Subject: Re: Sun4c random death revisited
To: None <port-sparc@netbsd.org>
From: Dan Debertin <airboss@nodewarrior.org>
List: port-sparc
Date: 12/15/2002 12:44:43
Jukka Marin <jmarin@pyy.jmp.fi> wrote:

> Umm, maybe you are suffering from the well-known problem discussed several
> times before..  Apparently, there is some hardware problem in the sun4c
> MMU which is triggered by NetBSD 1.6 kernel code.  AFAIK, there still isn't
> a good fix for the problem.  All my SS1's became completely useless the
> day I upgraded them to NetBSD 1.6.  There's a patch which makes the systems
> quite stable, but it also slows them down to 1/4 crawl.

I think Manuel B. was trying to attribute it to that problem last month
when he asked whether this machine was hw or sw flush. That problem is
apparently with IP[CX] and 1/1+ (and 2? not sure) that use sw flush,
whereas this model has hw flush. This instance might invalidate that
assumption, though, for all I know.

> 
> It's a pity - I've got four SS1's / SS1+'s, but they are quite useless now.

1.5.x isn't *that* far behind ... I wouldn't say they're useless.

Dan
--
/^Dan Debertin$/         
airboss@nodewarrior.org  | Did I sleep a little too late,
www.nodewarrior.org      | or am I awake?        --Byrne