System and method for efficient failover/failback techniques for fault-tolerant data storage system

• US 20020133735A1
• Filed: 01/16/2001
• Published: 09/19/2002
• Est. Priority Date: 01/16/2001
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: McKean, Brian D., Skazinski, Joseph G., Otterness, Noel S.
• Granted Patent: US 6,681,339 B2
• Time in Patent Office: Days
• US Class Current: 714/5
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units

Abstract

Structure and method for efficient failover and failback techniques in a data storage system utilizing a dual-active controller configuration for minimizing a delay in responding to I/O requests from a host system following a controller failure is described. A stripe lock data structure is defined to maintain reservation status or stripe locks of cache lines within data extents that are part of a logical unit or storage volume. When a controller fails, dirty cache line data of a failed controller is taken over by a survivor controller. The stripe lock data structure is used to process I/O requests from a host system, by the failed controller. The data storage system functions in a single-active configuration until the dirty cache line data is flushed to one or more storage volumes, by the survivor controller. The inventive structure and method provide utilize a storage volume reservation system. The stripe lock data structure is defined in memory within each of the two or more caching controllers. The stripe lock data structure is used to provide consistent information within each of the two or more caching controllers, and the stripe lock data structure is used by a failed controller to process I/O requests from a host system until dirty cache line data is flushed to one or more storage volumes by a survivor controller. Provides a method and structure which minimizes a delay required to begin processing of host I/O request following a controller failure.

Claims

1. A method for efficient failover/failback in a data storage system, the data storage system managed in a dual-active controller configuration, the method comprising:

defining a stripe lock data structure to maintain reservation status or stripe locks of cache lines within data extents that are part of a logical unit or storage volume;

when a controller fails, taking over dirty cache line data of a failed controller by a survivor controller; and

using the stripe lock data structure to process I/O requests from a host system, by the failed controller, until the dirty cache line data is flushed to one or more storage volumes, by the survivor controller.

2. The method of claim 1, wherein the taking over the dirty cache line data step further comprises:

moving the dirty cache line data into a read/write area of a survivor controller cache memory;

re-booting the failed controller; and

once the failed controller has re-booted, passing a host ID back to the failed controller, thereby enabling the failed controller to being accepting of I/O requests from the host system.

3. The method of claim 1, wherein the using the stripe lock data structure step further comprises:

receiving a host I/O request, by the failed controller, from the host system;

requesting a stripe lock, by the failed controller, from the survivor controller for data extents encompassed by the host I/O request;

granting the stripe lock, by the survivor controller, once cache line data within the survivor controller cache memory and covered by the stripe lock is flushed to the one or more storage volumes; and

processing the host I/O request by the failed controller.

4. The method of claim 1, further including:

re-segmenting the survivor controller cache memory to include a read/write area and a mirror area, thereby allowing the survivor controller and the failed controller to manage the data storage system in a dual active configuration; and

mirroring, by a controller, data to an alternate controller in response to host I/O requests, such that the alternate controller copies the data into an alternate controller cache memory, thereby providing a copy of dirty cache line data for each controller in the data storage system in preparation for a controller failure.

5. A computer program product for efficient failover/failback in a data storage system, the data storage system managed in dual active controller configuration, the computer program product including a computer readable medium and a computer mechanism stored thereon, the computer mechanism comprising:

defining a stripe lock data structure to maintain reservation status or stripe locks of cache lines within data extents that are part of a logical unit or storage volume;

when a controller fails, taking over dirty cache line data of a failed controller by a survivor controller; and

using the stripe lock data structure to process I/O requests from a host system, by the failed controller, until the dirty cache line data is flushed to one or more storage volumes, by the survivor controller.

6. The computer program product of claim 5, wherein the instruction for the taking over the dirty cache line data further comprises instructions for:

moving the dirty cache line data into a read/write area of a survivor controller cache memory;

re-booting the failed controller; and

once the failed controller has re-booted, passing a host ID back to the failed controller, thereby enabling the failed controller to being accepting of I/O requests from the host system.

7. The computer program product of claim 5, wherein the instruction for the using the stripe lock data structure further comprises instructions for:

receiving a host I/O request, by the failed controller, from the host system;

requesting a stripe lock, by the failed controller, from the survivor controller for data extents encompassed by the host I/O request;

granting the stripe lock, by the survivor controller, once cache line data within the survivor controller cache memory and covered by the stripe lock is flushed to the one or more storage volumes; and

processing the host I/O request by the failed controller.

8. The computer program product of claim 5, further comprising instructions for:

re-segmenting the survivor controller cache memory to include a read/write area and a mirror area, thereby allowing the survivor controller and the failed controller to manage the data storage system in a dual active configuration; and

mirroring, by a controller, data to an alternate controller in response to host I/O requests, such that the alternate controller copies the data into an alternate controller cache memory, thereby providing a copy of dirty cache line data for each controller in the data storage system in preparation for a controller failure.

9. In a computing environment that allows data access through two or more caching controllers, a storage volume reservation system comprising:

a stripe lock data structure defined in memory within each of said two or more caching controllers;

said stripe lock data structure providing consistent information within each of the two or more caching controllers; and

said stripe lock data structure being used by a failed controller to process I/O requests from a host system until dirty cache line data is flushed to one or more storage volumes by a survivor controller.

10. A caching storage controller device, comprising:

a memory defining a stripe lock data structure and storing stripe locks of cache lines within data extents that are part of a logical unit or storage volume shared by a plurality of caching storage controller devices;

the caching storage controller device configured to use the stripe lock data structure to process I/O requests from a host system until dirty cache line data is flushed to one or more storage volumes by a survivor controller following a controller failure.

11. The apparatus of claim 10, wherein the caching storage controller device controls a plurality of storage devices configured as a redundant array of independent disks (RAID).

14. The method in claim 13, wherein said storage unit comprises a logical unit.

15. The method in claim 13, wherein said storage unit comprises a storage volume.

12. A method for using a caching storage controller device, the method comprising:

defining a stripe lock data structure in a memory of the caching storage controller to maintain reservation status or stripe locks of cache lines within data extents that are part of a logical unit or storage volume shared by a plurality of caching storage controller devices;

when a controller fails, taking over dirty cache line data of a failed controller by a survivor controller; and

using the stripe lock data structure to process I/O requests from a host system, by the failed controller, until the dirty cache line data is flushed to one or more storage volumes, by the survivor controller.

13. In a computer system having a host computer and a data storage system having storage units coupled to the host through first and second multi-active data storage system controllers, a method for redirecting input/output requests from an intended first controller to a survivor second controller when said intended first controller is unavailable, the method comprising:

defining a data structure to store and maintain status of cache lines within data extents that are part of a storage unit;

when said intended first controller fails, taking over dirty cache line data of said failed intended first controller by said survivor second controller; and

processing input/output requests from said host system by said failed first controller using said stripe lock data structure to process input/output requests from said host system, by the failed controller, until the dirty cache line data is flushed to one or more storage volumes, by the survivor controller.