Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 16 Jul 2003 15:00:12 -0400 (EDT)
From:      John Baldwin <jhb@FreeBSD.org>
To:        "Cagle, John (ISS-Houston)" <john.cagle@hp.com>
Cc:        Patrik Veselik <veselik@ssakhk.cz>
Subject:   RE: maximum of CPUs
Message-ID:  <XFMail.20030716150012.jhb@FreeBSD.org>
In-Reply-To: <C50AB9511EE59B49B2A503CB7AE1ABD10476C7CB@cceexc19.americas.cpqcorp.net>

next in thread | previous in thread | raw e-mail | index | archive | help

On 16-Jul-2003 Cagle, John (ISS-Houston) wrote:
>> -----Original Message-----
>> From: John Baldwin [mailto:jhb@FreeBSD.org] 
>> On 15-Jul-2003 Cagle, John (ISS-Houston) wrote:
> <SNIP>
>> > --
>> > I/O APICs:      APIC ID Version State           Address
>> >                  8       0x11    usable          0xfec00000
>> >                  9       0x11    usable          0xfec01000
>> >                 10       0x11    usable          0xfec02000
>> > 
>> > Is this what you would expect to see on an 8-way server 
>> that supports
>> > hyperthreading?
>> 
>> Ugh, I would hope that the APIC ID's wouldn't collide with CPUs. :(
>> Note that you have real CPU's at ID's 8 and 10 and a logical one at
>> 9.  Currently my code doesn't renumber APIC ID's to try to cope with
>> this type of case.  Does the ACPI MADT table report the same values
>> for the APIC ID's of the I/O APICs?
> 
> I should have updated my BIOS before trying this out.  Sure enough, this
> was a BIOS bug that was corrected in March.  The I/O APICS are now
> numbered 16, 17 & 18 so as to not collide with processor's local APICS.
> (Looks like the original BIOS only accounted for processors 0..7,
> without hyperthreading.)

Ok, good.

> However, even with the properly renumbered IOAPICs, I still get the same
> panic: "No free physical APIC IDs found".

This is still expected with the current code.

> I'm going to add some debug messages and track this down further.  I'll
> let you know if I find anything.  I'll also check the MADT to see if it
> jives with everything else.

Tor's suggestion to bump up NAPICID to 256 might help.

-- 

John Baldwin <jhb@FreeBSD.org>  <><  http://www.FreeBSD.org/~jhb/
"Power Users Use the Power to Serve!"  -  http://www.FreeBSD.org/



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.20030716150012.jhb>