Hypervisor-driven hibernation

1. A method comprising:

executing, by a processing device, a hypervisor;

identifying a first virtual machine that is executing and a second virtual machine that is executing, the first virtual machine comprising a plurality of virtual processors;

determining, by the hypervisor, that the first virtual machine is to be hibernated while the second virtual machine remains awake, wherein the determining is performed without involvement of a guest operating system hosted by the first virtual machine;

stopping by the hypervisor, in view of the determining, a first virtual processor of the plurality of virtual processors of the first virtual machine;

persisting, by the hypervisor, a state of the stopped first virtual processor; and

in response to a hardware fault that occurs after the stopping of the first virtual processor and the persisting of the state of the stopped first virtual processor, re-starting, by the hypervisor, the stopped first virtual processor, the re-starting comprising loading the state of the stopped first virtual processor.

2. The method of claim 1 further comprising transmitting to the first virtual machine a signal that indicates that the first virtual machine has exited a stopped state.

3. The method of claim 1 further comprising:

stopping, by the hypervisor, a second virtual processor of the plurality of virtual processors of the first virtual machine; and

persisting, by the hypervisor, a state of the stopped second virtual processor.

4. The method of claim 1 further comprising stopping, by the hypervisor, one or more virtual devices of the first virtual machine.

5. An apparatus comprising:

a memory to store a first virtual machine and a second virtual machine; and

a processing device, operatively coupled to the memory, to execute the first virtual machine, the second virtual machine, and a hypervisor, wherein the processing device is to execute the hypervisor to:

identify the first virtual machine and the second virtual machine, the first virtual machine comprising a plurality of virtual processors;

determine that the first virtual machine is to be hibernated while the second virtual machine remains awake, wherein the determining is performed without involvement of a guest operating system hosted by the first virtual machine;

stop, in view of the determining, a first virtual processor of the plurality of virtual processors of the first virtual machine;

persist a state of the stopped first virtual processor; and

in response to a clock event that occurs after the stopping of the first virtual processor and the persisting of the state of the stopped first virtual processor, re-start the stopped first virtual processor, the re-starting comprising loading the state of the stopped first virtual processor.

6. The apparatus of claim 5 wherein the hypervisor is also to:

stop a second virtual processor of the first virtual machine; and

persist a state of the stopped second virtual processor.

7. A non-transitory computer readable storage medium, having instructions stored therein, which when executed, cause a processing device to:

execute, by the processing device, a hypervisor;

identify a first virtual machine that is executing and a second virtual machine that is executing, the first virtual machine comprising a plurality of virtual processors;

stop, via the hypervisor, a first virtual processor of the plurality of virtual processors of the first virtual machine while the second virtual machine remains awake, wherein the first virtual machine hosts a guest operating system that has no power management capability;

persist, via the hypervisor, a state of the stopped first virtual processor; and

in response to a hardware fault that occurs after the stopping of the first virtual processor and the persisting of the state of the stopped first virtual processor, re-start, via the hypervisor, the stopped first virtual processor, the re-starting comprising loading the state of the stopped first virtual processor.

8. The non-transitory computer readable storage medium of claim 7 , wherein the instructions further cause the processing device to transmit to the first virtual machine a signal that indicates that the first virtual machine has exited a stopped state.

9. The non-transitory computer readable storage medium of claim 7 ,

wherein the instructions further cause the processing device to:

stop, via the hypervisor, a second virtual processor of the plurality of virtual processors of the first virtual machine; and

persist, via the hypervisor, a state of the stopped second virtual processor.

10. The non-transitory computer readable storage medium of claim 7 , wherein the instructions further cause the processing device to stop, via the hypervisor, one or more virtual devices of the first virtual machine.