System and method for bi-directional failure detection of a site in a clustering system

• US 7,076,687 B2
• Filed: 10/16/2002
• Issued: 07/11/2006
• Est. Priority Date: 10/16/2002
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Abe, Toshiyuki, Fujibayashi, Akira, Yamagami, Kenji
• Primary Examiner(s): Beausoliel, Robert
• Assistant Examiner(s): MASKULINSKI, MICHAEL C
• Application Number:
  US10/273,048
• Publication Number:
  US 20040078644A1
• Time in Patent Office: 1,364 Days
• Field of Search: 714/5, 714/6, 714/42
• US Class Current: 714/6.31
• CPC Class Codes: G06F 11/0727 in a storage system, e.g. in a DASD or network based storage system drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units 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 11/0757 by exceeding a time limit, i.e. time-out, e.g. watchdogs
• CPC Class Codes: G06F 11/2069 Management of state, configuration or failover
• CPC Class Codes: G06F 11/2071 using a plurality of controllers

Abstract

A method for failure detection comprises: checking, at a first time, a state of a local volume that is mirrored at a second location; issuing a change state command to the local volume; checking, at a second time, the state of the local volume after a host at the second location issues a change state command; comparing the state of the local volume at the first time and at the second time; and initiating a fail over procedure if the state of the local volume is different at the second time from the first time.

Claims

1. A method, comprising:

obtaining, at a first time, a state of a local volume that is mirrored at a second location;

issuing a first change state command associated with the local volume;

obtaining, at a second time, the state of the local volume after a host at the second location issues a second change state command associated with a mirror volume; and

comparing the state of the local volume at the first time and at the second time to determine if there has been a failure at the second location.

2. The method of claim 1, wherein the change state command includes changing a volume between a primary volume state and a secondary volume state.

3. The method of claim 1, wherein the change state command includes changing a volume between a mirrored state and a suspended state.

4. The method of claim 1, further comprising notifying a system operator of a failure based on the comparison.

5. The method of claim 1, further comprising sending a change state command to the local volume before obtaining, at a second time, the state of the local volume.

6. The method of claim 1, further comprising initiating a fail over procedure based on the comparison.

7. A computer-readable medium having stored thereon computer-executable instructions to perform a method, the method comprising:

obtaining, at a first time, a state of a local volume that is mirrored at a second location;

issuing a first change state command associated with the local volume;

obtaining, at a second time, the state of the local volume after a host at the second location issues a second change state command associated with a mirror volume; and

comparing the state of the local volume at the first time and at the second time to determine if there has been a failure at the second location.

8. The computer-readable medium of claim 7, wherein the change state command includes changing a volume between a primary volume state and a secondary volume state.

9. The computer-readable medium of claim 7, wherein the change state command includes changing a volume between a mirrored state and a suspended state.

10. The computer-readable medium of claim 7, the method further comprising notifying a system operator of a failure based on the comparison.

11. The computer-readable medium of claim 7, the method further comprising sending a change state command to the local volume before obtaining, at a second time, the state of the local volume.

12. The computer-readable medium of claim 7, the method further comprising initiating a fail over procedure based on the comparison.

13. A system, comprising:

means for obtaining, at a first time, a state of a local volume that is mirrored at a second location;

means for issuing a first change state command associated with the local volume;

means for obtaining, at a second time, the state of the local volume after a host at the second location issues a second change state command associated with a mirror volume; and

means for comparing the state of the local volume at the first time and at the second time to determine if there has been a failure at the second location.

14. A system, comprising:

an engine operable to

obtain, at a first time, a state of a local volume that is mirrored at a second location;

issue a first change state command associated with the local volume;

obtain, at a second time, the state of the local volume after a host at the second location issues a second change state command associated with a mirror volume; and

compare the state of the local volume at the first time and at the second time to determine if there has been a failure at the second location.

15. The system of claim 14, wherein the change state command includes changing a volume between a primary volume state and a secondary volume state.

16. The system of claim 14, wherein the change state command includes changing a volume between a mirrored state and a suspended state.

17. The system of claim 14, wherein the engine is further capable to notify a system operator of a failure based on the comparison.

18. The system of claim 14, wherein the system further comprises a second engine, communicatively coupled to the first engine, capable to send a change state command to the local volume before the first engine obtains, at a second time, the state of the local volume.

19. The system of claim 14, wherein the first engine is further capable to initiate a fail over procedure based on the comparison.

20. A method, comprising:

checking a state of a local volume;

wherein the local volume is mirrored at a remote site,

issuing a first change state command to the local volume, wherein the first change state command is capable to change the local volume between a suspended state and a mirrored state; and

checking the state of the local volume after the issuing and after the remote site issues a second change state command to determine if a failure at the remote site has occurred.

21. The method of claim 20, further comprising initiating a fail over procedure based on the checking.

22. The method of claim 20, further comprising notifying a system operator of a failure based on the checking.

23. A method, comprising:

checking if a state of a volume at a first location that is mirrored at a second location is a first state after a host at the first location issues a first command for changing state of a pair of the volume at the first location and the mirrored volume at the second location and after a host at the second location issues a second command for changing status of the pair; and

determining if there has been a failure at the second location if the state is not the first state.

24. The method of claim 23, wherein the first command and the second command each comprise changing a volume between a primary volume state and a secondary volume state.

25. The method of claim 23, wherein the first command and the second command each comprise changing a volume between a mirrored state and a suspended state.

26. The method of claim 23, further comprising initiating a fail over procedure between the first and second locations.

27. The method of claim 23, further comprising obtaining a state of the volume at the first location before the host at the first location issues the first command,

wherein the first state is the status in the obtaining step.

28. The method of claim 23, wherein the status change at the second location is change from alive status to dead status.

29. A system comprising:

a first storage system comprising a first heartbeat volume, the first heartbeat volume operable to be in one of a first state and a second state;

a second storage system coupled to the first storage system the second storage system comprising a second heartbeat volume;

the second heartbeat volume operable to be in one of the first state and the second state;

wherein the state of the first heartbeat volume mirrors the state of the second heartbeat volume;

a first host operatively coupled to the first storage system, operable to check a state of the first heartbeat volume and to issue a first change state command to the first heartbeat volume; and

a second host operatively coupled to the second storage system, operable to check the state of the second heartbeat volume and to issue a second change state command to the second heartbeat volume;

wherein the first host is additionally operable to compare a first detected state of the first heartbeat volume before issuing the first change state command to a second detected state of the first heartbeat volume after the second host issues the second change state command; and

to detect a failure if the first detected state is different from the second detected state.

30. The system of claim 29, wherein the second host is additionally operable to compare a first detected state of the second heartbeat volume before issuing the second change state command to a second detected state of the second heartbeat volume after the first host issues the first change state command;

and to detect a failure if the first detected state is different from the second detected state.

31. The system of claim 29, wherein the first storage system further comprises a third heartbeat volume and the second storage system further comprises a fourth heartbeat volume.

32. The system of claim 29, further comprising a heartbeat state data structure comprising:

an address of the first heartbeat volume;

an address of the second heartbeat volume;

the state of the first heartbeat volume; and

the state of the second heartbeat volume.