System and method for improving disk drive performance during high frequency vibration conditions

• US 7,913,108 B1
• Filed: 03/28/2006
• Issued: 03/22/2011
• Est. Priority Date: 03/28/2006
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: De Lucia, Thomas M., Ives, Stephen Richard, Garvey, Michael D., Berenson, Jeffrey R., French, F. William
• Primary Examiner(s): Chu; Gabriel L.
• Assistant Examiner(s): KO, CHAE M
• Application Number:
  US11/391,104
• Time in Patent Office: 1,820 Days
• Field of Search: 714/5, 714/24, 714/42, 714/44
• US Class Current: 714/5.1
• CPC Class Codes: G06F 11/0727 in a storage system, e.g. in a DASD or network based storage system drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097
• CPC Class Codes: G06F 11/0793 Remedial or corrective actions recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40

Abstract

Described are a system and method for improving the performance of a disk drive in a data storage system by enabling the disk drive to “ride through” events that can induce disk drive errors. In response to an error message received from a disk drive, a disk director temporarily places the disk drive into a wait state. While in the wait state, the disk drive is prevented from shutting down, despite the current error and any subsequent errors that the disk drive may experience. The disk drive may continue to service I/O requests while in the wait state, with the disk director monitoring the disk drive performance. After the disk drive exits the wait state, the disk director can determine from the monitored results whether to shut down the disk drive or to permit the disk drive to return to normal operation.

Claims

1. A method for improving performance of a disk drive in a data storage system, the method comprising:

receiving an error message from the disk drive indicative of a disk drive error that is of sufficient significance to cause the disk drive to be shut down;

placing the disk drive into a wait state that persists for, at most, a defined period in response to the error message;

deferring shutting down the disk drive while the disk drive is in the wait state; and

continuing, by the disk drive, to service I/O (input/output) requests while in the wait state, even if the disk drive issues one or more additional error messages while operating in the wait state.

2. The method of claim 1, further comprising monitoring a performance of the disk drive while the disk drive is operating in the wait state.

3. The method of claim 2, further comprising removing the disk drive from the wait state before the defined period expires when the monitored performance indicates that the disk drive is capable of servicing I/O requests successfully.

4. The method of claim 2, further comprising restoring the disk drive to normal operation after the defined period expires when the monitored performance indicates that the disk drive is capable of servicing I/O requests successfully.

5. The method of claim 2, further comprising shutting down the disk drive after the defined period expires when the monitored performance indicates that the disk drive is incapable of consistently servicing I/O requests successfully.

6. The method of claim 1, further comprising the step of determining to place the disk drive into the wait state based on a type of the error message.

7. The method of claim 1, further comprising the step of determining to place the disk drive into the wait state based on an error rate.

8. The method of claim 1, further comprising removing the disk drive from the wait state and shutting down the disk drive after the disk drive reports a number of unsuccessful I/O operations while the disk drive is operating in the wait state.

9. The method of claim 1, wherein the step of placing the disk drive into the wait state includes the steps of receiving disk drive errors from a plurality of different disk drives over a period.

10. The method of claim 9, further comprising the steps of:

determining that the disk drive errors are indicative of an event that induced the plurality of disk drives to report the disk drive errors; and

raising an alarm that records the event.

11. A data storage system comprising:

a disk director receiving an error message from a disk drive indicative of a disk drive error that is of sufficient significance to cause the disk drive to be shut down, the disk director having a processor executing program code, the program code including;

program code for placing the disk drive into a wait state that persists for, at most, a defined period in response to the error message;

program code for deferring shutting down the disk drive while the disk drive is in the wait state; and

program code for continuing, by the disk drive, to service I/O (input/output) requests while in the wait state, even if the disk drive issues one or more additional error messages while operating in the wait state.

12. The data storage system of claim 11, wherein the program code further comprises program code for monitoring a performance of the disk drive while the disk drive is in the wait state.

13. The data storage system of claim 12, further comprising program code for removing the disk drive from the wait state before the defined period expires when the monitored performance indicates that the disk drive is capable of servicing I/O requests successfully.

14. The data storage system of claim 12, further comprising program code for returning the disk drive to normal operation after the defined period expires when the monitored performance indicates that the disk drive is capable of servicing I/O requests successfully.

15. The data storage system of claim 12, further comprising program code for shutting down the disk drive after the defined period expires when the monitored performance indicates that the disk drive is incapable of consistently servicing I/O requests successfully.

16. The data storage system of claim 11, wherein the program code further comprises program code for determining to place the disk drive into the wait state based on a type of the error message.

17. The data storage system of claim 11, wherein the program code further comprises program code for determining to place the disk drive into the wait state based on an error rate.

18. The data storage system of claim 11, wherein the program code for placing the disk drive into the wait state includes program code for determining from disk drive errors received from a plurality of different disk drives over a period that the disk drive errors are indicative of an event that is inducing the errors.

19. The data storage system of claim 18, wherein the program code further comprises program code for raising an alarm that records the event that induced the plurality of disk drives to report the disk drive errors.

20. A data storage system comprising:

a disk drive;

a storage processor in communication with the disk drive, the storage processor receiving an error message from the disk drive the disk drive to be shut down, and placing the disk drive into a wait state for, at most, a predefined period in response thereto, wherein shutting down the disk drive is deferred while the disk drive is in the wait state and the disk drive continues to service I/O (input/output) requests while in the wait state, even if the disk drive issues one or more additional error messages while operating in the wait state.

21. The data storage system of claim 20, further comprising means for monitoring a performance of the disk drive while the disk drive is operating in the wait state.

22. The data storage system of claim 20, further comprising means for removing the disk drive from the wait state before the defined period expires when the monitored performance indicates that the disk drive is capable of servicing I/O requests successfully.