Storage apparatus and method of controlling the same

• US 20060221393A1
• Filed: 03/21/2006
• Published: 10/05/2006
• Est. Priority Date: 03/29/2005
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Takaki, Toshiaki
• Granted Patent: US 7,464,220 B2
• Time in Patent Office: Days
• US Class Current: 358/1.160
• CPC Class Codes: G06F 11/1666 where the redundant component is memory or memory area
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 2212/286 Mirrored cache memory
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0673 Single storage device

Abstract

A storage apparatus comprising a plurality of nodes through which write-data received from a host is written into a disc, each of the nodes including a first memory in which the write-data is temporarily stored, a second memory, a copier which copies both write-data stored in the first memory and write-data stored in a first memory of another node into the second memory, the copier being able to make communication with a copier of the another node through a copier-interface, and a mode-switch which, when a trouble is found in the copier-interface, writes the write-data stored in the first memory into the disc without copying the write-data into the second memory.

Claims

1. A storage apparatus comprising a plurality of nodes through which write-data received from a host is written into a disc,

each of said nodes including:

a first memory in which said write-data is temporarily stored;

a second memory;

a copier which copies both write-data stored in said first memory and write-data stored in a first memory of another node into said second memory, said copier being able to make communication with a copier of said another node through a copier-interface; and

a mode-switch which, when a trouble is found in said copier-interface, writes said write-data stored in said first memory into said disc without copying said write-data into said second memory.

2. The storage apparatus as set forth in claim 1, wherein each of said nodes further includes a write-back device which, when said mode-switch switches a mode into another mode, writes said write-data stored in said second memory into said disc.

3. The storage apparatus as set forth in claim 1, wherein each of said nodes further includes a diagnosis device which diagnoses said copier when said node restarts after said copier was exchanged into a new one.

4. The storage apparatus as set forth in claim 1, wherein each of said nodes further includes a fail-over controller which, when another node stop operation thereof, takes over tasks to be carried out by said another node.

5. The storage apparatus as set forth in claim 1, wherein each of said nodes further includes a communicator which makes communication with another node when said copier-interface is troubled.

6. The storage apparatus as set forth in claim 1, wherein said first memory comprises a cache memory.

7. The storage apparatus as set forth in claim 1, wherein said second memory comprises a non-volatile memory.

8. The storage apparatus as set forth in claim 1, wherein a number of said nodes is two.

9. A storage apparatus comprising a plurality of nodes through which write-data received from a host is written into a disc,

each of said nodes including:

a first memory in which said write-data is temporarily stored;

a second memory as a backup memory for storing said write-data;

a copier which copies both write-data stored in said first memory and write-data stored in a first memory of another node into said second memory, said copier being able to make communication with a copier of said another node through a copier-interface; and

a processor which controls operation of said storage apparatus,

wherein when said copier-interface is not troubled, said processor operates in a write-back mode in which said processor informs said host of completion of write-data storage when or after said copier has copied both write-data stored in said first memory and write-data stored in a first memory of another node into said second memory, and then, writes said write-data into said disc, whereas when said copier-interface is troubled, said processor operates in a write-through mode in which said processor writes said write-data stored in said first memory into said disc without copying said write-data into said second memory, and then, informs said host of completion of write-data storage.

10. The storage apparatus as set forth in claim 9, wherein each of said nodes further includes a diagnosis device which diagnoses said copier when said node restarts after said copier was exchanged into a new one.

11. The storage apparatus as set forth in claim 9, wherein each of said nodes further includes a fail-over controller which, when another node stop operation thereof, takes over tasks to be carried out by said another node.

12. The storage apparatus as set forth in claim 9, wherein each of said nodes further includes a communicator which makes communication with another node when said copier-interface is troubled.

13. The storage apparatus as set forth in claim 9, wherein said first memory comprises a cache memory.

14. The storage apparatus as set forth in claim 9, wherein said second memory comprises a non-volatile memory.

15. The storage apparatus as set forth in claim 9, wherein a number of said nodes is two.

16. A method of controlling a storage apparatus comprising a plurality of nodes through which write-data received from a host is written into a disc, comprising:

copying, in each of said nodes, both write-data stored in a first memory and write-data stored in a first memory of another node into a second memory;

judging whether a copier-interface through which each of said nodes can made communication with another node is troubled; and

if said copier-interface is troubled, writing said write-data stored in said first memory into said disc without copying said write-data into said second memory.

17. The method as set forth in claim 16, further including writing backup write-data stored in said second memory into said disc, when said copier-interface is troubled.

18. The method as set forth in claim 16, further including diagnosing a copier used for copying both said write-data stored in said first memory and said write-data stored in a first memory of another node into said second memory, when each of said nodes restarts after said copier was exchanged into a new one.

19. The method as set forth in claim 16, further including a fail-over controlling step in which, when another node stop operation thereof, each of said nodes takes over tasks to be carried out by said another node.

20. The method as set forth in claim 16, further including making communication with another node when said copier-interface is troubled.

21. A program for causing a computer to carry out a method of controlling a storage apparatus comprising a plurality of nodes through which write-data received from a host is written into a disc, wherein steps executed by said computer in accordance with said program includes:

copying, in each of said nodes, both write-data stored in a first memory and write-data stored in a first memory of another node into a second memory;

judging whether a copier-interface through which each of said nodes can made communication with another node is troubled; and

if said copier-interface is troubled, writing said write-data stored in said first memory into said disc without copying said write-data into said second memory.

22. The program as set forth in claim 21, wherein said steps further includes writing backup write-data stored in said second memory into said disc, when said copier-interface is troubled.

23. The program as set forth in claim 21, wherein said steps further includes diagnosing a copier used for copying both said write-data stored in said first memory and said write-data stored in a first memory of another node into said second memory, when each of said nodes restarts after said copier was exchanged into a new one.

24. The program as set forth in claim 21, wherein said steps further includes a fail-over controlling step in which, when another node stop operation thereof, each of said nodes takes over tasks to be carried out by said another node.

25. The program as set forth in claim 21, wherein said steps further includes making communication with another node when said copier-interface is troubled.