System, and control method and program for input/output requests for storage systems

1. A system comprising:

a cluster formed of a plurality of storage nodes,

wherein each of the storage nodes includes

a storage control module that performs input/output (I/O) processes based on an assigned I/O request, and

a frontend module that assigns the I/O request given from a host apparatus to the storage control module of its own node or a corresponding another storage node,

wherein one or a plurality of virtual first logical volumes are provided to the host apparatus as storage regions for reading and writing data, and a virtual second logical volume correlated with any one of the one or the plurality of the virtual first logical volumes and is identifiable within one of the plurality of storage nodes is created in the one of the plurality of storage nodes in correlation with the storage control module disposed in the one of the plurality of storage nodes,

wherein the host apparatus transmits the I/O request in which a target volume from the one or the plurality of the virtual first logical volumes is designated for the I/O request to the one of the plurality of storage nodes, and

wherein the frontend module

manages a correspondence relationship between the one or plurality of the virtual first logical volumes and the virtual second logical volume as mapping information,

determines a target storage node from the plurality of storage nodes to process the I/O request given from the host apparatus, from identification information of the target volume of the one or the plurality of the virtual first logical volumes in view of the mapping information,

assigns the I/O request to the storage control module of its own node in a case where the determined target storage node is its own node, and

transfers the I/O request to another storage node in a case where the determined target storage node is the another storage node.

2. The system according to claim 1 ,

wherein each of the one or plurality of the virtual first logical volumes is managed as a pool crossing the respective storage nodes forming the cluster.

3. The system according to claim 1 ,

wherein the storage control module is set as a storage control module pair along with a storage control module disposed in another storage node which is different from its own node,

wherein one storage control module forming the storage control module pair is set to an active system, and the other storage control module is set to a standby system state, and

wherein the virtual second logical volume is created in correlation with the storage control module set to an active system state.

4. The system according to claim 3 , further comprising:

a cluster control module that controls the cluster,

wherein the cluster control module

monitors an occurrence of a failure in each of the storage nodes in the cluster,

switches the storage control module which is set to the standby system state forming the same storage control module pair along with the storage control module which is set to the active system state to an active system in a case where the occurrence of a failure in any one of the storage nodes is detected, and

updates the mapping information managed by the frontend module of each of the storage nodes such that a correspondence destination of the virtual second logical volume correlated with the storage control module which was set to the active system state is switched to the storage control module which was switched to the active system state.

5. The system according to claim 3 , further comprising:

a cluster control module that controls the cluster,

wherein the cluster control module moves the storage control module which is set to the active system state disposed in any one of the storage nodes to an added storage node in a case where the added storage node is added to the cluster, and

creates the second logical volume in the added storage node in correlation with the storage control module, and updates the mapping information managed by the frontend module of the added storage node such that a correspondence destination of the virtual second logical volume correlated with the storage control module which was set to the active system is switched to the storage control module moved to the added storage node.

6. The system according to claim 5 ,

wherein the cluster control module moves the storage control module which is set to an active system having the lowest load to the added storage node.

7. A control method for a system including a cluster of a plurality of storage nodes, each of the storage nodes including a storage control module that performs input/output (I/O) processes based on an assigned I/O request, and one or a plurality of virtual first logical volumes being provided to a host apparatus as storage regions for reading and writing data, the control method comprising:

a first step of creating a virtual second logical volume in one of the plurality of storage nodes that is correlated with any one of the one or the plurality of virtual first logical volumes and is identifiable within the one of the plurality of storage nodes in correlation with the storage control module disposed in the one of the plurality of storage nodes, and managing a correspondence relationship between the one or the plurality of the virtual first logical volumes and the virtual second logical volume as mapping information in each of the storage nodes;

a second step of determining a target storage node from the plurality of storage nodes to process the I/O request given from the host apparatus that is designated to a target volume from the one or the plurality of virtual first logical volumes, from identification information of the target volume in view of the mapping information; and

a third step of assigning the I/O request to the storage control module of its own node in a case where the determined target storage node is its own node, and transferring the I/O request to another storage node in a case where the determined target storage node is the another storage node.

8. The control method for the system according to claim 7 ,

wherein each of the one or the plurality of the virtual first logical volumes is managed as a pool crossing the respective storage nodes forming the cluster.

9. The control method for the system according to claim 7 ,

wherein the storage control module is set as a storage control module pair along with a storage control module disposed in another storage node which is different from its own node,

wherein one storage control module forming the storage control module pair is set to an active system state, and the other storage control module is set to a standby system state, and

wherein, in the first step, the virtual second logical volume is created in correlation with the storage control module set to the active system state.

10. The control method for the system according to claim 9 ,

wherein the occurrence of a failure in each of the storage nodes in the cluster is monitored,

wherein the storage control module which is set to the standby system state forming the same storage control module pair along with the storage control module which is set to the active system is switched to the active system state in a case where the occurrence of a failure in any one of the storage nodes is detected, and

wherein the mapping information managed by each of the storage nodes is updated such that a correspondence destination of the virtual second logical volume correlated with the original storage control module which was set to the active system state is switched to the storage control module which was switched to the active system state.

11. The control method for the system according to claim 9 ,

wherein the storage control module which is set to the active system state disposed in any one of the storage nodes is moved to an added storage node in a case where the added storage node is added to the cluster, and

wherein the virtual second logical volume is created in the added storage node in correlation with the storage control module, and the mapping information managed by each of the storage nodes is updated such that a correspondence destination of the second logical volume correlated with the original storage control module which was set to the active system state is switched to the storage control module moved to the added storage node.

12. The control method for the system according to claim 11 ,

wherein the storage control module which is set to the active system state having the lowest load is moved to the added storage node.

13. A non-transitory computer readable medium, storing instructions that are executed in a storage node in a system including cluster of a plurality of the storage nodes, each of the storage nodes including a storage control module that performs input/output (I/O) processes based on an assigned I/O request, and one or a plurality of virtual first logical volumes being provided to a host apparatus as storage regions for reading and writing data, the instructions causing the storage node to execute:

a first step of creating a virtual second logical volume in one of the plurality of storage nodes that is correlated with any one of the one or the plurality of virtual first logical volumes and is identifiable within the one of the plurality of storage nodes in correlation with the storage control module disposed in the one of the plurality of storage nodes, and managing a correspondence relationship between the one or the plurality of the virtual first logical volumes and the virtual second logical volume as mapping information in each of the storage nodes;

a second step of determining a target storage node from the plurality of storage nodes to process the I/O request given from the host apparatus that is designated to a target volume from the one or the plurality of virtual first logical volumes, from identification information of the target volume in view of the mapping information; and

a third step of assigning the I/O request to the storage control module of its own node in a case where the determined target storage node is its own node, and transferring the I/O request to another storage node in a case where the determined target storage node is the another storage node.