linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: mike kravetz <kravetz@us.ibm.com>
To: Mel Gorman <mel@csn.ul.ie>
Cc: akpm@osdl.org, jschopp@austin.ibm.com,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	lhms-devel@lists.sourceforge.net
Subject: Re: [PATCH 5/8] Fragmentation Avoidance V17: 005_fallback
Date: Wed, 12 Oct 2005 09:43:54 -0700	[thread overview]
Message-ID: <20051012164353.GA9425@w-mikek2.ibm.com> (raw)
In-Reply-To: <20051011151246.16178.40148.sendpatchset@skynet.csn.ul.ie>

On Tue, Oct 11, 2005 at 04:12:47PM +0100, Mel Gorman wrote:
> This patch implements fallback logic. In the event there is no 2^(MAX_ORDER-1)
> blocks of pages left, this will help the system decide what list to use. The
> highlights of the patch are;
> 
> o Define a RCLM_FALLBACK type for fallbacks
> o Use a percentage of each zone for fallbacks. When a reserved pool of pages
>   is depleted, it will try and use RCLM_FALLBACK before using anything else.
>   This greatly reduces the amount of fallbacks causing fragmentation without
>   needing complex balancing algorithms

I'm having a little trouble seeing how adding a new type (RCLM_FALLBACK)
helps.  Seems to me that pages put into the RCLM_FALLBACK area would have
gone to the global free list and available to anyone.  I must be missing
something here.

> +int fallback_allocs[RCLM_TYPES][RCLM_TYPES+1] = {
> +	{RCLM_NORCLM,	RCLM_FALLBACK, RCLM_KERN,   RCLM_USER, RCLM_TYPES},
> +	{RCLM_KERN,     RCLM_FALLBACK, RCLM_NORCLM, RCLM_USER, RCLM_TYPES},
> +	{RCLM_USER,     RCLM_FALLBACK, RCLM_NORCLM, RCLM_KERN, RCLM_TYPES},
> +	{RCLM_FALLBACK, RCLM_NORCLM,   RCLM_KERN,   RCLM_USER, RCLM_TYPES}

Do you really need that last line?  Can an allocation of type RCLM_FALLBACK
realy be made?

-- 
Mike

--
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:[~2005-10-12 16:44 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-10-11 15:12 [PATCH 0/8] Fragmentation Avoidance V17 Mel Gorman
2005-10-11 15:12 ` [PATCH 1/8] Fragmentation Avoidance V17: 001_antidefrag_flags Mel Gorman
2005-10-11 15:12 ` [PATCH 2/8] Fragmentation Avoidance V17: 002_usemap Mel Gorman
2005-10-13 13:56   ` Dave Hansen
2005-10-13 14:10     ` Mel Gorman
2005-10-13 14:18       ` Dave Hansen
2005-10-13 14:35         ` Mel Gorman
2005-10-16 20:44         ` Mel Gorman
2005-10-13 16:33       ` Joel Schopp
2005-10-11 15:12 ` [PATCH 3/8] Fragmentation Avoidance V17: 003_fragcore Mel Gorman
2005-10-11 15:12 ` [PATCH 4/8] Fragmentation Avoidance V17: 004_markfree Mel Gorman
2005-10-11 15:12 ` [PATCH 5/8] Fragmentation Avoidance V17: 005_fallback Mel Gorman
2005-10-12 16:43   ` mike kravetz [this message]
2005-10-12 17:21     ` Mel Gorman
2005-10-12 17:29       ` [Lhms-devel] " Joel Schopp
2005-10-14  5:12         ` Dave Hansen
2005-10-11 15:12 ` [PATCH 6/8] Fragmentation Avoidance V17: 006_largealloc_tryharder Mel Gorman
2005-10-13 19:07   ` Joel Schopp
2005-10-14  5:36     ` Dave Hansen
2005-10-11 15:12 ` [PATCH 7/8] Fragmentation Avoidance V17: 007_percpu Mel Gorman
2005-10-11 15:13 ` [PATCH 8/8] Fragmentation Avoidance V17: 008_stats Mel Gorman
2005-10-12 11:57   ` [Lhms-devel] " Dave Hansen
2005-10-12 12:19     ` Mel Gorman
2005-10-16  2:52 ` [PATCH 0/8] Fragmentation Avoidance V17 Paul Jackson
2005-10-16 11:59   ` Mel Gorman
2005-10-16 17:53     ` Paul Jackson
2005-10-16 18:03       ` 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=20051012164353.GA9425@w-mikek2.ibm.com \
    --to=kravetz@us.ibm.com \
    --cc=akpm@osdl.org \
    --cc=jschopp@austin.ibm.com \
    --cc=lhms-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    /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