Heuristic Approach for Faster Consistency Check in a Redundant Storage System

• US 20140108855A1
• Filed: 10/17/2012
• Published: 04/17/2014
• Est. Priority Date: 10/17/2012
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: LSI Corporation (Broadcom, Inc.)
• Inventors: Gopakumar, Manjusha, Goel, Ankit
• Granted Patent: US 8,904,244 B2
• Time in Patent Office: Days
• US Class Current: 714/6.2
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 2211/1071 Power loss, i.e. interrupted writes due to power loss in a RAID system

Abstract

A method for reducing an amount of time required for performing consistency checking in a redundant storage system includes steps of: providing an information repository associated with each of a primary drive and at least one redundant drive; storing, in the information repository, information relating to input/output failures on the primary drive and redundant drive; determining a likelihood that one or more regions of the primary drive and/or redundant drive contains inconsistent data as a function of the information stored in the information repository; and performing consistency checking on the one or more regions of the primary drive and the redundant drive determined to have at least a prescribed likelihood of containing inconsistent data to thereby reduce the amount of time required for performing consistency checking.

Claims

1. A method for reducing an amount of time required for performing consistency checking in a redundant storage system including a primary drive and at least one redundant drive, the method comprising steps of:

providing an information repository associated with each of the primary drive and at least one redundant drive;

storing, in said information repository, information relating to input/output failures on the primary drive and the at least one redundant drive;

determining a likelihood that one or more regions of at least one of the primary drive and the at least one redundant drive contains inconsistent data as a function of the information stored in said information repository; and

performing consistency checking on the one or more regions of at least one of the primary drive and the at least one redundant drive determined to have at least a prescribed likelihood of containing inconsistent data to thereby reduce the amount of time required for performing consistency checking.

2. The method of claim 1, wherein the step of providing an information repository comprises constructing a consistency check table for each of the primary drive and at least one redundant drive, the table including information regarding input/output failures corresponding to the primary drive and the at least one redundant drive.

3. The method of claim 2, wherein the information regarding input/output failures is based on at least one of an analysis of one or more failure events corresponding to at least one of the primary drive and the at least one redundant drive, historical failure data corresponding to at least one of the primary drive and the at least one redundant drive, failure patterns corresponding to at least one of the primary drive and the at least one redundant drive, drive performance and environmental characteristics corresponding to at least one of the primary drive and the at least one redundant drive, and reliability factors corresponding to at least one of the primary drive and the at least one redundant drive.

4. The method of claim 2, wherein the consistency check table comprises a list of sectors associated with at least one of the primary drive and the at least one redundant drive that are most likely to have inconsistent data.

5. The method of claim 2, wherein constructing the consistency check table comprises storing a location associated with a given region of at least one of the primary drive and the at least one redundant drive having at least a prescribed likelihood of having inconsistent data.

6. The method of claim 1, wherein the step of providing the information repository comprises storing the information as metadata on each of the primary drive and at least one redundant drive.

7. The method of claim 1, further comprising clearing an entry in the information repository when an associated region of at least one of the primary drive and the at least one redundant drive corresponding to the entry is successfully written.

8. The method of claim 1, wherein the step of determining the likelihood that one or more regions of at least one of the primary drive and the at least one redundant drive contains inconsistent data comprises monitoring one or more responses between a target device and an initiator device, and when a given one of the responses matches at least one entry in the information repository, initiating a prescribed action based on the given one of the responses.

9. An apparatus for reducing an amount of time required for performing consistency checking in a redundant storage system including a primary drive and at least one redundant drive, the apparatus comprising:

an information repository associated with each of the primary drive and the at least one redundant drive, the information repository being operative to store information relating to input/output failures on the primary drive and the at least one redundant drive;

a monitoring module operative to determine a likelihood that one or more regions of at least one of the primary drive and the at least one redundant drive contains inconsistent data as a function of the information stored in the information repository; and

a control module operative to perform consistency checking on the one or more regions of at least one of the primary drive and the at least one redundant drive determined to have at least the prescribed likelihood of containing inconsistent data to thereby reduce the amount of time required for performing consistency checking.

10. The apparatus of claim 9, wherein the information repository comprises a consistency check table for each of the primary drive and the at least one redundant drive, the table including information regarding input/output failures corresponding to the primary drive and the at least one redundant drive.

11. The apparatus of claim 10, further comprising an initialization module operative to construct the consistency check table and to add one or more entries to the table as a function of prescribed criteria.

12. The apparatus of claim 10, wherein the information regarding input/output failures is based on at least one of an analysis of one or more failure events corresponding to at least one of the primary drive and the at least one redundant drive, historical failure data corresponding to at least one of the primary drive and the at least one redundant drive, failure patterns corresponding to at least one of the primary drive and the at least one redundant drive, drive performance and environmental characteristics corresponding to at least one of the primary drive and the at least one redundant drive, and reliability factors corresponding to at least one of the primary drive and the at least one redundant drive.

13. The apparatus of claim 10, wherein the consistency check table comprises a list of sectors associated with at least one of the primary drive and the at least one redundant drive that are most likely to have inconsistent data.

14. The apparatus of claim 10, wherein the consistency check table comprises a location corresponding to a given region of at least one of the primary drive and the at least one redundant drive having at least a prescribed likelihood of having inconsistent data.

15. The apparatus of claim 9, wherein the information in the information repository is stored as metadata on each of the primary drive and at least one redundant drive.

16. The apparatus of claim 9, wherein the controller module is operative to clear an entry in the information repository when an associated region of at least one of the primary drive and the at least one redundant drive corresponding to the entry is successfully written.

17. The apparatus of claim 9, wherein the monitoring module is operative to monitor one or more responses between a target device and an initiator device, and when a given one of the responses matches at least one entry in the information repository, to initiate a prescribed action based on the given one of the responses.

18. The apparatus of claim 9, wherein the apparatus is fabricated in at least one integrated circuit.

19. A redundant storage system, comprising:

a primary drive;

at least one redundant drive, the at least one redundant drive being configured to mirror data stored on the primary drive;

an information repository associated with each of the primary drive and the at least one redundant drive, the information repository being operative to store information relating to input/output failures on the primary drive and at least one redundant drive;

a monitoring module operative to determine a likelihood that one or more regions of at least one of the primary drive and the at least one redundant drive contains inconsistent data as a function of the information stored in the information repository; and

a control module operative to perform consistency checking on the one or more regions of at least one of the primary drive and the at least one redundant drive determined to have at least a prescribed likelihood of containing inconsistent data to thereby reduce the amount of time required for performing consistency checking.

20. The system of claim 19, wherein the information repository comprises a consistency check table for each of the primary drive and the at least one redundant drive, the table including information regarding input/output failures corresponding to the primary drive and the at least one redundant drive.