Methods and systems for implementing shared disk array management functions
Multiple Array Management Functions (AMFs) are connected to multiple redundancy groups over a storage area network (SAN), such as a fiber-channel based SAN. The multiple AMFs share management responsibility of the redundancy groups, each of which typically includes multiple resources spread over multiple disks. The AMFs provide concurrent access to the redundancy groups for associated host systems. When a host requests an AMF to perform an operation on a resource, the AMF synchronizes with the other AMFs sharing control of the redundancy group that includes the resource to be operated on, so as to obtain access to the resource. While performing the operation, the AMF send replication data and state information associated with the resource such that if the AMF fails, any of the other AMFs are able to complete the operation and maintain data reliability and coherency.
1. In a data storage network, a method of maintaining data coherency using two or more array management functions (AMFs) that are able to concurrently access a redundancy group, the redundancy group including a plurality of resources, the method comprising:
receiving a request from a host, by a first one of the AMFs, to perform a first operation on data stored on a first one of the resources;
broadcasting a message from the first AMF to the other AMFs sharing access to the first resource so as to acquire access to the first resource;
performing the first operation on the data by the first AMF; and
sending replication and state data from the first AMF to the other AMFs concurrently with performing the operation such that if the first AMF fails while performing any steps of the operation, one of the other AMFs is able to complete the operation using said sent replication and state data.
2. The method of claim 1 , wherein the first operation is a write operation, the method further comprising receiving from the host the data to be written to the first resource by the first AMF.
3. The method of claim 2 , wherein the broadcast message is a write invalidate request, and wherein, responsive to the invalidate request, each of the AMFs sharing access to the resource invalidates corresponding data stored in its cache.
4. The method of claim 1 , wherein the first operation is a read operation.
5. The method of claim 4 , further comprising performing a search of the cache of each of the AMFs sharing access to the first resource for a copy of the data requested in the read request.
6. The method of claim 5 , further comprising reading the requested data from the first resource if none of the AMFs sharing access respond with a copy of the requested data.
7. The method of claim 5 , further comprising receiving the requested data from one of the AMFs sharing access to the resource.
8. The method of claim 4 , wherein the broadcast message identifies the data in the request, the method further comprising searching the cache of each of the AMFs sharing access to the first resource for the identified data, and forwarding the identified data to the first AMF if found in the cache.
9. The method of claim 1 , further comprising determining whether the data identified in the request is shared by one or more other AMFs.
10. In a data storage network, a method of maintaining data coherency using two or more array management functions (AMFs) that are able to concurrently access a redundancy group, the redundancy group including a plurality of resources, the method comprising:
receiving a request from a host, by a first one of the AMFs, to perform a first operation on data stored on a first one of the resources;
determining from the request whether the identified data is shared by one or more of the other AMFs; and
if so:
broadcasting a message from the first AMF to the other AMFs sharing access to the first resource so as to acquire access to the first resource; and
performing the first operation on the data by the first AMF; and
if not:
performing the first operation on the data by the first AMF; and
in both cases, sending replication and state data from the first AMF to the other AMFs concurrently with performing the first operation such that if the first AMF fails while performing any steps of the first operation, one of the other AMFs is able to complete the first operation using said sent replication and state data.
11. The method of claim 10 , wherein the request is one of a write data request and a read data request.
12. The method of claim 10 , wherein the broadcast message is a write invalidate request, and wherein, responsive to the invalidate request, each of the ALMFs sharing access to the resource invalidates corresponding data stored in its cache.
13. A data storage network, comprising:
two or more controllers communicably coupled to a redundancy group, each controller having one or more array management functions (AMFs), wherein two or more of said AMFs are able to concurrently access the redundancy group, the redundancy group including a plurality of resources, each controller further including:
means for receiving a request from a host to perform an operation on data stored on a first one of the resources by a first AMF;
means for broadcasting a message from the first AMF to other AMFs sharing access to the first resource so as to acquire access to the first resource;
means for performing the first operation on the data by the first AMF; and
means for sending replication and state data from the first AMF to the other AMFs concurrently with performing the operation such that if the first AMF fails while performing any steps of the operation, one of the other AMFs is able to complete the operation using said sent replication and state data.
14. A data storage network, comprising:
two or more controllers communicably coupled to a redundancy group, each controller having one or more array management functions (AMFs), wherein two or more of said AMFs are able to concurrently access the redundancy group, the redundancy group including a plurality of resources, each controller further including:
means for receiving a request from a host to perform a first operation on data stored on a first one of the resources by a first AMF;
means for determining from the request whether the identified data is shared by one or more of the other AMFs;
means for broadcasting a message from the first AMF to the other AMFs sharing access to the first resource so as to acquire access to the first resource if the data is shared;
means for performing the first operation on the data by the first AMF; and
means for sending replication and state data from the first AMF to the other AMFs concurrently with performing the operation such that if the first AMF fails while performing any steps of the operation, one of the other AMFs is able to complete the operation using said sent replication and state data.