Subject: Re: silo overflows, was fifo overruns
To: Jonathan Stone <jonathan@DSG.Stanford.EDU>
From: Scott Reynolds <scottr@Plexus.COM>
List: current-users
Date: 11/11/1997 23:37:43
On Tue, 11 Nov 1997, Jonathan Stone wrote:

> >The problem is the 8530: it is a very slow part; it must be accessed at
> >most once every 2us.
> Sorry, that turns out not to be the case.

well, actually it's 2.2 usec, but Jonathan's right that this isn't the
bottleneck.  the part can keep up quite well with fairly agressive
transfers; i have seen better than 5KB/sec through ppp on my hopped-up mac
IIcx (25MHz 68030).  i run my modem port at 57600 without inbound flow
control (i.e. rts is not connected).

> I'd tend to conclude this is a problem with the NetBSD Sparc kernel
> interrupt handling, or the zs driver, or both.

interrupt handling or the md front end; the mi back end i the same driver
that mac68k uses.