Rapid recovery from downtime of mirrored storage device

• US 10,380,021 B2
• Filed: 03/13/2013
• Issued: 08/13/2019
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Loaiza, Juan R., Umamageswaran, Kothanda, Friedman, David, Shi, Jia, Tao, Zuoyu, Tsukerman, Alex
• Primary Examiner(s): Dudek, Jr., Edward J
• Application Number:
  US13/801,319
• Publication Number:
  US 20140281272A1
• Time in Patent Office: 2,344 Days
• CPC Class Codes: G06F 11/2058 using more than 2 mirrored copies
• CPC Class Codes: G06F 11/2082 Data synchronisation
• CPC Class Codes: G06F 12/0804 with main memory updating G06F12/0806 takes precedence
• CPC Class Codes: G06F 12/0868 Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
• CPC Class Codes: G06F 12/12 Replacement control
• CPC Class Codes: G06F 2212/222 Non-volatile memory
• CPC Class Codes: G06F 2212/262 configured as RAID
• CPC Class Codes: G06F 2212/286 Mirrored cache memory

Abstract

No-loss rapid recovery performs resynchronization efficiently while concurrently allowing availability to mirrored data on the storage device. No-loss rapid recovery has two stages and involves storage devices that have both a non-volatile cache and primary storage and that operate as mirror buddies. The first stage is referred to herein as the buddy-retention stage. During the buddy-retention stage, writes to mirrored data are not performed on the offline mirror buddy but are performed on the online mirror buddy. The mirrored data changed in the online mirrored buddy is retained in the non-volatile cache of the retention buddy. The next stage is referred to herein as the rapid resynchronization stage. In this stage, the changed mirrored data retained by the retention buddy for no-loss rapid recovery is used to resynchronize the offline buddy. The storage device is resynchronized using the changed mirrored data retained in the cache of the mirror buddy.

Claims

1. A method, comprising steps of:

from a storage device client of a mirrored set of storage devices for mirroring data that includes a plurality of data blocks, a first storage device receiving one or more requests indicating to retain data blocks in a non-volatile cache of said first storage device;

wherein said first storage device and a second storage device belong to said mirrored set of storage devices;

in response to receiving one or more requests to write said plurality of data blocks stored in a primary store of said first storage device;

said first storage device writing said plurality of data blocks to said non-volatile cache of said first storage device;

in response to receiving said one or more requests indicating to retain data blocks, marking each data block of said plurality of data blocks for recovery retention;

performing cache management on said non-volatile cache, wherein performing cache management includes, while each data block of said plurality of data blocks is clean, foregoing replacing said each data block in response to said each data block being marked for recovery retention; and

after foregoing replacing said each data block of said plurality of data blocks, resynchronizing said second storage device using said plurality of data blocks retained in said non-volatile cache of said first storage device.

2. The method of claim 1, wherein the steps further include:

said storage device client of said mirrored set of storage devices transmitting said one or more requests to write said plurality of data blocks; and

said storage device client of said mirrored set of storage devices tracking in a list of dirty data blocks said plurality of data blocks.

3. The method of claim 2, wherein the step of resynchronizing includes:

based on the list of dirty data blocks, said storage device client identifying data blocks to resynchronize in said second storage device, wherein identifying data blocks to resynchronize includes identifying said plurality of data blocks;

said storage device client of said mirrored set of storage devices transmitting a request for said plurality of data blocks to said first storage device;

said first storage device retrieving said plurality of data blocks from said non-volatile cache and returning said plurality of data blocks to said storage device client; and

said storage device client transmitting a request to said second storage device to write said plurality of data blocks.

4. The method of claim 1, the steps further including:

receiving a message indicating to cease retaining said plurality of data blocks; and

in response to receiving said message, ceasing to retain said plurality of data blocks in said non-volatile cache.

5. The method of claim 4, wherein ceasing to retain includes discarding said plurality of data blocks from said non-volatile cache of said primary store of said first storage device.

6. The method of claim 1, the steps further including performing a write-though operation, wherein said write-through includes said writing said plurality of data blocks to said non-volatile cache of a primary store of said first storage device and writing said plurality of data blocks to said primary store.

7. The method of claim 1, wherein the step of resynchronizing includes:

said storage device client of said mirrored set of storage devices transmitting a request for said plurality of data blocks to said first storage device;

said first storage device retrieving said plurality of data blocks from said non-volatile cache and returning said plurality of data blocks to said storage device client; and

said storage device client transmitting a request to said second storage device to write said plurality of data blocks.

8. One or more non-transitory storage media storing sequences of instructions which, when executed by one or more computing devices, cause:

from a storage device client of a mirrored set of storage devices for mirroring data that includes a plurality of data blocks, a first storage device receiving one or more requests indicating to retain data blocks in a non-volatile cache of said first storage device;

wherein said first storage device and a second storage device belong to said mirrored set of storage devices;

in response to receiving one or more requests to write said plurality of data blocks stored in a primary store of said first storage device;

said first storage device writing said plurality of data blocks to said non-volatile cache of said first storage device;

in response to receiving said one or more requests indicating to retain data blocks, marking each data block of said plurality of data blocks for recovery retention;

performing cache management on said non-volatile cache, wherein performing cache management includes, while each data block of said plurality of data blocks is clean, foregoing replacing said each data block in response to said each data block being marked for recovery retention; and

after foregoing replacing said each data block of said plurality of data blocks, resynchronizing said second storage device using said plurality of data blocks retained in said non-volatile cache of said first storage device.

9. The one or more non-transitory storage media of claim 8, wherein the sequences of instructions include instructions that, when executed by said one or more computing devices, cause:

said storage device client of said mirrored set of storage devices transmitting said one or more requests to write said plurality of data blocks; and

said storage device client of said mirrored set of storage devices tracking in a list of dirty data blocks said plurality of data blocks.

10. The one or more non-transitory storage media of claim 9, wherein resynchronizing includes:

based on the list of dirty data blocks, said storage device client identifying data blocks to resynchronize in said second storage device, wherein identifying data blocks to resynchronize includes identifying said plurality of data blocks;

said storage device client of said mirrored set of storage devices transmitting a request for said plurality of data blocks to said first storage device;

said first storage device retrieving said plurality of data blocks from said non-volatile cache and returning said plurality of data blocks to said storage device client; and

said storage device client transmitting a request to said second storage device to write said plurality of data blocks.

11. The one or more non-transitory storage media of claim 8, wherein the sequences of instructions include instructions that, when executed by said one or more computing devices, cause:

receiving a message indicating to cease retaining said plurality of data blocks; and

in response to receiving said message, ceasing to retain said plurality of data blocks in said non-volatile cache.

12. The one or more non-transitory storage media of claim 11, wherein ceasing to retain includes discarding said plurality of data blocks from said non-volatile cache of said primary store of said first storage device.

13. The one or more non-transitory storage media of claim 8, wherein the sequences of instructions include instructions that, when executed by said one or more computing devices, cause performing a write-though operation, wherein said write-through operation includes said writing said plurality of data blocks to said non-volatile cache of a primary store of said first storage device and writing said plurality of data blocks to said primary store.

14. The one or more non-transitory storage media of claim 8, wherein the sequences of instructions include instructions that, when executed by said one or more computing devices, cause:

said storage device client of said mirrored set of storage devices transmitting a request for said plurality of data blocks to said first storage device;

said first storage device retrieving said plurality of data blocks from said non-volatile cache and returning said plurality of data blocks to said storage device client; and

said storage device client transmitting a request to said second storage device to write said plurality of data blocks.