Machine Check Exception in 2.6.0-test2

From: Ben Twijnstra (bentw@chello.nl)
Date: Mon Jul 28 2003 - 16:52:15 EST


Hi all,

When running a fairly CPU and thread-hungry application under 2.5.75,
2.6.0-test1 and 2.6.0-test2 I'm getting the following error messages on the
console:

Jul 25 00:16:31 durak kernel: CPU 0: Machine Check Exception: 0000000000000004
Jul 25 00:16:31 durak kernel: Bank 0: b600000000000175 at 0000000025a0cff8
Jul 25 00:16:31 durak kernel: Kernel panic: CPU context corrupt

Once I get this message, one of the threads becomes unkillable yet remains
soaking up CPU cycles.

This does not happen in the 2.4 kernels. How do I go about finding the source
of the problem? The address indicated in the second line indicates that this
happened somewhere in userspace (0x25a0cff8), but since this is a commercial
package I don't have any symbolic info. This last address changes between
runs, so I assume it's a virtual address.

Any ideas welcome.

Best regards,

Ben

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Thu Jul 31 2003 - 22:00:37 EST