Re: svn commit: r198868 - in head/sys: amd64/amd64 i386/i386

[ Available lists | Index of svn-src-all | Month of Nov 2009 | Week of 4 Nov 2009 | Raw email | View thread | Wrap long lines | Reply | Tag ]
From
Attilio Rao <attilio@freebsd.org>
Date
4 Nov 2009 16:06:02
Subject
Re: svn commit: r198868 - in head/sys: amd64/amd64 i386/i386
Message-ID
3bbf2fe10911040806l7293ab6l99cce51ea9d7a64c@mail.gmail.com


[ Hide this part ]
2009/11/4, Dag-Erling Smrgrav <des@des.no>:
> Attilio Rao <attilio@FreeBSD.org> writes:
> > Log:
> > Opteron rev E family of processor expose a bug where, in very rare
> > ocassions, memory barriers semantic is not honoured by the hardware
> > itself. As a result, some random breakage can happen in uninvestigable
> > ways (for further explanation see at the content of the commit itself).
>
> According to the reference you gave, OpenSolaris has a workaround for
> this issue. Perhaps we should adopt it?

IIRC, based on what I readed on-line, it could be still a WARNING msg,
but I didn't double-check for it.
On the other side, a possible complete solution would involve a
boot-time patching mechanism, but we don't have it right now
(differently from Linux) or disabling the SMP support, but it seems
mostly a too heavy loss of performance due to the rarely appearence of
the bug itself.

I think the WARNING msg is a good compromise to all these other approaches.

Attilio


--
Peace can only be achieved by understanding - A. Einstein


Elapsed time: 0.173 seconds