Data storage system employing a hot spare to proactively store array data in absence of a failure or pre-failure event

• US 10,241,877 B2
• Filed: 12/12/2016
• Issued: 03/26/2019
• Est. Priority Date: 12/12/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Camp, Charles J., Shuhatovich, Lev M.
• Primary Examiner(s): Patel, Jigar P
• Application Number:
  US15/376,248
• Publication Number:
  US 20180165169A1
• Time in Patent Office: 834 Days
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/1469 Backup restoration techniques
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 11/2071 using a plurality of controllers
• CPC Class Codes: G06F 11/2087 with a common controller
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 11/3041 where the computing system component is an input/output interface interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units G06F13/00
• CPC Class Codes: G06F 2201/88 Monitoring involving counting
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays

Abstract

A data storage system includes a controller, a hot spare storage device and a plurality of primary storage devices. The controller utilizes the hot spare storage device to mirror only a subset of each stripe of logical pages written across the data storage array, where the subset includes a logical page determined by a write input/output operation (IOP) policy. In response to receipt of a write IOP, the controller writes a stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices and mirrors the logical page determined by the write IOP policy on the hot spare storage device. In response to a failure of a storage device among the plurality of primary storage devices, contents of the failed storage device not already mirrored on the hot spare storage device are rebuilt on the hot spare storage device.

Claims

1. A method in a data storage system including a controller, a hot spare storage device and a plurality of primary storage devices across which a data storage array is striped, the method comprising:

the controller controlling storage of data on the hot spare storage device such that the hot spare storage device mirrors only a subset of each data stripe written across the primary storage devices, wherein the controller is configured by a write input/output operation (IOP) policy to dynamically determine the subset, and wherein the write IOP policy has a first setting that configures the controller to select a coldest subset of each data stripe having the lowest relative write frequency;

in response to receipt of a write IOP of a host while the controller is configured by the first setting of the write IOP policy, the controller;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the first setting of the IOP policy, the coldest subset of the particular data stripe; and

mirroring the coldest subset from the particular data stripe onto the hot spare storage device; and

in response to a failure of a failed storage device among the plurality of primary storage devices, rebuilding, on the hot spare storage device, contents of the failed storage device not already mirrored on the hot spare storage device.

2. The method of claim 1, wherein:

the plurality of primary storage devices includes a particular primary storage device;

the write IOP policy has a second setting in which the subset determined by the write IOP policy to be mirrored on the hot spare storage device is that written to the particular primary storage device; and

in response to receipt of a write IOP of a host while the controller is configured by the second setting of the write IOP policy, the controller;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the write IOP policy, the subset of the particular data stripe written to the particular primary storage device; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

3. The method of claim 1, wherein:

the write IOP policy has a second setting in which the subset determined by the write IOP policy to be mirrored on the hot spare storage device is selected to maintain approximately a same amount of data from each of the plurality of primary storage devices on the hot spare storage device; and

in response to receipt of a write IOP of a host while the controller is configured by the second setting of the write IOP policy, the controller;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the write IOP policy, the subset of the particular data stripe written to be mirrored on the hot spare storage drive; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

4. The method of claim 1, wherein:

the write IOP policy has a second setting in which the subset determined by the controller is that stored on a least healthy primary storage device among the plurality of primary storage devices; and

in response to receipt of a write IOP of a host while the controller is configured by the second setting of the write IOP policy, the controller;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the write IOP policy, the subset of the particular data stripe written to the least healthy primary storage device; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

5. The method of claim 1, wherein the rebuilding further comprises:

retaining on the hot spare storage device logical pages mirrored from the failed storage device; and

removing from the hot spare storage device any logical pages mirrored from any primary storage device other than the failed storage device.

6. The method of claim 1, wherein the controlling step includes the controller controlling storage of data as configured by the first setting of the write IOP policy in absence of any indication of a failure or pre-failure event regarding any of the plurality of primary storage devices.

7. The method of claim 3, and further comprising the controller switching between the first setting and the second setting of the write IOP policy based on at least one of a set including a health of the hot spare storage device and a workload metric.

8. The method of claim 4, and further comprising the controller switching between the first setting and the second setting of the write IOP policy based on at least one of a set including a health of the hot spare storage device and a workload metric.

9. The method of claim 1, and further comprising:

the controller determining the coldest subset based on a weighted combination of write accesses in both first and second monitoring intervals that gives greater weight to accesses in the first monitoring interval.

10. A data storage system, comprising:

a controller configured to be coupled to a hot spare storage device and to a plurality of primary storage devices across which a data storage array is striped, wherein the controller is configured to perform;

the controller controlling data storage on the hot spare storage device such that the hot spare storage device mirrors only a subset of each stripe of logical pages written across the data storage array, wherein the controller is configured by a write input/output operation (IOP) policy to dynamically determine the subset, and wherein the write IOP policy has a first setting that configures the controller to select a coldest subset of each data stripe having the lowest relative write frequency;

in response to receipt of a write IOP of a host while the controller is configured by the first setting of the write IOP policy, the controller;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the first setting of the IOP policy, the coldest subset of the particular data stripe; and

mirroring the coldest subset logical page from the particular data stripe determined by the write IOP policy on the hot spare storage device; and

in response to a failure of a failed storage device among the plurality of primary storage devices, rebuilding, on the hot spare storage device, contents of the failed storage device not already mirrored on the hot spare storage device.

11. The data storage system of claim 10, wherein:

the plurality of primary storage devices includes a particular primary storage device;

the write IOP policy has a second setting in which the subset determined by the write IOP policy to be mirrored on the hot spare storage device is that written to the particular primary storage device; and

the controller is configured by the second setting of the write IOP policy to perform;

in response to receipt of a write IOP of a host;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the write IOP policy, the subset of the particular data stripe written to the particular primary storage device; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

12. The data storage system of claim 10, wherein:

the write IOP policy has a second setting in which the subset determined by the write IOP policy to be mirrored on the hot spare storage device is selected to maintain approximately a same amount of data from each of the plurality of primary storage devices on the hot spare storage device;

the controller is configured by the second setting of the write IOP policy to perform;

in response to receipt of a write IOP of a host;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the write IOP policy, the subset of the particular data stripe; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

13. The data storage system of claim 10, wherein:

the write IOP policy has a second setting in which the subset determined by the controller is that stored on a least healthy primary storage device among the plurality of primary storage devices; and

the controller is configured by the second setting of the write IOP policy to perform;

in response to receipt of a write IOP of a host;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the IOP policy, the subset of the particular data stripe written to the least healthy primary storage device; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

14. The data storage system of claim 10, wherein the rebuilding includes:

the controller retaining on the hot spare storage device logical pages mirrored from the failed storage device; and

the controller removing from the hot spare storage device any logical pages mirrored from any primary storage device other than the failed storage device.

15. The data storage system of claim 10, and further comprising the hot spare storage device and the plurality of primary storage devices.

16. A program product, comprising:

a storage device; and

program code stored in the storage device, wherein the program code, when executed by a controller configured to be coupled to a hot spare storage device and to a plurality of primary storage devices across which a data storage array is striped, causes the controller to perform;

controlling data storage on the hot spare storage device such that the hot spare storage device mirrors only a subset of each stripe of logical pages written across the data storage array, wherein the controller is configured by a write input/output operation (IOP) policy to dynamically determine the subset, and wherein the write IOP policy has a first setting that configures the controller to select a coldest subset of each data stripe having the lowest relative write frequency;

in response to receipt of a write IOP of a host while the controller is configured by the first setting of the write IOP policy, the controller;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the first setting of the IOP policy, the coldest subset of the particular data stripe; and

mirroring the coldest subset from the particular data stripe on the hot spare storage device; and

in response to a failure of a failed storage device among the plurality of primary storage devices, rebuilding, on the hot spare storage device, contents of the failed storage device not already mirrored on the hot spare storage device.

17. The program product of claim 16, wherein:

the plurality of primary storage devices includes a particular primary storage device;

the write IOP policy has a second setting in which the subset determined by the write IOP policy to be mirrored on the hot spare storage device is that written to the particular primary storage device; and

the program code further causes the controller, when configured by the second setting of the write IOP policy, to perform;

in response to receipt of a write IOP of a host;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the write IOP policy, the subset of the particular data stripe written to the particular primary storage device; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

18. The program product of claim 16, wherein:

the write IOP policy has a second setting in which the subset determined by the write IOP policy to be mirrored on the hot spare storage device is selected to maintain approximately a same amount of data from each of the plurality of primary storage devices on the hot spare storage device;

the program code further causes the controller, when configured by the second setting of the write IOP policy, to perform;

in response to receipt of a write IOP of a host;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the write IOP policy, the subset of the particular data stripe; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

19. The program product of claim 16, wherein:

the write IOP policy has a second setting in which the subset determined by the controller is that stored on a least healthy primary storage device among the plurality of primary storage devices; and

the program code further causes the controller, when configured by the second setting of the write IOP policy, to perform;

in response to receipt of a write IOP of a host;

writing a particular data stripe including a plurality of logical data pages and a logical data protection page across the plurality of primary storage devices;

determining, in accordance with the second setting of the IOP policy, the subset of the particular data stripe written to the least healthy primary storage device; and

mirroring the determined subset from the particular data stripe onto the hot spare storage device.

20. The program product of claim 16, wherein the rebuilding includes:

the controller retaining on the hot spare storage device logical pages mirrored from the failed storage device; and

the controller removing from the hot spare storage device any logical pages mirrored from any primary storage device other than the failed storage device.