🚀 go-pugleaf

In article <1992Aug18.072833.15164@leland.Stanford.EDU>  
marcu@leland.Stanford.EDU (Marc Albert Ullman) writes:
> I agree with your comments on using "disk" to benchmark disk  
performance;
> however, I disagree with your conclusions.  When I upraded the original  
Maxtor
> XT-3830S in my cube to a Seagate ST41650N (Wren VIII) last year, I used  
the
> test you advocate to check the before and after performace.  While I did  
see
> a substantial improvement (~400kB/s with Maxtor; ~1.1MB/s with Seagate),
> these numbers are still *far* below the specified theoretical throughput
> from these devices.  The Wren VIII has a sustained transfer rate of
> 1.83 to 3.5MB/s for data coming *off the media* and asynchronous SCSI
> transfer rates of 1.65 to 3.0 MB/s.  

You compare real-world tests with the drive manufacturers' claims  
seemingly in an attempt to show that NeXT's SCSI driver is inferior to  
that of other vendors. Please, if you want to make such a claim, test  
NeXT's SCSI performance against someone else's SCSI performance, not  
against claimed theoretical performance.

> The problem with the NeXT SCSI
> driver is that it doesn't take advantage of various features of SCSI II
> like tagged command queueing and sychronous transfer (for which the
> drive can support transfer rates up to 5MB/s (which is faster than the
> 4MB/s max that the old '040 cubes can do because the 53C90A is only
> clocked at 20MHz).  The current driver operates in lock step with the
> drive, waiting for one command to complete before issuing the next,  
rather
> than overlapping them and allowing the drive to optimize its  
performance.

This is correct. NeXT currently supports neither sychronous SCSI nor  
tagged command queueing. I unsuccessfully lobbied to have them included in  
3.0. Before NeXT will support these SCSI features, they will put every  
type of hard drive that they ever shipped through qualification testing to  
make sure that implementing them won't "break" anyone's system. I am  
confident, however, that NeXT will eventually support these features. I  
therefore strongly recommend that anyone looking for a hard disk for a  
NeXT, who is interested in performance, get one that supports tagged  
command queueing. Don't bother with untagged command queueing.

> The inside story from NeXT is that improving disk performance, while it
> certainly could be done, is simply not a priority in a resource-strapped 
> development environment.

That was true while 3.0 was in development. Many of the engineers in the  
software group have now turned to other things.

M Carling
Director, Bay Area NeXT Group
--
Dan Quayle needs a new running mate.
George Bush undermines his chances of being re-elected Vice President.