From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: Christoph Lameter <cl@linux.com>
Cc: akpm@linux-foundation.org, Pekka Enberg <penberg@cs.helsinki.fi>,
linux-kernel@vger.kernel.org,
Eric Dumazet <eric.dumazet@gmail.com>, Tejun Heo <tj@kernel.org>
Subject: Re: [thisops uV2 02/10] vmstat: Optimize zone counter modifications through the use of this cpu operations
Date: Mon, 29 Nov 2010 14:28:01 -0500 [thread overview]
Message-ID: <20101129192801.GE25610@Krystal> (raw)
In-Reply-To: <alpine.DEB.2.00.1011291111110.4836@router.home>
* Christoph Lameter (cl@linux.com) wrote:
> We could do this with local cmpxchgs like in the following patch. This
> would avoid preemption disable and interrupt disable (at least on x86).
> Trouble is how do we make this fit for architectures that do not have
> cmpxchg?
All architectures should have a fallback nowadays, no ? This might involve
disabling interrupts around a cmpxchg emulation, which would make the slow path
disable/enable interrupts twice. Is it what you are concerned about ?
Thanks,
Matheu
>
>
> Index: linux-2.6/mm/vmstat.c
> ===================================================================
> --- linux-2.6.orig/mm/vmstat.c 2010-11-29 10:58:52.000000000 -0600
> +++ linux-2.6/mm/vmstat.c 2010-11-29 11:11:34.000000000 -0600
> @@ -169,18 +169,23 @@ void __mod_zone_page_state(struct zone *
> {
> struct per_cpu_pageset __percpu *pcp = zone->pageset;
> s8 __percpu *p = pcp->vm_stat_diff + item;
> - long x;
> - long t;
> + long o, n, t, z;
>
> - x = delta + __this_cpu_read(*p);
> + do {
> + z = 0;
> + t = this_cpu_read(pcp->stat_threshold);
> + o = this_cpu_read(*p);
> + n = delta + o;
> +
> + if (n > t || n < -t) {
> + /* Overflow must be added to zone counters */
> + z = n;
> + n = 0;
> + }
> + } while (o != n && this_cpu_cmpxchg(*p, o, n) != o);
>
> - t = __this_cpu_read(pcp->stat_threshold);
> -
> - if (unlikely(x > t || x < -t)) {
> - zone_page_state_add(x, zone, item);
> - x = 0;
> - }
> - __this_cpu_write(*p, x);
> + if (z)
> + zone_page_state_add(z, zone, item);
> }
> EXPORT_SYMBOL(__mod_zone_page_state);
>
> @@ -190,11 +195,7 @@ EXPORT_SYMBOL(__mod_zone_page_state);
> void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
> int delta)
> {
> - unsigned long flags;
> -
> - local_irq_save(flags);
> __mod_zone_page_state(zone, item, delta);
> - local_irq_restore(flags);
> }
> EXPORT_SYMBOL(mod_zone_page_state);
>
>
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
next prev parent reply other threads:[~2010-11-29 19:28 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-26 21:09 [thisops uV2 00/10] Upgrade of this_cpu_ops V2 Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 01/10] percpucounter: Optimize __percpu_counter_add a bit through the use of this_cpu() options Christoph Lameter
2010-11-27 14:42 ` Mathieu Desnoyers
2010-11-26 21:09 ` [thisops uV2 02/10] vmstat: Optimize zone counter modifications through the use of this cpu operations Christoph Lameter
2010-11-27 8:00 ` Pekka Enberg
2010-11-27 14:49 ` Mathieu Desnoyers
2010-11-29 16:16 ` Christoph Lameter
2010-11-29 17:13 ` Christoph Lameter
2010-11-29 19:28 ` Mathieu Desnoyers [this message]
2010-11-29 20:07 ` Christoph Lameter
2010-11-29 20:59 ` Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 03/10] percpu: Generic support for this_cpu_add,sub,dec,inc_return Christoph Lameter
2010-11-27 14:58 ` Mathieu Desnoyers
2010-11-29 16:08 ` Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 04/10] x86: Support " Christoph Lameter
2010-11-27 8:06 ` Pekka Enberg
2010-11-29 16:03 ` Christoph Lameter
2010-11-27 15:00 ` Mathieu Desnoyers
2010-11-29 16:31 ` Christoph Lameter
2010-11-29 18:33 ` Mathieu Desnoyers
2010-11-29 18:54 ` Christoph Lameter
2010-11-29 19:22 ` Mathieu Desnoyers
2010-11-29 20:09 ` Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 05/10] x86: Use this_cpu_inc_return for nmi counter Christoph Lameter
2010-11-27 8:07 ` Pekka Enberg
2010-11-27 15:00 ` Mathieu Desnoyers
2010-11-26 21:09 ` [thisops uV2 06/10] vmstat: Use this_cpu_inc_return for vm statistics Christoph Lameter
2010-11-27 8:09 ` Pekka Enberg
2010-11-29 16:04 ` Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 07/10] highmem: Use this_cpu_xx_return() operations Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 08/10] percpu: generic this_cpu_cmpxchg() and this_cpu_cmpxchg_double support Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 09/10] x86: this_cpu_cmpxchg and this_cpu_cmpxchg_double operations Christoph Lameter
2010-11-27 6:30 ` Eric Dumazet
2010-11-27 15:20 ` Mathieu Desnoyers
2010-11-29 16:11 ` Christoph Lameter
2010-11-26 21:09 ` [thisops uV2 10/10] slub: Lockless fastpaths Christoph Lameter
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20101129192801.GE25610@Krystal \
--to=mathieu.desnoyers@efficios.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=eric.dumazet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=penberg@cs.helsinki.fi \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.