Fail over cluster system and fail over method

1. A network storage system coupled to a client computer via a network, comprising:

a first node and a second node which provide the client computer with one or more file systems using one or more service IP addresses;

an inter-node communication path which couples the first node and the second node to each other; and

at least one disk subsystem coupled to the first node and the second node,

wherein the disk subsystem has plural logical units,

wherein at least one of the plural logical units is a shared logical unit which is used by the first node and the second node,

wherein the first node includes:

a priority recognizing processing module which consults a priority of a frame received from the client computer;

a priority level determining processing module which determines, based on the priority of the frame, an order of fail over priority for plural software resources including the service IP address and the file system; and

a first monitoring processing module which sends given monitoring signals at a given timing,

wherein the priority level determining processing module:

calculates a first value obtained by multiplying the priority by the number of frames that are received by the first node;

calculates a second value which is the product of the square of the priority and the number of frames that are received by the first node;

determines the order of fail over priority from the sum of the first value and the second value; and

stores the determined order of fail over priority in the shared logical unit, and

wherein the second node includes:

a second monitoring processing module which receives the monitoring signals sent from the first monitoring processing module and, when the monitoring signals fail to arrive at the given timing, judges that a failure has occurred in the first node; and

a fail over processing module which, when the second monitoring processing module judges that a failure has occurred in the first node, consults the order of fail over priority stored in the shared logical unit and performs fail over on the plural software resources according to the order of fail over priority consulted.

2. A cluster system coupled to a client computer via a network, comprising plural nodes which provide services to the client computer,

wherein a first node of the plural nodes has a priority recognizing processing module which consults a priority of a frame received from the client computer, and a priority level determining processing module which determines the order of fail over priority based on a calculation of the priority consulted by the priority recognizing processing module and the number of frames that are received by the first node, the calculation being multiplication of the priority or the square thereof and the number of frames that are received by the first node, and

wherein a second node of the plural nodes has a fail over processing module, which performs fail over on plural software resources managed by the first node according to an order of fail over priority that is based on the priority consulted by the priority recognizing processing module of the first node.

3. A fail over method for a cluster system which is coupled to a client computer via a network and which has plural nodes to provide services to the client computer, the method comprising:

consulting a priority of a frame which is received by a first node of the plural nodes from the client computer;

determining an order of fail over priority used to mount plural software resources managed by the first node to a second node of the plural nodes for fail over based on a calculation of the priority consulted and the number of frames that are received by the first node, the calculation being multiplication of the priority or the square thereof and the number of frames that are received by the first node; and

mounting the plural software resources to the second node of the plural nodes for fail over according to the order of fail over priority.