Ошибки NMI received for unknown reason 21 и 31 и Do you have a strange power saving mode enabled

[malike 3]

Столкнулся с проблемой, на одном из серверов под управлением ОС

root@storage:/etc/default$ uname -a
Linux storage 3.16.0-4-amd64 #1 SMP Debian 3.16.7-ckt11-1+deb8u5 (2015-10-09) x86_64 GNU/Linux

Стали появляться ошибки в консоле и соответствено  в /var/log/kern.log

Также на сервере были замечены "фризы" примерно в тоже время когда возникали эти ошибки. Решил начать бороться с проблемой.

Sep 20 21:32:33 storage kernel: [13914.963589] Uhhuh. NMI received for unknown reason 21 on CPU 22.
Sep 20 21:32:33 storage kernel: [13914.963605] Do you have a strange power saving mode enabled?
Sep 20 21:32:33 storage kernel: [13914.963617] Dazed and confused, but trying to continue
Sep 20 22:06:29 storage kernel: [15951.383028] Uhhuh. NMI received for unknown reason 31 on CPU 4.
Sep 20 22:06:29 storage kernel: [15951.383045] Do you have a strange power saving mode enabled?
Sep 20 22:06:29 storage kernel: [15951.383056] Dazed and confused, but trying to continue
Sep 20 23:26:10 storage kernel: [20733.534376] Uhhuh. NMI received for unknown reason 31 on CPU 11.
Sep 20 23:26:10 storage kernel: [20733.534391] Do you have a strange power saving mode enabled?
Sep 20 23:26:10 storage kernel: [20733.534403] Dazed and confused, but trying to continue
Sep 21 00:58:10 storage kernel: [26253.912410] Uhhuh. NMI received for unknown reason 21 on CPU 2.
Sep 21 00:58:10 storage kernel: [26253.912427] Do you have a strange power saving mode enabled?
Sep 21 00:58:10 storage kernel: [26253.912439] Dazed and confused, but trying to continue
Sep 21 01:04:58 storage kernel: [26661.671672] Uhhuh. NMI received for unknown reason 31 on CPU 9.
Sep 21 01:04:58 storage kernel: [26661.671688] Do you have a strange power saving mode enabled?
Sep 21 01:04:58 storage kernel: [26661.671700] Dazed and confused, but trying to continue
Sep 21 01:20:11 storage kernel: [27574.823938] i2c /dev entries driver
Sep 21 04:14:55 storage kernel: [38059.886166] Uhhuh. NMI received for unknown reason 21 on CPU 16.
Sep 21 04:14:55 storage kernel: [38059.886183] Do you have a strange power saving mode enabled?
Sep 21 04:14:55 storage kernel: [38059.886194] Dazed and confused, but trying to continue
Sep 21 09:15:01 storage kernel: [56067.772107] Uhhuh. NMI received for unknown reason 31 on CPU 14.
Sep 21 09:15:01 storage kernel: [56067.772125] Do you have a strange power saving mode enabled?
Sep 21 09:15:01 storage kernel: [56067.772137] Dazed and confused, but trying to continue
Sep 21 16:07:39 storage kernel: [80827.663209] Uhhuh. NMI received for unknown reason 21 on CPU 4.
Sep 21 16:07:39 storage kernel: [80827.663241] Do you have a strange power saving mode enabled?
Sep 21 16:07:39 storage kernel: [80827.663267] Dazed and confused, but trying to continue
Sep 21 23:34:23 storage kernel: [107634.161799] Uhhuh. NMI received for unknown reason 21 on CPU 9.
Sep 21 23:34:23 storage kernel: [107634.161829] Do you have a strange power saving mode enabled?
Sep 21 23:34:23 storage kernel: [107634.161855] Dazed and confused, but trying to continue
Sep 22 00:19:10 storage kernel: [110321.847546] Uhhuh. NMI received for unknown reason 21 on CPU 2.
Sep 22 00:19:10 storage kernel: [110321.847578] Do you have a strange power saving mode enabled?
Sep 22 00:19:10 storage kernel: [110321.847605] Dazed and confused, but trying to continue
Sep 22 01:37:26 storage kernel: [115017.753402] Uhhuh. NMI received for unknown reason 31 on CPU 1.
Sep 22 01:37:26 storage kernel: [115017.753433] Do you have a strange power saving mode enabled?
Sep 22 01:37:26 storage kernel: [115017.753460] Dazed and confused, but trying to continue
Sep 22 02:23:08 storage kernel: [117760.603696] Uhhuh. NMI received for unknown reason 31 on CPU 2.
Sep 22 02:23:08 storage kernel: [117760.603728] Do you have a strange power saving mode enabled?
Sep 22 02:23:08 storage kernel: [117760.603754] Dazed and confused, but trying to continue
Sep 22 04:07:35 storage kernel: [124028.559135] Uhhuh. NMI received for unknown reason 21 on CPU 19.
Sep 22 04:07:35 storage kernel: [124028.559165] Do you have a strange power saving mode enabled?
Sep 22 04:07:35 storage kernel: [124028.559192] Dazed and confused, but trying to continue

Как пишут в гугле, вариант неисправности, оперативка, блок питания, или винты.

Решил покопать в сторону

ASPM

С помощью технологии ASPM (Active-State Power Management) можно эффективно управлять потреблением энергии шин PCI Express (PCIe, Peripheral Component Interconnect Express) посредством их перевода в энергосберегающий режим, если подключенные через них устройства не используются. ASPM контролирует обе точки подключения и позволяет снизить потребление энергии, даже если подключенное устройство находится в рабочем режиме.

При активации ASPM задержка ответа устройства увеличивается из-за времени, затрачиваемого на переключение режимов шины. Можно определить четыре способа поведения ASPM:

default

Цитата

Настраивает состояние энергопотребления шины PCI Express в соответствии с параметрами, определенными на микропрограммном уровне (например, в BIOS). Этот режим используется по умолчанию.

powersave

Цитата

Максимальное энергосбережение независимо от воздействия на производительность системы.

performance

Цитата

Отключает ASPM и обеспечивает максимальную производительность PCI Express.

off

Цитата

Отключает его.

Решил пока отключить ASPM

pcie_aspm=off

а также NMI watchdog

nmi_watchdog=0

 

Для этого идем редактировать файл grub

nano /etc/default/grub

Ищем строку GRUB_CMDLINE_LINUX_DEFAULT

и дописываем nmi_watchdog=0 и pcie_aspm=off

Мой файл после изменения выглядит так:

# If you change this file, run 'update-grub' afterwards to update
# /boot/grub/grub.cfg.
# For full documentation of the options in this file, see:
#   info -f grub -n 'Simple configuration'

GRUB_DEFAULT=0
GRUB_TIMEOUT=5
GRUB_DISTRIBUTOR=`lsb_release -i -s 2> /dev/null || echo Debian`
GRUB_CMDLINE_LINUX_DEFAULT="quiet nmi_watchdog=0 pcie_aspm=off"
GRUB_CMDLINE_LINUX=""

# Uncomment to enable BadRAM filtering, modify to suit your needs
# This works with Linux (no patch required) and with any kernel that obtains
# the memory map information from GRUB (GNU Mach, kernel of FreeBSD ...)
#GRUB_BADRAM="0x01234567,0xfefefefe,0x89abcdef,0xefefefef"

# Uncomment to disable graphical terminal (grub-pc only)
#GRUB_TERMINAL=console

# The resolution used on graphical terminal
# note that you can use only modes which your graphic card supports via VBE
# you can see them in real GRUB with the command `vbeinfo'
#GRUB_GFXMODE=640x480

# Uncomment if you don't want GRUB to pass "root=UUID=xxx" parameter to Linux
#GRUB_DISABLE_LINUX_UUID=true

# Uncomment to disable generation of recovery mode menu entries
#GRUB_DISABLE_RECOVERY="true"

# Uncomment to get a beep at grub start
#GRUB_INIT_TUNE="480 440 1"

 

Далее пишем:

update-grub

 

И перегружаем машину.

 

P.S. Посмотрим как дальше будет вести себя машина. Если не поможет дальше будем тестировать память.