IMPLEMENTING ENHANCED DATA CACHING AND TAKEOVER OF NON-OWNED STORAGE DEVICES IN DUAL STORAGE DEVICE CONTROLLER CONFIGURATION WITH DATA IN WRITE CACHE

• US 20150052385A1
• Filed: 08/15/2013
• Published: 02/19/2015
• Est. Priority Date: 08/15/2013
• Status: Active Grant

• Current Assignee: GlobalFoundries, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Galbraith, Robert E., Tee, Stephen M., Weckwerth, Rick A., Mairet, Dennis C., Maitland, William J. Jr.
• Granted Patent: US 9,239,797 B2
• Time in Patent Office: Days
• US Class Current: 714/6.3
• CPC Class Codes: G06F 11/2025 using centralised failover control functionality
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2056 by mirroring
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units
• CPC Class Codes: G06F 11/2097 maintaining the standby controller/processing unit updated initialisation or re-synchronisation thereof G06F11/1658 and subgroups
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 12/0888 using selective caching, e.g. bypass
• CPC Class Codes: G06F 12/0891 using clearing, invalidating or resetting means
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/286 Mirrored cache memory
• CPC Class Codes: G06F 2212/312 In storage controller

Abstract

A method, system and computer program product are provided for implementing enhanced data caching and takeover of non-owned storage devices in a computer system. Each of a first controller and a second controller has a cache memory. During normal run-time, each storage device controller validates cached write data after it is written to its cache memory by reading the write data from its cache memory. If any error is detected on the read, then unit check failed storage device controller, which results in a reset of the failed storage device controller. When a storage device controller detects its dual partner controller fails, the surviving storage device controller queues host read/write operations for its storage devices already owned, and tests a cache mirrored copy from its cache memory of the failed first storage device controller before takeover of the failed controller'"'"'s storage devices.

Claims

1. A method for implementing enhanced data caching and takeover of non-owned storage devices in a computer system comprising:

providing each of a first storage device controller and a second storage device controller with a cache memory;

connecting a plurality of storage devices to the first storage device controller and second storage device controller, and assigning respective ones of the storage devices assigned to the first storage device controller, and respective other ones of the storage devices assigned to the second storage device controller;

during normal run-time, each storage device controller performing the steps of;

validating cached write data after writing data to its cache memory by reading the write data from its cache memory;

responsive to detecting any error on the read, unit check failed storage device controller to reset of the failed storage device controller;

responsive to a storage device controller fails, a surviving storage device controller performing the steps of;

queuing host read/write operations for storage devices assigned to the surviving storage device controller; and

testing from its cache memory a cache mirrored copy of the failed storage device controller'"'"'s cache before taking ownership of all storage devices.

2. The method as recited in claim 1 includes the surviving storage device controller performing the steps responsive to no errors being detected in cache mirrored copy, updating metadata on all storage devices indicating the cache memory of the failed storage device controller being out of synchronization.

3. The method as recited in claim 2 includes resume servicing of host read/write operations for storage devices assigned to the surviving storage device controller.

4. The method as recited in claim 2 includes taking ownership of all storage devices.

5. The method as recited in claim 4 includes begin servicing of host read/write operations for storage devices taken over from the failed storage device controller.

6. The method as recited in claim 5 includes flushing of cache to storage devices.

7. The method as recited in claim 6 includes bypassing cache memory for new write ops until the surviving storage device controller is re-mirrored with a partner controller.

8. The method as recited in claim 1 wherein during normal run-time, each storage device controller performing the steps of mirroring cache data writes to the cache memory of the other storage device controller.

9. The method as recited in claim 8 wherein validating of cached write data includes reading the write data from cache memory as part of the mirrors operation into the cache memory on a partner storage device controller.

10. The method as recited in claim 1 includes the surviving storage device controller responsive to errors being detected in cache mirrored copy performing the steps of resetting both the surviving storage device controller and the failed storage device controller and performing self power on reset.

11. The method as recited in claim 1 wherein error detecting both during normal run-time reads and for test reads responsive to a storage device controller fails include testing for one or more of Uncorrectable Error Correction Code (ECC) errors;

decompression errors, Cyclical Redundancy Check (CRC) errors and T10 differential errors, and any hardware fault of the storage device controller.

12. A system for implementing enhanced data caching and takeover of non-owned storage devices in a computer system comprising:

a first storage device controller having a cache memory;

a second storage device controller having a cache memory;

a plurality of storage devices connected to the first storage device controller and second storage device controller,

respective ones of the storage devices assigned to the first storage device controller, and respective other ones of the storage devices assigned to the second storage device controller;

during normal run-time, each storage device controller performing the steps of;

validating cached write data after writing data to its cache memory by reading the write data from its cache memory;

responsive to detecting any error on the cached write data read, unit check failed storage device controller to reset of the failed storage device controller;

responsive to a storage device controller fails, a surviving storage device controller performing the steps of;

queuing host read/write operations for storage devices assigned to the surviving storage device controller; and

testing from its cache memory a cache mirrored copy of the failed storage device controller'"'"'s cache before taking ownership of all storage devices.

13. The system as recited in claim 12 wherein error detecting both during normal run-time reads and for test reads responsive to a storage device controller fails include testing for one or more of uncorrectable Error Correction Code (ECC) errors;

decompression errors, Cyclical Redundancy Check (CRC) errors and T10 differential errors, and any hardware fault of the storage device controller.

14. The system as recited in claim 12 includes the surviving storage device controller performing the steps responsive to no errors being detected in cache mirrored copy, updating metadata on all storage devices indicating the cache memory of the failed storage device controller being out of synchronization.

15. The system as recited in claim 14 includes resume servicing of host read/write operations for storage devices assigned to the surviving storage device controller.

16. The system as recited in claim 14 includes taking ownership of all storage devices.

17. The system as recited in claim 16 includes begin servicing of host read/write operations for storage devices taken over from the failed storage device controller.

18. The system as recited in claim 17 includes flushing of cache to storage devices.

19. The system as recited in claim 18 includes bypassing cache memory for new write ops until the surviving storage device controller is re-mirrored with a partner controller.

20. The system as recited in claim 12 includes the surviving storage device controller responsive to errors being detected in cache mirrored copy performing the steps of resetting both the surviving storage device controller and the failed storage device controller and performing self power on reset.