Aufgrund eines Fehler im VirtualCenter 2.5, in Zusammenhang mit Konfiguriertem HA und DRS, kann nach nach einem VMotion die CPU Performance stark ansteigen. Dies bis zu 100%. Egal ob VMotion manuell oder automatisch via DRS ausgeführt wird.
Aufgetreten ist dieser Effekt bei virtuellen Novellserver. Bei Windows oder anderen Systemen ist mir dies noch nicht bekannt.

Die Beschreibung des Fehlers/Workaround in ist der KB von VMware zu finden.

To work around this issue:

Log in to VirtualCenter with Virtual Infrastructure Client as an administrator.
Right-click your cluster from the inventory.
Click Edit Settings.
Ensure that VMware DRS is shown as enabled. If it is not enabled check the box to enable VMware DRS.
Click OK.
Click an ESX Server from the Inventory.
Click the Configuration tab.
Click Advanced Settings.
Click the Mem option.
Locate the Mem.VMOverheadGrowthLimit parameter.
Change the value of this parameter to 5 and click OK.

To fix multiple ESX Server hosts

If this parameter needs to be changed on several hosts (or if the workaround fails for the individual host) use the following procedure to implement the workaround instead of changing every server individually:
Log on to the VirtualCenter Server Console as an administrator.
Make a backup copy of the vpxd.cfg file (typically it is located in C:\Documents and Settings\All Users\Application Data\VMware\VMware VirtualCenter\vpxd.cfg).
In the vpxd.cfg file, add the following configuration between the vpxd and the /vpxd tags:

This configuration provides an initial growth margin in MB-to-virtual machine overhead memory. You can increase this amount to larger values if doing so further improves virtual machine performance.

Restart the VMware VirtualCenter Server Service.

Note: When you restart the VMware VirtualCenter Server Service, the new value for the overhead limit should be pushed down to all the clusters in VirtualCenter.