Method for performing disk fault prediction operations

• US 5,761,411 A
• Filed: 08/24/1995
• Issued: 06/02/1998
• Est. Priority Date: 03/13/1995
• Status: Expired due to Term

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Compaq Computer Corporation (HP Inc.)
• Inventors: Lenny, Thomas R., Didner, Jonathan R., Bush, Kenneth L., Teague, Gaines C.
• Primary Examiner(s): Beausoliel, Jr., Robert W.
• Assistant Examiner(s): Palys, Joseph E.
• Application Number:
  US08/518,831
• Time in Patent Office: 1,013 Days
• Field of Search: 395/184.01, 395/183.18, 395/183.16, 395/185.02, 395/182.04, 395/183.01, 395/185.07, 395/182.03, 395/185.01, 371/21.1, 371/21.2, 371/21.3, 371/21.4, 371/21.5, 371/21.6, 371/51.1, 364/551.01
• US Class Current: 714/47.2
• CPC Class Codes: G06F 11/004 Error avoidance G06F11/07 and subgroups take precedence
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G11B 20/1816 Testing
• CPC Class Codes: H04L 41/00 Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A layered block device driver for accessing a storage device coupled to a computer system having a platform on which a disk fault prediction application operates. The layered block device driver includes a file system driver coupled to the computer system, at least one upper level driver coupled to the file system driver, an intermediate driver having a first coupling with the upper level driver for the exchange of messages between the intermediate driver and the upper level driver and a second coupling with the application which controls the exchange of messages between the application and the storage device, and a port driver coupled to the intermediate driver and the storage device. The intermediate driver includes an application processing routine for controlling exchanges between the application and the storage device, an upper level driver processing routine for handling exchanges between the upper level driver and the port driver, a queuing routine coupled to the application processing routine and the upper level processing routine, a flag coupled to the application processing routine and the upper level processing routine, a counter coupled to the application processing routine and the upper level processing routine and an interrupt routine coupled to the application processing routine, the upper level processing routine and the queuing routine.

Claims

1. For a computer system having a storage device coupled thereto, a platform, and a disk fault prediction ("DFP") application operating on said platform, a method of predicting an imminent failure of said storage device, comprising the steps of:

issuing, from said DFP application, at least one disk fault prediction command, to said storage device;

selecting an attribute as indicative of an imminent failure of a storage device;

monitoring said selected attribute during operation of said storage device; and

predicting an imminent failure of said storage device based upon changes in said monitored attribute, wherein said computer system is coupled to said storage device by a layered block device driver and said DFP application is coupled to said storage device by a DFP interface, an intermediate device driver is independently coupled to said DFP interface; and

wherein the step of issuing, from said DFP application, at least one disk fault prediction command, to said storage device further comprises the step of transferring said disk fault prediction command to said interface.

2. A method of predicting an imminent failure of a storage device according to claim 1 wherein said layered block device driver further comprises a file system driver coupled to said computer system and to said intermediate device driver and a port driver coupled to said intermediate device driver and said storage device and further comprising the step of issuing messages from said computer system to said storage device which are not related to disk fault prediction to said file system driver.

3. A method of predicting an imminent failure of a storage device according to claim 2 and further comprising the steps of:

selecting a threshold value for said selected attribute; and

predicting an imminent failure of said storage device upon determining that said monitored attribute crosses said selected threshold value.

4. A method of predicting an imminent failure of a storage device according to claim 3 wherein said selected attribute is a performance attribute and wherein the step of predicting an imminent failure of said storage device based upon changes in said monitored attribute further comprises the step of predicting an imminent failure of said storage device upon detecting a degradation in said performance attribute.

5. A method of predicting an imminent failure of a storage device according to claim 4 and further comprising the steps of:

selecting a threshold performance speed for said selected performance attribute; and

predicting an imminent failure of said storage device upon determining that said monitored performance attribute has a speed less than said threshold performance speed.

6. A method of predicting an imminent failure of a storage device according to claim 2 wherein said selected attribute is an error rate attribute and wherein the step of predicting an imminent failure of said storage device based upon changes in said monitored attribute further comprises the step of predicting an imminent failure of said storage device upon detecting an increase in said error rate attribute.

7. A method of predicting an imminent failure of a storage device according to claim 6 and further comprising the steps of:

selecting a threshold error rate for said selected error rate attribute; and

predicting an imminent failure of said storage device upon determining that said monitored error rate attribute has an error rate greater than said threshold error rate.

8. A method of predicting an imminent failure of a storage device according to claim 2 wherein said selected attribute is an event count attribute and wherein the step of predicting an imminent failure of said storage device based upon changes in said monitored attribute further comprises the step of predicting an imminent failure of said storage device upon detecting an increase in said event rate attribute.

9. A method of predicting an imminent failure of a storage device according to claim 8 and further comprising the steps of:

selecting a threshold event count for said selected event count attribute; and

predicting an imminent failure of said storage device upon determining that said monitored event count attribute has an event count greater than said threshold event count.

10. For a computer system having an upper level driver, a storage device coupled to said upper level driver, a platform and a DFP application operating on said platform, a method of predicting an imminent failure of said storage device, comprising the steps of:

reserving said storage device for said DFP application;

directing commands from said DFP application to said storage device;

queuing upper level driver commands while said storage device is reserved by said DFP application;

selecting an attribute as indicative of an imminent failure of said storage device;

monitoring said selected attribute during operation of said storage device; and

predicting an imminent failure of said storage device based upon changes in said monitored attribute.

11. A method of predicting an imminent failure of a storage device according to claim 10 and further comprising the steps of:

reserving said storage device for said upper level driver;

directing commands from said upper level driver to said storage device; and

queuing said DFP application commands while said storage device is reserved by said upper level driver.

12. A method of predicting an imminent failure of a storage device according to claim 11 and further comprising the steps of:

receiving interrupts from said storage device;

transferring replies from said storage device to said upper level driver if said storage device reply relates to said upper level driver command; and

transferring replies from said storage device to said DFP application if said storage device reply relates to said DFP application command.

13. A method of predicting an imminent failure of a storage device according to claim 12 and further comprising the steps of:

selecting a threshold value for said selected attribute; and

predicting an imminent failure of said storage device upon determining that said monitored attribute crosses said selected threshold value.

14. A method of predicting an imminent failure of a storage device according to claim 13 wherein said selected attribute is a performance attribute and wherein the step of predicting an imminent failure of said storage device based upon changes in said monitored attribute further comprises the step of predicting an imminent failure of said storage device upon detecting a degradation in said performance attribute.

15. A method of predicting an imminent failure of a storage device according to claim 14 and further comprising the steps of:

selecting a threshold performance speed for said selected performance attribute; and

predicting an imminent failure of said storage device upon determining that said monitored performance attribute has a speed less than said threshold performance speed.

16. A method of predicting an imminent failure of a storage device according to claim 12 wherein said selected attribute is an error rate attribute and wherein the step of predicting an imminent failure of said storage device based upon changes in said monitored attribute further comprises the step of predicting an imminent failure of said storage device upon detecting an increase in said error rate attribute.

17. A method of predicting an imminent failure of a storage device according to claim 16 and further comprising the steps of:

selecting a threshold error rate for said selected error rate attribute; and

predicting an imminent failure of said storage device upon determining that said monitored error rate attribute has an error rate greater than said threshold error rate.

18. A method of predicting an imminent failure of a storage device according to claim 12 wherein said selected attribute is an event count attribute and wherein the step of predicting an imminent failure of said storage device based upon changes in said monitored attribute further comprises the step of predicting an imminent failure of said storage device upon detecting an increase in said event rate attribute.

19. A method of predicting an imminent failure of a storage device according to claim 18 and further comprising the steps of:

selecting a threshold event count for said selected event count attribute; and

predicting an imminent failure of said storage device upon determining that said monitored event count attribute has an event count greater than said threshold event count.