[ale] Server fatal?

[Christopher Fowler]

I've got a server that yesterday locked up a few times.
It was also showing strange behavior.  For example when we started
tomcat and the servlets java complained about not being able to find 
classes.  After a reboot it started just fine.

This morning I saw many of these in dmesg:

mm/memory.c:101: bad pmd 0bc6cdd0(0000002000000000).
mm/memory.c:101: bad pmd 0bc6ce00(0000002000000000).
mm/memory.c:101: bad pmd 0bc6ce10(0000000200000000).
mm/memory.c:101: bad pmd 0bc6ce30(000000a800000000).
mm/memory.c:101: bad pmd 0bc6ce60(0000002000000000).
mm/memory.c:101: bad pmd 0bc6ceb0(0000000800000000).
mm/memory.c:101: bad pmd 0bc6cec0(000000a000000000).
mm/memory.c:101: bad pmd 0bc6cef0(0000008000000000).
mm/memory.c:101: bad pmd 0bc6cf00(0000000200000000).
mm/memory.c:101: bad pmd 0bc6cf20(0000008000000000).
mm/memory.c:101: bad pmd 0bc6cf40(0000000800000000).
mm/memory.c:101: bad pmd 0bc6cfe0(0000000200000000).
mm/memory.c:101: bad pmd 0bc6cff0(0000000800000000).

I did a google search and I see many emails where people have seen these
but no replies as to what could be the failure.  It may be too vague.

Is it memory or motherboard?  I'm not getting disk errors so I'm not
going to point my finger at the disks.