Service associated with persistent storage

• US 8,799,618 B2
• Filed: 04/12/2011
• Issued: 08/05/2014
• Est. Priority Date: 04/12/2011
• Status: Active Grant

• Current Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Original Assignee: Empire Technology Development LLC (Allied Inventors Management, LLC)
• Inventors: Cilibrasi, Rudi
• Primary Examiner(s): PEUGH, BRIAN R
• Application Number:
  US13/503,628
• Publication Number:
  US 20120290811A1
• Time in Patent Office: 1,211 Days
• Field of Search: None
• US Class Current: 711/202
• CPC Class Codes: G06F 12/023 Free address space management
• CPC Class Codes: G06F 12/0292 using tables or multilevel address translation means G06F12/023 takes precedence; address translation in virtual memory systems G06F12/10
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/064 Management of blocks
• 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 3/0679 Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]

Abstract

Examples are disclosed for allocating a block of persistent storage or accessing a block of persistent storage based on a storage service string that includes a universally unique identifier and associated metadata.

Claims

1. A method for allocating a block of persistent storage comprising:

generating a universally unique identifier for the block of persistent storage;

forming a storage service string to include the universally unique identifier and metadata, the metadata to indicate one or more characteristics for a storage service associated with the block of persistent storage; and

forwarding the storage service string to a storage device driver, wherein based, at least in part, on the storage service string, the storage device driver is to be configured to allocate the block of persistent storage from persistent storage accessible to the storage device driver.

2. A method according to claim 1, further comprising:

creating an entry in a sparse non-deterministic block index, the entry to include the universally unique identifier and associated metadata for the allocated block of persistent storage, wherein the sparse non-deterministic block index is to be available to one or more applications and/or file systems interconnected via one or more network communication links.

3. A method according to claim 1, wherein the one or more characteristics for the storage service comprises:

a size for the block of persistent storage;

an expiration time period for the block of persistent storage;

a number of allowed reads per given time period for the block of persistent storage;

or

a number of allowed writes per given time period for the block of persistent storage.

4. A method according to claim 3, wherein the expiration time period comprises an indication of a number of seconds since an epoch from which the block of persistent storage is set to expire, the epoch to be based on a date of Jan. 1, 1970.

5. A method according to claim 1, wherein generating a universally unique identifier comprises a file system or application generating a 32-byte random number.

6. A method according to claim 1, wherein forming the storage service string comprises encoding the universally unique identifier and metadata using Representational State Transfer (REST) architectural style to form a Uniform Resource Identifier (URI).

7. A method according to claim 6, wherein the URI includes an indication of a host associated with a location for the persistent storage accessible by the storage device driver.

8. A method according to claim 6, wherein forwarding the storage service string to a storage device driver comprises forwarding the storage service string using Hypertext Transfer Protocol (HTTP).

9. A method according to claim 1, wherein forwarding the storage service string to the storage device driver comprises forwarding the storage service string to the storage device driver via a first network communication link and the persistent storage to be accessible to the storage device driver via a second network communication link.

10. A method according to claim 1, wherein forwarding the storage service string to the storage device driver comprises forwarding the storage service string to the storage device driver via a first local communication link and the persistent storage to be accessible to the storage device driver via a second local communication link.

11. A method according to claim 1, further comprising:

using a cryptographic hash function to deterministically generate a pseudo-random identification from the universally unique identifier;

forming another storage service string to include the pseudo-random unique identifier and metadata, the metadata to indicate the one or more characteristics for the storage service associated with the allocated block of persistent storage; and

forwarding the other storage service string to the storage device driver, wherein based, at least in part, on the other storage service string, the storage device driver is to be configured to allocate a separate block of persistent storage from the persistent storage accessible to the storage device driver.

12. A method for allocating a block of persistent storage comprising:

at a storage device driver, receiving a storage service string that includes a universally unique identifier and metadata, the metadata to indicate one or more characteristics for a storage service associated with the block of persistent storage; and

allocating the block of persistent storage based, at least in part, on the storage service string, wherein the block of persistent storage is allocated from available persistent storage accessible to the storage device driver.

13. A method according to claim 12, wherein the one or more characteristics for the storage service comprises:

a size for the block of persistent storage;

an expiration time period for the block of persistent storage;

a number of allowed reads per given time period for the block of persistent storage;

or

a number of allowed writes per given time period for the block of persistent storage.

14. A method according to claim 12, wherein the universally unique identifier comprises a 32-byte number that was randomly generated by a file system or application that forwarded the received storage service string.

15. A method according to claim 12, wherein the storage service string comprises a Uniform Resource Identifier (URI) that encodes the universally unique identifier and metadata in accordance with Representational State Transfer (REST) architectural style.

16. A method according to claim 15, wherein receiving the storage service string comprises receiving the storage service string using Hypertext Transfer Protocol (HTTP).

17. A method according to claim 12, wherein the URI includes an indication of a host associated with a location for the persistent storage accessible by the storage device driver.

18. A method according to claim 12, further comprising:

writing to the allocated block of persistent storage, wherein writing to the allocated block of persistent storage includes using a cryptographic protocol to sign at least a portion of data to be written to the allocated block of persistent storage.

19. A method for a file system or application to access a block of persistent storage comprising:

obtaining a storage service string that includes a universally unique identifier and metadata, the metadata to indicate one or more characteristics for a storage service associated with the block of persistent storage; and

forwarding the storage service string to a storage device driver to submit a read request for the storage service associated with the block of persistent storage, wherein based, at least in part, on the storage service string, the storage device driver is to be configured to fulfill the read request by accessing the block of persistent storage from persistent storage accessible to the storage device driver.

20. A method according to claim 19, further comprising:

accessing an entry in a sparse non-deterministic block index to obtain the storage service string, the entry to include the universally unique identifier and associated metadata for the block of persistent storage, wherein the sparse non-deterministic block index is to be available to the file system or application via a local communication link or a network communication link.

21. A method according to claim 19, wherein the one or more characteristics for the storage service comprises:

a size for the block of persistent storage;

an expiration time period for the block of persistent storage;

a number of allowed reads per given time period for the block of persistent storage;

or

a number of allowed writes per given time period for the block of persistent storage.

22. A method according to claim 21, wherein the expiration time period comprises an indication of a number of seconds since an epoch from which the block of persistent storage is set to expire, the epoch to be based on a date of Jan. 1, 1970.

23. A method according to claim 19, wherein the storage service string comprises a Uniform Resource Identifier (URI) that encodes the universally unique identifier and metadata in accordance with Representational State Transfer (REST) architectural style.

24. A method according to claim 23, wherein forwarding the storage service string to the storage device driver comprises forwarding the storage service string using Hypertext Transfer Protocol (HTTP).

25. A method according to claim 19, wherein forwarding the storage service string to the storage device driver comprises forwarding the storage service string to the storage device driver via a first network communication link and the storage device driver to access the persistent storage via a second network communication link.

26. An apparatus for fulfilling a read request associated with a block of persistent storage, the apparatus comprising:

a service manager having logic, the logic configured to;

receive a storage service string that includes a universally unique identifier and metadata, the metadata to indicate one or more characteristics for a storage service associated with the block of persistent storage; and

fulfill the read request by accessing the block of persistent storage and provide data maintained therein to the requestor based, at least in part, on the storage service string.

27. An apparatus according to claim 26, wherein the universally unique identifier and associated metadata included in the storage service string were obtained by the requester from an entry in a sparse non-deterministic block index that is available to one or more applications and/or file systems interconnected via one or more network communication links.

28. An apparatus according to claim 26, wherein the one or more characteristics for the storage service comprises:

a size for the block of persistent storage;

an expiration time period for the block of persistent storage;

a number of allowed reads per given time period for the block of persistent storage;

or

a number of allowed writes per given time period for the block of persistent storage.

29. An apparatus according to claim 26, wherein the universally unique identifier comprises a 32-byte number that was randomly generated by the originator of the received storage service string.

30. An apparatus according to claim 26, wherein the storage service string comprises a Uniform Resource Identifier (URI) that encodes the universally unique identifier and metadata in accordance with Representational State Transfer (REST) architectural style.

31. An apparatus according to claim 30, wherein the URI includes an indication of a host associated with a location for persistent storage that includes the block of persistent storage.

32. An apparatus according to claim 30, wherein to receive the storage service string comprises to receive the storage service string using Hypertext Transfer Protocol (HTTP).

33. A system for allocating a block of persistent storage comprising:

a persistent storage device;

an application including an index manager having index logic, the index logic configured to;

generate a universally unique identifier for the block of persistent storage;

form a storage service string to include the universally unique identifier and metadata, the metadata to indicate one or more characteristics for a storage service associated with the block of persistent storage; and

forward the storage service string to submit an allocation request for the block of persistent storage; and

a storage device driver including a service manager having service logic, the service logic configured to;

receive the storage service string forwarded from the application; and

allocate the block of persistent storage to fulfill the allocation request based, at least in part, on the storage service string, wherein the block of persistent storage is allocated from available persistent storage maintained at the persistent storage device.

34. A system according to claim 33, wherein the index logic is further configured to:

create an entry in a sparse non-deterministic block index, the entry to include the universally unique identifier and associated metadata for the allocated block of persistent storage, wherein the sparse non-deterministic block index is to be available to the application and one or more other applications and/or file systems interconnected via one or more network communication links.

35. A system according to claim 33, wherein the one or more characteristics for the storage service comprises:

a size for the block of persistent storage;

an expiration time period for the block of persistent storage;

a number of allowed reads per given time period for the block of persistent storage;

or

a number of allowed writes per given time period for the block of persistent storage.

36. A system according to claim 33, wherein to form the storage service string comprises the index logic further configured to encode the universally unique identifier and metadata using Representational State Transfer (REST) architectural style to form a Uniform Resource Identifier (URI).

37. A system according to claim 36, wherein the URI includes an indication of a host associated with a location for the persistent storage device.

38. A system according to claim 33, wherein to forward the storage service string to a storage device driver comprises the index logic further configured to forward the storage service string using Hypertext Transfer Protocol (HTTP).

39. A system according to claim 33, wherein to forward the storage service string to the storage device driver comprises the index logic further configured to forward the storage service string to the storage device driver via a first network communication link and the persistent storage device to be accessible to the service logic of the storage device driver via a second network communication link.

40. A computer program product comprising a non-transitory medium having instructions for a file system or application to access a block of persistent storage, which, when executed by logic, cause the logic to:

obtain a storage service string that includes a universally unique identifier and metadata, the metadata to indicate one or more characteristics for a storage service associated with the block of persistent storage; and

forward the storage service string to a storage device driver to submit a read request for the storage service associated with the block of persistent storage, wherein based, at least in part, on the storage service string, the storage device driver is to be configured to fulfill the read request by accessing the block of persistent storage from persistent storage accessible to the storage device driver.

41. A computer program product according to claim 40, further comprising instructions to cause the logic to:

access an entry in a sparse non-deterministic block index to obtain the storage service string, the entry to include the universally unique identifier and associated metadata for the block of persistent storage, wherein the sparse non-deterministic block index is to be available to the file system or application via a local communication link or a network communication link.

42. A computer program product according to claim 40, wherein the one or more characteristics for the storage service comprises:

a size for the block of persistent storage;

an expiration time period for the block of persistent storage;

a number of allowed reads per given time period for the block of persistent storage;

or

a number of allowed writes per given time period for the block of persistent storage.

43. A computer program product according to claim 40, wherein the storage service string comprises a Uniform Resource Identifier (URI) that encodes the universally unique identifier and metadata in accordance with Representational State Transfer (REST) architectural style.

44. A computer program product according to claim 43, wherein to forward the storage service string to the storage device driver comprises to forward the storage service string using Hypertext Transfer Protocol (HTTP).

45. An apparatus for storing data, the apparatus comprising:

one or more blocks of persistent storage, each block of persistent storage to be configured such that separate blocks of persistent storage are allocated to separate universally unique identifiers, wherein the separate blocks of persistent storage are also configured to store variable blocks of data based, at least in part, on separate storage service strings respectively associated with the separate universally unique identifiers.

46. An apparatus according to claim 45, wherein a separate storage service string from among the separate storage service strings respectively associated with the separate universally unique identifiers comprises the separate storage service string to also include metadata, the metadata to indicate one or more characteristics for a storage service associated with a block of persistent storage from among the separate blocks of persistent storage.

48. An apparatus according to claim 45, wherein the one or more blocks of persistent storage comprise memory cells for at least one of a solid state hard drive or a hard disk drive.

47. An apparatus according to clam 46, wherein the one or more characteristics for the storage service comprises:

a size for the block of persistent storage;

an expiration time period for the block of persistent storage;

a number of allowed reads per given time period for the block of persistent storage;

or

a number of allowed writes per given time period for the block of persistent storage.