Disk drive array with efficient background rebuilding

• US 5,313,626 A
• Filed: 12/17/1991
• Issued: 05/17/1994
• Est. Priority Date: 12/17/1991
• Status: Expired due to Term

• Current Assignee: Dell USA LP (Dell Technologies Inc.)
• Original Assignee: Dell USA LP (Dell Technologies Inc.)
• Inventors: Overfield, Anthony L., Jones, Craig S.
• Primary Examiner(s): CHUN, DEBRA
• Application Number:
  US07/808,841
• Time in Patent Office: 882 Days
• Field of Search: 395/575, 395/425, 371/10.1, 371/21.1, 371/62
• US Class Current: 714/5.11
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• 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: G11C 29/74 using duplex memories, i.e. using dual copies
• CPC Class Codes: G11C 29/88 with partially good memories

Abstract

A disk drive array with a controller which provides: dynamic remapping for grown defects in the disk drives, multi-thread request processing with a variable number of forkings, defect tracking with both logical and physical lists, guarded writes of less than a full stripe optimized by selectably using the redundancy to limit the number of sectors involved, association of multiple operations with a single disk request in order to facilitate error handling, use of an access hiatus as indication of further opportunity to rebuild data in background, and scatter/scatter (bidirectional scatter/gather) operations.

Claims

1. A method of rebuilding a disk drive within a redundant array of disk drives, the method comprising the steps of:

a. initiating a background rebuild operation when no access requests have been received by said disk drive for at least a predetermined duration; and

interrupting said background rebuild operation before said background rebuild operation is complete if a new access request is received by said disk drive;

b. initiating a background rebuild operation when a programmable number N of access requests have been serviced since the last background rebuild operation, and continuing said background rebuild operation for at least a programmable duration; and

c. continuing steps (a) and (b) until said rebuild operation is complete.

2. The method of claim 1, wherein said programmable duration corresponds to a time duration.

3. A method of background data reconstruction on a disk drive within a drive array, the method comprising the steps of:

comparing a value corresponding to a length of a time since a last access request was received by said disk drive to a programmed threshold value;

when said corresponding value exceeds said threshold value, beginning said data reconstruction in said disk drive;

interrupting said reconstruction of step (b) upon receipt of an access request for said disk drive;

when said corresponding value fails to exceed said threshold value for a predetermined period of time T, delaying any pending access requests for said disk drive and performing said data reconstruction in said disk drive for a fixed interval.

4. A method for rebuilding a disk drive within a redundant array of inexpensive disks (RAID), the method comprising the steps of:

installing said disk drive within said RAID for access by a controller;

storing a value in said controller corresponding to a first time interval;

storing a value in said controller corresponding to a second time interval;

determining whether said disk drive has received an access request from said controller within a time period corresponding to said first time interval;

rebuilding said disk drive when an access request from said controller has not been received by said disk drive within said time period corresponding to said time interval, said continuing said rebuilding until an access request is received by said disk drive;

determining whether any rebuilding of said disk drive has occurred within a time period corresponding to said second time interval; and

rebuilding said disk drive when no rebuilding has occurred within said time period corresponding to said second time interval, and continuing said rebuilding for a predetermined amount of time.

5. The method according to claim 4 wherein said rebuilding of said disk drive comprises the steps of:

reading data on corresponding sectors of all disk drives within said RAID, except said disk drive that is being rebuilt;

performing an exclusive-or (XOR) operation on said read data and obtaining a result;

storing the result of said XOR operation on said corresponding sectors of said disk drive that is being rebuilt; and

continuing said steps of reading, performing and storing until all said corresponding sectors within said disk drive have been rebuilt.