From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1751471Ab1IZGy3 (ORCPT <rfc822;w@1wt.eu>);
	Mon, 26 Sep 2011 02:54:29 -0400
Received: from mail-yx0-f174.google.com ([209.85.213.174]:38249 "EHLO
	mail-yx0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1750830Ab1IZGy2 convert rfc822-to-8bit (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Mon, 26 Sep 2011 02:54:28 -0400
MIME-Version: 1.0
In-Reply-To: <1316940890-24138-6-git-send-email-gilad@benyossef.com>
References: <1316940890-24138-1-git-send-email-gilad@benyossef.com>
	<1316940890-24138-6-git-send-email-gilad@benyossef.com>
Date: Mon, 26 Sep 2011 09:54:27 +0300
X-Google-Sender-Auth: AzZnWH7QDYqhxIxGzBIR0oMD0bM
Message-ID: <CAOJsxLEHHJyPnCngQceRW04PLKFa3RUQEbc3rLwiOPXa7XZNeQ@mail.gmail.com>
Subject: Re: [PATCH 5/5] slub: Only IPI CPUs that have per cpu obj to flush
From: Pekka Enberg <penberg@cs.helsinki.fi>
To: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: linux-kernel@vger.kernel.org, Peter Zijlstra <a.p.zijlstra@chello.nl>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Russell King <linux@arm.linux.org.uk>,
        Chris Metcalf <cmetcalf@tilera.com>, linux-mm@kvack.org,
        Christoph Lameter <cl@linux-foundation.org>,
        Matt Mackall <mpm@selenic.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8BIT
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Sun, Sep 25, 2011 at 11:54 AM, Gilad Ben-Yossef <gilad@benyossef.com> wrote:
> Try to send IPI to flush per cpu objects back to free lists
> to CPUs to seems to have such objects.
>
> The check which CPU to IPI is racy but we don't care since
> asking a CPU without per cpu objects to flush does no
> damage and as far as I can tell the flush_all by itself is
> racy against allocs on remote CPUs anyway, so if you meant
> the flush_all to be determinstic, you had to arrange for
> locking regardless.
>
> Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
> CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
> CC: Frederic Weisbecker <fweisbec@gmail.com>
> CC: Russell King <linux@arm.linux.org.uk>
> CC: Chris Metcalf <cmetcalf@tilera.com>
> CC: linux-mm@kvack.org
> CC: Christoph Lameter <cl@linux-foundation.org>
> CC: Pekka Enberg <penberg@kernel.org>
> CC: Matt Mackall <mpm@selenic.com>
> ---
>  mm/slub.c |   15 ++++++++++++++-
>  1 files changed, 14 insertions(+), 1 deletions(-)
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 9f662d7..8baae30 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -1948,7 +1948,20 @@ static void flush_cpu_slab(void *d)
>
>  static void flush_all(struct kmem_cache *s)
>  {
> -       on_each_cpu(flush_cpu_slab, s, 1);
> +       cpumask_var_t cpus;
> +       struct kmem_cache_cpu *c;
> +       int cpu;
> +
> +       if (likely(zalloc_cpumask_var(&cpus, GFP_ATOMIC))) {
> +               for_each_online_cpu(cpu) {
> +                       c = per_cpu_ptr(s->cpu_slab, cpu);
> +                       if (c && c->page)
> +                               cpumask_set_cpu(cpu, cpus);
> +               }
> +               on_each_cpu_mask(cpus, flush_cpu_slab, s, 1);
> +               free_cpumask_var(cpus);
> +       } else
> +               on_each_cpu(flush_cpu_slab, s, 1);
>  }

AFAICT, flush_all() isn't all that performance sensitive. Why do we
want to reduce IPIs here? Also, I'm somewhat unhappy about introducing
memory allocations in memory shrinking code paths. If we really want
to do this, can we preallocate cpumask in struct kmem_cache, for
example?

                        Pekka