Methods and apparatus for managing error codes for storage systems coupled with external storage systems

• US 8,407,517 B2
• Filed: 04/08/2010
• Issued: 03/26/2013
• Est. Priority Date: 04/08/2010
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Hitachi, Ltd.
• Inventors: Kawaguchi, Tomohiro, Yamamoto, Akira
• Primary Examiner(s): KO, CHAE M
• Application Number:
  US12/756,475
• Publication Number:
  US 20110252274A1
• Time in Patent Office: 1,083 Days
• Field of Search: 714/6.2, 714/6.24
• US Class Current: 714/6.24
• CPC Class Codes: G06F 11/006 Identification G06F11/2289 takes precedence
• CPC Class Codes: G06F 11/1004 to protect a block of data words, e.g. CRC or checksum G06F11/1076 takes precedence; security arrangements for protecting computers or computer systems against unauthorized activity G06F21/00
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/2094 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 system comprising a plurality of storage systems, which uses storage devices of multiple levels of reliability. The reliability as a whole system is increased by keeping the error code for the relatively low reliability storage disks in the relatively high reliability storage system. The error code is calculated using hash functions and the value is used to compare with the hash value of the data read from the relatively low reliability storage disks.

Claims

1. A system comprising:

a first storage system including;

a first port to receive I/O operations from host computers;

a first storage controller including a first processor and first memory; and

a plurality of first storage devices, which stores data received from said host computers, and

a second storage system including;

a second port to receive I/O operations from said host computers via said first storage controller;

a second storage controller including a second processor and second memory; and

a plurality of second storage devices, which stores data received from said host computers,

wherein error check codes corresponding to data stored in said plurality of second storage devices are stored in said first storage system,

wherein, in response to I/O operations from said host computers to read data of a virtual volume, where the data are stored in said second storage system, check codes of the data stored are calculated and compared with corresponding error check codes for the data of the virtual volume and the corresponding error check codes are stored in said first storage system, and

wherein, if the result of the comparison indicates that the check codes and corresponding error check codes match, the data stored in said second storage system are transferred to said host computers.

2. The system according to claim 1,

wherein said plurality of first storage devices have a higher reliability than said plurality of second storage devices, and

wherein said error check codes are calculated by a first storage controller and are stored in said first memory.

3. The system according to claim 1,

wherein, in response to write I/O operations from said host computers to write data to the virtual volume, where the data are to be stored in said second storage system, said data are received in said first memory via said first port, said error check codes are generated by the first storage controller for the data received, and then said data are stored to said plurality of second storage devices via said second port, and

wherein said error check codes are generated by using hash function.

4. The system according to claim 1,

wherein, if the result of the comparison indicates that the check codes and corresponding error check codes do not match, the data stored in said second storage system are recovered by said second storage controller and then transferred to said host computers via said second and first ports.

5. The system according to claim 4,

wherein the data stored in the second storage system are stored by RAID level 5 and the data are recovered by using parity bits of the corresponding striped set.

6. The system according to claim 1,

wherein, if the result of the comparison indicates that the check codes and corresponding error check codes do not match, the data stored in said second storage system are recovered by said first storage controller using parity stored in said second storage system.

7. A system comprising:

a first storage system including;

a first port to receive I/O operations from host computers;

a first storage controller including a first processor and first memory; and

a plurality of first storage devices, which stores data received from said host computers,

a second storage system including;

a second port to receive I/O operations from said host computers via said first storage controller;

a second storage controller including a second processor and second memory; and

a plurality of second storage devices, which stores data received from said host computers, and

a third storage system including;

a third port to receive I/O operations from host computers;

a third storage controller including a third processor and third memory; and

a plurality of third storage devices, which stored data received from said host computers,

wherein error check codes corresponding to data stored in said plurality of second storage devices are stored in said first storage system,

wherein error check codes corresponding to data stored in said plurality of third storage devices are stored in said first storage system,

wherein said plurality of third storage devices stores duplicate data of said plurality of second storage devices,

wherein, in response to I/O operations from said host computers to read data of a virtual volume, where the data are stored in said second storage system, check codes of the data stored are calculated and compared with corresponding error check codes for the data of the virtual volume and the corresponding error check codes are stored in said first storage system, and

wherein, if the result of the comparison indicates that the check codes and corresponding error check codes do not match, the data stored in said third storage system are transferred to said host computers via said third and first ports.

8. The system according to claim 7,

if the result of the comparison indicates that the check codes and corresponding error check codes match, the data stored in said second storage system are transferred to said host computers.

9. The system according to claim 8,

wherein in response to I/O operations from said host computers to write data to the virtual volume, where the data are to be stored in said second storage system, said data are received in said first memory via said first port, error check codes are generated by the first storage controller for the data received, and then said data are stored to said plurality of second and third storage devices, and

wherein said error check codes are generated by using hash function.

10. A method for controlling an external storage system coupled to a first storage system comprising the steps of:

receiving a write I/O operation, for writing data to a virtual volume, which is sent from a host computer to said external storage via said first storage system;

calculating error check codes of data to be written by the write I/O operation by a first storage controller of said first storage system;

storing said error check codes to said first storage system;

storing said data to be written by the write I/O operation to a volume in said external storage system;

receiving a read I/O operation, for reading the data of the virtual volume, which is sent from a host computer to said external storage system via said first storage system;

calculating check code of data subject to the read I/O operation by said first storage system;

comparing said calculated check code with the corresponding error check codes stored in said first storage system; and

transferring said data subject to the read I/O operation from said external storage system to said host computer if the result of the comparison indicates that the check codes and corresponding error check codes match.

11. The method according to claim 10, further comprising the step of:

requesting recovery data to said external storage system and calculating correct data based on the recovery data by said first storage controller if the result of the comparison indicates that the check codes and corresponding error check codes do not match.

12. The method according to claim 11, further comprising the step of:

writing the correct data to a corresponding cache slot of said first storage system.

13. The method according to claim 10, further comprising the step of:

calculating correct data by said second storage controller if the result of the comparison indicates that the check codes and corresponding error check codes do not match.

14. The method according to claim 13, further comprising the steps of:

calculating a hash value of the correct data and comparing said hash value of the correct data with the corresponding error check code stored in said first storage system;

if the hash value of the correct data and the corresponding error check code match, transferring said correct data to said host computer.

15. The method according to claim 10, further comprising the step of:

transferring data from a second storage system if the result of the comparison indicates that the check codes and corresponding error check codes do not match, wherein said second storage system stores duplicate data written to said external storage system and is coupled to said first storage system.