Comment 60 for bug 1861359

Sultan put together a kernel with some debugging for me:

[101616.889859] __alloc_pages_nodemask: stall of 3683ms for order-0, mask: 0x100dca
[101616.889863] Call Trace:
[101616.889880] __alloc_pages_nodemask+0x34f/0x3b0
[101616.889887] alloc_pages_vma+0x7f/0x200
[101616.889893] do_anonymous_page+0x118/0x650
[101616.889898] __handle_mm_fault+0x760/0x7a0
[101616.889903] handle_mm_fault+0xca/0x200
[101616.889911] do_user_addr_fault+0x1f9/0x450
[101616.889917] __do_page_fault+0x58/0x90
[101616.889925] ? syscall_slow_exit_work+0x123/0x150
[101616.889930] do_page_fault+0x2c/0xe0
[101616.889938] page_fault+0x34/0x40
[101616.889943] RIP: 0033:0x7f0e38f80190
[101616.889949] Code: 78 04 41 bf 01 00 00 00 44 39 ef 0f 87 4f 01 00 00 41 83 c5 01 48 ba 00 00 00 00 00 80 fa ff 44 89 ee 48 8d 0c f9 48 c1 e6 03 <48> 89 11 48 83 c1 08 48 8b 7b 18 48 01 f7 48 39 f9 75 ed 44 89 68
[101616.889951] RSP: 002b:00007ffd1b151780 EFLAGS: 00010202
[101616.889955] RAX: 00007f0e27619000 RBX: 000006b3e615a810 RCX: 00007f0e27634000
[101616.889958] RDX: fffa800000000000 RSI: 000000000001aff8 RDI: 00000000000035fe
[101616.889960] RBP: 0000000000006bfd R08: 00007ffd1b151820 R09: 00000000292d95be
[101616.889962] R10: 0000000000000011 R11: 00007f0e2632d000 R12: 00007f0e3082e000
[101616.889964] R13: 00000000000035ff R14: 0000000000000001 R15: 0000000000000001

The trigger in this case was firefox loading https://code.launchpad.net/~ahasenack/qa-regression-testing/+git/qa-regression-testing/+merge/381582

Recent calls to journalctl > /tmp/foo had lead to a minute-long hang (though the mouse did make ~10ms motion every six or seven seconds), swap growth from 1MB to 62M, but no stacktraces.

Thanks