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

• US 6,611,897 B2
• Filed: 04/17/2002
• Issued: 08/26/2003
• Est. Priority Date: 03/22/1999
• Status: Expired due to Term

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Yamamoto, Akira, Kamo, Yoshihisa, Komachiya, Tsunetaka
• Primary Examiner(s): Robertson, David L.
• Application Number:
  US10/123,404
• Publication Number:
  US 20020112118A1
• Time in Patent Office: 496 Days
• Field of Search: 711/114
• US Class Current: 711/114
• CPC Class Codes: G06F 2211/1004 Adaptive RAID, i.e. RAID system adapts to changing circumstances, e.g. RAID1 becomes RAID5 as disks fill up
• CPC Class Codes: G06F 2211/1023 Different size disks, i.e. non uniform size of disks in RAID systems with parity
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0632 by initialisation or re-initialisation of storage systems
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

In a disk array subsystem capable of changing the data redundancy method between a duplicating method and a parity method, the load of data transfer occurring at the time of changing the data redundant method is reduced. In the disk array subsystem, since one data of the duplicated data are used for data for the parity data area, the one data secures an area for storing parity prepared from the data. With the arrangement, it is not necessary to transfer the data when the data redundancy method is changed from the duplicating to the parity method and the data transfer load is mitigated.

Claims

1. In a storage system that receives a write request for data from a host processor and stores said data on 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 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 or 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; and

when the method for implementing redundancy determined in the determining step is one which stores said data by generating parity data for a predetermined number of data blocks to thereby implement redundancy, storing said predetermined number of data blocks and the parity data thereof in different physical disks, respectively.

2. The method according to claim 1, wherein said determining step comprises the steps of:

collecting, by said storage controller, information of frequency of accessing said physical disk apparatuses; and

determining a method for implementing redundancy based on the collected access frequency information.

3. The method according to claim 1, wherein said determining step comprise steps of:

making, by said storage controller, at least one of an operation system of a host processor and an application on the host processor instruct a method for implementing redundancy; and

determining a method for implementing redundancy based on instructions from said making step.

4. The method according to claim 1, wherein said determining step comprise steps of:

receiving, by said storage controller, instructions for changing the redundancy implementing method through a service processor; and

determining a method for implementing redundancy based on instructions received in the receiving step.

5. 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.

6. The method according to claim 5, wherein said command for changing the method for implementing redundancy is received by said storage controller through a service processor.

7. 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.