Managing data placement based on flash drive wear level

• US 9,811,288 B1
• Filed: 12/30/2011
• Issued: 11/07/2017
• Est. Priority Date: 12/30/2011
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Inventors: Chen, Xiangping, Duprey, Dennis T., Linnell, Thomas E., Tao, Qin, Ku, Mark K.
• Primary Examiner(s): Rones, Charles
• Assistant Examiner(s): Dare, Ryan
• Application Number:
  US13/341,006
• Time in Patent Office: 2,139 Days
• Field of Search: None
• CPC Class Codes: G06F 3/0616 in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0679 Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays

Abstract

A method is used in managing data in a data storage system. A tiered storage pool is identified wherein the storage pool includes multiple tiers having multiple storage units. A wear indicator for each of the multiple storage units is monitored. A first storage unit having a wear indicator greater than a second storage unit is identified. High activity data on the first storage unit is also identified. The identified high activity data is migrated from the first storage unit to the second storage unit.

Claims

1. A method for use in managing data in a data storage system, the method comprising:

identifying a tiered storage pool wherein the storage pool includes multiple tiers, each tier having multiple storage units;

monitoring a wear indicator and a wear rate for each of the multiple storage units wherein the wear indicator is based on a lifetime erasure count associated with the multiple storage units and the wear rate is associated with the rate at which the wear indicator increases;

determining, for each of the multiple storage units, a predetermined warranty end period and a projected end of life value, wherein the end of life value is based on the wear indicator, the wear rate and the lifetime erasure count,

identifying a first storage unit wherein the projected end of life value will occur before the corresponding warranty end period and a second storage unit wherein the projected end of life value will not occur before its corresponding warranty end period;

identifying high activity data on the first storage unit wherein activity corresponds to an erasure count associated with the data; and

migrating the identified high activity data from the first storage unit to the second storage unit.

2. The method of claim 1 wherein the storage units are flash storage drives.

3. The method of claim 1 wherein the wear indicator is associated with an erasure count for each of the multiple storage units.

4. The method of claim 1 wherein wear indicator information is stored in a wear indicator map.

5. The method of claim 1 wherein high activity data is identified based on a temperature value of the data.

6. The method of claim 1 wherein the data is a slice of data.

7. The method of claim 1 wherein the first storage unit is a drive having the highest wear indicator and the second storage unit is a drive having the lowest wear indicator.

8. The method of claim 1 wherein migrating further includes:

receiving a threshold value;

determining a differential metric associated with the wear indicators of the first storage unit and second storage unit; and

in response to the differential metric exceeding the threshold value, migrating the identified high activity data from the first storage unit to the second storage unit and low activity data from the second storage unit to the first storage unit.

9. The method of claim 8 wherein the threshold is a dynamic value proportional to remaining expected life of a storage unit.

10. The method of claim 1 further comprising:

determining a tier end of life value, wherein the value is based on the expected remaining life of substantially all the storage units in the tier; and

in response to the tier end of life value exceeding a predetermined value, performing at least one of the following;

migrating the identified high activity data from the first storage unit to a storage unit associated with a different tier, notifying a user, diverting future I/O activity to another tier, or reducing write performance.

11. A system for use in managing data in a data storage system, the system comprising a processor configured to:

identify a tiered storage pool wherein the storage pool includes multiple tiers, each tier having multiple storage units;

monitor a wear indicator and a wear rate for each of the multiple storage units wherein the wear indicator is based on a lifetime erasure count associated with the multiple storage units and the wear rate is associated with the rate at which the wear indicator increases;

determined, for each of the multiple storage units, a predetermined warranty end period and a projected end of life value, wherein the end of life value is based on the wear indicator, the wear rate and the lifetime erasure count;

identify a first storage unit wherein the projected end of life value will occur before the corresponding warranty end period and a second storage unit wherein the projected end of life value will not occur before its corresponding warranty end period;

identify high activity data on the first storage unit wherein activity corresponds to an erasure count associated with the data; and

migrate the identified high activity data from the first storage unit to the second storage unit.

12. The system of claim 11 wherein the storage units are flash storage drives.

13. The system of claim 11 wherein the wear indicator is associated with an erasure count for each of the multiple storage units.

14. The system of claim 11 wherein wear indicator information is stored in a wear indicator map.

15. The system of claim 11 wherein high activity data is identified based on a temperature value of the data.

16. The system of claim 11 wherein the data is a slice of data.

17. The system of claim 11 wherein the first storage unit is a drive having the highest wear indicator and the second storage unit is a drive having the lowest wear indicator.

18. The system of claim 11 wherein the processor is further configured to:

receive a threshold value;

determine a differential metric associated with the wear indicators of the first storage unit and second storage unit; and

in response to the differential metric exceeding the threshold value, migrate the identified high activity data from the first storage unit to the second storage unit and low activity data from the second storage unit to the first storage unit.

19. The system of claim 18 wherein the threshold is a dynamic value proportional to remaining expected life of a storage unit.

20. The system of claim 11, wherein the processor is further configured to:

determine a tier end of life value, wherein the value is based on the expected remaining life of substantially all the storage units in the tier; and

in response to the tier end of life value exceeding a predetermined value, performing at least one of the following;

migrate the identified high activity data from the first storage unit to a storage unit associated with a different tier, notify a user, divert future I/O activity to another tier, or reduce subsequent write performance.