Wear leveling of solid state disks distributed in a plurality of redundant array of independent disk ranks

• US 8,639,877 B2
• Filed: 06/30/2009
• Issued: 01/28/2014
• Est. Priority Date: 06/30/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Benhase, Michael Thomas, Walls, Andrew Dale
• Primary Examiner(s): Bradley, Matthew
• Assistant Examiner(s): GOLDSCHMIDT, CRAIG S
• Application Number:
  US12/495,244
• Publication Number:
  US 20100332749A1
• Time in Patent Office: 1,673 Days
• Field of Search: 711/114
• US Class Current: 711/114
• CPC Class Codes: G06F 11/108 Parity data distribution in semiconductor storages, e.g. in SSD
• CPC Class Codes: G06F 11/1096 Parity calculation or recalculation after configuration or reconfiguration of the system
• CPC Class Codes: G06F 12/0246 in block erasable memory, e.g. flash memory
• CPC Class Codes: G06F 2212/7208 Multiple device management, e.g. distributing data over multiple flash devices
• CPC Class Codes: G06F 2212/7211 Wear leveling

Abstract

A computational device allocates a plurality of solid state disks to a plurality of redundant array of independent disk (RAID) ranks, wherein a different solid state disk is absent in each RAID rank of the plurality of RAID ranks. The computational device determines at least one selected solid state disk from the plurality of solid state disks, wherein the at least one selected solid state disk is estimated to have undergone a greater amount of wear in comparison to other solid state disks in the plurality of solid state disks. Relatively more data and parity information is written to those RAID ranks in which the at least one selected solid state disk is absent in comparison to those RAID ranks in which the at least one selected solid state disk is present.

Claims

1. A method, comprising:

allocating, by a computational device, a plurality of solid state disks to a plurality of redundant array of independent disk (RAID) ranks, wherein a different solid state disk is absent in each RAID rank of the plurality of RAID ranks, and wherein the plurality of RAID ranks are fewer in number than the plurality of solid state disks;

maintaining a first indicator corresponding to each RAID rank, wherein the first indicator indicates the amount of data and parity to be written to a corresponding RAID rank, and maintaining a second indicator corresponding to each solid state disk, wherein the second indicator indicates an amount of wear undergone by a corresponding solid state disk;

determining a first solid state disk from the plurality of solid state disks, wherein the first solid state disk is estimated to have undergone a greater amount of wear in comparison to other solid state disks in the plurality of solid state disks;

determining a second solid state disk from the plurality of solid state disks, wherein the second solid state disk is estimated to have a lesser amount of life left in comparison to other solid state disks in the plurality of solid state disks; and

writing relatively more data and parity information to those RAID ranks in which the second selected solid state disk is absent in comparison to those RAID ranks in which the second solid state disk is present.

2. The method of claim 1, wherein:

the allocated solid state disks in each RAID rank are fewer in number than the plurality of solid state disks; and

each solid state disk of the plurality of solid state disks is shared by more than one RAID rank.

3. The method of claim 2, further comprising:

performing distributed sparing by preferentially allocating spare space on those solid state disks that are estimated to have undergone a greater amount of wear in comparison to other solid state disks in the plurality of solid state disks.

4. The method of claim 3, wherein:

in response to the plurality of solid state disks being allocated in a log structured array, adding metadata to an index of the log structured array, wherein in log structured arrays each write is performed without any overwriting of previously performed writes; and

in response to the plurality of solid state disks being allocated as home area storage systems, rotating RAID ranks based on stripe number.

5. The method of claim 3,

wherein if the first indicator for a first RAID rank indicates a first number, then a first number of stripes of data and parity information are written to the first RAID rank before stripes of additional data and parity information are written to another RAID rank, and wherein the method further comprises:

maintaining a data structure that indicates an adjustment to be made to a value stored in the first indicator based on differences in second indicator values of the plurality of solid state disks.

6. The method of claim 1, wherein the computational device is a RAID controller, and wherein the plurality of solid state disks are operatively coupled to the RAID controller.

7. A controller for configuring a plurality of solid state disks, the controller comprising:

a memory; and

a processor coupled to the memory, wherein the processor performs operations, the operations comprising;

allocating the plurality of solid state disks to a plurality of redundant array of independent disk (RAID) ranks, wherein a different solid state disk is absent in each RAID rank of the plurality of RAID ranks, and wherein the plurality of RAID ranks are fewer in number than the plurality of solid state disks;

maintaining a first indicator corresponding to each RAID rank, wherein the first indicator indicates the amount of data and parity to be written to a corresponding RAID rank, and maintaining a second indicator corresponding to each solid state disk, wherein the second indicator indicates an amount of wear undergone by a corresponding solid state disk;

determining a first solid state disk from the plurality of solid state disks, wherein the first solid state disk is estimated to have undergone a greater amount of wear in comparison to other solid state disks in the plurality of solid state disks; and

determining, a second solid state disk from the plurality of solid state disks, wherein the second solid state disk is estimated to have a lesser amount of life left in comparison to other solid state disks in the plurality of solid state disks; and

writing relatively more data and parity information to those RAID ranks in which the second selected solid state disk is absent in comparison to those RAID ranks in which the second solid state disk is present.

8. The controller of claim 7, wherein:

the allocated solid state disks in each RAID rank are fewer in number than the plurality of solid state disks; and

each solid state disk of the plurality of solid state disks is shared by more than one RAID rank.

9. The controller of claim 8, the operations further comprising:

performing distributed sparing by preferentially allocating spare space on those solid state disks that are estimated to have undergone a greater amount of wear in comparison to other solid state disks in the plurality of solid state disks.

10. The controller of claim 9, wherein:

in response to the plurality of solid state disks being allocated in a log structured array, adding metadata to an index of the log structured array, wherein in log structured arrays each write is performed without any overwriting of previously performed writes; and

in response to the plurality of solid state disks being allocated as home area storage systems, rotating RAID ranks based on stripe number.

11. The controller of claim 9, wherein if the first indicator for a first RAID rank indicates a first number, then a first number of stripes of data and parity information are written to the first RAID rank before stripes of additional data and parity information are written to another RAID rank, and wherein the operations further comprise:

maintaining a data structure that indicates an adjustment to be made to a value stored in

the first indicator based on differences in second indicator values of the plurality of solid state disks.

12. The controller of claim 7, wherein the controller is a RAID controller, and wherein the plurality of solid state disks are operatively coupled to the RAID controller.

13. A computer program product for wear leveling of a plurality of solid state disks, the computer program product comprising:

a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code configured to;

allocate the plurality of solid state disks to a plurality of redundant array of independent disk (RAID) ranks, wherein a different solid state disk is absent in each RAID rank of the plurality of RAID ranks, and wherein the plurality of RAID ranks are fewer in number than the plurality of solid state disks;

maintain a first indicator corresponding to each RAID rank, wherein the first indicator indicates the amount of data and parity to be written to a corresponding RAID rank, and maintaining a second indicator corresponding to each solid state disk, wherein the second indicator indicates an amount of wear undergone by a corresponding solid state disk;

determine a first solid state disk from the plurality of solid state disks, wherein the first solid state disk is estimated to have undergone a greater amount of wear in comparison to other solid state disks in the plurality of solid state disks; and

determine, a second solid state disk from the plurality of solid state disks, wherein the second solid state disk is estimated to have a lesser amount of life left in comparison to other solid state disks in the plurality of solid state disks; and

write relatively more data and parity information to those RAID ranks in which the second selected solid state disk is absent in comparison to those RAID ranks in which the second solid state disk is present.

14. The computer program product of claim 13, wherein:

the allocated solid state disks in each RAID rank are fewer in number than the plurality of solid state disks; and

each solid state disk of the plurality of solid state disks is shared by more than one RAID rank.

15. The computer program product of claim 14, wherein the computer readable program code is further configured to:

perform distributed sparing by preferentially allocating spare space on those solid state disks that are estimated to have undergone a greater amount of wear in comparison to other solid state disks in the plurality of solid state disks.

16. The computer program product of claim 15, wherein:

in response to the plurality of solid state disks being allocated in a log structured array, adding metadata to an index of the log structured array, wherein in log structured arrays each write is performed without any overwriting of previously performed writes; and

in response to the plurality of solid state disks being allocated as home area storage systems, rotating RAID ranks based on stripe number.

17. The computer program product of claim 15, wherein if the first indicator for a first RAID rank indicates a first number, then a first number of stripes of data and parity information are written to the first RAID rank before stripes of additional data and parity information are written to another RAID rank, and wherein the computer readable program code is further configured to:

maintain a data structure that indicates an adjustment to be made to a value stored in the first indicator based on differences in second indicator values of the plurality of solid state disks.