[openib-general] machine check stop

Steve Wise swise at opengridcomputing.com
Fri Nov 4 12:20:38 PST 2005


Searching on the web shows this particular "4 bank 4" check when there 
are memory problems.

I was just wondering if bad kernel/module code could cause this, or if 
really indicates a HW system issue, and if anyone else has seen this 
running openib stress tests on X86_64...

Thanx,

Stevo.


----- Original Message ----- 
From: "Roland Dreier" <rolandd at cisco.com>
To: "Steve Wise" <swise at opengridcomputing.com>
Cc: <openib-general at openib.org>
Sent: Friday, November 04, 2005 2:05 PM
Subject: Re: [openib-general] machine check stop


>    Steve> CPU 0: Machine Check Stop 4 Bank 4: b200000000070f0 TSC
>    Steve> blah blah blah.
>
> The chipset and/or CPU detected "something bad" like a parity error or
> something like that.
>
> You'll need to know all the details of your system and find some
> low-level documentation to decode the machine check output.
>
> - R.
> 




More information about the general mailing list