Disk drive using defect list to perform uninterrupted writing of non-relocated data blocks and caching of relocated data blocks for deferred writing

• US 6,606,714 B1
• Filed: 04/17/2000
• Issued: 08/12/2003
• Est. Priority Date: 04/17/2000
• Status: Expired due to Fees

• Current Assignee: Western Digital Corporation
• Original Assignee: Western Digital Technologies Incorporated (Western Digital Corporation)
• Inventors: Thelin, Gregory B.
• Primary Examiner(s): Baderman, Scott
• Assistant Examiner(s): Damiano, Anne L.
• Application Number:
  US09/550,465
• Time in Patent Office: 1,212 Days
• Field of Search: 714/6, 714/8
• US Class Current: 714/6.13
• CPC Class Codes: G06F 12/0868 Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
• CPC Class Codes: G06F 2003/0697 device management, e.g. handlers, drivers, I/O schedulers
• CPC Class Codes: G06F 2212/461 Sector or disk block
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0676 Magnetic disk device
• CPC Class Codes: G11B 20/1883 Methods for assignment of alternate areas for defective areas
• CPC Class Codes: G11B 2220/20 Disc-shaped record carriers

Abstract

A disk drive is disclosed for receiving a write command from a host computer, the write command comprising a plurality of logical block addresses (LBAs) and a plurality of data blocks. The plurality of data blocks comprises at least one non-relocated data block (NRDB) and at least one relocated data block (RDB), and at least one of the LBAs corresponds to the NRDB and at least one of the LBAs corresponds to the RDB. The disk drive comprises a disk comprising a plurality of first disk locations each having a defect, a plurality of second disk locations for storing NRDBs, and a plurality of spare disk locations for storing RDBs. A defect list is used to map LBAs from the plurality of first disk locations to the plurality of spare disk locations. A cache is logically partitioned into a first set of memory locations managed using a first cache data structure, and a second set of memory locations managed using a second cache data structure. A disk control system uses the first cache data structure to store the NRDB in a first memory location selected from the first set of memory locations. The disk control system evaluates the defect list using the LBAs to identify the RDB and using the second cache data structure stores the RDB in a second memory location selected from the second set of memory locations. During a first time interval established for writing NRDBs, the disk control system uses the first cache data structure to write the NRDB to one of the second disk locations. During a second time interval established for writing RDBs, the disk control system uses the second cache data structure to write the RDB to one of the spare disk locations.

Claims

1. A disk drive for receiving a write command from a host computer, the write command comprising a plurality of logical block addresses (LBAs) and a plurality of data blocks, wherein:

the plurality of data blocks comprises at least one non-relocated data block (NRDB) and at least one relocated data block (RDB), and

at least one of the LBAs corresponds to the at least one NRDB and at least one of the LBAs corresponds to the at least one RDB,

the disk drive comprising;

a disk comprising;

a plurality of first disk locations each having a defect;

a plurality of second disk locations for storing NRDBs; and

a plurality of spare disk locations for storing RDBs;

a defect list for mapping LBAs from the plurality of first disk locations to the plurality of spare disk locations;

a cache logically partitioned into a first set of memory locations managed using a first cache data structure, and a second set of memory locations managed using a second cache data structure; and

a disk control system for;

using the first cache data structure to store the NRDB in a first memory location selected from the first set of memory locations;

evaluating the defect list using the LBAs to identify the RDB and using the second cache data structure to store the RDB in a second memory location selected from the second set of memory locations;

during a first time interval established for writing NRDBs, using the first cache data structure to write the NRDB to one of the second disk locations; and

during a second time interval established for writing RDBs, using the second cache data structure to write the RDB to one of the spare disk locations.

2. The disk drive as recited in claim 1, wherein:

the RDB is stored in a third memory location selected from the first set of memory locations using the first cache data structure; and

the RDB is copied from the third memory location to the second memory location using the first and second cache data structures.

3. The disk drive as recited in claim 1, wherein the first and second cache data structures are used to reassign the second memory location from the first cache data structure to the second cache data structure.

4. The disk drive as recited in claim 1, wherein the number of second set memory locations changes over time to compensate for changes to the number of LBAs mapped from the plurality of first disk locations to the plurality of spare disk locations.

5. A method of performing a write operation in a disk drive in response to a write command received from a host computer, the write command comprising a plurality of logical block addresses and a plurality of data blocks, wherein:

the plurality of data blocks comprises at least one non-relocated data block (NRDB) and at least one relocated data block (RDB), and

at least one of the LBAs corresponds to the at least one NRDB and at least one of the LBAs corresponds to the at least one RDB,

the disk drive comprising;

a disk comprising;

a plurality of first disk locations each having a defect;

a plurality of second disk locations for storing NRDBs; and

a plurality of spare disk locations for storing RDBs;

a defect list for mapping a LBAs from the plurality of first disk locations to the plurality of spare disk locations; and

a cache logically partitioned into a first set of memory locations managed using a first cache data structure, and a second set of memory locations managed using a second cache data structure,

the method of performing the write operation comprising the steps of;

using the first cache data structure to store the NRDB in a first memory location selected from the first set of memory locations;

evaluating the defect list using the LBAs to identify the RDB and using the second cache data structure to store the RDB in a second memory location selected from the second set of memory locations;

during a first time interval established for writing NRDBs, using the first cache data structure to write the NRDB to one of the second disk locations; and

during a second time interval established for writing RDBs, using the second cache data structure to write the RDB to one of the spare disk locations.

6. The method as recited in claim 5, further comprising the steps of:

storing the RDB in a third memory location selected from the first set of memory locations using the first cache data structure; and

copying the RDB from the third memory location to the second memory location using the first and second cache data structures.

7. The method as recited in claim 5, further comprising the step of using the first and second cache data structures to reassign the second memory location from the first set cache data structure to the second cache data structure.

8. The method as recited in claim 5, further comprising the step of changing the number of second set memory locations over time to compensate for changes to the number of LBAs mapped from the plurality of first disk locations to the plurality of spare disk locations.