LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Christoph Lameter <clameter@sgi.com>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Andrew Morton <akpm@osdl.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	Christoph Lameter <clameter@engr.sgi.com>
Subject: Re: [PATCH 0/8] Create ZONE_MOVABLE to partition memory between movable and non-movable pages
Date: Fri, 26 Jan 2007 08:01:07 -0800 (PST)	[thread overview]
Message-ID: <Pine.LNX.4.64.0701260756580.6141@schroedinger.engr.sgi.com> (raw)
In-Reply-To: <Pine.LNX.4.64.0701261334240.19245@skynet.skynet.ie>

On Fri, 26 Jan 2007, Mel Gorman wrote:

> I haven't thought about it much so I probably am missing something. The major
> difference I see is when only one zone is present. In that case, a number of
> loops presumably get optimised away and the behavior is very different
> (presumably better although you point out no figures exist to prove it). Where
> there are two or more zones, the code paths should be similar whether there
> are 2, 3 or 4 zones present.

The balancing of allocations between zones is becoming unnecessary. Also 
in a NUMA system we then have zone == node which allows for a series of 
simplifications.
 
> As the common platforms will always have more than one zone, it'll be heavily
> tested and I'm guessing that distros are always going to have to ship kernels
> with ZONE_DMA for the devices that require it. The only platform I see that
> may have problems at the moment is IA64 which looks like the only platform
> that can have one and only one zone. I am guessing that Christoph will catch
> problems here fairly quickly although a non-optional ZONE_MOVABLE would throw
> a spanner into the works somewhat.

There are 6 platforms that have only one zone. These are not major 
platforms. In order for major platforms to go to a single zone in general 
we would have to implement a generic mechanism to do an allocation where 
one can specify the memory boundaries. Many DMA engines have different
limitations from what ZONE_DMA and ZONE_DMA32 can provide. If such a 
scheme would be implemented then those would be able to utilize memory 
better and the amount of bounce buffers would be reduced.

  reply	other threads:[~2007-01-26 16:01 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-01-25 23:44 Mel Gorman
2007-01-25 23:45 ` [PATCH 1/8] Add __GFP_MOVABLE for callers to flag allocations that may be migrated Mel Gorman
2007-01-26 12:27   ` Nick Piggin
2007-01-26 13:25     ` Mel Gorman
2007-01-25 23:45 ` [PATCH 2/8] Create the ZONE_MOVABLE zone Mel Gorman
2007-01-26 16:28   ` Christoph Lameter
2007-01-26 16:49     ` Mel Gorman
2007-01-29 17:28     ` Mel Gorman
2007-01-26 17:16   ` Christoph Lameter
2007-01-26 17:24     ` Mel Gorman
2007-01-26 17:25       ` Christoph Lameter
2007-01-26 17:38         ` Mel Gorman
2007-01-29 17:31     ` Mel Gorman
2007-01-25 23:45 ` [PATCH 3/8] Allow huge page allocations to use GFP_HIGH_MOVABLE Mel Gorman
2007-01-26 16:33   ` Christoph Lameter
2007-01-26 16:58     ` Mel Gorman
2007-01-26 17:04       ` Christoph Lameter
2007-01-26 17:20         ` Mel Gorman
2007-01-26 17:22           ` Christoph Lameter
2007-01-26 17:37             ` Mel Gorman
2007-01-26 17:45               ` Christoph Lameter
2007-01-26 17:53                 ` Mel Gorman
2007-01-26 18:20                   ` Christoph Lameter
2007-01-26 20:37                     ` Mel Gorman
2007-01-26 18:35                   ` Chris Friesen
2007-01-26 20:44                     ` Mel Gorman
2007-01-26 21:37                       ` Chris Friesen
2007-01-25 23:46 ` [PATCH 4/8] x86 - Specify amount of kernel memory at boot time Mel Gorman
2007-01-25 23:46 ` [PATCH 5/8] ppc and powerpc " Mel Gorman
2007-01-25 23:46 ` [PATCH 6/8] x86_64 " Mel Gorman
2007-01-25 23:47 ` [PATCH 7/8] ia64 " Mel Gorman
2007-01-25 23:47 ` [PATCH 8/8] Add documentation for additional boot parameter and sysctl Mel Gorman
2007-01-26 11:07 ` [PATCH 0/8] Create ZONE_MOVABLE to partition memory between movable and non-movable pages Andrew Morton
2007-01-26 14:29   ` Mel Gorman
2007-01-26 16:01     ` Christoph Lameter [this message]
2007-01-26 15:56   ` Christoph Lameter
2007-01-26 19:46     ` Andrew Morton
2007-01-26 19:58       ` Christoph Lameter
2007-01-26 20:27         ` Andrew Morton
2007-01-29 21:54           ` Christoph Lameter
2007-01-29 22:36             ` Andrew Morton
2007-01-29 22:45               ` Christoph Lameter
2007-01-29 22:50                 ` Russell King
2007-01-29 23:37                   ` Christoph Lameter
2007-01-30  0:09                     ` Andrew Morton
2007-01-30  9:53                       ` Peter Zijlstra
2007-02-02  5:27                         ` Christoph Lameter
2007-02-02  5:22                       ` Christoph Lameter
2007-01-26 16:21 ` Christoph Lameter
2007-01-26 16:48   ` Mel Gorman
2007-01-26 17:02     ` Christoph Lameter
2007-01-26 17:20       ` 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=Pine.LNX.4.64.0701260756580.6141@schroedinger.engr.sgi.com \
    --to=clameter@sgi.com \
    --cc=akpm@osdl.org \
    --cc=clameter@engr.sgi.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --subject='Re: [PATCH 0/8] Create ZONE_MOVABLE to partition memory between movable and non-movable pages' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).