APPARATUS, SYSTEM, AND METHOD FOR MANAGING OUT-OF-SERVICE CONDITIONS

• US 20130019072A1
• Filed: 01/19/2012
• Published: 01/17/2013
• Est. Priority Date: 01/19/2011
• Status: Active Grant

• Current Assignee: SanDisk Technologies LLC (Western Digital Corporation)
• Original Assignee: Fusion-IO Incorporated (Western Digital Corporation)
• Inventors: Strasser, John, Flynn, David, Inskeep, Bill
• Granted Patent: US 9,213,594 B2
• Time in Patent Office: Days
• US Class Current: 711/154
• CPC Class Codes: G06F 11/1044 with specific ECC/EDC distribution
• CPC Class Codes: G06F 11/108 Parity data distribution in semiconductor storages, e.g. in SSD
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• 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 3/0673 Single storage device

Abstract

An adaptive logical storage element comprises a plurality of solid-state storage elements accessible in parallel. The logical storage element includes logical storage units, which may include logical page, logical storage divisions (erase blocks), and so on. Each logical storage unit comprises a plurality of physical storage units. A logical storage unit may include one or more physical storage units that are out-of-service (OOS). The OOS status of logical storage units is tracked by OOS metadata. When data is stored on the logical storage element, padding data is provided to physical storage units that are OOS, and valid and/or parity data is provided to in-service physical storage units. A write data pipeline accesses the OOS metadata to insert padding data, and a read data pipeline accesses the OOS metadata to strip padding data.

Claims

1. A method for managing storage operations on logical storage units each comprising a respective plurality of physical storage units accessible in parallel, the method comprising:

receiving a request to perform a storage operation on a logical storage unit; and

adapting a storage operation performed on the logical storage unit to account for physical storage units of the logical storage unit that are out of service in response to the request.

2. The method of claim 1, wherein adapting the storage operation comprises masking physical storage units of the logical storage unit that are out of service.

3. The method of claim 1, further comprising referencing out-of-service metadata of the logical storage unit to identify out-of-service physical storage units of the logical storage unit.

4. The method of claim 3, further comprising maintaining the out-of-service metadata at one of a page level of granularity, an erase block level of granularity, a die level of granularity, a plane level of granularity, and a storage element level of granularity.

5. The method of claim 1, wherein the storage operation comprises storing data on the logical storage unit, and wherein adapting the storage operation comprises combining padding data with data of the storage operation to mask the out-of-service physical storage units with the padding data.

6. The method of claim 1, wherein the storage operation comprises storing data on the logical storage unit, and wherein adapting the storage operation comprises issuing a programming command configured to program data on in-service physical storage units of the logical storage unit and ignoring the out-of-service physical storage units of the logical storage unit.

7. The method of claim 1, wherein the storage operation comprises reading data of the logical storage unit, and wherein adapting the storage operation comprises stripping data corresponding to the out-of-service physical storage units from data read from the logical storage unit.

8. The method of claim 1, wherein the storage operation comprises reading data of the logical storage unit, and wherein adapting the storage operation comprises stripping padding data from data read from the logical storage unit, wherein the padding data prevents an ECC codeword from overrunning a storage boundary.

9. The method of claim 1, further comprising accessing each physical storage unit of the logical storage unit using the same address.

10. The method of claim 1, further comprising remapping one or more replacement physical storage units into the logical storage unit to replace physical storage units in the first set in response to a number of out-of-service physical storage units of the logical storage unit exceeding a threshold.

11. An apparatus for performing storage operations, comprising:

a plurality of storage elements; and

a storage controller in parallel communication with each of the plurality of storage elements to form a plurality of logical storage units, each logical storage unit comprising respective physical storage units of the storage elements;

wherein the storage controller is configured to adapt storage operations performed on the logical storage units in accordance with out-of-service metadata that identifies physical storage units that are out of service.

12. The apparatus of claim 11, wherein the storage controller adapts a storage operation to store data on a logical storage unit by mapping padding data to out-of-service physical storage units of the logical storage unit on a bus coupling the storage controller to the storage elements.

13. The apparatus of claim 12, wherein the storage controller comprises a switch to combine padding data with data of the storage operation such that the padding data masks the out-of-service physical storage units of the logical storage unit.

14. The apparatus of claim 12, wherein the storage controller provides the same physical address to each physical storage unit of the logical storage unit and programs data on the logical storage unit using a single program command.

15. The apparatus of claim 14, wherein the storage controller configures the single program command to bypass out-of-service physical storage units of the logical storage unit.

16. The apparatus of claim 11, wherein the storage controller adapts a storage operation to read data on a logical storage unit by stripping data corresponding to out-of-service physical storage units from data read from the logical storage unit.

17. The apparatus of claim 11, wherein the storage controller ignores status pertaining to physical storage units that are out of service.

18. The apparatus of claim 11, wherein the storage controller identifies a physical storage unit to hold parity data of a logical storage unit using the out-of-service metadata.

19. The apparatus of claim 11, wherein the storage controller replaces an out-of-service physical storage unit of a logical storage unit with a replacement physical storage unit in response to a number of out-of-service physical storage units of the logical storage unit exceeding a threshold.

20. A computer-readable storage medium comprising instructions to cause a computing device to perform a method, comprising:

receiving a request to perform a storage operation on one of a plurality of logical storage units, each logical storage unit comprising a respective plurality of physical storage units accessible in parallel;

referencing out-of-service metadata to identify physical storage units of the logical storage unit that are out of service; and

adapting a storage operation performed on the logical storage unit to mask the physical storage units that are out of service.

21. The computer-readable storage medium of claim 20, wherein adapting the storage operation comprises one of:

mapping padding data to the out-of-service physical storage units on a bus that couples the storage controller to the physical storage units of the logical storage unit; and

stripping data corresponding to the out-of-service physical storage units from data read from the physical storage units of the logical storage unit.