*BSD News Article 73406


Return to BSD News archive

Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.ecn.uoknor.edu!qns3.qns.net!imci4!newsfeed.internetmci.com!usenet.eel.ufl.edu!warwick!yama.mcc.ac.uk!viking.ucsalf.ac.uk!not-for-mail
From: mark@plato.ucsalf.ac.uk (Mark Powell)
Newsgroups: comp.periphs.scsi,list.freebsd.scsi,list.freebsd.questions,comp.unix.bsd.freebsd.misc
Subject: Does Adaptec 7880 Ultra support simultaneous wide and narrow transfers?
Date: 11 Jul 1996 10:14:32 +0100
Organization: Computer Services Unit, University College Salford, Salford, Manchester, UK
Lines: 67
Message-ID: <4s2glo$ee@plato.ucsalf.ac.uk>
NNTP-Posting-Host: plato.ucsalf.ac.uk
Xref: euryale.cc.adfa.oz.au comp.periphs.scsi:55516 comp.unix.bsd.freebsd.misc:23301

Hi,
  I have a motherboard with a built in 7880 Ultra with a narrow and a wide connector
surface mounted. I have a Conner CFP4207S on the narrow channel with TERM/PWR enabled
and a Conner CFP4207W on the wide channel with TERM/PWR enabled. I wanted to move my
FreeBSD-2.1-stable filesystem from the narrow disk to the wide. I assumed that I could
simply copy all the data over with (narrow on sd0, wide on sd1; with 512k on board
data buffer):

$ dd if=/dev/sd0c of=/dev/sd1c bs=512k

However, this only yields data transfer rates in the 200K/s range. I've tried both
larger and smaller buffer sizes with no apparent increase. I'm beginning to wonder
if the 7870 chipset is performing these transfers simultaneously. I would expect
such a command to push both drives at full speed with the drive access lights on
solidly. However, the drive lights are alternating off/no for around 1 sec. periods.
Am I expecting the wrong thing here?
If I turn on WIDE negotiation for the W drive, the kernel enables 16bit transfers:

ahc0 <Adaptec aic7880 Ultra SCSI host adapter> rev 0 int a irq 11 on
 pci0:18
 mapreg[10] type=1 addr=00006000 size=0100.
 mapreg[14] type=0 addr=f2000000 size=1000.
ahc0: BurstLen = 8DWDs, Latency Timer = 32PCLKS
ahc0: Reading SEEPROM...done.
ahc0: aic7880 Wide Channel, SCSI Id=7, 16 SCBs
Reseting Channel A
ahc0: Downloading Sequencer Program...Done
ahc0: Probing channel A
ahc0: target 0 synchronous at 10.0MHz, offset = 0xf
(ahc0:0:0): "CONNER CFP4207S  4.28GB 1524" type 0 fixed SCSI 2
sd0(ahc0:0:0): Direct-Access 4096MB (8388608 512 byte sectors)
sd0(ahc0:0:0): with 3999 cyls, 20 heads, and an average 104 sectors/
track
ahc0: target 1 using 16Bit transfers
ahc0: target 1 synchronous at 10.0MHz, offset = 0x8
(ahc0:1:0): "CONNER CFP4207W  4.28GB 1524" type 0 fixed SCSI 2
sd1(ahc0:1:0): Direct-Access 4096MB (8388608 512 byte sectors)
sd1(ahc0:1:0): with 3999 cyls, 20 heads, and an average 104 sectors/
track
ahc0: target 2 synchronous at 10.0MHz, offset = 0x8
(ahc0:2:0): "HP C1533A 9503" type 1 removable SCSI 2
st0(ahc0:2:0): Sequential-Access density code 0x24, variable blocks,
 write-enabled
ahc0:A:4: refuses WIDE negotiation.  Using 8bit transfers
ahc0: target 4 synchronous at 4.4MHz, offset = 0xf
(ahc0:4:0): "TOSHIBA CD-ROM XM-3701TA 0236" type 5 removable SCSI 2
cd0(ahc0:4:0): CD-ROM 
cd0(ahc0:4:0): NOT READY asc:4,1
cd0(ahc0:4:0):  Logical unit is in process of becoming ready
can't get the size

However, the same command causes the following SCSI errors on the console:

sd0(ahc0:0:0): timed out in dataout phase, SCSISIGI == 0x48
ahc0: Issued Channel A Bus Reset #2. 2 SCBs aborted
sd0(ahc0:0:0): UNIT ATTENTION asc:29,0
sd0(ahc0:0:0):  Power on, reset, or bus device reset occurred field 
replaceable unit: 14

This effectively hangs the machine, requiring a reset. 
Whats wrong here?
-- 
Mark Powell - Senior Network Technician - Room: C806
Computer Services Unit, University College Salford, Salford, Manchester, UK.
Tel:	+44 161 745 3376	Fax:	+44 161 736 3596
Email:	mark@ucsalf.ac.uk	finger mark@ucsalf.ac.uk (for PGP key)
<A HREF="http://www.ucsalf.ac.uk/~mark/">Home Page</A>