Method and apparatus for implementing redundancy on data stored in a disk array subsystem based on use frequency or importance of the data

In a storage system that receives a write request for data from a host processor and stores said data in a plurality of physical disk apparatuses, said storage system includes a storage controller that receives said data write request from said host processor through a host processor interface, said storage controller dividing or segmenting said data in units of a data block to store the data in said physical disk apparatuses, a method of implementing redundancy on said data comprising the steps of:

• determining a method for implementing redundancy based on at least one of use frequency of said data and importance of said data;
• when the method for implementing redundancy determined in the determining step is one which stores said data in both a first storage area and a second storage area to thereby duplicate said data, storing said data in said first and second storage areas such that, in said second storage area, said data are continuously stored in a same physical disk in units of a parity group, and in said first storage area, data blocks constituting a parity group are stored in a plurality of physical disks in a distributed manner;
• when said storage controller receives a command for changing the method for implementing redundancy determined in said determining step, reading data blocks from said second storage area in units of a parity group;
• generating parity data from data blocks constituting said parity group which has been read;
• storing said parity data generated in said generating step in said first storage area such that said parity data is stored in a physical disk different from those physical disks that store therein data blocks constituting the parity group associated with said parity data;
• and
• after storing said parity data in said first storage area, erasing the data blocks in said second storage area that were used for generating said parity data.

In a storage system that receives a write request for data from a host processor and stores said data in a plurality of physical disk apparatuses, said storage system includes a storage controller that receives said data write request from said host processor through a host processor interface, said storage controller dividing or segmenting said data in units of a data block to store said data on said physical disks, a method of implementing redundancy comprising the steps of:

• determining a method for implementing redundancy based on at least one of use frequency of said data and importance of said data;
• when the method for implementing redundancy determined in said determining step is one which uses parity data for implementing redundancy, generating parity data from data blocks constituting a parity group and storing said parity data and each of said data blocks used for generating said parity data in different physical disks constituting a first storage area, respectively;
• and
• when said storage controller receives a command for changing the method for implementing redundancy determined in said determining step, continuously reading respective data blocks constituting a parity group stored in said first storage area and continuously storing said respective data blocks in a physical disk of said second storage area.