Limiting access operations in a data storage device

• US 10,534,716 B2
• Filed: 07/13/2016
• Issued: 01/14/2020
• Est. Priority Date: 07/13/2016
• Status: Active Grant

• Current Assignee: Seagate Technology LLC (Seagate Technology Holdings Plc)
• Original Assignee: Seagate Technology LLC (Seagate Technology Holdings Plc)
• Inventors: Jannyavula Venkata, Sumanth, Gaertner, Mark A., Backman, Jonathan G.
• Primary Examiner(s): Farrokh, Hashem
• Application Number:
  US15/209,584
• Publication Number:
  US 20180018269A1
• Time in Patent Office: 1,280 Days
• Field of Search: 711138
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 12/0253 Garbage collection, i.e. reclamation of unreferenced memory
• 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 12/0888 using selective caching, e.g. bypass
• CPC Class Codes: G06F 2212/1008 Correctness of operation, e.g. memory ordering
• CPC Class Codes: G06F 2212/1036 Life time enhancement
• CPC Class Codes: G06F 2212/222 Non-volatile memory
• CPC Class Codes: G06F 2212/281 Single cache
• CPC Class Codes: G06F 2212/313 In storage device
• CPC Class Codes: G06F 2212/7203 Temporary buffering, e.g. using volatile buffer or dedicated buffer blocks
• CPC Class Codes: G06F 2212/7204 Capacity control, e.g. partitioning, end-of-life degradation
• CPC Class Codes: G06F 2212/7205 Cleaning, compaction, garbage collection, erase control

Abstract

A hybrid data storage device disclosed herein includes a main data store, one or more data storage caches, and a data storage cache management sub-system. The hybrid data storage device is configured to limit write operations on the one or more data storage caches to less than an endurance value for the data storage cache. In one implementation, the data storage cache management sub-system limits or denies requests for promotion of data from the main data store to the one or more data storage caches. In another implementation, the data storage cache management sub-system limits garbage collection operations on the data storage cache.

Claims

1. A method comprising:

dividing a remaining lifetime of a data storage cache into a series of time periods;

receiving a write request from a storage controller to write one or more clusters to the data storage cache during a first time period in the series of time periods, the write request being received as part of a request to perform a garbage collection operation on the data storage cache;

determining a maximum number of write operations allowable on the data storage cache during the first time period; and

declining the write request if allowing the write request would exceed the maximum number of write operations allowable on the data storage cache during the first time period by skipping migration of valid data on the data storage cache during garbage collection operations, wherein the valid data for which migration is skipped is chosen from valid data that has remained on the data storage cache longer than a threshold period of time.

2. The method of claim 1, further comprising allowing the write request if allowing the write request would not exceed the maximum number of write operations permitted on the storage cache during the first time period.

3. The method of claim 1, wherein determining a maximum number of write operations allowable on the data storage cache during the first time period comprises:

dividing a number of remaining allowable write operations over the remaining lifetime of the storage cache by a number of periods remaining in the series of time periods.

4. The method of claim 3, wherein the number of remaining allowable write operations over the remaining lifetime of the storage cache is determined by the difference between an expected lifetime write operations endurance of the storage device minus a number of write operations already performed on the storage device over the life of the storage device.

5. The method of claim 4, wherein the expected lifetime write operations endurance of the storage cache is determined based on at least one of:

a write-related failure, a data retention requirement, an operating temperature, and a bit error rate.

6. The method of claim 1, wherein the valid data for which migration is skipped is chosen from the valid data that has remained on the data storage cache longer than the predetermined threshold based on a heuristic.

7. The method of claim 6, wherein the heuristic is based on a history built for the valid data that has remained on the data storage cache longer than the predetermined threshold.

8. A method comprising:

dividing a remaining lifetime of a data storage cache into a series of time periods;

receiving a write request from a storage controller to write one or more clusters to the data storage cache during a first time period in the series of time periods, the write request being received as part of a request to perform a garbage collection operation on the data storage cache;

determining a maximum number of write operations allowable on the data storage cache during the first time period;

declining the write request if allowing the write request would exceed the maximum number of write operations allowable on the data storage cache during the first time period by skipping migration of valid data on the data storage cache during garbage collection operations, wherein the valid data for which migration is skipped is chosen from valid data that has remained on the data storage cache longer than a threshold period of time; and

selecting one or more blocks including one or more pages of valid data from the valid data that has remained on the data storage cache longer than the threshold period of time for erasure during the garbage collection operation if a write amplification of the garbage collection operation exceeds a write amplification limit condition without migrating the one or more pages of valid data.

9. The method of claim 8, wherein the one or more blocks including one or more pages of valid data selected for erasure during a garbage collection operation is sufficient to limit the write amplification of the garbage collection operation to less than the write amplification limit condition.

10. The method of claim 8, wherein the one or more blocks including one or more pages of valid data selected for erasure from the valid data that has remained on the data storage cache longer than the threshold period of time are selected randomly.

11. The method of claim 8, wherein the one or more blocks including one or more pages of valid data selected for erasure from the valid data that has remained on the data storage cache longer than the threshold period of time are selected according to the Least Recently Used (LRU) block.

12. A data storage device comprising:

a data storage medium including a main data store and a data storage cache; and

a data storage cache management sub-system configured to write clusters of data from the main data store to the data storage cache, the data storage cache management sub-system further configured to limit write operations on the data storage cache by skipping migration of valid data on the data storage cache during garbage collection operations, wherein the valid data for which migration is skipped is chosen from valid data has remained on the data storage cache longer than a threshold period of time.

13. The data storage device of claim 12, wherein the data storage cache management sub-system is further configured to limit write operations on the data storage cache by denying promotion requests from a main data store to the data storage cache.

14. The data storage device of claim 12, wherein the data storage cache management sub-system is further configured to limit write operations on the data storage cache by modifying an over-provisioning level of the storage cache.

15. The data storage device of claim 12, wherein the data storage cache is coherent with the main store.

16. The data storage device of claim 12, wherein the data storage cache management sub-system is configured to adjust the expected lifetime write operations endurance on the data storage cache based on one or more of:

write failures, a data retention requirement, operating temperatures, and bit error rate.

17. The data storage device of claim 12, wherein the valid data for which migration is skipped is chosen from the valid data that has remained on the data storage cache longer than the predetermined threshold based on a heuristic.

18. The method of claim 17, wherein the heuristic is based on a history built for the valid data that has remained on the data storage cache longer than the predetermined threshold.