On Mon, Jun 15, 2009 at 03:51:45PM +0300, Giorgos Mavrikas wrote:
> Package: linux-image-amd64
> Version: 2.6.26-2
> Severity: normal
>
> I run a standard amd64 kernel in a core 2 duo machine under heavy network traffic, and I keep getting tons of these (more than 28 in less that 2 days) the last few weeks, regardless of all reboots:
>
> [186974.720505] swapper: page allocation failure. order:0, mode:0x20
> [186974.720543] Pid: 0, comm: swapper Not tainted 2.6.26-2-amd64 #1
> [186974.720577]
> [186974.720578] Call Trace:
> [186974.720626] <IRQ> [<ffffffff80276b64>] __alloc_pages_internal+0x3a6/0x3bf
> [186974.720683] [<ffffffff802954bc>] kmem_getpages+0x96/0x164
> [186974.720719] [<ffffffff80295b1c>] fallback_alloc+0x16b/0x1e1
> [186974.720758] [<ffffffff8029572e>] kmem_cache_alloc_node+0x105/0x138
> [186974.720797] [<ffffffff803b5a2f>] __alloc_skb+0x3c/0x12d
> [186974.720834] [<ffffffff803f0497>] tcp_delack_timer+0x0/0x1eb
> [186974.720869] [<ffffffff803eda19>] tcp_send_ack+0x28/0xca
> [186974.720905] [<ffffffff803f061a>] tcp_delack_timer+0x183/0x1eb
> [186974.720940] [<ffffffff803f0497>] tcp_delack_timer+0x0/0x1eb
> [186974.720977] [<ffffffff8023ca35>] run_timer_softirq+0x16a/0x1e2
> [186974.721015] [<ffffffff802393fb>] __do_softirq+0x5c/0xd1
> [186974.721052] [<ffffffff8020d2cc>] call_softirq+0x1c/0x28
> [186974.721087] [<ffffffff8020f3d0>] do_softirq+0x3c/0x81
> [186974.721121] [<ffffffff8023935b>] irq_exit+0x3f/0x83
> [186974.721154] [<ffffffff8020f630>] do_IRQ+0xb9/0xd9
> [186974.721188] [<ffffffff80212c37>] mwait_idle+0x0/0x4d
> [186974.721222] [<ffffffff8020c46d>] ret_from_intr+0x0/0x19
> [186974.721255] <EOI> [<ffffffff80212c78>] mwait_idle+0x41/0x4d
> [186974.721298] [<ffffffff8020ac79>] cpu_idle+0x89/0xb3

Hi,
The next release of Debian (6.0, code name Squeeze) will be based
on 2.6.32. Please test the current 2.6.32 from unstable/testing and tell
us whether the problem persists. If so, we should report it upstream
to the kernel.org developers.

The 2.6.32 kernel is available from packages.debian.org and can
be installed in both Debian stable, testing and unstable
installations.

Thanks,
Moritz



--
To UNSUBSCRIBE, email to debian-kernel-REQUEST@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
Archive: 20100301224746.GA15826@galadriel.inutil.org">http://lists.debian.org/20100301224746.GA15826@galadriel.inutil.org

I have the exact same problem as the original reporter with Debian lenny
and kernel 2.6.32-bpo.3-amd64 using a Core 2 Duo machine with 2GB of
RAM. I tested the RAM using memtest86 and did not find problems.

The failure seems to occur whenever heavy load is present, e.g.,
transferring big amounts of data between harddrives or the final linking
of a libwebkit build. Please find enclosed the relevant part of dmesg.
I'll be happy to provide additional information, please let me know
what could be helpful.

[ 889.310248] swapper: page allocation failure. order:2, mode:0x4020
[ 889.310253] Pid: 0, comm: swapper Not tainted 2.6.32-bpo.3-amd64 #1
[ 889.310255] Call Trace:
[ 889.310257] <IRQ> [<ffffffff810b9465>] ?
__alloc_pages_nodemask+0x55b/0x5ce
[ 889.310283] [<ffffffffa031265f>] ? iwl_rx_allocate+0x9f/0x2bf
[iwlcore]
[ 889.310288] [<ffffffff810e50c2>] ? kmalloc_large_node+0x5d/0x9a
[ 889.310292] [<ffffffff8123c654>] ? __alloc_skb+0x69/0x15a
[ 889.310298] [<ffffffffa031265f>] ? iwl_rx_allocate+0x9f/0x2bf
[iwlcore]
[ 889.310305] [<ffffffffa034d382>] ? iwl_rx_handle+0x1a0/0x214 [iwlagn]
[ 889.310310] [<ffffffffa031288d>] ? iwl_rx_replenish_now+0xe/0x17
[iwlcore]
[ 889.310315] [<ffffffffa034dadd>] ? iwl_irq_tasklet+0x2e1/0x40f
[iwlagn]
[ 889.310320] [<ffffffff8105229e>] ? tasklet_action+0x78/0xce
[ 889.310323] [<ffffffff81053961>] ? __do_softirq+0xdd/0x1a0
[ 889.310328] [<ffffffffa030e329>] ? iwl_isr_ict+0xe0/0x200 [iwlcore]
[ 889.310332] [<ffffffff81011cac>] ? call_softirq+0x1c/0x30
[ 889.310335] [<ffffffff81013903>] ? do_softirq+0x3f/0x7c
[ 889.310338] [<ffffffff810537d0>] ? irq_exit+0x36/0x76
[ 889.310341] [<ffffffff81012ffa>] ? do_IRQ+0xa0/0xb6
[ 889.310344] [<ffffffff810114d3>] ? ret_from_intr+0x0/0x11
[ 889.310345] <EOI> [<ffffffff8102b5b4>] ?
hpet_legacy_next_event+0x0/0x7
[ 889.310357] [<ffffffffa02954e6>] ? acpi_idle_enter_bm+0x26a/0x29e
[processor]
[ 889.310361] [<ffffffffa02954df>] ? acpi_idle_enter_bm+0x263/0x29e
[processor]
[ 889.310366] [<ffffffff8122dadb>] ? cpuidle_idle_call+0x95/0xee
[ 889.310370] [<ffffffff8100fe90>] ? cpu_idle+0xa2/0xda
[ 889.310372] Mem-Info:
[ 889.310373] Node 0 DMA per-cpu:
[ 889.310376] CPU 0: hi: 0, btch: 1 usd: 0
[ 889.310378] CPU 1: hi: 0, btch: 1 usd: 0
[ 889.310379] Node 0 DMA32 per-cpu:
[ 889.310382] CPU 0: hi: 186, btch: 31 usd: 201
[ 889.310384] CPU 1: hi: 186, btch: 31 usd: 173
[ 889.310389] active_anon:333238 inactive_anon:111739 isolated_anon:32
[ 889.310390] active_file:254 inactive_file:310 isolated_file:0
[ 889.310391] unevictable:0 dirty:0 writeback:95737 unstable:0
[ 889.310391] free:2745 slab_reclaimable:1436 slab_unreclaimable:24224
[ 889.310392] mapped:461 shmem:48 pagetables:2655 bounce:0
[ 889.310394] Node 0 DMA free:7768kB min:40kB low:48kB high:60kB
active_anon:3672kB inactive_anon:3816kB active_file:8kB
inactive_file:60kB unevictable:0kB isolated(anon):0kB isolated(file):0kB
present:15364kB mlocked:0kB dirty:0kB writeback:896kB mapped:0kB
shmem:0kB slab_reclaimable:0kB slab_unreclaimable:436kB kernel_stack:0kB
pagetables:12kB unstable:0kB bounce:0kB writeback_tmp:0kB
pages_scanned:0 all_unreclaimable? no
[ 889.310404] lowmem_reserve[]: 0 1935 1935 1935
[ 889.310407] Node 0 DMA32 free:3212kB min:5608kB low:7008kB high:8412kB
active_anon:1329280kB inactive_anon:443140kB active_file:1008kB
inactive_file:1180kB unevictable:0kB isolated(anon):128kB
isolated(file):0kB present:1981992kB mlocked:0kB dirty:0kB
writeback:382052kB mapped:1844kB shmem:192kB slab_reclaimable:5744kB
slab_unreclaimable:96460kB kernel_stack:1160kB pagetables:10608kB
unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0
all_unreclaimable? no
[ 889.310417] lowmem_reserve[]: 0 0 0 0
[ 889.310420] Node 0 DMA: 10*4kB 12*8kB 5*16kB 4*32kB 8*64kB 2*128kB
0*256kB 1*512kB 2*1024kB 2*2048kB 0*4096kB = 7768kB
[ 889.310429] Node 0 DMA32: 555*4kB 0*8kB 0*16kB 1*32kB 1*64kB 1*128kB
1*256kB 1*512kB 0*1024kB 0*2048kB 0*4096kB = 3212kB
[ 889.310437] 97175 total pagecache pages
[ 889.310438] 96540 pages in swap cache
[ 889.310440] Swap cache stats: add 137591, delete 41051, find 31/38
[ 889.310442] Free swap = 5430040kB
[ 889.310443] Total swap = 5980152kB
[ 889.314144] 507392 pages RAM
[ 889.314144] 9875 pages reserved
[ 889.314144] 5783 pages shared
[ 889.314144] 493369 pages non-shared
[ 889.314144] iwlagn 0000:03:00.0: Failed to allocate SKB buffer with
GFP_ATOMIC. Only 0 free buffers remaining.



--
To UNSUBSCRIBE, email to debian-kernel-REQUEST@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
Archive: S4MTVppB.1272614867.2996750.michalda@mail.asamnet. de">http://lists.debian.org/S4MTVppB.1272614867.2996750.michalda@mail.asamnet. de

On Fri, 2010-04-30 at 10:07 +0200, Daniel Michalik wrote:
> I have the exact same problem as the original reporter with Debian lenny
> and kernel 2.6.32-bpo.3-amd64 using a Core 2 Duo machine with 2GB of
> RAM. I tested the RAM using memtest86 and did not find problems.
[...]

You are seeing a different bug, already reported as #572932.

Ben.

--
Ben Hutchings
Once a job is fouled up, anything done to improve it makes it worse.