DL380 G5 hangs at random points.

[Colin Patterson_1]

This server started blue screening with (Error code 0x0000002D, 0x00000000. We replaced the P400 array controller, the motherboard, memory in stages with not change. The problem has progressed to the server hanging during the Smart Start CD boot or randomly during system diags. It's basically totally unstable and we cannot get any solid failure results to record. Initially we were told to upgrade the firmware and drivers but that doesn't seem to be relevent with the smart start hanging. Looking at the CPU's now but reqally clutching at straws. Can't privide a config dump or memory dump attach as the thing won't stay up long enough.

[TarunJain]

Hi Colin,
Looks like you have replaced all the suspected spare parts.
Please let us know the status after replacing processor.
If it is multiprocessor system then what is the status with single processor?
Is there any fault recorded in IML?
Maybe the system board needs to be replaced again.

[Colin Patterson_1]

Thanks for the response. We are getting the customers system operators to rum HPS tool as we have no logon access to the servers. They are struggling to get any reports or memory dumps as it won't stay up long enough to do this. We are also awaiting the delivery of the two processors so I will update following that change. The IML only shows the crash stop code.

[TarunJain]

Hi Colin,
Is there any device installed on PCI-X or PCI-e? Could it be removed for troubleshooting?

[Colin Patterson_1]

Hi,

Device PCIe P400 raid controller was removed and server run at minimum hardware config. We have replaced the CPU's and monitoring. I will update with results on 23rd.

Thanks