今天过来发现泰国人说服务器出问题了,结果上去一看dmesg里输出了一串信息如下
INFO: task kacpi_notify:155 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kacpi_notify D ffff88042fc28400 0 155 2 0x00000000
ffff88041da19b30 0000000000000046 0000000000000000 ffff88041da19af4
ffff88041d535ed0 ffff88042fc28400 ffff880028296980 000000012e96bbb3
ffff88041da150e8 ffff88041da19fd8 0000000000010518 ffff88041da150e8
Call Trace:
[<ffffffff814c8fc5>] schedule_timeout+0x225/0x2f0
[<ffffffff81061321>] ? __enqueue_rt_entity+0x2a1/0x2e0
[<ffffffff81061768>] ? enqueue_rt_entity+0x68/0x80
[<ffffffff814c8c33>] wait_for_common+0x123/0x180
[<ffffffff8105c490>] ? default_wake_function+0x0/0x20
[<ffffffff814c8d4d>] wait_for_completion+0x1d/0x20
[<ffffffff8109198b>] kthread_stop+0x4b/0xd0
[<ffffffffa014542a>] acpi_pad_idle_cpus+0xbc/0xd6 [acpi_pad]
[<ffffffffa014570c>] acpi_pad_handle_notify+0x96/0x196 [acpi_pad]
[<ffffffff810116e0>] ? __switch_to+0xd0/0x320
[<ffffffff81059d12>] ? finish_task_switch+0x42/0xd0
[<ffffffff814c8286>] ? thread_return+0x4e/0x778
[<ffffffff812ca0ad>] ? acpi_hw_write_port+0x32/0x87
[<ffffffff812b0e7c>] ? acpi_os_execute_deferred+0x0/0x36
[<ffffffffa014582a>] acpi_pad_notify+0x1e/0x5b [acpi_pad]
[<ffffffff812c12ba>] acpi_ev_notify_dispatch+0x64/0x72
[<ffffffff812b0ea5>] acpi_os_execute_deferred+0x29/0x36
[<ffffffff8108c610>] worker_thread+0x170/0x2a0
[<ffffffff81091ca0>] ? autoremove_wake_function+0x0/0x40
[<ffffffff8108c4a0>] ? worker_thread+0x0/0x2a0
[<ffffffff81091936>] kthread+0x96/0xa0
[<ffffffff810141ca>] child_rip+0xa/0x20
[<ffffffff810918a0>] ? kthread+0x0/0xa0
[<ffffffff810141c0>] ? child_rip+0x0/0x20
在网上搜了一圈,发现都不是很靠谱,因为发生问题的全是acpi相关的服务,所以就把acpid关闭了,重启服务器之后发现一切正常。
于是猜想可能是acpi出问题导致了硬盘被关闭,之前还发生过acpi导致服务器重启的情况,这玩意在centos下似乎极不好使呀
把acpid关闭还是没有解决问题,于是再试了一下在内核中加入参数acpi_pad.disable=1再看看状态