linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
To: Mel Gorman <mel@csn.ul.ie>
Cc: kosaki.motohiro@jp.fujitsu.com,
	Linux Memory Management List <linux-mm@kvack.org>,
	Christoph Lameter <cl@linux-foundation.org>,
	Nick Piggin <npiggin@suse.de>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Lin Ming <ming.m.lin@intel.com>,
	Zhang Yanmin <yanmin_zhang@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Pekka Enberg <penberg@cs.helsinki.fi>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH 21/25] Use allocation flags as an index to the zone watermark
Date: Wed, 22 Apr 2009 09:26:10 +0900 (JST)	[thread overview]
Message-ID: <20090422092429.6271.A69D9226@jp.fujitsu.com> (raw)
In-Reply-To: <1240266011-11140-22-git-send-email-mel@csn.ul.ie>

> ALLOC_WMARK_MIN, ALLOC_WMARK_LOW and ALLOC_WMARK_HIGH determin whether
> pages_min, pages_low or pages_high is used as the zone watermark when
> allocating the pages. Two branches in the allocator hotpath determine which
> watermark to use. This patch uses the flags as an array index and places
> the three watermarks in a union with an array so it can be offset. This
> means the flags can be used as an array index and reduces the branches
> taken.
> 
> Signed-off-by: Mel Gorman <mel@csn.ul.ie>
> Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
> ---
>  include/linux/mmzone.h |    8 +++++++-
>  mm/page_alloc.c        |   18 ++++++++----------
>  2 files changed, 15 insertions(+), 11 deletions(-)
> 
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index f82bdba..c1fa208 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -275,7 +275,13 @@ struct zone_reclaim_stat {
>  
>  struct zone {
>  	/* Fields commonly accessed by the page allocator */
> -	unsigned long		pages_min, pages_low, pages_high;
> +	union {
> +		struct {
> +			unsigned long	pages_min, pages_low, pages_high;
> +		};
> +		unsigned long pages_mark[3];
> +	};
> +

hmmm... I don't like union hack. 
Why can't we change all caller to use page_mark?




>  	/*
>  	 * We don't know if the memory that we're going to allocate will be freeable
>  	 * or/and it will be released eventually, so to avoid totally wasting several
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 376d848..e61867e 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -1157,10 +1157,13 @@ failed:
>  	return NULL;
>  }
>  
> -#define ALLOC_NO_WATERMARKS	0x01 /* don't check watermarks at all */
> -#define ALLOC_WMARK_MIN		0x02 /* use pages_min watermark */
> -#define ALLOC_WMARK_LOW		0x04 /* use pages_low watermark */
> -#define ALLOC_WMARK_HIGH	0x08 /* use pages_high watermark */
> +/* The WMARK bits are used as an index zone->pages_mark */
> +#define ALLOC_WMARK_MIN		0x00 /* use pages_min watermark */
> +#define ALLOC_WMARK_LOW		0x01 /* use pages_low watermark */
> +#define ALLOC_WMARK_HIGH	0x02 /* use pages_high watermark */
> +#define ALLOC_NO_WATERMARKS	0x08 /* don't check watermarks at all */
> +#define ALLOC_WMARK_MASK	0x07 /* Mask to get the watermark bits */

the mask only use two bit. but mask definition is three bit (0x07), why?


> +
>  #define ALLOC_HARDER		0x10 /* try to alloc harder */
>  #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
>  #ifdef CONFIG_CPUSETS
> @@ -1463,12 +1466,7 @@ zonelist_scan:
>  
>  		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
>  			unsigned long mark;
> -			if (alloc_flags & ALLOC_WMARK_MIN)
> -				mark = zone->pages_min;
> -			else if (alloc_flags & ALLOC_WMARK_LOW)
> -				mark = zone->pages_low;
> -			else
> -				mark = zone->pages_high;
> +			mark = zone->pages_mark[alloc_flags & ALLOC_WMARK_MASK];
>  			if (!zone_watermark_ok(zone, order, mark,
>  				    classzone_idx, alloc_flags)) {
>  				if (!zone_reclaim_mode ||
> -- 
> 1.5.6.5
> 



--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2009-04-22  0:25 UTC|newest]

Thread overview: 105+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-04-20 22:19 [PATCH 00/25] Cleanup and optimise the page allocator V6 Mel Gorman
2009-04-20 22:19 ` [PATCH 01/25] Replace __alloc_pages_internal() with __alloc_pages_nodemask() Mel Gorman
2009-04-21  1:44   ` KOSAKI Motohiro
2009-04-21  5:55   ` Pekka Enberg
2009-04-20 22:19 ` [PATCH 02/25] Do not sanity check order in the fast path Mel Gorman
2009-04-21  1:45   ` KOSAKI Motohiro
2009-04-21  5:55   ` Pekka Enberg
2009-04-20 22:19 ` [PATCH 03/25] Do not check NUMA node ID when the caller knows the node is valid Mel Gorman
2009-04-21  2:44   ` KOSAKI Motohiro
2009-04-21  6:00   ` Pekka Enberg
2009-04-21  6:33   ` Paul Mundt
2009-04-20 22:19 ` [PATCH 04/25] Check only once if the zonelist is suitable for the allocation Mel Gorman
2009-04-21  3:03   ` KOSAKI Motohiro
2009-04-21  7:09   ` Pekka Enberg
2009-04-20 22:19 ` [PATCH 05/25] Break up the allocator entry point into fast and slow paths Mel Gorman
2009-04-21  6:35   ` KOSAKI Motohiro
2009-04-21  7:13     ` Pekka Enberg
2009-04-21  9:30       ` Mel Gorman
2009-04-21  9:29     ` Mel Gorman
2009-04-21 10:44       ` KOSAKI Motohiro
2009-04-20 22:19 ` [PATCH 06/25] Move check for disabled anti-fragmentation out of fastpath Mel Gorman
2009-04-21  6:37   ` KOSAKI Motohiro
2009-04-20 22:19 ` [PATCH 07/25] Check in advance if the zonelist needs additional filtering Mel Gorman
2009-04-21  6:52   ` KOSAKI Motohiro
2009-04-21  9:47     ` Mel Gorman
2009-04-21  7:21   ` Pekka Enberg
2009-04-21  9:49     ` Mel Gorman
2009-04-20 22:19 ` [PATCH 08/25] Calculate the preferred zone for allocation only once Mel Gorman
2009-04-21  7:03   ` KOSAKI Motohiro
2009-04-21  8:23     ` Mel Gorman
2009-04-21  7:37   ` Pekka Enberg
2009-04-21  8:27     ` Mel Gorman
2009-04-21  8:29       ` Pekka Enberg
2009-04-20 22:19 ` [PATCH 09/25] Calculate the migratetype " Mel Gorman
2009-04-21  7:37   ` KOSAKI Motohiro
2009-04-21  8:35     ` Mel Gorman
2009-04-21 10:19       ` KOSAKI Motohiro
2009-04-21 10:30         ` Mel Gorman
2009-04-20 22:19 ` [PATCH 10/25] Calculate the alloc_flags " Mel Gorman
2009-04-21  9:03   ` KOSAKI Motohiro
2009-04-21 10:05     ` Mel Gorman
2009-04-21 10:12       ` KOSAKI Motohiro
2009-04-21 10:37         ` Mel Gorman
2009-04-21 10:40           ` KOSAKI Motohiro
2009-04-20 22:19 ` [PATCH 11/25] Calculate the cold parameter " Mel Gorman
2009-04-21  7:43   ` Pekka Enberg
2009-04-21  8:41     ` Mel Gorman
2009-04-21  9:07   ` KOSAKI Motohiro
2009-04-21 10:08     ` Mel Gorman
2009-04-21 14:59     ` Christoph Lameter
2009-04-21 14:58   ` Christoph Lameter
2009-04-20 22:19 ` [PATCH 12/25] Remove a branch by assuming __GFP_HIGH == ALLOC_HIGH Mel Gorman
2009-04-21  7:46   ` Pekka Enberg
2009-04-21  8:45     ` Mel Gorman
2009-04-21 10:25       ` Pekka Enberg
2009-04-21  9:08   ` KOSAKI Motohiro
2009-04-21 10:31     ` KOSAKI Motohiro
2009-04-21 10:43       ` Mel Gorman
2009-04-20 22:19 ` [PATCH 13/25] Inline __rmqueue_smallest() Mel Gorman
2009-04-21  7:58   ` Pekka Enberg
2009-04-21  8:48     ` Mel Gorman
2009-04-21  9:52   ` KOSAKI Motohiro
2009-04-21 10:11     ` Mel Gorman
2009-04-21 10:22       ` KOSAKI Motohiro
2009-04-20 22:20 ` [PATCH 14/25] Inline buffered_rmqueue() Mel Gorman
2009-04-21  9:56   ` KOSAKI Motohiro
2009-04-20 22:20 ` [PATCH 15/25] Inline __rmqueue_fallback() Mel Gorman
2009-04-21  9:56   ` KOSAKI Motohiro
2009-04-20 22:20 ` [PATCH 16/25] Save text by reducing call sites of __rmqueue() Mel Gorman
2009-04-21 10:47   ` KOSAKI Motohiro
2009-04-20 22:20 ` [PATCH 17/25] Do not call get_pageblock_migratetype() more than necessary Mel Gorman
2009-04-21 11:03   ` KOSAKI Motohiro
2009-04-21 16:12     ` Mel Gorman
2009-04-22  2:25       ` KOSAKI Motohiro
2009-04-20 22:20 ` [PATCH 18/25] Do not disable interrupts in free_page_mlock() Mel Gorman
2009-04-21  7:55   ` Pekka Enberg
2009-04-21  8:50     ` Mel Gorman
2009-04-21 15:05       ` Christoph Lameter
2009-04-22  0:13   ` KOSAKI Motohiro
2009-04-22 14:43     ` Lee Schermerhorn
2009-04-20 22:20 ` [PATCH 19/25] Do not setup zonelist cache when there is only one node Mel Gorman
2009-04-20 22:20 ` [PATCH 20/25] Do not check for compound pages during the page allocator sanity checks Mel Gorman
2009-04-22  0:20   ` KOSAKI Motohiro
2009-04-22 10:09     ` Mel Gorman
2009-04-22 10:41       ` KOSAKI Motohiro
2009-04-20 22:20 ` [PATCH 21/25] Use allocation flags as an index to the zone watermark Mel Gorman
2009-04-22  0:26   ` KOSAKI Motohiro [this message]
2009-04-22  0:41     ` David Rientjes
2009-04-22 10:21     ` Mel Gorman
2009-04-22 10:23       ` Mel Gorman
2009-04-20 22:20 ` [PATCH 22/25] Update NR_FREE_PAGES only as necessary Mel Gorman
2009-04-22  0:35   ` KOSAKI Motohiro
2009-04-20 22:20 ` [PATCH 23/25] Get the pageblock migratetype without disabling interrupts Mel Gorman
2009-04-20 22:20 ` [PATCH 24/25] Re-sort GFP flags and fix whitespace alignment for easier reading Mel Gorman
2009-04-21  8:04   ` Pekka Enberg
2009-04-21  8:52     ` Mel Gorman
2009-04-21 15:08       ` Christoph Lameter
2009-04-21 15:24         ` Mel Gorman
2009-04-20 22:20 ` [PATCH 25/25] Use a pre-calculated value instead of num_online_nodes() in fast paths Mel Gorman
2009-04-21  8:08   ` Pekka Enberg
2009-04-21  9:01     ` Mel Gorman
2009-04-21 15:09       ` Christoph Lameter
2009-04-21  8:13 ` [PATCH 00/25] Cleanup and optimise the page allocator V6 Pekka Enberg
2009-04-22 14:13   ` Mel Gorman
  -- strict thread matches above, loose matches on Subject: below --
2009-03-20 10:02 [PATCH 00/25] Cleanup and optimise the page allocator V5 Mel Gorman
2009-03-20 10:03 ` [PATCH 21/25] Use allocation flags as an index to the zone watermark Mel Gorman

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=20090422092429.6271.A69D9226@jp.fujitsu.com \
    --to=kosaki.motohiro@jp.fujitsu.com \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --cc=ming.m.lin@intel.com \
    --cc=npiggin@suse.de \
    --cc=penberg@cs.helsinki.fi \
    --cc=peterz@infradead.org \
    --cc=yanmin_zhang@linux.intel.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox