From owner-freebsd-scsi Sun Aug 22 6:35:42 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from news-ma.rhein-neckar.de (news-ma.rhein-neckar.de [193.197.90.3]) by hub.freebsd.org (Postfix) with ESMTP id 9A56414CD4 for ; Sun, 22 Aug 1999 06:35:27 -0700 (PDT) (envelope-from naddy@mips.rhein-neckar.de) Received: from mips.rhein-neckar.de (uucp@localhost) by news-ma.rhein-neckar.de (8.8.8/8.8.8) with bsmtp id PAA18743; Sun, 22 Aug 1999 15:35:19 +0200 (CEST) (envelope-from naddy@mips.rhein-neckar.de) Received: by mips.rhein-neckar.de id m11IX4l-000WyTC (Debian Smail-3.2.0.101 1997-Dec-17 #2); Sun, 22 Aug 1999 14:50:19 +0200 (CEST) Message-ID: <19990822145018.L16148@mips.rhein-neckar.de> Date: Sun, 22 Aug 1999 14:50:18 +0200 From: Christian Weisgerber To: mjacob@feral.com Cc: freebsd-scsi@FreeBSD.ORG Subject: Re: Bizarre effect reading old tape References: <19990822000408.J16148@mips.rhein-neckar.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.93.2 In-Reply-To: ; from Matthew Jacob on Sat, Aug 21, 1999 at 03:37:06PM -0700 Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Matthew Jacob: > > (sa0:ncr0:0:6:0): MODE SELECT(06). CDB: 15 0 0 0 c 0 > > (sa0:ncr0:0:6:0): ILLEGAL REQUEST csi:10,8,0,0 > > (sa0:ncr0:0:6:0): MODE SELECT(06). CDB: 15 0 0 0 c 0 > > (sa0:ncr0:0:6:0): ILLEGAL REQUEST csi:10,8,0,0 > > I take it this means that an attempt to put it in variable failed? Yes. That's the other problem I mentioned. Setting the blocksize (with mt) fails with SCSI errors. -- Christian "naddy" Weisgerber naddy@mips.rhein-neckar.de See another pointless homepage at . To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Sun Aug 22 9:35:29 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from news-ma.rhein-neckar.de (news-ma.rhein-neckar.de [193.197.90.3]) by hub.freebsd.org (Postfix) with ESMTP id 76A3814BCF for ; Sun, 22 Aug 1999 09:35:26 -0700 (PDT) (envelope-from bigeye.rhein-neckar.de!naddy@mips.rhein-neckar.de) Received: from mips.rhein-neckar.de (uucp@localhost) by news-ma.rhein-neckar.de (8.8.8/8.8.8) with bsmtp id SAA00748 for freebsd-scsi@freebsd.org; Sun, 22 Aug 1999 18:34:15 +0200 (CEST) (envelope-from bigeye.rhein-neckar.de!naddy@mips.rhein-neckar.de) Received: by mips.rhein-neckar.de id m11IaBl-000WyUC (Debian Smail-3.2.0.101 1997-Dec-17 #2); Sun, 22 Aug 1999 18:09:45 +0200 (CEST) From: naddy@mips.rhein-neckar.de (Christian Weisgerber) Subject: Re: tape: can't set blocksize on Wangtek Date: 22 Aug 1999 18:12:16 +0200 Message-ID: <7pp7h0$18d$1@bigeye.rhein-neckar.de> References: <7pk3r1$89o$1@bigeye.rhein-neckar.de> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8bit To: freebsd-scsi@freebsd.org Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Christian Weisgerber wrote: > 4.0-CURRENT from a few days ago, QIC-1000 tape drive: > sa0: Removable Sequential Access SCSI-CCS device Okay, I think I'm seeing a pattern here. It seems I can successfully change the block size if there is no tape inserted. (Or after an "mt offline", which presumably amounts to the same thing even if the tape is still physically in the drive.) Changing the block size after a tape has been inserted but not yet read from works sometimes. No recognizable pattern yet. Changing the block size after the tape has been read from fails reliably. -- Christian "naddy" Weisgerber naddy@mips.rhein-neckar.de To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Sun Aug 22 9:36: 1 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from news-ma.rhein-neckar.de (news-ma.rhein-neckar.de [193.197.90.3]) by hub.freebsd.org (Postfix) with ESMTP id C2903155E3 for ; Sun, 22 Aug 1999 09:35:45 -0700 (PDT) (envelope-from bigeye.rhein-neckar.de!naddy@mips.rhein-neckar.de) Received: from mips.rhein-neckar.de (uucp@localhost) by news-ma.rhein-neckar.de (8.8.8/8.8.8) with bsmtp id SAA00772 for freebsd-scsi@freebsd.org; Sun, 22 Aug 1999 18:35:29 +0200 (CEST) (envelope-from bigeye.rhein-neckar.de!naddy@mips.rhein-neckar.de) Received: by mips.rhein-neckar.de id m11IaLY-000WyUC (Debian Smail-3.2.0.101 1997-Dec-17 #2); Sun, 22 Aug 1999 18:19:52 +0200 (CEST) From: naddy@mips.rhein-neckar.de (Christian Weisgerber) Subject: Re: Bizarre effect reading old tape Date: 22 Aug 1999 18:22:23 +0200 Message-ID: <7pp83v$1id$1@bigeye.rhein-neckar.de> References: <19990821154220.H16148@mips.rhein-neckar.de> To: freebsd-scsi@freebsd.org Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Matthew Jacob wrote: > Put it in variable mode and see what happens- I suspect that the 'fake' > variable that some QIC drives have might be at fault. Okay, now that I've managed to change block sizes without booting new kernels, here are the results: fixed/512 the tape is read correctly fixed/1024 the tape is read with interspersed null blocks variable the tape isn't read at all Specifically, in variable mode I get a SCSI error again. tar and dd abort with "/dev/nrsa0: Invalid argument", so I assume sa(4) has propagated EINVAL back to the read(2) call. I have a kernel with CAMDEBUG running now. If somebody tells me just what debugging output to enable and report, I'll happily post the results. -- Christian "naddy" Weisgerber naddy@mips.rhein-neckar.de To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Mon Aug 23 7:16:52 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from ivory.lm.com (ivory.telerama.com [205.201.1.20]) by hub.freebsd.org (Postfix) with ESMTP id 49B7914C33 for ; Mon, 23 Aug 1999 07:16:37 -0700 (PDT) (envelope-from ncrawler@telerama.com) Received: from gauntlet.telerama.com (ncrawler@gauntlet.telerama.com [205.201.1.214]) by ivory.lm.com (8.8.5/8.6.12) with SMTP id KAA29008; Mon, 23 Aug 1999 10:15:47 -0400 (EDT) Date: Mon, 23 Aug 1999 10:15:46 -0400 (EDT) From: Chris Tracy To: freebsd-SCSI@freebsd.org Cc: Chris Tracy Subject: weird SCSI problems... Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hiyah.. I'm not subscribed to the freebsd-SCSI mailing list, so if anyone has any info about this, it'd be great if you could CC me in... Anyways... Here's the problem: I'm using an Intel Pentium II 350mhz based machine, with a Buslogic SCSI card in it. The machine used to be running the 2.2.x branch, and I've recently wiped off the drives and have installed the 3.2-19990803-STABLE release. For the most part, the machine runs great. However, this is the machine that runs Amanda for us, and one day, while I was running Amanda, I got the following error message, right before the machine crashed... Here's a transript of what exactly happened: ----------------------- % amcheck lm Amanda Tape Server Host Check ----------------------------- /usr/home/holding-disk: 2178706 KB disk space available, using 2076306 KB. NOTE: skipping tape-writable test. Tape Telerama01 label ok. Server check took 9.904 seconds. Amanda Backup Client Hosts Check -------------------------------- WARNING: kappa.webnz.net: selfcheck request timed out. Host down? Client check: 9 hosts checked in 29.163 seconds, 1 problem found. (brought to you by Amanda 2.4.1p1) % amflush -f lm Scanning /usr/home/holding-disk... 19990818: found non-empty Amanda directory. Flushing dumps in 19990818, today: 19990818 to tape drive /dev/nrsa0. Expecting tape Telerama01 or a new tape. (The last dumps were to tape Telerama1 0) Are you sure you want to do this? y driver: send-cmd time 0.011 to taper: START-TAPER 19990818 taper: pid 1390 executable taper version 2.4.1p1 taper: read label `Telerama01' date `19990718' Aug 18 22:13:04 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc5502f00 - timed out Aug 18 22:13:04 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc5502f00 - timed out Aug 18 22:13:21 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc5502f00 - timed out Aug 18 22:13:21 qbert /kernel: bt0: No longer in timeout Aug 18 22:13:21 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc5502f00 - timed out Aug 18 22:13:21 qbert /kernel: bt0: No longer in timeout Aug 18 22:13:21 qbert /kernel: (sa0:bt0:0:2:0): WRITE(06). CDB: a 0 0 80 0 0 % Aug 18 22:13:21 qbert /kernel: (sa0:bt0:0:2:0): WRITE(06). CDB: a 0 0 80 0 0 Aug 18 22:13:21 qbert /kernel: (sa0:bt0:0:2:0): UNIT ATTENTION asc:29,0 Aug 18 22:13:21 qbert /kernel: (sa0:bt0:0:2:0): UNIT ATTENTION asc:29,0 Aug 18 22:13:21 qbert /kernel: (sa0:bt0:0:2:0): Power on, reset, or bus device r eset occurred Aug 18 22:13:21 qbert /kernel: (sa0:bt0:0:2:0): Power on, reset, or bus device r eset occurred % % cd /usr/home/hold ^C Cannot create dfWAA01394: Device not configured queueup: cannot create data temp file dfWAA01394, uid=0: Device not configured zsh: segmentation fault su operator qbert# qbert# Aug 18 22:14:21 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc55024c0 - timed ou t Aug 18 22:14:21 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc55024c0 - timed out Aug 18 22:15:01 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc55024c0 - timed out Aug 18 22:15:01 qbert /kernel: (da0:bt0:0:0:0): CCB 0xc55024c0 - timed out Aug 18 22:15:01 qbert /kernel: bt0: No longer in timeout Aug 18 22:15:01 qbert /kernel: bt0: No longer in timeout Aug 18 22:15:01 qbert /kernel: (da0:bt0:0:0:0): Invalidating pack Aug 18 22:15:01 qbert /kernel: (da0:bt0:0:0:0): Invalidating pack Aug 18 22:15:01 qbert last message repeated 15 times Aug 18 22:15:01 qbert /kernel: spec_getpages: I/O read failure: (error code=6) Aug 18 22:15:01 qbert last message repeated 15 times Aug 18 22:15:01 qbert /kernel: spec_getpages: I/O read failure: (error code=6) Aug 18 22:15:01 qbert /kernel: size: 4096, resid: 4096, a_count: 4096, valid: 0x 0 Aug 18 22:15:01 qbert /kernel: size: 4096, resid: 4096, a_count: 4096, valid: 0x Aug 18 22:15:01 qbert /kernel: nread: 0, reqpage: 0, pindex: 57, pcount: 1 Aug 18 22:15:01 qbert /kernel: nread: 0, reqpage: 0, pindex: 57, pcount: 1 Aug 18 22:15:01 qbert /kernel: vm_fault: pager read error, pid 1383 (csh) Aug 18 22:15:01 qbert /kernel: vm_fault: pager read error, pid 1383 (csh) Aug 18 22:15:01 qbert /kernel: (da0:bt0:0:0:0): Invalidating pack Aug 18 22:15:01 qbert /kernel: (da0:bt0:0:0:0): Invalidating pack Aug 18 22:15:01 qbert sendmail[1401]: NOQUEUE: SYSERR(root): queuename: Cannot c reate "qfWAA01401" in "/var/spool/mqueue" (euid=0): Device not configured Aug 18 22:15:01 qbert sendmail[1401]: NOQUEUE: SYSERR(root): queuename: Cannot c reate "qfWAA01401" in "/var/spool/mqueue" (euid=0): Device not configured Aug 18 22:15:01 qbert sendmail[1394]: WAA01394: SYSERR(operator): Cannot create dfWAA01394: Device not configured Aug 18 22:15:01 qbert sendmail[1394]: WAA01394: SYSERR(operator): Cannot create dfWAA01394: Device not configured Aug 18 22:15:01 qbert sendmail[1394]: WAA01394: SYSERR(operator): queueup: canno t create data temp file dfWAA01394, uid=0: Device not configured Aug 18 22:15:01 qbert sendmail[1394]: WAA01394: SYSERR(operator): queueup: canno t create data temp file dfWAA01394, uid=0: Device not configured Aug 18 22:15:01 qbert sendmail[1394]: WAA01394: SYSERR(operator): queueup: canno t create data temp file dfWAA01394, uid=0: Device not configured Aug 18 22:15:11 qbert sshd[1395]: log: ROOT LOGIN as 'root' from gauntlet.telera ma.com Aug 18 22:15:11 qbert /kernel: vm_fault: pager read error, pid 1403 (zsh) Aug 18 22:15:11 qbert /kernel: vm_fault: pager read error, pid 1403 (zsh) Aug 18 22:15:11 qbert sshd[1395]: fatal: Local: Command terminated on signal 11. Aug 18 22:15:11 qbert sshd[1395]: fatal: Local: Command terminated on signal 11. Aug 18 22:15:19 qbert sshd[1404]: log: ROOT LOGIN as 'root' from gauntlet.telera ma.com Aug 18 22:15:19 qbert /kernel: vm_fault: pager read error, pid 1406 (zsh) Aug 18 22:15:19 qbert /kernel: vm_fault: pager read error, pid 1406 (zsh) Aug 18 22:15:19 qbert sshd[1404]: fatal: Local: Command terminated on signal 11. Aug 18 22:15:19 qbert sshd[1404]: fatal: Local: Command terminated on signal 11. qbert# qbert# qbert# qbert# shutdown -r now zsh: Input/output error: shutdown Aug 18 22:16:36 qbert /kernel: spec_getpages: I/O read failure: (error code=6) qbert# Aug 18 22:16:36 qbert /kernel: spec_getpages: I/O read failure: (error co de=6) Aug 18 22:16:36 qbert /kernel: size: 65536, resid: 65536, a_count: 65536, valid: 0x0 Aug 18 22:16:36 qbert /kernel: size: 65536, resid: 65536, a_count: 65536, valid: 0x0 Aug 18 22:16:36 qbert /kernel: nread: 0, reqpage: 0, pindex: 0, pcount: 16 Aug 18 22:16:36 qbert /kernel: nread: 0, reqpage: 0, pindex: 0, pcount: 16 Aug 18 22:16:36 qbert /kernel: spec_getpages: I/O read failure: (error code=6) Aug 18 22:16:36 qbert /kernel: spec_getpages: I/O read failure: (error code=6) Aug 18 22:16:36 qbert /kernel: size: 65536, resid: 65536, a_count: 65536, valid: 0x0 Aug 18 22:16:36 qbert /kernel: size: 65536, resid: 65536, a_count: 65536, valid: 0x0 Aug 18 22:16:36 qbert /kernel: nread: 0, reqpage: 0, pindex: 0, pcount: 16 Aug 18 22:16:36 qbert /kernel: nread: 0, reqpage: 0, pindex: 0, pcount: 16 -------------------------- So basically it looks like some part of our SCSI bus is failing hardcore... Here is the results of the 'dmesg' command so everyone can see exactly how this machine's hardware is configured..... -------------------------- Copyright (c) 1992-1999 FreeBSD Inc. Copyright (c) 1982, 1986, 1989, 1991, 1993 The Regents of the University of California. All rights reserved. FreeBSD 3.2-19990803-STABLE #0: Wed Aug 18 13:55:26 EDT 1999 root@qbert.telerama.com:/usr/src/sys/compile/QBERT Timecounter "i8254" frequency 1193182 Hz CPU: Pentium II (299.75-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x634 Stepping = 4 Features=0x80fbff real memory = 134217728 (131072K bytes) config> di zp0 config> di ze0 config> di lnc0 config> di le0 config> di ie0 config> di fe0 config> di ep0 config> di ed0 config> di cs0 config> di wt0 config> di scd0 config> di mcd0 config> di matcdc0 config> di aha0 config> di adv0 config> q avail memory = 126984192 (124008K bytes) Preloaded elf kernel "kernel" at 0xc036b000. Preloaded userconfig_script "/boot/kernel.conf" at 0xc036b09c. Probing for devices on PCI bus 0: chip0: rev 0x03 on pci0.0.0 chip1: rev 0x03 on pci0.1.0 chip2: rev 0x01 on pci0.7.0 ide_pci0: rev 0x01 on pci0.7.1 chip3: rev 0x01 on pci0.7.3 bt0: rev 0x08 int a irq 11 on pci0.11.0 bt0: BT-958 FW Rev. 5.07B Ultra Wide SCSI Host Adapter, SCSI ID 7, 192 CCBs fxp0: rev 0x05 int a irq 9 on pci0.12.0 fxp0: Ethernet address 00:a0:c9:db:03:18 Probing for devices on PCI bus 1: Probing for PnP devices: Probing for devices on the ISA bus: sc0 on isa sc0: VGA color <16 virtual consoles, flags=0x0> atkbdc0 at 0x60-0x6f on motherboard atkbd0 irq 1 on isa psm0 not found sio0 at 0x3f8-0x3ff irq 4 flags 0x10 on isa sio0: type 16550A sio1 at 0x2f8-0x2ff irq 3 on isa sio1: type 16550A fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa fdc0: FIFO enabled, 8 bytes threshold fd0: 1.44MB 3.5in wdc0 not found at 0x1f0 wdc1 not found at 0x170 ppc0 at 0x378 irq 7 flags 0x40 on isa ppc0: Generic chipset (ECP/PS2/NIBBLE) in COMPATIBLE mode ppc0: FIFO with 16/16/8 bytes threshold lpt0: on ppbus 0 lpt0: Interrupt-driven port ppi0: on ppbus 0 plip0: on ppbus 0 ex0 not found bt: unit number (1) too high bt1 not found at 0x330 vga0 at 0x3b0-0x3df maddr 0xa0000 msize 131072 on isa npx0 on motherboard npx0: INT 16 interface Waiting 15 seconds for SCSI devices to settle sa0 at bt0 bus 0 target 2 lun 0 sa0: Removable Sequential Access SCSI-2 device sa0: 10.000MB/s transfers (10.000MHz, offset 15) da1 at bt0 bus 0 target 1 lun 0 da1: Fixed Direct Access SCSI-2 device da1: 20.000MB/s transfers (10.000MHz, offset 15, 16bit), Tagged Queueing Enabled da1: 4340MB (8888924 512 byte sectors: 255H 63S/T 553C) da0 at bt0 bus 0 target 0 lun 0 da0: Fixed Direct Access SCSI-2 device da0: 20.000MB/s transfers (10.000MHz, offset 15, 16bit), Tagged Queueing Enabled da0: 4340MB (8888924 512 byte sectors: 255H 63S/T 553C) changing root device to da0s1a WARNING: / was not properly dismounted ----- As you can see, this machine has 3 SCSI devices -- 0 and 1 are internal 4GB seagate barracudas, 2 is our external HP tape drive. So anyways, I am pretty convinced it is either the card, or one of the SCSI devices, or maybe even a bug in the BusLogic SCSI driver (I doubt it, but who knows..heheh)? It seems as though something on the SCSI bus reset itself or something, from what I've seen in the error message.. Could this be a termination problem? I've doublechecked all of our termination, and it seems to be OK !?!? ... If anyone has any suggestions, even on things to try, I'd appreciate it! FYI -- this particular problem has only happened once. The machine HAS been working OK since this happened, but I'm convinced it could happen again... Like I said, I'm not subscribed to this list, so please CC me in any response.. I will check back to the mailing list anyways even if I don't hear anything in e-mail. Thanks in advance!!! -Chris To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Mon Aug 23 7:30:32 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from feral.com (feral.com [192.67.166.1]) by hub.freebsd.org (Postfix) with ESMTP id 735B214BCE for ; Mon, 23 Aug 1999 07:30:26 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from semuta.feral.com (semuta [192.67.166.70]) by feral.com (8.8.7/8.8.7) with ESMTP id HAA13592; Mon, 23 Aug 1999 07:26:43 -0700 Date: Mon, 23 Aug 1999 07:26:41 -0700 (PDT) From: Matthew Jacob Reply-To: mjacob@feral.com To: Christian Weisgerber Cc: freebsd-scsi@FreeBSD.ORG Subject: Re: tape: can't set blocksize on Wangtek In-Reply-To: <7pp7h0$18d$1@bigeye.rhein-neckar.de> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > Christian Weisgerber wrote: > > > 4.0-CURRENT from a few days ago, QIC-1000 tape drive: > > sa0: Removable Sequential Access SCSI-CCS device > > Okay, I think I'm seeing a pattern here. > It seems I can successfully change the block size if there is no > tape inserted. (Or after an "mt offline", which presumably amounts to > the same thing even if the tape is still physically in the drive.) Yes- that's likely with a fixed blocksize device that bases what size it is set to on what the tape can support. This may be complicated by the fake variable mode that some drives support. > > Changing the block size after a tape has been inserted but not yet > read from works sometimes. No recognizable pattern yet. Changing > the block size after the tape has been read from fails reliably. Yes- and this may get worse- I'm about to commit changes that will do a test read at tape mount time in order to determine existing blocksize and tape density (or, rather, force the drive to set these values by getting it to do a media access). There are two problems you've reported- one where you have trouble changing blocksize and the other where reading the tape gives you NULLs and other things, etc.. The former problem you've tripped over while trying to set 'variable' mode (at my request) to see if your tape is readable in fake 'variable' mode. I'm not sure what to tell you to do at this point. What mode was this tape *written* under? -matt To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Mon Aug 23 11:14:34 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from gordius.gordian.com (gordius.gordian.com [192.73.220.81]) by hub.freebsd.org (Postfix) with ESMTP id 3EFBF156B3 for ; Mon, 23 Aug 1999 11:14:26 -0700 (PDT) (envelope-from steve@gordian.com) X-bait: aablmeh@gordian.com,mmblmeh@gordian.com,zzblmeh@gordian.com Received: from gordian.com (asclepius.gordian.com [192.73.220.254]) by gordius.gordian.com (8.9.3/8.9.3) with ESMTP id LAA04167; Mon, 23 Aug 1999 11:14:07 -0700 (PDT) Message-ID: <37C18F6E.4FD79CD1@gordian.com> Date: Mon, 23 Aug 1999 11:14:06 -0700 From: Steve Khoo Organization: Gordian; Santa Ana Heights, CA X-Mailer: Mozilla 4.61 [en] (X11; U; FreeBSD 2.2.8-STABLE i386) X-Accept-Language: en MIME-Version: 1.0 To: Mark Salyzyn Cc: freebsd-scsi@FreeBSD.ORG Subject: Re: dpt scsi smartraid iv controller, in raid 5 mode... ? References: <199908191539.AA17493@bohica.dpt.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Mark Salyzyn wrote: > > In article <19990818085508.N7187@freebie.lemis.com>, you wrote: > >I haven't heard of any bugs. I have heard suggestions that the RAID-5 > >performance is even worse than RAID-5 has to be, but I don't have much > >in the way of evidence. > > It will depend on the mix of FW you are using, cache and drives. DPT's > RAID-5 performance typically exceeds what is expected (IMHO) due to > our use of the cache on the controller, but can also suck for something as > subtle as a bogus stripe size selection. > > >> while other people have said that dpt support doesn't know about the > >> raid iv drivers. > >I suppose that depends on who you get at DPT support. > > Since the IV generation driver was written by Simon Shapiro, DPT support > (and DPT engineering) are at somewhat of a disadvantage. This is changing > as they come up to speed. LINUX ran into a similar issues with Michael > Neuffer effectively becoming a volunteer DPT support person instead of > DPT providing the support. > > >> also there is rumor of support for the raid v card 'soon'. > >Yes. There is a rumour. > > No rumor, I released the driver to any who would ask for it on August 3 > and announced it here and in freebsd-hardware. Currently, only Mirapoint > has taken to testing the driver. I saw that announcement. Too bad it wasn't for 3.2. Otherwise I would have a nice file server with DPT V up and running by now. > > The driver provides passthrough, so we have a working native command > line based configuration tool (dptutil). An engineer is working on porting > the storage manager to the X11/LessTIF environment. This driver is a > SCSI based driver. This sounds cool. Any idea if simon's version is going to have something similar? > Simon Shapiro is working on a higher performance Monolithic driver > which should be out real soon. Any idea when "real soon" is? I need to put together a system soon, and would much prefer to use a DPT V. > >> please excuse the hotmail acct :/ > >I will. My mail system won't :-) > > I get grumpy when I see email from earthlink, considering their > gross indecency back in the Cantor and Siegel days and the > ensuing spam ;-/. > > But I learned many years ago that it doesn't matter which > country, or internet service, you are on, they are all people > deserving of respect! > > ;-> > > Sincerely -- Mark Salyzyn > ObjDisclaimer: I know nothing, and what I say does not > represent DPT. SEK -- Steve E. Khoo GORDIAN Systems Manager 20361 Irvine Ave. Internet: steve@gordian.com Santa Ana Heights, CA 92707 Voice:(714)850-0205 Fax:(714)850-0533 HTTP://WWW.GORDIAN.COM Wanna be blacklisted by our spam filter? mailto: aablme@gordian.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Mon Aug 23 13:14: 9 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from narnia.plutotech.com (narnia.plutotech.com [206.168.67.130]) by hub.freebsd.org (Postfix) with ESMTP id CE3B4157D8 for ; Mon, 23 Aug 1999 13:13:29 -0700 (PDT) (envelope-from gibbs@narnia.plutotech.com) Received: (from gibbs@localhost) by narnia.plutotech.com (8.9.3/8.7.3) id OAA58981; Mon, 23 Aug 1999 14:02:31 -0600 (MDT) Date: Mon, 23 Aug 1999 14:02:31 -0600 (MDT) From: "Justin T. Gibbs" Message-Id: <199908232002.OAA58981@narnia.plutotech.com> To: Chris Tracy Cc: scsi@FreeBSD.org Subject: Re: weird SCSI problems... X-Newsgroups: pluto.freebsd.scsi In-Reply-To: User-Agent: tin/pre-1.4-980818 ("Laura") (UNIX) (FreeBSD/4.0-CURRENT (i386)) Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org In article you wrote: > bt0: rev 0x08 int a irq 11 on > pci0.11.0 > bt0: BT-958 FW Rev. 5.07B Ultra Wide SCSI Host Adapter, SCSI ID 7, 192 > CCBs Try dropping down to the 5.06I FW. You can pick it up from ftp://ftp.mylex.com/pub/flashbios/wpflash.exe The author of the Linux driver reported problems with 5.07B some time back and 5.06I seems to be a stable release. -- Justin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Mon Aug 23 13:14:35 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from narnia.plutotech.com (narnia.plutotech.com [206.168.67.130]) by hub.freebsd.org (Postfix) with ESMTP id DB2AB1501B for ; Mon, 23 Aug 1999 13:14:33 -0700 (PDT) (envelope-from gibbs@narnia.plutotech.com) Received: (from gibbs@localhost) by narnia.plutotech.com (8.9.3/8.7.3) id OAA58987; Mon, 23 Aug 1999 14:03:40 -0600 (MDT) Date: Mon, 23 Aug 1999 14:03:40 -0600 (MDT) From: "Justin T. Gibbs" Message-Id: <199908232003.OAA58987@narnia.plutotech.com> To: Stephen McKay Cc: scsi@FreeBSD.org Subject: Re: Can I rescue this 2940UW? X-Newsgroups: pluto.freebsd.scsi In-Reply-To: <199908211612.CAA10348@nymph.detir.qld.gov.au> User-Agent: tin/pre-1.4-980818 ("Laura") (UNIX) (FreeBSD/4.0-CURRENT (i386)) Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > When I try to access data I get a panic: sequencer parity error. This means that something on the aic7880 itself is fried. I doubt that flashing to a different BIOS rev will have any effect on this problem. -- Justin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Mon Aug 23 23:42: 8 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from gilliam.users.flyingcroc.net (gilliam.users.flyingcroc.net [207.246.128.2]) by hub.freebsd.org (Postfix) with ESMTP id 1F5C5159A7 for ; Mon, 23 Aug 1999 23:42:05 -0700 (PDT) (envelope-from ross@gilliam.users.flyingcroc.net) Received: (from ross@localhost) by gilliam.users.flyingcroc.net (8.9.3/8.9.3) id XAA04913; Mon, 23 Aug 1999 23:28:31 -0700 (PDT) Date: Wed, 18 Aug 1999 13:37:22 -0700 (PDT) Message-Id: <199908240628.XAA04913@gilliam.users.flyingcroc.net> Subject: Re: camcontrol reset 0:3:0 hangs systems To: sthaug@nethelp.no Cc: freebsd-scsi@FreeBSD.ORG From: "Kenneth D. Merry" Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org sthaug@nethelp.no wrote... > System: FreeBSD 3.2-STABLE as of 17. august, 2xPII-450, Adaptec SCSI > controller: > > ahc0: rev 0x00 int a irq 11 on pci0.12.0 > ahc0: aic7890/91 Wide Channel A, SCSI Id=7, 16/255 SCBs > > and 4 IBM disks: > [ ... ] > A "camcontrol reset 0" works fine, "Reset of bus 0 was successful". > > A "camcontrol reset 0:3:0" (trying to reset da2) reliably hangs the > system (no response from the command, everything hangs). Error messages > on console: > > (xpt0:ahc0:0:3:0): Bus Device Reset Message Sent > ahc0: Bus Device Reset on A:3. 1 SCBs aborted. > > The hang occurs whether the system runs a uniprocessor or an SMP kernel, > and it doesn't matter which disk is attempted reset either. [ ... ] That's a known problem. I think I know how to fix it, but I haven't had a chance to do so yet. Hopefully I'll get to it before the end of the month. Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Mon Aug 23 23:42:41 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from gilliam.users.flyingcroc.net (gilliam.users.flyingcroc.net [207.246.128.2]) by hub.freebsd.org (Postfix) with ESMTP id 15D90159BF for ; Mon, 23 Aug 1999 23:42:05 -0700 (PDT) (envelope-from ross@gilliam.users.flyingcroc.net) Received: (from ross@localhost) by gilliam.users.flyingcroc.net (8.9.3/8.9.3) id XAA04741; Mon, 23 Aug 1999 23:28:20 -0700 (PDT) Date: Mon, 16 Aug 1999 06:56:13 -0700 (PDT) Message-Id: <199908240628.XAA04741@gilliam.users.flyingcroc.net> From: To: "Justin T. Gibbs" Cc: scsi@FreeBSD.ORG Subject: Adaptec RAID support WAS Re: Adaptec AIC-7896 flakyness Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, 15 Aug 1999, Justin T. Gibbs wrote: > >Now...if you could let me know what, if anything is being done for a > >driver for the Adaptec ARO-1130 RAIDport add-on card, I'm all ears. :) > > Not much. I haven't been able to get the necessary documentation for > RAID support from Adaptec. hmmm...I just noticed that there's a kld for SCO Unix compatibility. Adaptec ships a driver for SCO Unix and SCO Unixware (why, I have no idea). I have a feeling that there'd be a chicken and egg problemtrying to load a kld before the kernel is even running though. I grep'd the LINT kernel source for any mention of SCO and saw nothing. Is this a track even worth pursuing? James Smallacombe PlantageNet, Inc. CEO and Janitor up@3.am http://3.am ========================================================================= ISPF 3 - The Forum for ISPs by ISPs(tm) || Nov 15-17, 1999, New Orleans 3 days of clues, news, and views from the industry's best and brightest. Visit for information and registration. ========================================================================= To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 0:30:32 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from db.geocrawler.com (db.gotocity.com [165.90.140.10]) by hub.freebsd.org (Postfix) with ESMTP id 24D1A14CA5 for ; Tue, 24 Aug 1999 00:30:27 -0700 (PDT) (envelope-from nobody@db.geocrawler.com) Received: (from nobody@localhost) by db.geocrawler.com (8.8.8/8.8.8) id CAA14695; Tue, 24 Aug 1999 02:27:44 -0500 Date: Tue, 24 Aug 1999 02:27:44 -0500 Message-Id: <199908240727.CAA14695@db.geocrawler.com> To: freebsd-scsi@freebsd.org Subject: The I/O is too slow than linux From: "Geocrawler.com" Reply-To: "liudong" Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org This message was sent from Geocrawler.com by "liudong" Be sure to reply to that address. some of dmesg output: ..... ahc0: aic7896/97 Wide Channel A, SCSI Id=7, 16/255 SCBs ahc1: rev 0x00 int a irq 19 on pci0.12.1 ahc1: aic7896/97 Wide Channel B, SCSI Id=7, 16/255 SCBs ...... Waiting 5 seconds for SCSI devices to settle pass4 at ahc1 bus 0 target 6 lun 0 pass4: Fixed Processor SCSI-2 device pass4: 3.300MB/s transfers da0 at ahc0 bus 0 target 0 lun 0 da0: Fixed Direct Access SCSI-2 device da0: 80.000MB/s transfers (40.000MHz, offset 31, 16bit), Tagged Queueing Enabled da0: 17501MB (35843520 512 byte sectors: 255H 63S/T 2231C) da1 at ahc0 bus 0 target 0 lun 1 da1: Fixed Direct Access SCSI-2 device da1: 80.000MB/s transfers (40.000MHz, offset 31, 16bit), Tagged Queueing Enabled da1: 35003MB (71687040 512 byte sectors: 255H 63S/T 4462C) da2 at ahc0 bus 0 target 0 lun 2 da2: Fixed Direct Access SCSI-2 device da2: 80.000MB/s transfers (40.000MHz, offset 31, 16bit), Tagged Queueing Enabled da2: 17501MB (35843520 512 byte sectors: 255H 63S/T 2231C) changing root device to da0s1a da3 at ahc1 bus 0 target 1 lun 0 da3: Fixed Direct Access SCSI-3 device da3: 40.000MB/s transfers (20.000MHz, offset 31, 16bit), Tagged Queueing Enabled da3: 17501MB (35843670 512 byte sectors: 255H 63S/T 2231C) ffs_mountfs: superblock updated for soft updates ffs_mountfs: superblock updated for soft updates then run ... # time dd if=/dev/da0 of=/dev/null count=200000 200000+0 records in 200000+0 records out 102400000 bytes transferred in 36.852771 secs (2778624 bytes/sec) real 0m36.911s user 0m0.372s sys 0m5.982s The same computer in linux(2.2.5): # time dd if=/dev/sda of=/dev/null count=200000 200000+0 records in 200000+0 records out 0.52user 2.29system 0:09.05elapsed 31%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (89major+13minor)pagefaults 0swaps What is the problem!!?? Geocrawler.com - The Knowledge Archive To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 0:43:36 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from metriclient-1.uoregon.edu (metriclient-1.uoregon.edu [128.223.172.1]) by hub.freebsd.org (Postfix) with ESMTP id 72F1114EAE for ; Tue, 24 Aug 1999 00:43:31 -0700 (PDT) (envelope-from gurney_j@efn.org) Received: (from jmg@localhost) by metriclient-1.uoregon.edu (8.9.1/8.8.7) id AAA21213; Tue, 24 Aug 1999 00:43:18 -0700 (PDT) Message-ID: <19990824004318.26611@hydrogen.fircrest.net> Date: Tue, 24 Aug 1999 00:43:18 -0700 From: John-Mark Gurney To: up@3.am Cc: "Justin T. Gibbs" , scsi@FreeBSD.ORG Subject: Re: Adaptec RAID support WAS Re: Adaptec AIC-7896 flakyness References: <199908240628.XAA04741@gilliam.users.flyingcroc.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 In-Reply-To: <199908240628.XAA04741@gilliam.users.flyingcroc.net>; from up@3.am on Mon, Aug 16, 1999 at 06:56:13AM -0700 Reply-To: John-Mark Gurney Organization: Cu Networking X-Operating-System: FreeBSD 3.0-RELEASE i386 X-PGP-Fingerprint: B7 EC EF F8 AE ED A7 31 96 7A 22 B3 D8 56 36 F4 X-Files: The truth is out there X-URL: http://resnet.uoregon.edu/~gurney_j/ Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org up@3.am scribbled this message on Aug 16: > On Sun, 15 Aug 1999, Justin T. Gibbs wrote: > > > >Now...if you could let me know what, if anything is being done for a > > >driver for the Adaptec ARO-1130 RAIDport add-on card, I'm all ears. :) > > > > Not much. I haven't been able to get the necessary documentation for > > RAID support from Adaptec. > > hmmm...I just noticed that there's a kld for SCO Unix compatibility. > Adaptec ships a driver for SCO Unix and SCO Unixware (why, I have no > idea). I have a feeling that there'd be a chicken and egg problemtrying > to load a kld before the kernel is even running though. I grep'd the > LINT kernel source for any mention of SCO and saw nothing. > > Is this a track even worth pursuing? that's for SCO user land binary compatibility... adding SCO kernel compatibility is a completely different story... -- John-Mark Gurney Voice: +1 541 684 8449 Cu Networking P.O. Box 5693, 97405 "The soul contains in itself the event that shall presently befall it. The event is only the actualizing of its thought." -- Ralph Waldo Emerson To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 1: 1: 0 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from ren.detir.qld.gov.au (ns.detir.qld.gov.au [203.46.81.66]) by hub.freebsd.org (Postfix) with ESMTP id 4A11914FAA for ; Tue, 24 Aug 1999 01:00:55 -0700 (PDT) (envelope-from syssgm@detir.qld.gov.au) Received: by ren.detir.qld.gov.au; id RAA16292; Tue, 24 Aug 1999 17:26:06 +1000 (EST) Received: from ogre.detir.qld.gov.au(167.123.8.3) by ren.detir.qld.gov.au via smap (3.2) id xma016251; Tue, 24 Aug 99 17:25:38 +1000 Received: from atlas.detir.qld.gov.au (atlas.detir.qld.gov.au [167.123.8.9]) by ogre.detir.qld.gov.au (8.8.8/8.8.7) with ESMTP id RAA26071; Tue, 24 Aug 1999 17:25:37 +1000 (EST) Received: from nymph.detir.qld.gov.au (nymph.detir.qld.gov.au [167.123.10.10]) by atlas.detir.qld.gov.au (8.8.5/8.8.5) with ESMTP id RAA26053; Tue, 24 Aug 1999 17:25:36 +1000 (EST) Received: from nymph.detir.qld.gov.au (localhost.detir.qld.gov.au [127.0.0.1]) by nymph.detir.qld.gov.au (8.8.8/8.8.7) with ESMTP id RAA14124; Tue, 24 Aug 1999 17:25:36 +1000 (EST) (envelope-from syssgm@nymph.detir.qld.gov.au) Message-Id: <199908240725.RAA14124@nymph.detir.qld.gov.au> To: "Justin T. Gibbs" Cc: Stephen McKay , scsi@FreeBSD.org Subject: Re: Can I rescue this 2940UW? References: <199908232003.OAA58987@narnia.plutotech.com> In-Reply-To: <199908232003.OAA58987@narnia.plutotech.com> from "Justin T. Gibbs" at "Mon, 23 Aug 1999 14:03:40 -0600" Date: Tue, 24 Aug 1999 17:25:36 +1000 From: Stephen McKay Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Monday, 23rd August 1999, "Justin T. Gibbs" wrote: >> When I try to access data I get a panic: sequencer parity error. > >This means that something on the aic7880 itself is fried. I doubt that >flashing to a different BIOS rev will have any effect on this problem. Bummer. :-( I assumed it was just some setup that the BIOS was supposed to do that the ahc driver doesn't do for itself. Oh well, another piece of junk for my collection... Stephen. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 3: 9:29 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from implode.root.com (root.com [209.102.106.178]) by hub.freebsd.org (Postfix) with ESMTP id E41A715998 for ; Tue, 24 Aug 1999 03:09:14 -0700 (PDT) (envelope-from dg@implode.root.com) Received: from implode.root.com (localhost [127.0.0.1]) by implode.root.com (8.8.8/8.8.5) with ESMTP id DAA14184; Tue, 24 Aug 1999 03:05:45 -0700 (PDT) Message-Id: <199908241005.DAA14184@implode.root.com> To: "liudong" Cc: freebsd-scsi@FreeBSD.ORG Subject: Re: The I/O is too slow than linux In-reply-to: Your message of "Tue, 24 Aug 1999 02:27:44 CDT." <199908240727.CAA14695@db.geocrawler.com> From: David Greenman Reply-To: dg@root.com Date: Tue, 24 Aug 1999 03:05:45 -0700 Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >then run ... ># time dd if=/dev/da0 of=/dev/null count=200000 >200000+0 records in >200000+0 records out >102400000 bytes transferred in 36.852771 secs (2778624 bytes/sec) > >real 0m36.911s >user 0m0.372s >sys 0m5.982s You need to use the raw device for tests like this and you should specify a blocksize as well, e.g.: time dd if/dev/rda0 of=/dev/null bs=64k count=200000 The block device should only be used when mounting the filesystem. -DG David Greenman Co-founder/Principal Architect, The FreeBSD Project - http://www.freebsd.org Creator of high-performance Internet servers - http://www.terasolutions.com Pave the road of life with opportunities. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 3:24:37 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from mrelay.jrc.it (mrelay.jrc.it [139.191.1.65]) by hub.freebsd.org (Postfix) with ESMTP id EB54114D85 for ; Tue, 24 Aug 1999 03:24:33 -0700 (PDT) (envelope-from nick.hibma@jrc.it) Received: from elect8 (elect8.jrc.it [139.191.71.152]) by mrelay.jrc.it (LMC5692) with SMTP id MAA02244; Tue, 24 Aug 1999 12:24:07 +0200 (MET DST) Date: Tue, 24 Aug 1999 12:23:53 +0200 (MET DST) From: Nick Hibma X-Sender: n_hibma@elect8 Reply-To: Nick Hibma To: David Greenman Cc: liudong , freebsd-scsi@FreeBSD.ORG Subject: Re: The I/O is too slow than linux In-Reply-To: <199908241005.DAA14184@implode.root.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On a 3.2 machine here: bash-2.03# time dd if=/dev/da0 of=/dev/null count=128000 128000+0 records in 128000+0 records out 65536000 bytes transferred in 19.586158 secs (3346037 bytes/sec) real 0m19.602s user 0m0.242s sys 0m3.602s bash-2.03# time dd if=/dev/rda0 of=/dev/null count=1000 bs=64k 1000+0 records in 1000+0 records out 65536000 bytes transferred in 7.724508 secs (8484165 bytes/sec) real 0m7.749s user 0m0.015s sys 0m0.060s Quite a difference. Linux adapts the blocksize to the read size? Does their implementation of dd do something funny? Nick ahc0: rev 0x03 int a irq 12 on pci0.10.0 da0 at ahc0 bus 0 target 1 lun 0 da0: Fixed Direct Access SCSI-2 device da0: 10.000MB/s transfers (10.000MHz, offset 15), Tagged Queueing Enabled da0: 4340MB (8888924 512 byte sectors: 255H 63S/T 553C) On Tue, 24 Aug 1999, David Greenman wrote: > >then run ... > ># time dd if=/dev/da0 of=/dev/null count=200000 > >200000+0 records in > >200000+0 records out > >102400000 bytes transferred in 36.852771 secs (2778624 bytes/sec) > > > >real 0m36.911s > >user 0m0.372s > >sys 0m5.982s > > You need to use the raw device for tests like this and you should specify > a blocksize as well, e.g.: > > time dd if/dev/rda0 of=/dev/null bs=64k count=200000 > > The block device should only be used when mounting the filesystem. > > -DG > > David Greenman > Co-founder/Principal Architect, The FreeBSD Project - http://www.freebsd.org > Creator of high-performance Internet servers - http://www.terasolutions.com > Pave the road of life with opportunities. > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-scsi" in the body of the message > > -- ISIS/STA, T.P.270, Joint Research Centre, 21020 Ispra, Italy To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 11:36:31 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from implode.root.com (root.com [209.102.106.178]) by hub.freebsd.org (Postfix) with ESMTP id A3AD1150D1 for ; Tue, 24 Aug 1999 11:36:00 -0700 (PDT) (envelope-from dg@implode.root.com) Received: from implode.root.com (localhost [127.0.0.1]) by implode.root.com (8.8.8/8.8.5) with ESMTP id LAA15347; Tue, 24 Aug 1999 11:33:59 -0700 (PDT) Message-Id: <199908241833.LAA15347@implode.root.com> To: Nick Hibma Cc: liudong , freebsd-scsi@FreeBSD.ORG Subject: Re: The I/O is too slow than linux In-reply-to: Your message of "Tue, 24 Aug 1999 12:23:53 +0200." From: David Greenman Reply-To: dg@root.com Date: Tue, 24 Aug 1999 11:33:59 -0700 Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >bash-2.03# time dd if=/dev/da0 of=/dev/null count=128000 >128000+0 records in >128000+0 records out >65536000 bytes transferred in 19.586158 secs (3346037 bytes/sec) > >real 0m19.602s >user 0m0.242s >sys 0m3.602s > >bash-2.03# time dd if=/dev/rda0 of=/dev/null count=1000 bs=64k >1000+0 records in >1000+0 records out >65536000 bytes transferred in 7.724508 secs (8484165 bytes/sec) > >real 0m7.749s >user 0m0.015s >sys 0m0.060s > > >Quite a difference. Linux adapts the blocksize to the read size? Does >their implementation of dd do something funny? As I recall, Linux doesn't have block devices (or is it that it doesn't have character devices?....hmmm). -DG David Greenman Co-founder/Principal Architect, The FreeBSD Project - http://www.freebsd.org Creator of high-performance Internet servers - http://www.terasolutions.com Pave the road of life with opportunities. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 12: 4:32 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.26.10.9]) by hub.freebsd.org (Postfix) with ESMTP id 85E91151F4 for ; Tue, 24 Aug 1999 12:04:25 -0700 (PDT) (envelope-from bde@godzilla.zeta.org.au) Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.7/8.8.7) id FAA00684; Wed, 25 Aug 1999 05:03:14 +1000 Date: Wed, 25 Aug 1999 05:03:14 +1000 From: Bruce Evans Message-Id: <199908241903.FAA00684@godzilla.zeta.org.au> To: dg@root.com, nick.hibma@jrc.it Subject: Re: The I/O is too slow than linux Cc: freebsd-scsi@FreeBSD.ORG, shift@263.net Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org >>Quite a difference. Linux adapts the blocksize to the read size? Does >>their implementation of dd do something funny? > > As I recall, Linux doesn't have block devices (or is it that it doesn't >have character devices?....hmmm). Linux has only block devices, but for some reason (probably better clustering) they are much faster than ours despite using a smaller block size (1K instad of 2K). I/O is not clustered in any way for FreeBSD block devices, so the throughput is at best the same as for a block size of 2K with the corresponding character device. For IDE devices it is much worse, since the silly DIOCGPART ioctl() is called for every i/o and it does a sillier wait for i/o to complete. This causes amazing slow speeds for newfs on a buffered IDE device (waiting is worse for writes). I've only found one useful class of uses for buffered devices. It is good (*) for un-breaking disk utilities that don't do i/o in blocks, e.g., Linux fsck.ext2. (*) Not actually good for writes, since write errors can not be returned to the application. Bruce To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Tue Aug 24 15:11:19 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from frmug.org (frmug-gw.frmug.org [193.56.58.252]) by hub.freebsd.org (Postfix) with ESMTP id 1444215423 for ; Tue, 24 Aug 1999 15:11:11 -0700 (PDT) (envelope-from roberto@keltia.freenix.fr) Received: (from uucp@localhost) by frmug.org (8.9.3/frmug-2.5/nospam) with UUCP id AAA11155 for freebsd-scsi@FreeBSD.ORG; Wed, 25 Aug 1999 00:10:08 +0200 (CEST) (envelope-from roberto@keltia.freenix.fr) Received: by keltia.freenix.fr (Postfix, from userid 101) id EC85E8795; Tue, 24 Aug 1999 23:46:56 +0200 (CEST) Date: Tue, 24 Aug 1999 23:46:56 +0200 From: Ollivier Robert To: freebsd-scsi@FreeBSD.ORG Subject: Re: The I/O is too slow than linux Message-ID: <19990824234656.A40168@keltia.freenix.fr> Mail-Followup-To: freebsd-scsi@FreeBSD.ORG References: <199908241833.LAA15347@implode.root.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii User-Agent: Mutt/0.95.5i In-Reply-To: <199908241833.LAA15347@implode.root.com>; from David Greenman on Tue, Aug 24, 1999 at 11:33:59AM -0700 X-Operating-System: FreeBSD 4.0-CURRENT/ELF ctm#5543 AMD-K6 MMX @ 200 MHz Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org According to David Greenman: > As I recall, Linux doesn't have block devices (or is it that it doesn't > have character devices?....hmmm). They have only block devices under Linux. I never understood why. The other way around (like we have) with only character devices makes sense with an unified VM/buffer cache architecture. -- Ollivier ROBERT -=- FreeBSD: The Power to Serve! -=- roberto@keltia.freenix.fr FreeBSD keltia.freenix.fr 4.0-CURRENT #73: Sat Jul 31 15:36:05 CEST 1999 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Wed Aug 25 9: 7:43 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from grisu.bik-gmbh.de (grisu.bik-gmbh.de [194.233.237.82]) by hub.freebsd.org (Postfix) with ESMTP id D008F15135 for ; Wed, 25 Aug 1999 09:07:30 -0700 (PDT) (envelope-from cracauer@gilgamesch.bik-gmbh.de) Received: from gilgamesch.bik-gmbh.de (gilgamesch.bik-gmbh.de [194.233.237.194]) by grisu.bik-gmbh.de (8.8.8/8.6.9) with ESMTP id SAA10485; Wed, 25 Aug 1999 18:06:47 +0200 (MEST) Received: (from cracauer@localhost) by gilgamesch.bik-gmbh.de (8.9.3/8.7.3) id SAA69455; Wed, 25 Aug 1999 18:06:28 +0200 (MET DST) Date: Wed, 25 Aug 1999 18:06:28 +0200 From: Martin Cracauer To: liudong Cc: freebsd-scsi@FreeBSD.ORG Subject: Re: The I/O is too slow than linux Message-ID: <19990825180628.B66149@cons.org> References: <199908240727.CAA14695@db.geocrawler.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.95.4i In-Reply-To: <199908240727.CAA14695@db.geocrawler.com>; from Geocrawler.com on Tue, Aug 24, 1999 at 02:27:44AM -0500 Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org In <199908240727.CAA14695@db.geocrawler.com>, Geocrawler.com wrote: > # time dd if=/dev/da0 of=/dev/null count=200000 > 200000+0 records in > 200000+0 records out > 102400000 bytes transferred in 36.852771 secs (2778624 bytes/sec) > > real 0m36.911s > user 0m0.372s > sys 0m5.982s > > The same computer in linux(2.2.5): > # time dd if=/dev/sda of=/dev/null count=200000 > 200000+0 records in > 200000+0 records out > 0.52user 2.29system 0:09.05elapsed 31%CPU (0avgtext+0avgdata 0maxresident)k > 0inputs+0outputs (89major+13minor)pagefaults 0swaps > > What is the problem!!?? In addition to what other said, don't use /dev/null in benchmarks. Speed varies greatly over different operating systems (Ultrix on MIPS Decstations is real fun here). A dd replacement that can discard (or generate) data is in ports/misc/cstream. In fact, one of the major reasons to roll that tool is benchmarking and the /dev/null variances. You can use cstream to "benchmark" /dev/null: Linux: /home/cracauer(oskar)3% cstream -n 50m -o/dev/null -v1 -i- 52428800 B 50.0 MB 0.04 s 1220098940 B/s 1.14 GB/s FreeBSD: ~(knight)20% cstream -n 50m -o/dev/null -v1 -i- 52428800 B 50.0 MB 0.11 s 456219899 B/s 435.09 MB/s Both are 486/DX-100 256 KB cache. Blocksize 8k. I would also recommend testing through the filesystem, as amount of readahead and other parameters of the block devices may have different best values for direct block devices or when using a filesystem, especially one that isn't fresh or when using other patterns than sequential read. Not to speak of simultaneous access from several applications. When I switched a major application of my employer from a linear (complete) read of a file to mmapp()ing, FreeBSD looked even better than before. FreeBSD could take advantage of the fact that the application runs didn't touch every block of the file, just most. We originally found that complete reading was better than partly reading (we touch about than 30-70% of the file's blocks), but that data was gathered from pre-FreeBSD operating systems, which filled the holes with readahead anyway, hence no speedup from jumping and part-reading. Or in other words, don't benchmark, measure real applications and redo the measurement when the OS changes. And don't speculate about what the OS might be doing. If if you figure out what the OS does, you usually don't have experience to translate that behaviour into performance. Martin -- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Martin Cracauer http://www.cons.org/cracauer/ BSD User Group Hamburg, Germany http://www.bsdhh.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Wed Aug 25 13: 1:55 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from ivory.lm.com (ivory.telerama.com [205.201.1.20]) by hub.freebsd.org (Postfix) with ESMTP id A5C6014F73 for ; Wed, 25 Aug 1999 13:01:48 -0700 (PDT) (envelope-from ncrawler@telerama.com) Received: from gauntlet.telerama.com (ncrawler@gauntlet.telerama.com [205.201.1.214]) by ivory.lm.com (8.8.5/8.6.12) with SMTP id QAA20965 for ; Wed, 25 Aug 1999 16:01:47 -0400 (EDT) Date: Wed, 25 Aug 1999 16:01:47 -0400 (EDT) From: Chris Tracy To: scsi@freebsd.org Subject: Re: weird SCSI problems... In-Reply-To: <199908232002.OAA58981@narnia.plutotech.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Mon, 23 Aug 1999, Justin T. Gibbs wrote: > In article you wrote: > > > bt0: rev 0x08 int a irq 11 on > > pci0.11.0 > > bt0: BT-958 FW Rev. 5.07B Ultra Wide SCSI Host Adapter, SCSI ID 7, 192 > > CCBs > > Try dropping down to the 5.06I FW. You can pick it up from > ftp://ftp.mylex.com/pub/flashbios/wpflash.exe > > The author of the Linux driver reported problems with 5.07B some time > back and 5.06I seems to be a stable release. Humm... So, I gave this firmware change a try. We are now running the 5.06I firmware. Unfortunately, I am still having the same problem. Except now, it is more frequent, and now it usually happens upon bootup. I've gotten different error messages, but there are all to the effect of: (da0:bt0:0:0:0): CCB 0xc55024c0 - timed out (da0:bt0:0:0:0): CCB 0xc55024c0 - timed out (da0:bt0:0:0:0): CCB 0xc55024c0 - timed out bt0: No longer in timeout bt0: No longer in timeout (da0:bt0:0:0:0): Invalidating pack (da0:bt0:0:0:0): Invalidating pack This usually happens right after the filesystem checks, although it has happened as late as when it starts the syslog daemon... If it let the machine stay on long enough after these messages, it usually results in nasty kernel page faults and stuff. The strangest thing is, the machine will boot some time and get to the login prompt, and work fine. I haven't seen it crash once after I got to a login prompt and logged in and everything. It just seems to do it on bootup after the filesystem checks. I noticed some people talking about the "Motor spin up" jumpers on SCSI harddrives who were having similar problems. I was going to try shorting the "Motor spin enable" jumper and see if that'll make a difference. I'm also getting ready to try another SCSI card... Unfortunately I don't have any others that'll support this drive, so I might go and pickup a 2940UW. Is this the best SCSI card to pickup these days? If anyone else has any ideas, please let me know! Thanks, -Chris. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Wed Aug 25 20: 2:34 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from cheddar.netmonger.net (cheddar.netmonger.net [209.54.21.140]) by hub.freebsd.org (Postfix) with ESMTP id 68B0614E94 for ; Wed, 25 Aug 1999 20:02:31 -0700 (PDT) (envelope-from chris@cheddar.netmonger.net) Received: (from chris@localhost) by cheddar.netmonger.net (8.8.8/8.8.8) id WAA24489; Wed, 25 Aug 1999 22:59:28 -0400 (EDT) Message-ID: <19990825225928.A24365@netmonger.net> Date: Wed, 25 Aug 1999 22:59:28 -0400 From: Christopher Masto To: scsi@freebsd.org Subject: Seagate vs Quantum.. opinions? Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.91.1i Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I have a situation where I asked for Seagate Barracudas and was shipped "QUANTUM ATLAS IV 9 WLS 0707" instead. Before I send them back, I want to make sure I'd be making the right decision. As people here have intimate knowledge of which drives FreeBSD gets along best with, and which ones have nasty quirks and firmware bugs, should I keep the Atlases or the Barracudas? -- Christopher Masto Senior Network Monkey NetMonger Communications chris@netmonger.net info@netmonger.net http://www.netmonger.net Free yourself, free your machine, free the daemon -- http://www.freebsd.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Wed Aug 25 20:18:40 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from picnic.mat.net (picnic.mat.net [206.246.122.133]) by hub.freebsd.org (Postfix) with ESMTP id 4C70415ACD for ; Wed, 25 Aug 1999 20:18:04 -0700 (PDT) (envelope-from chuckr@picnic.mat.net) Received: from localhost (chuckr@localhost) by picnic.mat.net (8.9.3/8.9.3) with ESMTP id XAA05809; Wed, 25 Aug 1999 23:15:12 -0400 (EDT) (envelope-from chuckr@picnic.mat.net) Date: Wed, 25 Aug 1999 23:15:12 -0400 (EDT) From: Chuck Robey To: Christopher Masto Cc: scsi@FreeBSD.ORG Subject: Re: Seagate vs Quantum.. opinions? In-Reply-To: <19990825225928.A24365@netmonger.net> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Wed, 25 Aug 1999, Christopher Masto wrote: > I have a situation where I asked for Seagate Barracudas and was > shipped "QUANTUM ATLAS IV 9 WLS 0707" instead. Before I send them > back, I want to make sure I'd be making the right decision. > > As people here have intimate knowledge of which drives FreeBSD gets > along best with, and which ones have nasty quirks and firmware bugs, > should I keep the Atlases or the Barracudas? Have you tried the IBM drives? I know you said Seagate and Quantum, but the IBM drives seem (to me) to be, all at the same time, the cheapest, coolest, quietest, and very nearly the fastest. Check the prices, if you go to the places I go to, you're in for a shock. I am really starting to be an IBM booster (take a look at all the free source code available at their site, if you need other reasons). Times sure have changed, haven't they? They don't seem to be trying to be such open monopolists these days. > -- > Christopher Masto Senior Network Monkey NetMonger Communications > chris@netmonger.net info@netmonger.net http://www.netmonger.net > > Free yourself, free your machine, free the daemon -- http://www.freebsd.org/ > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-scsi" in the body of the message > ---------------------------+----------------------------------------------- Chuck Robey | Interests include any kind of voice or data chuckr@picnic.mat.net | communications topic, C programming, and Unix. 213 Lakeside Drive Apt T-1 | Greenbelt, MD 20770 | picnic.mat.net: FreeBSD/i386 (301) 220-2114 | jaunt.mat.net : FreeBSD/Alpha ---------------------------+----------------------------------------------- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Wed Aug 25 20:42:41 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from sammy.tibco.com (sammy.tibco.com [192.216.111.146]) by hub.freebsd.org (Postfix) with ESMTP id 7864A159BD for ; Wed, 25 Aug 1999 20:42:35 -0700 (PDT) (envelope-from aram@tibco.com) Received: from osgood.tibco.com (osgood.tibco.com [160.101.240.42]) by sammy.tibco.com (8.9.3/8.9.3) with ESMTP id UAA10767 for ; Wed, 25 Aug 1999 20:40:35 -0700 (PDT) Received: from venus.tibco.com (venus.tibco.com [160.101.240.40]) by osgood.tibco.com (8.9.3/8.9.3) with ESMTP id UAA21210 for ; Wed, 25 Aug 1999 20:41:05 -0700 (PDT) Received: from tibco.com ([160.101.22.192]) by venus.tibco.com (Netscape Messaging Server 3.6) with ESMTP id AAA62A5; Wed, 25 Aug 1999 20:36:12 -0700 Message-ID: <37C4B74A.9CE2EC1D@tibco.com> Date: Wed, 25 Aug 1999 20:40:58 -0700 From: "Aram Compeau" Organization: TIBCO X-Mailer: Mozilla 4.5 [en] (WinNT; I) X-Accept-Language: en MIME-Version: 1.0 Cc: Christopher Masto , scsi@FreeBSD.ORG Subject: Re: Seagate vs Quantum.. opinions? References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I'd have to second the opinion on the IBM drives. Definitely top o' my list as well. I'd recommend the IBM 18ES (moderate) line or their 18LZX line (high end) of SCSI drives. If you are limited to a choice between Seagate and Quantum, I'd take Seagate. I have had 'issues' with some Quantum drives failing in the past. Since that time, I have avoided them like the plague. Now, this was many years ago, so I have no idea if they are putting out great drives now. Also, this is obviously personal 'anecdotal' experience and not the result of some massive reliability survey. The only other data point I have is that several people I know have gotten burned using Quantum IDE drives recently (not a reflection on SCSI drives, but a general indication of quality). You didn't ask about it, but I'd have to say that I'd be EXTREMELY upset with a vendor that shipped me a substitute drive without my knowledge!! I've had good luck ordering SCSI drives from Hyper Microsystems, Inc. (reasonable shipping & good service): http://www.hypermicro.com/ Cheers, Aram Compeau Chuck Robey wrote: > On Wed, 25 Aug 1999, Christopher Masto wrote: > > > I have a situation where I asked for Seagate Barracudas and was > > shipped "QUANTUM ATLAS IV 9 WLS 0707" instead. Before I send them > > back, I want to make sure I'd be making the right decision. > > > > As people here have intimate knowledge of which drives FreeBSD gets > > along best with, and which ones have nasty quirks and firmware bugs, > > should I keep the Atlases or the Barracudas? > > Have you tried the IBM drives? I know you said Seagate and Quantum, but > the IBM drives seem (to me) to be, all at the same time, the cheapest, > coolest, quietest, and very nearly the fastest. Check the prices, if > you go to the places I go to, you're in for a shock. > > I am really starting to be an IBM booster (take a look at all the free > source code available at their site, if you need other reasons). Times > sure have changed, haven't they? They don't seem to be trying to be > such open monopolists these days. > > > -- > > Christopher Masto Senior Network Monkey NetMonger Communications > > chris@netmonger.net info@netmonger.net http://www.netmonger.net > > > > Free yourself, free your machine, free the daemon -- http://www.freebsd.org/ > > > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > > with "unsubscribe freebsd-scsi" in the body of the message > > > > ---------------------------+----------------------------------------------- > Chuck Robey | Interests include any kind of voice or data > chuckr@picnic.mat.net | communications topic, C programming, and Unix. > 213 Lakeside Drive Apt T-1 | > Greenbelt, MD 20770 | picnic.mat.net: FreeBSD/i386 > (301) 220-2114 | jaunt.mat.net : FreeBSD/Alpha > ---------------------------+----------------------------------------------- > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-scsi" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Wed Aug 25 22:54:21 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from feral.com (feral.com [192.67.166.1]) by hub.freebsd.org (Postfix) with ESMTP id 03D6C14C0A for ; Wed, 25 Aug 1999 22:54:18 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from semuta.feral.com (semuta [192.67.166.70]) by feral.com (8.8.7/8.8.7) with ESMTP id WAA25424; Wed, 25 Aug 1999 22:54:01 -0700 Date: Wed, 25 Aug 1999 22:53:59 -0700 (PDT) From: Matthew Jacob Reply-To: mjacob@feral.com To: Chuck Robey Cc: Christopher Masto , scsi@FreeBSD.ORG Subject: Re: Seagate vs Quantum.. opinions? In-Reply-To: Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > On Wed, 25 Aug 1999, Christopher Masto wrote: > > > I have a situation where I asked for Seagate Barracudas and was > > shipped "QUANTUM ATLAS IV 9 WLS 0707" instead. Before I send them > > back, I want to make sure I'd be making the right decision. > > > > As people here have intimate knowledge of which drives FreeBSD gets > > along best with, and which ones have nasty quirks and firmware bugs, > > should I keep the Atlases or the Barracudas? > > Have you tried the IBM drives? I know you said Seagate and Quantum, but > the IBM drives seem (to me) to be, all at the same time, the cheapest, > coolest, quietest, and very nearly the fastest. Check the prices, if > you go to the places I go to, you're in for a shock. > > I am really starting to be an IBM booster (take a look at all the free > source code available at their site, if you need other reasons). Times > sure have changed, haven't they? They don't seem to be trying to be > such open monopolists these days. Those who do not remember their past are condemned to repeat it, or some such...Don't kid yourself- they're still into world domination, just keeping a lower profile these days and letting Linus do the running for a while. IBM drives are okay, but like a lot of IBM stuff, sometimes do things gratuitously different. Also, they sometimes die in midlife- unlike Seagate drives which, past initial mortality, seem to go for years. > > > -- > > Christopher Masto Senior Network Monkey NetMonger Communications > > chris@netmonger.net info@netmonger.net http://www.netmonger.net > > > > Free yourself, free your machine, free the daemon -- http://www.freebsd.org/ > > > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > > with "unsubscribe freebsd-scsi" in the body of the message > > > > ---------------------------+----------------------------------------------- > Chuck Robey | Interests include any kind of voice or data > chuckr@picnic.mat.net | communications topic, C programming, and Unix. > 213 Lakeside Drive Apt T-1 | > Greenbelt, MD 20770 | picnic.mat.net: FreeBSD/i386 > (301) 220-2114 | jaunt.mat.net : FreeBSD/Alpha > ---------------------------+----------------------------------------------- > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-scsi" in the body of the message > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Wed Aug 25 23:50:34 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from sax.sax.de (sax.sax.de [193.175.26.33]) by hub.freebsd.org (Postfix) with ESMTP id CF04015420 for ; Wed, 25 Aug 1999 23:50:24 -0700 (PDT) (envelope-from j@uriah.heep.sax.de) Received: (from uucp@localhost) by sax.sax.de (8.8.8/8.8.8) with UUCP id IAA24800; Thu, 26 Aug 1999 08:50:20 +0200 (CEST) (envelope-from j@uriah.heep.sax.de) Received: (from j@localhost) by uriah.heep.sax.de (8.9.3/8.9.1) id IAA36964; Thu, 26 Aug 1999 08:28:12 +0200 (MET DST) (envelope-from j) Message-ID: <19990826082811.18950@uriah.heep.sax.de> Date: Thu, 26 Aug 1999 08:28:11 +0200 From: J Wunsch To: scsi@FreeBSD.ORG Cc: Christopher Masto Subject: Re: Seagate vs Quantum.. opinions? Reply-To: Joerg Wunsch References: <19990825225928.A24365@netmonger.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.88 In-Reply-To: <19990825225928.A24365@netmonger.net>; from Christopher Masto on Wed, Aug 25, 1999 at 10:59:28PM -0400 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 Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org As Christopher Masto wrote: > I have a situation where I asked for Seagate Barracudas and was > shipped "QUANTUM ATLAS IV 9 WLS 0707" instead. Before I send them > back, I want to make sure I'd be making the right decision. I think this decision can't be wrong (to return the Quantums since they aren't what you asked for). I can remember Kenneth's repeated statements that Seagate and IBM are those who make the drives with the best SCSI firmware, and this also matches my own experience (with the notable exception of Seagate Medalist, which are -- sorry -- crap). All i've seen so far from Quantum tells me that they've got a, ahem, very special understanding of the SCSI standard, to put it mildly. -- 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. ;-) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Thu Aug 26 5:57:49 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from medicus.medicusnet.de (medicus.medicusnet.de [195.226.123.18]) by hub.freebsd.org (Postfix) with ESMTP id 2761C14FB6 for ; Thu, 26 Aug 1999 05:57:29 -0700 (PDT) (envelope-from Stefan_Huerter@LU2.maus.de) Received: from medicus.medicusnet.de (root@medicus.medicusnet.de [192.168.1.1]) by medicus.medicusnet.de (8.8.8/8.8.7) with ESMTP id OAA10668 for ; Thu, 26 Aug 1999 14:55:05 +0200 Message-ID: <199908261021.p49134@lu2.maus.de> Date: Thu, 26 Aug 1999 10:21:00 +0200 From: Stefan_Huerter@LU2.maus.de (Stefan Huerter) Subject: Seagate vs Quantum.. opinions? Organization: Quark Ludwigshafen 2 +49-6237-920345 To: scsi@FreeBSD.ORG X-Gateway: Mauscon(0.9.4)/medicus.medicusnet.de, MausTausch X-Gateway-Admin: murphy@medicus.medicusnet.de X-MAUS-X-Line: R+ Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Guckux Christopher > I have a situation where I asked for Seagate Barracudas and was > shipped "QUANTUM ATLAS IV 9 WLS 0707" instead. Before I send them > back, I want to make sure I'd be making the right decision. I can only report my experiences from Germany: A few years ago I bought a Quantum ATLAS 2GB drive, it works fine, for a half year, than it get a head crash. My experience with Quantums service is terrible, I have to wait for more than 6 months for exchange of one of their "High-End High Quality server disks". 9 months later it dies once more (no head crash, it seems to be electrical), and it takes one time more, more than 6 months for Quantum to send me a new drive. Another fact: I was selling Seagate' Barracuda from the first hour and their first drives has really problems, about ~25% dies after a few weeks (the other running today also :), sending back, and it takes about 4 weeks to get a new one. These experiences with Seagate are continued until now. For me: No more Quantum. Bye Stefan To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Thu Aug 26 18: 7:58 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from mail.HiWAAY.net (fly.HiWAAY.net [208.147.154.56]) by hub.freebsd.org (Postfix) with ESMTP id 39C841540C for ; Thu, 26 Aug 1999 18:07:55 -0700 (PDT) (envelope-from dkelly@nospam.hiwaay.net) Received: from nospam.hiwaay.net (tnt8-216-180-14-29.dialup.HiWAAY.net [216.180.14.29]) by mail.HiWAAY.net (8.9.1a/8.9.0) with ESMTP id UAA19155; Thu, 26 Aug 1999 20:04:27 -0500 (CDT) Received: from localhost (localhost [127.0.0.1]) by nospam.hiwaay.net (8.9.3/8.9.3) with ESMTP id TAA26012; Thu, 26 Aug 1999 19:46:04 -0500 (CDT) (envelope-from dkelly@nospam.hiwaay.net) Message-Id: <199908270046.TAA26012@nospam.hiwaay.net> X-Mailer: exmh version 2.0.2 2/24/98 To: mjacob@feral.com Cc: scsi@FreeBSD.ORG From: David Kelly Subject: Re: Seagate vs Quantum.. opinions? In-reply-to: Message from Matthew Jacob of "Wed, 25 Aug 1999 22:53:59 PDT." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Thu, 26 Aug 1999 19:46:04 -0500 Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Matthew Jacob writes: > IBM drives are okay, but like a lot of IBM stuff, sometimes do things > gratuitously different. Speaking of which, "camcontrol defects -f block" and every other variation of "camcontrol defects" fails to list the bad blocks on my IBM drives. # camcontrol defects -f block error reading defect list: Input/output error # tail /var/log/messages Aug 26 19:40:22 nospam /kernel: (pass2:ncr0:0:0:0): extraneous data discarded. Aug 26 19:40:22 nospam /kernel: (pass2:ncr0:0:0:0): COMMAND FAILED (9 80) @0xc0a84400. Aug 26 19:40:22 nospam /kernel: (pass2:ncr0:0:0:0): extraneous data discarded. Aug 26 19:40:22 nospam /kernel: (pass2:ncr0:0:0:0): COMMAND FAILED (9 80) @0xc0a84400. Similar messages when using Adaptec SCSI cards. Has this been addressed in newer -stable, or -current? Am running -stable as of June 13. Have mentioned this problem before. Guess I should send-pr? -- David Kelly N4HHE, dkelly@nospam.hiwaay.net ===================================================================== The human mind ordinarily operates at only ten percent of its capacity -- the rest is overhead for the operating system. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Fri Aug 27 2:46:34 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from ren.detir.qld.gov.au (ns.detir.qld.gov.au [203.46.81.66]) by hub.freebsd.org (Postfix) with ESMTP id 164E715485 for ; Fri, 27 Aug 1999 02:46:28 -0700 (PDT) (envelope-from syssgm@detir.qld.gov.au) Received: by ren.detir.qld.gov.au; id TAA08360; Fri, 27 Aug 1999 19:44:45 +1000 (EST) Received: from ogre.detir.qld.gov.au(167.123.8.3) by ren.detir.qld.gov.au via smap (3.2) id xmaa08352; Fri, 27 Aug 99 19:44:34 +1000 Received: from atlas.detir.qld.gov.au (atlas.detir.qld.gov.au [167.123.8.9]) by ogre.detir.qld.gov.au (8.8.8/8.8.7) with ESMTP id TAA06901; Fri, 27 Aug 1999 19:44:34 +1000 (EST) Received: from nymph.detir.qld.gov.au (nymph.detir.qld.gov.au [167.123.10.10]) by atlas.detir.qld.gov.au (8.8.5/8.8.5) with ESMTP id TAA01420; Fri, 27 Aug 1999 19:44:33 +1000 (EST) Received: from nymph.detir.qld.gov.au (localhost.detir.qld.gov.au [127.0.0.1]) by nymph.detir.qld.gov.au (8.8.8/8.8.7) with ESMTP id TAA28444; Fri, 27 Aug 1999 19:44:32 +1000 (EST) (envelope-from syssgm@nymph.detir.qld.gov.au) Message-Id: <199908270944.TAA28444@nymph.detir.qld.gov.au> To: David Kelly Cc: freebsd-scsi@freebsd.org, syssgm@detir.qld.gov.au Subject: Re: Seagate vs Quantum.. opinions? References: <199908270046.TAA26012@nospam.hiwaay.net> In-Reply-To: <199908270046.TAA26012@nospam.hiwaay.net> from David Kelly at "Thu, 26 Aug 1999 19:46:04 -0500" Date: Fri, 27 Aug 1999 19:44:32 +1000 From: Stephen McKay Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Thursday, 26th August 1999, David Kelly wrote: >Matthew Jacob writes: >> IBM drives are okay, but like a lot of IBM stuff, sometimes do things >> gratuitously different. > >Speaking of which, "camcontrol defects -f block" and every other >variation of "camcontrol defects" fails to list the bad blocks on my >IBM drives. >Similar messages when using Adaptec SCSI cards. Oh! I've been blaming my ncr SCSI card! (Well, the driver for it, at least.) I'm sure everyone complaining about not being able to read defects lists is using an ncr based card. I've got some non-ibm disks I can temporarily hook up. I'll try them too. And I'll try an aha-1540 too just for kicks. Stephen. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Fri Aug 27 2:52:58 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from ren.detir.qld.gov.au (ns.detir.qld.gov.au [203.46.81.66]) by hub.freebsd.org (Postfix) with ESMTP id 62C4915485 for ; Fri, 27 Aug 1999 02:52:53 -0700 (PDT) (envelope-from syssgm@detir.qld.gov.au) Received: by ren.detir.qld.gov.au; id TAA08464; Fri, 27 Aug 1999 19:50:45 +1000 (EST) Received: from ogre.detir.qld.gov.au(167.123.8.3) by ren.detir.qld.gov.au via smap (3.2) id xma008458; Fri, 27 Aug 99 19:50:36 +1000 Received: from atlas.detir.qld.gov.au (atlas.detir.qld.gov.au [167.123.8.9]) by ogre.detir.qld.gov.au (8.8.8/8.8.7) with ESMTP id TAA06997; Fri, 27 Aug 1999 19:50:35 +1000 (EST) Received: from nymph.detir.qld.gov.au (nymph.detir.qld.gov.au [167.123.10.10]) by atlas.detir.qld.gov.au (8.8.5/8.8.5) with ESMTP id TAA01622; Fri, 27 Aug 1999 19:50:35 +1000 (EST) Received: from nymph.detir.qld.gov.au (localhost.detir.qld.gov.au [127.0.0.1]) by nymph.detir.qld.gov.au (8.8.8/8.8.7) with ESMTP id TAA28541; Fri, 27 Aug 1999 19:50:34 +1000 (EST) (envelope-from syssgm@nymph.detir.qld.gov.au) Message-Id: <199908270950.TAA28541@nymph.detir.qld.gov.au> To: Matthew Jacob Cc: freebsd-scsi@freebsd.org, syssgm@detir.qld.gov.au Subject: Re: Seagate vs Quantum.. opinions? References: In-Reply-To: from Matthew Jacob at "Wed, 25 Aug 1999 22:53:59 -0700" Date: Fri, 27 Aug 1999 19:50:34 +1000 From: Stephen McKay Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Wednesday, 25th August 1999, Matthew Jacob wrote: >IBM drives are okay, but like a lot of IBM stuff, sometimes do things >gratuitously different. Also, they sometimes die in midlife- unlike >Seagate drives which, past initial mortality, seem to go for years. When people vouch for their favourite drives I would like them to also give an estimate of how many drives they are basing their opinions on. For example, I've got 3 IBM SCSI disks. Love them. Quiet, low heat, fairly fast. I've got some really old Seagates. Love them (well, they used to be fast for their day). I've got some not-quite-so-old Seagates. Hate them. Noisy, hot. But the point is that this is only 10 drives total that I'm basing all this on. (This isn't counting a fair collection of really, really old hardware thrown at me instead of the bin). So, how many drives have you watched live and die? Stephen. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Fri Aug 27 7:59:41 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from proteus.eclipse.net.uk (proteus.eclipse.net.uk [195.188.32.118]) by hub.freebsd.org (Postfix) with ESMTP id 6C44A15E41 for ; Fri, 27 Aug 1999 07:59:38 -0700 (PDT) (envelope-from stuart@eclipse.net.uk) Received: from eclipse.net.uk (elara.eclipse.net.uk [195.188.32.31]) by proteus.eclipse.net.uk (Postfix) with ESMTP id C7A8F9B13; Fri, 27 Aug 1999 15:59:15 +0100 (BST) Message-ID: <37C6A840.1DF131AA@eclipse.net.uk> Date: Fri, 27 Aug 1999 16:01:20 +0100 From: Stuart Henderson Organization: Eclipse Networking Ltd. X-Mailer: Mozilla 4.61 [en] (WinNT; I) X-Accept-Language: en-GB MIME-Version: 1.0 To: Stephen McKay Cc: David Kelly , freebsd-scsi@FreeBSD.ORG Subject: Re: Seagate vs Quantum.. opinions? References: <199908270046.TAA26012@nospam.hiwaay.net> <199908270944.TAA28444@nymph.detir.qld.gov.au> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > Oh! I've been blaming my ncr SCSI card! (Well, the driver for it, > at least.) I'm sure everyone complaining about not being able to read > defects lists is using an ncr based card. I can't read the defects list on HP-branded seagate and (quantum? not sure) 9gb drives with ncr895 (on 3.2-release). To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Fri Aug 27 9:26:56 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from feral.com (feral.com [192.67.166.1]) by hub.freebsd.org (Postfix) with ESMTP id 389E91553A for ; Fri, 27 Aug 1999 09:26:50 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from semuta.feral.com (semuta [192.67.166.70]) by feral.com (8.8.7/8.8.7) with ESMTP id JAA31429; Fri, 27 Aug 1999 09:25:27 -0700 Date: Fri, 27 Aug 1999 09:25:25 -0700 (PDT) From: Matthew Jacob Reply-To: mjacob@feral.com To: Stephen McKay Cc: freebsd-scsi@freebsd.org Subject: Re: Seagate vs Quantum.. opinions? In-Reply-To: <199908270950.TAA28541@nymph.detir.qld.gov.au> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > > >IBM drives are okay, but like a lot of IBM stuff, sometimes do things > >gratuitously different. Also, they sometimes die in midlife- unlike > >Seagate drives which, past initial mortality, seem to go for years. > > When people vouch for their favourite drives I would like them to also > give an estimate of how many drives they are basing their opinions on. > > For example, I've got 3 IBM SCSI disks. Love them. Quiet, low heat, > fairly fast. I've got some really old Seagates. Love them (well, they > used to be fast for their day). I've got some not-quite-so-old Seagates. > Hate them. Noisy, hot. But the point is that this is only 10 drives > total that I'm basing all this on. (This isn't counting a fair collection > of really, really old hardware thrown at me instead of the bin). > > So, how many drives have you watched live and die? Over my entire career? 1000s.... But it's a fair question- Less than 100 for recent memory. But this also should be qualified by environment. Those who watch today over 100s of drives will have them in a room with reasonable power and cooling. The less than 100 drives I currently have are in > 85 degree F year round, flakey power and dust bad enough that anyone with allergies can't stay in the room more than 30 seconds. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Fri Aug 27 9:38:39 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from feral.com (feral.com [192.67.166.1]) by hub.freebsd.org (Postfix) with ESMTP id D7D0A1554E for ; Fri, 27 Aug 1999 09:38:28 -0700 (PDT) (envelope-from mjacob@feral.com) Received: from semuta.feral.com (semuta [192.67.166.70]) by feral.com (8.8.7/8.8.7) with ESMTP id JAA31510; Fri, 27 Aug 1999 09:37:40 -0700 Date: Fri, 27 Aug 1999 09:37:39 -0700 (PDT) From: Matthew Jacob Reply-To: mjacob@feral.com To: Stephen McKay Cc: David Kelly , freebsd-scsi@FreeBSD.ORG Subject: Re: Seagate vs Quantum.. opinions? In-Reply-To: <199908270944.TAA28444@nymph.detir.qld.gov.au> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > On Thursday, 26th August 1999, David Kelly wrote: > > >Matthew Jacob writes: > >> IBM drives are okay, but like a lot of IBM stuff, sometimes do things > >> gratuitously different. > > > >Speaking of which, "camcontrol defects -f block" and every other > >variation of "camcontrol defects" fails to list the bad blocks on my > >IBM drives. > > >Similar messages when using Adaptec SCSI cards. > > Oh! I've been blaming my ncr SCSI card! (Well, the driver for it, at least.) > I'm sure everyone complaining about not being able to read defects lists is > using an ncr based card. I've got some non-ibm disks I can temporarily hook > up. I'll try them too. And I'll try an aha-1540 too just for kicks. If it's a problem with other than the drive, send-pr as appropriate or it won't get fixed (no snickers from the audience, please...) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Fri Aug 27 20: 4:33 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from mail.HiWAAY.net (fly.HiWAAY.net [208.147.154.56]) by hub.freebsd.org (Postfix) with ESMTP id 3C20814C08 for ; Fri, 27 Aug 1999 20:04:30 -0700 (PDT) (envelope-from dkelly@nospam.hiwaay.net) Received: from nospam.hiwaay.net (tnt4-208-166-127-25.dialup.HiWAAY.net [208.166.127.25]) by mail.HiWAAY.net (8.9.1a/8.9.0) with ESMTP id WAA18932; Fri, 27 Aug 1999 22:04:27 -0500 (CDT) Received: from localhost (localhost [127.0.0.1]) by nospam.hiwaay.net (8.9.3/8.9.3) with ESMTP id WAA60668; Fri, 27 Aug 1999 22:02:08 -0500 (CDT) (envelope-from dkelly@nospam.hiwaay.net) Message-Id: <199908280302.WAA60668@nospam.hiwaay.net> X-Mailer: exmh version 2.0.2 2/24/98 To: Stephen McKay Cc: David Kelly , freebsd-scsi@freebsd.org From: David Kelly Subject: Re: Seagate vs Quantum.. opinions? In-reply-to: Message from Stephen McKay of "Fri, 27 Aug 1999 19:44:32 +1000." <199908270944.TAA28444@nymph.detir.qld.gov.au> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Fri, 27 Aug 1999 22:02:08 -0500 Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Stephen McKay writes: > >Speaking of which, "camcontrol defects -f block" and every other > >variation of "camcontrol defects" fails to list the bad blocks on my > >IBM drives. > > >Similar messages when using Adaptec SCSI cards. > > Oh! I've been blaming my ncr SCSI card! (Well, the driver for it, at least. ) > I'm sure everyone complaining about not being able to read defects lists is > using an ncr based card. I've got some non-ibm disks I can temporarily hook > up. I'll try them too. And I'll try an aha-1540 too just for kicks. None of these work for me, 3 systems, all with different 3.2-STABLE: IBM DCAS (4.3G) on early 2940 (7860 based?) IBM DCHS (? I forgot, but its 9G) on Symbios '875 IBM DDRS (9G) on 7890 (Asus P2S MB) I've typed up what little I know into send-pr. -- David Kelly N4HHE, dkelly@nospam.hiwaay.net ===================================================================== The human mind ordinarily operates at only ten percent of its capacity -- the rest is overhead for the operating system. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Fri Aug 27 21:27: 6 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from panzer.kdm.org (panzer.kdm.org [216.160.178.169]) by hub.freebsd.org (Postfix) with ESMTP id 7C8DD1513C for ; Fri, 27 Aug 1999 21:26:56 -0700 (PDT) (envelope-from ken@panzer.kdm.org) Received: (from ken@localhost) by panzer.kdm.org (8.9.3/8.9.1) id WAA93707; Fri, 27 Aug 1999 22:25:09 -0600 (MDT) (envelope-from ken) Message-Id: <199908280425.WAA93707@panzer.kdm.org> Subject: Re: Seagate vs Quantum.. opinions? In-Reply-To: <199908280302.WAA60668@nospam.hiwaay.net> from David Kelly at "Aug 27, 1999 10:02:08 pm" To: dkelly@hiwaay.net (David Kelly) Date: Fri, 27 Aug 1999 22:25:09 -0600 (MDT) Cc: syssgm@detir.qld.gov.au (Stephen McKay), freebsd-scsi@FreeBSD.ORG From: "Kenneth D. Merry" X-Mailer: ELM [version 2.4ME+ PL54 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org David Kelly wrote... > Stephen McKay writes: > > >Speaking of which, "camcontrol defects -f block" and every other > > >variation of "camcontrol defects" fails to list the bad blocks on my > > >IBM drives. > > > > >Similar messages when using Adaptec SCSI cards. > > > > Oh! I've been blaming my ncr SCSI card! (Well, the driver for it, at least. > ) > > I'm sure everyone complaining about not being able to read defects lists is > > using an ncr based card. I've got some non-ibm disks I can temporarily hook > > up. I'll try them too. And I'll try an aha-1540 too just for kicks. > > None of these work for me, 3 systems, all with different 3.2-STABLE: > > IBM DCAS (4.3G) on early 2940 (7860 based?) > IBM DCHS (? I forgot, but its 9G) on Symbios '875 > IBM DDRS (9G) on 7890 (Asus P2S MB) > > I've typed up what little I know into send-pr. It works for me with a DDRS drive on a 2940UW (7880-based) board: # uname -rs FreeBSD 3.2-STABLE # camcontrol inquiry da1 pass1: Fixed Direct Access SCSI-2 device pass1: Serial Number RE2B9804 pass1: 20.000MB/s transfers (20.000MHz, offset 15), Tagged Queueing Enabled # camcontrol defects da1 -f phys -G Got 4 defects: 189:6:72 189:6:73 189:6:74 189:6:75 The stable build is from earlier this month (August). There shouldn't be any difference in behavior in this regard between a 7880 and 7890. I'd like to see you try the physical defect format with one of your drives on an Adaptec controller. In your PR, you specified block format, which I've only seen work for Quantum disks. (Not saying it doesn't work on others, but I know it usually doesn't work for IBM or Seagate disks.) Physical sector format usually works, though. You also didn't specify the PLIST or GLIST. You should at least try specifying the PLIST. You should also use the -v switch to camcontrol so you'll hopefully get sense information if the command fails. The NCR driver is known to be a little flaky around the edges sometimes, so I'm not surprised it might complain. Unfortunately, complaints from the NCR driver don't help much, because the only people who know how to decipher them are Stefan and Gerard, and they only pop up occasionally. I'll respond to the PR in a minute, so this stuff gets in the database. The bottom line is you'll have to provide more info before the problem can be fixed. Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Sat Aug 28 0:38:40 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from panzer.kdm.org (panzer.kdm.org [216.160.178.169]) by hub.freebsd.org (Postfix) with ESMTP id 6672C14F0D for ; Sat, 28 Aug 1999 00:38:36 -0700 (PDT) (envelope-from ken@panzer.kdm.org) Received: (from ken@localhost) by panzer.kdm.org (8.9.3/8.9.1) id BAA94296; Sat, 28 Aug 1999 01:37:40 -0600 (MDT) (envelope-from ken) Message-Id: <199908280737.BAA94296@panzer.kdm.org> Subject: Re: Seagate vs Quantum.. opinions? In-Reply-To: from Gerard Roudier at "Aug 28, 1999 09:25:33 am" To: groudier@club-internet.fr (Gerard Roudier) Date: Sat, 28 Aug 1999 01:37:39 -0600 (MDT) Cc: dkelly@hiwaay.net, syssgm@detir.qld.gov.au, freebsd-scsi@FreeBSD.ORG From: "Kenneth D. Merry" X-Mailer: ELM [version 2.4ME+ PL54 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Gerard Roudier wrote... > On Fri, 27 Aug 1999, Kenneth D. Merry wrote: > > David Kelly wrote... > > > None of these work for me, 3 systems, all with different 3.2-STABLE: > > > > > > IBM DCAS (4.3G) on early 2940 (7860 based?) > > > IBM DCHS (? I forgot, but its 9G) on Symbios '875 > > > IBM DDRS (9G) on 7890 (Asus P2S MB) > > > > > > I've typed up what little I know into send-pr. > > > > It works for me with a DDRS drive on a 2940UW (7880-based) board: [ ... ] > > I'd like to see you try the physical defect format with one of your drives > > on an Adaptec controller. In your PR, you specified block format, which > > I've only seen work for Quantum disks. (Not saying it doesn't work on > > others, but I know it usually doesn't work for IBM or Seagate disks.) > > > > Physical sector format usually works, though. > > > > You also didn't specify the PLIST or GLIST. You should at least try > > specifying the PLIST. You should also use the -v switch to camcontrol so > > you'll hopefully get sense information if the command fails. > > > > The NCR driver is known to be a little flaky around the edges sometimes, so > > I'm not surprised it might complain. Unfortunately, complaints from the > > NCR driver don't help much, because the only people who know how to > > decipher them are Stefan and Gerard, and they only pop up occasionally. > > > > I'll respond to the PR in a minute, so this stuff gets in the database. > > The bottom line is you'll have to provide more info before the problem can > > be fixed. > Hi guys, > > The problem that has been reported about read defect failure using > SYM53C8XX chips is due to the device reporting more data than expected. > Call it a data overrun condition detected by the SIM, if you did prefer > so. Thanks for the description! > The reason can be one of the following: > > - SCSI device that does not follow the transfer size field specified in > the SCSI command. > - Application that provide a too small data buffer. > > So, the error condition should not depend on the controller/driver being > used. At most, it may be reported differently. > > If you have the source of the application (camcontrol), you may try the > following: > > - Check that it provides a right sized data buffer and fix it if it does > not so. > - Make it use a LARGE data buffer since modern LARGE disks may have LONG > defect lists. camcontrol uses a 65000 byte buffer for the defect list data. With the 10-byte read defect data command, it can be increased to at most 65536 bytes, because the transfer length field is only two bytes long. In any case, with 65000 bytes you can hold 8124 defects, which is probably far more than are on his disks. There is a 12 byte read defect data command in the SCSI-3 spec, but who knows whether this drive will support it? In any case, David, I'd say try the following things, in light of what Gerard said: - first, try using the -v switch, -f phys (instead of block format, since only Quantum disks seem to support it, and the SCSI-2 spec says: "NOTE 110 The use of the block format is not recommended. There is no universal model that sensibly defines the meaning of the logical block address of a defect. In the usual case, a defect that has been reassigned no longer has a logical block address.") and -PG. - If that doesn't work, try increasing the dlist_length parameter in readdefects() in src/sbin/camcontrol/camcontrol.c to 65536. - If that doesn't work, you can try using the 12 byte read defect data command. There are definitions for it in /usr/include/cam/scsi/scsi_da.h. On second thought, you won't gain anything by doing that. Right now, we limit transfers to and from the kernel via the passthrough interface to 64K. (It could be increased to 128K, but the aha driver/cards don't support it, and we haven't yet implemented buffer chaining or a way to dynamically figure out the maximum transfer size of a given command path.) It would also be helpful to see what happens on an Adaptec controller, as this could be the result of a bug in the NCR driver. Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Sat Aug 28 13:49:36 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from metriclient-1.uoregon.edu (metriclient-1.uoregon.edu [128.223.172.1]) by hub.freebsd.org (Postfix) with ESMTP id 10D4914CBF for ; Sat, 28 Aug 1999 13:49:31 -0700 (PDT) (envelope-from gurney_j@efn.org) Received: (from jmg@localhost) by metriclient-1.uoregon.edu (8.9.1/8.8.7) id NAA02784; Sat, 28 Aug 1999 13:48:25 -0700 (PDT) Message-ID: <19990828134825.64785@hydrogen.fircrest.net> Date: Sat, 28 Aug 1999 13:48:25 -0700 From: John-Mark Gurney To: "Kenneth D. Merry" Cc: David Kelly , Stephen McKay , freebsd-scsi@FreeBSD.ORG Subject: Re: Seagate vs Quantum.. opinions? References: <199908280302.WAA60668@nospam.hiwaay.net> <199908280425.WAA93707@panzer.kdm.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.69 In-Reply-To: <199908280425.WAA93707@panzer.kdm.org>; from Kenneth D. Merry on Fri, Aug 27, 1999 at 10:25:09PM -0600 Reply-To: John-Mark Gurney Organization: Cu Networking X-Operating-System: FreeBSD 3.0-RELEASE i386 X-PGP-Fingerprint: B7 EC EF F8 AE ED A7 31 96 7A 22 B3 D8 56 36 F4 X-Files: The truth is out there X-URL: http://resnet.uoregon.edu/~gurney_j/ Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Kenneth D. Merry scribbled this message on Aug 27: > I'd like to see you try the physical defect format with one of your drives > on an Adaptec controller. In your PR, you specified block format, which > I've only seen work for Quantum disks. (Not saying it doesn't work on > others, but I know it usually doesn't work for IBM or Seagate disks.) I was wondering why one of my drives IMPRIMIS 94601-15 4614 wasn't returning the grown list, so I switched to -f phys and now it also returns the defect information... all the drives below return defect info, the Imprimis is the only one that doesn't support -f block: at scbus0 target 1 lun 0 (pass0,da0) at scbus0 target 2 lun 0 (pass1,da3) at scbus0 target 3 lun 0 (pass2,da6) at scbus0 target 4 lun 0 (pass3,da5) at scbus1 target 0 lun 0 (pass5,da2) at scbus1 target 1 lun 0 (pass6,da1) at scbus1 target 2 lun 0 (pass7,da4) the fujitsu and imprimis drives are actually scsi1 drives.. controlers: bt0: rev 0x00 int a irq 15 on pci0.8.0 bt0: BT-946C FW Rev. 4.28D Narrow SCSI Host Adapter, SCSI ID 7, 100 CCBs adv0: rev 0x02 int a irq 12 on pci0.10.0 adv0: AdvanSys Ultra SCSI Host Adapter, SCSI ID 7, queue depth 240 -- John-Mark Gurney Voice: +1 541 684 8449 Cu Networking P.O. Box 5693, 97405 "The soul contains in itself the event that shall presently befall it. The event is only the actualizing of its thought." -- Ralph Waldo Emerson To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Sat Aug 28 14:34:31 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from verdi.nethelp.no (verdi.nethelp.no [158.36.41.162]) by hub.freebsd.org (Postfix) with SMTP id 289861569C for ; Sat, 28 Aug 1999 14:34:16 -0700 (PDT) (envelope-from sthaug@nethelp.no) Received: (qmail 47461 invoked by uid 1001); 28 Aug 1999 21:32:53 +0000 (GMT) To: ken@kdm.org Cc: groudier@club-internet.fr, dkelly@hiwaay.net, syssgm@detir.qld.gov.au, freebsd-scsi@FreeBSD.ORG Subject: Re: Seagate vs Quantum.. opinions? From: sthaug@nethelp.no In-Reply-To: Your message of "Sat, 28 Aug 1999 01:37:39 -0600 (MDT)" References: <199908280737.BAA94296@panzer.kdm.org> X-Mailer: Mew version 1.05+ on Emacs 19.34.2 Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Date: Sat, 28 Aug 1999 23:32:53 +0200 Message-ID: <47459.935875973@verdi.nethelp.no> Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org > In any case, David, I'd say try the following things, in light of what > Gerard said: > > - first, try using the -v switch, -f phys (instead of block format, since > only Quantum disks seem to support it, and the SCSI-2 spec says: "NOTE > 110 The use of the block format is not recommended. There is no universal > model that sensibly defines the meaning of the logical block address of > a defect. In the usual case, a defect that has been reassigned no longer > has a logical block address.") and -PG. Using -v results in "CAM status is 0" here. > - If that doesn't work, try increasing the dlist_length parameter in > readdefects() in src/sbin/camcontrol/camcontrol.c to 65536. Are you sure you mean 65536? If I try 65536, it *seems* to work (no error message), but all I get is "Got 0 defects". But I'm wondering if 65536 is being interpreted as 0 (because this is a 2 byte field). I tried a slightly smaller number (65532), and got the expected error messages. I don't believe this is a result of a defect larger than 65536, since it happens with several disks here, some of them pretty new. > It would also be helpful to see what happens on an Adaptec controller, as > this could be the result of a bug in the NCR driver. It works just fine on an Adaptec controller, no problem retrieving defect list from IBM disks using "camcontrol defects -f phys -P". With an NCR based controller, the kernel logs (pass0:ncr0:0:2:0): extraneous data discarded. (pass0:ncr0:0:2:0): COMMAND FAILED (9 0) @0xc086c200. and camcontrol says "error reading defect list: Input/output error". I think we need the NCR driver experts. Steinar Haug, Nethelp consulting, sthaug@nethelp.no To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message From owner-freebsd-scsi Sat Aug 28 14:38:47 1999 Delivered-To: freebsd-scsi@freebsd.org Received: from panzer.kdm.org (panzer.kdm.org [216.160.178.169]) by hub.freebsd.org (Postfix) with ESMTP id D81A414FDB for ; Sat, 28 Aug 1999 14:38:40 -0700 (PDT) (envelope-from ken@panzer.kdm.org) Received: (from ken@localhost) by panzer.kdm.org (8.9.3/8.9.1) id PAA01880; Sat, 28 Aug 1999 15:38:21 -0600 (MDT) (envelope-from ken) Message-Id: <199908282138.PAA01880@panzer.kdm.org> Subject: Re: Seagate vs Quantum.. opinions? In-Reply-To: <47459.935875973@verdi.nethelp.no> from "sthaug@nethelp.no" at "Aug 28, 1999 11:32:53 pm" To: sthaug@nethelp.no Date: Sat, 28 Aug 1999 15:38:21 -0600 (MDT) Cc: groudier@club-internet.fr, dkelly@hiwaay.net, syssgm@detir.qld.gov.au, freebsd-scsi@FreeBSD.ORG From: "Kenneth D. Merry" X-Mailer: ELM [version 2.4ME+ PL54 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-scsi@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org sthaug@nethelp.no wrote... > > In any case, David, I'd say try the following things, in light of what > > Gerard said: > > > > - first, try using the -v switch, -f phys (instead of block format, since > > only Quantum disks seem to support it, and the SCSI-2 spec says: "NOTE > > 110 The use of the block format is not recommended. There is no universal > > model that sensibly defines the meaning of the logical block address of > > a defect. In the usual case, a defect that has been reassigned no longer > > has a logical block address.") and -PG. > > Using -v results in "CAM status is 0" here. Hmm, so there isn't a SCSI error, and the controller driver didn't pass an error back either. > > - If that doesn't work, try increasing the dlist_length parameter in > > readdefects() in src/sbin/camcontrol/camcontrol.c to 65536. > > Are you sure you mean 65536? If I try 65536, it *seems* to work (no error > message), but all I get is "Got 0 defects". But I'm wondering if 65536 is > being interpreted as 0 (because this is a 2 byte field). I tried a slightly > smaller number (65532), and got the expected error messages. Oops, it is a 2-byte field. So increasing it to 65536 would probably cause problems. > I don't believe this is a result of a defect larger than 65536, since it > happens with several disks here, some of them pretty new. I think you're probably right. > > It would also be helpful to see what happens on an Adaptec controller, as > > this could be the result of a bug in the NCR driver. > > It works just fine on an Adaptec controller, no problem retrieving defect > list from IBM disks using "camcontrol defects -f phys -P". With an NCR > based controller, the kernel logs > > (pass0:ncr0:0:2:0): extraneous data discarded. > (pass0:ncr0:0:2:0): COMMAND FAILED (9 0) @0xc086c200. > > and camcontrol says "error reading defect list: Input/output error". > > I think we need the NCR driver experts. I agree. This looks like an NCR driver issue. (The fact that the Adaptec driver works okay seems to point in that direction.) Ken -- Kenneth Merry ken@kdm.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message