linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: CAI Qian <caiqian@redhat.com>
To: David Rientjes <rientjes@google.com>
Cc: linux-mm <linux-mm@kvack.org>
Subject: Re: known oom issues on numa in -mm tree?
Date: Tue, 11 Jan 2011 04:46:27 -0500 (EST)	[thread overview]
Message-ID: <976317569.44499.1294739187129.JavaMail.root@zmail06.collab.prod.int.phx2.redhat.com> (raw)
In-Reply-To: <1182272788.40910.1294716934667.JavaMail.root@zmail06.collab.prod.int.phx2.redhat.com>

BTW, the latest linux-next also had the similar issue.

- kswapd was running for a long time.

runnable tasks:
            task   PID         tree-key  switches  prio     exec-runtime         sum-exec        sum-sleep
----------------------------------------------------------------------------------------------------------
R        kswapd1    82    564957.671501     32922   120    564986.657154   1188257.259742   3555627.915255

- it was looping for drain_local_pages.

oom02           R  running task        0  2023   1969 0x00000088
 0000000000000282 ffff88041d219df0 ffff88041fbf8ef0 ffffffff81100800
 ffff880418ab5b18 0000000000000282 ffffffff8100c9ee ffff880418ab5ba8
 0000000087654321 0000000000000000 ffff880000000000 0000000000000001
Call Trace:
 [<ffffffff81100800>] ? drain_local_pages+0x0/0x20
 [<ffffffff8100c9ee>] ? apic_timer_interrupt+0xe/0x20
 [<ffffffff81097ea6>] ? smp_call_function_many+0x1b6/0x210
 [<ffffffff81097e82>] ? smp_call_function_many+0x192/0x210
 [<ffffffff81100800>] ? drain_local_pages+0x0/0x20
 [<ffffffff81097f22>] ? smp_call_function+0x22/0x30
 [<ffffffff81068184>] ? on_each_cpu+0x24/0x50
 [<ffffffff810fe68c>] ? drain_all_pages+0x1c/0x20
 [<ffffffff81100d04>] ? __alloc_pages_nodemask+0x4e4/0x840
 [<ffffffff81138e09>] ? alloc_page_vma+0x89/0x140
 [<ffffffff8111c481>] ? handle_mm_fault+0x871/0xd80
 [<ffffffff814a4ecd>] ? schedule+0x3fd/0x980
 [<ffffffff8100c9ee>] ? apic_timer_interrupt+0xe/0x20
 [<ffffffff8100c9ee>] ? apic_timer_interrupt+0xe/0x20
 [<ffffffff814aadd3>] ? do_page_fault+0x143/0x4b0
 [<ffffffff8100a7b4>] ? __switch_to+0x194/0x320
 [<ffffffff814a4ecd>] ? schedule+0x3fd/0x980
 [<ffffffff814a7ad5>] ? page_fault+0x25/0x30

- although the local pages were low.

Node 1 Normal free:8052kB min:8136kB low:10168kB high:12204kB active_anon:8026400kB inactive_anon:0kB active_file:0kB inactive_file:20kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:8273920kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:116kB slab_reclaimable:23728kB slab_unreclaimable:175932kB kernel_stack:176kB pagetables:17136kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:10 all_unreclaimable? no
lowmem_reserve[]: 0 0 0 0
Node 0 DMA: 0*4kB 0*8kB 1*16kB 0*32kB 2*64kB 1*128kB 1*256kB 0*512kB 1*1024kB 1*2048kB 3*4096kB = 15888kB
Node 0 DMA32: 10*4kB 10*8kB 7*16kB 8*32kB 4*64kB 8*128kB 10*256kB 2*512kB 4*1024kB 2*2048kB 534*4096kB = 2200808kB
Node 0 Normal: 519*4kB 824*8kB 440*16kB 202*32kB 87*64kB 29*128kB 15*256kB 11*512kB 3*1024kB 8*2048kB 1065*4096kB = 4422620kB
Node 1 Normal: 579*4kB 205*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 1*4096kB = 8052kB

It could also be reproduced by using mempolicy alone. The test just hung at memset() while allocating memory.

set_mempolicy(MPOL_BIND, &nmask, MAXNODES);
while(1) {
    s = mmap(NULL, length, PROT_READ|PROT_WRITE,
                MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
    memset(s, '\a', length);
}

CAI Qian

--
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/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2011-01-11  9:46 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-06  8:03 known oom issues on numa in -mm tree? CAI Qian
2011-01-11  0:04 ` David Rientjes
2011-01-11  1:36   ` CAI Qian
2011-01-11  3:18     ` David Rientjes
2011-01-11  3:35       ` CAI Qian
2011-01-11  9:46         ` CAI Qian [this message]
2011-01-11  9:55           ` CAI Qian
2011-01-11 10:11             ` CAI Qian
2011-01-26 10:45           ` David Rientjes
2011-01-28  6:47             ` CAI Qian
2011-01-28 10:31               ` David Rientjes
2011-01-28 14:33                 ` CAI Qian
2011-01-28 14:36                   ` CAI Qian

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=976317569.44499.1294739187129.JavaMail.root@zmail06.collab.prod.int.phx2.redhat.com \
    --to=caiqian@redhat.com \
    --cc=linux-mm@kvack.org \
    --cc=rientjes@google.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 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).