Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 25 Feb 1999 16:59:41 -0500 (EST)
From:      Andrew Gallatin <gallatin@cs.duke.edu>
To:        Darryl Okahata <darrylo@sr.hp.com>
Cc:        scsi@FreeBSD.ORG
Subject:   Re: dual-channel U2W scsi performance 
Message-ID:  <14037.50689.119860.239392@grasshopper.cs.duke.edu>
In-Reply-To: <199902252003.MAA06761@mina.sr.hp.com>
References:  <14035.5458.71518.652907@grasshopper.cs.duke.edu> <199902252003.MAA06761@mina.sr.hp.com>

next in thread | previous in thread | raw e-mail | index | archive | help

Darryl Okahata writes:
 > Andrew Gallatin <gallatin@cs.duke.ed> wrote:
 > 
 > > Justin T. Gibbs writes:
 > >  > 
 > >  > There must be something wrong with your cables.  I've had several instance
 > > s
 > >  > where a loose connector pin caused intermittent parity-errors.  If both
 > >  > the driver and the end device are reporting errors, they can't be wrong.
 > >  > I've tested SE operation on the aic7896, so I know that it can work
 > >  > with the current driver.
 > > 
 > > Before I turned off parity in scsi-select, I tried all possible
 > > combinations of cabling (my setup is motherboard connecter -> internal
 > > cable -> external connector-> external cable -> box w/2 4G cheetahs ->
 > > active terminator), I switched out both cables, the external
 > > connector, the terminator & the box w/2 cheetahs.. No combination
 > > worked on the second channel.  All combinations worked on the first
 > > channel.  (by worked, I mean probed w/o parity errors)
 > 
 >      How long is the total cable length, starting at the motherboard?
 > At 20MHz, the max cable length is something like 1.5 meters, or a bit
 > less than 5 feet.  Also, you are using high-quality external cables,
 > right?

I'd estimate the total cable length at <= 1m.  The cables are good
quality, and the internal cable & external connector were actually
temporarily borrowed from the secondary channel of a DPT raid setup
(where the external connection is to an identical cable & identical
box with 2 identical cheetahs). I trust the cables..

------------------------------------------------------------------------------
Andrew Gallatin, Sr Systems Programmer	http://www.cs.duke.edu/~gallatin
Duke University				Email: gallatin@cs.duke.edu
Department of Computer Science		Phone: (919) 660-6590


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-scsi" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?14037.50689.119860.239392>