bb@wjh12.harvard.edu (Brent Byer) (06/11/89)
In article <32705@bu-cs.BU.EDU> bzs@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