Claims
- 1. A method for operating a storage system, the storage system including a supervising processor coupled to at least one head disk assembly ("HDA"), each HDA including an HDA controller and at least one storage medium, wherein the processor accesses the at least one HDA at selected times to exchange data therewith, said method comprising the steps of:
- a first HDA of the at least one HDA determining whether a first predetermined time has elapsed since a most recent access of the first HDA by the processor;
- if the first predetermined time has elapsed, the first HDA performing a selected predictive failure analysis ("PFA") to predict future failure of the at least one storage medium of the first HDA; and
- if the first predetermined time has not elapsed, the first HDA refraining from performing any PFA.
- 2. The method of claim 1, the at least one HDA being a single HDA.
- 3. The method of claim 1, the at least one HDA comprising multiple HDAs.
- 4. The method of claim 1, the first predetermined time comprising about 100 ms.
- 5. The method of claim 1, further comprising the steps of:
- the first HDA determining whether a second predetermined time has elapsed since a most recent performance of PFA by the first HDA; and
- if the second predetermined time has elapsed, the first HDA performing a selected PFA to predict future failure of the at least one storage medium of the first HDA.
- 6. The method of claim 1, the step of the first HDA performing a selected PFA further including the steps of identifying potential causes of the predicted future failure.
- 7. The method of claim 1, the step of the first HDA performing a selected PFA further comprising the steps of:
- in response to any access by the processor of the first HDA to exchange data therewith, aborting the first HDA's performance of the selected PFA.
- 8. A data storage medium tangibly embodying a machine-readable program of instructions, the program of instructions including method steps for operating a storage system, the storage system including a supervising processor coupled to at least one head disk assembly ("HDA"), each HDA including an HDA controller and at least one storage medium, wherein the processor accesses the at least one HDA at selected times to exchange data therewith, said method steps comprising:
- a first HDA of the at least one HDA determining whether a first predetermined time has elapsed since a most recent access of the first HDA by the processor;
- if the first predetermined time has elapsed, the first HDA performing a selected predictive failure analysis ("PFA") to predict future failure of the at least one storage medium of the first HDA; and
- if the first predetermined time has not elapsed, the first HDA refraining from performing any PFA.
- 9. The data storage medium of claim 8, the at least one HDA being a single HDA.
- 10. The data storage medium of claim 8, the at least one HDA comprising multiple HDAs.
- 11. The data storage medium of claim 8, the first predetermined time comprising about 100 ms.
- 12. The data storage medium of claim 8, the method steps further comprising:
- the first HDA determining whether a second predetermined time has elapsed since a most recent performance of PFA by the first HDA; and
- if the second predetermined time has elapsed, the first HDA performing a selected PFA to predict future failure of the at least one storage medium of the first HDA.
- 13. The data storage medium of claim 8, the step of the first HDA performing a selected PFA further including the steps of identifying potential causes of the predicted future failure.
- 14. The data storage medium of claim 8, the step of the first HDA performing a selected PFA further comprising the steps of:
- in response to any access by the processor of the first HDA to exchange data therewith, aborting the first HDA's performance of the selected PFA.
Parent Case Info
This application is a division of application Ser. No. 08/614,427, filed Mar. 12, 1996, now U.S. Pat. No. 5,717,850.
US Referenced Citations (23)
Non-Patent Literature Citations (1)
Entry |
Ng, Spencer W., et al., "Maintaining Good Performance In Disk Arrays During Failure Via Uniform Parity Group Distribution", IEEE Publications Ondisc, pp. 260-269 (Mar. 1993). |
Divisions (1)
|
Number |
Date |
Country |
Parent |
614427 |
Mar 1996 |
|