[comp.periphs] Disk Xfer rates

markb@denali (10/18/88)

Since I was unable to send mail directly to terryk, I
must post.  Sorry.

Terry, thanks for your benchmark info.  You are looking for a standard
diskio behchmark, but the only one that comes close, it seems is the
AIM.  I think Sun uses this and the U. Toronto BM.

I may be able to give you the source for mine.  Does page alligned and
non-page aligned reads and writes both single and multi tasking emulations.
The AIM benchmark is kind-of a standard, but as my posting said, this 
gives variable (like in a lot) results.

Ours does multiple block sizes, too, to look at FS implications.  Send
me some mail or give me a call at (415)962-3471 if you are interested
in pursuing this further.

Did you say you had a SCSI sabre???? 
                      ^^^^

					markb

Mark Bradley				"Faster, faster, until the thrill of
Manager I/O Subsystems			 speed overcomes the fear of death."
Silicon Graphics Computer Systems
Mountain View, CA			     ---Hunter S. Thompson

hawkes@mips.COM (John Hawkes) (10/20/88)

In article <20702@sgi.SGI.COM> markb@denali writes:
> [ stuff ]
>Terry, thanks for your benchmark info.  You are looking for a standard
>diskio behchmark, but the only one that comes close, it seems is the
>AIM. [ deleted stuff ]
>
>I may be able to give you the source for mine.

Be careful.  I think the AIM benchmark suite is a proprietary commercial
product and is protected by copyright.

-- 
John Hawkes    DISCLAIMER: <generic disclaimer, what do I know anyway, etc>
{ames,decwrl,prls,pyramid}!mips!hawkes  OR  hawkes@mips.com