WTB: Pro380, VAXstation

From: Dave Mitton <dave_at_mitton.com>
Date: Mon Apr 19 23:49:25 2004

On 4/17/2004 08:00 AM -0500, cctech-request_at_classiccmp.org wrote:
>Date: Thu, 15 Apr 2004 20:49:04 -0400
>From: Paul Koning <pkoning_at_equallogic.com>
>Subject: RE: WTB: Pro380, VAXstation
>To: arcarlini_at_iee.org, cctalk_at_classiccmp.org
>
> >>>>> "Antonio" == Antonio Carlini <arcarlini_at_iee.org> writes:
>
> >> As for a Pro being the easiest route, I wouldn't say so. The bus
> >> architecture is completely unrelated to that of any other PDP11,
> >> and ugly/messy/baroque/bogus at that. There is NO DMA. The
> >> Ethernet card uses the worst Ethernet chip I know.
>
> Antonio> Out of interest, which chip would that be?
>
>Intel 82586, if I remember right. It uses queues, not rings, for its
>commands. There are race conditions in the programming interface so
>that the chip sometimes sets a queue to empty at the same time that
>the driver puts a new entry on the queue, which forces the driver to
>notice that and repair the confusion.
>
>This is why real Ethernet chips use rings.
>
> paul

In the process of debugging that driver, the programmer involved with it,
found and identified a number of problems/bugs that Intel was unaware of
and refused to admit to until they finally isolated and fixed them in a
later rev.

Dave. (I only did NFT and FALs on DECnet-PRO)
Received on Mon Apr 19 2004 - 23:49:25 BST