Machine Check Exception

Jochen Garcke garckej at iam.uni-bonn.de
Mon Apr 29 03:59:00 CDT 2002


Hi,

in the last week I got twice a Machine Check Exception on our 
PowerEdge 8450 running kernel2.4.9-31 with added xfs.

One is for CPU5, 00...007, Bank 0, f607e00022000800 at 7607e00022000800
CPU context corrput,
the other one for CPU2 , 00..004, Bank 0, f604e00022000800 at 7604e00022000800
CPU context corrput

I found a tool to decode the number (parsemce.c) which says
for the first one:
Status: (7) Machine Check in progress.
Error IP valid
Restart IP valid.
parsebank(0): f607e00022000800 @ 7607e00022000800
	External tag parity error
	MISC register information valid
	Bus and interconnect error
	Participation: Local processor originated request
	Timeout: Request did not timeout
	Request: Generic error
	Transaction type : Instruction
	Memory/IO : Memory access

And the second one
Status: (4) Machine Check in progress.
Restart IP invalid.
parsebank(0): f604e00022000800 @ 7604e00022000800
	External tag parity error
	MISC register information valid
	Bus and interconnect error
	Participation: Local processor originated request
	Timeout: Request did not timeout
	Request: Generic error
	Transaction type : Instruction
	Memory/IO : Memory access

My guess is that some part of the RAM has a hardware defect, since two
different CPUs were involved. Only problem which of the 5 GB ?

Any help would be appreciated.

Thanks,
  Jochen

-- 
Jochen Garcke                                     mail: jochen at garcke.de
Institut fuer Angewandte Mathematik, Uni Bonn   wissrech.iam.uni-bonn.de
GCD Deutschland (Die Comic Datenbank)                  www.garcke.de/GCD
The future is viridian                            www.viridiandesign.org 




More information about the Linux-PowerEdge mailing list