linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Mel Gorman <mel@csn.ul.ie>
To: Andy Whitcroft <apw@shadowen.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Bart Van Assche <bart.vanassche@gmail.com>,
	bugme-daemon@bugzilla.kernel.org, linux-mm@kvack.org
Subject: Re: [Bug 9941] New: Zone "Normal" missing in /proc/zoneinfo
Date: Wed, 13 Feb 2008 15:38:29 +0000	[thread overview]
Message-ID: <20080213153829.GB1328@csn.ul.ie> (raw)
In-Reply-To: <20080213152302.GA32416@shadowen.org>

On (13/02/08 15:23), Andy Whitcroft didst pronounce:
> On Wed, Feb 13, 2008 at 11:52:25AM +0000, Mel Gorman wrote:
> 
> > > > > > $ grep zone /proc/zoneinfo
> > > > > >
> > > > > > Output with 2.6.24:
> > > > > > Node 0, zone      DMA
> > > > > > Node 0, zone    DMA32
> > > > > > Node 0, zone   Normal
> > > > > >
> > > > > > Output with 2.6.24.2:
> > > > > > Node 0, zone      DMA
> > > > > > Node 0, zone    DMA32
> > > > > >
> > 
> > The greater surprise to me is that "Normal" ever appeared. The zone is empty,
> > why is information appearing about it? I checked the dmesg for an x86_64
> > machine with 1GB of RAM that was running 2.6.24 here and there is no sign
> > of Normal.
> > 
> > mel@arnold:/tmp$ grep zone zoneinfo.before 
> > Node 0, zone      DMA
> > Node 0, zone    DMA32
> > 
> > The loop looks like
> > 
> >         for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
> >                 if (!populated_zone(zone))
> >                         continue;
> > 
> > It makes no sense for it to show up *unless* 2.6.24 was compiled as a 32
> > bit kernel by accident. Could this be the case?
> 
> Interestingly I would not expect to see DMA32 at all if the kernel was
> compiled 32 bit as CONFIG_DMA32 defaults to X86_64.
> 

D'oh, of course. This couldn't have been a 32 bit kernel.

> Could we simply have less ram detected/present in this boot.  That would
> make the zone dissappear if it became empty.
> 
> The e820 output as reported by the old and new kernels would confirm the
> memory size is detected the same.  Also some idea of how much memory is
> supposed be in the machine might shed some light.  If the overall is near
> to 4GB it may be remapping for the AGP apature or something similar which
> is shifting memory up above the boundary.
> 


-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab

--
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:[~2008-02-13 15:38 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <bug-9941-27@http.bugzilla.kernel.org/>
2008-02-12 18:06 ` [Bug 9941] New: Zone "Normal" missing in /proc/zoneinfo Andrew Morton
2008-02-13  7:39   ` Bart Van Assche
2008-02-13  7:45     ` Andrew Morton
2008-02-13 11:52       ` Mel Gorman
2008-02-13 13:45         ` Bart Van Assche
2008-02-13 14:34           ` Mel Gorman
2008-02-13 15:32             ` Bart Van Assche
2008-02-13 15:23         ` Andy Whitcroft
2008-02-13 15:38           ` Mel Gorman [this message]

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=20080213153829.GB1328@csn.ul.ie \
    --to=mel@csn.ul.ie \
    --cc=akpm@linux-foundation.org \
    --cc=apw@shadowen.org \
    --cc=bart.vanassche@gmail.com \
    --cc=bugme-daemon@bugzilla.kernel.org \
    --cc=linux-mm@kvack.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 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).