Compreendendo Exceções de Verificação de Máquina (MCE)

4

Enquanto tentando depurar freqüentes congelamentos do meu novo laptop (arquitetura KabyLake) em execução Ubuntu 16.04 Eu tropecei nestas entradas em kern.log :

kernel: [    0.041634] mce: [Hardware Error]: Machine check events logged

Desde então, instalei mcelog , mas não sei o que fazer com os logs. O conteúdo de /var/log/mcelog é:

mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 3880018086 ADDR fef1cf00 
TIME 1479298799 Wed Nov 16 13:19:59 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 43880018086 ADDR fef1ff00 
TIME 1479298799 Wed Nov 16 13:19:59 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 3880018086 ADDR fef1cf00 
TIME 1479321645 Wed Nov 16 19:40:45 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 43880018086 ADDR fef1ff00 
TIME 1479321645 Wed Nov 16 19:40:45 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 43880000086 ADDR fef1db80 
TIME 1479328438 Wed Nov 16 21:33:58 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 13880000086 ADDR fef1dc00 
TIME 1479328438 Wed Nov 16 21:33:58 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 43880000086 ADDR fef1db80 
TIME 1479333991 Wed Nov 16 23:06:31 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 13880000086 ADDR fef1dc00 
TIME 1479333991 Wed Nov 16 23:06:31 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 43880000086 ADDR fef1db80 
TIME 1479373350 Thu Nov 17 10:02:30 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 13880000086 ADDR fef1dc00 
TIME 1479373350 Thu Nov 17 10:02:30 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 3880018086 ADDR fef1cf00 
TIME 1479373810 Thu Nov 17 10:10:10 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee0000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 43880018086 ADDR fef1ff00 
TIME 1479373810 Thu Nov 17 10:10:10 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee0000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 3880018086 ADDR fef1cf00 
TIME 1479375712 Thu Nov 17 10:41:52 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 43880018086 ADDR fef1ff00 
TIME 1479375712 Thu Nov 17 10:41:52 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 3880018086 ADDR fef1cf00 
TIME 1479385932 Thu Nov 17 13:32:12 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 43880018086 ADDR fef1ff00 
TIME 1479385932 Thu Nov 17 13:32:12 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 3880018086 ADDR fef1cf00 
TIME 1479387666 Thu Nov 17 14:01:06 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 43880018086 ADDR fef1ff00 
TIME 1479387666 Thu Nov 17 14:01:06 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 43880000086 ADDR fef1db80 
TIME 1479456710 Fri Nov 18 09:11:50 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 13880000086 ADDR fef1dc00 
TIME 1479456710 Fri Nov 18 09:11:50 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 0
CPU 0 BANK 6 
MISC 43880000086 ADDR fef1db80 
TIME 1479459374 Fri Nov 18 09:56:14 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142
mcelog: Family 6 Model 8e CPU: only decoding architectural errors
Hardware event. This is not a software error.
MCE 1
CPU 0 BANK 7 
MISC 13880000086 ADDR fef1dc00 
TIME 1479459374 Fri Nov 18 09:56:14 2016
MCG status:
MCi status:
Error overflow
Uncorrected error
MCi_MISC register valid
MCi_ADDR register valid
Processor context corrupt
MCA: corrected filtering (some unreported errors in same region)
Generic CACHE Level-2 Generic Error
STATUS ee2000000040110a MCGSTATUS 0
MCGCAP c08 APICID 0 SOCKETID 0 
CPUID Vendor Intel Family 6 Model 142

Algumas observações (por favor corrija-me se alguma delas estiver errada):

  • Quase todos os erros parecem ocorrer na mesma página ( ADDR fef1xxx )
  • Apenas os bancos 6 e 7 parecem ser afetados.
  • Todas as entradas contêm "estouro de erro" e "erro não corrigido".

A FAQ do mcelog menciona que uma "baixa taxa de erros de memória corrigidos é esperada e não requer substituição de hardware ou outra ação ". As entradas de log contêm a frase "Erro não corrigido", o que sugere que eu realmente deveria tomar alguma ação.

Minhas perguntas são:

  1. O que esses erros significam e devo me preocupar com eles?
  2. Esses erros de hardware podem ser a causa dos congelamentos de todo o sistema?
  3. Devo substituir o laptop (ou peças) pelo fabricante?
  4. Há alguma outra ação que eu deva tomar?
por justfortherec 18.11.2016 / 10:50

2 respostas

4

Primeiro, temo não poder dar boas respostas às suas perguntas. Eu também possuo um Dell XPS 13 (9360) e vejo as mesmas mensagens MCE. Estou em contato com o suporte da Dell por causa disso. Eles substituíram a placa-mãe, mas isso não ajudou. Mesmas mensagens nos logs. Em algum momento eles concluíram que é provavelmente um falso positivo. Eles não tinham idéia do que está causando isso (problema mcelog / kernel / Intel?). A correspondência com o Suporte ainda está em andamento.

<rant> Btw, conversando com o suporte da Dell é uma experiência muito desagradável. Eles parecem apenas sugerir as soluções "padrão", como redefinir o firmware, executar testes de auto-avaliação e assim por diante. Eu não tive a impressão de falar com alguém com alguma visão técnica. </rant>

Para adicionar mais detalhes, vejo o mesmo problema no Fedora 24, de modo que não parece estar relacionado ao Ubuntu.

Com relação às suas perguntas:

What do these errors mean and should I worry about them?

Eu não sei. O suporte da Dell acha que esses são falsos positivos.

Could these hardware errors be the cause of the freezes of the entire system?

Além das mensagens, meu sistema funciona bem. Eu acho que o congelamento é um problema diferente.

Should I have the laptop (or parts) replaced by the manufacturer?

A substituição da placa principal não corrigiu o problema do MCE. Pode resolver o problema do congelamento, embora pareça que isso foi corrigida por uma atualização do kernel .

Are there any other actions I should take?

Se você ainda não estiver em contato com o Suporte, entre em contato. Talvez eles encontrem uma solução real quando perceberem que isso afeta mais clientes.

    
por 14.12.2016 / 11:37
1

Eu recebi os mesmos erros no mce, comecei a aparecer na inicialização nas últimas atualizações do kernel (Fedora 25), mas perdi a faixa na qual a atualização exata começou a aparecer. O notebook é o Dell Inspiron 5567 (Intel i5 7200U). No entanto, o sistema funciona perfeitamente após a inicialização, por isso tenho 100% de certeza de que isso é falso positivo aparecendo por algum motivo.

    
por 13.04.2017 / 13:30