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*
- **:**:**:**.*** cpu*:****)MC:PCPU**** B:4 S:0x**************** M:0x0 A:0x**** 7
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
Resolution
- 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.
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.