I have two Hyper-V hosts running a total of around 20 VMs. I recently came across some odd behavior that ended up in a call to Microsoft Support, as I couldn’t figure it out on my own and we didn’t want to spend any more time on it ourselves. Basically, I was seeing the following:
As you can see, ping times were all over the place. We found a solution in a combination of KB articles and blog posts.
I have three VMs that are multi-proc and all three of them were doing this. All three VMs are running a flavor of Windows Server 2003. I don’t know if this happens with other OSs on multi-proc VMs… I am guessing not. With the /usepmtimer switch added in the boot.ini file, all three are now working as expected. I hope that the Hyper-V team is working on a solution to this so that boot.ini file manipulation is not required in the future.