Multiple disk data storage system for reducing power consumption

• US 7,234,074 B2
• Filed: 12/17/2003
• Issued: 06/19/2007
• Est. Priority Date: 12/17/2003
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cohn, David Leslie, Kistler, Michael David
• Primary Examiner(s): Duncan; Marc
• Application Number:
  US10/738,712
• Publication Number:
  US 20050138284A1
• Time in Patent Office: 1,280 Days
• Field of Search: 714/6, 714/701, 713/324, 711/114
• US Class Current: 714/6.12
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 2211/1057 Parity-multiple bits-RAID6, i.e. RAID 6 implementations
• CPC Class Codes: G06F 3/0625 Power saving in storage systems
• CPC Class Codes: G06F 3/0634 by changing the state or mode of one or more devices
• CPC Class Codes: G06F 3/0643 Management of files
• CPC Class Codes: G06F 3/068 Hybrid storage device
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A data storage system in which each of a set of disks has a first portion for either popular data or error correction information (parity or Reed-Solomon code symbols) associated with the popular data, and a second portion used for other data. A disk controller connected to the set of disks maintains a first popular data block in the first portion of a first of the set of disks and a second popular data block in the first portion of a second of the set of disks. The system maintains at least two of the disks in an active state. The active disks are selected to insure that any data in the popular data blocks can be determined from data stored in the active disks. An additional disk is maintained in an active state if write access is permitted or if there is an additional popular data block.

Claims

1. A data storage system, including

a set of disks including at least first, second and third disks, each having a first portion for popular data or error correction information associated with the popular data and each having a remaining portion used for remaining data;

a disk controller connected to the set of disks and configured to maintain a first popular data block in the first portion of the first disk and a second popular data block in the first portion of the second disk, wherein the disk controller includes;

means for maintaining at least two of the disks in the set of disks in an active state, wherein the at least two active disks are selected to insure that any data in the popular data blocks can be determined from data stored in the active disks; and

means for biasing to an inactive state at least one of the disks in the set of disks that is not selected as an active disk, such that power consumption is reduced.

2. The system of claim 1, wherein the error correction information is encoded using Reed-Solomon encoding based on the data in the first and second popular data blocks.

3. The system of claim 2, wherein the disk controller is further configured to maintain additional popular data blocks, each popular data block being maintained in the first portion of a corresponding disk, and wherein the means for maintaining at least two disks in an active state comprises means for maintaining active disks equaling the number of popular data blocks.

4. The system of claim 2, wherein the set of disks includes at least one disk for storing the Reed-Solomon encoded error correction information.

5. The system of claim 2, wherein the means for maintaining at least two active disks further comprises means for maintaining at least three active disks if the disks can be written to.

6. A data storage system, including

a set of disks including at least first, second and third disks, each having a first portion for popular data or error correction information associated with the popular data and each having a remaining portion used for remaining data, wherein the error correction information comprises parity information derived from an exclusive OR product of data in the first portions of the other disks;

a disk controller connected to the set of disks and configured to maintain a first popular data block in the first portion of the first disk and a second popular data block in the first portion of the second disk, wherein the disk controller includes;

means for maintaining at least two of the disks in the set of disks in an active state, wherein the at least two active disks are selected to insure that any data in the popular data blocks can be determined from data stored in the active disks.

7. The system of claim 6, wherein the disk controller is further configured to maintain additional popular data blocks, each popular data block being maintained in the first portion of a corresponding disk, and wherein the means for maintaining at least two disks in an active state comprises means for maintaining active disks equaling the number of popular data blocks.

8. The system of claim 7, wherein the disk controller is further configured to replicate each popular data block in the first portion of at least one other disk.

9. The system of claim 8, wherein the means for maintaining the active disks includes means for insuring that one of the active disks contains the parity information and that all popular data blocks can be accessed or algorithmically computed from data in the first portions of the active disks.

10. A method of storing data in an array of N disks, where N is an integer greater than an integer K, said method comprising:

maintaining at least a first block of popular data in a first address region of a first subset of the disks in the disk array and a second block of popular data in a first address region of a second subset of the disks, wherein said maintaining includes maintaining K popular data blocks in the first address regions of K disks;

maintaining Reed-Solomon error correction code in a first address region of a third subset of the disks; and

maintaining the remaining address region of the disks using a RAID 4 or RAID 5 storage organization.

11. The method of claim 10, and further comprising maintaining at least K of the set of disks in an active state.

12. The method of claim 11, wherein maintaining at least K of the set of disks in an active state further comprises:

maintaining at least K+1 of the set of disks in an active state; and

permitting write access to the K popular data blocks.

13. The method of claim 12, and further comprising biasing the remaining N−

(K+1) disks to an inactive state.

14. A computer program product for storing data in an array of N disks, where N is an integer greater than an integer K, said computer program product comprising a computer readable storage medium having stored therein:

computer code means for maintaining at least a first block of popular data in a first address region of a first subset of the disks in the disk array and a second block of popular data in a first address region of a second subset of disks, wherein said computer code means for maintaining includes computer code means for maintaining K popular data blocks in the first address regions of K disks;

computer code means for maintaining Reed-Solomon error correction code in a first address region of a third subset of the disks; and

computer code means for maintaining the remaining address region of the disks using RAID 4 or RAID 5.

15. The computer program product of claim 14, and further comprising code means for maintaining at least K of the set of disks in an active state.

16. The computer program product of claim 15, wherein:

said code means for maintaining at least K of the set of disks in an active state further comprises code means for maintaining at least K+1 of the set of disks in an active state; and

said computer program product further comprises code means for permitting write access to the K popular data blocks.

17. The computer program product of claim 16, and further comprising code means for biasing the at least N−

(K+1) disks in an inactive state.