Metadata for managing I/O and storage for a virtualization environment

• US 9,256,374 B1
• Filed: 09/29/2014
• Issued: 02/09/2016
• Est. Priority Date: 08/10/2011
• Status: Active Grant

• Current Assignee: Nutanix Incorporated
• Original Assignee: Nutanix Incorporated
• Inventors: Aron, Mohit, Bhardwaj, Rishi, Guturi, Venkata Ranga Radhanikanth
• Primary Examiner(s): Verbrugge, Kevin
• Assistant Examiner(s): GOLDSCHMIDT, CRAIG S
• Application Number:
  US14/500,730
• Time in Patent Office: 498 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 12/1466 Key-lock mechanism
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0641 De-duplication techniques
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G06F 9/52 Program synchronisation; Mutual exclusion, e.g. by means of semaphores

Abstract

Disclosed is an improved approach for using advanced metadata to implement an architecture for managing I/O operations and storage devices for a virtualization environment. According to some embodiments, a Service VM is employed to control and manage any type of storage device, including directly attached storage in addition to networked and cloud storage. The advanced metadata is used to track data within the storage devices. A lock-free approach is implemented in some embodiments to access and modify the metadata.

Claims

1. A method for performing lock free processing of metadata for storage devices in a virtualization system, comprising:

identifying a metadata structure hierarchy with a plurality of levels including at least a first level corresponding to a virtual storage unit and a mapping between portions of the virtual storage unit to contiguous physical storage, and a second level corresponding to information describing the physical storage;

reading from the metadata structure in a first order from the first level to the second level without locking; and

writing to the metadata structure in a second order from the second level to the first level without locking, wherein the second order is opposite of the first order.

2. The method of claim 1, in which the virtual storage unit comprises a virtual disk, the physical storage comprises an extent, and the mapping comprises a mapping between one or more extents and a virtual disk address space.

3. The method of claim 2, in which the mapping can be used to identify an extent identifier using a virtual disk identifier and an offset within the virtual disk.

4. The method of claim 2, in which one or more extents corresponds to a file having multiple extents.

5. The method of claim 1, in which the mapping comprises information pertaining to replica information and extent information.

6. The method of claim 5, in which the extent information comprises a reference count, a checksum, or an offset location.

7. The method of claim 1, in which an extent is de-duplicated, and the metadata comprises an indication of de-duplication for the extent.

8. The method of claim 7, in which an update to a virtual disk address space causes replacement of an existing extent with a replacement extent.

9. The method of claim 7, in which de-duplicated extents have the same extent identifier.

10. The method of claim 1, in which a reference count is maintained to indicate a number of references for an extent.

11. The method of claim 1, in which garbage collection is implemented by removing extraneous or dangling items in the metadata.

12. The method of claim 1, in which a race condition is identified, and accessing of the metadata is restarted.

13. The method of claim 12, in which the race condition is identified because of an inconsistency in the metadata.

14. The method of claim 13, in which a check is made whether the inconsistency is resolved after the restart, wherein an error condition is identified if the inconsistency is not resolved.

15. The method of claim 1, in which an update operation to an item of metadata is performed such that the item is confirmed not to have been changed by another entity from start of the update operation to conclusion of the update operation.

16. The method of claim 15, in which a compare and swap procedure is performed to perform the update operation.

17. The method of claim 1, in which an intent to update an item of metadata is recorded, where the intent can be accessed by other operations.

18. A storage system comprising storage devices in a virtualization system, comprising:

a processor to handle computing instructions to access the storage devices; and

computer readable medium comprising metadata for the virtualization system, wherein the metadata comprises a metadata structure hierarchy with a plurality of levels including at least a first level corresponding to a virtual storage unit and a mapping between portions of the virtual storage unit to contiguous physical storage, and a second level corresponding to information describing the physical storage, in which lock-free access of the metadata is implemented by the processor reading from the metadata structure in a first order from the first level to the second level without locking and writing to the metadata structure in a second order from the second level to the first level without locking, wherein the second order is opposite of the first order.

19. The system of claim 18, in which the virtual storage unit comprises a virtual disk, the physical storage comprises an extent, and the mapping comprises a mapping between one or more extents and a virtual disk address space.

20. The system of claim 19, in which the mapping can be used to identify an extent identifier using a virtual disk identifier and an offset within the virtual disk.

21. The system of claim 18, in which one or more extents corresponds to a file having multiple extents.

22. The system of claim 18, in which the mapping comprises information pertaining to replica information and extent information.

23. The system of claim 22, in which the extent information comprises a reference count, a checksum, or an offset location.

24. The system of claim 18, in which an extent is de-duplicated, and the metadata comprises an indication of de-duplication for the extent.

25. The system of claim 24, in which an update to a virtual disk address space causes replacement of an existing extent with a replacement extent.

26. The system of claim 24, in which de-duplicated extents have the same extent identifier.

27. The system of claim 18, in which a reference count is maintained to indicate a number of references for an extent.

28. A computer program product embodied on a non-transitory computer usable medium, the computer readable medium having stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a method for performing lock free processing of metadata for storage devices in a virtualization system, the method comprising:

identifying a metadata structure hierarchy with a plurality of levels including at least a first level corresponding to a virtual storage unit and a mapping between portions of the virtual storage unit to contiguous physical storage, and a second level corresponding to information describing the physical storage;

reading from the metadata structure in a first order from the first level to the second level without locking; and

writing to the metadata structure in a second order from the second level to the first level without locking, wherein the second order is opposite of the first order.

29. The computer program product of claim 28, in which the virtual storage unit comprises a virtual disk, the physical storage comprises an extent, and the mapping comprises a mapping between one or more extents and a virtual disk address space.

30. The computer program product of claim 29, in which the mapping can be used to identify an extent identifier using a virtual disk identifier and an offset within the virtual disk.

31. The computer program product of claim 29, in which one or more extents corresponds to a file having multiple extents.

32. The computer program product of claim 28, in which the mapping comprises information pertaining to replica information and extent information.

33. The computer program product of claim 32, in which the extent information comprises a reference count, a checksum, or an offset location.

34. The computer program product of claim 28, in which an extent is de-duplicated, and the metadata comprises an indication of de-duplication for the extent.

35. The computer program product of claim 34, in which an update to a virtual disk address space causes replacement of an existing extent with a replacement extent.

36. The computer program product of claim 34, in which de-duplicated extents have the same extent identifier.

37. The computer program product of claim 28, in which a reference count is maintained to indicate a number of references for an extent.

38. The computer program product of claim 28, in which garbage collection is implemented by removing extraneous or dangling items in the metadata.

39. The computer program product of claim 28, in which a race condition is identified, and accessing of the metadata is restarted.

40. The computer program product of claim 39, in which the race condition is identified because of an inconsistency in the metadata.

41. The computer program product of claim 40, in which a check is made whether the inconsistency is resolved after the restart, wherein an error condition is identified if the inconsistency is not resolved.

42. The computer program product of claim 28, in which an update operation to an item of metadata is performed such that the item is confirmed not to have been changed by another entity from start of the update operation to conclusion of the update operation.

43. The computer program product of claim 42, in which a compare and swap procedure is performed to perform the update operation.

44. The computer program product of claim 28, in which an intent to update an item of metadata is recorded, where the intent can be accessed by other operations.