Data storage organization for distributed computing in an intelligent disk drive

• US 7,325,095 B2
• Filed: 02/28/2005
• Issued: 01/29/2008
• Est. Priority Date: 02/28/2005
• Status: Expired due to Fees

• Current Assignee: Western Digital Technologies Incorporated (Western Digital Corporation)
• Original Assignee: Hitachi Global Storage Technologies Netherlands BV (Western Digital Corporation)
• Inventors: Williams, Larry Lynn
• Primary Examiner(s): Bragdon; Reginald
• Assistant Examiner(s): Namazi; Mehdi
• Application Number:
  US11/069,285
• Publication Number:
  US 20060193074A1
• Time in Patent Office: 1,065 Days
• Field of Search: None
• US Class Current: 711/112
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0676 Magnetic disk device

Abstract

An intelligent disk drive is described which includes means for executing distributed computing tasks including a CPU and associated memory. The communication interface with the host computer is modified to allow the host computer to send executable code for a task to the drive and to allow the drive to communicate the results and status information about the task to the host computer. A method of organizing data for distributed processing in the intelligent disk drive is described which utilizes physical placement of the data around the rotating disk to optimize the execution of the task. In one embodiment head switching is used as further optimization in a disk drive having a plurality of heads to implement alternatives in the task program. In another embodiment, the intelligent disk drive has means for reading from at least one or more heads simultaneously while writing to another head.

Claims

1. A method of operating a disk drive comprising the steps of:

receiving a task definition command from a host computer which defines a task for the disk drive, the task requiring first and second alternative blocks of information during execution;

storing at least first and second alternative blocks of information at first and second physical locations on first and second disk surfaces respectively, the first and second physical locations being selected to optimize execution of the task;

executing the task to determine whether the first or the second alternative block of information is needed; and

reading the first or second alternative block of information.

2. The method of claim 1 wherein the first and second physical locations are located on first and second disk surfaces at a common angular and radial position and the step of reading the first or second alternative block of information further comprises selecting a head for the first disk surface to read the first alternative block or selecting a head for the second disk surface to read in the second alternative block.

3. The method of claim 1 wherein the task is executed as an interruptible process using the data for the task, and the method further comprises storing task status and pointers when an interrupt occurs and resuming execution of the task using the stored task status and pointers when the interrupt has been processed.

4. The method of claim 1 further comprising the steps of:

signaling the host that the task has completed;

transmitting results of the task to the host; and

resetting task status flags to indicate that no task is pending after the task has completed.

5. The method of claim 4 wherein the step of signaling further comprises means for sending a request for a diagnostic inquiry.

6. The method of claim 4 wherein the step of transmitting further comprises responding to a diagnostic inquiry from the host by sending information on the results of the task.

7. The method of claim 1 wherein the step of receiving the task definition command further comprises using a logical block identifier in the task definition command for previously written data as the source for the task.

8. The method of claim 1 wherein step of receiving a task definition command further comprises accepting the task as data in a write command which follows a diagnostic command.

9. A method of operating a disk drive comprising the steps of:

receiving a task definition command from a host computer, the task including processing a first series of units of input information sequentially stored on a first track to generate a series of units of output information; and

executing the task by repeating the steps of reading a first unit in the first series of units of input information from the first track using a first head positioned over the first track, generating a first unit of the series of units of output information and writing the first unit of the series of units of output information on a second track using a second head without moving the first head.

10. The method of claim 9 wherein the first head is attached to a first actuator and the second head is attached to a second actuator.

11. The method of claim 9 wherein the first and second heads are attached to first and second micro-actuators respectively and are attached to a common actuator.

12. The method of claim 9 wherein the step of writing the first unit of the series of units of output information occurs in parallel with the step of reading a second unit in the first series of units of input information.

13. The method of claim 9 wherein the task further includes processing a second series of units of input information in combination with the first series of units of input information and the method further comprises storing second series of units of input information on a third disk surface with corresponding units in the first and second series of units of input information being stored at a common angular position so that corresponding units in the first and second series can be read simultaneously from the first and third disk surfaces as the disks rotate.

14. The method of claim 9 wherein the task definition command includes a specification of a task program code and a specification of data for the task program.

15. The method of claim 9 wherein the task program is executed as an interruptible process using the data for the task, and the method further comprises storing task status and pointers when an interrupt occurs and resuming execution of the task program using the stored task status and pointers when the interrupt has been processed.

16. The method of claim 9 further comprising the steps of:

signaling the host that the task program has completed;

transmitting results of the task program to the host; and

resetting task status flags to indicate that no task program is pending after the task program has completed.

17. The method of claim 16 wherein the step of signaling further comprises means for sending a request for a diagnostic inquiry.

18. The method of claim 16 wherein the step of transmitting further comprises responding to a diagnostic inquiry from the host by sending information on the results of the task program.

19. The method of claim 9 wherein the step of receiving the task definition command further comprises using a logical block identifier in the task definition command for previously written data as the source for the task program.

20. The method of claim 9 wherein step of receiving a task definition command further comprises accepting the task program as data in a write command which follows a diagnostic command.

21. A disk drive comprising:

a processor and a memory for storing data and a program for the processor;

a task control program executable by the processor loaded into the memory, the task control program including means for accepting a task definition command from a host computer, the task definition command including a specification of a task program of code executable by the processor and a specification of data for the task program;

means for executing the task program as an interruptible process using the data for the task, the means for executing the task program including means for storing task status and pointers when an interrupt occurs and resuming execution of the task program when an interrupt has been processed;

means for storing at least first and second alternative blocks of information on first and second disk surfaces, the first and second alternative blocks being stored at a common angular position;

means for executing the task to determine whether the first or the second alternative block of information is needed;

means for selecting a head for the first disk surface to read the first alternative block or selecting a head for the second disk surface to read in the second alternative block based on the step of executing the task; and

means for signaling the host that the task program has completed.

22. The disk drive of claim 21 wherein means for accepting a task definition command further comprises means for accepting the task program as data in a write command which follows a diagnostic command.

23. The disk drive of claim 21 wherein the means for signaling further comprises means for sending a request for a diagnostic inquiry.

24. The disk drive of claim 21 wherein the means for accepting a task definition command further comprises means for using a logical block identifier for previously written data as the source for the task program.

25. A disk drive comprising:

a processor and a memory for storing data and a program for the processor;

a task control program executable by the processor loaded into the memory, the task control program including means for accepting a task definition command from a host computer, the task definition command including a specification of a task program of code executable by the processor and a specification of data for the task program;

means for executing the task program as an interruptible process using the data for the task, the means for executing the task program including means for storing task status and pointers when an interrupt occurs and resuming execution of the task program when an interrupt has been processed;

means for executing the task by repeating the steps of reading a first unit in the first series of units of input information from the first track using a first head positioned over the first track, generating a first unit of the series of units of output information and writing the first unit of the series of units of output information on a second track using a second head without moving the first head; and

means for signaling the host that the task program has completed.

26. The disk drive of claim 25 further comprising first and second actuators and wherein the first head is attached to a first actuator and the second head is attached to a second actuator.

27. The disk drive of claim 25 further comprising first and second micro-actuators and wherein the first and second heads are attached to first and second respectively and are attached to a common actuator.

28. The disk drive of claim 25 wherein means for accepting a task definition command further comprises means for accepting the task program as data in a write command which follows a diagnostic command.

29. The disk drive of claim 25 wherein the means for signaling further comprises means for sending a request for a diagnostic inquiry.

30. The disk drive of claim 25 wherein the means for accepting a task definition command further comprises means for using a logical block identifier for previously written data as the source for the task program.