RAID system, RAID controller and rebuilt/copy back processing method thereof

• US 20070101187A1
• Filed: 03/17/2006
• Published: 05/03/2007
• Est. Priority Date: 10/28/2005
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Konta, Yoshihito, Daikokuya, Hidejirou, Kubota, Norihide, Ito, Mikio, Takahashi, Hideo, Ikeuchi, Kazuhiko, Makino, Tsukasa, Ochi, Hiroaki, Mochizuki, Shinya, Sato, Yasutake
• Granted Patent: US 7,562,249 B2
• Time in Patent Office: Days
• US Class Current: 714/6
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1088 Reconstruction on already foreseen single or plurality of spare disks
• CPC Class Codes: G06F 11/1662 the resynchronized component or unit being a persistent storage device re-synchronization of failed mirror storage G06F11/2082; rebuild or reconstruction of parity RAID storage G06F11/1008
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 2211/1059 Parity-single bit-RAID5, i.e. RAID 5 implementations

Abstract

A RAID system access a physical disk and perform Rebuild/Copy back processing according to a host I/O request, so as to implement high-speed Rebuild/Copy back processing without interfering with the processing of a normal I/O. When one disk device fails, out of a plurality of disk devices constituting a RAID configuration, the controller performs Rebuild/Copy back processing to reconstruct the RAID. In Rebuild/Copy back, the controller reads the data from one disk and writes the data to another disk, so the presence of a normal I/O is judged, and when a normal I/O is absent, read and write of these different disk drives are executed simultaneously. By this, the Rebuild/Copy back time can be decreased.

Claims

1. A RAID system for accessing a connected disk device and executing an I/O request according to the I/O request requested by a host, comprising:

a plurality of said disk devices constituting a RAID; and

a controller for executing an operation of reading data of a disk device, other than a failed disk device, when one of said plurality of disk devices failed, and writing the data to a spare disk device or a new disk device in parts for a plurality of times to execute Rebuild, or Copy back processing for reconstructing the RAID configuration,

wherein said controller judges whether a normal I/O request, including an I/O request from said host, does not arrive for a predetermined time, and executes read and write processing of said Rebuild or Copy back in parallel if said normal I/O request does not arrive for a predetermined time.

2. The RAID system according to claim 1, wherein said controller records the processing completion time of a normal I/O request each time the processing of said normal I/O request completes, and compares said processing completion time and current time to judge whether a normal I/O request does not arrive for a predetermined time.

3. The RAID system according to claim 1, wherein said controller balances and executes said normal I/O request and a request for one time of said Rebuild/Copy back, and issues a write and read request of the next Rebuild/Copy back according to the completion of parallel write and read of said Rebuild/Copy back.

4. The RAID system according to claim 1, wherein said controller further comprises a progress table for managing the progress status of said Rebuild/Copy back processing,

and said controller creates a read request for one time for Rebuild or Copy back processing according to said progress table, and updates said progress table according to the completion of the parallel write and read of said Rebuild/Copy back.

5. The RAID system according to claim 3, wherein said controller further comprises:

a RAID control module for executing a request for said Rebuild/Copy back by dividing the request into processing up to read and processing from write; and

a Rebuild/Copy back module for issuing the read request and write request of said Rebuild/Copy back processing independently to said RAID control module.

6. The RAID system according to claim 5, wherein said Rebuild/Copy back module judges the transition between the case when a normal I/O request does not arrive for a predetermined time and the case when said normal I/O request arrives within a predetermined time, and issues the read and write requests of said Rebuild or Copy back in parallel according to said judgment result.

7. The RAID system according to claim 1, wherein said controller issues a read request for one time of said Rebuild or Copy back processing when the case when said normal I/O request arrives within a predetermined time transits to the case when said normal I/O request does not arrive for a predetermined time, and issues read and write requests for said Rebuild or Copy back in parallel when the processing of said read request completes.

8. The RAID system according to claim 1, wherein when one of said plurality of disk devices constituting said RAID fails, said controller executes an operation of reading data of a disk device, other than the failed disk device, and writing the data to a spare disk device in parts for a plurality of times,

and after executing the Rebuild processing for reconstructing the RAID configuration, said controller executes an operation of reading the data in said spare disk device and writing the data to a new disk device provided in place of said failed disk device, in parts for a plurality of times, so as to execute Copy back processing.

9. A RAID controller for accessing a connected disk device and executing an I/O request according to the I/O request requested by a host, comprising:

a first interface circuit for controlling interface with said host;

a second interface circuit for controlling interface with said plurality of disk devices constituting the RAID; and

a controller for executing an operation of reading data of a disk device, other than a failed disk device, when one of said plurality of disk devices fails, and writing the data to a spare disk device or a new disk device in parts for a plurality of times, and executing Rebuild or Copy back processing for reconstructing the RAID configuration,

wherein said controller judges whether a normal I/O request, including an I/O request from said host, does not arrive for a predetermined time, and executes read and write processing of said Rebuild or Copy back in parallel if a normal I/O request does not arrive for a predetermined time.

10. The RAID controller according to claim 9, wherein said controller records the processing completion time of a normal I/O request each time the processing of said normal I/O request completes, and compares said processing completion time and current time to judge whether a normal I/O request does not arrive for a predetermined time.

11. The RAID controller according to claim 9, wherein said controller balances and executes said normal I/O request and a request for one time of said Rebuild/Copy back, and issues a write and read request of the next Rebuild/Copy back according to the completion of parallel write and read of said Rebuild/Copy back.

12. The RAID controller according to claim 9, wherein said controller further comprises a progress table for managing the progress status of said Rebuild/Copy back processing,

and said controller creates a read request for one time for Rebuild or Copy back processing according to said progress table, and updates said progress table according to the completion of the parallel write and read of said Rebuild/Copy back.

13. The RAID controller according to claim 11, wherein said controller further comprises:

a RAID control module for executing a request for said Rebuild/Copy back by dividing the request into processing up to read and processing from write; and

a Rebuild/Copy back module for issuing the read request and write request of said Rebuild/Copy back processing independently to said RAID control module.

14. The RAID controller according to claim 13, wherein said Rebuild/Copy back module judges the transition between the case when a normal I/O request does not arrive for a predetermined time and the case when said normal I/O request arrives within a predetermined time, and issues the read and write requests of said Rebuild or Copy back in parallel according to said judgment result.

15. The RAID controller according to claim 9, wherein said controller issues a read request for one time of said Rebuild or Copy back processing when the case when said normal I/O request arrives within a predetermined time transits to the case when said normal I/O request does not arrive for a predetermined time, and issues read and write requests for said Rebuild or Copy back in parallel when the processing of said read request completes.

16. The RAID controller according to claim 9, wherein when one of said plurality of disk devices constituting said RAID fails, said controller executes an operation of reading data of a disk device, other than the failed disk device, and writing the data to a spare disk device in parts for a plurality of times,

and after executing the Rebuild processing for reconstructing the RAID configuration, said controller executes an operation of reading the data in said spare disk device and writing the data to a new disk device provided in place of said failed disk device, in parts for a plurality of times, so as to execute Copy back processing.

17. A Rebuild/Copy back processing method for a RAID system which accesses a connected disk device and executes an I/O request according to the I/O request requested by a host, comprising the steps of:

processing Rebuild/Copy back for executing an operation of reading data of a disk device, other than a failed disk device, when one of said plurality of disk devices constituting said RAID fails, and writing the data to a spare disk device or a new disk device in part for a plurality of times to execute Rebuild or Copy back processing for reconstructing the RAID configuration;

judging whether a normal I/O request, including an I/O request from said host, does not arrive for a predetermined time; and

executing read and write processing of said Rebuild or Copy back in parallel if said normal I/O request does not arrive for a predetermined time.

18. The Rebuild/Copy back processing method for a RAID system according to claim 17, wherein said judgment step further comprises:

a step of recording the processing completion time of a normal I/O request each time the processing of said normal I/O request completes; and

a step of comparing said processing completion time and current time to judge whether a normal I/O request does not arrive for a predetermined time.

19. The Rebuild/Copy back processing method for a RAID system according to claim 18, further comprising a step of balancing and executing said normal I/O request and request for one time of said Rebuild and Copy back,

wherein said parallel processing step further comprises a step of issuing a write and read request of the next Rebuild/Copy back according to completion of the parallel write and read of said Rebuild/Copy back.

20. The Rebuild/Copy back processing method for a RAID system according to claim 18, further comprising:

a step of creating a read request for one time for Rebuild and Copy back processing according to a progress table for managing the progress status of said Rebuild/Copy back processing; and

a step of updating said progress table according to completion of the parallel write and read of said Rebuild/Copy back.