Method and apparatus for improved disk access

• US 5,088,081 A
• Filed: 03/28/1990
• Issued: 02/11/1992
• Est. Priority Date: 03/28/1990
• Status: Expired due to Term

• Current Assignee: Intel Corporation
• Original Assignee: Prime Computer, Inc. (DR Holdings, Inc. of Delaware)
• Inventors: Farr, William
• Primary Examiner(s): Envall, Jr., Roy N.
• Assistant Examiner(s): HINDI, NABIL Z
• Application Number:
  US07/500,729
• Time in Patent Office: 685 Days
• Field of Search: 371/2.2, 371/10.2, 371/10.1, 369/54, 369/58, 369/59, 360/22, 360/24, 360/27, 360/47
• US Class Current: 369/47.14
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2211/104 Metadata, i.e. metadata associated with RAID systems with parity
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0673 Single storage device
• CPC Class Codes: G11B 20/1816 Testing
• CPC Class Codes: G11B 20/1833 by adding special lists or symbols to the coded information G11B20/1806, G11B20/1866 take precedence
• 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
• CPC Class Codes: G11B 7/0037 with discs
• CPC Class Codes: G11C 29/70 Masking faults in memories by using spares or by reconfiguring

Abstract

In a RAID level 5 disk drive subsystem, one or more additional disk drives, called "reserve" disks are intercoupled to the array of disk drives and a control system is included for storing recovered digital data on the additional disk drive if a sector on one of the disk drives becomes defective. The system reduces the number of disk accesses required to obtain the information stored on the defective sector. Once the information has been recovered, it is then stored on the "reserve" disk. Thereafter, whenever this information is required, the system reads the required information from the "reserve" disk, instead of going through an entire recovery process for the defective sector. Since the recovery process can take a time that is greater than several disk access times, the present invention improves the speed and the availability of data. In another embodiment of the invention, a bitmap memory is used wherein bits in the bitmap memory representing sectors may be set to indicate whether or not sectors are defective. In a further embodiment of the invention, a disk drive tester, which can be embodied in either hardware or software, is incorporated into the apparatus for periodically testing the "reserve" disk.

Claims

1. In a system including an array of disk drives comprising a plurality of disk drives connected to and controlled by a disk system controller, said disk drives having sectors for storing information in a digital format thereon, said information including a combination of digital data and digital redundant information, the redundant information allowing recovery of the digital data if a sector storing at least a portion of the digital information on one of the disk drives is defective, the improvement comprising:

at least one additional disk drive means intercoupled to the array of disk drives; and

control means for storing recovered digital data on the at least one additional disk drive means if a sector on one of the disk drives in the plurality of disk drives is defective.

2. The system of claim 1 further comprising means for determining a defective sector.

3. The system of claim 2 wherein said at least one additional disk drive means further comprises a disk drive controller means intercoupled between said at least one additional disk drive means and said disk system controller.

4. The system of claim 1 further comprising:

a disk drive tester means intercoupled to the disk drive controller means of said at least one additional disk drive means for periodically testing a condition of at least a data storage sector on said at least one additional disk drive means.

5. The system of claim 4 wherein said disk drive tester means is implemented by computer hardware.

6. The system of claim 4 wherein said disk drive tester means is implemented by computer software.

7. The system of claim 4 further comprising means for providing a signal indicating that said at least one additional disk drive means is defective controlled by said disk drive tester means.

8. The system of claim 1 wherein said redundant array of disk drives comprises a RAID Level 5 system.

9. The system of claim 1 further comprising memory means intercoupled to said array of disk drives and to said at least one additional disk drive means, said memory means including a plurality of memory locations each corresponding respectively to a sector in the array of disk drives, each of said memory locations containing information indicating if a sector is defective.

10. The system of claim 9 wherein said memory means comprises random access memory.

11. The system of claim 9 further comprising initializing means for setting the information in each memory location to a known state wherein the known state indicates that a sector is not defective.

12. The system of claim 11 comprising additional control means for changing the state of the information in a memory location upon detection of a respective corresponding defective sector in said array of disk drives.

13. In a system including an array of disk drives comprising a plurality of disk drives connected to and controlled by a disk system controller, said disk drives having sectors for storing information in a digital format thereon, said information including a combination of digital data and digital redundant information, the redundant information allowing recovery of the digital data if a sector storing at least a portion of the digital information on one of the disk drives is defective, a method of storing data on an additional reserve disk comprising the steps of:

(a) providing at least one additional disk drive means intercoupled to the array of disk drives;

(b) determining a defective sector;

(c) recovering data stored on the defective sector; and

(d) storing the recovered data on said at least one additional disk drive means.

14. The method of claim 13 further comprising the steps of:

(a) providing at least one additional sector on a disk drive in the plurality of disk drives that comprise the array said additional sector not being located on said additional disk drive; and

(b) storing the recovered data in said additional sector instead of on said at least one additional disk drive.

15. The method of claim 14 further comprising the step of storing the recovered data on said at least one additional disk drive when said at least one additional sector has data stored therein.

16. The method of claim 13 further comprising the step of periodically testing a condition of at least a data storage sector on said at least one additional disk drive.

17. The method of claim 13 further comprising the steps of:

(a) providing a memory having a plurality of memory locations each corresponding to a sector in a array of disk drives;

(b) storing in each memory location information indicating the status of the corresponding sector; and

(c) checking a corresponding memory location for the status of the corresponding sector prior to accessing said sector.

18. An apparatus for storing digital data comprising:

(a) a plurality of digital data storage means comprising data storage sectors;

(b) means for detecting a defect in the data storage means wherein the detecting means detects defects in the data storage sectors;

(c) means responsive to the detecting means for recovering the data stored in the defective data storage means;

(d) means responsive to the recovering means for storing the recovered data on one of the data storage means different from the defective data storage means.

19. The apparatus of claim 18 wherein the means for storing the recovered data stores the recovered data in a sector on a separate data storage means.