[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20080416192238.GA12115@sgi.com>
Date: Wed, 16 Apr 2008 14:22:38 -0500
From: Jack Steiner <steiner@....com>
To: Ingo Molnar <mingo@...e.hu>
Cc: tglx@...utronix.de, linux-mm@...ck.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] - Increase MAX_APICS for large configs
On Wed, Apr 16, 2008 at 08:45:43PM +0200, Ingo Molnar wrote:
>
> * Jack Steiner <steiner@....com> wrote:
>
> > Increase the maximum number of apics when running very large
> > configurations. This patch has no affect on most systems.
> >
> > Signed-off-by: Jack Steiner <steiner@....com>
> >
> > I think this area of the code will be substantially changed when the
> > full x2apic patch is available. In the meantime, this seems like an
> > acceptible alternative. The patch has no effect on any 32-bit kernel.
> > It adds ~4k to the size of 64-bit kernels but only if NR_CPUS > 255.
>
> ugly ... but well - applied. What's the static size cost of 64K APICs?
64k APICs would add ~8k to the static size of the kernel. Most of the
increase is in the phys_cpu_present_map[].
When the x2apic patch is integrated, I expect (may be wrong) that this
array will be eliminated since x2apic increases the max APIC_ID to 32 bits,
Note that MAX_APICS is really misnamed. It is not the maximum number of APICs. It
is the value of the largest APIC ID. IDs are not necessarily dense.
--- jack
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists