Managing wear on independent storage devices

• US 8,499,116 B2
• Filed: 06/11/2010
• Issued: 07/30/2013
• Est. Priority Date: 06/11/2010
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Roberts, David Andrew, Chang, Jichuan, Ranganathan, Parthasarathy
• Primary Examiner(s): PEUGH, BRIAN R
• Application Number:
  US12/813,772
• Publication Number:
  US 20110307679A1
• Time in Patent Office: 1,145 Days
• Field of Search: None
• US Class Current: 711/103
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G11C 16/349 Arrangements for evaluating degradation, retention or wearout, e.g. by counting erase cycles
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

In a method of managing wear on a plurality of independent storage devices having respective sets of memory cells, access characteristics of the memory cells in the plurality of independent storage devices are monitored. In addition, an instruction to access data on at least one of the memory cells is received and an independent storage device of the plurality of independent storage devices is selected to access data on at least one of the memory cells of the selected independent storage device based upon one or more predetermined selection policies and the monitored access characteristics of the memory cells in the plurality of independent storage devices. Moreover, the selected independent storage device is assigned to access data on at least one of the memory cells of the selected independent storage device according to the received instruction.

Claims

1. A method of managing wear on a plurality of independent storage devices having respective sets of memory cells, said method comprising:

monitoring access characteristics of the memory cells in the plurality of independent storage devices, wherein monitoring access characteristics includes calculating an average number of accesses per independent storage device for each of the plurality of independent storage devices, and a read/write access ratio of the memory cells;

receiving an instruction to access data on at least one of the memory cells;

selecting an independent storage device, of the plurality of independent storage devices, to access data on at least one of the memory cells of the selected independent storage device based upon one or more predetermined selection policies and the monitored access characteristics of the memory cells in the plurality of independent storage devices; and

assigning the selected independent storage device to access data on at least one of the memory cells of the selected independent storage device according to the received instruction.

2. The method according to claim 1, wherein the one or more predetermined selection policies comprise a selection policy configured to level wear of the memory cells relatively evenly across the plurality of independent storage devices.

3. The method according to claim 2, wherein the one or more predetermined selection policies comprise a selection policy configured to randomly select the independent storage device from the plurality of independent storage devices to level wear relatively evenly across the plurality of independent storage devices.

4. The method according to claim 1, wherein the one or more predetermined selection policies comprise a selection policy to manage lifetimes of the independent storage devices associated with at least one of performance, power efficiency, and reliability of the independent storage devices.

5. The method according to claim 1, wherein the one or more predetermined selection policies comprise a selection policy configured to skew selection of the independent storage device to one or more predetermined independent storage devices, such that the memory cells of the selected independent storage device is accessed a greater number of times as compared with the memory cells of other ones of the plurality of independent storage devices.

6. The method according to claim 1, wherein the plurality of independent storage devices comprise at least two heterogeneous storage devices having different susceptibilities to failure and wherein selecting the independent storage device in accordance with one or more predetermined selection policies further comprises factoring the susceptibilities to failure of the heterogeneous storage devices in selecting the independent storage device.

7. The method according to claim 1, further comprising:

determining intended applications of the plurality of independent storage devices; and

wherein selecting the independent storage device in accordance with one or more predetermined selection policies further comprises factoring the intended applications of the plurality of independent storage devices in selecting the independent storage device.

8. The method according to claim 1, wherein multiple ones of the plurality of independent storage devices are configured to store the same data, and wherein selecting the independent storage device in accordance with one or more predetermined selection policies further comprises factoring replication of the data among the multiple ones of the plurality of independent storage devices in selecting the independent storage device.

9. The method according to claim 1, wherein monitoring the access characteristics of the memory cells further comprises monitoring a number of times each of the memory cells is at least one of written to, read from, erased, and a count of the number of memory cells that have failed per storage device.

10. The method according to claim 1, further comprising:

receiving data pertaining one or more access characteristics of storage devices located in a separate cluster; and

wherein selecting the independent storage device further comprises selecting device independent storage device based upon the received data along with the monitored access characteristics and the one or more predetermined selection policies.

11. An apparatus for managing wear on a plurality of independent storage devices having respective sets of memory cells, said apparatus comprising:

a memory on which is stored machine readable instructions to;

monitor access characteristics of the memory cells in the plurality of independent storage devices and to calculate, using the monitored access characteristics, an average number of accesses per independent storage device for each of the plurality of independent storage devices, and a read/write access ratio of the memory cells;

receive an instruction to access data on at least one of the memory cells;

select an independent storage device to be accessed based upon one or more predetermined selection policies and the monitored access characteristics of the memory cells; and

assign the selected independent storage device to access data on at least one of the memory cells of the selected independent storage device according to the received instruction; and

a processor to implement machine readable instructions.

12. The apparatus according to claim 11, wherein the apparatus comprises one of a network switch and a router.

13. The apparatus according to claim 11, wherein the one or more predetermined selection policies comprise a selection policy to level wear of the memory cells relatively evenly across the plurality of independent storage devices.

14. The apparatus according to claim 11, wherein the one or more predetermined selection policies comprise a selection policy to manage lifetimes of the independent storage devices associated with at least one of performance, power efficiency, and reliability.

15. The apparatus according to claim 11, wherein the one or more predetermined selection policies comprise a selection policy to skew selection of the independent storage device to one or more predetermined independent storage devices, such that the memory cells of the selected independent storage device is at least one of read and manipulated a greater number of times as compared with the memory cells of other ones of the plurality of independent storage devices.

16. The apparatus according to claim 11, wherein the plurality of independent storage devices comprise at least two heterogeneous storage devices having different susceptibilities to failure and wherein the machine readable instructions are to factor the susceptibilities to failure of the heterogeneous storage devices in selecting the independent storage device.

17. The apparatus according to claim 11, wherein the machine readable instructions are to determine intended applications of the plurality of independent storage devices and to factor the intended applications of the plurality of independent storage devices in selecting the independent storage device.

18. The apparatus according to claim 11, wherein multiple ones of the plurality of independent storage devices are to store the same data, and wherein the machine readable instructions are further to factor replication of the data among the multiple ones of the plurality of independent storage devices in selecting the independent storage device.

19. The apparatus according to claim 11, wherein the apparatus is part of a first cluster and wherein the machine readable instructions are to receive data pertaining one or more access characteristics of storage devices located in at least one other cluster separate from the first cluster and wherein the machine readable instructions are to select the independent storage device based upon the received data along with the monitored access characteristics and the one or more predetermined selection policies.

20. A non-transitory computer readable storage medium on which is embedded one or more computer programs that when executed by a processor, implement a method of managing wear on a plurality of independent storage devices having respective sets of memory cells, said one or more computer programs comprising computer code to:

monitor access characteristics of the memory cells in a first cluster comprising a plurality of independent storage devices;

receive data pertaining to one or more access characteristics of independent storage devices located in at least one other cluster separate from the first cluster;

receive an instruction to access data on at least one memory cell;

select from a group comprising the first cluster and the at least one other cluster, an independent storage device to access data on at least one of the memory cells of the selected independent storage device based upon one or more predetermined selection policies, the data received from the at least one other cluster, and the monitored access characteristics of the memory cells in the first cluster of independent storage devices; and

assign the selected independent storage device to access data on at least one of the memory cells of the selected independent storage device according to the received instruction.