|
Hi Steve,
I think this has nothing directly to do with xen, it's more a sort of
out of kernel memory in linux.
See below.
Am 25.10.2011 schrieb "Steve Allison <xen-users@xxxxxxxxxxxxxxxxxx>":
> Dear list,
>
> I am seeing an error across multiple machines during heavy I/O, either
> disk or network. The VMs are on different Intel CPUs (Core 2 Quad, Core
> i5, Xeon) with varying boards (Abit, Asus, Supermicro).
>
> Machines that get this error are running either BackupPC, Zabbix (MySQL)
> or SABNZBd. I can also reproduce the error on the Supermicros with a
> looped wget of an ubuntu ISO as they are on Gbit ethernet and will
> download at ~70MB/s.
>
> I prefer Debian, however whilst troubleshooting I have used SUSE kernel
> with Debian and CentOS. I have compiled kernels from 2.6.3x to 3.0.x and
> Xen 4.0.1 to 4.1, and have yet to shake the issue.
>
> The following is an output of the error. This is usually repeated
> several times. There is plenty of RAM available, usually 1GB+ is used in
> buffers/cache, but ~1GB of swap is also available should it be needed.
>
> Its worth noting that the "swapper" portion is usually a random process.
> I've seen it say "mingetty", "rsyslog" amongst others. However "swapper"
> is the most common.
>
> [488054.896037] swapper: page allocation failure. order:0, mode:0x20
The message above comes from the linux kernel function __alloc_pages_nodemask()
which means, no free memory and then dump_stack() is called - see below.
> [488054.896056] Pid: 0, comm: swapper Not tainted 2.6.32-5-amd64 #1
> [488054.896067] Call Trace:
> [488054.896074]<IRQ> [<ffffffff810ba5d6>] ? __alloc_pages_nodemask+0x592/0x5f4
> [488054.896100] [<ffffffff810e6912>] ? new_slab+0x5b/0x1ca
> [488054.896112] [<ffffffff810e6c71>] ? __slab_alloc+0x1f0/0x39b
> [488054.896124] [<ffffffff8124851e>] ? __alloc_skb+0x3e/0x15a
> [488054.896135] [<ffffffff8124851e>] ? __alloc_skb+0x3e/0x15a
> [488054.896146] [<ffffffff810e704d>] ? kmem_cache_alloc_node+0x8b/0x10b
> [488054.896158] [<ffffffff8124851e>] ? __alloc_skb+0x3e/0x15a
> [488054.896170] [<ffffffff8128b0e7>] ? tcp_delack_timer+0x0/0x1fe
> [488054.896182] [<ffffffff812880fd>] ? tcp_send_ack+0x23/0xf4
> [488054.896193] [<ffffffff8128b275>] ? tcp_delack_timer+0x18e/0x1fe
> [488054.896207] [<ffffffff8105a5ff>] ? run_timer_softirq+0x1c9/0x268
> [488054.896220] [<ffffffff81094a9f>] ? handle_IRQ_event+0x117/0x126
> [488054.896234] [<ffffffff81053cab>] ? __do_softirq+0xdd/0x1a6
> [488054.896245] [<ffffffff81096154>] ? handle_percpu_irq+0x4e/0x6a
> [488054.896258] [<ffffffff81011cac>] ? call_softirq+0x1c/0x30
> [488054.896269] [<ffffffff8101322b>] ? do_softirq+0x3f/0x7c
> [488054.896280] [<ffffffff81053b1b>] ? irq_exit+0x36/0x76
Xen is only involved as an interrupt is delivered from hypervisor to the linux
kernel.
> [488054.896291] [<ffffffff811ef48c>] ? xen_evtchn_do_upcall+0x33/0x41
> [488054.896304] [<ffffffff81011cfe>] ? xen_do_hypervisor_callback+0x1e/0x30
> [488054.896313]<EOI> [<ffffffff810093aa>] ? hypercall_page+0x3aa/0x1001
> [488054.896330] [<ffffffff810093aa>] ? hypercall_page+0x3aa/0x1001
> [488054.896343] [<ffffffff8100e160>] ? xen_vcpuop_set_next_event+0x0/0x60
> [488054.896354] [<ffffffff8100dcb3>] ? xen_safe_halt+0xc/0x15
> [488054.896366] [<ffffffff8100be63>] ? xen_idle+0x37/0x40
> [488054.896377] [<ffffffff8100feb1>] ? cpu_idle+0xa2/0xda
> [488054.896388] [<ffffffff814f5cdd>] ? start_kernel+0x3dc/0x3e8
> [488054.896397] Mem-Info:
> [488054.896404] Node 0 DMA per-cpu:
> [488054.896413] CPU 0: hi: 0, btch: 1 usd: 0
> [488054.896422] CPU 1: hi: 0, btch: 1 usd: 0
> [488054.896431] CPU 2: hi: 0, btch: 1 usd: 0
> [488054.896439] CPU 3: hi: 0, btch: 1 usd: 0
> [488054.896447] Node 0 DMA32 per-cpu:
> [488054.896456] CPU 0: hi: 186, btch: 31 usd: 185
> [488054.896465] CPU 1: hi: 186, btch: 31 usd: 172
> [488054.896473] CPU 2: hi: 186, btch: 31 usd: 166
> [488054.896482] CPU 3: hi: 186, btch: 31 usd: 148
> [488054.896494] active_anon:89704 inactive_anon:31826 isolated_anon:0
> [488054.896497] active_file:27715 inactive_file:277856 isolated_file:0
> [488054.896499] unevictable:0 dirty:30010 writeback:0 unstable:0
> [488054.896501] free:2220 slab_reclaimable:11510 slab_unreclaimable:1813
> [488054.896503] mapped:2981 shmem:102 pagetables:1274 bounce:0
> [488054.896532] Node 0 DMA free:6996kB min:36kB low:44kB high:52kB active_anon:0kB inactive_anon:152kB active_file:56kB inactive_file:5148kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:12304kB mlocked:0kB dirty:0kB writeback:0kB mapped:32kB shmem:0kB slab_reclaimable:100kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no
> [488054.896575] lowmem_reserve[]: 0 1751 1751 1751
> [488054.896593] Node 0 DMA32 free:1884kB min:5332kB low:6664kB high:7996kB active_anon:358816kB inactive_anon:127152kB active_file:110804kB inactive_file:1106276kB unevictable:0kB isolated(anon):0kB isolated(file):0kB present:1793760kB mlocked:0kB dirty:120040kB writeback:0kB mapped:11892kB shmem:408kB slab_reclaimable:45940kB slab_unreclaimable:7252kB kernel_stack:1176kB pagetables:5096kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no
> [488054.896639] lowmem_reserve[]: 0 0 0 0
> [488054.896656] Node 0 DMA: 3*4kB 1*8kB 2*16kB 1*32kB 4*64kB 2*128kB 3*256kB 3*512kB 2*1024kB 1*2048kB 0*4096kB = 6996kB
> [488054.896695] Node 0 DMA32: 19*4kB 2*8kB 0*16kB 0*32kB 0*64kB 4*128kB 1*256kB 0*512kB 1*1024kB 0*2048kB 0*4096kB = 1884kB
> [488054.896733] 306011 total pagecache pages
> [488054.896741] 338 pages in swap cache
> [488054.896748] Swap cache stats: add 1457, delete 1119, find 106250/106300
> [488054.896757] Free swap = 1044524kB
> [488054.896764] Total swap = 1048568kB
> [488054.900014] 458752 pages RAM
> [488054.900014] 9907 pages reserved
> [488054.900014] 303804 pages shared
> [488054.900014] 151251 pages non-shared
> [488054.900014] SLUB: Unable to allocate memory on node -1 (gfp=0x20)
> [488054.900014] cache: kmalloc-256, object size: 256, buffer size: 256, default order: 0, min order: 0
> [488054.900014] node 0: slabs: 62, objs: 992, free: 0
>
>
> Any guidance much appreciated.
Maybe you must give more memory to the linux system but I'am not real sure,
beeing not an expert there.
Dietmar.
>
> Regards,
> Steve.
>
>
| 
Home