From owner-freebsd-scsi Sun Nov 10 00:03:18 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA22469 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 00:03:18 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA22443; Sun, 10 Nov 1996 00:03:11 -0800 (PST) Message-Id: <199611100803.AAA22443@freefall.freebsd.org> To: Jaye Mathisen cc: hackers@freebsd.org, scsi@freebsd.org Subject: Re: Anybody compiling -current with AHC_DEBUG? In-reply-to: Your message of "Sat, 09 Nov 1996 23:46:27 PST." Date: Sun, 10 Nov 1996 00:03:11 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Nope, but its easy enough to fix. Change DEBUGTARGET to DEBUGTARG, and use this for your ahc_print_scb function: static void ahc_print_scb(scb) struct scb *scb; { struct hardware_scb *hscb = scb->hscb; printf("scb:%p control:0x%x tcl:0x%x cmdlen:%d cmdpointer:0x%lx\n", scb, hscb->control, hscb->tcl, hscb->cmdlen, hscb->cmdpointer ); printf(" datlen:%d data:0x%lx segs:0x%x segp:0x%lx\n", hscb->datalen, hscb->data, hscb->SG_segment_count, hscb->SG_list_pointer); printf(" sg_addr:%lx sg_len:%ld\n", hscb->ahc_dma[0].addr, hscb->ahc_dma[0].len); } >From this mail, this must mean that you continue to have problems with your RAID box and the FreeBSD driver. I have a hunch that this may be related to a problem with how the driver is setting up the termination settings. How is your bus setup??? -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-scsi Sun Nov 10 00:40:57 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA24206 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 00:40:57 -0800 (PST) Received: from mx.serv.net (mx.serv.net [199.201.191.10]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA24107; Sun, 10 Nov 1996 00:38:31 -0800 (PST) Received: from MindBender.serv.net by mx.serv.net (8.7.5/SERV Revision: 2.30) id AAA16753; Sun, 10 Nov 1996 00:38:38 -0800 (PST) Received: from localhost.HeadCandy.com (michaelv@localhost.HeadCandy.com [127.0.0.1]) by MindBender.serv.net (8.7.5/8.7.3) with SMTP id AAA18952; Sun, 10 Nov 1996 00:38:16 -0800 (PST) Message-Id: <199611100838.AAA18952@MindBender.serv.net> X-Authentication-Warning: MindBender.serv.net: Host michaelv@localhost.HeadCandy.com [127.0.0.1] didn't use HELO protocol To: "Justin T. Gibbs" cc: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A.) Sender: owner-freebsd-scsi@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Chernov) , current@freebsd.org, scsi@freebsd.org Subject: Re: SCSI system becomes broken in -current? In-reply-to: Your message of Sat, 09 Nov 96 19:04:22 -0800. <199611100304.TAA07061@freefall.freebsd.org> Date: Sun, 10 Nov 1996 00:38:16 -0800 From: "Michael L. VanLoon -- HeadCandy.com" >>Needless to say that it works OK under Win95. >They probably have a quirk entry for it. Either that, or there is a new >bug in the driver. The changes I made shouldn't have effected tagged >queueing, so the bug should be reproducible with tagged queueing disabled. I *seriously* doubt Win95 does tagged-queuing. In fact, I wouldn't be surprised if it did everything via PIO. If you said it worked OK under WinNT, that might be different (although I would expect them to have a pretty comprehensive quirk database, or some such). ----------------------------------------------------------------------------- Michael L. VanLoon michaelv@MindBender.serv.net --< Free your mind and your machine -- NetBSD free un*x >-- NetBSD working ports: 386+PC, Mac 68k, Amiga, Atari 68k, HP300, Sun3, Sun4/4c/4m, DEC MIPS, DEC Alpha, PC532, VAX, MVME68k, arm32... NetBSD ports in progress: PICA, others... ----------------------------------------------------------------------------- From owner-freebsd-scsi Sun Nov 10 03:13:45 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id DAA00694 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 03:13:45 -0800 (PST) Received: from altos.rnd.runnet.ru (altos.rnd.runnet.ru [195.208.248.40]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id DAA00675 for ; Sun, 10 Nov 1996 03:13:20 -0800 (PST) Received: from altos.rnd.runnet.ru (altos.rnd.runnet.ru [195.208.248.253]) by altos.rnd.runnet.ru (8.7.5/8.7.3) with SMTP id OAA13148; Sun, 10 Nov 1996 14:12:40 +0300 (MSK) Message-ID: <3285B8A7.41C67EA6@run.net> Date: Sun, 10 Nov 1996 11:12:39 +0000 From: Maxim Bolotin Organization: Rostov State University Computer Center X-Mailer: Mozilla 3.01 (X11; I; FreeBSD 2.1.5-RELEASE i386) MIME-Version: 1.0 To: scsi@freebsd.org CC: max@run.net Subject: Re: SCSI system becomes broken in -current? References: <3.0.32.19961109214202.00d8cef8@awod.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >>I have >>ahc0: at 0x1c00-0x1cff irq 11 on eisa0 slot 1 >>ahc0: aic7770 >= Rev E, Single Channel, SCSI Id=7, 4 SCBs >>ahc0: target 0 Tagged Queuing Device >>(ahc0:0:0): "CONNER CFP1060S 1.05GB 2135" type 0 fixed SCSI 2 >>sd0(ahc0:0:0): Direct-Access 1013MB (2074880 512 byte sectors) Unfortunately I have same problem with my AIC7770 (Acer Altos7000) ahc0: at 0x9c00-0x9cff irq 11 on eisa0 slot 9 ahc0: aic7770 <= Rev C, Twin Channel, A SCSI Id=7, B SCSI Id=7, 4 SCBs ahc0 waiting for scsi devices to settle (ahc0:0:0): "MICROP 4110-09NB_Nov18F TN0F" type 0 fixed SCSI 2 sd0(ahc0:0:0): Direct-Access 1002MB (2053880 512 byte sectors) (ahc0:1:0): "MICROP 4110-09NB_Nov18F TN0F" type 0 fixed SCSI 2 sd1(ahc0:1:0): Direct-Access 1002MB (2053880 512 byte sectors) (ahc0:4:0): "MICROP 4110-09NB_Nov18F TN0F" type 0 fixed SCSI 2 and the same problem like reset bus, and so on. -- Rostov State University Computer Center Rostov-on-Don, MAB1-RIPE From owner-freebsd-scsi Sun Nov 10 06:02:47 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id GAA10210 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 06:02:47 -0800 (PST) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id GAA10200; Sun, 10 Nov 1996 06:02:41 -0800 (PST) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id OAA01274; Sun, 10 Nov 1996 14:46:18 +0100 (MET) Received: from localhost (localhost [127.0.0.1]) by klemm.gtn.com (8.8.2/8.8.2) with ESMTP id NAA00866; Sun, 10 Nov 1996 13:14:14 +0100 (MET) Date: Sun, 10 Nov 1996 13:14:14 +0100 (MET) From: Andreas Klemm To: =?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?= cc: FreeBSD-current , scsi@freebsd.org Subject: Re: SCSI system becomes broken in -current? In-Reply-To: <199611100133.EAA00401@nagual.ru> Message-ID: X-try-apsfilter: ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz X-Fax: +49 2137 2018 X-Phone: +49 2137 2020 MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Sun, 10 Nov 1996, [KOI8-R] áÎÄÒÅÊ þÅÒÎÏ× wrote: > It work for me without any error for very long time, but after > todays rebuild I often got: > > sd0(ahc0:0:0): timed out in dataout phase, SCSISIGI == 0x0 > Ordered Tag queued > Ordered Tag sent Which syslog settings do you use, so that you can get the messages out of a logfile ?! BTW, I have sinilar problems when doing backups on tape only if tagged queuing is enabled. -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-scsi Sun Nov 10 09:23:34 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA20302 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 09:23:34 -0800 (PST) Received: from serge.jbj.org (serge.JBJ.ORG [198.178.231.60]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA20293 for ; Sun, 10 Nov 1996 09:23:29 -0800 (PST) Received: (from serge@localhost) by serge.jbj.org (8.6.12/8.6.12) id MAA07471; Sun, 10 Nov 1996 12:23:19 -0500 Date: Sun, 10 Nov 1996 12:23:19 -0500 Message-Id: <199611101723.MAA07471@serge.jbj.org> From: Serge Pashenkov To: ache@nagual.ru CC: gibbs@freefall.freebsd.org, scsi@freebsd.org In-reply-to: <199611100617.JAA00321@nagual.ru> (ache@nagual.ru) Subject: Re: SCSI system becomes broken in -current? Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Andrey A. Chernov wrote: > As I already say, it will be nice to put this firmware upgrade somewhere on > FreeBSD ftp with proper link from the hardware FAQ to eliminate possible > problems... I have this upgrade on my hard disk, so if anybody needs it I'd be glad to spread the wealth :-). serge From owner-freebsd-scsi Sun Nov 10 09:57:50 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id JAA21596 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 09:57:50 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA21583; Sun, 10 Nov 1996 09:57:43 -0800 (PST) Received: by sovcom.kiae.su id AA09890 (5.65.kiae-1 ); Sun, 10 Nov 1996 20:47:23 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Sun, 10 Nov 96 20:47:23 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id UAA00409; Sun, 10 Nov 1996 20:36:19 +0300 (MSK) Message-Id: <199611101736.UAA00409@nagual.ru> Subject: Re: SCSI system becomes broken in -current? In-Reply-To: <96Nov9.230310pst.177557@crevenia.parc.xerox.com> from "Bill Fenner" at "Nov 9, 96 11:03:01 pm" To: fenner@parc.xerox.com (Bill Fenner) Date: Sun, 10 Nov 1996 20:36:18 +0300 (MSK) Cc: gibbs@freefall.freebsd.org, current@freebsd.org, scsi@freebsd.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > In message <199611100215.SAA04532@freefall.freebsd.org> you write: > >I tried www.conner.com, but Seagate has that now... > > Seagate bought Conner earlier this year. They have all the conner-related > stuff mixed in on their web and ftp site. (e.g. look through the drive > model numbers and you will find the CFP1080S, etc.) I already do it, their WWW/FTP have only CFP1060S jumper settings... BTW, I already have an upgrade (thanx to Serge) and it fix tagged queueing bug really. -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Sun Nov 10 10:05:48 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA22138 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 10:05:48 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA22128 for ; Sun, 10 Nov 1996 10:05:41 -0800 (PST) Received: by sovcom.kiae.su id AA09898 (5.65.kiae-1 ); Sun, 10 Nov 1996 20:47:24 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Sun, 10 Nov 96 20:47:24 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id UAA00450; Sun, 10 Nov 1996 20:45:26 +0300 (MSK) Message-Id: <199611101745.UAA00450@nagual.ru> Subject: Re: SCSI system becomes broken in -current? In-Reply-To: <199611101723.MAA07471@serge.jbj.org> from "Serge Pashenkov" at "Nov 10, 96 12:23:19 pm" To: serge@jbj.org (Serge Pashenkov) Date: Sun, 10 Nov 1996 20:45:26 +0300 (MSK) Cc: gibbs@freefall.freebsd.org, scsi@freebsd.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > > As I already say, it will be nice to put this firmware upgrade somewhere on > > FreeBSD ftp with proper link from the hardware FAQ to eliminate possible > > problems... > > I have this upgrade on my hard disk, so if anybody needs it I'd be > glad to spread the wealth :-). I also put it to ftp://ftp.relcom.ru/msdos/hardware/hdd/scsi/barunix.exe -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Sun Nov 10 10:39:29 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA23686 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 10:39:29 -0800 (PST) Received: from Octopussy.MI.Uni-Koeln.DE (Octopussy.MI.Uni-Koeln.DE [134.95.166.20]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id KAA23676 for ; Sun, 10 Nov 1996 10:39:26 -0800 (PST) Received: from x14.mi.uni-koeln.de (annexr2-48.slip.Uni-Koeln.DE) by Octopussy.MI.Uni-Koeln.DE with SMTP id AA06144 (5.67b/IDA-1.5 for ); Sun, 10 Nov 1996 19:39:22 +0100 Received: (from se@localhost) by x14.mi.uni-koeln.de (8.8.2/8.6.9) id TAA03033; Sun, 10 Nov 1996 19:16:13 +0100 (MET) Message-Id: <199611101816.TAA03033@x14.mi.uni-koeln.de> Date: Sun, 10 Nov 1996 19:14:52 +0100 From: se@zpr.uni-koeln.de (Stefan Esser) To: pvp@fareast.rosprint.ru (Vladimir P. Frolov) Cc: scsi@freebsd.org Subject: Re: SCSI problem In-Reply-To: <3285631A.167EB0E7@fareast.rosprint.ru>; from Vladimir P. Frolov on Nov 10, 1996 15:07:38 +1000 References: <3285631A.167EB0E7@fareast.rosprint.ru> X-Mailer: Mutt 0.45 Mime-Version: 1.0 Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Vladimir P. Frolov writes: > Every night (after several hours of inactivity ) > there are some errors on my SCSI subsytem. > > > environment: > FreeBSD 2.1.5 > IWIll P55TU with Adaptec 7880 (2940 UW) > enable disconnection for HDD - no > termination: Low-Off/ High-On > IBM HDD: DFRSS2W (wide SCSI drive) connected to wide connector > autostart - on > D TI SY - on > TERM PWR EN - on > TOSHIBA SCSI-2 CD-ROM connected to 50pin connector > terminated via pluged terminators > > syslog: > ------- > sd0(ahc0:0:0): timed out in command phase, SCSISIGI == 0x4 > sd0(ahc0:0:0): asserted ATN - device reset in message buffer > sd0(ahc0:0:0): timed out in dataout phase, SCSISIGI == 0x0 > ahc0: Issued Channel A Bus Reset #1. 2 SCBs aborted > sd0(ahc0:0:0): UNIT ATTENTION asc:29,0 > sd0(ahc0:0:0): Power on, reset, or bus device reset occurred > , retries:3 > > swap_pager: I/O error - pagein failed; blkno 11152, size 8192, error 5 > vm_fault: pager input (probably hardware) error, PID 92 failure > sd0(ahcsd0(ahc0:0:0): NOT READY asc:4,1 > sd0(ahc0:0:0): Logical unit is in process of becoming ready > , retries:3 Ahh, the IBM DFRS ... Well, but it was cheap, wasn't it ? This is the "SOHO" version of the DFHS, with identical technical specs, except it is not suitable for 24 hour operation. There once was a report in a German computer magazine (c't), according to which the drive will be automatically powered down (and restarted after about one minute) when it has been up for too long. It is sold for systems that get switched off each night, and their owners will never notice. But this is fatal for a server ... Try to get that drive replaced by some other model. The DFHS is about 50% more expensive, but there was a cheap (OEM) version of the Quantum Atlas 2GB being offered all around, which seems to be technically identical to the "normal" Atlas. It was manufactured for some large OEM, which did not accept the drives (for whatever reasons) and now are sold cheaply (with OEM specific firmware). Sorry, but there most probably isn't any software solution. You could try to perform a controlled STOP/START cycle of the drive at a more suitable time (with the SCSI driver knowing that there will be no reply from the drive for more than a minute). Regards, STefan From owner-freebsd-scsi Sun Nov 10 15:42:07 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA00736 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 15:42:07 -0800 (PST) Received: from who.cdrom.com (who.cdrom.com [204.216.27.3]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA00729 for ; Sun, 10 Nov 1996 15:42:05 -0800 (PST) Received: from ican.net (ican.net [198.133.36.9]) by who.cdrom.com (8.7.5/8.6.11) with SMTP id OAA26672 for ; Sun, 10 Nov 1996 14:33:32 -0800 (PST) Received: from gate.ican.net(really [198.133.36.2]) by ican.net via sendmail with esmtp id for ; Sun, 10 Nov 1996 17:33:19 -0500 (EST) (Smail-3.2 1996-Jul-4 #1 built 1996-Jul-10) Received: (from smap@localhost) by gate.ican.net (8.7.5/8.7.3) id RAA05638 for ; Sun, 10 Nov 1996 17:32:36 -0500 (EST) Received: from cabal.io.org(10.1.6.2) by gate.ican.net via smap (V1.3) id sma005636; Sun Nov 10 17:32:24 1996 Received: from localhost (taob@localhost) by cabal.io.org (8.7.6/8.7.3) with SMTP id RAA10274 for ; Sun, 10 Nov 1996 17:32:24 GMT X-Authentication-Warning: cabal.io.org: taob owned process doing -bs Date: Sun, 10 Nov 1996 17:32:24 +0000 () From: Brian Tao To: FREEBSD-SCSI-L Subject: CCD vs. hardware RAIDs (more numbers) Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk After much delay with vanishing U.S. distributors and customs hassles, I now have three rackmount enclosures, each with seven 2GB drives (eventually becoming part of a news server cluster). ccd in 2.2-961014-SNAP was very easy to setup, once I realized a drive in the array somehow had its filesystem set to "SystemV" type and not "4.2BSD". To continue some of the benchmarks I performed with the CMD and Streamlogic RAIDION RAIDs, I striped three of the 2GB drives together. This probably isn't a fair test, but I think it's in the right ballpark. The test server is the same PPro200, but now upgraded to the Oct 14 snapshot. I used Quantum 2GB wide drives, mounted in a DAE-800 rackmount enclosure from Connector Resources Unlimited (http://www.cruinc.com/): FreeBSD 2.2-961014-SNAP #0: Sun Nov 10 02:06:41 EST 1996 root@news-in.ican.net:/mnt/sys/compile/NEWS Calibrating clock(s) relative to mc146818A clock... i586 clock: 199305096 Hz, i8254 clock: 1193158 Hz CPU: Pentium Pro (199.31-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x617 Stepping=7 Features=0xf9ff,MTRR,PGE,MCA,CMOV> real memory = 134217728 (131072K bytes) avail memory = 129789952 (126748K bytes) Probing for devices on PCI bus 0: chip0 rev 2 on pci0:0 chip1 rev 1 on pci0:1:0 chip2 rev 0 on pci0:1:1 de0 rev 18 int a irq 10 on pci0:10 de0: SMC 9332 DC21140 [10-100Mb/s] pass 1.2 de0: address 00:00:c0:6b:eb:e6 de0: enabling 10baseT port ahc0 rev 0 int a irq 11 on pci0:11 ahc0: aic7880 Wide Channel, SCSI Id=15, 16 SCBs ahc0 waiting for scsi devices to settle (ahc0:0:0): "Quantum XP32150W L912" type 0 fixed SCSI 2 sd0(ahc0:0:0): Direct-Access 2151MB (4406960 512 byte sectors) sd0(ahc0:0:0): with 3907 cyls, 10 heads, and an average 112 sectors/track (ahc0:1:0): "Quantum XP32150W 81HB" type 0 fixed SCSI 2 sd1(ahc0:1:0): Direct-Access 2050MB (4199760 512 byte sectors) sd1(ahc0:1:0): with 3907 cyls, 10 heads, and an average 107 sectors/track (ahc0:2:0): "Quantum XP32150W L912" type 0 fixed SCSI 2 sd2(ahc0:2:0): Direct-Access 2151MB (4406960 512 byte sectors) sd2(ahc0:2:0): with 3907 cyls, 10 heads, and an average 112 sectors/track [...] Stripe size used was 64K, to match those on the hardware RAID's. The CMD-5500 was the faster of the two hardware RAIDs, clocking in at 14MB/s writing and 11MB/s reading to a 256MB file on a RAID 0 filesystem. The ccd filesystem hit 11MB/s writing and almost 21MB/s reading a 256MB file. This looked like there was a cache effect (F/W SCSI-2 peaks at 20MB/s, does it not?). I repeated the iozone with 512MB; this time it reported about 11.5MB/s writing and 17.5MB/sec reading. Bonnie was also quite a bit faster on the throughput tests, but a little slower with the random seeks. Increasing the stripe set to five drives improved the stats (results are included at the end of this message). Mounted async, the CCD filesystem is *fast*... it outperforms the CMD-5500 (with 64MB of write-back cache) on the 10000-file touch/touch/unlink test. The 15556-file FreeBSD source tree can be untarred onto it from another drive in 62 seconds flat. :) So for about US$5200 (rack enclosure, seven 2GB fast/wide drives), you get something that can be just as fast or faster than a hardware RAID, at about one-third the $/GB cost (less if you don't go for the fancy enclosure). Of course, you don't get the same amount of reliability or protection against drive failure, and depending on your application that could easily be worth the premium on a "real" RAID. But for raw disk performance, ccd keeps up quite nicely. >>>>> # iozone 256 65536 [...] Writing the 256 Megabyte file, 'iozone.tmp'...24.000000 seconds Reading the file...12.804688 seconds IOZONE performance measurements: 11184810 bytes/second for writing the file 20963842 bytes/second for reading the file # iozone 512 65536 [...] Writing the 512 Megabyte file, 'iozone.tmp'...45.968750 seconds Reading the file...30.593750 seconds IOZONE performance measurements: 11679040 bytes/second for writing the file 17548385 bytes/second for reading the file -------Sequential Output-------- ---Sequential Input-- --Random-- -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks--- Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU single 256 3473 29.0 3555 7.6 1659 5.4 4782 44.6 3716 5.6 105.2 2.0 raidion 256 985 8.2 954 1.9 772 2.2 4754 44.3 5110 5.6 120.8 1.7 cmd 256 7213 59.4 7176 16.1 3521 11.1 7328 68.4 6136 6.7 187.8 2.7 ccd3 256 10965 88.2 11356 28.9 7134 23.2 10302 96.5 12596 20.3 163.7 3.0 ccd5 256 12129 97.1 14036 35.0 8299 27.0 10233 96.3 14351 23.5 181.0 3.4 SINGLE touch: 0.277u 56.454s 3:54.02 24.2% 10+170k 166+20314io 14pf+0w retouch: 0.193u 2.796s 1:49.61 2.7% 17+190k 2+10000io 0pf+0w unlink: 0.199u 4.792s 1:52.40 4.4% 167+226k 1+10000io 6pf+0w RAIDION touch: 0.245u 57.470s 1:16.07 75.8% 10+171k 159+20314io 15pf+0w retouch: 0.174u 2.797s 0:11.59 25.5% 16+176k 2+10000io 0pf+0w unlink: 0.171u 4.838s 0:13.55 36.9% 160+216k 1+10000io 3pf+0w CMD touch: 0.192u 56.159s 1:08.75 81.9% 10+169k 166+20314io 29pf+0w retouch: 0.187u 2.764s 0:09.25 31.7% 16+185k 1+10000io 0pf+0w unlink: 0.216u 4.757s 0:11.07 44.8% 164+220k 2+10000io 0pf+0w CCD-async touch: 0.230u 58.327s 0:59.14 99.0% 10+170k 165+ 314io 6pf+0w retouch: 0.203u 2.576s 0:02.61 106.1% 20+192k 1+ 0io 0pf+0w unlink: 0.182u 4.264s 0:04.68 94.8% 168+222k 1+ 305io 6pf+0w <<<<< -- Brian Tao (BT300, taob@io.org, taob@ican.net) Senior Systems and Network Administrator, Internet Canada Corp. "Though this be madness, yet there is method in't" From owner-freebsd-scsi Sun Nov 10 21:05:36 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id VAA13523 for freebsd-scsi-outgoing; Sun, 10 Nov 1996 21:05:36 -0800 (PST) Received: from fareast.rosprint.ru (fareast.rosprint.ru [193.232.88.195]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id VAA13500 for ; Sun, 10 Nov 1996 21:05:22 -0800 (PST) Received: from fareast.rosprint.ru (localhost.rosprint.ru [127.0.0.1]) by fareast.rosprint.ru (8.7.5/8.7.3) with SMTP id PAA16880 for ; Mon, 11 Nov 1996 15:03:47 +1000 (VSK) Message-ID: <3286B3B3.794BDF32@fareast.rosprint.ru> Date: Mon, 11 Nov 1996 15:03:47 +1000 From: "Vladimir P. Frolov" X-Mailer: Mozilla 3.01 (X11; I; FreeBSD 2.1.5-RELEASE i386) MIME-Version: 1.0 To: scsi@freebsd.org Subject: IBM DFRS drive automatic shutdown Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk How can I switch off automatic shutdown of IBM's DFRS HDD? From owner-freebsd-scsi Mon Nov 11 22:46:09 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id WAA26595 for freebsd-scsi-outgoing; Mon, 11 Nov 1996 22:46:09 -0800 (PST) Received: from lsd.relcom.eu.net (ache@lsd.relcom.eu.net [193.124.23.23]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id WAA26585; Mon, 11 Nov 1996 22:46:04 -0800 (PST) Received: (from ache@localhost) by lsd.relcom.eu.net (8.8.2/8.8.2) id JAA02474; Tue, 12 Nov 1996 09:45:58 +0300 (MSK) Message-Id: <199611120645.JAA02474@lsd.relcom.eu.net> Subject: SCB paging is most dangerous option now! To: current@freebsd.org, scsi@freebsd.org Date: Tue, 12 Nov 1996 09:45:57 +0300 (MSK) From: =?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?= (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Well, situation becomes even worse after latest SCB paging changes: for all previous damages I was able to restore my disk, but now all inodes are completely clean! -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Mon Nov 11 23:04:04 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id XAA27702 for freebsd-scsi-outgoing; Mon, 11 Nov 1996 23:04:04 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id XAA27655; Mon, 11 Nov 1996 23:03:56 -0800 (PST) Message-Id: <199611120703.XAA27655@freefall.freebsd.org> To: =?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?= (Andrey A. Chernov) cc: current@freebsd.org, scsi@freebsd.org Subject: Re: SCB paging is most dangerous option now! In-reply-to: Your message of "Tue, 12 Nov 1996 09:45:57 +0300." <199611120645.JAA02474@lsd.relcom.eu.net> Date: Mon, 11 Nov 1996 23:03:56 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk What were the error messages? >Well, situation becomes even worse after latest SCB paging changes: >for all previous damages I was able to restore my disk, but >now all inodes are completely clean! >-- >Andrey A. Chernov > >http://www.nagual.ru/~ache/ -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-scsi Tue Nov 12 08:22:37 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA02840 for freebsd-scsi-outgoing; Tue, 12 Nov 1996 08:22:37 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id IAA02585; Tue, 12 Nov 1996 08:19:56 -0800 (PST) Received: by sovcom.kiae.su id AA18466 (5.65.kiae-1 ); Tue, 12 Nov 1996 19:06:49 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Tue, 12 Nov 96 19:06:49 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id SAA00746; Tue, 12 Nov 1996 18:41:17 +0300 (MSK) Message-Id: <199611121541.SAA00746@nagual.ru> Subject: Re: SCB paging is most dangerous option now! In-Reply-To: <199611120703.XAA27655@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 11, 96 11:03:56 pm" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Tue, 12 Nov 1996 18:41:16 +0300 (MSK) Cc: current@freebsd.org, scsi@freebsd.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > What were the error messages? > They not stored anywhere now because it seems ANY disk write cause immediately destruction of inode table including syslog writes. As I remember there was something like: data overrun of XXXX bytes detected followed by various retraining/resetting failure attempts. As I remember no one successfull write's happens. my configuration: ahc0: at 0x1c00-0x1cff irq 11 on eisa0 slot 1 ahc0: aic7770 >= Rev E, Single Channel, SCSI Id=7, 4 SCBs when SCB paging is enabled, this line looks like ahc0: aic7770 >= Rev E, Single Channel, SCSI Id=7, 4/255 SCBs ahc0: target 0 Tagged Queuing Device (ahc0:0:0): "CONNER CFP1060S 1.05GB 213C" type 0 fixed SCSI 2 ^^^^ upgraded sd0(ahc0:0:0): Direct-Access 1013MB (2074880 512 byte sectors) ahc0: target 1 Tagged Queuing Device (ahc0:1:0): "IBM DORS-32160 S84A" type 0 fixed SCSI 2 sd1(ahc0:1:0): Direct-Access 2063MB (4226725 512 byte sectors) As I already say, SCB paging works with any _one_ device alone. -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Tue Nov 12 15:06:06 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA02835 for freebsd-scsi-outgoing; Tue, 12 Nov 1996 15:06:06 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA02805; Tue, 12 Nov 1996 15:05:51 -0800 (PST) Message-Id: <199611122305.PAA02805@freefall.freebsd.org> To: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) cc: current@freebsd.org, scsi@freebsd.org Subject: Re: SCB paging is most dangerous option now! In-reply-to: Your message of "Tue, 12 Nov 1996 18:41:16 +0300." <199611121541.SAA00746@nagual.ru> Date: Tue, 12 Nov 1996 15:05:48 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >> What were the error messages? >> > >They not stored anywhere now because it seems ANY disk write cause >immediately destruction of inode table including syslog writes. >As I remember there was something like: > >data overrun of XXXX bytes detected > >followed by various retraining/resetting failure attempts. >As I remember no one successfull write's happens. This sounds like a cache coherency bug with your motherboard. What kind is it? The reason I belive this to be the case is that: 1) SCB paging causes the same piece of memory to be DMA'ed in and out in rapid succession - much more often then in the non paging case. The amount of DMA will see a dramatic increase when you switch from 1 to two active targets. 2) After I saw your bug report last night, I again attempted to reproduce the error. I made my 2940 look as much like a 2842 as I could by making the driver believe that it only has 4 SCBs. After about 30 minutes of poinding my two disks with as many as 30 outstanding transactions at a time, I gave up. I will try again tonight with my aic7850 card (3 SCBs) as soon as I can rip the machine apart and rearange my disks. Now I don't have access to a Rev E board anywhere, and the driver does take advantage of undocumented features of that revision of the aic7770. I can send you a little snippet of code that can verify that the 1 important feature, being able to store full 8 bit values in the QIN and QOUTFIFO does work on your card without you having to turn on SCB paging. I don't believe this to be the case since 1 drive would not work at all either. If someone has either a 2742A(T) or 2842A that they'd like to send me, I may be able to debug this further. If it is DMA related, it should be easy to see that by playing with your cache settings and trying to reproduce the problem. If you are going to do this, attempt to repro it *only in single user mode*, with your filesystems mounted read only, by starting multiple processes acessing the disks. I have yet to lose any disk data with this kind of testing, and this will usually fail easily if the problem you are reporting still exists. If the system starts to go south, note what the error messages are and hit the reset button. Multiple dds (at least 8 to each drive) from the raw partitions of your disks to /dev/null will work nicely. -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-scsi Wed Nov 13 07:43:10 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id HAA24574 for freebsd-scsi-outgoing; Wed, 13 Nov 1996 07:43:10 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id HAA24563; Wed, 13 Nov 1996 07:42:38 -0800 (PST) Received: by sovcom.kiae.su id AA15233 (5.65.kiae-1 ); Wed, 13 Nov 1996 18:35:54 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Wed, 13 Nov 96 18:35:54 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id SAA00239; Wed, 13 Nov 1996 18:34:26 +0300 (MSK) Message-Id: <199611131534.SAA00239@nagual.ru> Subject: Re: SCB paging is most dangerous option now! In-Reply-To: <199611122305.PAA02805@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 12, 96 03:05:48 pm" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Wed, 13 Nov 1996 18:34:25 +0300 (MSK) Cc: current@freebsd.org, scsi@freebsd.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > This sounds like a cache coherency bug with your motherboard. What kind > is it? OPTI895 VL/ISA-PB486P3 > 2) After I saw your bug report last night, I again attempted to reproduce > the error. I made my 2940 look as much like a 2842 as I could by making > the driver believe that it only has 4 SCBs. After about 30 minutes of > poinding my two disks with as many as 30 outstanding transactions at a > time, I gave up. I will try again tonight with my aic7850 card (3 SCBs) > as soon as I can rip the machine apart and rearange my disks. I don't even wait a minutes, I got inodes wipe on very _first_ write immediately. > If it is DMA related, it should be easy to see that by playing with your > cache settings and trying to reproduce the problem. If you are going to do > this, attempt to repro it *only in single user mode*, with your filesystems > mounted read only, by starting multiple processes acessing the disks. I > have yet to lose any disk data with this kind of testing, and this will > usually fail easily if the problem you are reporting still exists. If the > system starts to go south, note what the error messages are and hit the > reset button. Multiple dds (at least 8 to each drive) from the raw > partitions of your disks to /dev/null will work nicely. I read only mode I got the almost same result with SCB paging as without it. This bug affects _writing_only_, not reading. And I can't start 8 dds for each drive in both modes, 3 dds per drive is enough to cause "Queue Full" in both modes, but it is harmless due to read only. If I increase dds count, I got "timed out in dataout phase" for SCB mode or "timed out in message out phase" for non-SCB mode. -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Wed Nov 13 08:06:22 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id IAA25528 for freebsd-scsi-outgoing; Wed, 13 Nov 1996 08:06:22 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id IAA25507; Wed, 13 Nov 1996 08:06:12 -0800 (PST) Message-Id: <199611131606.IAA25507@freefall.freebsd.org> To: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) cc: current@freebsd.org, scsi@freebsd.org Subject: Re: SCB paging is most dangerous option now! In-reply-to: Your message of "Wed, 13 Nov 1996 18:34:25 +0300." <199611131534.SAA00239@nagual.ru> Date: Wed, 13 Nov 1996 08:06:10 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >I read only mode I got the almost same result with SCB paging as without it. >This bug affects _writing_only_, not reading. >And I can't start 8 dds for each drive in both modes, >3 dds per drive is enough to cause "Queue Full" in both modes, but >it is harmless due to read only. This is probably what is causing your corruption in the SCB Paging case. Which drive can only do 3 transactions at a time? I'm sure that your IBM can do more. It may very well be that one of your drives doesn't like the fact that the code with SCB paging turned on will basically continually pound on that drive, causing queue full conditions, until there aren't enough transactions queued to make this happen any more. The patch I posted for Andreas' problem may help in this regard. As for your problem happening on the "first write", are you sure this isn't the "first sync" after boot?? >If I increase dds count, I got "timed out in dataout phase" for SCB mode or >"timed out in message out phase" for non-SCB mode. That dataout phase one could actually be "while idle". I just found a bug in the diagnostic code that reports that. Hmmm. >-- >Andrey A. Chernov > >http://www.nagual.ru/~ache/ -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-scsi Wed Nov 13 14:19:40 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA21063 for freebsd-scsi-outgoing; Wed, 13 Nov 1996 14:19:40 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id OAA21057; Wed, 13 Nov 1996 14:19:28 -0800 (PST) Received: by sovcom.kiae.su id AA27514 (5.65.kiae-1 ); Thu, 14 Nov 1996 01:14:47 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Thu, 14 Nov 96 01:14:46 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id BAA00212; Thu, 14 Nov 1996 01:13:25 +0300 (MSK) Message-Id: <199611132213.BAA00212@nagual.ru> Subject: Re: SCB paging is most dangerous option now! In-Reply-To: <199611131606.IAA25507@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 13, 96 08:06:10 am" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Thu, 14 Nov 1996 01:13:25 +0300 (MSK) Cc: current@FreeBSD.org, scsi@FreeBSD.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > >I read only mode I got the almost same result with SCB paging as without it. > >This bug affects _writing_only_, not reading. > >And I can't start 8 dds for each drive in both modes, > >3 dds per drive is enough to cause "Queue Full" in both modes, but > >it is harmless due to read only. > > This is probably what is causing your corruption in the SCB Paging case. > Which drive can only do 3 transactions at a time? I'm sure that your IBM > can do more. It may very well be that one of your drives doesn't like the > fact that the code with SCB paging turned on will basically continually > pound on that drive, causing queue full conditions, until there aren't > enough transactions queued to make this happen any more. The patch I > posted for Andreas' problem may help in this regard. No, _any_ of two drives says "Queue full" after 2-3 dds and goes to "timed out" state after more dds which ends up with "panic: Timed-out command times out again" It happens equally in both SCB paging and not SCB paging modes. BTW, I see it only for dds, I can start f.e. about 20 "ls -lR" safely. Does it means that Tagged Queueing not work well with 2842? > As for your problem happening on the "first write", are you sure this isn't > the "first sync" after boot?? I mean first physical write, of course. It happens just after fsck puts info lines about each drive at boot phase. -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Wed Nov 13 14:42:11 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id OAA22563 for freebsd-scsi-outgoing; Wed, 13 Nov 1996 14:42:11 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA22553; Wed, 13 Nov 1996 14:42:05 -0800 (PST) Message-Id: <199611132242.OAA22553@freefall.freebsd.org> To: Keith Mitchell cc: scsi@freebsd.org Subject: Re: SCB paging is most dangerous option now! In-reply-to: Your message of "Wed, 13 Nov 1996 17:32:31 EST." <199611132232.RAA00558@unix.guru.org> Date: Wed, 13 Nov 1996 14:42:03 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >I upgraded to the 11/12 current today (from 10/17) and am experiencing major >SCSI lockup problems with the new driver. The computer will lockup with >the SCSI light solid usually during the bootup (while its starting all of >the daemons). Can you see if this patch to current affects that behavior at all? -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== Index: aic7xxx.seq =================================================================== RCS file: /home/ncvs/src/sys/dev/aic7xxx/aic7xxx.seq,v retrieving revision 1.48 diff -c -r1.48 aic7xxx.seq *** aic7xxx.seq 1996/11/11 05:16:36 1.48 --- aic7xxx.seq 1996/11/13 22:38:44 *************** *** 540,546 **** mvi CLRSINT1,CLRATNO /* drop ATN */ p_mesgout_outb: dec DINDEX ! or CLRSINT1, CLRREQINIT mov SCSIDATL,SINDIR p_mesgout4: --- 540,546 ---- mvi CLRSINT1,CLRATNO /* drop ATN */ p_mesgout_outb: dec DINDEX ! mvi CLRSINT1, CLRREQINIT mov SCSIDATL,SINDIR p_mesgout4: *************** *** 839,851 **** /* * Bus free phase. It might be useful to interrupt the device ! * driver if we aren't expecting this. For now, make sure that ! * ATN isn't being asserted and look for a new command. */ p_busfree: ! mvi CLRSINT1,CLRATNO ! clr LASTPHASE ! /* * if this is an immediate command, perform a psuedo command complete to * notify the driver. --- 839,848 ---- /* * Bus free phase. It might be useful to interrupt the device ! * driver if we aren't expecting this. */ p_busfree: ! mvi LASTPHASE, P_BUSFREE /* * if this is an immediate command, perform a psuedo command complete to * notify the driver. *************** *** 901,907 **** */ inb_next: ! or CLRSINT1, CLRREQINIT mov NONE,SCSIDATL /*dummy read from latch to ACK*/ inb_next_wait: test SSTAT1,REQINIT jz inb_next_wait /* wait for next byte */ --- 898,904 ---- */ inb_next: ! mvi CLRSINT1, CLRREQINIT mov NONE,SCSIDATL /*dummy read from latch to ACK*/ inb_next_wait: test SSTAT1,REQINIT jz inb_next_wait /* wait for next byte */ *************** *** 910,916 **** mov DINDEX,SINDEX mov DINDIR,SCSIBUSL ret /*read byte directly from bus*/ inb_last: ! or CLRSINT1, CLRREQINIT mov NONE,SCSIDATL ret /*dummy read from latch to ACK*/ mesgin_phasemis: --- 907,913 ---- mov DINDEX,SINDEX mov DINDIR,SCSIBUSL ret /*read byte directly from bus*/ inb_last: ! mvi CLRSINT1, CLRREQINIT mov NONE,SCSIDATL ret /*dummy read from latch to ACK*/ mesgin_phasemis: Index: aic7xxx_reg.h =================================================================== RCS file: /home/ncvs/src/sys/dev/aic7xxx/aic7xxx_reg.h,v retrieving revision 1.16 diff -c -r1.16 aic7xxx_reg.h *** aic7xxx_reg.h 1996/11/11 05:16:41 1.16 --- aic7xxx_reg.h 1996/11/13 22:40:12 *************** *** 681,686 **** --- 681,688 ---- #define MSG5 0x03a #define LASTPHASE 0x03b + #define P_BUSFREE 0x01 + #define ARG_1 0x03c #define RETURN_1 0x03c #define SEND_MSG 0x80 From owner-freebsd-scsi Wed Nov 13 15:03:16 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA23440 for freebsd-scsi-outgoing; Wed, 13 Nov 1996 15:03:16 -0800 (PST) Received: from sequent.kiae.su (sequent.kiae.su [193.125.152.6]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id PAA23435; Wed, 13 Nov 1996 15:03:07 -0800 (PST) Received: by sequent.kiae.su id AA29634 (5.65.kiae-2 ); Thu, 14 Nov 1996 01:48:04 +0300 Received: by sequent.KIAE.su (UUMAIL/2.0); Thu, 14 Nov 96 01:48:03 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id BAA00285; Thu, 14 Nov 1996 01:47:18 +0300 (MSK) Message-Id: <199611132247.BAA00285@nagual.ru> Subject: Re: SCB paging is ... (Interesting result) In-Reply-To: <199611132213.BAA00212@nagual.ru> from "áÎÄÒÅÊ þÅÒÎÏ×" at "Nov 14, 96 01:13:25 am" X-Elm-Osv: (Our standard violations) hdr-charset=US-ASCII To: ache@nagual.ru (=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=) Date: Thu, 14 Nov 1996 01:47:18 +0300 (MSK) Cc: gibbs@freefall.freebsd.org, current@FreeBSD.org, scsi@FreeBSD.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk > Does it means that Tagged Queueing not work well with 2842? I just try turn Tagged Queueing OFF and SCB paging ON and it works even for writes! Some test results: 1) TAG=OFF SCB=OFF I can easily start up to 8 dds on each drive without any errors. 2) TAG=OFF SCB=ON I can start up to 6 dds on each drive, more dds cause "timed out in message out phase" error -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Wed Nov 13 15:07:08 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA23651 for freebsd-scsi-outgoing; Wed, 13 Nov 1996 15:07:08 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA23618; Wed, 13 Nov 1996 15:06:56 -0800 (PST) Message-Id: <199611132306.PAA23618@freefall.freebsd.org> To: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) cc: current@FreeBSD.org, scsi@FreeBSD.org Subject: Re: SCB paging is ... (Interesting result) In-reply-to: Your message of "Thu, 14 Nov 1996 01:47:18 +0300." <199611132247.BAA00285@nagual.ru> Date: Wed, 13 Nov 1996 15:06:55 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk >> Does it means that Tagged Queueing not work well with 2842? > >I just try turn Tagged Queueing OFF and SCB paging ON and it works >even for writes! You will only be using a maximum of 4 SCBs if you don't use tagged queueing (assuming only 2 devices active) since you can only have two SCBs active per non-tagged target. In otherwords, you will not be getting the heavy DMA load from moving SCBs in and out of the card's hadware SCB ram in this scenario. >Some test results: >1) TAG=OFF SCB=OFF >I can easily start up to 8 dds on each drive without any errors. >2) TAG=OFF SCB=ON >I can start up to 6 dds on each drive, more dds cause >"timed out in message out phase" error Hmm. Does the patch I just posted have any effect on your timeouts? >-- >Andrey A. Chernov > >http://www.nagual.ru/~ache/ -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-scsi Wed Nov 13 15:49:31 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id PAA26287 for freebsd-scsi-outgoing; Wed, 13 Nov 1996 15:49:31 -0800 (PST) Received: from unix.guru.org (unix.guru.org [198.82.200.65]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id PAA26265 for ; Wed, 13 Nov 1996 15:49:21 -0800 (PST) Received: (from kmitch@localhost) by unix.guru.org (8.8.2/8.7.3) id SAA00360; Wed, 13 Nov 1996 18:48:10 -0500 (EST) From: Keith Mitchell Message-Id: <199611132348.SAA00360@unix.guru.org> Subject: Re: SCB paging is most dangerous option now! In-Reply-To: <199611132242.OAA22553@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 13, 96 02:42:03 pm" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Wed, 13 Nov 1996 18:48:10 -0500 (EST) Cc: scsi@freebsd.org X-Mailer: ELM [version 2.4ME+ PL25 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > Can you see if this patch to current affects that behavior at all? No change. From owner-freebsd-scsi Thu Nov 14 00:01:42 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id AAA22002 for freebsd-scsi-outgoing; Thu, 14 Nov 1996 00:01:42 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA21994; Thu, 14 Nov 1996 00:01:39 -0800 (PST) Message-Id: <199611140801.AAA21994@freefall.freebsd.org> To: Keith Mitchell cc: ache, scsi Subject: Re: SCB paging is most dangerous option now! In-reply-to: Your message of "Wed, 13 Nov 1996 18:48:10 EST." <199611132348.SAA00360@unix.guru.org> Date: Thu, 14 Nov 1996 00:01:39 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk >> Can you see if this patch to current affects that behavior at all? > >No change. > How about this one. You will have to back out the other diff I sent. -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== Index: dev/aic7xxx/aic7xxx.seq =================================================================== RCS file: /usr/cvs/src/sys/dev/aic7xxx/aic7xxx.seq,v retrieving revision 1.48 diff -c -r1.48 aic7xxx.seq *** aic7xxx.seq 1996/11/11 05:16:36 1.48 --- aic7xxx.seq 1996/11/14 07:25:49 *************** *** 540,546 **** mvi CLRSINT1,CLRATNO /* drop ATN */ p_mesgout_outb: dec DINDEX ! or CLRSINT1, CLRREQINIT mov SCSIDATL,SINDIR p_mesgout4: --- 540,546 ---- mvi CLRSINT1,CLRATNO /* drop ATN */ p_mesgout_outb: dec DINDEX ! mvi CLRSINT1, CLRREQINIT mov SCSIDATL,SINDIR p_mesgout4: *************** *** 839,850 **** /* * Bus free phase. It might be useful to interrupt the device ! * driver if we aren't expecting this. For now, make sure that ! * ATN isn't being asserted and look for a new command. */ p_busfree: ! mvi CLRSINT1,CLRATNO ! clr LASTPHASE /* * if this is an immediate command, perform a psuedo command complete to --- 839,848 ---- /* * Bus free phase. It might be useful to interrupt the device ! * driver if we aren't expecting this. */ p_busfree: ! mvi LASTPHASE, P_BUSFREE /* * if this is an immediate command, perform a psuedo command complete to *************** *** 901,916 **** */ inb_next: ! or CLRSINT1, CLRREQINIT mov NONE,SCSIDATL /*dummy read from latch to ACK*/ inb_next_wait: - test SSTAT1,REQINIT jz inb_next_wait /* wait for next byte */ - inb_first: test SSTAT1,PHASEMIS jnz mesgin_phasemis mov DINDEX,SINDEX mov DINDIR,SCSIBUSL ret /*read byte directly from bus*/ inb_last: - or CLRSINT1, CLRREQINIT mov NONE,SCSIDATL ret /*dummy read from latch to ACK*/ mesgin_phasemis: --- 899,913 ---- */ inb_next: ! mvi CLRSINT0, CLRSPIORDY mov NONE,SCSIDATL /*dummy read from latch to ACK*/ inb_next_wait: test SSTAT1,PHASEMIS jnz mesgin_phasemis + test SSTAT0, SPIORDY jz inb_next_wait + inb_first: mov DINDEX,SINDEX mov DINDIR,SCSIBUSL ret /*read byte directly from bus*/ inb_last: mov NONE,SCSIDATL ret /*dummy read from latch to ACK*/ mesgin_phasemis: Index: dev/aic7xxx/aic7xxx_reg.h =================================================================== RCS file: /usr/cvs/src/sys/dev/aic7xxx/aic7xxx_reg.h,v retrieving revision 1.16 diff -c -r1.16 aic7xxx_reg.h *** aic7xxx_reg.h 1996/11/11 05:16:41 1.16 --- aic7xxx_reg.h 1996/11/13 07:03:04 *************** *** 439,444 **** --- 439,446 ---- * beyond the bounds of its * command. */ + #define SCB_TRACE_POINT 0xf1 + #define BRKADRINT 0x08 #define SCSIINT 0x04 #define CMDCMPLT 0x02 *************** *** 530,535 **** --- 532,538 ---- #define MK_MESSAGE 0x80 #define DISCENB 0x40 #define TAG_ENB 0x20 + #define TRACE_SCB 0x10 #define ABORT_SCB 0x08 #define DISCONNECTED 0x04 #define SCB_TAG_TYPE 0x03 *************** *** 681,686 **** --- 684,691 ---- #define MSG5 0x03a #define LASTPHASE 0x03b + #define P_BUSFREE 0x01 + #define ARG_1 0x03c #define RETURN_1 0x03c #define SEND_MSG 0x80 Index: i386/scsi/aic7xxx.c =================================================================== RCS file: /usr/cvs/src/sys/i386/scsi/aic7xxx.c,v retrieving revision 1.85 diff -c -r1.85 aic7xxx.c *** aic7xxx.c 1996/11/11 05:24:44 1.85 --- aic7xxx.c 1996/11/13 05:38:59 *************** *** 1206,1227 **** if (xs->error == XS_NOERROR) xs->error = XS_DRIVER_STUFFUP; break; case SCSI_BUSY: xs->error = XS_BUSY; sc_print_addr(xs->sc_link); printf("Target Busy\n"); break; - case SCSI_QUEUE_FULL: - /* - * The upper level SCSI code will someday - * handle this properly. - */ - printf("Queue Full\n"); - /* - * XXX requeue this unconditionally. - */ - STAILQ_INSERT_HEAD(&ahc->waiting_scbs, scb, links); - break; default: sc_print_addr(xs->sc_link); printf("unexpected targ_status: %x\n", hscb->status); --- 1206,1243 ---- if (xs->error == XS_NOERROR) xs->error = XS_DRIVER_STUFFUP; break; + case SCSI_QUEUE_FULL: + if (scb->hscb->control & TAG_ENB) { + /* + * The upper level SCSI code in 3.0 + * handles this properly... + */ + struct scsi_link *sc_link; + + sc_link = xs->sc_link; + if (sc_link->active > 2 + && sc_link->opennings != 0) { + /* truncate the opennings */ + sc_link->opennings = 0; + sc_print_addr(sc_link); + printf("Tagged openings reduced to " + "%d\n", sc_link->active); + } + /* + * XXX requeue this unconditionally. + */ + STAILQ_INSERT_TAIL(&ahc->waiting_scbs, scb, + links); + break; + } + /* Else treat as if it is a BUSY condition */ + scb->hscb->status = SCSI_BUSY; + /* Fall Through... */ case SCSI_BUSY: xs->error = XS_BUSY; sc_print_addr(xs->sc_link); printf("Target Busy\n"); break; default: sc_print_addr(xs->sc_link); printf("unexpected targ_status: %x\n", hscb->status); *************** *** 1371,1376 **** --- 1387,1430 ---- case MSGIN_PHASEMIS: break; #endif + case SCB_TRACE_POINT: + { + /* + * Print out the bus phase + */ + char *phase; + u_int8_t scbindex = ahc_inb(ahc, SCB_TAG); + u_int8_t lastphase = ahc_inb(ahc, LASTPHASE); + + scb = ahc->scb_data->scbarray[scbindex]; + sc_print_addr(scb->xs->sc_link); + + switch (lastphase) { + case P_DATAOUT: + phase = "Data-Out"; + break; + case P_DATAIN: + phase = "Data-In"; + break; + case P_COMMAND: + phase = "Command"; + break; + case P_MESGOUT: + phase = "Message-Out"; + break; + case P_STATUS: + phase = "Status"; + break; + case P_MESGIN: + phase = "Message-In"; + break; + default: + phase = "busfree"; + break; + } + printf("- %s\n", phase); + break; + } default: printf("ahc_intr: seqint, " "intstat == 0x%x, scsisigi = 0x%x\n", *************** *** 2090,2095 **** --- 2144,2154 ---- if (ahc->tagenable & mask) hscb->control |= TAG_ENB; } + + /* Set the trace flag if this is the target we want to trace */ + if (ahc->unit == 2 && xs->sc_link->target == 3) + hscb->control |= TRACE_SCB; + hscb->tcl = ((xs->sc_link->target << 4) & 0xF0) | (IS_SCSIBUS_B(ahc,xs->sc_link)? SELBUSB : 0) | (xs->sc_link->lun & 0x07); *************** *** 2490,2496 **** */ bus_state = ahc_inb(ahc, LASTPHASE); ! switch(bus_state & PHASE_MASK) { case P_DATAOUT: printf("in dataout phase"); --- 2549,2555 ---- */ bus_state = ahc_inb(ahc, LASTPHASE); ! switch(bus_state) { case P_DATAOUT: printf("in dataout phase"); From owner-freebsd-scsi Thu Nov 14 01:20:15 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id BAA25706 for freebsd-scsi-outgoing; Thu, 14 Nov 1996 01:20:15 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id BAA25641; Thu, 14 Nov 1996 01:20:04 -0800 (PST) Received: by sovcom.kiae.su id AA22127 (5.65.kiae-1 ); Thu, 14 Nov 1996 11:57:55 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Thu, 14 Nov 96 11:57:54 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id LAA00223; Thu, 14 Nov 1996 11:55:18 +0300 (MSK) Message-Id: <199611140855.LAA00223@nagual.ru> Subject: Re: SCB paging is most dangerous option now! In-Reply-To: <199611140801.AAA21994@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 14, 96 00:01:39 am" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Thu, 14 Nov 1996 11:55:17 +0300 (MSK) Cc: kmitch@unix.guru.org, scsi@freefall.freebsd.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > >> Can you see if this patch to current affects that behavior at all? > > > >No change. > > > > How about this one. You will have to back out the other diff I sent. Nothing changes expect diagnostics, with SCB=ON, TAG=ON, readonly, I got after 2-3 dds on any disk (as I remember, they moves up quickly): Tagged opening reduced to 3 no command for scb 2 (cmdcmplt) ... QOUTCNT=1 timed out while idle ... resets ... panic: timed-out command times out again -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Thu Nov 14 03:39:00 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id DAA02344 for freebsd-scsi-outgoing; Thu, 14 Nov 1996 03:39:00 -0800 (PST) Received: from news1.gtn.com (news1.gtn.com [192.109.159.3]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id DAA02339; Thu, 14 Nov 1996 03:38:57 -0800 (PST) Received: (from uucp@localhost) by news1.gtn.com (8.7.2/8.7.2) with UUCP id MAA12880; Thu, 14 Nov 1996 12:16:26 +0100 (MET) Received: from localhost (localhost [127.0.0.1]) by klemm.gtn.com (8.8.2/8.8.2) with SMTP id MAA00704; Thu, 14 Nov 1996 12:05:13 +0100 (MET) Date: Thu, 14 Nov 1996 12:05:13 +0100 (MET) From: Andreas Klemm To: "Justin T. Gibbs" cc: =?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?= , current@freebsd.org, scsi@freebsd.org Subject: Re: SCB paging is ... (Interesting result) In-Reply-To: <199611132306.PAA23618@freefall.freebsd.org> Message-ID: X-try-apsfilter: ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz X-Fax: +49 2137 2018 X-Phone: +49 2137 2020 MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk On Wed, 13 Nov 1996, Justin T. Gibbs wrote: > Hmm. Does the patch I just posted have any effect on your timeouts? BTW, sorry, I didn't test your patch, yet. What do you think / expect: That with your patch tagged queuing will work ? Or should I enable both: tagged queuing _and_ SCB paging ? -- andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik GmbH Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.de pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by <<< ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD <<< From owner-freebsd-scsi Thu Nov 14 05:11:21 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id FAA07965 for freebsd-scsi-outgoing; Thu, 14 Nov 1996 05:11:21 -0800 (PST) Received: from unix.guru.org (kmitch@unix.guru.org [198.82.200.65]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id FAA07959 for ; Thu, 14 Nov 1996 05:11:19 -0800 (PST) Received: (from kmitch@localhost) by unix.guru.org (8.8.2/8.7.3) id IAA00361; Thu, 14 Nov 1996 08:11:11 -0500 (EST) Date: Thu, 14 Nov 1996 08:11:11 -0500 (EST) From: Keith Mitchell Message-Id: <199611141311.IAA00361@unix.guru.org> To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Cc: scsi@freebsd.org Subject: Re: SCB paging is most dangerous option now! Newsgroups: local.freebsd.scsi References: <199611132348.SAA00360@unix.guru.org> Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In article you wrote: > How about this one. You will have to back out the other diff I sent. Still no change - Still locks up hard. It appears that it is the first SCSI channel that is locking up though. (don't know if that makes a difference or not). From owner-freebsd-scsi Thu Nov 14 10:13:05 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA22737 for freebsd-scsi-outgoing; Thu, 14 Nov 1996 10:13:05 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA22649; Thu, 14 Nov 1996 10:12:26 -0800 (PST) Message-Id: <199611141812.KAA22649@freefall.freebsd.org> To: Andreas Klemm cc: =?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?= , current@freebsd.org, scsi@freebsd.org Subject: Re: SCB paging is ... (Interesting result) In-reply-to: Your message of "Thu, 14 Nov 1996 12:05:13 +0100." Date: Thu, 14 Nov 1996 10:12:22 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >On Wed, 13 Nov 1996, Justin T. Gibbs wrote: > >> Hmm. Does the patch I just posted have any effect on your timeouts? > >BTW, sorry, I didn't test your patch, yet. What do you think / expect: > >That with your patch tagged queuing will work ? Or should I enable >both: tagged queuing _and_ SCB paging ? Just try tagged queueing for the moment. After many different attempts with strange I/O loads, I was able to get SCB paging to die on me although I basically got timeouts and not inode death, so I'm not sure if it is the same problem as Andrey's. >-- >andreas@klemm.gtn.com /\/\___ Wiechers & Partner Datentechnik Gmb >H > Andreas Klemm ___/\/\/ Support Unix -- andreas.klemm@wup.d >e >pgp p-key http://www-swiss.ai.mit.edu/~bal/pks-toplev.html >>> powered by << >< >ftp://sunsite.unc.edu/pub/Linux/system/Printing/aps-491.tgz >>> FreeBSD << >< > -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-scsi Thu Nov 14 10:16:28 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id KAA23084 for freebsd-scsi-outgoing; Thu, 14 Nov 1996 10:16:28 -0800 (PST) Received: from freefall.freebsd.org (localhost.cdrom.com [127.0.0.1]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id KAA23077; Thu, 14 Nov 1996 10:16:19 -0800 (PST) Message-Id: <199611141816.KAA23077@freefall.freebsd.org> To: Keith Mitchell cc: scsi@freebsd.org Subject: Re: SCB paging is most dangerous option now! In-reply-to: Your message of "Thu, 14 Nov 1996 08:11:11 EST." <199611141311.IAA00361@unix.guru.org> Date: Thu, 14 Nov 1996 10:16:17 -0800 From: "Justin T. Gibbs" Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk >In article you > wrote: > >> How about this one. You will have to back out the other diff I sent. > >Still no change - Still locks up hard. It appears that it is the first SCSI >channel that is locking up though. (don't know if that makes a difference or >not). What was the last working kernel for you? Have you tried the AHC_FORCE_PIO? -- Justin T. Gibbs =========================================== FreeBSD: Turning PCs into workstations =========================================== From owner-freebsd-scsi Thu Nov 14 18:19:42 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id SAA03370 for freebsd-scsi-outgoing; Thu, 14 Nov 1996 18:19:42 -0800 (PST) Received: from mailgate.execpc.com (root@mailgate.execpc.com [169.207.16.5]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id SAA03365 for ; Thu, 14 Nov 1996 18:19:40 -0800 (PST) Received: from earth.execpc.com (joegreco@earth [169.207.16.1]) by mailgate.execpc.com (8.7.6/8.7.5) with ESMTP id UAA24239; Thu, 14 Nov 1996 20:19:50 -0600 Received: (from joegreco@localhost) by earth.execpc.com (8.7.6/8.7) id UAA09545; Thu, 14 Nov 1996 20:19:27 -0600 (CST) From: Joe Greco Message-Id: <199611150219.UAA09545@earth.execpc.com> Subject: Question about AHA-3940U "UltraSCSI" To: freebsd-scsi@freebsd.org Date: Thu, 14 Nov 1996 20:19:27 -0600 (CST) Cc: jgreco@brasil.moneng.mei.com Reply-To: jgreco@brasil.moneng.mei.com 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-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi all, OS: FreeBSD 2.2-CURRENT (few days before -ALPHA) Machine: ASUS P55TP4XE, P133 CPU, 32MB RAM, NCR 810 I recently acquired an Adaptec 3940U. This is the "Ultra-SCSI" capable variant of the 3940, which I have been using successfully for quite some time. The drives I have connected to it, two ranks of six Seagate ST-31055N's each, are Ultra-SCSI capable. FreeBSD sees the 3940U and identifies it as an Ultra SCSI controller. However, if I enable Ultra-SCSI mode in the Adaptec setup menu, FreeBSD still sees the controller, but experiences errors when writing to the drive. I have not tried reading. The Adaptec utilities have no problems verifying, etc., the disks, so I do not think it is a cabling issue. My guess is that perhaps nobody has actually had one of these to play with, or something like that. I am in absolutely no need of Ultra-SCSI support... I bought the U drives for the extra cache, and I bought the controller because it seemed silly not to buy a controller capable of keeping up with the drives. However, the intended application is "Usenet news", so it is really not going to be noticeable to me if I do not run these as Ultra-SCSI. However, I would gladly provide any further information, testing, access to the box, etc., if anyone is interested in resolving this issue. This machine is _NOT_ in service at this time, so I am more than able to abuse/crash/etc it at this time!! (But I only have a few weeks before I want to put this box on line.) Thanks, ... Joe From owner-freebsd-scsi Fri Nov 15 01:18:43 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id BAA29067 for freebsd-scsi-outgoing; Fri, 15 Nov 1996 01:18:43 -0800 (PST) Received: from hda.hydro.com (vkhdib01.hda.hydro.com [136.164.216.55]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id BAA29046 for ; Fri, 15 Nov 1996 01:18:32 -0800 (PST) Received: from hktthpc (hktthpc.hfi.hydro.com) by hda.hydro.com with SMTP id ; Fri, 15 Nov 1996 10:17:56 +0100 Message-Id: <328C3392.3688@hydro.com> Date: Fri, 15 Nov 1996 10:10:42 +0100 From: Terje Thogersen Organization: Norsk Hydro ASA X-Mailer: Mozilla 2.0 (WinNT; I) Mime-Version: 1.0 To: freebsd-scsi@freebsd.org Cc: terje.thogersen@hda.hydro.com Subject: od0(ahc1:4:0)Target Busy, or : My OD-disk times out continuosly Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Hi all! I have FreeBSD 2.1.5 release running on an Cyrix6x86-P150, QDI MB, with an Adaptec 3940 (no U or W) host-adapter. I also have a Fujitsu 2511A 128 MB od disk. I enabled the od driver, and if I tried to read 240.000 bytes from the disk, I'd get about 100 "od0(ahc1:4:0)Target Busy". I poked about a bit, and found the "OD_BOGUS_TIMEOUT" kernel parameter, which looked promising. However, the problem still persists. (yes, after config, make/install kernel + boot) After looking through the code, I found the "Target Busy" in the driver for the Adaptec. I've also found the #ifdef OD_BOGUS_TIMEOUT in the od driver. Problem is : what is the connection between the two? An almost blind guess is that the ahc drives sees the bogus timeout problem and reports it before the od-driver can mask it? Another guess is that this is in fact a real timeout, since the od disk of course slower than a disk. The problem is then : How can I up the timeout for the od-drive? So : Is the OD_BOGUS_TIMEOUT stuff the problem, and how can we fix this, or is this a real timeout, and how can I up the timeout for the od? Regards, -Terje ___________________________________________________________________________ Terje Thøgersen, IS Advisor | E-mail : terje.thogersen@hydro.com Norsk Hydro a.s, Hydro Finance | Tel : +47-2243 2100 From owner-freebsd-scsi Fri Nov 15 03:57:33 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id DAA08470 for freebsd-scsi-outgoing; Fri, 15 Nov 1996 03:57:33 -0800 (PST) Received: from unix.guru.org (kmitch@unix.guru.org [198.82.200.65]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id DAA08450 for ; Fri, 15 Nov 1996 03:57:12 -0800 (PST) Received: (from kmitch@localhost) by unix.guru.org (8.8.2/8.7.3) id GAA00433; Fri, 15 Nov 1996 06:57:02 -0500 (EST) From: Keith Mitchell Message-Id: <199611151157.GAA00433@unix.guru.org> Subject: Re: SCB paging is most dangerous option now! In-Reply-To: <199611142050.MAA04525@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 14, 96 12:50:39 pm" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Fri, 15 Nov 1996 06:57:02 -0500 (EST) Cc: scsi@freebsd.org X-Mailer: ELM [version 2.4ME+ PL25 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > It seems to work fine on my P54TP4 with a 2940, so it may be related > to the PCI-PCI bridge on the 3940. I know that Stefan made some > changes in this area, so perhaps he knows. Basically I rely on > the return value of pci_map_mem. If it succeeds, I use Mem I/O. > If not, I use PIO. Well, All is not totally well. Last night during the backup, I got: sd0(ahc0:0:0): timed out in dataout phase, SCSISIGI == 0x4 SEQADDR == 0x13d Ordered Tag queued sd0(ahc0:0:0): timed out in dataout phase, SCSISIGI == 0x4 SEQADDR == 0x13c sd0(ahc0:0:0): timed out in dataout phase, SCSISIGI == 0x4 SEQADDR == 0x13c ahc0: Issued Channel A Bus Reset. 3 SCBs aborted Ordered Tag sent st0(ahc0:4:0): UNIT ATTENTION asc:29,0 st0(ahc0:4:0): Power on, reset, or bus device reset occured Ordered Tag sent st0(ahc0:4:0): timed out in datain phase, SCSISIGI == 0xc6 After this happened the computer rebooted but the sd0 drive seemed to be "offline". I had to power cycle to bring it back up. This is without either patch. Should I try one of those to see if it fixes it?? Thanks. From owner-freebsd-scsi Sat Nov 16 07:22:42 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id HAA02314 for freebsd-scsi-outgoing; Sat, 16 Nov 1996 07:22:42 -0800 (PST) Received: from irz301.inf.tu-dresden.de (irz301.inf.tu-dresden.de [141.76.1.11]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id HAA02303 for ; Sat, 16 Nov 1996 07:22:36 -0800 (PST) Received: from sax.sax.de (sax.sax.de [193.175.26.33]) by irz301.inf.tu-dresden.de (8.6.12/8.6.12-s1) with ESMTP id QAA18759; Sat, 16 Nov 1996 16:21:52 +0100 Received: (from uucp@localhost) by sax.sax.de (8.6.12/8.6.12-s1) with UUCP id QAA06405; Sat, 16 Nov 1996 16:21:42 +0100 Received: (from j@localhost) by uriah.heep.sax.de (8.8.2/8.6.9) id QAA27375; Sat, 16 Nov 1996 16:16:08 +0100 (MET) From: J Wunsch Message-Id: <199611161516.QAA27375@uriah.heep.sax.de> Subject: Re: IBM DFRS drive automatic shutdown To: freebsd-scsi@FreeBSD.org (FreeBSD SCSI list) Date: Sat, 16 Nov 1996 16:16:07 +0100 (MET) Cc: pvp@fareast.rosprint.ru (Vladimir P. Frolov) Reply-To: joerg_wunsch@uriah.heep.sax.de (Joerg Wunsch) In-Reply-To: <3286B3B3.794BDF32@fareast.rosprint.ru> from "Vladimir P. Frolov" at "Nov 11, 96 03:03:47 pm" X-Phone: +49-351-2012 669 X-PGP-Fingerprint: DC 47 E6 E4 FF A6 E9 8F 93 21 E0 7D F9 12 D6 4E X-Mailer: ELM [version 2.4ME+ PL17 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk As Vladimir P. Frolov wrote: > How can I switch off automatic shutdown of IBM's DFRS HDD? Sorry, you can't. As far as i know, IBM explicitly marks these items as ``Not for server use.'' -- cheers, J"org joerg_wunsch@uriah.heep.sax.de -- http://www.sax.de/~joerg/ -- NIC: JW11-RIPE Never trust an operating system you don't have sources for. ;-) From owner-freebsd-scsi Sat Nov 16 12:37:22 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA17314 for freebsd-scsi-outgoing; Sat, 16 Nov 1996 12:37:22 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA17304 for ; Sat, 16 Nov 1996 12:37:19 -0800 (PST) Received: by sovcom.kiae.su id AA13285 (5.65.kiae-1 ); Sat, 16 Nov 1996 23:19:11 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Sat, 16 Nov 96 23:19:11 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id XAA00223; Sat, 16 Nov 1996 23:17:42 +0300 (MSK) Message-Id: <199611162017.XAA00223@nagual.ru> Subject: Re: cvs commit: src/sys/i386/conf GENERIC LINT options.i386 src/sys/dev/aic7xxx aic7xxx.seq aic7xxx_reg.h src/sys/i386/scsi aic7xxx In-Reply-To: <199611160119.RAA01758@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 15, 96 05:19:52 pm" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Sat, 16 Nov 1996 23:17:42 +0300 (MSK) Cc: CVS-committers@freefall.freebsd.org, cvs-all@freefall.freebsd.org, cvs-sys@freefall.freebsd.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk > gibbs 96/11/15 17:19:52 > > Modified: sys/dev/aic7xxx aic7xxx.seq aic7xxx_reg.h > Fix the SCB paging problem that I was seeing. This was only on my 7850 > controller and stems from the fact that its QINFIFO can only handle 3bit > SCB identifiers. This means that you can only have 8 transactions open at > a time with the current paging scheme to these controllers. The code added > to enforce this is generic in that it tests for the number of relevent bits > that the QINFIFO can store and adjusts the max accordingly. It may be possible > to come up with a scheme that allows for more than 8 commands at a time, but > I don't know that it is worth the effort simply to fix a low end card. The > aic7880 still can do 255. It NOT crash my system with TAG=on SCB=on now! Thanks! -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Sat Nov 16 12:51:51 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA17776 for freebsd-scsi-outgoing; Sat, 16 Nov 1996 12:51:51 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA17771 for ; Sat, 16 Nov 1996 12:51:48 -0800 (PST) Received: by sovcom.kiae.su id AA18406 (5.65.kiae-1 ); Sat, 16 Nov 1996 23:41:23 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Sat, 16 Nov 96 23:41:22 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id XAA00397; Sat, 16 Nov 1996 23:39:10 +0300 (MSK) Message-Id: <199611162039.XAA00397@nagual.ru> Subject: Re: cvs commit: src/sys/i386/conf GENERIC LINT options.i386 src/sys/dev/aic7xxx aic7xxx.seq aic7xxx_reg.h src/sys/i386/scsi aic7xxx In-Reply-To: <199611160119.RAA01758@freefall.freebsd.org> from "Justin T. Gibbs" at "Nov 15, 96 05:19:52 pm" To: gibbs@freefall.freebsd.org (Justin T. Gibbs) Date: Sat, 16 Nov 1996 23:39:10 +0300 (MSK) Cc: CVS-committers@freefall.freebsd.org, cvs-all@freefall.freebsd.org, cvs-sys@freefall.freebsd.org, scsi@freebsd.org From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > gibbs 96/11/15 17:19:52 > > Modified: sys/dev/aic7xxx aic7xxx.seq aic7xxx_reg.h > Fix the SCB paging problem that I was seeing. This was only on my 7850 > controller and stems from the fact that its QINFIFO can only handle 3bit > SCB identifiers. This means that you can only have 8 transactions open at > a time with the current paging scheme to these controllers. The code added > to enforce this is generic in that it tests for the number of relevent bits > that the QINFIFO can store and adjusts the max accordingly. It may be possible > to come up with a scheme that allows for more than 8 commands at a time, but > I don't know that it is worth the effort simply to fix a low end card. The > aic7880 still can do 255. > > This problem may be related to what Andrey was seeing since I don't have n > aic7770 rev E chip here to test on, but as soon as someone probes one of these > cards with this new code, the dmesg output will tell the whole story. I forget to mention that now it correctly says: ahc0: aic7770 >= Rev E, Single Channel, SCSI Id=7, 4/4 SCBs instead of ahc0: aic7770 >= Rev E, Single Channel, SCSI Id=7, 4/255 SCBs in old variant. -- Andrey A. Chernov http://www.nagual.ru/~ache/ From owner-freebsd-scsi Sat Nov 16 12:54:28 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id MAA17959 for freebsd-scsi-outgoing; Sat, 16 Nov 1996 12:54:28 -0800 (PST) Received: from irz301.inf.tu-dresden.de (irz301.inf.tu-dresden.de [141.76.1.11]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id MAA17951 for ; Sat, 16 Nov 1996 12:54:25 -0800 (PST) Received: from sax.sax.de (sax.sax.de [193.175.26.33]) by irz301.inf.tu-dresden.de (8.6.12/8.6.12-s1) with ESMTP id VAA25963; Sat, 16 Nov 1996 21:51:54 +0100 Received: (from uucp@localhost) by sax.sax.de (8.6.12/8.6.12-s1) with UUCP id VAA14206; Sat, 16 Nov 1996 21:51:52 +0100 Received: (from j@localhost) by uriah.heep.sax.de (8.8.2/8.6.9) id VAA27970; Sat, 16 Nov 1996 21:35:50 +0100 (MET) From: J Wunsch Message-Id: <199611162035.VAA27970@uriah.heep.sax.de> Subject: Re: od0(ahc1:4:0)Target Busy, or : My OD-disk times out continuosly To: freebsd-scsi@FreeBSD.org (FreeBSD SCSI list) Date: Sat, 16 Nov 1996 21:35:50 +0100 (MET) Cc: terje.thogersen@hda.hydro.com Reply-To: joerg_wunsch@uriah.heep.sax.de (Joerg Wunsch) In-Reply-To: <328C3392.3688@hydro.com> from Terje Thogersen at "Nov 15, 96 10:10:42 am" X-Phone: +49-351-2012 669 X-PGP-Fingerprint: DC 47 E6 E4 FF A6 E9 8F 93 21 E0 7D F9 12 D6 4E X-Mailer: ELM [version 2.4ME+ PL17 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.org X-Loop: FreeBSD.org Precedence: bulk As Terje Thogersen wrote: > I enabled the od driver, and if I tried to read 240.000 bytes from the disk, > I'd get about 100 "od0(ahc1:4:0)Target Busy". I'm afraid you will have to dig further. I've never seen this... Hint: enable SCSIDEBUG (a kernel option), and turn on debugging using scsi(8). This should get you some more output, so you could tell us which operation is actually causing the error. -- cheers, J"org joerg_wunsch@uriah.heep.sax.de -- http://www.sax.de/~joerg/ -- NIC: JW11-RIPE Never trust an operating system you don't have sources for. ;-) From owner-freebsd-scsi Sat Nov 16 13:37:43 1996 Return-Path: owner-freebsd-scsi Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id NAA21770 for freebsd-scsi-outgoing; Sat, 16 Nov 1996 13:37:43 -0800 (PST) Received: from sovcom.kiae.su (sovcom.kiae.su [193.125.152.1]) by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id NAA21761; Sat, 16 Nov 1996 13:37:34 -0800 (PST) Received: by sovcom.kiae.su id AA28616 (5.65.kiae-1 ); Sun, 17 Nov 1996 00:20:40 +0300 Received: by sovcom.KIAE.su (UUMAIL/2.0); Sun, 17 Nov 96 00:20:39 +0300 Received: (from ache@localhost) by nagual.ru (8.8.2/8.8.2) id AAA00705; Sun, 17 Nov 1996 00:19:05 +0300 (MSK) Message-Id: <199611162119.AAA00705@nagual.ru> Subject: New SCSI changes & Tagged queueing To: gibbs@freebsd.org, scsi@freebsd.org Date: Sun, 17 Nov 1996 00:19:04 +0300 (MSK) From: "=?KOI8-R?Q?=E1=CE=C4=D2=C5=CA_=FE=C5=D2=CE=CF=D7?=" (Andrey A. Chernov) Organization: self X-Class: Fast X-Mailer: ELM [version 2.4ME+ PL28 (25)] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@freebsd.org X-Loop: FreeBSD.org Precedence: bulk After 3 dds I still got sd1(ahc0:1:0): Tagged openings reduced to 3 but no death after it. -- Andrey A. Chernov http://www.nagual.ru/~ache/