Method and system for ensuring reliability of cache data and metadata subsequent to a reboot

• US 9,032,151 B2
• Filed: 11/14/2008
• Issued: 05/12/2015
• Est. Priority Date: 09/15/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Iyigun, Mehmet, Bak, Yevgeniy, Fortin, Michael, Fields, David, Ergan, Cenk, Kirshenbaum, Alexander
• Primary Examiner(s): Shah, Sanjiv
• Assistant Examiner(s): Gossage, Glenn
• Application Number:
  US12/271,472
• Publication Number:
  US 20100070701A1
• Time in Patent Office: 2,370 Days
• Field of Search: 711/113, 711/115, 711/118, 711/141
• US Class Current: 711/118
• CPC Class Codes: G06F 11/1441 Resetting or repowering
• CPC Class Codes: G06F 12/0833 in combination with broadcast means (e.g. for invalidation or updating)
• CPC Class Codes: G06F 12/0862 with prefetch
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 12/128 adapted to multidimensional cache systems, e.g. set-associative, multicache, multiset or multilevel
• CPC Class Codes: G06F 12/14 Protection against unauthorised use of memory or access to memory
• CPC Class Codes: G06F 2212/1052 Security improvement
• CPC Class Codes: G06F 2212/2022 Flash memory
• CPC Class Codes: G06F 2212/2146 being detachable, e.g.. USB memory
• CPC Class Codes: G06F 2212/222 Non-volatile memory
• CPC Class Codes: G06F 2212/466 Metadata, control data
• CPC Class Codes: G06F 2212/62 Details of cache specific to multiprocessor cache arrangements
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

To ensure that the contents of a non-volatile memory device cache may be relied upon as accurately reflecting data stored on disk storage, it may be determined whether the cache contents and/or disk contents are modified during a power transition, causing cache contents to no longer accurately reflect data stored in disk storage. The cache device may be removable from the computer, and unexpected removal of the cache device may cause cache contents to no longer accurately reflect data stored in disk storage. Cache metadata may be managed during normal operations and across power transitions, ensuring that cache metadata may be efficiently accessed and reliably saved and restored across power transitions. A state of a log used by a file system may be determined prior to and subsequent to reboot of an operating system in order to determine whether data stored on a cache device may be reliably used.

Claims

1. A method for operating a computer that is coupled to a storage medium and a cache device, the computer comprising an operating system, the method comprising acts of:

(A) activating a write recorder component configured for identifying write operations performed to the storage medium which are not performed to the cache device;

(B) in response to a request to write a data item to the storage medium at an address, causing the data item to be written to the storage medium at the address and to the cache device at a corresponding address;

(C) capturing a snapshot of the data item written to the cache device at the corresponding address;

(D) subsequent to a reboot of the operating system, determining whether the data item written to the cache device at the corresponding address can reliably be used to satisfy a request to read the data item from the storage medium at the address, the determining including determining, via the write recorder component, whether the data item written to the storage medium at the address was modified after completion of act (B); and

(E) if it is determined in act (D) that the data item written to the cache device at the corresponding address cannot reliably be used to satisfy the request to read the data item from the storage medium at the address, then causing the cache device to be updated using the snapshot and data from the write recorder component.

2. The method of claim 1, wherein the acts (A)-(E) are performed by the operating system.

3. The method of claim 1, wherein the storage medium comprises a disk storage device.

4. The method of claim 1, wherein the cache device is removable from the computer.

5. The method of claim 1, wherein the operating system is configured for activating the write recorder component when it is determined that the operating system is being shut down.

6. The method of claim 1, wherein the act (D) is performed in response to the request to read the data item from the storage medium at the address, and the method further comprises verifying that the data item written to the cache device at the corresponding address was not modified after completion of the act (B).

7. The method of claim 6, wherein act (B) further comprises generating a representation of at least the data item written to the storage medium at the address and writing the representation to the cache device, and wherein the act of verifying in act (D) comprises:

(D1) retrieving the representation that was written to the cache device;

(D2) re-generating the representation; and

(D3) comparing the retrieved representation to the re-generated representation to determine whether the data item written to the cache device at the corresponding address can reliably be used to satisfy the request to read the data item written to the storage medium at the address.

8. At least one computer storage medium that is a memory device storing instructions that, when executed by a computer comprising an operating system and coupled to a cache device, cause the computer to perform a method comprising acts of:

(A) activating a write recorder component configured for identifying write operations performed to the computer storage medium which are not performed to the cache device;

(B) in response to a request to write a data item to the computer storage medium at an address, causing the data item to be written to the computer storage medium at the address and to the cache device at a corresponding address;

(C) capturing a snapshot of the data item written to the cache device at the corresponding address;

(D) subsequent to a reboot of the operating system, determining whether the data item written to the cache device at the corresponding address can reliably be used to satisfy a request to read the data item from the computer storage medium at the address, the determining including determining, via the write recorder component, whether the data item written to the computer storage medium device at the address was modified after completion of act (B); and

(E) if it is determined in act (D) that the data item written to the cache device at the corresponding address cannot reliably be used to satisfy the request to read the data item from the storage medium at the address, then causing the cache device to be updated using the snapshot and data from the write recorder component.

9. The at least one computer storage medium of claim 8, wherein the act (E) further comprises causing the data item to be read from the computer storage medium at the address when it is determined, after the update, that the data item written to the cache device at the corresponding address cannot reliably be used to satisfy the request to read the data item from the storage medium at the address.

10. The at least one computer storage medium of claim 8, wherein the act (E) further comprises causing the data item to be evicted from the cache device at the corresponding address when it is determined that, after the update, the data item written to the cache device at the corresponding address cannot reliably be used to satisfy the request to read the data item from the storage medium at the address.

11. The at least one computer storage medium of claim 8, wherein the act (B) further comprises generating a representation of at least the data item written to the storage medium at the address and writing the representation to the cache device, wherein the act of determining in act (D) comprises:

(D1) retrieving the representation that was written to the cache device;

(D2) re-generating the representation; and

(D3) comparing the retrieved representation to the re-generated representation to determine whether the data item written to the cache device at the corresponding address can reliably be used to satisfy the request to read the data item written to the storage medium at the address.

12. The at least one computer storage medium of claim 8, wherein the act (B) further comprises generating a representation of at least the data item written to the storage medium at the address and writing the representation to the cache device, wherein the act of generating a representation comprises employing a cryptographic technique.

13. The at least one computer storage medium of claim 8, wherein the act (B) further comprises employing cache metadata to determine the corresponding address on the cache device to which the data item is written, and wherein the act (D) further comprises determining whether the cache metadata was modified after act (B).

14. A computer, comprising:

a storage medium having at least one address at which data is stored;

a cache device having at least one address at which data is stored;

a write recorder component configured for identifying write operations performed to the storage medium which are not performed to the cache device;

at least one processor programmed via an operating system to;

in response to a request to write a data item to the storage medium at a first address, cause the data item to be written to the storage medium at the first address and to the cache device at a corresponding address;

capture a snapshot of the data item written to the cache device at the corresponding address;

identify, via the write recorder component, an occurrence of a write operation to the storage medium at the first address which is not also performed to the cache device at the corresponding address;

determine, subsequent to a reboot of the operating system, whether the data item written to the cache device at the corresponding address can reliably be used to satisfy a request to read the data item from the storage medium at the first address, at least in part by determining, via the write recorder component, whether the data item written to the storage medium at the first address was modified after it was written to the storage medium at the first address and to the cache device at the corresponding address; and

upon determining that the data item on the cache device at the corresponding address cannot reliably be used to satisfy the request to read the data item from the storage medium at the first address, causing the cache device to be updated using the snapshot and data from the write recorder component.

15. The computer of claim 14, wherein the at least one processor is programmed to, if it is determined that the data item stored on the cache device at the corresponding address cannot reliably be used to satisfy the read request to read the data item from the storage medium at the first address, evict the data item from the cache device at the corresponding address, and satisfy the request by reading the data item from the storage medium at the first address.

16. The computer of claim 14, wherein the operating system is configured to activate the write recorder component when it is determined that the operating system is being shut down.

17. The computer of claim 14, wherein the write operation which the at least one processor is programmed to identify is to a file system on the storage medium, and wherein the at least one processor is programmed to identify an occurrence of a write operation to the storage medium at an address by placing a log used by the file system in a particular state prior to the reboot of the operating system, and determining whether the log is in the particular state following the reboot of the operating system.

18. The computer of claim 14, wherein the at least one processor is programmed to prevent an occurrence of a write operation to the storage medium at the first address which is not also performed to the cache device at the corresponding address.

19. The computer of claim 18, wherein the write operation which the at least one processor is programmed to prevent is to a volume on the storage medium, and wherein the at least one processor is programmed to prevent the occurrence of the write operation to the storage medium at the first address by making the volume inaccessible.