All of lore.kernel.org
 help / color / mirror / Atom feed
From: Johannes Weiner <hannes@saeurebad.de>
To: Rik van Riel <riel@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
	Christoph Lameter <clameter@sgi.com>
Subject: Re: [patch 02/20] Use an indexed array for LRU variables
Date: Wed, 05 Mar 2008 01:31:10 +0100	[thread overview]
Message-ID: <87lk4yc8q9.fsf@saeurebad.de> (raw)
In-Reply-To: <20080304225226.653954413@redhat.com> (Rik van Riel's message of "Tue, 04 Mar 2008 17:51:59 -0500")

Hi Rik,

Rik van Riel <riel@redhat.com> writes:

> Index: linux-2.6.25-rc3-mm1/include/linux/mmzone.h
> ===================================================================
> --- linux-2.6.25-rc3-mm1.orig/include/linux/mmzone.h	2008-03-04 14:12:52.000000000 -0500
> +++ linux-2.6.25-rc3-mm1/include/linux/mmzone.h	2008-03-04 14:59:31.000000000 -0500
> @@ -80,8 +80,8 @@ struct zone_padding {
>  enum zone_stat_item {
>  	/* First 128 byte cacheline (assuming 64 bit words) */
>  	NR_FREE_PAGES,
> -	NR_INACTIVE,
> -	NR_ACTIVE,
> +	NR_INACTIVE,	/* must match order of LRU_[IN]ACTIVE */
> +	NR_ACTIVE,	/*  "     "     "   "       "         */
>  	NR_ANON_PAGES,	/* Mapped anonymous pages */
>  	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
>  			   only modified from process context */
> @@ -105,6 +105,13 @@ enum zone_stat_item {
>  #endif
>  	NR_VM_ZONE_STAT_ITEMS };

How about a #define LRU_STAT_BASE NR_INACTIVE ...

> Index: linux-2.6.25-rc3-mm1/include/linux/mm_inline.h
> ===================================================================
> --- linux-2.6.25-rc3-mm1.orig/include/linux/mm_inline.h	2007-07-08 19:32:17.000000000 -0400
> +++ linux-2.6.25-rc3-mm1/include/linux/mm_inline.h	2008-03-04 14:59:31.000000000 -0500
> @@ -1,40 +1,51 @@
>  static inline void
> +add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
> +{
> +	list_add(&page->lru, &zone->list[l]);
> +	__inc_zone_state(zone, NR_INACTIVE + l);

... in order to avoid using NR_INACTIVE in places like this?

(LRU_STAT_BASE is a bad name, I apologize)

Or perhaps a macro lru_stat (it's getting worse...) that yields the zone
stat index corresponding to the lru list type?  I think this would
increase readability.

	Hannes

WARNING: multiple messages have this Message-ID (diff)
From: Johannes Weiner <hannes@saeurebad.de>
To: Rik van Riel <riel@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
	Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
	Christoph Lameter <clameter@sgi.com>
Subject: Re: [patch 02/20] Use an indexed array for LRU variables
Date: Wed, 05 Mar 2008 01:31:10 +0100	[thread overview]
Message-ID: <87lk4yc8q9.fsf@saeurebad.de> (raw)
In-Reply-To: <20080304225226.653954413@redhat.com> (Rik van Riel's message of "Tue, 04 Mar 2008 17:51:59 -0500")

Hi Rik,

Rik van Riel <riel@redhat.com> writes:

> Index: linux-2.6.25-rc3-mm1/include/linux/mmzone.h
> ===================================================================
> --- linux-2.6.25-rc3-mm1.orig/include/linux/mmzone.h	2008-03-04 14:12:52.000000000 -0500
> +++ linux-2.6.25-rc3-mm1/include/linux/mmzone.h	2008-03-04 14:59:31.000000000 -0500
> @@ -80,8 +80,8 @@ struct zone_padding {
>  enum zone_stat_item {
>  	/* First 128 byte cacheline (assuming 64 bit words) */
>  	NR_FREE_PAGES,
> -	NR_INACTIVE,
> -	NR_ACTIVE,
> +	NR_INACTIVE,	/* must match order of LRU_[IN]ACTIVE */
> +	NR_ACTIVE,	/*  "     "     "   "       "         */
>  	NR_ANON_PAGES,	/* Mapped anonymous pages */
>  	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
>  			   only modified from process context */
> @@ -105,6 +105,13 @@ enum zone_stat_item {
>  #endif
>  	NR_VM_ZONE_STAT_ITEMS };

How about a #define LRU_STAT_BASE NR_INACTIVE ...

> Index: linux-2.6.25-rc3-mm1/include/linux/mm_inline.h
> ===================================================================
> --- linux-2.6.25-rc3-mm1.orig/include/linux/mm_inline.h	2007-07-08 19:32:17.000000000 -0400
> +++ linux-2.6.25-rc3-mm1/include/linux/mm_inline.h	2008-03-04 14:59:31.000000000 -0500
> @@ -1,40 +1,51 @@
>  static inline void
> +add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
> +{
> +	list_add(&page->lru, &zone->list[l]);
> +	__inc_zone_state(zone, NR_INACTIVE + l);

... in order to avoid using NR_INACTIVE in places like this?

(LRU_STAT_BASE is a bad name, I apologize)

Or perhaps a macro lru_stat (it's getting worse...) that yields the zone
stat index corresponding to the lru list type?  I think this would
increase readability.

	Hannes

--
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:[~2008-03-05  0:32 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-04 22:51 [patch 00/20] VM pageout scalability improvements (V5) Rik van Riel
2008-03-04 22:51 ` Rik van Riel
2008-03-04 22:51 ` [patch 01/20] move isolate_lru_page() to vmscan.c Rik van Riel
2008-03-04 22:51   ` Rik van Riel
2008-03-04 22:51 ` [patch 02/20] Use an indexed array for LRU variables Rik van Riel
2008-03-04 22:51   ` Rik van Riel
2008-03-05  0:31   ` Johannes Weiner [this message]
2008-03-05  0:31     ` Johannes Weiner
2008-03-04 22:52 ` [patch 03/20] use an array for the LRU pagevecs Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 04/20] free swap space on swap-in/activation Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 05/20] define page_file_cache() function Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 06/20] split LRU lists into anon & file sets Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 07/20] SEQ replacement for anonymous pages Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 08/20] add some sanity checks to get_scan_ratio Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 09/20] add newly swapped in pages to the inactive list Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 10/20] more aggressively use lumpy reclaim Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 11/20] No Reclaim LRU Infrastructure Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-05  0:34   ` minchan Kim
2008-03-05  0:34     ` minchan Kim
2008-03-05  4:21     ` Rik van Riel
2008-03-05  4:21       ` Rik van Riel
2008-03-04 22:52 ` [patch 12/20] Non-reclaimable page statistics Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 13/20] scan noreclaim list for reclaimable pages Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 14/20] ramfs pages are non-reclaimable Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 15/20] SHM_LOCKED pages are nonreclaimable Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 16/20] non-reclaimable mlocked pages Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-05  0:28   ` minchan Kim
2008-03-05  0:28     ` minchan Kim
2008-03-05  4:18     ` Rik van Riel
2008-03-05  4:18       ` Rik van Riel
2008-03-04 22:52 ` [patch 17/20] mlock vma pages under mmap_sem held for read Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 18/20] handle mlocked pages during map/unmap and truncate Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 19/20] account mlocked pages Rik van Riel
2008-03-04 22:52   ` Rik van Riel
2008-03-04 22:52 ` [patch 20/20] cull non-reclaimable anon pages from the LRU at fault time Rik van Riel
2008-03-04 22:52   ` Rik van Riel

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=87lk4yc8q9.fsf@saeurebad.de \
    --to=hannes@saeurebad.de \
    --cc=Lee.Schermerhorn@hp.com \
    --cc=clameter@sgi.com \
    --cc=kosaki.motohiro@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=riel@redhat.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 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.