Storage system, storage control device, and storage control method detecting read error response and performing retry read access to determine whether response includes an error or is valid

• US 7,590,884 B2
• Filed: 09/29/2005
• Issued: 09/15/2009
• Est. Priority Date: 06/30/2005
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Shimmitsu, Masaru, Ikeno, Masami, Noda, Yuuji, Sato, Hiroaki, Konta, Yoshihito, Yoshiya, Yukihiro, Daikokuya, Hidejirou, Kubota, Norihide, Hirano, Tadashi, Ito, Mikio, Takahashi, Hideo, Ikeuchi, Kazuhiko, Nakagami, Tsuyoshi, Kikuchi, Nobuyuki, Toshine, Naoyoshi, Inai, Yusuke, Takahashi, Eisaku, Sato, Yasutake
• Primary Examiner(s): Baderman; Scott T
• Assistant Examiner(s): SCHELL, JOSEPH O
• Application Number:
  US11/237,662
• Publication Number:
  US 20070002482A1
• Time in Patent Office: 1,447 Days
• Field of Search: 714 1- 57, 711/118, 711/138
• US Class Current: 714/6.13
• CPC Class Codes: G06F 11/1435 using file system or storage system metadata
• CPC Class Codes: G06F 11/1612 where the redundant component is persistent storage
• CPC Class Codes: G06F 11/2056 by mirroring
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0623 in relation to content
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G11B 20/1879 Direct read-after-write methods
• CPC Class Codes: G11B 2020/183 wherein at least one additional attempt is made to read or write the data when a first attempt is unsuccessful

Abstract

In a storage system, a disk device performs recovery and transfers read data to a control device, and the control device judges the validity of the recovery to prevent a transfer of erroneous data. A control device read-accesses a disk device, and the disk device returns read data and a recovered read error response. A control device, at the time of an initial recovered read error, performs a retry of a similar command, and if an error does not occur for read commands including the retry read command, judges the data to be valid. Uncertain data (suspect data) upon occurrence of a recovered read error is restored through disk retry, and accurate read data can be transferred to the host.

Claims

1. A storage system, comprising:

a plurality of disk devices configured as a redundant system,

a control unit which performs reading and writing of data from and to said each disk device according to requests from a higher-level apparatus, wherein said control unit comprises;

a cache memory which stores data of each said disk device; and

a processing unit which read-accesses each said disk device and receives read data and a response result from each said disk device, wherein said processing unit;

when the response to the read access of one of said disk devices is a recovered read error response, performs retry read access of same data on another of said disk devices constituting said redundant system,

discriminates whether the response from said disk device accessed by said retry read does not include an error, and judges the read data obtained from said retry read access to be valid, and

after executing said retry read access, performs read access of said one disk device with usage of the cache memory of said disk device disabled, receives read data, compares the read data with read data from said another disk device, and executes diagnostics of said one disk device.

2. The storage system according to claim 1,

wherein, when said comparison result is satisfactory, said processing unit executes replacement processing of the relevant area of said one disk device.

3. The storage system according to claim 1,

wherein, when said comparison result is not satisfactory, said processing unit executes detachment processing of said one disk device.

4. A storage system, comprising:

at least one disk device; and

a control unit which performs reading and writing of data from and to said disk devices according to requests from a higher-level apparatus,

wherein said control unit comprises;

a cache memory which stores data of said disk device; and

a processing unit which read-accesses said disk device and receives read data and a response result from said disk device, wherein said processing unit;

when the response to the read access of one of said disk devices is a recovered read error response, performs retry read access of same data on said read-accessed disk device with usage of cache memory disabled, discriminates that the response from said disk device to said retry read access does not comprise an error, and judges the read data obtained by said retry read access to be valid, and

in response to reception of a repeated recovered read error response from said retry read-accessed disk device, again performs retry read access of the same data on said read-accessed disk device with usage of cache memory disabled, discriminates that an error is not included, compares the read data with the read data obtained at the time of said recovered read error response, and executes diagnostics of said disk device.

5. The storage system according to claim 4,

wherein, when said comparison result is satisfactory, said processing unit executes replacement processing of the relevant area of said disk device, and transfers said read data to an external apparatus.

6. The storage system according to claim 4,

wherein, when said comparison result is not satisfactory, said processing unit executes replacement processing of the relevant area of said disk device, and notifies said external apparatus of an error.

7. A storage control device, which in response to a request from a higher-level apparatus performs reading and writing of data from and to at least one of a plurality of disk devices configured as a redundant system, comprising:

a cache memory which stores data of each said disk device; and

a processing unit which read-accesses said disk device, and receives read data and a response result from said disk device, wherein said processing unit;

when the response to read access of one of said disk devices is a recovered read error response, performs retry read access of same data on another of said disk devices constituting said redundant system, and

after executing said retry read access, performs read access of said one disk device with usage of the cache memory of said disk device disabled, receives read data, compares the read data with read data from said another disk device, and executes diagnostics of said one disk device.

8. The storage control device according to claim 7, wherein, when said comparison result is satisfactory, said processing unit executes replacement processing of the relevant area of said one disk device.

9. The storage control device according to claim 7, wherein, when said comparison result is not satisfactory, said processing unit executes detachment processing of said one disk device.

10. A storage control device, which in response to a request from a higher-level apparatus performs reading and writing of data from and disk devices, comprising:

a cache memory which stores data of said disk device; and

a processing unit which read-accesses said disk device, and receives read data and a response result from said disk device, wherein said processing unit;

when said response upon receiving said read data is a recovered read error response,

performs retry read access of same data on said read-accessed disk device with usage of cache memory disabled, discriminates that the response from said disk device to said retry read access does not comprise an error, and judges the read data obtained by said retry read access to be valid, and

upon reception of a repeated recovered read error response from said retry read-accessed disk device, again performs retry read access of the same data on said read-accessed disk device with usage of cache memory disabled, discriminates that an error is not included, compares the read data with the read data obtained at the time of said recovered read error, and executes diagnostics of said disk device.

11. The storage control device according to claim 10, wherein, when said comparison result is satisfactory, said processing unit executes replacement processing of the relevant area of said disk device, and transfers said read data to an external apparatus.

12. The storage control device according to claim 10, wherein, when said comparison result is not satisfactory, said processing unit executes replacement processing of the relevant area of said disk device, and notifies said external apparatus of an error.

13. A storage control method for performing reading and writing of data from and to disk devices, in response to a request from a higher-level apparatus, comprising:

read-accessing said disk device, and receiving read data and a response result from said disk device;

performing retry read access of same data on another disk device when said response upon reception of said read data is a recovered read error response; and

discriminating that the response from said disk device to said retry read access does not comprise an error, and judging the read data obtained by said retry read access to be valid, wherein said retry read access step comprises;

after execution of said retry read access, performing read access of said disk device with usage of cache memory of said disk device disabled;

receiving the read data; and

comparing the read data with the read data from said another disk device and of executing diagnostics of said disk device.

14. The storage control method according to claim 13, further comprising a step, when said comparison result is satisfactory, of executing replacement processing of the relevant area of said one disk device.

15. The storage control method according to claim 13, further comprising a step, when said comparison result is not satisfactory, of executing detachment processing of said one disk device.

16. The storage control method according to claim 13, wherein said retry read access step comprises a step, in response to said recovered read error response, of performing retry read access of the same data on said read-accessed disk device with usage of cache memory disable,

and said validity judgment step comprises:

a step of discriminating that the response from said disk device to said retry read access does not comprise an error; and

a step of judging the read data obtained by said retry read access to be valid.

17. A storage control method for performing reading and writing of data from and to disk devices, in response to a request from a higher-level apparatus, comprising:

read-accessing said disk device, and receiving read data and a response result from said disk device;

performing retry read access of the same data on said disk device when said response upon reception of said read data is a recovered read error response; and

discriminating that a response from said disk device to said retry read access does not comprise an error, and judging read data obtained by said retry read access to be valid, wherein said retry read access comprises;

in response to said recovered read error response, performing retry read access of the same data on said read-accessed disk device with usage of cache memory disable,

said validity judgment comprises;

discriminating that the response from said disk device to said retry read access does not comprise an error, and

judging the read data obtained by said retry read access to be valid;

again performing, in response to the reception of a repeated recovered read error response from said disk device of said retry read access, retry read access of the same data on said read-accessed disk device with usage of cache memory disabled;

discriminating that an error is not included, and

comparing the read data with the read data obtained at the time of said recovered read error, and of executing diagnostics of said disk device.

18. The storage control method according to claim 17, further comprising:

a step, when said comparison result is satisfactory, of executing replacement processing of the relevant area of said disk device; and

a step of transferring said read data to an external apparatus.

19. The storage control method according to claim 17, further comprising:

a step, when said comparison result is not satisfactory, of executing replacement processing of the relevant area of said disk device; and

a step of notifying said external apparatus of an error.