Storage subsystem and method for controlling the same

• US 8,489,937 B2
• Filed: 12/06/2011
• Issued: 07/16/2013
• Est. Priority Date: 12/06/2011
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Okada, Gosuke, Yamazaki, Takashi, Motonaga, Mamoru, Shiino, Naoto, Nozawa, Takashi, Hokazono, Megumi
• Primary Examiner(s): LE, DIEU MINH T
• Application Number:
  US13/378,926
• Publication Number:
  US 20130145223A1
• Time in Patent Office: 588 Days
• Field of Search: 714/42, 714/54, 714/6.1, 714/6.11, 714/6.12, 714/6.13, 714/6.3, 714/718
• US Class Current: 714/42
• CPC Class Codes: G06F 2003/0697 device management, e.g. handlers, drivers, I/O schedulers
• CPC Class Codes: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD

Abstract

In storage subsystems, due to the significant increase in HDD capacity, the time for executing online verification is elongated, affecting accesses from the host computer. By comprehending the status of accesses to the HDD, the sections where error has occurred and the status of restoration thereof, it becomes possible to detect defective or error sections efficiently at an early stage, according to which the reliability and access performance of the storage subsystem can be improved. The present storage subsystem executes one or more of the following processes: (M1) intensive verification of a circumference of an error LBA, (M2) an area-based prioritized verification, and (M3) continuous verification performed for a long period of time to (V1) an area in which error has occurred via IO access, (V2) a highly accessed area, and (V3) during a period of time when IO access is low.

Claims

1. A storage subsystem coupled with a host computer, comprising:

a memory device configured to store data from the host computer; and

a management unit configured to manage a storage area of the memory device;

wherein the management unit is configured to execute a first verification processing performed periodically at predetermined cycles to the memory device, and to execute a second verification processing that differs from the first verification processing,

wherein the second verification processing is executed to a continuous area anterior and posterior to an error section detected by an IO access from the host computer, and the second verification processing is executed when an error is detected by the IO access.

2. The storage subsystem according to claim 1, wherein when the error is detected again using the second verification processing, after restoring the error, the second verification processing is resumed from the error restored section.

3. The storage subsystem according to claim 1, wherein when the error is detected again using the second verification processing, after restoring the error, the second verification processing is resumed from a section where the second verification processing was started.

4. The storage subsystem according to claim 1, wherein the continuous area anterior and posterior to the error section configured to execute the second verification processing is determined by one of the following values:

(L1) a constant value determined in advance by the storage subsystem;

(L2) a value allocated by the type of an HDD or SSD drive constituting a memory unit;

(L3) a value designated by a system administrator;

(L4) a variable value set via a TOV (Time Out of Verification) by the system;

(L5) a variable value set via the TOV of the HDD or the SSD drive;

(L6) a variable value set via error type; and

(L7) a variable value determined by the capacity of the HDD or the SSD drive.

5. The storage subsystem according to claim 1, wherein the second verification processing is executed to an area where an IO access frequency from the host computer is high or an area where IO access time therefrom is long.

6. The storage subsystem according to claim 5, wherein the area where the IO access frequency is high or the area where the IO access time is long is determined by a count value stored in an area-based IO access frequency table composed of an area number, a count value of the IO access number and a count value of the IO access time.

7. The storage subsystem according to claim 1, wherein the second verification processing is executed continuously for a predetermined time or for a predetermined number of areas.

8. The storage subsystem according to claim 7, wherein the continuously performed verification operation is executed for a period of time when the IO access frequency is smaller than a threshold determined in advance.

9. The storage subsystem according to claim 8, wherein when the IO access frequency exceeds the threshold determined in advance during the continuously performed verification operation, the verification operation is discontinued.

10. The storage subsystem according to claim 7, wherein the continuously performed verification operation is executed based on execution information set in advance.

11. The storage subsystem according to claim 10, wherein the execution information is composed of a day-of-week information, period of time information, and execution information composed of a verification execution time or number of execution areas.

12. The storage subsystem according to claim 1, wherein the second verification processing is composed of a verification processing of a continuous area anterior and posterior to the error section determined using the IO access from the host computer and a verification processing executed continuously for a predetermined time or to a predetermined number of areas.

13. The storage subsystem according to claim 1, wherein the second verification processing is composed of a verification processing executed to an area where an IO access frequency from the host computer is high or an area where an IO access time is long, and a verification processing executed during a period of time when the IO access frequency is low.

14. The storage subsystem according to claim 1, wherein the first and second verification processings are not executed to an area unused by the storage unit.

15. A method for controlling a storage subsystem coupled with a host computer,

the storage subsystem comprising:

a memory device configured to store data from the host computer; and

a management unit configured to manage a storage area of the memory device;

the method comprising;

executing, by the management unit, a first verification processing performed periodically at predetermined cycles to the memory device; and

executing, by the management unit, a second verification processing that differs from the first verification processing,

wherein the step of executing the second verification processing comprises executing to a continuous area anterior and posterior to an error section detected by an IO access from the host computer, and the second verification processing is executed when an error is detected by the IO access.

16. The method for controlling a storage subsystem according to claim 15, wherein the step of executing the second verification processing comprises executing to an area where an IO access frequency from the host computer is high or an area where IO access time therefrom is long.

17. The method for controlling a storage subsystem according to claim 15, wherein the second verification processing comprises executing continuously for a predetermined time or for a predetermined number of areas.

18. The method for controlling a storage subsystem according to claim 15, wherein the steps of executing the first and second verification processings are not executed to an area unused by the storage unit.