[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <200911051113.33889.rusty@rustcorp.com.au>
Date: Thu, 5 Nov 2009 11:13:33 +1030
From: Rusty Russell <rusty@...tcorp.com.au>
To: Christoph Lameter <cl@...ux-foundation.org>
Cc: Ingo Molnar <mingo@...e.hu>,
Ian Campbell <Ian.Campbell@...rix.com>,
Tejun Heo <tj@...nel.org>,
"Paul E. McKenney" <paulmck@...ibm.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Andrew Morton <akpm@...ux-foundation.org>,
"linux-kernel" <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] Correct nr_processes() when CPUs have been unplugged
On Wed, 4 Nov 2009 05:04:32 am Christoph Lameter wrote:
> On Tue, 3 Nov 2009, Ingo Molnar wrote:
>
> > Sidenote: percpu areas currently are kept allocated on x86.
>
> They must be kept allocated for all possible cpus. Arch code cannot decide
> to not allocate per cpu areas.
>
> Search for "for_each_possible_cpu" in the source tree if you want more
> detail.
Yeah, handling onlining/offlining of cpus is a hassle for most code.
But I can see us wanting abstractions for counters which handle being per-cpu
or per-node and doing the folding etc. automagically. It's best that this
be done by looking at all the existing users to see if there's a nice API
which would cover 90%.
Cheers,
Rusty.
--
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