Multiple disk, variable RPM data storage system for reducing power consumption

• US 20050204097A1
• Filed: 03/11/2004
• Published: 09/15/2005
• Est. Priority Date: 03/11/2004
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Rajamony, Ramakrishnan, Kistler, Michael David
• Granted Patent: US 7,079,341 B2
• Time in Patent Office: Days
• US Class Current: 711/114
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 11/3485 for I/O devices
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G11B 19/28 Speed controlling, regulating, or indicating G11B19/24 takes precedence
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A data storage system includes a set of disks where each disk is operable in a plurality of discrete angular velocity levels. A disk controller controls the angular velocity of each active disk. The controller replicates a first portion of data on a plurality of the disks stores a second class of data in the set of disks without replication. The disk controller routes data requests to one of the active disks based, at least in part, on the current loading of the active disks to maintain balanced loading on the active disks. The disk controller alters the angular velocity of at least one of the active disks upon detecting that the latency of one or more of the data requests differs from a specified threshold. In this manner, the disk controller maintains the angular velocity of the active disks at approximately the same minimum angular velocity needed to attain acceptable performance. The disk controller may replicate the first portion of data on each of the disks in the set of disks. The disk controller may balance the loading on the active disks by routing an incoming request to the active disk with the least loading. The disk controller may maintain each of the active disks at approximately the same angular velocity by preventing the angular velocity of any active disk from differing from the angular velocity of any other active disk by more than one discrete level. The disk controller may recognize two or more levels of request priorities. In this embodiment, the disk controller routes requests of a first priority to an active disk in a first subset of active disks based, at least in part, on the current loading of the disks in the first subset and route requests of a second priority to an active disk in a second subset of active disks based, at least in part, on the current loading of the disks in the second subset.

Claims

1. A data storage system, including

a set of disks, each of the set of disks being operable in a plurality of discrete angular velocity levels;

a disk controller enabled to control the angular velocity of each active disk in the set of disks and configured to replicate a first portion of data on a plurality of the set of disks and to store a second class of data in the set of disks without replication; and

wherein the disk controller is configured to route requests for data in the first portion of data to one of the active disks based, at least in part, on the current loading of the active disks and wherein the disk controller is further configured to alter the angular velocity of at least one of the active disks responsive to determining that the latency associated with one or more of the data requests differs from a specified threshold.

2. The system of claim 1, wherein the disk controller is further configured to replicate the first portion of data on each of the disks in the set of disks.

3. The system of claim 1, wherein the disk controller balances the loading on the active disks by routing an incoming request to the active disk with the least loading.

4. The system of claim 3, wherein each of the disks is capable of rotating at any of a set of discrete angular velocity levels and wherein the disk controller prevents the angular velocity of any active disk from differing from the angular velocity of any other active disk by more than one discrete level.

5. The system of claim 4, wherein altering the angular velocity includes increasing the angular velocity of at least one of the active disks to the next highest discrete level if the latency is unacceptably high.

6. The system of claim 4, wherein altering the angular velocity of includes decreasing the angular velocity of at least one of the active disks to the next lowest discrete level if the latency is below a specified threshold.

7. The system of claim 1, wherein the disk controller recognizes two or more levels of request priorities and wherein the disk controller routes requests of a first priority to an active disk in a first subset of active disks based, at least in part, on the current loading of the disks in the first subset and the disk controller routes requests of a second priority to an active disk in a second subset of active disks based, at least in part, on the current loading of the disks in the second subset.

8. A disk controller computer program product including computer executable instructions, stored on a computer readable medium, for conserving power consumption in a dynamic RPM (DRPM) disk subsystem, comprising:

disk controller computer code means for replicating a first portion of data on a plurality of the set of disks and for activating two or more of the disks;

disk controller computer code means for storing a second class of data in the set of disks without replication; and

disk controller code means for maintaining the angular velocity of each of the active disks at a minimum angular velocity sufficient to attain a specified performance level.

9. The computer program product of claim 8, wherein the code means for replicate the first portion of data comprises code means for replicating the first portion of data on each of the disks in the set of disks.

10. The computer program product of claim 8, further comprising code means, responsive to a request for data on disk subsystem, for balancing the loading on the active disks by routing the request to the active disk with the least loading.

11. The computer program product of claim 10, wherein each of the disks is capable of rotating at any of a set of discrete angular velocity levels and wherein the computer program product further includes code means for preventing the angular velocity of any active disk from differing from the angular velocity of any other active disk by more than one discrete level whereby the angular velocities of all of the active disks are approximately equal.

12. The computer program product of claim 11, wherein altering the angular velocity includes increasing the angular velocity of at least one of the active disks if the latency is unacceptably high.

13. The computer program product of claim 11, wherein altering the angular velocity includes decreasing the angular velocity of at least one of the active disks if the latency is below a specified threshold.

14. The computer program product of claim 8, wherein the disk controller recognizes two or more levels of request priorities and further code means for routing requests of a first priority to an active disk in a first subset of active disks based, at least in part, on the current loading of the disks in the first subset and the disk controller routes requests of a second priority to an active disk in a second subset of active disks based, at least in part, on the current loading of the disks in the second subset.

17. The method of claim 8, further comprising, responsive to a request for data on disk subsystem, balancing the loading on the active disks by routing the request to the active disk with the least loading.

18. The method of claim 17, wherein each of the disks is capable of rotating at any of a set of discrete angular velocity levels and wherein the method further includes preventing the angular velocity of any active disk from differing from the angular velocity of any other active disk by more than one discrete level whereby the angular velocities of all of the active disks are approximately equal.

19. The method of claim 18, wherein altering the angular velocity includes increasing the angular velocity of at least one of the active disks if the latency is unacceptably high.

20. The method of claim 19, wherein altering the angular velocity of includes decreasing the angular velocity of at least one of the active disks if the latency is below a specified threshold.

15. A method for conserving power consumption in a dynamic RPM (DRPM) disk subsystem, comprising:

replicating a first portion of data on a plurality of the set of disks;

storing a second class of data in the set of disks without replication;

activating two or more of the set of disks; and

maintaining the angular velocity of each of the active disks at a minimum angular velocity sufficient to attain a specified performance level.

16. The method of claim 15, wherein replicating the first portion of data comprises replicating the first portion of data on each of the disks in the set of disks.

21. The method of claim 15, wherein the disk controller recognizes two or more levels of request priorities and further code means for routing requests of a first priority to an active disk in a first subset of active disks based, at least in part, on the current loading of the disks in the first subset and the disk controller routes requests of a second priority to an active disk in a second subset of active disks based, at least in part, on the current loading of the disks in the second subset.