Data storage system employing a hot spare to store and service accesses to data having lower associated wear

• US 10,459,808 B2
• Filed: 06/26/2017
• Issued: 10/29/2019
• Est. Priority Date: 12/30/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Walls, Andrew D.
• Primary Examiner(s): Contino, Paul
• Application Number:
  US15/633,020
• Publication Number:
  US 20170315884A1
• Time in Patent Office: 855 Days
• CPC Class Codes: G06F 11/1662 the resynchronized component or unit being a persistent storage device re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008
• CPC Class Codes: G06F 11/2017 where memory access, memory control or I/O control functionality is redundant redundant communication control functionality G06F11/2005; redundant storage control functionality G06F11/2089
• CPC Class Codes: G06F 11/2056 by mirroring
• CPC Class Codes: G06F 11/2064 while ensuring consistency
• 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 11/3034 where the computing system component is a storage system, e.g. DASD based or network based digital input from or digital output to record carriers G06F3/06; digital recording or reproducing G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 2201/88 Monitoring involving counting

Abstract

A controller monitors access frequencies of address ranges mapped to a data storage array. Based on the monitoring, the controller identifies frequently accessed ones of the address ranges that have lower associated wear, for example, those that are read more often than written. In response to the identifying, the controller initiates copying of a dataset associated with the identified address ranges from the data storage array to a spare storage device while refraining from copying other data from the data storage array onto the spare storage device. The controller directs read input/output operations (IOPs) targeting the identified address ranges to be serviced by access to the spare storage device. In response to a failure of a failed storage device among the plurality of primary storage devices, the controller rebuilds contents of the failed storage device on the spare storage device in place of the dataset associated with the identified address ranges.

Claims

1. A method in a data storage system including a controller, a spare storage device, and a plurality of primary storage devices, the method comprising:

storing a data storage array distributed across the plurality of primary storage devices, wherein each of the plurality of primary storage devices and the spare storage device contains a plurality of blocks of physical storage;

the controller identifying frequently accessed address ranges mapped to the data storage array that are read more often than written;

in response to the identifying, the controller initiating copying of a dataset associated with the identified address ranges from the data storage array onto the spare storage device while refraining from copying other data from the data storage array onto the spare storage device;

prior to a failure of a failed storage device among the plurality of primary storage devices, the controller directing read input/output operations (IOPs) targeting the dataset to be serviced by access to the spare storage device; and

based on the failure of a failed storage device, rebuilding contents of the failed storage device on the spare storage device in place of the dataset associated with the identified address ranges, wherein the rebuilding includes;

initiating an invalidate and erasure process to invalidate all entries no longer to be used and erase blocks no longer valid from the spare storage device; and

during the erasure process, the controller directing servicing of an IOP targeting data in the dataset by reference to the spare storage device.

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

the controller ending copying of the data associated with the identified address ranges prior to the spare storage device becoming full based on at least a response time of an TOP serviced by accessing the spare storage device.

3. The method of claim 2, wherein the ending copying further comprises the controller ending copying of the data associated with the identified address ranges prior to the spare storage device becoming full based on a number of pending IOPs to be serviced by accessing the spare storage device.

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

based on monitoring of access frequencies of address ranges mapped to the data storage array, the controller repeatedly updating the identified address ranges and the dataset on the spare storage device.

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

the controller resizing the dataset based on at least one of a set including a number of pending IOPs to be serviced by the spare storage device and a response time of an IOP serviced by accessing the spare storage device.

6. The method of claim 1, wherein:

the method further comprises the controller determining whether to service read IOPs requesting data within the dataset by reference to the spare storage device based on a read IOP policy;

wherein the controller performs the directing for those read IOPs for which the read IOP policy indicates are to be serviced by reference to the spare storage device.

7. The method of claim 6, and further comprising:

in response to a read IOP targeting a particular data granule within the dataset, the controller initiating concurrent retrieval of the particular data granule from both the data storage array and the spare storage device and cancelling retrieval of the particular data granule from one of the data storage array and the spare storage device based on the read IOP policy.