Supposedly failed CPUs DL380G3

[anawrocki]

I have a DL380 G3 with dual 2.4 GHz CPUs. Insight Manager and the system mgmt home page randomly show that either CPU1, CPU2 or both CPUs at the same time have failed and that they should be replaced. If I do hardware diags all hardware checks out and I am not experiencing any other symptoms.

The system has all the latest firmware, drivers, and agents. There is not a thermal condition... we have great AC, I have reset NVRAM, reinstalled support packs, reinstalled firmware, and yet condition still exists. I have spent over 2 hours with HP and they have no ideas.

Anyone here seen this before?

 

[TheLad]

Is the server genuinly overheating? I have seen these sort of errors on a server where it is overheating due to being stored in a small non air-conditioned area.

-----------------------------------------------------
"It's true, its damn true!"
-----------------------------------------------------

 

[anawrocki]

No, as stated, there is not a thermal condition. It is in a very well cooled data center.