kernel: Uhhuh. NMI received.

[CA1138832]

I just installed a new Proliant BL20pG3 with RedHat Enterprise Linux AS3. The server has crashed twice. I see the following in /var/log/messages:

kernel: Uhhuh. NMI received. Dazed and confused, but trying to continue

kernel: You probably have a hardware problem with your RAM chips

Insight Manager shows no problems with memory or anything else. Comments? Advice? Thanks in advance.

[CA1335662]

Intersting! I'm not sure that it's germane to you problem but I'm getting the same error out of my old DL320 G1. NMIs that look like they've something to do with memory but CPQ server diag nostics and memory diagnostics turn up nothing. The server runs Windows 2000, it has all the Windows updates, all the CPQ firmware and drivers updated.

I get the "dazed and confused" message when running the Mersenne Prime torture test found on the Ultimate Boot CD. When I run the Prime95 torture test in Windows it blue screens pretty quickly. The problem seems to happen even with the memory I just purchased.

[CA1138832]

Thanks Bill, this is valuabe information for me. I wasn't aware of this torture test. I'm going to get a copy of this and start experimenting with it. What I've done so far is just replaced the memory in my BL20pG3. Only time will tell. What's interesting is the two times I crashed, we were running heavier than normal resource intensive stuff on this box. Thanks Bill.