ESX/ESXi 4.0 Update 1, 4.0 Update 2 and 4.1 fail with a purple diagnostic screen on AMD Opteron 6100-series processor based systems

Symptoms

When running ESX/ESXi 4.0 Update 1, ESX/ESXi 4.0 Update 2, or ESX/ESXi 4.1 on systems using the AMD Opteron 6100 series processors, you may experience these symptoms:
  • You experience a purple diagnostic screen due to a Machine Check Exception (MCE)
  • The purple diagnostic screen has a log message matching one of these signatures (where * is a wildcard for any valid hexadecimal digit, that is 0-9 and a-f):
    • **:**:**:**.*** cpu*:****)MC:PCPU**** B:4 S:0x**************** M:0x0 A:0x**** 7

    • **:**:**:**.*** cpu*:****)MCE: ***: Machine Check Global status on cpu**: 0x7 (cputype:4 16 9 1 AMD Opteron(tm) Processor 617*): Restart IP valid. Error IP val
      **:**:**:**.*** cpu*:****)MCE: ***: MCE on cpu** bank4: Status:0x**************** Misc:0x0 Addr:0x****: ECC error.Valid.Overflow.UC.Err enabled.Addr valid.

    • @BlueScreen: Hardware (Machine) Error: Uncorrected ECC error in L3 Cache LRU on cpu ** cache index 0x**** PCPU** in world ****:idle*

Note: To confirm if you are using AMD Opteron 6100-series processors, select the host in vSphere Client and click theSummary Tab. The Processor Type is listed under General.

Purpose

This article describes a specific Machine Check Exception. If you observe an MCE that does not exactly match the above signature, see Decoding Machine Check Exception (MCE) output after a purple screen error (1005184). If you observe a purple diagnostic screen that does not cite MC, MCE, or Hardware (Machine) Error, see Interpreting an ESX host purple diagnostic screen (1004250).

Resolution

To resolve this issue upgrade your BIOS to the latest version available. Changes were made in these BIOS releases to address this issue.
 
For more information, see:
  • HP Customer Advisory c02641719 and HP ProLiant G7 BIOS System ROM dated 12/20/2010 or later.
  • Dell Release Notes R295040 and Dell PowerEdge R715 and R815 BIOS 1.4.1 dated 1/24/2011 or later.

    Note: The preceding links were correct as of March 2, 2011. If you find the link is broken, provide feedback and a VMware employee will update the link.
Note: If you experience this issue on a system with the updated system BIOS, file a support request with VMware Technical Support and with your server hardware vendor. VMware recommends that you contact your server vendor directly for more information on how to proceed.

Alternatively as a workaround for affected systems, configure the system through BIOS setup options to run in a full or high performance mode where processor power saving features are not utilized. The actual method and its description varies among server vendors, consult your specific server vendor for more information.


Based on VMware KB 1030509
  • 0 användare blev hjälpta av detta svar
Hjälpte svaret dig?

Relaterade artiklar

Hardware and firmware requirements for 64-bit guest operating systems

PurposeThis article explains the host machine hardware and firmware requirements for installing...

Logging in to the vCenter Server 5.0 Web Client fails with the error: unable to connect to vCenter Inventory Service

DetailsAfter upgrading from vCenter Server 4.1 to 5.0, you experience these symptoms:Cannot log...

Multiple network entries in vCenter Server 5.0.x after migrating virtual machines from a virtual switch to a virtual distributed switch

SymptomsAfter migrating virtual machines from a virtual switch to a virtual Distributed...

Minimum requirements for the VMware vCenter Server 5.x Appliance

PurposeIf you are using the VMware vCenter Server Appliance, beginning with vSphere 5.0 you can...