From owner-freebsd-scsi@FreeBSD.ORG Sun Sep 11 04:08:12 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D929916A420 for ; Sun, 11 Sep 2005 04:08:12 +0000 (GMT) (envelope-from ameliorating@morton.to) Received: from pool-70-22-227-152.bos.east.verizon.net (pool-70-22-227-152.bos.east.verizon.net [70.22.227.152]) by mx1.FreeBSD.org (Postfix) with SMTP id 922CC43D58 for ; Sun, 11 Sep 2005 04:08:09 +0000 (GMT) (envelope-from ameliorating@morton.to) Received: from 110.207.104.93 (EHLO blabbermouths) by pool-70-22-227-152.bos.east.verizon.net with SMTP; Sun, 11 Sep 2005 00:08:06 -0400 id 5210188016screamer80322 for freebsd-scsi@freebsd.org; Sun, 11 Sep 2005 00:08:06 -0400 Mime-Version: 1.0 (Apple Message framework v728) Content-Transfer-Encoding: 7bit Message-Id: <2747394577.9475881695@pool-70-22-227-152.bos.east.verizon.net> Content-Type: text/plain; charset=US-ASCII; format=flowed To: freebsd-scsi@freebsd.org From: Eve Date: Sun, 11 Sep 2005 00:08:05 -0400 X-Mailer: Apple Mail (2.728) Subject: Our pills doctor tested and approved! X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 11 Sep 2005 04:08:13 -0000 You and your partner can relax and take your time to choose the moment that's right for both of you. http://jcr.kt7tp8qe8uqak22w7kkw7k22.vigoniaakeh.com/?ygwhspm Children speak in the field what they hear in the house. Behold the man. (Ecce Homo) Look for the ridiculous in everything, and you will find it. The illegal we do immediately. The unconstitutional takes a little longer. The limits of my language mean the limits of my world. I think there is a world market for maybe five computers. Too low they build, who build beneath the stars. From owner-freebsd-scsi@FreeBSD.ORG Sun Sep 11 15:16:21 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 57E8516A41F; Sun, 11 Sep 2005 15:16:21 +0000 (GMT) (envelope-from dean@stack.nl) Received: from mailhost.stack.nl (vaak.stack.nl [131.155.140.140]) by mx1.FreeBSD.org (Postfix) with ESMTP id E7C0143D45; Sun, 11 Sep 2005 15:16:20 +0000 (GMT) (envelope-from dean@stack.nl) Received: from snail.stack.nl (snail.stack.nl [IPv6:2001:610:1108:5010::131]) by mailhost.stack.nl (Postfix) with ESMTP id 725B6A2FF2; Sun, 11 Sep 2005 17:16:19 +0200 (CEST) Received: by snail.stack.nl (Postfix, from userid 1600) id 67FE02287F; Sun, 11 Sep 2005 17:16:19 +0200 (CEST) Date: Sun, 11 Sep 2005 17:16:19 +0200 From: Dean Strik To: Danny Braniss Message-ID: <20050911151619.GC15948@stack.nl> References: Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="UFHRwCdBEJvubb2X" Content-Disposition: inline In-Reply-To: X-Really: Yes User-Agent: Mutt/1.5.9i Cc: Danny Howard , freebsd-questions@freebsd.org, freebsd-scsi@freebsd.org Subject: Re: Fibre Channel disks to two Systems? X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 11 Sep 2005 15:16:21 -0000 --UFHRwCdBEJvubb2X Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Danny Braniss wrote: > hi danny > you are asking too many questions :-), but w/r to netapp: > same computer, 1gbE, NFS is about 50% slower than FC. > btw, iSCSI (still beta) is only slightly faster than NFS > (note NFS is UDP, iSCSI is TCP). Of course NFS can be TCP as well. And must be TCP for NFSv4. > as to reliability, the netapp is worth avery penny (actualy K$ :-), had o= nly=20 > one major breakdown in over 10 years. Same experiences here, with lots of NetApps. I would however not be happy running PostgreSQL over NFS. With FC/iSCSI, no problem. --=20 Dean C. Strik Eindhoven University of Technology dean@stack.nl | dean@ipnet6.org | http://www.ipnet6.org/ "This isn't right. This isn't even wrong." -- Wolfgang Pauli --UFHRwCdBEJvubb2X Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2 (FreeBSD) iD8DBQFDJEpD5Td/bYnvOAMRAjAeAJ0fqkAEa0fq9UBGJNRUYZ++4dt36wCfai/H 0s62PYd1Qw0abmjnMjz33pU= =aSVy -----END PGP SIGNATURE----- --UFHRwCdBEJvubb2X-- From owner-freebsd-scsi@FreeBSD.ORG Sun Sep 11 18:59:10 2005 Return-Path: X-Original-To: freebsd-scsi@FreeBSD.ORG Delivered-To: freebsd-scsi@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1831216A41F for ; Sun, 11 Sep 2005 18:59:10 +0000 (GMT) (envelope-from tonix@interazioni.it) Received: from smtp.ufficiopostale.it (servizi.interazioni.it [194.183.4.167]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5465043D49 for ; Sun, 11 Sep 2005 18:59:08 +0000 (GMT) (envelope-from tonix@interazioni.it) Received: (qmail 22348 invoked by uid 85); 11 Sep 2005 18:59:06 -0000 Received: from tonix@interazioni.it by avsmtp.ufficiopostale.it by uid 88 with qmail-scanner-1.12 (nod32: 1.1213 (20050909)/. Clear:. Processed in 0.200379 secs); 11 Sep 2005 18:59:06 -0000 X-Qmail-Scanner-Mail-From: tonix@interazioni.it via avsmtp.ufficiopostale.it X-Qmail-Scanner: 1.12 (Clear:. Processed in 0.200379 secs) Received: from unknown (HELO IATonino.interazioni.it) (tonix@interazioni.it@213.233.2.94) by relay.interazioni.net with SMTP; 11 Sep 2005 18:59:06 -0000 Message-Id: <6.2.3.4.0.20050911192854.04db7b90@pop.ufficiopostale.it> X-Mailer: QUALCOMM Windows Eudora Version 6.2.3.4 Date: Sun, 11 Sep 2005 19:56:08 +0100 To: freebsd-scsi@FreeBSD.ORG From: "tonix (Antonio Nati)" In-Reply-To: <20050909135705.O84118@sasami.jurai.net> References: <6.2.3.4.0.20050901172618.0532ecb0@pop.ufficiopostale.it> <20050906084747.A84118@sasami.jurai.net> <6.2.3.4.0.20050907153854.04c36bc8@pop.ufficiopostale.it> <6.2.3.4.0.20050907163520.05554a30@pop.ufficiopostale.it> <6.2.3.4.0.20050907164953.0548c070@pop.ufficiopostale.it> <20050907133856.C84118@sasami.jurai.net> <6.2.3.4.0.20050909120032.053cc160@pop.ufficiopostale.it> <20050909135705.O84118@sasami.jurai.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Subject: Re: IDAD0 rebuilding (was: Re: camcontrol and IDAD0) X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 11 Sep 2005 18:59:10 -0000 At 18.58 09/09/2005, Matthew N. Dodd wrote: >On Fri, 9 Sep 2005, tonix (Antonio Nati) wrote: >>Finally, these controllers seems to be unusable in a production >>environment with FreeBSD. > >I don't think anyone has really tested rebuilding a volume while the >system is running. > >I'd be interested in the results of changing the definition of >IDA_QCB_MAX from 256 to 128. > >See sys/dev/ida/idavar.h: > > #define IDA_QCB_MAX 256 With IDA_QCB_MAX => 128; processes working process 1 -> tar of whole disk to file, then gzip file, then delete file process 2 -> rebuild world process 3 -> every ten second "idacontrol show" action: during these jobs, I extract one disk, wait 20 seconds and insert it again observing until rebuilding has finished. With DL360 G1 2x933 CPU and Integrated Smart Array, RAID = 1 (2 x 18GB disks) No problems with controller rebuilding priority on every level (low, medium, high) idacontrol always shows correct status and percent of rebuilding still to be done Only some console logs like "ida_command: out of QCBs" When disk is removed or inserted great bunchs of soft errors. A lot of soft errors every time "idacontrol show" is run. With DL580 G1 4x700 CPU and Integrated Smart Array, RAID = 0+1 (4 x 36GB disks) Systems never hangs but rebuilding does not work (apparently). When reinserting the extracted disk, rebuild does not start until I run "idacontrol recover". After running this command, rebuilding seem extremely slow, and after a few minutes status of RAID set turns to "interim". Again "idacontrol recover" and again "interim" after a few minutes. Display of rebuilding missing start from 50% (as only one disk of two must be rebuilded). With DL580 G1 4x700 CPU and Integrated Smart Array, RAID = 5 (3+1 x 9GB disks) When Smart Array is initializating the RAID 5 set, bootstrap says Smart Arrays is yet optimizing datas, while idacontrol says arrays is OK. Who to trust? Still to test rebuilding with processes doing I/O. Tonino >-- >10 40 80 C0 00 FF FF FF FF C0 00 00 00 00 10 AA AA 03 00 00 00 08 00 From owner-freebsd-scsi@FreeBSD.ORG Mon Sep 12 00:11:35 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 870E816A41F; Mon, 12 Sep 2005 00:11:35 +0000 (GMT) (envelope-from jonathan@fosburgh.org) Received: from pop-siberian.atl.sa.earthlink.net (pop-siberian.atl.sa.earthlink.net [207.69.195.71]) by mx1.FreeBSD.org (Postfix) with ESMTP id 32D9A43D45; Mon, 12 Sep 2005 00:11:35 +0000 (GMT) (envelope-from jonathan@fosburgh.org) Received: from user-0cetsk1.cable.mindspring.com ([24.238.242.129] helo=gw.fosburgh.org) by pop-siberian.atl.sa.earthlink.net with esmtp (Exim 3.36 #10) id 1EEbv4-0007g1-00; Sun, 11 Sep 2005 20:11:34 -0400 Received: by gw.fosburgh.org (Postfix, from userid 1001) id E8305B781; Sun, 11 Sep 2005 19:13:54 -0500 (CDT) From: Jonathan Fosburgh To: freebsd-questions@freebsd.org Date: Sun, 11 Sep 2005 19:13:53 -0500 User-Agent: KMail/1.8.2 References: <20050909185935.GI31865@ratchet.nebcorp.com> In-Reply-To: <20050909185935.GI31865@ratchet.nebcorp.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200509111913.54170.jonathan@fosburgh.org> Cc: Danny Howard , freebsd-scsi@freebsd.org Subject: Re: Fibre Channel disks to two Systems? X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Sep 2005 00:11:35 -0000 On Friday 09 September 2005 01:59 pm, Danny Howard wrote: > > >From my research, I am thus far most impressed with the SANbloc 2Gb, > > which holds fourteen FC drives in a 3U rackmount. It can be had with > redundant RAID controllers, or as a JBOD. There are similar products > from other vendors as well. Unfortunately I have no experience doing anything SAN related on FreeBSD, but I think I can say that you would do just fine with any Engenio-based (IBM, StorageTek, Maxxan, etc) product. They seem to manufacture most of the modular fibre channel storage out there, and they also sell FC-attached SATA hardware. Of course if someone actually mentions they support FreeBSD then probably go with that, otherwise you are likely to be on your own. > > I could concievably do the RAID in software by running a gstripe across a > set of gmirrors. > > As I understand it, I can have an FC loop with one or more drives, > connected to two servers, and either server can talk to one or the other > drives exclusively. My QUESTION is: how is the arbitration done in > FreeBSD? You run camcontrol on either server and activate / deactivate > drives in the loop? > > What happens if say, the primary server locks up in some weird manner? > Can it block the backup server from talking to the drives? (We can > always have a NOC tech turn off a badly failed primary database, and > power-cycle the disk array, if needed ...) > > A really far-out idea I had was that with fourteen drive bays I could > have two hot spares, and then set up a stripe across four mirrored pairs > (4x2 = 8-disk RAID10) and then with the remaining four drives assign > each to be a third component of the gmirrored pairs, let the gmirrors > sync up, then detach those drives from the gmirrors, mount them on the > backup database, gstripe those containers together, and have a > point-in-time "snapshot" of the drive array that could be mounted on the > backup server, from which I could run database dumps, or conduct > failover tests, etc. (I could kick this around -geom. :) > > Uhmmm, has anyone done similar? Suggestions? Feedback? Advice? > > Or, should I try to get a NetApp, or similar device, even though FreeBSD > does not support iSCSI, because NFS performance over GigE may still beat > FC? I can't believe that FreeBSD would have such poor support for FC that NFS performs better. :) Remember you dealing with block I/O on the storage array and file I/O on the NetApp (which I think supports either NFS or CIFS). There are (or have been) some proprietary database vendors (Microsoft comes to mind...) who don't allow their databases to run on any kind of NAS setup (which is what the NetApp is). Granted I don't know if Postres gives support for putting databases on raw devices or if it only supports putting the database on a filesystem, so you may not get the full benefits of using block storage. Still, for a database, I think you should use block storage if at all possible. Alas, I can't speak to how you can give multiple FreeBSD systems access to the same storage device. > > Also, does anyone have a FreeBSD-friendly storage systems integrator or > other vendor they can reccomend, particularly one near the San Francisco > area? I keep contacting various vendors who then fail to get back to > me. :( Personally I have never seen a storage vendor who supports FreeBSD, but I deal with large enterprise players where Linux is only just in the last couple of years enjoying broad support. Maybe the smaller vendors are more likely to support FreeBSD. Are there any Bay area FBSD user's groups? You might try them. > > Thanks for all feedback and suggestions! > > Sincerely, > -danny -- Jonathan Fosburgh Storage Engineer/Architect From owner-freebsd-scsi@FreeBSD.ORG Mon Sep 12 11:02:14 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5B25516A425 for ; Mon, 12 Sep 2005 11:02:14 +0000 (GMT) (envelope-from owner-bugmaster@freebsd.org) Received: from freefall.freebsd.org (freefall.freebsd.org [216.136.204.21]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0E9B543D62 for ; Mon, 12 Sep 2005 11:02:11 +0000 (GMT) (envelope-from owner-bugmaster@freebsd.org) Received: from freefall.freebsd.org (peter@localhost [127.0.0.1]) by freefall.freebsd.org (8.13.3/8.13.3) with ESMTP id j8CB2BMW025566 for ; Mon, 12 Sep 2005 11:02:11 GMT (envelope-from owner-bugmaster@freebsd.org) Received: (from peter@localhost) by freefall.freebsd.org (8.13.3/8.13.1/Submit) id j8CB2ABh025560 for freebsd-scsi@freebsd.org; Mon, 12 Sep 2005 11:02:10 GMT (envelope-from owner-bugmaster@freebsd.org) Date: Mon, 12 Sep 2005 11:02:10 GMT Message-Id: <200509121102.j8CB2ABh025560@freefall.freebsd.org> X-Authentication-Warning: freefall.freebsd.org: peter set sender to owner-bugmaster@freebsd.org using -f From: FreeBSD bugmaster To: freebsd-scsi@FreeBSD.org Cc: Subject: Current problem reports assigned to you X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Sep 2005 11:02:14 -0000 Current FreeBSD problem reports Critical problems Serious problems S Submitted Tracker Resp. Description ------------------------------------------------------------------------------- o [2001/05/03] kern/27059 scsi (symbios) SCSI subsystem hangs under heav o [2001/06/29] kern/28508 scsi problems with backup to Tandberg SLR40 st o [2002/06/17] kern/39388 scsi ncr/sym drivers fail with 53c810 and more o [2002/07/22] kern/40895 scsi wierd kernel / device driver bug s [2003/09/30] kern/57398 scsi Current fails to install on mly(4) based o [2003/12/26] kern/60598 scsi wire down of scsi devices conflicts with a [2004/01/10] kern/61165 scsi [panic] kernel page fault after calling c o [2004/09/15] kern/71778 scsi 5.3 BETA3 doesnt see Adaptec 2015S FW Rev o [2004/12/02] kern/74607 scsi FreeBSD 5.3 install CD crashes on SCSI de o [2004/12/02] kern/74627 scsi Adaptec 2940U2W Can't boot 5.3 o [2005/06/04] kern/81887 scsi Adaptec SCSI 2130S aac0: GetDeviceProbeIn 11 problems total. Non-critical problems S Submitted Tracker Resp. Description ------------------------------------------------------------------------------- o [2000/12/06] kern/23314 scsi aic driver fails to detect Adaptec 1520B o [2001/08/15] kern/29727 scsi [amr] [patch] amr_enquiry3 structure in a o [2002/02/23] kern/35234 scsi World access to /dev/pass? (for scanner) o [2002/06/02] kern/38828 scsi [feature request] DPT PM2012B/90 doesn't o [2002/10/29] kern/44587 scsi dev/dpt/dpt.h is missing defines required o [2003/10/01] kern/57469 scsi [patch] Quirk for Conner CP3500 6 problems total. From owner-freebsd-scsi@FreeBSD.ORG Mon Sep 12 12:07:37 2005 Return-Path: X-Original-To: freebsd-scsi@FreeBSD.ORG Delivered-To: freebsd-scsi@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 52E9516A41F for ; Mon, 12 Sep 2005 12:07:37 +0000 (GMT) (envelope-from tonix@interazioni.it) Received: from smtp.ufficiopostale.it (servizi.interazioni.it [194.183.4.167]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6CE2C43D53 for ; Mon, 12 Sep 2005 12:07:35 +0000 (GMT) (envelope-from tonix@interazioni.it) Received: (qmail 50315 invoked by uid 85); 12 Sep 2005 12:07:34 -0000 Received: from tonix@interazioni.it by avsmtp.ufficiopostale.it by uid 88 with qmail-scanner-1.12 (nod32: 1.1213 (20050909)/. Clear:. Processed in 0.143109 secs); 12 Sep 2005 12:07:34 -0000 X-Qmail-Scanner-Mail-From: tonix@interazioni.it via avsmtp.ufficiopostale.it X-Qmail-Scanner: 1.12 (Clear:. Processed in 0.143109 secs) Received: from unknown (HELO IATonino.interazioni.it) (tonix@interazioni.it@213.233.2.94) by relay.interazioni.net with SMTP; 12 Sep 2005 12:07:34 -0000 Message-Id: <6.2.3.4.0.20050912130613.053f5a60@pop.ufficiopostale.it> X-Mailer: QUALCOMM Windows Eudora Version 6.2.3.4 Date: Mon, 12 Sep 2005 13:07:29 +0100 To: freebsd-scsi@FreeBSD.ORG From: "tonix (Antonio Nati)" In-Reply-To: <6.2.3.4.0.20050911192854.04db7b90@pop.ufficiopostale.it> References: <6.2.3.4.0.20050901172618.0532ecb0@pop.ufficiopostale.it> <20050906084747.A84118@sasami.jurai.net> <6.2.3.4.0.20050907153854.04c36bc8@pop.ufficiopostale.it> <6.2.3.4.0.20050907163520.05554a30@pop.ufficiopostale.it> <6.2.3.4.0.20050907164953.0548c070@pop.ufficiopostale.it> <20050907133856.C84118@sasami.jurai.net> <6.2.3.4.0.20050909120032.053cc160@pop.ufficiopostale.it> <20050909135705.O84118@sasami.jurai.net> <6.2.3.4.0.20050911192854.04db7b90@pop.ufficiopostale.it> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Cc: Subject: Re: IDAD0 rebuilding (was: Re: camcontrol and IDAD0) X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 12 Sep 2005 12:07:37 -0000 At 19.56 11/09/2005, tonix (Antonio Nati) wrote: >With IDA_QCB_MAX => 128; > >processes working > process 1 -> tar of whole disk to file, then gzip file, > then delete file > process 2 -> rebuild world > process 3 -> every ten second "idacontrol show" >action: > during these jobs, I extract one disk, wait 20 seconds and > insert it again observing until rebuilding has finished. > > > >With DL580 G1 4x700 CPU and Integrated Smart Array, RAID = 5 (3+1 x 9GB disks) > When Smart Array is initializating the RAID 5 set, > bootstrap says Smart Arrays is yet optimizing datas, > while idacontrol says arrays is OK. Who to trust? > > Still to test rebuilding with processes doing I/O. While RAID5 is rebuilding system never hangs, just millions of soft errors. Tonino >>-- >>10 40 80 C0 00 FF FF FF FF C0 00 00 00 00 10 AA AA 03 00 00 00 08 00 > >_______________________________________________ >freebsd-scsi@freebsd.org mailing list >http://lists.freebsd.org/mailman/listinfo/freebsd-scsi >To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" From owner-freebsd-scsi@FreeBSD.ORG Thu Sep 15 12:53:54 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id CAECC16A41F for ; Thu, 15 Sep 2005 12:53:54 +0000 (GMT) (envelope-from ath@niksun.com) Received: from anuket.mj.niksun.com (gwnew.niksun.com [65.115.46.162]) by mx1.FreeBSD.org (Postfix) with ESMTP id 40EE943D45 for ; Thu, 15 Sep 2005 12:53:51 +0000 (GMT) (envelope-from ath@niksun.com) Received: from stiegl.mj.niksun.com (stiegl.mj.niksun.com [10.70.0.231]) by anuket.mj.niksun.com (8.13.1/8.13.1) with ESMTP id j8FCxVhO003216; Thu, 15 Sep 2005 08:59:31 -0400 (EDT) (envelope-from ath@niksun.com) Received: from stiegl.mj.niksun.com (localhost [127.0.0.1]) by stiegl.mj.niksun.com (Postfix) with ESMTP id ED95C5778; Thu, 15 Sep 2005 08:53:50 -0400 (EDT) Date: Thu, 15 Sep 2005 08:53:50 -0400 From: Andrew Heybey To: freebsd-scsi@freebsd.org Message-ID: <20050915085350.3a14cb88@stiegl.mj.niksun.com> X-Mailer: Sylpheed-Claws 1.9.11 (GTK+ 2.6.8; i386-portbld-freebsd4.11) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.85.1/1082/Wed Sep 14 11:22:17 2005 on anuket.mj.niksun.com X-Virus-Status: Clean Cc: Subject: LUN probing problem with 6.0-BETA4 and seagate drive X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Sep 2005 12:53:54 -0000 I just upgraded a box from 5.3 to 6.0-BETA4. I have this drive on the system: da5 at ahc1 bus 0 target 0 lun 0 da5: Fixed Direct Access SCSI-3 device da5: 40.000MB/s transfers (20.000MHz, offset 63, 16bit) da5: 34732MB (71132960 512 byte sectors: 255H 63S/T 4427C) I think that the "SX" means it has EMC firmware (not sure of the drives history, it is an ebay purchase). It is attached to this HBA: ahc1: port 0x6000-0x60ff mem 0xfc001000-0xfc001fff irq 17 at device 4.1 on pci1 With 5.3 it worked fine. With 6.0-BETA4, I get 200+ iterations of this message at boot time: Sep 13 14:26:45 spaten kernel: SEQADDR == 0x16c Sep 13 14:26:45 spaten kernel: ahc1:A:0: Message reject for 80 -- ignored Sep 13 14:26:45 spaten kernel: (probe0:ahc1:0:0:56): Unexpected busfree in Message-in phase Sep 13 14:26:45 spaten kernel: SEQADDR == 0x16c Sep 13 14:26:45 spaten kernel: ahc1:A:0: Message reject for 80 -- ignored Sep 13 14:26:45 spaten kernel: (probe0:ahc1:0:0:57): Unexpected busfree in Message-in phase I worked around the problem by applying the following patch to sys/cam/cam_xpt.c: Index: cam_xpt.c =================================================================== RCS file: /usr/local/repos/fbsdcvs/src/sys/cam/cam_xpt.c,v retrieving revision 1.155 diff -u -u -r1.155 cam_xpt.c --- cam_xpt.c 1 Jul 2005 15:21:29 -0000 1.155 +++ cam_xpt.c 15 Sep 2005 12:47:06 -0000 @@ -477,6 +477,15 @@ }, { /* + * This Seagate drive with EMC firmware causes + * "Unexpected busfree" and "message reject" + * messages at boot time when LUNs are probed. + */ + { T_DIRECT, SIP_MEDIA_FIXED, "SEAGATE", "SX336704*", "*" }, + CAM_QUIRK_NOLUNS, /*mintags*/0, /*maxtags*/0 + }, + { + /* * The Hitachi CJ series with J8A8 firmware apparantly has * problems with tagged commands. * PR: 23536 Is this the correct thing to do, or is there a bug in the ahc driver? I am curious why I get "Unexpected busfree" messages with 6.0-BETA4 and not with 5.3. If the quirk is the right thing to do, it should probably be "SX*"... andrew From owner-freebsd-scsi@FreeBSD.ORG Thu Sep 15 15:33:06 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B33CC16A41F for ; Thu, 15 Sep 2005 15:33:06 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id DA37F43D5D for ; Thu, 15 Sep 2005 15:33:02 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [192.168.254.14] (imini.samsco.home [192.168.254.14]) (authenticated bits=0) by pooker.samsco.org (8.13.3/8.13.3) with ESMTP id j8FFWxNW089781; Thu, 15 Sep 2005 09:32:59 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <4329942A.4010705@samsco.org> Date: Thu, 15 Sep 2005 09:32:58 -0600 From: Scott Long User-Agent: Mozilla/5.0 (Macintosh; U; PPC Mac OS X Mach-O; en-US; rv:1.7.7) Gecko/20050416 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Andrew Heybey References: <20050915085350.3a14cb88@stiegl.mj.niksun.com> In-Reply-To: <20050915085350.3a14cb88@stiegl.mj.niksun.com> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-2.8 required=3.8 tests=ALL_TRUSTED autolearn=failed version=3.0.2 X-Spam-Checker-Version: SpamAssassin 3.0.2 (2004-11-16) on pooker.samsco.org Cc: freebsd-scsi@freebsd.org Subject: Re: LUN probing problem with 6.0-BETA4 and seagate drive X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Sep 2005 15:33:06 -0000 Andrew Heybey wrote: > I just upgraded a box from 5.3 to 6.0-BETA4. > > I have this drive on the system: > > da5 at ahc1 bus 0 target 0 lun 0 > da5: Fixed Direct Access SCSI-3 device > da5: 40.000MB/s transfers (20.000MHz, offset 63, 16bit) > da5: 34732MB (71132960 512 byte sectors: 255H 63S/T 4427C) > > I think that the "SX" means it has EMC firmware (not sure of the drives > history, it is an ebay purchase). > > It is attached to this HBA: > > ahc1: port 0x6000-0x60ff mem 0xfc001000-0xfc001fff irq 17 at device 4.1 on pci1 > > With 5.3 it worked fine. With 6.0-BETA4, I get 200+ iterations of this message at boot time: > > Sep 13 14:26:45 spaten kernel: SEQADDR == 0x16c > Sep 13 14:26:45 spaten kernel: ahc1:A:0: Message reject for 80 -- ignored > Sep 13 14:26:45 spaten kernel: (probe0:ahc1:0:0:56): Unexpected busfree in Message-in phase > Sep 13 14:26:45 spaten kernel: SEQADDR == 0x16c > Sep 13 14:26:45 spaten kernel: ahc1:A:0: Message reject for 80 -- ignored > Sep 13 14:26:45 spaten kernel: (probe0:ahc1:0:0:57): Unexpected busfree in Message-in phase > > I worked around the problem by applying the following patch to sys/cam/cam_xpt.c: > > Index: cam_xpt.c > =================================================================== > RCS file: /usr/local/repos/fbsdcvs/src/sys/cam/cam_xpt.c,v > retrieving revision 1.155 > diff -u -u -r1.155 cam_xpt.c > --- cam_xpt.c 1 Jul 2005 15:21:29 -0000 1.155 > +++ cam_xpt.c 15 Sep 2005 12:47:06 -0000 > @@ -477,6 +477,15 @@ > }, > { > /* > + * This Seagate drive with EMC firmware causes > + * "Unexpected busfree" and "message reject" > + * messages at boot time when LUNs are probed. > + */ > + { T_DIRECT, SIP_MEDIA_FIXED, "SEAGATE", "SX336704*", "*" }, > + CAM_QUIRK_NOLUNS, /*mintags*/0, /*maxtags*/0 > + }, > + { > + /* > * The Hitachi CJ series with J8A8 firmware apparantly has > * problems with tagged commands. > * PR: 23536 > > Is this the correct thing to do, or is there a bug in the ahc driver? I am > curious why I get "Unexpected busfree" messages with 6.0-BETA4 and not with > 5.3. If the quirk is the right thing to do, it should probably be "SX*"... > > andrew This problem is likely due to the more agressive lun scanning that was added a few months ago. It is currently being reviewed and fixed right now, so stay tuned. I expect it to be fixed when BETA5 is built. Scott From owner-freebsd-scsi@FreeBSD.ORG Fri Sep 16 08:21:23 2005 Return-Path: X-Original-To: freebsd-scsi@hub.freebsd.org Delivered-To: freebsd-scsi@hub.freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5277916A41F; Fri, 16 Sep 2005 08:21:23 +0000 (GMT) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [216.136.204.21]) by mx1.FreeBSD.org (Postfix) with ESMTP id E23BF43D48; Fri, 16 Sep 2005 08:21:22 +0000 (GMT) (envelope-from linimon@FreeBSD.org) Received: from freefall.freebsd.org (linimon@localhost [127.0.0.1]) by freefall.freebsd.org (8.13.3/8.13.3) with ESMTP id j8G8LMje074299; Fri, 16 Sep 2005 08:21:22 GMT (envelope-from linimon@freefall.freebsd.org) Received: (from linimon@localhost) by freefall.freebsd.org (8.13.3/8.13.1/Submit) id j8G8LMIC074295; Fri, 16 Sep 2005 08:21:22 GMT (envelope-from linimon) Date: Fri, 16 Sep 2005 08:21:22 GMT From: Mark Linimon Message-Id: <200509160821.j8G8LMIC074295@freefall.freebsd.org> To: linimon@FreeBSD.org, freebsd-i386@FreeBSD.org, freebsd-scsi@FreeBSD.org Cc: Subject: Re: kern/60641: [sym] Sporadic SCSI bus resets with 53C810 under load X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 16 Sep 2005 08:21:23 -0000 Old Synopsis: Sporadic SCSI bus resets with 53C810 under load New Synopsis: [sym] Sporadic SCSI bus resets with 53C810 under load Responsible-Changed-From-To: freebsd-i386->freebsd-scsi Responsible-Changed-By: linimon Responsible-Changed-When: Fri Sep 16 08:20:44 GMT 2005 Responsible-Changed-Why: Over to maintainer(s). http://www.freebsd.org/cgi/query-pr.cgi?pr=60641 From owner-freebsd-scsi@FreeBSD.ORG Sat Sep 17 00:05:20 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1DC6A16A41F for ; Sat, 17 Sep 2005 00:05:20 +0000 (GMT) (envelope-from ababurko@adelphia.net) Received: from pobox.webstakez.com (pobox.webstakez.com [24.75.44.213]) by mx1.FreeBSD.org (Postfix) with SMTP id F046443D5F for ; Sat, 17 Sep 2005 00:05:15 +0000 (GMT) (envelope-from ababurko@adelphia.net) Received: (qmail 40993 invoked by uid 1014); 17 Sep 2005 00:06:27 -0000 Received: from 24.54.72.242 by pobox.webstakez.com (envelope-from , uid 89) with qmail-scanner-1.24 (clamdscan: 0.83/761. spamassassin: 2.64. perlscan: 1.24. Clear:RC:0(24.54.72.242):SA:0(-2.0/4.0):. Processed in 5.975149 secs); 17 Sep 2005 00:06:27 -0000 X-Spam-Status: No, hits=-2.0 required=4.0 X-Qmail-Scanner-Mail-From: ababurko@adelphia.net via pobox.webstakez.com X-Qmail-Scanner: 1.24 (Clear:RC:0(24.54.72.242):SA:0(-2.0/4.0):. Processed in 5.975149 secs) Received: from 24-54-72-242.kntnny.adelphia.net (HELO ?192.168.69.100?) (bob@phreakout.net@24.54.72.242) by pobox.webstakez.com with SMTP; 17 Sep 2005 00:06:20 -0000 Message-ID: <432B5DA9.3020503@adelphia.net> Date: Fri, 16 Sep 2005 20:04:57 -0400 From: Bob Ababurko User-Agent: Mozilla Thunderbird 1.0.2 (Macintosh/20050317) X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-scsi@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: not booting from Netraid card on install X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 17 Sep 2005 00:05:20 -0000 Hello- I posted a similar message to the freebsd-questions list but wanted to also make sure some of the SCSI people saw this in hopes that someone will catch my error or problem. I am setting up a machine with a 3 channel NetRAID D4943 card and a Biostar M7VIG 400. I have the card set up one one channel with four WD 9.15GB 10k U2 LVD SCSI drives in raid 5 and have been able to install the OS. The drive capacity is correctly shown as is the amr drive/partitions when I booted the machine off the install floppies to install the OS(FreeBSD5.4). Install seems to go fine and have no problem....the leds on the raid 5 array light up when data was being downloaded from Internet. When I try to reboot/boot the box, it hits the floppy drive and then just hangs(just as specified in the BIOS). If I change the BIOS to not include the scsi bus, then it says that there is not system disk. There are no messages or errors on the screen. Does anyone have any advice for this problem? Thanks, Bob From owner-freebsd-scsi@FreeBSD.ORG Sat Sep 17 07:01:55 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A5C7916A41F for ; Sat, 17 Sep 2005 07:01:55 +0000 (GMT) (envelope-from ade@lovett.com) Received: from mail.lovett.com (foo.lovett.com [67.134.38.158]) by mx1.FreeBSD.org (Postfix) with ESMTP id 660EC43D4C for ; Sat, 17 Sep 2005 07:01:55 +0000 (GMT) (envelope-from ade@lovett.com) Received: from hellfire.lab.lovett.com ([192.168.32.20]:51972) by mail.lovett.com with esmtpa (Exim 4.52 (FreeBSD)) id 1EGWhv-000PNv-2W for freebsd-scsi@freebsd.org; Sat, 17 Sep 2005 00:01:55 -0700 Mime-Version: 1.0 (Apple Message framework v734) Content-Transfer-Encoding: 7bit Message-Id: <3A1FD217-5880-4845-9F64-5DD9395D1C6D@FreeBSD.org> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed To: freebsd-scsi@freebsd.org From: Ade Lovett Date: Sat, 17 Sep 2005 00:01:54 -0700 X-Mailer: Apple Mail (2.734) Sender: ade@lovett.com X-SA-Exim-Connect-IP: 192.168.32.20 X-SA-Exim-Mail-From: ade@lovett.com X-SA-Exim-Scanned: No (on mail.lovett.com); SAEximRunCond expanded to false Subject: CAM tags / reset problem X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 17 Sep 2005 07:01:55 -0000 The observed behaviour is this: there is a bus reset during device probing / negotiation during boot, and after the system is up many of the scsi devices are found to be running with dev_openings = 1, which is less than the mintags = 2 setting, even though tag queueing is supposedly enabled. Performance is impaired as a result. The cause appears to be as follows: in cam_xpt.c, the routine xpt_dev_ccbq_resize saves, in dev->tag_saved_openings, the requested queue size _if and only if_ tag queueing is either enabled (SID_CmdQue is set) or is _scheduled_ to be enabled (CAM_DEV_TAG_AFTER_COUNT is set). However, the following sequence can occur: 1) Device transfer settings are negotiated. The device can support tags, so CAM_DEV_TAG_AFTER_COUNT is set (tag queueing is _not_ immediately enabled). 2) Before enough commands have been sent to cause tag queueing to be started, the bus is reset and all transfer settings are reset. This results in xpt_set_transfer_settings being called, and in turn this clears SID_CmdQue and calls xpt_dev_ccbq_resize (to resize the queue down to its non-tagged size, typically 1), and only then clears CAM_DEV_TAG_AFTER_COUNT (which was of course set) and its associated count. This causes xpt_dev_ccbq_resize to save the requested queue size even though it does not relate to the desired size with tag queueing enabled. 3) If tag-queueing is enabled again, e.g. after another negotiation, then the saved value (1) of tag_saved_openings is used rather than the correct value. The fix seems to be to clear CAM_DEV_TAG_AFTER_COUNT _before_ resizing the queue, as per the following patch: http://people.FreeBSD.org/~ade/sys-dev-cam-xpt.c I'd like permission to commit this to HEAD, followed by a relatively quick MFC to RELENG_6 (I know I've missed BETA5, but would like to get it into -RELEASE) -aDe From owner-freebsd-scsi@FreeBSD.ORG Sat Sep 17 07:13:11 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C2B8216A41F; Sat, 17 Sep 2005 07:13:11 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3BC5A43D45; Sat, 17 Sep 2005 07:13:10 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [192.168.254.11] (junior.samsco.home [192.168.254.11]) (authenticated bits=0) by pooker.samsco.org (8.13.4/8.13.4) with ESMTP id j8H7D9wa011255; Sat, 17 Sep 2005 01:13:09 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <432BC20B.2090603@samsco.org> Date: Sat, 17 Sep 2005 01:13:15 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.8) Gecko/20050615 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Ade Lovett References: <3A1FD217-5880-4845-9F64-5DD9395D1C6D@FreeBSD.org> In-Reply-To: <3A1FD217-5880-4845-9F64-5DD9395D1C6D@FreeBSD.org> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, score=-2.8 required=3.8 tests=ALL_TRUSTED autolearn=failed version=3.0.2 X-Spam-Checker-Version: SpamAssassin 3.0.2 (2004-11-16) on pooker.samsco.org Cc: freebsd-scsi@freebsd.org Subject: Re: CAM tags / reset problem X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 17 Sep 2005 07:13:11 -0000 Ade Lovett wrote: > The observed behaviour is this: there is a bus reset during device > probing / negotiation during boot, and after the system is up many of > the scsi devices are found to be running with dev_openings = 1, which > is less than the mintags = 2 setting, even though tag queueing is > supposedly enabled. Performance is impaired as a result. > > The cause appears to be as follows: in cam_xpt.c, the routine > xpt_dev_ccbq_resize saves, in dev->tag_saved_openings, the requested > queue size _if and only if_ tag queueing is either enabled (SID_CmdQue > is set) or is _scheduled_ to be enabled (CAM_DEV_TAG_AFTER_COUNT is > set). However, the following sequence can occur: > > 1) Device transfer settings are negotiated. The device can support > tags, so CAM_DEV_TAG_AFTER_COUNT is set (tag queueing is _not_ > immediately enabled). > > 2) Before enough commands have been sent to cause tag queueing to be > started, the bus is reset and all transfer settings are reset. This > results in xpt_set_transfer_settings being called, and in turn this > clears SID_CmdQue and calls xpt_dev_ccbq_resize (to resize the queue > down to its non-tagged size, typically 1), and only then clears > CAM_DEV_TAG_AFTER_COUNT (which was of course set) and its associated > count. This causes xpt_dev_ccbq_resize to save the requested queue > size even though it does not relate to the desired size with tag > queueing enabled. > > 3) If tag-queueing is enabled again, e.g. after another negotiation, > then the saved value (1) of tag_saved_openings is used rather than > the correct value. > > The fix seems to be to clear CAM_DEV_TAG_AFTER_COUNT _before_ resizing > the queue, as per the following patch: > > http://people.FreeBSD.org/~ade/sys-dev-cam-xpt.c > > I'd like permission to commit this to HEAD, followed by a relatively > quick MFC to RELENG_6 (I know I've missed BETA5, but would like to get > it into -RELEASE) > > -aDe > It's a bit late tonight for me to think coherently about this and give the patch a good review, but I promise that it will happen. Maybe Justin, Ken, Matt, or Nate can also step in and look at it. Are you saying that there are multiple bus resets happening in relatively quick succession on each bus during the inital probe? Are you observing this with only a particular controller family, or with multiple ones? Scott From owner-freebsd-scsi@FreeBSD.ORG Sat Sep 17 07:19:10 2005 Return-Path: X-Original-To: freebsd-scsi@freebsd.org Delivered-To: freebsd-scsi@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id CCB3116A41F for ; Sat, 17 Sep 2005 07:19:10 +0000 (GMT) (envelope-from ade@lovett.com) Received: from mail.lovett.com (foo.lovett.com [67.134.38.158]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8745943D4C for ; Sat, 17 Sep 2005 07:19:10 +0000 (GMT) (envelope-from ade@lovett.com) Received: from hellfire.lab.lovett.com ([192.168.32.20]:52018) by mail.lovett.com with esmtpa (Exim 4.52 (FreeBSD)) id 1EGWyc-000PSv-BV; Sat, 17 Sep 2005 00:19:10 -0700 In-Reply-To: <432BC20B.2090603@samsco.org> References: <3A1FD217-5880-4845-9F64-5DD9395D1C6D@FreeBSD.org> <432BC20B.2090603@samsco.org> Mime-Version: 1.0 (Apple Message framework v734) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <8A5A248D-7529-4EE7-A7B7-4CB81C3ABDDB@freebsd.org> Content-Transfer-Encoding: 7bit From: Ade Lovett Date: Sat, 17 Sep 2005 00:19:09 -0700 To: Scott Long X-Mailer: Apple Mail (2.734) Sender: ade@lovett.com X-SA-Exim-Connect-IP: 192.168.32.20 X-SA-Exim-Mail-From: ade@lovett.com X-SA-Exim-Scanned: No (on mail.lovett.com); SAEximRunCond expanded to false Cc: freebsd-scsi@freebsd.org Subject: Re: CAM tags / reset problem X-BeenThere: freebsd-scsi@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: SCSI subsystem List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 17 Sep 2005 07:19:10 -0000 On Sep 17, 2005, at 00:13 , Scott Long wrote: > It's a bit late tonight for me to think coherently about this and give > the patch a good review, but I promise that it will happen. Maybe > Justin, Ken, Matt, or Nate can also step in and look at it. Are > you saying that there are multiple bus resets happening in > relatively quick > succession on each bus during the inital probe? Are you observing > this > with only a particular controller family, or with multiple ones? This is fallout from the well-documented issues with multiple Seagate drives on an Adaptec 39320 controller: ahd0: port 0x3400-0x34ff, 0x3000-0x30ff me m 0xfc200000-0xfc201fff irq 48 at device 1.0 on pci2 ahd0: [GIANT-LOCKED] aic7902: Ultra320 Wide Channel A, SCSI Id=7, PCI-X 101-133Mhz, 512 SCBs After the recent nswbuf patch, we were still noticing anomalies with performance on the chain. This is certainly a degenerate case (Seagate drives on a U320 chain), but as far as I can tell it applies to any set of controller/disk pairs should multiple bus resets occur on startup. I've got another test box with Hitachi drives (same controller) and am trying to figure out a way to engineer a set of events that would cause such multiple resets but have as yet been unsuccessful. However, with this patch, we now have chains of 7/8 Seagate drives running at U320 with overall bus throughput around 312MBps. Prior to this, on random read/writes, we were observing less than 100MBps. It definitely merits looking at to see if it breaks anything elsewhere (particularly with "well-behaved" SCSI controller/disk combinations), hence the request for review. -aDe