JP2014093012A - Disk array controller, method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the problem that a disk device has no dedicated area, and therefore, fault analysis information is not acquired.SOLUTION: The disk array controller includes: access means for performing access to a disk array device constituted of a plurality of disk devices, all the storage capacities of which are not the same; surplus storage area calculation means for deciding a surplus storage area generated from the difference of the storage capacity of the plurality of disk devices; and read write information acquisition means for acquiring history information of the access and storing the same in the surplus storage area.

Description

  The present invention relates to a disk array controller, a method, and a program.

  In Patent Document 1, a storage area that is not included in the configuration of a RAID (Redundant Array of Inexpensive Disks) system is set as a surplus storage area, and if there is a storage device in which a failure is predicted, the storage area is stored there. A technique for copying existing data to a surplus storage area is described.

  Patent Document 2 describes a technique in which a RAID controller creates log information in response to an event such as an error and records the log information in a log recording area included in a reserved area of a disk drive.

JP 2010-160623 A JP 2005-107838 A

  When the technique of the above document is used, there is no dedicated area in the disk device, and failure analysis information cannot be acquired.

  Patent Document 1 does not describe storing data such as history information of access to a disk device in a surplus storage area, although a surplus storage area of RAID exists.

  Patent Document 2 can secure only a limited area called a reserve area. Therefore, there is no description about storing data such as access history information to the disk device in the reserved area.

  The disk array controller according to the present invention includes an access unit that accesses a disk array device including a plurality of disk devices whose storage capacities are not all the same, and a surplus storage area resulting from the difference in the storage capacities of the plurality of disk devices For each disk device, and access information acquisition means for acquiring the access history information and storing it in the excess storage area.

  According to the method of the present invention, a disk array device composed of a plurality of disk devices whose storage capacities are not all the same is accessed, and a surplus storage area resulting from the difference in the storage capacities of the plurality of disk devices is determined for each of the disk devices. The access history information is acquired and stored in the surplus storage area.

  The computer program according to the present invention includes a process for accessing a disk array device composed of a plurality of disk devices whose storage capacities are not all the same, and a surplus storage area resulting from the difference in the storage capacities of the plurality of disk devices. The computer is caused to execute processing that is determined for each disk device and processing that acquires the access history information and stores it in the surplus storage area.

  According to the present invention, failure analysis information can be acquired.

FIG. 1 shows an example of the configuration of a disk array system. FIG. 2 shows an example of the operation of the disk array controller. FIG. 3 shows an example of the surplus storage area management table. FIG. 4 is a flowchart showing an example of the operation of the disk array controller. FIG. 5 shows an example of the configuration of the disk array system according to the second embodiment. FIG. 6 is a flowchart illustrating an example of the operation of the abnormality detection unit. FIG. 7 shows an example of the configuration of the disk array controller according to the third embodiment.

  A first embodiment for carrying out the invention will be described in detail with reference to the drawings.

  In a disk array system such as RAID, an “event” indicating a typical type of failure is defined in advance, and the user can confirm whether or not “event” is registered and understand the content of the failure. There is a case. However, there are many failures in which the “event” itself is not defined. In that case, more detailed information is required for failure analysis.

  Further, in RAID, since the stored data is duplicated, parity is created, etc., the amount of data such as read / write processing to the disk increases. For this reason, when a failure occurs, the amount of data required for failure analysis also increases.

  For these reasons, in the present invention, it is useful information for identifying the cause of the failure, and obtains access history information to the disk, for example, firmware trace log, etc., in which the aforementioned “event” is not defined. To do. In the present invention, failure analysis of the disk array system 10 is facilitated by storing the acquired information in a relatively large storage area.

  FIG. 1 shows an example of the configuration of the disk array system 10.

  The disk array system 10 includes a disk array controller 20 and a disk array device 30.

  The disk array controller 20 includes an access unit 21, a surplus area calculation unit 22, a surplus area management unit 23, an access information acquisition unit 24, and a RAID information management unit 25.

The disk array device 30 is composed of a plurality of disk devices 31 whose storage capacities are not all the same. The disk array device 30 includes, for example, three units (disk device 31-A, disk device 31-B, and disk device 31-C) shown in the figure. The access unit 21 accesses the disk array device 30. (Read / write processing) is executed.

  The surplus area calculation unit 22 determines, for each disk device 31, a surplus storage area resulting from the difference between the storage capacity of the disk device 31 having the smallest storage capacity and the storage capacity of each disk device. Calculate the total of the excess storage area.

  The surplus area management unit 23 stores a surplus storage area management table for managing the surplus storage area of each disk device 31.

  The access information acquisition unit 24 acquires history information of access to the disk array device 30 and stores it in the surplus storage area of the disk device 31.

  The RAID information management unit 25 manages information related to the disk array device 30.

  Here, the disk device 31 is a storage device such as a physical disk.

  The access unit 21, the surplus area calculation unit 22, the surplus area management unit 23, the access information acquisition unit 24, and the RAID information management unit 25 are configured by hardware such as a logic circuit.

  In addition, the access unit 21, the surplus area calculation unit 22, the surplus area management unit 23, the access information acquisition unit 24, and the RAID information management unit 25 are configured so that the processor of the disk controller 20 that is a computer executes a program on a memory (not shown). It may be realized by executing.

  FIG. 2 shows an example of the operation of the disk array controller 20.

  FIG. 2 shows a case where the disk array device 30 is composed of, for example, three disk devices 31. The disk array device 30 includes a disk device 31-A, a disk device 31-B, and a disk device 31-C. For example, the disk device 31-B and the disk device are compared with the disk device 31-A. It is assumed that 31-C has a large storage capacity.

  As shown in FIG. 2, in the disk array device 30, the RAID area necessary for RAID operation uses the same storage capacity in each disk device 31 due to the characteristics of RAID. For this reason, if the storage capacities of the respective disk devices 31 are not all the same, an extra storage area always exists in addition to the RAID area.

  In the case of the configuration of FIG. 2, the disk device 31-B and the disk device 31-C include a surplus storage area. Note that the value calculated by the surplus area calculation unit 23 is used as the size of the surplus storage area.

  The access information acquisition unit 24 sequentially stores the acquired data in this surplus storage area.

  Further, the surplus area management unit 23 manages the data in the surplus storage area by using a surplus storage area management table indicating the use status of the surplus storage area, and deletes old data as appropriate.

  FIG. 3 shows an example of the surplus storage area management table.

  The surplus area management unit 23 manages the surplus storage area of the disk device 31 using the surplus storage area management table.

  When there are sufficient surplus storage areas, the surplus area management unit 23 stores the history information of access to the disk array device 30 in the surplus storage area in time series.

  Further, the surplus area management unit 23 divides the surplus storage area into a certain size, and uses the surplus storage area management table, assigns management numbers to the stored data in chronological order, and manages the data.

  As shown in FIG. 3, for example, the management number is assigned from “000001”, and when the stored data reaches a certain size, the storage at “000001” is terminated and the next number is assigned. To do. For example, numbers such as “000002” and “000003” are sequentially assigned.

  On the other hand, when the surplus storage area is insufficient, the surplus area management unit 23 deletes data from the old management number in the surplus storage area management table, and secures an area where data can be stored.

  FIG. 4 is a flowchart showing an example of the operation of the disk array controller 20. The operation of the disk array controller 20 in this embodiment will be described with reference to FIG.

  First, the surplus area calculation unit 22 calculates surplus storage areas existing in each disk device 31 (S11).

  Next, using the result of (S11), the surplus area management unit 23 creates a surplus storage area management table (S12) so that the surplus storage area of each disk device 31 can be managed.

  Next, the access unit 21 receives a request from the host computer 40 and starts access (read / write processing) to the disk array device 20 (S13).

  Corresponding to (S13), the access information acquisition unit 24 acquires access (read / write processing) history information (S14).

  Furthermore, the access information acquisition unit 24 confirms whether the history information of access (read / write processing) can be stored in the surplus storage area (S15).

  As a result, when there is no area for storing data in the surplus storage area (No in S15), the surplus area management unit 23 deletes the oldest data stored in the surplus storage area (S16).

  On the other hand, when there is an area for storing data in the surplus storage area (Yes in S15), the access information acquisition unit 24 stores access (read / write processing) history information in the surplus storage area (S17).

  The disk array system 10 according to the present embodiment has the following effects.

Failure analysis information can be acquired. The reason is that a dedicated area is added to the disk device 31.
<Second Embodiment>
FIG. 5 shows an example of the configuration of the disk array system 10 according to the second embodiment.

  In the present embodiment, an abnormality detection unit 26 is added to the configuration of the first embodiment.

  The abnormality detection unit 26 monitors the history information of access to the disk array device 30 acquired by the access information acquisition unit 24 and detects whether or not the access has been normally performed.

  Here, the abnormality detection unit 26 is configured by hardware such as a logic circuit.

  Further, the abnormality detection unit 26 may be realized by the processor of the disk controller 20 being a computer executing a program on a memory (not shown).

  FIG. 6 is a flowchart illustrating an example of the operation of the abnormality detection unit 26.

  The abnormality detection unit 26 monitors the history information of access to the disk array device 30 acquired by the access information acquisition unit 24 (S21).

  As a result, the abnormality detection unit 26 detects whether or not the access to the disk array device 30 has been normally performed from the access history information in (S21) (S22).

  The disk array system 10 according to the present embodiment has the following effects.

  It is possible to detect whether or not the access to the disk array device 30 has been normally performed.

The reason is that the abnormality detection unit 26 monitors the history information of access to the disk array device 30 acquired by the access information acquisition unit 24.
<Third embodiment>
FIG. 7 shows an example of the configuration of the disk array controller 20 according to the third embodiment.

  The disk array controller 20 of this embodiment includes an access unit 21, a surplus area calculation unit 22, and an access information acquisition unit 24.

  The access unit 21 accesses a disk array device 30 composed of a plurality of disk devices 31 whose storage capacities are not all the same.

  The surplus area calculation unit 22 determines a surplus storage area resulting from a difference in storage capacities of the plurality of disk devices 31 for each disk device 31.

  The access information acquisition unit 24 acquires access history information and stores it in a surplus storage area.

  The disk array controller 20 according to the present embodiment has the following effects.

  Failure analysis information can be acquired. The reason is that a dedicated area is added to the disk device 31.

  While the present invention has been described with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

DESCRIPTION OF SYMBOLS 10 Disk array system 20 Disk array controller 21 Access part 22 Surplus area calculation part 23 Surplus area management part 24 Access information acquisition part 25 RAID information management part 26 Abnormality detection part 30 Disk array apparatus 31 Disk apparatus 40 Host computer

Claims (10)

Access means for accessing a disk array device composed of a plurality of disk devices whose storage capacities are not all the same;
Surplus area calculation means for determining, for each disk device, a surplus storage area resulting from the difference in storage capacity of the plurality of disk devices;
A disk array controller comprising: access information acquisition means for acquiring the access history information and storing it in the surplus storage area.   2. The disk array controller according to claim 1, wherein the surplus storage area results from a difference in storage capacity between the disk device having the smallest storage capacity and each of the disk devices.   3. The disk array controller according to claim 1, further comprising an abnormality detection unit that monitors the access history information acquired by the access information acquisition unit and detects whether or not the access has been normally performed. The disk array controller according to any one of claims 1 to 3,
A disk array system comprising the plurality of disk devices whose storage capacities are not all the same. Access a disk array device composed of a plurality of disk devices whose storage capacities are not all the same,
Determining a surplus storage area resulting from the difference in storage capacity of the plurality of disk devices for each of the disk devices;
A method of obtaining the access history information and storing it in the surplus storage area. The surplus storage area results from the difference in storage capacity between the disk device with the smallest storage capacity and each of the disk devices;
The method of claim 5.   The method according to claim 5 or 6, wherein the access history information is monitored to detect whether or not the access has been normally performed. A process of accessing a disk array device composed of a plurality of disk devices whose storage capacities are not all the same;
Processing for determining, for each disk device, a surplus storage area resulting from the difference in storage capacity of the plurality of disk devices;
Processing for acquiring the access history information and storing it in the surplus storage area;
A program that causes a computer to execute. The surplus storage area results from the difference in storage capacity between the disk device with the smallest storage capacity and each of the disk devices;
The program according to claim 8. A process of monitoring the access history information;
A program for causing a computer to execute processing for detecting whether or not the access has been normally performed.

Images