Abstract: The invention relates to a method of enabling multiple operating systems to run concurrently on the same computer, the method comprising: scheduling a plurality of tasks for execution by at least first and second operating systems, wherein each task has one of a plurality of priorities; setting the priority of each operating system in accordance with the priority of the next task scheduled for execution by the respective operating system; and providing a common program arranged to compare the priorities of all operating systems and to pass control to the operating system having the highest priority. Accordingly, the invention resides in the idea that different operating systems can be run more efficiently on a single CPU by changing the priority of each operating system over time. In other words, each operating system has a flexible priority.

Abstract: A method for managing virtual machines, the method comprising providing a virtual Advanced Configuration and Power Interface, ACPI, arranged to interact with the virtual machines, and interacting with a real ACPI based on interaction between the virtual ACPI and the plurality of virtual machines.

Abstract: According to the present invention, there is provided a data processing system comprising: a dedicated physical device for access by a single client only; a shared physical device for shared access by multiple clients; a partition of a first type associated with the dedicated physical device, the first type partition comprising said single client and a first device driver for accessing the dedicated physical device; a partition of a second type associated with the shared physical device, the second type partition comprising a second device driver for accessing the shared physical device, and a back end driver for accessing the second device driver; and multiple partitions of the third type each comprising a respective one of said multiple clients and a front end driver for accessing the shared physical device via the second type partition.

Abstract: The present invention provides a scheduling method for a data processing system comprising at least one physical CPU, and one or more virtual machines each assigned to one or more virtual CPUs, the method comprising: a first scheduling step in which one of said virtual machines is elected to run on said physical CPU; and a second scheduling step in which at least one of the virtual CPUs assigned to the elected virtual machine is elected to run on said physical CPU. The second scheduling step is applied to the virtual machine only. When a virtual machine instance is elected to run on a given CPU, the second level scheduling determines the virtual CPU instance to run. The second level scheduling is global and can cause a virtual CPU migration from one physical CPU to another. In order to ensure correct task scheduling at guest level, virtually equivalent (in terms of calculation power) virtual CPUs should be provided to the scheduler.

Abstract: The invention provides a data processing system for the support of secure networking on a single, virtualized hardware platform. The data processing system comprises a Network Interface Controller NIC to control access to a physical network; a first operating system comprising an NIC driver to manage the NIC, and a first Virtual Network Interface Controller VNIC driver. The system further comprises at least one second operating system comprising at least one second VNIC driver associated with a networking stack; and a Virtual Machine Monitor VMM to enable concurrent operation of the first and second operating systems, and to emulate a virtual network, the VMM comprising first and second VNICs to provide access to the virtual network by the first and second operating systems through the first and second VNIC drivers, respectively.

Abstract: In a preferred embodiment, the present invention provides a method of load balancing in a data processing system comprising a plurality of physical CPUs and a plurality of virtual CPUs, the method comprising: mapping one or more virtual CPUs to each of said physical CPUs; and dynamically adapting the mapping depending on the load of said physical CPUs and the negative load indicative of the load of all other virtual CPUs that are allocated to each physical CPU.

Abstract: The present invention provides a scheduling method for a data processing system comprising at least one physical CPU, and one or more virtual machines each assigned to one or more virtual CPUs, the method comprising: a first scheduling step in which one of said virtual machines is elected to run on said physical CPU; and a second scheduling step in which at least one of the virtual CPUs assigned to the elected virtual machine is elected to run on said physical CPU. The second scheduling step is applied to the virtual machine only. When a virtual machine instance is elected to run on a given CPU, the second level scheduling determines the virtual CPU instance to run. The second level scheduling is global and can cause a virtual CPU migration from one physical CPU to another. In order to ensure correct task scheduling at guest level, virtually equivalent (in terms of calculation power) virtual CPUs should be provided to the scheduler.

Abstract: A method for managing virtual machines, the method comprising providing a virtual Advanced Configuration and Power Interface, ACPI, arranged to interact with the virtual machines, and interacting with a real ACPI based on interaction between the virtual ACPI and the plurality of virtual machines. (FIG.

Abstract: The invention provides a data processing system for the support of secure networking on a single, virtualized hardware platform. The data processing system comprises a Network Interface Controller NIC to control access to a physical network; a first operating system comprising an NIC driver to manage the NIC, and a first Virtual Network Interface Controller VNIC driver. The system further comprises at least one second operating system comprising at least one second VNIC driver associated with a networking stack; and a Virtual Machine Monitor VMM to enable concurrent operation of the first and second operating systems, and to emulate a virtual network, the VMM comprising first and second VNICs to provide access to the virtual network by the first and second operating systems through the first and second VNIC drivers, respectively.

Abstract: According to the present invention, there is provided a data processing system comprising: a dedicated physical device for access by a single client only; a shared physical device for shared access by multiple clients; a partition of a first type associated with the dedicated physical device, the first type partition comprising said single client and a first device driver for accessing the dedicated physical device; a partition of a second type associated with the shared physical device, the second type partition comprising a second device driver for accessing the shared physical device, and a back end driver for accessing the second device driver; and multiple partitions of the third type each comprising a respective one of said multiple clients and a front end driver for accessing the shared physical device via the second type partition.

Abstract: In a preferred embodiment, the present invention provides a method of load balancing in a data processing system comprising a plurality of physical CPUs and a plurality of virtual CPUs, the method comprising: mapping one or more virtual CPUs to each of said physical OPUs; and dynamically adapting the mapping depending on the load of said physical CPUs.