RAID Array Data Member Copy Offload in High Density Packaging

• US 20080189723A1
• Filed: 02/06/2007
• Published: 08/07/2008
• Est. Priority Date: 02/06/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Elliott, John C., Kubo, Robert A., Lucas, Gregg S.
• Granted Patent: US 7,673,167 B2
• Time in Patent Office: Days
• US Class Current: 719/326
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/1096 Parity calculation or recalculation after configuration or reconfiguration of the system
• CPC Class Codes: G06F 2211/1023 Different size disks, i.e. non uniform size of disks in RAID systems with parity
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

A computer-implemented method replaces a redundant array of independent disks (RAID) array member storage device configured in high density packaging. The high density packaging includes a plurality of field-replaceable units (FRUs). Each FRU has an associated plurality of storage devices. A first spare storage device of a first FRU is captured. The first FRU is dedicated as a plurality of spare storage devices by a RAID controller. A small computer system interface (SCSI) enclosure services (SES) processor (SESP) is initialized to read data from the RAID array member storage device and transfer the data to the first spare storage device. The first spare storage device and the RAID array member storage device are co-resident within a serial attached small computer system interface (SAS) expander local port domain.

Claims

1. A computer-implemented method for replacing a redundant array of independent disks (RAID) array member storage device configured in high density packaging, the high density packaging including a plurality of field-replaceable units (FRUs), each FRU having an associated plurality of storage devices, comprising:

capturing a first spare storage device of a first FRU, the first FRU dedicated as a plurality of spare storage devices by a RAID controller; and

initializing a small computer system interface (SCSI) enclosure services (SES) processor (SESP) to read data from the RAID array member storage device and transfer the data to the first spare storage device, wherein the first spare storage device and the RAID array member storage device are co-resident within a serial attached small computer system interface (SAS) expander local port domain.

2. The method of claim 1, wherein initializing a SESP to read data from the RAID array member storage device is performed by the RAID controller.

3. The method of claim 1, further including migrating remaining storage devices within a second FRU having the RAID array member storage device to the first FRU.

4. The method of claim 3, wherein migrating remaining storage devices within the second FRU further includes initializing the SESP to read and transfer data from the remaining storage devices to a plurality of spare storage devices within the first FRU.

5. The method of claim 2, wherein initializing the SESP to read data is performed in parallel with the RAID controller maintaining write updates to the first storage device and the RAID array member storage device.

6. The method of claim 1, wherein a single SESP corresponding to an independent storage device interconnect fabric is dedicated to read data from the RAID array member storage device and the first spare storage device.

7. The method of claim 1, wherein management of data on the RAID array member storage device and the first spare storage device is performed using differing RAID controllers.

8. The method of claim 1, further including dividing the RAID array member storage device into a plurality of sub-regions, informing a peer RAID controller of a first sub-region of the plurality of sub-regions, the first sub-region assigned to the SESP for transferring the data, and locking the first sub-region to prevent data contamination.

9. The method of claim 8, wherein locking the first sub-region is performed by the RAID controller.

10. A system for replacing a redundant array of independent disks (RAID) array member storage device configured in high density packaging, the high density packaging including a plurality of field-replaceable units (FRUs), each FRU having an associated plurality of storage devices, comprising:

a RAID controller for capturing a first spare storage device of a first FRU, the first FRU dedicated as a plurality of spare storage devices by a RAID controller; and

a small computer system interface (SCSI) enclosure services (SES) processor (SESP) which is initialized by the RAID controller to read data from the RAID array member storage device and transfer the data to the first spare storage device, wherein the first spare storage device and the RAID array member storage device are co-resident within a serial attached small computer system interface (SAS) expander local port domain.

11. The system of claim 10, wherein the RAID controller migrates remaining storage devices within a second FRU having the RAID array member storage device to the first FRU.

12. The system of claim 11, wherein the RAID controller directs the SESP to read and transfer data from the remaining storage devices to a plurality of spare storage devices within the first FRU.

13. The system of claim 10, wherein the RAID controller initializes the SESP to read data in parallel with maintaining write updates to the first storage device and the RAID array member storage device.

14. The system of claim 10, wherein a single SESP corresponding to an independent storage device interconnect fabric is dedicated to read data from the RAID array member storage device and the first spare storage device.

15. The system of claim 10, wherein management of data on the RAID array member storage device and the first spare storage device is performed using differing RAID controllers.

16. The system of claim 10, wherein the RAID controller divides the RAID array member storage device into a plurality of sub-regions, informs a peer RAID controller of a first sub-region of the plurality of sub-regions, the first sub-region assigned to the SESP for transferring the data, and locks the first sub-region to prevent data contamination.

17. An article of manufacture including code for replacing a redundant array of independent disks (RAID) array member storage device configured in high density packaging, the high density packaging including a plurality of field-replaceable units (FRUs), each FRU having an associated plurality of storage devices, wherein the code is capable of causing operations to be performed comprising:

capturing a first spare storage device of a first FRU, the first FRU dedicated as a plurality of spare storage devices by a RAID controller; and

initializing a small computer system interface (SCSI) enclosure services (SES) processor (SESP) to read data from the RAID array member storage device and transfer the data to the first spare storage device, wherein the first spare storage device and the RAID array member storage device are co-resident within a serial attached small computer system interface (SAS) expander local port domain.

18. The article of manufacture of claim 17, wherein initializing a SESP to read data from the RAID array member storage device is performed by the RAID controller.

19. The article of manufacture of claim 17, further including code capable of performing the operation of migrating remaining storage devices within a second FRU having the RAID array member storage device to the first FRU.

20. The article of manufacture of claim 19, wherein migrating remaining storage devices within the second FRU further includes initializing the SESP to read and transfer data from the remaining storage devices to a plurality of spare storage devices within the first FRU.