kernel-testers.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: Gene Heskett <gene.heskett-H+0wwilmMs3R7s880joybQ@public.gmane.org>
Cc: John Stoffel <john-HgN6juyGXH5AfugRpC6u6w@public.gmane.org>,
	Linux Kernel list
	<linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	"linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org"
	<linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
	Minchan Kim <minchan.kim-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
	"Rafael J. Wysocki" <rjw-KKrjLPT3xs0@public.gmane.org>,
	Kernel Testers List
	<kernel-testers-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	David Howells <dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	KOSAKI Motohiro
	<kosaki.motohiro-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
Subject: Re: OOM killer in 2.6.31-rc2
Date: Fri, 10 Jul 2009 21:24:55 +0800	[thread overview]
Message-ID: <20090710132455.GB17773@localhost> (raw)
In-Reply-To: <200907091703.06691.gene.heskett-H+0wwilmMs3R7s880joybQ@public.gmane.org>

On Thu, Jul 09, 2009 at 05:03:06PM -0400, Gene Heskett wrote:
> On Thursday 09 July 2009, John Stoffel wrote:
> >>>>>> "Gene" == Gene Heskett <gene.heskett-H+0wwilmMs3R7s880joybQ@public.gmane.org> writes:
> >
> >Gene> On Wednesday 08 July 2009, Wu Fengguang wrote:
> >>> On Wed, Jul 08, 2009 at 01:15:15PM +0800, Wu Fengguang wrote:
> >>>> On Tue, Jul 07, 2009 at 11:42:07PM -0400, Gene Heskett wrote:
> >
> >Gene> [...]
> >
> >>>> I guess your near 800MB slab cache is somehow under scanned.
> >>>
> >>> Gene, can you run .31 with this patch? When OOM happens, it will tell
> >>> us whether the majority slab pages are reclaimable. Another way to
> >>> find things out is to run `slabtop` when your system is moderately
> >>> loaded.
> >
> >Gene> Its been running continuously, and after 24 hours is now showing:
> >
> >Just wondering, is this your M2N-SLI Deluxe board?
> Yes.
> >I've got the same
> >board, with 4Gb of RAM and I haven't noticed any loss of RAM from my
> >looking (quickly) at top output.
> 
> I am short approximately 500 megs according to top:
> Mem:   3634228k total,  3522984k used,   111244k free,   308096k buffers
> Swap:  8385912k total,      568k used,  8385344k free,  2544716k cached
> 
> From dmesg:
> [    0.000000] TOM2: 0000000120000000 aka 4608M  <what is this?

That 4608M includes memory hole I guess.

> [...]
> [    0.000000] 2694MB HIGHMEM available.
> [    0.000000] 887MB LOWMEM available.
> 
> The bios signon does say 4092M IIRC.
> 
> >But I also haven't bothered to upgrade the BIOS on this board at all
> >since I got it back in March of 2008.  No need in my book so far.
> 
> I had been running the original bios, #1502, because 1604 and 1701 had very 
> poor uptimes.  1502 caused an oops about 15 lines into the boot but that 
> triggered a remap and it was bulletproof after that running a 32 bit 64G+PAE 
> kernel.  (I haven't quite made the jump to a 64 bit install, yet...)
> 
> >> uname -a
> >
> >Linux sail 2.6.31-rc1 #6 SMP PREEMPT Wed Jun 24 21:40:33 EDT 2009 x86_64
> > GNU/Linux
> 
> Linux coyote.coyote.den 2.6.31-rc2 #4 SMP PREEMPT Wed Jul 8 09:37:15 EDT 2009 
> i686 athlon i386 GNU/Linux
> >> cat /proc/meminfo
> >
> >MemTotal:        3987068 kB
> >MemFree:          170608 kB
> >Buffers:          355272 kB
> >Cached:          2034416 kB
> >SwapCached:            0 kB
> >Active:          1836284 kB
> >Inactive:        1482444 kB
> >Active(anon):     857076 kB
> >Inactive(anon):    86112 kB
> >Active(file):     979208 kB
> >Inactive(file):  1396332 kB
> >Unevictable:        3972 kB
> >Mlocked:            3972 kB
> >SwapTotal:             0 kB
> >SwapFree:              0 kB
> >Dirty:                36 kB
> >Writeback:             0 kB
> >AnonPages:        933160 kB
> >Mapped:           141188 kB
> >Slab:             398124 kB
> >SReclaimable:     348212 kB
> >SUnreclaim:        49912 kB
> >PageTables:        30916 kB
> >NFS_Unstable:          0 kB
> >Bounce:                0 kB
> >WritebackTmp:          0 kB
> >CommitLimit:     1993532 kB
> >Committed_AS:    1570980 kB
> >VmallocTotal:   34359738367 kB
> >VmallocUsed:      116160 kB
> >VmallocChunk:   34359584603 kB
> >DirectMap4k:        4992 kB
> >DirectMap2M:     4188160 kB
> 
> MemTotal:        3634228 kB
> MemFree:          114312 kB
> Buffers:          309088 kB
> Cached:          2541864 kB
> SwapCached:           72 kB
> Active:          1584988 kB
> Inactive:        1739508 kB
> Active(anon):     354584 kB
> Inactive(anon):   120072 kB
> Active(file):    1230404 kB
> Inactive(file):  1619436 kB
> Unevictable:         100 kB
> Mlocked:             100 kB
> HighTotal:       2759560 kB
> HighFree:          13020 kB
> LowTotal:         874668 kB
> LowFree:          101292 kB
> SwapTotal:       8385912 kB
> SwapFree:        8385344 kB
> Dirty:                52 kB
> Writeback:             0 kB
> AnonPages:        473576 kB
> Mapped:           111332 kB
> Slab:             143624 kB
> SReclaimable:     127820 kB
> SUnreclaim:        15804 kB
> PageTables:         8776 kB
> NFS_Unstable:          0 kB
> Bounce:                0 kB
> WritebackTmp:          0 kB
> CommitLimit:    10203024 kB
> Committed_AS:    1029032 kB
> VmallocTotal:     122880 kB
> VmallocUsed:       44180 kB
> VmallocChunk:      65924 kB
> HugePages_Total:       0
> HugePages_Free:        0
> HugePages_Rsvd:        0
> HugePages_Surp:        0
> Hugepagesize:       4096 kB
> DirectMap4k:        8184 kB
> DirectMap4M:      901120 kB
> 
> Huge diffs it appears. ??

Most relevant ones:

- 300+MB >4G memory is not reachable by kernel and user space
- 2.7GB high memory is not usable for slab caches and some other
  kernel users

Thanks,
Fengguang

      parent reply	other threads:[~2009-07-10 13:24 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <200907061056.00229.gene.heskett@verizon.net>
     [not found] ` <200907061056.00229.gene.heskett-H+0wwilmMs3R7s880joybQ@public.gmane.org>
2009-07-07  6:12   ` OOM killer in 2.6.31-rc2 Wu Fengguang
2009-07-07 14:57     ` Gene Heskett
2009-07-08  2:17       ` Wu Fengguang
2009-07-08  3:42         ` Gene Heskett
2009-07-08  5:15           ` Wu Fengguang
2009-07-08  7:55             ` Wu Fengguang
2009-07-08 14:22               ` Gene Heskett
2009-07-09 14:42               ` Gene Heskett
2009-07-09 20:41                 ` John Stoffel
     [not found]                   ` <19030.22024.132029.196682-HgN6juyGXH5AfugRpC6u6w@public.gmane.org>
2009-07-09 21:03                     ` Gene Heskett
2009-07-10 13:09                       ` John Stoffel
     [not found]                         ` <19031.15772.404288.544946-HgN6juyGXH5AfugRpC6u6w@public.gmane.org>
2009-07-10 13:18                           ` Wu Fengguang
     [not found]                       ` <200907091703.06691.gene.heskett-H+0wwilmMs3R7s880joybQ@public.gmane.org>
2009-07-10 13:24                         ` Wu Fengguang [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=20090710132455.GB17773@localhost \
    --to=fengguang.wu-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
    --cc=dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=gene.heskett-H+0wwilmMs3R7s880joybQ@public.gmane.org \
    --cc=john-HgN6juyGXH5AfugRpC6u6w@public.gmane.org \
    --cc=kernel-testers-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=kosaki.motohiro-+CUm20s59erQFUHtdCDX3A@public.gmane.org \
    --cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
    --cc=minchan.kim-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org \
    --cc=rjw-KKrjLPT3xs0@public.gmane.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).