RAID system and rebuild/copy back processing method thereof

• US 20070088976A1
• Filed: 02/23/2006
• Published: 04/19/2007
• Est. Priority Date: 09/30/2005
• 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 7,631,218 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 2211/1059 Parity-single bit-RAID5, i.e. RAID 5 implementations

Abstract

A RAID system access a physical disk according to a host I/O request, and perform Rebuild/Copy back processing, for implementing high-speed Rebuild/Copy back processing without interrupting the processing of a normal I/O. When one disk device out of a plurality of disk devices constituting the RAID configuration fails, the processing size for one time of Rebuild/Copy back to reconstruct the RAID is changed according to the presence of a normal I/O managed in RAID control. When a normal I/O is present, Rebuild/Copy back can be executed without interrupting the processing of the normal I/O, and in a static state where a normal I/O is absent, a processing size larger than the size in that state can be specified so as to implement Rebuild/Copy back processing at high-speed.

Claims

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

a plurality of the disk devices constituting the RAID; and

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

wherein the controller judges whether a normal I/O request, including an I/O request from the host, does not arrive for a predetermined time, and when a normal I/O request does not arrive for a predetermined time, sets larger the request processing size for one time of Rebuild or Copy back processing, which is to be executed in parts for a plurality of times, compared with the size in the case when the normal I/O request arrives within the predetermined time.

2. The RAID system according to claim 1,

wherein the controller records the processing completion time of a normal I/O request each time when processing of the normal I/O request completes, and compares the processing completion time with 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 the controller executes balancing the normal I/O request and a request for one time of the Rebuild/Copy back, and issues the next Rebuild/Copy back request according to the completion of processing of the Rebuild/Copy back request.

4. The RAID system according to claim 1,

wherein the controller further comprises a progress table for managing the progress status of the Rebuild/Copy back processing,

and wherein the controller creates a request for one time of Rebuild or Copy back processing according to the progress table, and updates the progress table.

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

a RAID control module for executing balancing the normal I/O request and a request for one time of the Rebuild/Copy back; and

a Rebuild/Copy back module for referring to a progress table for managing the progress status of the Rebuild/Copy back processing, and issuing the next Rebuild/Copy back request according to the completion of processing of the Rebuild/Copy back request.

6. The RAID system according to claim 5,

wherein the RAID control module records the processing completion time of a normal I/O request each time when the processing of the normal I/O request completes, and compares the processing completion time with current time to judge whether a normal I/O request does not arrive for a predetermined time, and

the Rebuild/Copy back module inquires of the RAID control module about the judgment result, and when a normal I/O request does not arrive for a predetermined, the Rebuild/Copy back module issues the Rebuild/Copy back request by setting the request processing size for one time of the Rebuild/Copy back larger, compared with the size in the case when the normal I/O request arrives within the predetermined time.

7. The RAID system according to claim 1, wherein when a normal I/O request does not arrive for a predetermined time, the controller sets the request processing size for one time of the Rebuild or Copy back processing to be a multiple of the processing size of the case when the I/O request arrives within the predetermined time.

8. The RAID system according to claim 1, wherein the controller further comprises:

a first interface circuit for controlling interface with the host;

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

a control unit which is connected to the first interface circuit and the second interface circuit for executing the normal I/O processing and the Rebuild or Copy back processing,

and wherein the control unit judges whether a normal I/O request, including an I/O request from the host, does not arrive for a predetermined time, and when a normal I/O request does not arrive for a predetermined time, sets larger the request processing size for one time of Rebuild or Copy back processing, which is to be executed in parts for a plurality of times, compared with the size in the case when the normal I/O request arrives within the predetermined time.

9. The RAID system according to claim 1,

wherein when one of the plurality of disk devices constituting the RAID fails, the controller executes the operation to read data of a disk device, other than the failed disk device, and to write data to a spare disk device in parts for a plurality of times so as to reconstruct the RAID configuration, then executes Copy back processing by executing, in parts for a plurality of times, operation to read data of the spare disk device and to write data to a new disk device provided in place of the failed disk device.

10. The RAID system according to claim 5, wherein the control unit further comprises a cache memory for storing a part of the data of the disk device,

and wherein said control unit requests an I/O request that cannot use the cache memory, out of the I/O requests from the host, as the normal I/O.

11. A Rebuild/Copy back processing method for a RAID system for accessing a connected disk device according to an I/O request requested from a host and executing the I/O request, comprising the steps of:

executing Rebuild or Copy back processing for reconstructing the RAID configuration, when one of the plurality of disk device constituting the RAID fails, by executing in parts a plurality of times of operation to read data of a disk device, other than the failed disk device, and to write data to a spare disk device or a new disk device;

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

setting the request processing size for one time of Rebuild or Copy back processing to be executed in parts for a plurality of times larger, when a normal I/O request does not arrive for a predetermined time, compared with the size in the case when the normal I/O request arrives within the predetermined time.

12. The Rebuild/Copy back processing method for a RAID system according to claim 11, wherein the judgment step further comprises:

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

a step of comparing the processing completion time with current time to judge whether a normal I/O request arrives for a predetermined time.

13. The Rebuild/Copy back processing method for a RAID system according to claim 11, further comprising a step of executing balancing the normal I/O request and a request for one time of the Rebuild/Copy back,

wherein the step of executing the Rebuild/Copy back processing further comprises a step of issuing the next Rebuild/Copy back request according to the completion of processing of the Rebuild/Copy back request.

14. The Rebuild/Copy back processing method for a RAID system according to claim 11, wherein the step of executing the Rebuild/Copy back processing further comprises the steps of:

referring to a progress table for managing the progress status of the Rebuild/Copy back and creating a request for one time of Rebuild or Copy back processing; and

updating the progress table.

15. The Rebuild/Copy back processing method for a RAID system according to claim 11, further comprising a step of executing balancing the normal I/O request and a request for one time of the Rebuild/Copy back by a RAID control module,

wherein the processing step further comprises a step of referring to a progress table for managing the progress status of the Rebuild/Copy back processing according to the completion of processing of the Rebuild/Copy back request, and issuing the next Rebuild/Copy back request to the RAID control module.

16. The Rebuild/Copy back processing method for a RAID system according to claim 15, wherein the judgment step further comprises:

a step of, by the RAID control module, recording the processing completion time of a normal I/O request each time when the processing of the normal I/O request completes; and

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

and wherein the step of issuing the Rebuild/Copy back request further comprises;

a step of inquiring of the RAID control module about the judgment result; and

a step of issuing the Rebuild/Copy back request by setting the request processing size for one time of the Rebuild or Copy back processing larger, when a normal I/O request does not arrive for a predetermined time, compared with the size in the case when the normal I/O request arrives within the predetermined time.

17. The Rebuild/Copy back processing method for a RAID system according to claim 11, wherein the setting step further comprises a step of setting the request processing size for one time of the Rebuild or Copy back processing to be a multiple of the processing size when a normal I/O request does not arrive for a predetermined time, compared with the processing size in the case when the normal I/O request arrives within the predetermined time.

18. The Rebuild/Copy back processing method for a RAID system according to claim 11,

wherein the judgment step further comprises a step of judging whether a normal I/O request, including an I/O request from the host, does not arrive for a predetermined time by a control unit which is connected to a first interface circuit for controlling interface with the host, and a second interface circuit for controlling interface with the plurality of disk devices for executing the normal I/O processing and the Rebuild or Copy back processing, and

the setting step further comprises a step of setting the request processing size for one time of Rebuild or Copy back processing to be executed in parts for a plurality of times larger, when a normal I/O request does not arrive for a predetermined time, compared with the size in the case when the normal I/O request arrives within the predetermined time.

19. The Rebuild/Copy back processing method for a RAID system according to claim 11, wherein the step of executing the Rebuild/Copy back processing further comprises:

a Rebuild processing step of reconstructing the RAID configuration, when one of the plurality of disk devices constituting the RAID fails, by executing operation to read data of a disk device, other than the failed disk device, and to write the data to a spare disk device in parts for a plurality of times; and

a step of executing the Copy back processing after executing the Rebuild processing, by executing, in parts for a plurality of times, operation to read data of the spare disk device and to write data to a new disk device provided in place of the failed disk device.

20. The Rebuild/Copy back processing method for a RAID system according to claim 15, further comprising a step of requesting an I/O request that cannot use a cache memory, which stores a part of the data of the disk device, as the normal I/O, out of the I/O requests from the host.