BUG: soft lockup - CPU#7 stuck for 61s! [kswapd1:85]

Asked by Robert Klahn

kswapd takes 100% of a CPU according to top. Some other processes become unresponsive. Receive repeated messages in dmesg output. This is happening on two servers with very different architectures (one is Intel Xeon from Dell, the other AMD Opteron from HP). The things in common are both are Ubuntu 10.04.1 LTS 2.6.32-27-generic #49-Ubuntu SMP, and both run large nginx reverse proxy caching servers.

Only a powercycle fixes the problem. Machine will not reboot from the command line.

[4968944.303182] BUG: soft lockup - CPU#7 stuck for 61s! [kswapd1:85]
[4968944.307747] Modules linked in: ip6table_filter ip6_tables iptable_filter ip_tables x_tables joydev fbcon tileblit font bitblit softcursor usbhid hid vga16fb dell_wmi vgastate dcdbas psmouse power_meter serio_raw bnx2 lp parport ses enclosure megaraid_sas
[4968944.307766] CPU 7:
[4968944.307767] Modules linked in: ip6table_filter ip6_tables iptable_filter ip_tables x_tables joydev fbcon tileblit font bitblit softcursor usbhid hid vga16fb dell_wmi vgastate dcdbas psmouse power_meter serio_raw bnx2 lp parport ses enclosure megaraid_sas
[4968944.307783] Pid: 85, comm: kswapd1 Not tainted 2.6.32-27-generic #49-Ubuntu PowerEdge R710
[4968944.307786] RIP: 0010:[<ffffffff810f3a59>] [<ffffffff810f3a59>] find_get_pages+0x59/0xf0
[4968944.307793] RSP: 0018:ffff88092af19b20 EFLAGS: 00000282
[4968944.307795] RAX: ffff880597a5c6a8 RBX: ffff88092af19b70 RCX: 0000000000000000
[4968944.307797] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffea001236ff10
[4968944.307799] RBP: ffffffff81012cae R08: 0000000000000000 R09: 000000000000000e
[4968944.307801] R10: 0000000000000000 R11: ffff880597a5c6a8 R12: ffff88092af19be0
[4968944.307804] R13: 0000000000000002 R14: ffffea001705bb50 R15: 0000000000000002
[4968944.307806] FS: 0000000000000000(0000) GS:ffff880028260000(0000) knlGS:0000000000000000
[4968944.307808] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b
[4968944.307810] CR2: 00007f1ddbdb2020 CR3: 0000000001001000 CR4: 00000000000006e0
[4968944.307813] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[4968944.307815] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
[4968944.307817] Call Trace:
[4968944.307822] [<ffffffff811003b0>] ? __remove_mapping+0x90/0x110
[4968944.307825] [<ffffffff810fe0e2>] ? pagevec_lookup+0x22/0x30
[4968944.307828] [<ffffffff810ff263>] ? invalidate_mapping_pages+0x73/0x140
[4968944.307832] [<ffffffff8115a50e>] ? generic_detach_inode+0x19e/0x210
[4968944.307835] [<ffffffff8115b5bd>] ? generic_drop_inode+0x1d/0x80
[4968944.307838] [<ffffffff8115b1fd>] ? prune_icache+0x27d/0x2b0
[4968944.307841] [<ffffffff8115b26f>] ? shrink_icache_memory+0x3f/0x50
[4968944.307844] [<ffffffff811011c5>] ? shrink_slab+0x125/0x190
[4968944.307847] [<ffffffff81103766>] ? balance_pgdat+0x526/0x6d0
[4968944.307850] [<ffffffff811008c0>] ? isolate_pages_global+0x0/0x50
[4968944.307853] [<ffffffff81103a0e>] ? kswapd+0xfe/0x150
[4968944.307858] [<ffffffff810846a0>] ? autoremove_wake_function+0x0/0x40
[4968944.307861] [<ffffffff81103910>] ? kswapd+0x0/0x150
[4968944.307864] [<ffffffff81084326>] ? kthread+0x96/0xa0
[4968944.307868] [<ffffffff810131ea>] ? child_rip+0xa/0x20
[4968944.307871] [<ffffffff81084290>] ? kthread+0x0/0xa0

Question information

Language:
English Edit question
Status:
Answered
For:
Ubuntu linux-meta Edit question
Assignee:
No assignee Edit question
Last query:
Last reply:
Revision history for this message
Vin Shankar (v-shankar) said :
#1

Thanks for reporting this and helping to make Ubuntu better. As this is in fact a bug report rather than a support question, I'm converting it to that.

Revision history for this message
Jes Slow (cluelesscoder) said :
#2

This question should be closed.

Can you help with this problem?

Provide an answer of your own, or ask Robert Klahn for more information if necessary.

To post a message you must log in.