Academic workstations -- Non-facts

Brent Byer bb at wjh12.harvard.edu
Sun Jun 11 10:41:08 AEST 1989


In article <32705 at bu-cs.BU.EDU> bzs at bu-cs.BU.EDU (Barry Shein) writes:
>.......
>Bad guess, go measure it, .....
>
>An ethernet can deliver data at almost 1MB per second, go look at the
>specs on your standard 27msec SCSI cheapo, 20KB/sec is not unusual for
>maximum disk transfer rate, about 1/40th the speed of an ethernet.
>

Hey, Barry:  If you're going to be arrogant, make sure you're correct.
		(i.e., don't make "bad guesses, go measure it"  :-) )

Your data point of 20KB/sec is off by a factor of 5.  At least.

I did measure it.  Using a mundane Micropolis 1325, 70MB drive,
30msec access, controlled using a SCSI-ST506 adapter (even slower
than straight SCSI).

Real-world measurement:  A tree of 220 .c source files totaling 1.58 MB
			(reported by 'wc'), I do a

				  grep "^Z" */*.c

			which completes in 15-17 secs  (10 measurements).

Looks like 100KB/sec.	[ No sleaze; only 800KB of system buffers ]

>
>I am not saying there aren't cases where a diskful workstation is far
>better, I'm just saying most people don't know what they're talking
>about or have motives other than understanding the technology.
>-- 
>	-Barry Shein
>
>Software Tool & Die, Purveyors to the Trade

[  This does not prove anything wrt diskful vs diskless, but I
   don't like to see professionals using gross exaggeration to
   support their arguments.
]

What the heck,  "We're all bozos on this bus."

	brent byer



More information about the Comp.unix.questions mailing list