Subject: Re: UltraDMA performance.
To: None <port-i386@NetBSD.ORG>
From: Wolfgang Rupprecht <wolfgang@wsrcc.com>
List: port-i386
Date: 01/05/2001 06:28:37
bouyer@asim.lip6.fr (Manuel Bouyer) writes:
> because pciide doesn't know (yet) that this board can do Ultra/66.
> The problem is that via uses the same vendor/device ID and revision for
> both the Ultra/33 and Ultra/66 controllers. We need some trick to detect
> a Ultra/66 capable one.

I don't know if this is related, but -current running on the Asus A7v
which has a Ultra/66 Via chip and Ultra/100 Promise chip will lock up
solidly (no ddb) if a drive is put on each Ultra/100 Promise channels.

One rare time it did let one break into DDB.  I saw:

        pciide 1:1 bogus intr     <this message repeats at high rate>
        ...
        syscall_plain (1f, 1f, 8, bfbfdc7c, bfbfda04)  syscall_plain+0x95

-wolfgang
-- 
       Wolfgang Rupprecht <wolfgang+gnus@dailyplanet.wsrcc.com>
		    http://www.wsrcc.com/wolfgang/
Coming soon: GPS mapping tools for Open Systems. http://www.gnomad-mapping.com/