Resource virtualization switch

• US 7,502,884 B1
• Filed: 07/11/2005
• Issued: 03/10/2009
• Est. Priority Date: 07/22/2004
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Xsigo Systems (Oracle Corporation)
• Inventors: Shah, Shreyas, Anand, Ramalingam K., Krishnamurthi, Ashok, Vinod, Subramaniam
• Primary Examiner(s): Knoll; Clifford H
• Application Number:
  US11/179,085
• Time in Patent Office: 1,338 Days
• Field of Search: 710316-317, 370/395.21, 370/396
• US Class Current: 710/316
• CPC Class Codes: G06F 11/2005 using redundant communication controllers
• CPC Class Codes: G06F 13/12 using hardware independent of the central processor, e.g. channel or peripheral processor
• CPC Class Codes: G06F 13/128 for dedicated transfers to a network for protocol converters G06F13/387
• CPC Class Codes: G06F 13/4022 using switching circuits, e.g. switching matrix, connection or expansion network G06F13/4009 takes precedence
• CPC Class Codes: G06F 13/42 Bus transfer protocol, e.g. handshake; Synchronisation
• CPC Class Codes: G06F 13/4221 being an input/output bus, e.g. ISA bus, EISA bus, PCI bus, SCSI bus
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/0662 Virtualisation aspects
• CPC Class Codes: G06F 3/0664 at device level, e.g. emulation of a storage device or system
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: H04L 12/4641 Virtual LANs, VLANs, e.g. virtual private networks [VPN] LAN interconnection over a bridge based backbone H04L12/462; encapsulation techniques H04L12/4633; routing of packets H04L45/00; packet switches H04L49/00; virtual private networks for security H04L63/0272
• CPC Class Codes: H04L 41/04 Network management architectures or arrangements
• CPC Class Codes: H04L 49/00 Packet switching elements
• CPC Class Codes: H04L 49/357 Fibre channel switches
• CPC Class Codes: H04L 49/70 Virtual switches
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

Methods and apparatus are provided for virtualizing resources including peripheral components and peripheral interfaces. Peripheral component such as hardware accelerators and peripheral interfaces such as port adapters are offloaded from individual servers onto a resource virtualization switch. Multiple servers are connected to the resource virtualization switch over an I/O bus fabric such as PCI Express or PCI-AS. The resource virtualization switch allows efficient access, sharing, management, and allocation of resources.

Claims

1. A resource virtualization switch, comprising:

a plurality of resources;

virtualization logic configured to obtain data from a plurality of servers each including at least a processor and memory, the plurality of servers connected to the resource virtualization switch over an I/O bus fabric and operable to interact with the resource virtualization switch using a plurality of virtual device drivers, wherein the virtualization logic is configured to provide the data to a selected resource using mapping of the virtual device drivers to a plurality of actual device drivers corresponding to the plurality of resources.

2. The resource virtualization switch of claim 1, wherein the plurality of resources are mapped in an aggregated address space.

3. The resource virtualization switch of claim 1, wherein each of the plurality of servers have individual virtual address spaces.

4. The resource virtualization switch of claim 1, wherein each of the plurality of servers is assigned a portion of the aggregated address space.

5. The resource virtualization switch of claim 1, wherein resources are dynamically reconfigurable and can be mapped to any of the plurality of servers.

6. The resource virtualization switch of claim 5, wherein the resources are dynamically reconfigurable and can be mapped to any of the plurality of servers by reprogramming an address translation mechanism associated with the virtualization logic.

7. The resource virtualization switch of claim 1, wherein the plurality of servers comprise guest operating systems, system images, and virtual machines.

8. The resource virtualization switch of claim 1, wherein the plurality of servers communicate with the plurality of resources using virtual device drivers and wherein the plurality of resources comprise a plurality of peripheral components and peripheral interfaces.

9. The resource virtualization switch of claim 1, wherein the virtualization logic is associated with a plurality of queues, each of the plurality of queues assigned to an application associated with the plurality of servers.

10. The resource virtualization switch of claim 9, wherein different service levels associated with a quality of service policy are applied to the plurality of queues.

11. The resource virtualization switch of claim 1, wherein peripheral components include hardware accelerators.

12. The resource virtualization switch of claim 11, wherein peripheral components include cryptographic accelerators, KVM, and XML accelerators.

13. The resource virtualization switch of claim 1, wherein peripheral interfaces include port adapters.

14. The resource virtualization switch of claim 13, wherein peripheral interfaces include NIC and HBA interfaces.

15. The resource virtualization switch of claim 13, wherein peripheral interfaces include SATA, TOE, and iSCSI interfaces.

16. The resource virtualization switch of claim 1, wherein virtualization logic manages an aggregated address space associated with the plurality of servers.

17. The resource virtualization switch of claim 1, wherein virtualization logic performs polling of descriptor queues associated with the plurality of servers to obtain data from the plurality of servers.

18. The resource virtualization switch of claim 17, wherein descriptors in the descriptor queues include data addresses and data lengths.

19. The resource virtualization switch of claim 1, wherein the resource virtualization switch further comprises an I/O bus switch.

20. The resource virtualization switch of claim 1, wherein the I/O bus fabric is a PCI Express fabric.

21. The resource virtualization switch of claim 1, wherein the I/O bus fabric is a PCI-AS fabric.

22. The resource virtualization switch of claim 13, wherein the I/O bus fabric is a PCI-AS fabric that assigns identifiers to each of the plurality of servers.

23. The resource virtualization switch of claim 1, wherein the plurality of resources includes a shared and virtualized local disk that allows the creation of stateless computing.

24. The resource virtualization switch of claim 1, wherein the resource virtualization switch further comprises a control plane.

25. The resource virtualization switch of claim 1, wherein each of the plurality of servers includes a processor, memory, and an address space.

26. A method for mapping resources, the method comprising:

providing a plurality of resources;

providing a plurality of servers connected to a resource virtualization switch using an I/O bus, the plurality of servers operable to interact with the resource virtualization switch using a plurality of virtual device drivers;

mapping the plurality of resources into an aggregated address space managed by the resource virtualization switch, the aggregated address space including address spaces associated with the plurality of servers, wherein the resource virtualization switch operates the plurality of resources by mapping the virtual device drivers to actual device drivers.

27. The resource virtualization switch of claim 26, wherein each of the plurality of servers have individual virtual address spaces.

28. The resource virtualization switch of claim 26, wherein each of the plurality of servers is assigned a portion of the aggregated address space.

29. The resource virtualization switch of claim 26, wherein resources are dynamically reconfigurable and can be mapped to any of the plurality of servers.

30. The resource virtualization switch of claim 29, wherein the resources are dynamically reconfigurable and can be mapped to any of the plurality of servers by reprogramming an address translation mechanism associated with the virtualization logic.

31. The resource virtualization switch of claim 26, wherein the plurality of servers comprise guest operating systems, system images, and virtual machines.

32. The resource virtualization switch of claim 26, wherein the plurality of servers communicate with the plurality of resource using virtual device drivers and wherein the plurality of resources comprise a plurality of peripheral components and peripheral interfaces.

33. The resource virtualization switch of claim 26, wherein the virtualization logic is associated with a plurality of queues, each of the plurality of queues assigned to an application associated with the plurality of servers.

34. The resource virtualization switch of claim 33, wherein different service levels associated with a quality of service policy are applied to the plurality of queues.

35. A system comprising:

I/O bus means for connecting a plurality of servers to a resource virtualization switch;

means for mapping the plurality of resources into an aggregated address space managed by the resource virtualization switch, the aggregated address space including address spaces associated with the plurality of servers, wherein the resource virtualization switch operates the plurality of resources by mapping virtual device drivers to actual device drivers.

36. The resource virtualization switch of claim 35, wherein each of the plurality of servers have individual virtual address spaces.

37. The resource virtualization switch of claim 35, wherein each of the plurality of servers is assigned a portion of the aggregated address space.

38. The resource virtualization switch of claim 35, wherein resources are dynamically reconfigurable and can be mapped to any of the plurality of servers.

39. The resource virtualization switch of claim 38, wherein the resources are dynamically reconfigurable and can be mapped to any of the plurality of servers by reprogramming an address translation mechanism associated with the virtualization logic.

40. The resource virtualization switch of claim 35, wherein the plurality of resources includes a shared and virtualized local disk that allows the creation of stateless computing.

41. A system for implementing a resource virtualization, the system comprising:

a bus interface coupled to a plurality of servers, wherein the bus interface provides serialized switched access to the plurality of servers;

a plurality of peripherals, the plurality of peripherals including network interfaces connected to external network devices;

a processor configured to receive virtual device driver requests for access to ones of the plurality of peripherals from the plurality of servers, wherein the processor identifies ones of the plurality of peripherals for handling the requests and accesses ones of the plurality of peripherals using actual device drivers.

42. The system of claim 41, wherein the bus interface is a PCI Express interface.

43. The system of claim 41, wherein the plurality of servers is included in a server farm.

44. The system of claim 41, wherein the plurality of servers is included in a server rack.

45. The system of claim 41, wherein the plurality of peripherals include network interfaces implemented as network interface cards.

46. The system of claim 41, wherein the plurality of peripherals include hardware accelerators.

47. The system of claim 41, wherein the processor is further configured to apply traffic shaping and quality of service schemes at a bus level.

48. The system of claim 41, wherein the processor is associated with virtualization logic.