Method and system for proactive drive replacement for high availability storage systems

• US 7,373,559 B2
• Filed: 09/08/2004
• Issued: 05/13/2008
• Est. Priority Date: 09/08/2004
• Status: Active Grant

• Current Assignee: RPX Corporation
• Original Assignee: COPAN Systems, Inc. (Hewlett-Packard Enterprise Company)
• Inventors: Guha, Aloke
• Primary Examiner(s): Beausoliel, Robert
• Assistant Examiner(s): Riad, Amine
• Application Number:
  US10/937,226
• Publication Number:
  US 20050060618A1
• Time in Patent Office: 1,343 Days
• Field of Search: 360/61, 714/54, 714/47
• US Class Current: 714/54
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G06F 11/1662 the resynchronized component or unit being a persistent storage device re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G11B 19/04 Arrangements for preventing, inhibiting, or warning against double recording on the same blank or against other recording or reproducing malfunctions

Abstract

Methods for preventing the failure of disk drives in storage systems are disclosed. A system and a computer program product for preventing the failure are also disclosed. Factors relating to the aging or early onset of errors in a disk drive are monitored. These factors are then compared to thresholds. In case the thresholds are exceeded, an indication for the replacement of the disk drive is given. Sudden rises in the factors are also used to indicate the impeding failure of disk drives.

Claims

1. A method for disk drive replacement in a power-managed RAID storage system having a plurality of disk drives that are powered-on at a time before data access and are otherwise powered-off, the method comprising:

monitoring a factor relating to powering-on a particular disk drive in the plurality of disk drives;

determining a manufacturer threshold for replacement of the particular disk drive, the manufacturer threshold specified by a manufacturer of the particular disk drive for the factor;

determining a percentage threshold less than the manufacturer threshold specified by the manufacturer;

predicting a time at which the particular disk drive will fail based on the percentage threshold as applied to the factor and based on a power management characteristic of the particular disk drive;

powering on a replacement disk drive if it is powered off; and

transferring data from the particular disk drive to the replacement disk drive if the predicted time is below the percentage threshold before failure of the particular disk drive; and

using the replacement disk drive in place of the particular disk drive.

2. The method of claim 1, wherein the factors include power-on hours.

3. The method of claim 1, wherein the percentage threshold is derived from the mean-time-to-failure of the particular disk drive.

4. The method of claim 3, wherein the mean-time-to-failure is derived from a function of temperature measurement.

5. The method of claim 1, wherein the factors include start stops.

6. The method of claim 1, wherein the power management characteristic includes a predicted frequency of start stops.

7. The method of claim 1, wherein the power management characteristic includes a measured frequency of start stops.

8. The method of claim 1, wherein the power management characteristic includes a predicted frequency of power-on/off cycles.

9. The method of claim 1, wherein the power management characteristic includes a measured frequency of power-on/off cycles.

10. The method of claim 1, further comprising:

monitoring changes in a value for the factor; and

determining, after two or more consecutive calculations, that the particular drive should be replaced if the change in value for the factor increases.

11. The computer readable medium of claim 10, wherein the one or more instructions further comprise:

monitoring changes in a value for the factor; and

determining, after two or more consecutive calculations, that the particular drive should be replaced if the change in value for the factor increases.

12. An apparatus for disk drive replacement in a power-managed RAID storage system having a plurality of disk drives that are powered-on at a time before data access and are otherwise powered-off, the apparatus comprising:

a processor;

a machine-readable storage medium including instructions executable by the processor for;

monitoring a factor relating to powering-on a particular disk drive in the plurality of disk drives;

determining a manufacturer threshold for replacement of the particular disk drive, the manufacturer threshold specified by a manufacturer of the particular disk drive for the factor;

determining a percentage threshold less than the manufacturer threshold specified by the manufacturer;

predicting a time at which the particular disk drive will fail based on the percentage threshold as applied to the factor and based on a power management characteristic of the particular disk drive;

powering on a replacement disk drive if it is powered off; and

transferring data from the particular disk drive to a replacement disk drive if the predicted time is below the threshold before failure of the particular disk drive; and

using the replacement disk drive in place of the particular disk drive.

13. A machine-readable storage medium including instructions executable by a processor for preventing disk drive failures in a power-managed RAID storage system having a plurality of disk drives that are powered-on at a time before data access and are otherwise powered-off, the machine-readable storage medium comprising one or more instructions for:

monitoring a factor relating to powering-on a particular disk drive in the plurality of disk drives;

determining a manufacturer threshold for replacement of the particular disk drive, the manufacturer threshold specified by a manufacturer of the particular disk drive for the factor;

determining a percentage threshold less than the manufacturer threshold specified by the manufacturer;

predicting a time at which the particular disk drive will fail based on the percentage threshold as applied to the factor and based on a power management characteristic of the particular disk drive;

powering on a replacement disk drive if it is powered off; and

transferring data from the particular disk drive to a replacement disk drive if the predicted time is below at least one threshold before failure of the particular disk drive; and

using the replacement disk drive in place of the particular disk drive.

14. The apparatus of claim 13, wherein instructions are further executable by the processor for:

monitoring changes in a value for the factor; and

determining, after two or more consecutive calculations, that the particular drive should be replaced if the change in value for the factor increases.

15. The apparatus of claim 13, wherein the factors include power-on hours.

16. The apparatus of claim 13, wherein the percentage threshold is derived from the mean-time-to-failure of the particular disk drive.

17. The apparatus of claim 16, wherein the mean-time-to-failure is derived from a function of temperature measurement.

18. The apparatus of claim 13, wherein the factors include start stops.

19. The apparatus of claim 13, wherein the power management characteristic includes a predicted frequency of start stops.

20. The apparatus of claim 13, wherein the power management characteristic includes a measured frequency of start stops.

21. The apparatus of claim 13, wherein the power management characteristic includes a predicted frequency of power-on/off cycles.

22. The apparatus of claim 13, wherein the power management characteristic includes a measured frequency of power-on/off cycles.