlying graph code would probably be > worth a PhD Dissertation. > [snip] > If you want soft updates in the LFS code, which might make *some* > sense, in terms of reducing the work for the cleaner, and adding > implicit write gathering, and similar benefits to LFS, then you > should do this: > [snip] To a first approximation, I'm parsing: "Well, it would be a real fine piece of academic calisthenics but I don't think you'll get much mileage out of it in the real world." ;-) Jeez, I do rem- ember "studying" this stuff one weekend and getting good and swamped in graph theory and thinking that I had come up with a better model but then realizing that it was only better for the special class of objects that I was obsessed with at the time. As a practical expedient I'm going to see if my "generalized seg- ment bubble sort" fever dream is valid and useful for the special case of append-only operations. It takes advantage of a small predictive capability to switch the positions of consecutive seg- ments should this be deemed a win by the algorithm. If the thing requires a prohibitively far-sighted prediction or if it winds up simply restating everything I've learned so far on the subject in the general case, well, then... back to the drawing board. > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 08:52:46 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA26625 for freebsd-fs-outgoing; Fri, 17 Jul 1998 08:52:46 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id IAA26608 for ; Fri, 17 Jul 1998 08:52:41 -0700 (PDT) (envelope-from michaelh@cet.co.jp) Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.8.8/CET-v2.2) with SMTP id PAA10506; Fri, 17 Jul 1998 15:51:05 GMT Date: Sat, 18 Jul 1998 00:51:05 +0900 (JST) From: Michael Hancock To: "Alton, Matthew" cc: "'Terry Lambert'" , FreeBSD-fs@FreeBSD.ORG Subject: RE: LFS & soft updates In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF901776611@STLABCEXG011> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org After you've implemented softupdates in LFS and NTFS you'll probably have learned enough to tackle a general solution as Terry suggests. ;-) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 09:07:49 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA04190 for freebsd-fs-outgoing; Fri, 17 Jul 1998 09:07:49 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id JAA04123 for ; Fri, 17 Jul 1998 09:07:43 -0700 (PDT) (envelope-from michaelh@cet.co.jp) Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.8.8/CET-v2.2) with SMTP id QAA10588; Fri, 17 Jul 1998 16:06:02 GMT Date: Sat, 18 Jul 1998 01:06:02 +0900 (JST) From: Michael Hancock To: "Alton, Matthew" cc: "'FreeBSD-fs@FreeBSD.ORG'" Subject: RE: LFS Hacking In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF90177660E@STLABCEXG011> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Wed, 15 Jul 1998, Alton, Matthew wrote: > Vahalla's > _UNIX Internals_ has shed considerable light on the subject. Yeah, excellent book. One thing that was wrong in the book was that it said in BSD 4.4 you were able to take advantage of state and process paths in chunks of components up to mount points in stateful systems. But it actually works as it does in SYSV processing component at a time as if all file systems were stateless. If we did take advantage of such state then stacking would probably even more complicated to get right. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 09:46:01 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id JAA11397 for freebsd-fs-outgoing; Fri, 17 Jul 1998 09:46:01 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewayb.anheuser-busch.com (gatewayb.anheuser-busch.com [151.145.250.253]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id JAA11384 for ; Fri, 17 Jul 1998 09:45:59 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewayb.anheuser-busch.com; id LAA10220; Fri, 17 Jul 1998 11:43:29 -0500 Received: from stlabcexg004.anheuser-busch.com( 151.145.101.160) by gatewayb via smap (V2.1) id xma009962; Fri, 17 Jul 98 11:43:10 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id ; Fri, 17 Jul 1998 17:46:10 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF901776614@STLABCEXG011> From: "Alton, Matthew" To: "Hancock, Michael (Internet)" Cc: "'FreeBSD-fs@FreeBSD.ORG'" Subject: RE: LFS Hacking Date: Fri, 17 Jul 1998 17:46:53 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > -----Original Message----- > From: Hancock, Michael (Internet) > Sent: Friday, July 17, 1998 11:06 AM > To: Alton, Matthew > Cc: 'FreeBSD-fs@FreeBSD.ORG' > Subject: RE: LFS Hacking > > On Wed, 15 Jul 1998, Alton, Matthew wrote: > > > Vahalla's > > _UNIX Internals_ has shed considerable light on the subject. > > Yeah, excellent book. One thing that was wrong in the book was that > it > said in BSD 4.4 you were able to take advantage of state and process > paths > in chunks of components up to mount points in stateful systems. But > it > actually works as it does in SYSV processing component at a time as if > all > file systems were stateless. > > If we did take advantage of such state then stacking would probably > even > more complicated to get right. [Alton, Matthew] Is Heideman's (or anyone else's) FS stacking being worked on right now? I tell ya, I spent a good 10 minutes last night in lamentation mode over the egregious and unforgivable termination of the ARPA BSD funding. I'm acclimating to the whole cathedral/bazaar thing but I just jones away something awful for the academic rigor and coordination that the old-timers had. I'm going to think up a way to do something about this. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 11:59:33 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA00371 for freebsd-fs-outgoing; Fri, 17 Jul 1998 11:59:33 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA00366 for ; Fri, 17 Jul 1998 11:59:32 -0700 (PDT) (envelope-from michaelh@cet.co.jp) Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.8.8/CET-v2.2) with SMTP id SAA11011; Fri, 17 Jul 1998 18:57:49 GMT Date: Sat, 18 Jul 1998 03:57:49 +0900 (JST) From: Michael Hancock To: "Alton, Matthew" cc: "'FreeBSD-fs@FreeBSD.ORG'" Subject: RE: LFS Hacking In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF901776614@STLABCEXG011> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Fri, 17 Jul 1998, Alton, Matthew wrote: > Is Heideman's (or anyone else's) FS stacking being worked on > right now? I was working on fixing layering violations with ref counting and locks on the VOP name ops. Heidemann's framework requires a symmetry such that the ops are the same above and below. These layering violations break the symmetry indirectly by side-effect. Terry uses the term "making it reflexive" to describe coding such that where the caller is responsible for releasing any references it takes. This is important in the case of stacking. He gets a lot of heat for using these odd terms but I find it convenient to use a single word to describe something that would normally take a sentence or two. I got most of it done before all these projects came along at work and I'm just too buried right now to finish the final 3 cases. One of these will be the toughest, VOP_RENAME. I understand the ufs_rename code now enough to do it correctly. I actually had to print the source out and highlight all the gotos to different exit points among other things before I had a clue as what was happening in there. Union_rename might be a good challenge, though. I expected NFS to be hard but now I expect it to be one of the easier ones. It's just bigger code, I mean the guy just didn't believe in subroutines or something. If I can just get these done then I can get rid of all the WILLRELE infrastructure. After this is done, work will be need to done to deal with vnode and cached object coherency, where cached objects are data pages or attributes such as the file size. John Heidemann has a paper on an approach that incorporates a central cache manager. It's a good paper but I'm not entirely convinced that his hand-off approach to locking and distributed protocols is really workable. > I tell ya, I spent a good 10 minutes last night in lamentation > mode over the > egregious and unforgivable termination of the ARPA BSD funding. > I'm > acclimating to the whole cathedral/bazaar thing but I just jones > away > something awful for the academic rigor and coordination that the > old-timers > had. I'm going to think up a way to do something about this. I'm still impressed by cathedrals and these days you can see Michelangelos in a bazaar now and then. Regards, Mike To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 14:13:38 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA23784 for freebsd-fs-outgoing; Fri, 17 Jul 1998 14:13:38 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewaya.anheuser-busch.com (gatewaya.anheuser-busch.com [151.145.250.252]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id OAA23742 for ; Fri, 17 Jul 1998 14:13:26 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewaya.anheuser-busch.com; id QAA21779; Fri, 17 Jul 1998 16:10:47 -0500 Received: from stlabcexg004.anheuser-busch.com(stlabcexg004 151.145.101.160) by gatewaya via smap (V2.1) id xma021769; Fri, 17 Jul 98 16:10:22 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id ; Fri, 17 Jul 1998 22:13:31 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF901776615@STLABCEXG011> From: "Alton, Matthew" To: "'FreeBSD-fs@FreeBSD.ORG'" Subject: Dual optimized disks Date: Fri, 17 Jul 1998 22:14:21 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I am working up a hare-brained crackpot FS scheme which uses 2 disks - one is read optimized and the other is write optimized but are logically identical. Is this a good idea? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 14:32:47 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA27620 for freebsd-fs-outgoing; Fri, 17 Jul 1998 14:32:47 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from smtp04.primenet.com (daemon@smtp04.primenet.com [206.165.6.134]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id OAA27598 for ; Fri, 17 Jul 1998 14:32:40 -0700 (PDT) (envelope-from tlambert@usr09.primenet.com) Received: (from daemon@localhost) by smtp04.primenet.com (8.8.8/8.8.8) id OAA18512; Fri, 17 Jul 1998 14:32:26 -0700 (MST) Received: from usr09.primenet.com(206.165.6.209) via SMTP by smtp04.primenet.com, id smtpd018402; Fri Jul 17 14:32:15 1998 Received: (from tlambert@localhost) by usr09.primenet.com (8.8.5/8.8.5) id OAA11571; Fri, 17 Jul 1998 14:31:57 -0700 (MST) From: Terry Lambert Message-Id: <199807172131.OAA11571@usr09.primenet.com> Subject: Re: LFS Hacking To: michaelh@cet.co.jp (Michael Hancock) Date: Fri, 17 Jul 1998 21:31:56 +0000 (GMT) Cc: Matthew.Alton@anheuser-busch.com, FreeBSD-fs@FreeBSD.ORG In-Reply-To: from "Michael Hancock" at Jul 18, 98 01:06:02 am X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > Vahalla's > > _UNIX Internals_ has shed considerable light on the subject. > > Yeah, excellent book. One thing that was wrong in the book was that it > said in BSD 4.4 you were able to take advantage of state and process paths > in chunks of components up to mount points in stateful systems. But it > actually works as it does in SYSV processing component at a time as if all > file systems were stateless. > > If we did take advantage of such state then stacking would probably even > more complicated to get right. The point was that the underlying VOP_LOOKUP could take one or more of the remainder of the path components in the cn_pnbuf to return a vnode. This allows things like network transport of relatively rooted paths from a network mount point. The code *still* permits this, but no one takes advantage of it in FreeBSD (in the Ficus project, this is used to do remote stack proxy to VFS layers on other machines). This is, in fact, why it is *wrong* to expect the underlying code to free your path buffers for you, or for VOP_ABORTOP to do it for you. The underlying layer may not be in the same address space, or even on the same machine. This means only the caller can free the memory with a 100% guarantee that the allocation and return occurs in the same address space. Proxy interfaces need to copy components across address spaces on the way in, and proxy modifications back on the way out. This is, in fact, the basis of my arguments for opaque, pre-parsed lists of path components in the calling interface. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 16:52:44 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id QAA18840 for freebsd-fs-outgoing; Fri, 17 Jul 1998 16:52:44 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from gatewayb.anheuser-busch.com (gatewayb.anheuser-busch.com [151.145.250.253]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id QAA18835 for ; Fri, 17 Jul 1998 16:52:42 -0700 (PDT) (envelope-from Matthew.Alton@anheuser-busch.com) Received: by gatewayb.anheuser-busch.com; id SAA12081; Fri, 17 Jul 1998 18:50:16 -0500 Received: from stlabcexg004.anheuser-busch.com( 151.145.101.160) by gatewayb via smap (V2.1) id xma012068; Fri, 17 Jul 98 18:50:11 -0500 Received: by stlabcexg004.anheuser-busch.com with Internet Mail Service (5.5.1960.3) id ; Sat, 18 Jul 1998 00:53:12 +0100 Message-ID: <31B3F0BF1C40D11192A700805FD48BF901776616@STLABCEXG011> From: "Alton, Matthew" To: "'FreeBSD-fs@FreeBSD.ORG'" Subject: LFS & soft updates Date: Fri, 17 Jul 1998 23:19:57 +0100 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.1960.3) Content-Type: text/plain Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org What is the status of the McKusick soft-update work? Specifically, I need to know if it is usable under 2.2.6 and if I have access to the code. Bear with me folks, this is just the manic phase. Good Things will come of all this mail traffic in the productive frenzy phase when I do all the coding. Then comes the quiescent phase where I mainly read philosophy and sleep. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Fri Jul 17 23:37:42 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id XAA25606 for freebsd-fs-outgoing; Fri, 17 Jul 1998 23:37:42 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from parkplace.cet.co.jp (parkplace.cet.co.jp [202.32.64.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id XAA25601 for ; Fri, 17 Jul 1998 23:37:40 -0700 (PDT) (envelope-from michaelh@cet.co.jp) Received: from localhost (michaelh@localhost) by parkplace.cet.co.jp (8.8.8/CET-v2.2) with SMTP id GAA13541; Sat, 18 Jul 1998 06:36:11 GMT Date: Sat, 18 Jul 1998 15:36:11 +0900 (JST) From: Michael Hancock To: "Alton, Matthew" cc: "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: LFS & soft updates In-Reply-To: <31B3F0BF1C40D11192A700805FD48BF901776616@STLABCEXG011> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Fri, 17 Jul 1998, Alton, Matthew wrote: > What is the status of the McKusick soft-update work? > Specifically, I need to know if it is usable under 2.2.6 and > if I have access to the code. It's only for current. If you don't have current then have a look at http://www.freebsd.org/~julian. > Bear with me folks, this is just the manic phase. Good > Things will come of all this mail traffic in the productive > frenzy phase when I do all the coding. Then comes the > quiescent phase where I mainly read philosophy and > sleep. ;-) Ok, don't keep us in the dark when you decide where you're going. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sat Jul 18 00:21:47 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id AAA28540 for freebsd-fs-outgoing; Sat, 18 Jul 1998 00:21:47 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from critter.freebsd.dk (critter.freebsd.dk [195.8.133.1] (may be forged)) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id AAA28534 for ; Sat, 18 Jul 1998 00:21:41 -0700 (PDT) (envelope-from phk@critter.freebsd.dk) Received: from critter.freebsd.dk (localhost [127.0.0.1]) by critter.freebsd.dk (8.8.7/8.8.5) with ESMTP id JAA01847; Sat, 18 Jul 1998 09:18:23 +0200 (CEST) To: "Alton, Matthew" cc: "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: Dual optimized disks In-reply-to: Your message of "Fri, 17 Jul 1998 22:14:21 BST." <31B3F0BF1C40D11192A700805FD48BF901776615@STLABCEXG011> Date: Sat, 18 Jul 1998 09:18:20 +0200 Message-ID: <1845.900746300@critter.freebsd.dk> From: Poul-Henning Kamp Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org In message <31B3F0BF1C40D11192A700805FD48BF901776615@STLABCEXG011>, "Alton, Mat thew" writes: >I am working up a hare-brained crackpot FS scheme which >uses 2 disks - one is read optimized and the other is write >optimized but are logically identical. Is this a good idea? s/2/N/ and it sounds like LFS with each segment on a separate disk, which performance wise can be a good idea. -- Poul-Henning Kamp FreeBSD coreteam member phk@FreeBSD.ORG "Real hackers run -current on their laptop." "ttyv0" -- What UNIX calls a $20K state-of-the-art, 3D, hi-res color terminal To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sat Jul 18 02:36:34 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id CAA05412 for freebsd-fs-outgoing; Sat, 18 Jul 1998 02:36:34 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from smtp02.primenet.com (daemon@smtp02.primenet.com [206.165.6.132]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id CAA05407 for ; Sat, 18 Jul 1998 02:36:31 -0700 (PDT) (envelope-from tlambert@usr07.primenet.com) Received: (from daemon@localhost) by smtp02.primenet.com (8.8.8/8.8.8) id CAA08550; Sat, 18 Jul 1998 02:36:11 -0700 (MST) Received: from usr07.primenet.com(206.165.6.207) via SMTP by smtp02.primenet.com, id smtpd008544; Sat Jul 18 02:36:07 1998 Received: (from tlambert@localhost) by usr07.primenet.com (8.8.5/8.8.5) id CAA03733; Sat, 18 Jul 1998 02:35:59 -0700 (MST) From: Terry Lambert Message-Id: <199807180935.CAA03733@usr07.primenet.com> Subject: Re: LFS & soft updates To: michaelh@cet.co.jp (Michael Hancock) Date: Sat, 18 Jul 1998 09:35:59 +0000 (GMT) Cc: Matthew.Alton@anheuser-busch.com, FreeBSD-fs@FreeBSD.ORG In-Reply-To: from "Michael Hancock" at Jul 18, 98 03:36:11 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > What is the status of the McKusick soft-update work? > > Specifically, I need to know if it is usable under 2.2.6 and > > if I have access to the code. > > It's only for current. If you don't have current then have a > look at http://www.freebsd.org/~julian. See my recent postings. The soft updates code is intrinsically tied to the buffer cache implementation because of what constitutes a dependency. Because 2.2.6 and -current have different implementations, the code will not port over easily. The implementations are similar, of course, but the code depends on a brute-force soloution to a graph problem. To do the port, you would effectively have to do what I suggested was necessary for an LFS port. One interesting thing to note is that there may, in fact, be more dependencies being queued than is strictly necessary; doing the documentation of the events/actors might be a good thing for the -current code, as well, since it might lead to simplifications of the existing code. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message From owner-freebsd-fs Sat Jul 18 07:19:52 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id HAA24779 for freebsd-fs-outgoing; Sat, 18 Jul 1998 07:19:52 -0700 (PDT) (envelope-from owner-freebsd-fs@FreeBSD.ORG) Received: from usc.usc.unal.edu.co ([200.21.26.65]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id HAA24773 for ; Sat, 18 Jul 1998 07:19:50 -0700 (PDT) (envelope-from giffunip@asme.org) Received: from unalmodem01.usc.unal.edu.co by usc.usc.unal.edu.co (AIX 4.1/UCB 5.64/4.03) id AA12562; Sat, 18 Jul 1998 09:59:42 -0400 Message-Id: <35B0AEA4.AEBAA77B@asme.org> Date: Sat, 18 Jul 1998 09:18:12 -0500 From: "Pedro F. Giffuni" Organization: U. Nacional de Colombia X-Mailer: Mozilla 4.04 [en] (X11; I; FreeBSD 2.2.6-RELEASE i386) Mime-Version: 1.0 To: "Alton, Matthew" Cc: "'FreeBSD-fs@FreeBSD.ORG'" Subject: Re: LFS Hacking References: <31B3F0BF1C40D11192A700805FD48BF90177660D@STLABCEXG011> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-fs@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org A small search for "Sprite OS" in altavista took me to this place: http://casaturn.kaist.ac.kr/~sikang/os/lfs/ enjoy, Pedro Alton, Matthew wrote: > OK people, I'm hip-deep in LFS code and the vfs/vnode interface > and all the other goodies we need to make LFS happen. Are there > any wish-list type requests or design deltas or anything before I > move into the 'you should have said something earlier' phase? > Right now, I'm just trying to stabilize the existing code. Once this > done, I'll apply lessons learned to logging metadata only to make > a journaling filesystem. > > Matthew Alton > Computer Services - UNIX Systems Administration > (314)632-6644 matthew.alton@anheuser-busch.com > alton@plantnet.com > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-fs" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-fs" in the body of the message