System and method for redundant communication between redundant controllers
View Patent ↗A fibre 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 the event of a failure involving a controller or controller interface, the virtual disks that are accessed via the affected interfaces are re-mapped to another interface in order to continue to provide high data availability.
1. A storage area network comprising:
a plurality of loosely-coupled storage controllers arranged in a redundant configuration to include only one master storage controller and one or more slave storage controllers, said storage controllers configured to collectively provide virtual storage space to a plurality of servers;
a first channel coupled to each of the redundant controllers configured to provide a first path for communication among the storage controllers;
a second channel coupled to each of the redundant controllers configured to provide a second path for communication among the storage controllers;
a third channel coupled to each of the redundant controllers configured to provide a third path for communication among the storage controllers; and
a plurality of physical disk drives coupled to respective back-ends of the storage controllers; wherein
the third channel comprises a portion of one or more of the physical disk drives that is accessible to all the storage controllers;
wherein each of the portions on the one or more physical disk drives include a first region which is writable only by the master storage controller and a second region which is writable by the slave storage controllers;
wherein the second region further comprises:
a respective area for each of the slave storage controllers, each said area including:
a first section that the master storage controller can write data to and the respective slave storage controller can read data from; and
a second section that the respective slave storage controller can write data to and the master storage controller can read data from.
2. The storage area network according to claim 1 , wherein the first channel comprises a direct network connection among the storage controllers.
3. The storage area network according to claim 1 , wherein each of the storage controllers includes a respective front-end interface and the second channel comprises a link to the respective front-end interface of each storage controller.
4. The storage area network according to claim 3 , wherein:
the respective front-end interface includes one or more fibre channel host adapter boards; and
the second channel comprises a link to each fibre channel host adapter board.
5. The storage area network according to claim 1 , wherein the third channel comprises a portion on each of the physical disk drives.
6. The storage area network according to claim 1 , wherein each of the storage controllers are configured to communicate with each of the servers.
7. The storage area network according to claim 1 , wherein each of the storage controllers are configured to communicate with each physical disk drive within the storage area network.
8. The storage area network according to claim 1 , wherein:
each storage controller comprises a respective communication routine that, when executing, is configured to send messages over one or more of the first, second and third channels.
9. The storage area network according to claim 1 , wherein each communication routine is further configured to use the first channel as a primary route to send a message and use the second channel as an alternative route if delivery using the first channel fails.
10. The storage area network according to claim 9 , wherein each communication routine is further configured to use the third channel if delivery using the first and second channel both fail.