Methods and systems for implementing shared disk array management functions

In a data storage system, a method of dynamically sharing management of a redundancy group between two or more array management functions (AMFs), wherein the AMFs are able to concurrently access the redundancy group, the redundancy group including a plurality of resources, the method comprising the steps of:

• receiving a request from a host by a first one of the AMFs to perform a first operation on a first one of the resources;
• synchronizing with the other AMFs so as to acquire access to the first resource;
• and
• performing the first operation on the first resource.

A data storage network system comprising:

• one or more redundancy groups, each redundancy group including multiple resources spread over multiple disks;
• two or more array management functions (AMFs) sharing redundancy group management of the one or more redundancy groups, wherein the AMFs are able to concurrently access the one or more redundancy groups;
• and
• a interconnect medium for interconnecting the AMFs with the one or more redundancy groups.

A method of reconstructing a redundancy group when one of its disks fails in a data storage network system comprising two or more array management functions (AMFs) interconnected with the redundancy group, wherein the redundancy group includes multiple resources spread over multiple disks, wherein the redundancy group also includes a replacement disk, wherein the AMFs all share management of the redundancy group, and wherein the AMFs are able to concurrently access the redundancy group, the method comprising the steps of:

• arbitrating for control of a first resource by a first one of the AMFs;
• arbitrating for control of a second resource by a second one of the AMFs;
• and
• concurrently reconstructing the first and second resources using the replacement disk.

A method of expanding a redundancy group when an extra disk is added to it in a data storage network system comprising two or more array management functions (AMFs) interconnected with the redundancy group, wherein the redundancy group includes multiple resources spread over multiple disks, wherein the AMFs all share management of the redundancy group, and wherein the AMFs are able to concurrently access the redundancy group, the method comprising the steps of:

• arbitrating for control of a first resource by a first one of the AMFs;
• arbitrating for control of a second resource by a second one of the AMFs;
• and
• concurrently expanding the first and second resources using the extra disk.

A method of pipelining replication of incoming host data in a data storage network system comprising a redundancy group interconnected with two or more array management functions (AMFs), wherein the redundancy group includes multiple resources spread over multiple disks, wherein the AMFs all share management of the redundancy group, and wherein the AMFs are able to concurrently access the redundancy group, the method comprising the steps of:

• receiving a write command by a first AMF from the host to write at least two data sets to two or more of the resources;
• acquiring a lock by the first AMF on the first resource to which the first data set is to be written;
• writing the first data set to the first resource;
• and concurrently
• performing a first replication operation wherein replication data and state information associated with the first resource is sent to the other AMFs, such that if the first AMF fails while performing the write operation, one of the other AMFs is able to complete the write operation.

In a data storage system, a method of dynamically sharing management of a redundancy group between two or more array management functions (AMFs), wherein the AMFs are able to concurrently access the redundancy group, the redundancy group including a plurality of resources, the method comprising the steps of:

• determining an arbiter AMF for a first one of the resources, wherein the arbiter AMF is one of the two or more AMFs sharing management of the redundancy group, and wherein the arbiter AMF is able to grant a lock for the first resource;
• communicating a lock request from a first one of the AMFs to the arbiter AMF requesting a lock on the first resource;
• and
• performing an operation on the first resource by the first AMF once the lock on the first resource has been granted by the arbiter AMF.