1 Reply Latest reply on Feb 23, 2018 6:13 AM by admmedlifer

    Machine Check Exception AMD Opteron 6238

    huexos

      Hello Team, does someone know how to decode a Machine Check Exception generated by a AMD Opteron 6238? this processor is mounted in a bl465c gen8 server running with Windows Server 2008 R2, this are the messages:

       

      Critical,4278,432,0x0005,CPU,,,12/12/2017 07:05:00,914: Uncorrectable Machine Check Exception (Board 0, Processor 1, APIC ID 0x00000020, Bank 0x00000004, Status 0xBA000080'00020C0F, Address 0x00000000'00000000, Misc 0xC0050FFF'01000000)

       

      Critical,4278,434,0x0005,CPU,,,12/12/2017 07:05:00,915: Uncorrectable Machine Check Exception (Board 0, Processor 1, APIC ID 0x00000021, Bank 0x00000004, Status 0xBA000080'00020C0F, Address 0x00000000'00000000, Misc 0xC0040FFE'01000000)

       

      Thanks in advance

        • Re: Machine Check Exception AMD Opteron 6238
          admmedlifer

          http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2012/10/24593_APM_v21.pdf Chapter 9

           

          You're status flag is odd (i.e.bit 0 is set) that already mean's it's software recoverable.  The address is zero so I'd assume it's a null reference by some firmware.  You should update you're firmware since it's probably due for an update

           

          You can look at table 9-4 to validate my interpretation, but the level of this bug seems low.  I think what Windows 2k8 is telling you is that the MCE was not hardware corrected (uncorrected) however I assume the system continued on fine.

           

          A lo of this stuff (assuming you read the manual) is system dependent, a shortcut would be to look through event logs to see what else was failing or happening at the same time.