Data storage system using 3-party hand-off protocol to facilitate failure recovery

• US 20030229826A1
• Filed: 06/10/2002
• Published: 12/11/2003
• Est. Priority Date: 06/10/2002
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Sun Microsystems Incorporated (Oracle Corporation)
• Inventors: Talagala, Nisha, Lee, Whay Sing
• Granted Patent: US 7,007,196 B2
• Time in Patent Office: Days
• US Class Current: 714/42
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units

Abstract

A data storage system is disclosed in which a 3-party hand-off protocol is utilized to maintain a single coherent logical image. In particular, the functionality of the data storage system is separated into distinct processing modules. Each processing module is implemented in a distinct central processing unit (CPU). Alternatively, the first type processing module and the third type processing module can be implemented in a common CPU. Isolating the different functions of the data storage system into distinct CPUs facilitates failure recovery. A characteristic of the 3-party hand-off protocol is that, if an abnormal state occurs, a surviving module has sufficient information to proceed to recover from said abnormal state after detecting the abnormal state, without depending on a failing module, by retrying the data storage operation with another processing module or the failing module or cleaning up after the failed data storage operation, resulting in improved failure recovery.

Claims

1. A data storage system comprising:

a first type processing module for partially executing a first group of data storage operations;

a second type processing module for partially executing a second group of data storage operations; and

a third type processing module for partially executing a third group of data storage operations, wherein at least two of said first, second, and third type processing modules are required to cooperate in a hand-off manner to fully execute any one of said data storage operations, and wherein if an abnormal state arises when attempting to fully execute a particular data storage operation, a particular module of said first, second, and third type processing modules involved in executing said particular data storage operation detects said abnormal state and proceeds to recover from said abnormal state.

2. A data storage system as recited in claim 1 wherein said first group comprises a read operation and a write operation.

3. A data storage system as recited in claim 1 wherein said second group comprises a read operation, a write operation, a stage operation, and a destage operation.

4. A data storage system as recited in claim 1 wherein said third group comprises a stage operation and a destage operation.

5. A data storage system as recited in claim 1 wherein said particular module proceeds to recover from said abnormal state by retrying said particular data storage operation with another module.

6. A data storage system as recited in claim 1 wherein said particular module proceeds to recover from said abnormal state by cleaning up a pending task of said particular data storage operation.

7. A data storage system as recited in claim 1 wherein said first type processing module, said second type processing module, and said third type processing module are each implemented in a plurality of distinct central processing units.

8. A data storage system as recited in claim 1 wherein said first type processing module and said third type processing module are implemented in a common central processing unit.

9. A data storage system comprising:

a) a disk drive for storing a plurality of data;

b) a first memory for storing a plurality of cache data;

c) a second memory for storing metadata associated with stored data including said cache data and said data;

d) a first type processing module for partially executing a first group of data storage operations and for handling said cache data;

e) a second type processing module for partially executing a second group of data storage operations and for managing said metadata; and

f) a third type processing module for partially executing a third group of data storage operations and for handling said data and said cache data, wherein at least two of said first, second, and third type processing modules are required to cooperate in a hand-off manner to fully execute any one of said data storage operations, and wherein if an abnormal state arises when attempting to fully execute a particular data storage operation, a particular module of said first, second, and third type processing modules involved in executing said particular data storage operation detects said abnormal state and proceeds to recover from said abnormal state.

10. A data storage system as recited in claim 9 wherein said first group comprises a read operation and a write operation.

11. A data storage system as recited in claim 9 wherein said second group comprises a read operation, a write operation, a stage operation, and a destage operation.

12. A data storage system as recited in claim 9 wherein said third group comprises a stage operation and a destage operation.

13. A data storage system as recited in claim 9 wherein said particular module proceeds to recover from said abnormal state by retrying said particular data storage operation with another module.

14. A data storage system as recited in claim 9 wherein said particular module proceeds to recover from said abnormal state by cleaning up a pending task of said particular data storage operation.

15. A data storage system as recited in claim 9 wherein said first type processing module, said second type processing module, and said third type processing module are each implemented in a plurality of distinct central processing units.

16. A data storage system as recited in claim 9 wherein said first type processing module and said third type processing module are implemented in a common central processing unit.

17. A method of responding to a plurality of requests from one or more external systems received by a data storage system, comprising:

a) accessing each request at said data storage system comprising a first type processing module for partially executing a first group of data storage operations, a second type processing module for partially executing a second group of data storage operations, and a third type processing module for partially executing a third group of data storage operations;

b) in response to each request, fully executing a corresponding one of said data storage operations by using at least two of said first, second, and third type processing modules cooperating in a hand-off manner; and

c) if an abnormal state arises during said b), detecting said abnormal state and proceeding to recover from said abnormal state by using a particular module of said first, second, and third type processing modules involved in executing said corresponding data storage operation.

18. A method as recited in claim 17 wherein said first group comprises a read operation and a write operation.

19. A method as recited in claim 17 wherein said second group comprises a read operation, a write operation, a stage operation, and a destage operation.

20. A method as recited in claim 17 wherein said third group comprises a stage operation and a destage operation.

21. A method as recited in claim 17 wherein said proceeding to recover from said abnormal state comprises:

retrying said corresponding data storage operation with another module.

22. A method as recited in claim 17 wherein said proceeding to recover from said abnormal state comprises:

cleaning up a pending task of said corresponding data storage operation.

23. A method as recited in claim 17 wherein said first type processing module, said second type processing module, and said third type processing module are each implemented in a plurality of distinct central processing units.

24. A method as recited in claim 17 wherein said first type processing module and said third type processing module are implemented in a common central processing unit.