System and method for starting a cloud-based virtualization system with partially deprivileged host OS

1. A computing cloud comprising:

at least one computing node having a Virtual Machine (VM) running on a non-privileged level; and

a plurality of additional computing nodes, each node having a Hypervisor with the highest privilege level, and a Virtual Machine Monitor (VMM) running with no higher privilege level than the Hypervisor, and Virtual Machines (VMs) running on a non-privileged level; and

each node having a Primary operating system (POS) running within the corresponding VM; and

each POS having direct access to hardware device of the corresponding computing node; and

the VMs of the corresponding node using the POS of its node to access the hardware devices.

2. The computing cloud of claim 1 , wherein the POS is migratable from one node to another node in online or offline mode.

3. The computing cloud of claim 1 , wherein the VMs are migratable from one node to another node.

4. The computing cloud of claim 3 , wherein POS or its VM can migrate on-the-fly after system failure or overload.

5. The computing cloud of claim 1 , wherein secure isolation enables any VM to communicate with the POS via intermediation dedicated code rerouting messages between processes so that VM processes are not aware of POS processes.

6. The computing cloud of claim 5 , wherein a POS that becomes unsecure is terminated and a new POS is launched in the computing cluster.

7. The computing cloud of claim 1 , wherein the hardware device is any of a mass storage device, a hardware interface device, a video device subsystem and a human interface device.

8. The computing cloud of claim 1 , wherein the cloud is a server farm.

9. The computing cloud of claim 1 , wherein application memory area of at least one VM is protected from accessing by the hardware resources; and

the applications are trusted applications that cannot be observed or modified by other software of the computing cloud.

10. The cloud of claim 1 , further comprising a secure boot manager for starting a secure VM using trusted hypervisor.

11. The computing cloud of claim 1 , further comprising means for migrating the POS from a node with a trusted hypervisor to another node with trusted hypervisor.

12. The computing cloud of claim 1 , further comprising at least one node with a trusted component.

13. The computing cloud of claim 12 , wherein the trusted component is a driver or the hypervisor.

14. A method of operating a computing cloud comprising:

initializing at least one computing node having a Virtual Machine (VM) running on a non-privileged level; and

initializing a plurality of additional computing nodes, each node having a Hypervisor with the highest privilege level, and a Virtual Machine Monitor (VMM) running with no higher privilege level than the Hypervisor, and Virtual Machines (VMs) running on a non-privileged level; and

launching Primary operating system (POS) on each node and running within the corresponding VM, each POS having direct access to hardware device of the corresponding computing node; and

the VMs of the corresponding node using the POS to access the hardware device.

15. The method of claim 14 , further comprising migrating the POS from one node to another node, the migrating comprising:

stopping Primary OS execution;

saving Primary OS CPU context;

saving contents of Primary OS memory;

creating a Primary VM on the another node;

granting the Primary VM access to some host PC devices;

loading saved Primary OS CPU context into a virtual CPU;

loading saved Primary OS memory into a VM;

resuming Primary OS execution inside Primary VM.

16. The method of claim 15 , further comprising updating a configuration the POS to conform to hardware changes after migration.

17. The method of claim 14 , further comprising migrating the POS from one node to another node, the migrating comprising:

installing a boot manager component of the Hypervisor restarting the POS;

during host boot, having the Hypervisor take control before the Primary OS;

creating a Primary VM;

granting the Primary VM access to some host node devices;

starting the Primary OS booting process inside the Primary VM under control of Hypervisor; and

resuming Primary OS execution inside the Primary VM.

18. The method of claim 17 , further comprising updating a configuration the POS to conform to hardware changes after migration.

19. The method of claim 14 , further comprising migrating the POS from one node to another node, the migrating comprising:

installing a boot manager component of the Hypervisor;

restarting the Primary OS;

during host boot, having the Hypervisor take control before the Primary OS;

creating the Primary VM;

granting the Primary VM access to some host node devices;

initiating Primary OS installation process inside the Primary VM; and

resuming Primary OS execution inside the Primary VM.

20. The method of claim 19 , further comprising updating a configuration the POS to conform to hardware changes after migration.