System and method for a redundant communication channel via storage area network back-end

• US 6,883,065 B1
• Filed: 06/28/2002
• Issued: 04/19/2005
• Est. Priority Date: 11/15/2001
• Status: Expired due to Term

• Current Assignee: Innovations In Memory LLC
• Original Assignee: Xiotech Corporation
• Inventors: Pittelkow, Michael Henry, Olson, Mark David
• Primary Examiner(s): Padmanabhan, Mano
• Assistant Examiner(s): Namazi, Mehdi
• Application Number:
  US10/183,979
• Time in Patent Office: 1,026 Days
• Field of Search: 709/206, 709/207, 709/208, 711/111, 711/112, 711/114, 711/203, 711/1, 714/6, 714/9, 714/5, 714/11
• US Class Current: 711/114
• 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 11/0784 Routing of error reports, e.g. with a specific transmission path or data flow
• CPC Class Codes: G06F 11/201 between storage system components
• CPC Class Codes: G06F 11/2092 Techniques of failing over between control units
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 2003/0697 device management, e.g. handlers, drivers, I/O schedulers
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems

Abstract

A fiber channel storage area network (SAN) provides virtualized storage space for a number of servers to a number of virtual disks implemented on various virtual redundant array of inexpensive disks (RAID) devices striped across a plurality of physical disk drives. The SAN includes plural controllers and communication paths to allow for fail-safe and fail-over operation. The plural controllers can be loosely-coupled to provide n-way redundancy and have more than one independent channel for communicating with one another. In particular, respective portions from each of the back-end physical disk drives within the SAN are used as one of these alternative communication channels to pass messages between controllers. Such an alternative communications channel provides even further redundancy and robustness in the system.

Claims

1. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

means for communicating among the storage controllers over an alternative communications channel;

wherein

the storage area network comprises a plurality of physical disk drives coupled to a respective back-end of each of the storage controllers, said physical disk drives configured to provide the virtualized storage; and

the means for communicating further comprises a respective portion on at least one of the physical disk drives, wherein one or more messages are stored in each of the respective portions, said one or more messages being exchanged between the master controller and any of the slave controllers.

4. The storage area network according to claim 1, wherein each respective portion includes a separate area associated with each slave controller.

5. The storage area network according to claim 4, wherein each separate area further comprises:

a first region in which the master controller can write data to and the associated slave controller can retrieve data from; and

a second region in which the associated slave controller can write data to and the master controller can read data from.

6. The storage area network according to claim 1, further comprising:

a primary communication channel among the storage controllers; and

wherein any one of the storage controllers is configured to use the means for communicating as an alternative communications channel if the primary communication channel is unavailable.

2. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, a plurality of servers, access to virtualized storage wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

means for communicating among the storage controllers over an alternative communications channel wherein;

the storage area network comprises a plurality of physical disk drives coupled a respective back-end of each of storage controllers, said physical disk drives configured to provide the virtualized storage; and

the means for communicating further comprises a respective portion on each one of the physical disk drives, wherein one or more messages are stored in each of the respective portions, said one or more messages being exchanged between the master controller and any of the slave controllers.

3. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

means for communicating among the storage controllers over an alternative communications channel wherein;

the storage area network comprises a plurality of physical disk drives coupled to a respective back-end of each of the storage controllers, said physical disk drives configured to provide the virtualized storage; and

the means for communicating further comprises a respective portion on at least one additional disk drive, said at least one additional disk drive being separate from the physical disk drives, wherein one or more messages are stored in each of the respective portions, said one or more messages being exchanged between the master controller and any of the slave controllers.

7. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, to a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

a communication channel coupled to each of the controllers for communicating among the controllers, the communications channel comprising a memory device accessible by all of the storage controllers, said memory device configured to store one or more messages between the master controller and the slave controllers wherein;

the storage area network comprises a plurality of physical disk drives coupled to a respective back-end of each of the storage controllers, said physical disk drives configured to provide the virtualized storage; and

wherein the memory device further comprises a respective portion on at least one of the physical disk drives, wherein the one or more messages are stored in each of the respective portions.

11. The storage area network according to claim 7, wherein each respective portion includes a separate area associated with each slave controller.

12. The storage area network according to claim 11, wherein each separate area further comprises:

a first region in which the master controller can write data to and the associated slave controller can retrieve data from; and

a second region in which the associated slave controller can write data to and the master controller can retrieve data from.

13. The storage area network according to claim 12, wherein none of the slave controllers are permitted to write data to any of the first regions and, for each of the second regions, only the associated slave controller is permitted to that second region.

14. The storage area network according to claim 12, further comprising:

respective first polling routines executing on each slave controller, configured to;

determine if a new inbound message has been written to the associated first region; and

determine if a new outbound message is ready to be written to the associated second region.

15. The storage area network according to claim 12, further comprising:

a polling routine executing on the master controller, configured to;

determine if a new outbound message is ready to be written to any of the first regions; and

determine if a new inbound message has been written to any of the second regions.

17. The storage area network according to claim 11, wherein each separate area further comprises:

a region in which the associated slave controller is configured to write information regarding results of an election process performed among the storage controllers.

18. The storage area network according to claim 11, wherein each separate area further comprises:

a region in which the associated slave controller is configured to retrieve information regarding its operational status.

8. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, to a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

a communication channel coupled to each of the controllers for communicating among the controllers, the communications channel comprising a memory device accessible by all of the storage controllers, said memory device configured to store one or more messages between the master controller and the slave controllers wherein;

the storage area network comprises a plurality of physical disk drives coupled to a respective back-end of each of the storage controllers, said physical disk drives configured to provide the virtualized storage; and

wherein the memory device further comprises a respective portion on each one of the physical disk drives, wherein the one or more messages are stored in each of the respective portions.

9. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, to a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

a communication channel coupled to each of the controllers for communicating among the controllers, the communications channel comprising a memory device accessible by all of the storage controllers, said memory device configured to store one or more messages between the master controller and the slave controllers;

wherein the memory device includes one or more semiconductor memories and the one or more messages are stored on each of the semiconductor memories.

10. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, to a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

a communication channel coupled to each of the controllers for communicating among the controllers, the communications channel comprising a memory device accessible by all of the storage controllers, said memory device configured to store one or more messages between the master controller and the slave controllers wherein;

the storage area network comprises a plurality of physical disk drives coupled to a respective back-end of each of the storage controllers, said physical disk drives configured to provide the virtualized storage; and

wherein the memory device comprises a respective portion on at least one additional disk drives, said at least one additional disk drive being separate from the physical disk drives, wherein the one or more messages are stored in each of the respective portions.

16. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, to a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

a communication channel coupled to each of the controllers for communicating among the controllers, the communications channel comprising a memory device accessible by all of the storage controllers, said memory device configured to store one or more messages between the master controller and the slave controllers;

wherein the one or more stored messages include respective digital signatures to permit authentication of each respective message.

19. A storage area network comprising:

a plurality of loosely-coupled storage controllers arranged in a redundant configuration to provide, to a plurality of servers, access to virtualized storage, wherein one of the storage controllers operates as a master controller and the other storage controller or controllers operate as slave controllers; and

a communication channel coupled to each of the controllers for communicating among the controllers, the communications channel comprising a memory device accessible by all of the storage controllers, said memory device configured to store one or more messages between the master controller and the slave controllers wherein;

a primary communication channel among the storage controllers; and

wherein at least one of the storage controllers is configured to use the memory device as an alternative communications channel if the primary communication channel is unavailable.

20. A method, in a storage area network comprising plural loosely-coupled redundant controllers, for providing a back-end message channel, the method comprising the steps of:

arranging the controllers to include a master controller and one or more slave controllers;

allocating a respective storage portion on each of a plurality of physical disk drives which are coupled to a respective back-end of each controller;

in response to a first slave controller having a first message to forward to the master controller, writing of said first message to each of the storage portions by the first slave controller; and

in response to the master controller having a second message to forward to a second slave controller;

writing of said second message to each of the storage portions by the master controller.

21. The method according to claim 20, further comprising the step of:

retrieving the first message from at least one of the storage portions by the master controller.

22. The method according to claim 20, further comprising the step of:

retrieving the second message from at least one of the storage portions by the second slave controller.

23. The method according to claim 20, wherein:

the step of writing the first message further includes the step of digitally signing the first message by the first slave controller; and

the step of writing the second message further includes the step of digitally signing the second message by the master controller.

24. The method according to claim 20, further comprising the steps of:

polling the storage portions, by each of the slave controllers, to determine if the master controller has written the second message to the storage portions; and

retrieving the second message, by the second slave controller, in response to determining that the master controller has written the second message, wherein said second message is retrieved from any one of the storage portions.

25. The method according to claim 20, further comprising the step of:

polling the storage portions, by the master controller, to determine if the first slave controller has written the first message to the storage portions; and

retrieving the first message, by the master controller, in response to determining that the first slave controller has written the first message, wherein said first message is retrieved from any of the storage portions.

26. The method according to claim 20, further comprising the steps of:

connecting the plural controllers via a primary communication channel;

detecting, at any of the plural controllers, whether the primary communication channel is unavailable to that particular storage controller; and

in response to determining the primary communication channel is unavailable, using, by that particular controller, the storage portions as an alternative communication channel.