Methods and structure to maintain raid configuration information on disks of the array

• US 5,822,782 A
• Filed: 10/27/1995
• Issued: 10/13/1998
• Est. Priority Date: 10/27/1995
• Status: Expired due to Term

• Current Assignee: Avago Technologies General IP PTE Limited (Broadcom, Inc.)
• Original Assignee: Symbion Incorporated (Broadcom, Inc.)
• Inventors: Kloeppner, John R., Humlicek, Donald R., Rink, Curtis W., Phillips, Grover G.
• Primary Examiner(s): Swann, Tod R.
• Assistant Examiner(s): PEIKARI, BEHZAD
• Application Number:
  US08/549,383
• Time in Patent Office: 1,082 Days
• Field of Search: 395/441, 395/497.01, 395/497.02, 395/497.03, 395/182.05, 364/DIG. 1
• US Class Current: 711/170
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 3/0626 Reducing size or complexity of storage systems
• CPC Class Codes: G06F 3/0634 by changing the state or mode of one or more devices
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

Methods and associated apparatus operable in a RAID subsystem to improve the speed and flexibility of initializing the subsystem by storing configuration and identification information in a reserved area on each disk drive in the subsystem. The reserved area on each disk drive of the disk array contains a unique identifier to identify the particular disk drive from all others and further contains group configuration information regarding all groups in which the particular disk drive is a member. The configuration and identification information is generated and written to each disk drive in the disk array when the particular disk drive is configured so as to be added or deleted from groups of the subsystem. Upon subsystem reset (e.g. power on reset or other reset operations), the RAID controller in the subsystem determines the proper configuration of the RAID groups despite temporary unavailability or physical relocation of one or more disk drives in the disk array. In addition, entire groups of disk drives may be moved from one subsystem to another and automatically recognized by the new controller when the controller is reset.

Claims

1. In a RAID storage subsystem having a plurality of disk drives configured into a plurality of groups and a controller, a method operable in said controller for detecting configuration changes in said subsystem comprising the steps of:

storing configuration information on each of said disk drives wherein said configuration information includes group configuration information corresponding to each group of said plurality of groups with which the corresponding disk drive is associated;

reading said configuration information from said disk drives; and

reconfiguring said plurality of groups of said subsystem in accordance with configuration information read from said disk drives independent of the physical location of said disk drives within said RAID subsystem.

2. The method of claim 1 wherein said configuration information includes a unique identifier to identify each of said disk drives from all other disk drives in said subsystem.

3. The method of claim 2 wherein the step of reconfiguring includes the steps of:

identifying all disk drives which are members of each group;

determining the operability of each of said identified drives; and

activating each of said groups for which all of said disk drives associated with said each of said groups are determined to be operable, wherein said activating step includes commencement of processing of I/O requests from an attached host computer system.

4. The method of claim 2 further comprising the step of activating at least one of said plurality of groups to process host computer I/O requests.

5. The method of claim 4 wherein said controller is associated with a non-volatile memory containing information identifying physical locations in said RAID subsystem which contained a disk drive and wherein the step of activating includes the step of:

activating all of said plurality of groups for which all of said disk drives associated therewith are operational and all of said disk drives associated therewith are in physical locations identified by said information in said associated memory.

6. The method of claim 4 wherein said controller is associated with a non-volatile memory containing information identifying physical locations in said RAID subsystem which contained a disk drive and wherein the step of activating includes the step of:

activating all of said plurality of groups for which all of said disk drives associated therewith are operational and some of said disk drives associated therewith are in physical locations other than those identified by said information in said associated memory.

7. The method of claim 4 wherein the step of activating includes the step of:

activating all of said plurality of groups for which at least one of said disk drives associated therewith is inaccessible.

8. The method of claim 7 further comprising the step of:

enabling a group, having at least one inaccessible disk drive, for processing of I/O requests in response to detection of all inaccessible disk drives associated with said group.

9. The method of claim 7 further comprising the step of:

disabling a group, having at least one inaccessible disk drive, from processing of I/O requests in response to receipt of an I/O request.

10. In a RAID storage subsystem having a plurality of disk drives configured into a plurality of groups and a controller, an apparatus for detecting configuration changes in said subsystem comprising:

means for storing configuration information on each of said disk drives wherein said configuration information includes group configuration information corresponding to each group of said plurality of groups with which the corresponding disk drive is associated;

means for reading said configuration information from said disk drives; and

means for reconfiguring said plurality of groups of said subsystem in accordance with configuration information read from said disk drives independent of the physical location of said disk drives within said RAID subsystem.

11. The apparatus of claim 10 wherein said configuration information includes a unique identifier to identify each of said disk drives from all other disk drives in said subsystem.

12. The apparatus of claim 11 wherein the means for reconfiguring includes:

means for identifying all disk drives which are members of each group;

means for determining the operability of each of said identified drives; and

means for activating each of said groups for which all of said disk drives associated with said each of said groups are determined to be operable, wherein said means for activating includes commencement of processing of I/O requests from an attached host computer system.

13. The apparatus of claim 11 further comprising means for activating at least one of said plurality of groups to process host computer I/O requests.

14. The apparatus of claim 13 wherein said controller is associated with a non-volatile memory containing information identifying physical locations in said RAID subsystem which contained a disk drive and wherein the means for activating includes:

means for activating all of said plurality of groups for which all of said disk drives associated therewith are operational and all of said disk drives associated therewith are in physical locations identified by said information in said associated memory.

15. The apparatus of claim 13 wherein said controller is associated with a non-volatile memory containing information identifying physical locations in said RAID subsystem which contained a disk drive and wherein the means for activating includes:

means for activating all of said plurality of groups for which all of said disk drives associated therewith are operational and some of said disk drives associated therewith are in physical locations other than those identified by said information in said associated memory.

16. The apparatus of claim 13 wherein the means for activating includes:

means for activating all of said plurality of groups for which at least one of said disk drives associated therewith is inaccessible.

17. The apparatus of claim 16 further comprising:

means for enabling a group, having at least one inaccessible disk drive, for processing of I/O requests in response to detection of all inaccessible disk drives associated with said group.

18. The apparatus of claim 16 further comprising:

means for disabling a group, having at least one inaccessible disk drive, from processing of I/O requests in response to receipt of an I/O request.