Hi all,

I just found this forum this evening, but this has been a recurring issue for several months, so I'm afraid I'm coming into it rather frustrated.

I have a new whitebox ESXi 5.0.0 build that has been pink-screening repeatedly since I put the thing together back in March. The error message reads: PCPU 0: no heartbeat (but 2/2 IPIs received).

There doesn't seem to be any rhyme or reason to the frequency; sometimes it happens after running for 6-10 hours, and sometimes it happens in less than 1 hour. I get the error message regardless of whether there are 3 VM's running or none (in fact, I've seen it on a fresh reinstall with no VM's configured yet).

Here's the vital stats:
ASUS E35M1-M PRO
8GB RAM (DDR3 1066)
Intel Pro/1000 GT network adapter (82541PI) x2

Onboard NIC is disabled since I have 2 additional ones, and since the reviews for that mobo seem to point to the onboard NIC as its worst feature. I've turned off all power options from the new-fangled UEFI BIOS that I could find.

I received 2 bad power supplies in a row, so I was hoping that was the issue, but it hasn't been solved when I put in a known good one. I believe I've isolated the issue to the NICs - I did a clean install without the NICs plugged in (had to enable onboard briefly) and the machine ran for 5 days with no issues. I know that NIC isn't on the HCL for 5.0, but I've seen posts around the Internet that it works out okay for the most part, including one here: viewtopic.php?f=25&t=3505&p=13372&hilit=82541PI

I'll happily admit to being rather new to ESXi, but I've tried to do my research and I've found next to nothing on that error message. I've talked to one of my buddies (a sysadmin over an enterprise VMware network) and he can't think of anything else to try either. Could anyone point me in the right direction?

Any and all help is very appreciated.

Just a guess: this may be caused by incompatible CPU power state settings. Try to experiment with different BIOS settings, e.g. disable low power states.

- Andreas

Just something to try.....

I had this problem when using a motherboard that required force air cooling on the NorthBridge chip. I had it in a tower case that did not provide enough airflow to the NorthBridge and after running for various amounts of time it would give a similar Pink Screen with the 'no heartbeat' error.

Directing more cooling to the NB solved the problem, and it is very stable now.

Hope you find a solution