PSOD with exception type 14 in world 1100

[Cruicer]

I've been getting a PSOD with exception type 14 in world 1100 for the past few days. Running ESX 3.5.0 build 123630 on a HP ProLiant BL685c G5. I have two nodes in the cluster and the other host is running without issue. Suggestions? Luckily I only have two VMs running and the other host can handle them fine.

[coco26]

Hello - did you find a solution to this. I have been getting the same error. VMWare have said its faulty cpu chip, but having swapped this the error remains to happen regularly. all other hosts are the same in the cluster, but with no psod's

[Cruicer]

Apparently I had some bad DIMMs, Replace 5 and I was good to go.

[dickybird]

You can run smartstart/diagnostics on your hardware.

If this is intemittent problem, try replacing whole memory module/backplane, that what we had after service tehs multiple visits and log not telling anything for our intermittent PSOD problem (it used to come within 10-15 minutes) of system reboot.

[Phaedrus1]

I had a similar issue with a DL 580 G4. Intermittent crashes. After using a CPU testing tool from HP it was determined that a CPU was bad. After replacing it there were no more PSOD incidents. Drove us crazy for a while because there was no pattern.

Good Luck!

[coco26]

These PSOD's are at best ambiguous, finding it increasingly difficult to map back to hardware - which is usually vmware's recommendation, 'contact the hardware vendor'

smartstart tests never seem to throw any light, even the recommended memtest iso seems hit and miss.

Phaedrus1 - dont suppose you remember the cpu testing tool from HP, sounds helpful

[Phaedrus1]

Sorry, I do not have the exact filename of the CPU monitoring tool since I have mentally blocked it due to the anguish it caused me (also it was over a year ago) but I do remember calling HP support and escalating the problem ASAP to engineering and asking them to provide monitoring for CPU since I had already exhausted my memory testing tool option.