Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 06 Jun 2006 12:37:58 +0100
From:      Pete French <petefrench@ticketswitch.com>
To:        jfvogel@gmail.com
Cc:        freebsd-stable@freebsd.org
Subject:   Re: Dual Opteron system will not run SMP
Message-ID:  <E1FnZsk-0007i7-DE@dilbert.firstcallgroup.co.uk>
In-Reply-To: <2a41acea0606051012r5831971qb3d2fb88e701225@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
> We (Intel networking group) have seen issues with SMP and amd64
> as well, although I dont know that its fully characterized (what works
> and what doesnt) yet.

When I tried mine under amd64 it seemed to behave slightly better oddly
enough - it would at least boot up the SMP kernel without ACPI, though
it would not recognise the second processor. The other difference when
I was doing that test was that I was using an IDE drive though. I
suppose I really need to put amd64 onto a normal disc drive and try
booting that to narrow down which change made the difference there.

> If just non-ACPI isnt sufficient, the other thing SAFE does is turn
> off disk DMA. I have an as-yet unreleased system that has this
> same type of issue, and the problem is that two PCI device ID's
> are not recognized, so maybe that will be your problem.

Interesting - I didn't realise you could do that with SCSI controllers. I
had been wondering what 'safe' does differently, and whether I could
fill up loader.conf with approrpiate values to emulate what 'safe' does
and then start commenting them out one at a time.

I'll do some more experiments and report back. I don't particularly mind if
it doesn't work in the end (I'll just sell the pair of Opterons on ebay and
buy a single faster one), but it's always good to try and track down a bug, so
thanks for taking an interest.

-pete.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E1FnZsk-0007i7-DE>