Disk drive steering write data to write cache based on workload

• US 8,959,284 B1
• Filed: 06/28/2010
• Issued: 02/17/2015
• Est. Priority Date: 06/28/2010
• Status: Active Grant

• Current Assignee: Western Digital Technologies Incorporated (Western Digital Corporation)
• Original Assignee: Western Digital Technologies Incorporated (Western Digital Corporation)
• Inventors: Boyle, William B., Meyer, Alan T., Syu, Mei-Man L.
• Primary Examiner(s): Shah, Sanjiv
• Assistant Examiner(s): Gossage, Glenn
• Application Number:
  US12/824,959
• Time in Patent Office: 1,695 Days
• Field of Search: 711/113
• US Class Current: 711/113
• CPC Class Codes: G06F 12/0804 with main memory updating G06F12/0806 takes precedence
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 2212/222 Non-volatile memory
• CPC Class Codes: G06F 2212/224 Disk storage
• CPC Class Codes: G11B 5/012 Recording on, or reproducing or erasing from, magnetic disks G11B17/00, G11B19/00 take precedence

Abstract

A disk drive is disclosed comprising a non-volatile write cache and a head actuated over a disk. A plurality of write commands are received from a host, wherein each write command comprises write data. A workload for a non-cache area of the disk is determined, and when the workload for the non-cache area of the disk is less than a threshold independent of a workload for the write cache, substantially all of the write data is stored in the non-cache area of the disk. When the workload for the non-cache area of the disk is greater than the threshold independent of the workload for the write cache, a first percentage of the write data is stored in the non-volatile write cache and a second percentage of the write data is stored in the non-cache area of the disk, wherein the first percentage is proportional to the workload for the non-cache area of the disk.

Claims

1. A disk drive comprising:

a non-volatile write cache;

a disk;

a head actuated over the disk; and

control circuitry operable to;

receive a plurality of write commands from a host, wherein each write command comprises write data;

determine a workload for a non-cache area of the disk independent of a sequentiality of the write commands;

when the workload for the non-cache area of the disk is less than a threshold independent of a workload for the write cache, store substantially all of the write data in the non-cache area of the disk; and

when the workload for the non-cache area of the disk is greater than the threshold independent of the workload for the write cache, store a first percentage of the write data in the non-volatile write cache and a second percentage of the write data in the non-cache area of the disk, wherein the first percentage is proportional to the workload for the non-cache area of the disk.

2. The disk drive as recited in claim 1, wherein the non-volatile write cache comprises a non-volatile semiconductor memory.

3. The disk drive as recited in claim 1, wherein the non-volatile write cache comprises part of the disk.

4. The disk drive as recited in claim 1, wherein the control circuitry is further operable to:

store the plurality of write commands in a command queue; and

determine the workload for the non-cache area of the disk based on a number of commands stored in the command queue.

5. The disk drive as recited in claim 1, wherein the control circuitry is further operable to determine the workload based on a frequency of the write commands received from the host.

6. The disk drive as recited in claim 1, wherein the control circuitry is further operable to:

store the plurality of write commands in a disk command queue; and

determine the workload based on a rotational position optimization (RPO) algorithm for selecting the write commands from the disk command queue based at least on a radial location of the head.

7. The disk drive as recited in claim 1, wherein the control circuitry is further operable to:

maintain a plurality of access patterns of the write commands received from the host; and

determine the workload based on the access patterns.

8. The disk drive as recited in claim 1, wherein the control circuitry is further operable to:

receive a command load message from the host; and

determine the workload based on the command load message.

9. The disk drive as recited in claim 1, wherein the first and second percentages are further based on an amount of free space in the non-volatile write cache.

10. The disk drive as recited in claim 1, wherein the first and second percentages are further based on a percentage of life remaining for the non-volatile write cache.

11. The disk drive as recited in claim 1, wherein the control circuitry is further operable to flush the write data from the non-volatile write cache to the non-cache area of the disk during an idle mode.

12. The disk drive as recited in claim 1, wherein the control circuitry is further operable to:

execute the write commands based on a rotational position optimization (RPO) algorithm for the disk; and

select the write data to be stored in the non-volatile write cache in response to the RPO algorithm.

13. The disk drive as recited in claim 1, wherein the control circuitry is further operable to select the write data to be stored in the non-volatile write cache in response to a time-out limit assigned to each write command.

14. A method of operating a disk drive, the disk drive comprising a head actuated over a disk and a non-volatile write cache, the method comprising:

receiving a plurality of write commands from a host, wherein each write command comprises write data;

determining a workload for a non-cache area of the disk independent of a sequentiality of the write commands;

when the workload for the non-cache area of the disk is less than a threshold independent of a workload for the write cache, store substantially all of the write data in the non-cache area of the disk; and

when the workload for the non-cache area of the disk is greater than the threshold independent of the workload for the write cache, storing a first percentage of the write data in the non-volatile write cache and a second percentage of the write data in the non-cache area of the disk, wherein the first percentage is proportional to the workload for the non-cache area of the disk.

15. The method as recited in claim 14, wherein the non-volatile write cache comprises a non-volatile semiconductor memory.

16. The method as recited in claim 14, wherein the non-volatile write cache comprises part of the disk.

17. The method as recited in claim 14, further comprising:

storing the plurality of write commands in a command queue; and

determining the workload for the non-cache area of the disk based on a number of commands stored in the command queue.

18. The method as recited in claim 14, further comprising determining the workload based on a frequency of the write commands received from the host.

19. The method as recited in claim 14, further comprising:

storing the plurality of write commands in a disk command queue; and

determining the workload based on a rotational position optimization (RPO) algorithm for selecting the write commands from the disk command queue based at least on a radial location of the head.

20. The method as recited in claim 14, further comprising:

maintaining a plurality of access patterns of the write commands received from the host; and

determining the workload based on the access patterns.

21. The method as recited in claim 14, further comprising:

receiving a command load message from the host; and

determining the workload based on the command load message.

22. The method as recited in claim 14, wherein the first and second percentages are further based on an amount of free space in the non-volatile write cache.

23. The method as recited in claim 14, wherein the first and second percentages are further based on a percentage of life remaining for the non-volatile write cache.

24. The method as recited in claim 14, further comprising flushing the write data from the non-volatile write cache to the non-cache area of the disk during an idle mode.

25. The method as recited in claim 14, further comprising:

executing the write commands based on a rotational position optimization (RPO) algorithm for the disk; and

selecting the write data to be stored in the non-volatile write cache in response to the RPO algorithm.

26. The method as recited in claim 14, further comprising selecting the write data to be stored in the non-volatile write cache in response to a time-out limit assigned to each write command.