[3222] in linux-scsi channel archive
Re: Mylex 960?
daemon@ATHENA.MIT.EDU (Justin Brown W.)
Thu Feb 5 21:41:19 1998
Date: Thu, 5 Feb 1998 14:43:26 -0600 (CST)
From: "Justin Brown W." <jbrown@tanstaafl.busprod.com>
To: "Leonard N. Zubkoff" <lnz@dandelion.com>
cc: linux-scsi@vger.rutgers.edu
In-Reply-To: <199802051949.LAA16436@dandelion.com>
On Thu, 5 Feb 1998, Leonard N. Zubkoff wrote:
> While I do believe the DAC960 is quick, that sounds like a bit too quick. If
> NT actually read all 18GB, that would imply an I/O rate of about 600MB/second.
> There's simply no way that two Wide UltraSCSI channels can do that, let alone
> the disks. Not to mention that there isn't enough PCI or main memory
> bandwidth to sustain that.
>
> Leonard
>
Here's the scoop:
Everex Dual PPro 200 w/ 128 megs of ram
Mylex 960 dual channel wide scsi-3 raid only controller
Two Seagate 9.1 gig 7200 rpm barracudas in a raid 0 configuration
Dos 6.0 boot disk
format c /u
Takes 28 seconds by my watch.
Weither the bus can handle it, the controller can handle it, or if the
hand of god reached down, brushed the machine and a miracle occured, it
took 28 seconds. I doubt it's actually reading and writing every byte on
the raid. Based on comparison to ultra-narrow scsi, this thing flew and
that was what shocked our entire technical staff. Our experience with
raid was limited to ultra-narrow DPT up to that point.
-Justin
+- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -+
| Justin William Brown | "Damnit Jim, I'm a Doctor not a target!" |
jbrown@tanstaafl.busprod.com |
| jbrown@gnu.ai.mit.edu | "What happens when V.R. becomes R.L.?" |
+- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -+
