JP2013161383A - Information processing device, information processing method, program and information processing system - Google Patents

Abstract

To provide an information processing apparatus, an information processing method, a program, and an information processing system for realizing a storage system capable of handling data with good operability on a file basis.
An information processing apparatus according to an aspect of the present technology includes an acquisition unit, a holding unit, and a transmission unit. The acquisition unit acquires a real address, which is an address on the storage area where the file is stored, of a storage device having a storage area where the file is stored at a predetermined address. The holding unit holds a virtual storage area that is a virtual storage area corresponding to a real address on the storage area and having a virtual address that is a virtual address of a file stored at the real address. In response to an access request to the virtual address on the virtual storage area, the transmission unit transmits the real address corresponding to the virtual address that is the target of the access request.
[Selection] Figure 2

Description

  The present technology relates to an information processing apparatus, an information processing method, a program, and an information processing system for realizing a storage system.

  Conventionally, a storage system having a plurality of storages connected to a network such as a SAN (Storage Area Network) is known. In such a storage system, for example, a storage virtualization technology that virtually displays a plurality of storages for a computer system that processes data is used. Patent Document 1 describes various methods related to such storage virtualization technology (see, for example, paragraphs [0007] to [0010] of Patent Document 1).

JP 2004-240803 A

  Various data are stored by the storage system as described above. In recent years, for example, data such as moving image content shot by a camera or the like is often handled on a file basis. Therefore, there is a need for a storage system that can handle such content data and the like on a file basis with good operability.

  In view of the circumstances as described above, an object of the present technology is to provide an information processing apparatus, an information processing method, a program, and an information processing system for realizing a storage system that can handle data with good operability on a file basis. There is to do.

In order to achieve the above object, an information processing apparatus according to an embodiment of the present technology includes an acquisition unit, a holding unit, and a transmission unit.
The acquisition unit acquires a real address, which is an address on the storage area where the file is stored, of a storage device having a storage area where the file is stored at a predetermined address.
The holding unit holds a virtual storage area that is a virtual storage area corresponding to a real address on the storage area and having a virtual address that is a virtual address of a file stored at the real address.
In response to an access request to the virtual address on the virtual storage area, the transmission unit transmits the real address corresponding to the virtual address that is the target of the access request.

  In this information processing apparatus, the real address of the file stored in the storage device is acquired. A virtual storage area having a virtual address corresponding to the real address is held. When there is an access request to the virtual address, a real address corresponding to the virtual address is transmitted in response to the access request. This makes it possible to make an access request using a real address to the storage device. As a result, it is possible to realize a storage system that can handle data with good operability on a file basis.

The acquisition unit may acquire a real address in each storage area of one or more storage devices. In this case, the virtual storage area may have the virtual addresses respectively corresponding to the real addresses acquired in the storage areas.
As a result, each storage area of a plurality of storage devices can be virtually seen as one. As a result, a storage system with good operability is realized.

The storage area may have a plurality of hierarchies. In this case, the real address may include information on a hierarchy in which the file is stored among the plurality of hierarchies.
This makes it possible to make an access request to the storage device based on the hierarchy information in which the file is stored.

  The virtual storage area stores a first virtual address corresponding to the first real address of the first file stored in the first storage device in a second storage device different from the first storage device. You may have in common as a 2nd virtual address corresponding to the 2nd real address of the 2nd file which is a copy of the said 1st file memorize | stored.

  For example, for the purpose of redundancy of stored files, a second file that is a copy of the first file stored in the first storage device is stored in the second storage device. In such a case, the same address may be used in common as a virtual address corresponding to each of the first and second real addresses.

The information processing apparatus may further include a first determination unit that determines whether an access request to the first virtual address is a read access or a write access. In this case, the transmission unit is one of the first and second real addresses based on the determination by the first determination unit in response to an access request to the first virtual address. May be sent.
This enables load balancing.

The information processing apparatus may further include a second determination unit that determines a load state of each of the first and second storage devices. In this case, the transmission unit is one of the first and second real addresses based on the determination by the second determination unit in response to an access request to the first virtual address. May be sent.
This enables load balancing.

An information processing method according to an aspect of the present technology acquires a real address of a storage device having a storage area where a file is stored at a predetermined address, which is an address on the storage area where the file is stored. Including.
A virtual storage area which is a virtual storage area corresponding to a real address on the storage area and having a virtual address which is a virtual address of a file stored at the real address is held.
In response to an access request to the virtual address on the virtual storage area, the real address corresponding to the virtual address targeted by the access request is transmitted.

  A program according to an embodiment of the present technology causes a computer to execute the information processing method.

An information processing system according to an embodiment of the present technology includes a storage device and an information processing device.
The storage device has a storage area in which a file is stored at a predetermined address.
The information processing apparatus includes an acquisition unit, a holding unit, and a transmission unit.
The acquisition unit acquires a real address that is an address on the storage area of the storage device where the file is stored.
The holding unit holds a virtual storage area that is a virtual storage area corresponding to a real address on the storage area and having a virtual address that is a virtual address of a file stored at the real address.
In response to an access request to the virtual address on the virtual storage area, the transmission unit transmits the real address corresponding to the virtual address that is the target of the access request.

  As described above, according to the present technology, it is possible to realize a storage system that can handle data on a file basis with high operability.

1 is a schematic diagram illustrating a configuration example of a storage system as an information processing system according to an embodiment of the present technology. It is an example of a database table held as information in a virtual storage area. It is a table which shows the mirroring setting information in a storage system. FIG. 3 is a schematic diagram illustrating an operation of a storage system when a client device opens a predetermined directory in a virtual storage area. FIG. 3 is a schematic diagram illustrating an operation of a storage system when a client device opens a predetermined file (open access execution). FIG. 3 is a schematic diagram illustrating an operation of a storage system when a client device newly creates a file. FIG. 3 is a schematic diagram showing the operation of the storage system when the client device writes data to a file. FIG. 3 is a schematic diagram illustrating an operation of a storage system when a client device performs file deletion / name change and the like. FIG. 3 is a schematic diagram illustrating an operation of a storage system that performs load balancing (load distribution) for open access from a client device. FIG. 3 is a schematic diagram illustrating an operation of a storage system when a storage device as a storage server is newly added. FIG. 3 is a schematic diagram illustrating an operation of a storage system when a storage device as a storage server is deleted from the storage system. FIG. 3 is a schematic diagram illustrating an operation of a storage system when a failure occurs in a file server. FIG. 3 is a schematic diagram illustrating an operation of a storage system when a failure occurs in a management apparatus that is a file server management server.

  Hereinafter, embodiments according to the present technology will be described with reference to the drawings.

[Storage system configuration]
FIG. 1 is a schematic diagram illustrating a configuration example of a storage system as an information processing system according to an embodiment of the present technology.

  The storage system 100 includes a first storage device 10, a second storage device 20, and a management device 30 that manages the operations of the first and second storage devices 10 and 20. The management device 30 functions as an information processing device according to the present embodiment. The number of storage devices included in the storage system 100 is not limited.

  Hereinafter, a storage device included in the storage system 100 may be referred to as a storage server. The management device 30 may be described as a file server management server.

  The first and second storage devices 10 and 20 and the management device 30 are connected to each other through a network 40. As the network 40, for example, a local area network (LAN), a wide area network (WAN), or the like is used. The type of network 40 and the protocol used for it are not limited. For example, a configuration in which the first storage device 10 and the management device 30 are connected by a LAN, and these and the second storage device 20 are connected by a WAN is also possible.

  The first and second storage devices 10 and 20 have storage devices (not shown) that store files such as moving image content, respectively. As the storage device, for example, an SSD (Solid State Drive), a RAID device in which a plurality of disks are bundled by a RAID (Redundant Arrays of Inexpensive Disks) technique, or the like is used. Alternatively, a disk in which disks are bundled by an iSCSI (Internet Small Computer System Interface) initiator may be used. Alternatively, a storage device using an HDD (Hard Disk Drive) or a tape may be used. Various other storage devices may be used.

  These storage devices may be incorporated in the first and second storage devices 10 and 20. Alternatively, the first and second storage devices 10 and 20 may be connected as external storage devices through a network or the like. As each storage device, a device constituting a cluster storage may be used.

  A storage area is formed in each of the first and second storage devices 10 and 20 by the storage device included in each of the first and second storage devices 10 and 20. In the present embodiment, the storage area has a directory structure having a plurality of hierarchies. Files such as moving image contents are stored in a predetermined directory in the storage area.

  A file stored in a predetermined directory is represented by a real address which is an address on a storage area. Typically, the real address is a path (see real path name in FIG. 2). Hereinafter, a path as a real address of each storage area of the first and second storage devices 10 and 20 is referred to as a real file path.

  The notation of the actual file path is not limited. A real address other than a path may be used as the real address of each storage area.

  The management apparatus 30 also includes a nonvolatile storage device that includes, for example, an HDD, a flash memory, and other solid-state memory.

  As the first and second storage devices 10 and 20 and the management device 30, for example, computers such as PCs (Personal Computers) are used. Information processing by each device is realized by cooperation of software such as a ROM (Read Only Member) stored in a computer and hardware resources such as a PC. More specifically, a CPU (Central Processing Unit) is executed by loading a program constituting software stored in a ROM or the like into a RAM (Random Access Memory) and executing it.

  That is, the functional blocks and modules of each device shown in FIG. 1 are realized by the CPU or the like operating based on a program. The program is installed in each device via a recording medium, for example. Alternatively, it may be installed via a global network or the like. Note that hardware may be provided as appropriate to implement each block or module.

  Various file accesses are performed on the storage system 100 according to the present embodiment by an external device (host) connected through the network 40. Examples of the external device include an output device that outputs material data such as video data and audio data to the storage system 100 as a file. There is also an editing apparatus that reads a predetermined file from the storage system 100 and executes an editing process or the like. In addition, various client devices 50 that handle files can be cited as external devices.

  Examples of file access include various accesses such as opening a file (including creation of a file), writing data to the file, reading data from the file, changing the metadata of the file, and closing the file. The type of file access is not limited.

  In the present embodiment, write access for writing data to a file is defined including open access for opening the file. That is, the write access means an access for writing data to a file opened by the open access with the write attribute. Also, read access to read data written to a file is defined including open access to open the file. That is, the read access means an access for reading data from a file opened by the read attribute open access.

  Therefore, the determination of the open access attribute is included in the determination of whether the file access is a read access or a write access.

  In this embodiment, the entire storage system 100 is recognized as one storage from the client device 50 by using a virtual environment or the like.

  As illustrated in FIG. 1, the management apparatus 30 includes a file access reception module 31, a file access response module 32, and a file management module 33. The management apparatus 30 includes a file server management module 34, a file server failure detection module 35, and a mirror management module 36.

  The file management module 33 creates a virtual volume for making each storage area of the first and second storage devices 10 and 20 virtually appear as one. The virtual volume is a virtual storage area for files stored in the storage areas of the first and second storage devices 10 and 20.

  The file management module 33 acquires actual file paths on the storage areas of the first and second storage devices 10 and 20. A virtual address corresponding to the actual file path acquired in each storage area of the first and second storage devices 10 and 20 is set. The virtual address is a virtual address of a file stored in the actual file path in each storage area.

  In the present embodiment, the virtual storage area has a directory structure having a plurality of hierarchies. Therefore, files such as moving image content are virtually stored in a predetermined directory in the virtual storage area.

  A file stored in a virtual directory is typically represented by a path (see the virtual path name in FIG. 2). Hereinafter, a path as a virtual address is referred to as a virtual file path. The notation of the virtual file path is not limited. A virtual address other than the path may be used.

  The virtual storage area is provided to the client device 50. The client device 50 recognizes (for example, mounts) and manages the virtual storage area using a predetermined application, for example. The client device 50 executes various file accesses to files virtually stored in the virtual storage area using the virtual file path that the virtual storage area has.

  Execution of file access using a virtual file path by a client device means an access request to a virtual address in a virtual storage area in the present embodiment.

  As described above, in the present embodiment, the file management module 33 acquires actual file paths on the storage areas of the first and second storage devices 10 and 20. As shown in the real path name of FIG. 2, the real file path includes information on a predetermined hierarchy in which the file is stored.

  A virtual file path is set corresponding to the acquired real file path. A virtual storage area having a directory structure having such a virtual file path is created. The virtual storage area is stored in a predetermined storage device of the management apparatus 30. The file management module 33 functions as an acquisition unit according to the present embodiment.

  In addition, the file management module 33 uses the table 200 (see FIG. 2) which is information on the virtual storage area, and the real address of the file stored in each storage area of the first and second storage devices 10 and 20 And manage virtual addresses. The file management module 33 also executes processing such as updating and changing the table 200. That is, in the present embodiment, the file management module 33 holds and manages the information in the virtual storage area. Accordingly, the file management module 33 also functions as a holding unit according to the present embodiment.

  FIG. 2 is an example of a database table held as virtual storage area information. The table 200 shown in FIG. 2 includes a column (column) 210 in which a virtual file path name is written, a column 220 that represents the type of object represented by the actual file path, and columns 230 and 240 that represent the actual file path name. Further, the table 200 includes a column 250 indicating a correspondence state between the real file path and the virtual file path, a column 260 indicating the last access time, and the like.

  Looking at the field where the first record (row) 270 of the table 200 intersects with each of the above-mentioned columns, the directory 1 of the storage server 1 which is the first storage device 10 is obtained as the actual file path name 1. has been written. Further, the directory 2 of the storage server 2 that is the second storage device 20 is written as the actual file path name 2. Virtual directory 1 is written in column 210 as a virtual file path corresponding to these actual file paths.

  Further, looking at the second record 271 of the table 200, the file 1 stored in the directory 1 of the storage server 1 is written as the actual file path name 1. Further, the file 1 stored in the directory 2 of the storage server 2 is written as the actual file path name 2. A virtual file 1 stored in the virtual directory 1 is written as a virtual file path corresponding to these real file paths.

  Similarly, when looking at the third record 272 of the table 200, the file 2 stored in the directory 1 of the storage server 1 is written as the actual file path name 1. In addition, the file 2 stored in the directory 2 of the storage server 2 is written as the actual file path name 2. A virtual file 2 stored in the virtual directory 1 is written as a virtual file path corresponding to these real file paths.

  Information about the virtual directory 2 is written in the fourth and subsequent records (records 280 to 282) of the table 200. Typically, the table 200 is written with more information than that shown in FIG.

  As described above, in this embodiment, a common virtual file path is set between predetermined directories of the first and second storage devices 10 and 20. A shared virtual file path is set between predetermined files in the first and second storage devices 10 and 20. This will be explained.

  In the present embodiment, basically, the first and second storage devices 10 and 20 operate in an active / passive configuration. That is, the first and second storage devices 10 and 20 operate as a main cluster and a sub cluster, respectively.

  Therefore, in the present embodiment, the file written in the first storage device 10 that is the mirror source is mirrored in the second storage device 20 that is the mirror source. As a result, a second file that is a copy of the first file stored in the first storage device 10 is stored in the second storage device 20.

  FIG. 3 is a table showing mirroring setting information in the storage system 100. Such a table 300 is stored in the storage device and is referred to by the mirror management module 36 shown in FIG. The mirror management module 36 will be described later.

  In the column 310 of the table 300 shown in FIG. 3, the file server 1 is written as the storage name that is the mirror source. Then, the actual file path of the directory 1 of the file server 1 is written in the column 320. In the column 330, the actual file path of the directory 1 of the file server 2 is written. The directory 1 is a directory in which a second file that is a copy of the first file stored in the directory 1 of the file server 1 is stored. When there are a plurality of mirror destinations, the actual file path names of the mirror destinations are also described in the other columns 340. In the column 350, the set mirroring operation state is written.

  Based on this mirroring setting, in the present embodiment, a first virtual address (column 210) corresponding to the first real address (column 220 shown in FIG. 2) of the first file is set. In the present embodiment, the first virtual address is commonly used as the second virtual address corresponding to the second real address (column 240) of the copied second file. That is, the virtual file path name in the column 210 shown in FIG. 2 corresponds to both the first and second virtual addresses in this embodiment.

  Thus, for example, when mirroring is set for the purpose of redundancy of stored files, the same one is commonly used as the virtual address corresponding to each of the first and second real addresses. Also good.

  A state of correspondence between the real file path and the virtual file path shown in the column 250 of the table 200 in FIG. 2 will be described. For example, there is a temporary inconsistency between the virtual file path and the actual file path due to deletion or addition of a storage device included in the storage system 100, or due to a change in the actual directory or virtual directory in which the file is stored. There is a case. Therefore, the correspondence state between the real file path and the virtual file path is determined, and the result is written in the column 250. For example, as shown in a record 272, when it is determined that there is a mismatch between the real file path and the virtual file path, information indicating that the rebuild is in progress is written.

  Information on the last access time indicated in the column 260 of the table 200 is used, for example, for determining whether or not the file management module 33 refers to the table 200 is omitted. For example, it is assumed that the file access from the client device 50 to the virtual file path is within a predetermined time from the previous access. In that case, the reference to the table 200 is omitted, and the previous real file path is transmitted. By executing such processing, the load on the management device 30 can be suppressed.

  The file access reception module 31 illustrated in FIG. 1 receives file access from the client device 50. Specifically, an I / O request issued by executing file access is received. The file access receiving module 31 performs a predetermined operation according to the type of file access received.

  The file access response module 32 returns a predetermined command in response to the file access from the client device 50 to the client device. The file access response module 32 functions as a transmission unit according to the present embodiment.

  The file server management module 34 manages file servers included in the storage system 100. For example, when a storage server is added to the storage system 100 or a storage server is deleted from the storage system 100, the file server management module 34 executes processing to be described later.

  The mirror management module 36 manages mirroring settings in the storage system 100 based on the table showing the mirroring setting information shown in FIG.

  The file server failure detection module 35 detects whether the file server 1 (first storage device 10) and the file server 2 (second storage device 20) are operating normally. The file server failure detection module 35 detects a failure by means such as taking a heartbeat from each file server or receiving a notification of the failure when a failure occurs.

  Next, functional configurations of the first and second storage devices 10 and 20 will be described. As shown in FIG. 1, in the present embodiment, the first storage device 10 and the second storage device 20 have substantially the same configuration. Therefore, the configuration of the first storage device 10 will be described as a representative.

  The first storage device 10 includes a file system 11, an IRP (I / O Request Packet) operation module 12, a mirroring module 13, a file access status notification module 14, and a failure notification module 15.

  The file system 11 manages files stored in the storage area of the first storage device 10. For example, file access is executed by a predetermined application that the client device 50 has. The executed file access is issued as an I / O request to the file system 11. The file system 11 that has received the I / O request executes a predetermined access. The result of this access is returned to the IRP operation module 12.

  The IRP operation module 12 is implemented as a filter driver of the file system 11. The IRP operation module 12 can hook the I / O request sent to the file system 11 and send a copy thereof to the mirroring module 13 and the file access status notification module 14 respectively.

  The mirroring module 13 performs mirroring. For example, a write access is executed to the first storage device 10 that is a mirror source, and a file is written to the storage area of the first storage device 10. The writing is executed by the file system 11 that has received the I / O request, and the access result (hereinafter referred to as the first access result) is returned to the IRP operation module 12.

  The mirroring module transfers the file to be written to the second storage device 20 that is the mirror destination. In this embodiment, the mirroring module 13 also transmits a copy of the I / O request transmitted from the IRP operation module 12. A copy of the I / O request is transferred to the file system 21 of the second storage device 20.

  The file system 21 that has received the copy of the I / O request executes writing of the file to the storage area of the second storage device 20. The result of writing is returned to the IRP operation module 12 of the first storage device 10 as an access result (hereinafter referred to as a second access result).

  The first and second access results are transmitted from the IRP operation module 12 to the mirroring module 13. Then, the mirroring module 13 determines the consistency of the first and second access results. The determination of consistency is performed, for example, by managing the first and second access results in transactions. In addition, any method for determining consistency may be employed.

  For example, if both the first and second access results are success or failure, the success or failure result of the 10 I / O request to the first storage device is returned to the client device 50.

  If one of the first and second accesses is successful and the other is unsuccessful, it is determined that the first and second access results are not consistent, and error processing is executed. The error processing is typically executed by the management device 30, but may be executed by the first storage device 10.

  For example, when the first access result is successful and the second access result is unsuccessful, the address of the write destination related to the write access to the second storage device 20 that has failed is registered as an error address. Then, the write access to the second storage device 20 and the file are retransmitted. Thereby, the writing by the file system of the second storage device 20 is executed again. Note that read access to addresses registered as error addresses is restricted.

  When the first access result is unsuccessful and the second access result is successful, the address of the write destination relating to the write access to the first storage device 10 that has failed is registered as an error address. Then, the file written in the storage area of the second storage device 20 is returned to the first storage device 10, and the file writing is executed by the file system 11.

  Thus, in the present embodiment, file access to the first storage device 10 is transferred to the second storage device 20, and the consistency of the access results of both is determined. Then, when it is determined that the consistency between the first and second access results is not maintained, the error processing as described above is appropriately executed. This makes it possible to realize a high-quality storage system 100 using file level mirroring.

  Further, by transferring file access, it is possible to share a file access exclusion mechanism, and it is possible to handle a plurality of file entries equivalent to one file entry. As a result, for example, a plurality of files managed by a plurality of storage devices can be transparently handled as one file.

  In other words, it is possible to synchronize to the file access state at the file level in the same manner as RAID1. Further, it is possible to construct a flexible system regardless of the disk capacity of the mirror destination and the number of mirror destinations. For example, it is not necessary to prepare special hardware or software for the second storage device 20 that is a slave cluster. As the second storage device 20, for example, a well-known disk device such as NAS (Network Attached Storage) can be used. As a result, convenience in constructing the system is enhanced.

  Further, a flexible setting such as assigning a plurality of second storage devices 20 to one first storage device 10 or changing a cluster according to each folder is possible. In addition, a specific file can be recorded in a specific secondary cluster, and mirroring with a flexible configuration can be performed.

  In addition, when multiple secondary clusters are prepared at the mirror destination, when creating a new folder at the mirror source, it becomes possible to select the mirror destination of the folder from the remaining capacity of the mirror destination, etc. It is also possible to perform a load balancing configuration.

  The error processing described above is an example, and any other processing may be executed as the error processing.

  The file access status notification module 14 shown in FIG. 1 notifies the management device 30 of the status of file access being executed for the first storage device 10. The file access state typically means a load state of the first storage device 10 accompanying a file access from the client device 50.

  The load state of the first storage device 10 includes, for example, an I / O request transmitted from the IRP operation module 12, an access result, a determination result of consistency of an access result by the mirroring module 13, or an execution state of error processing. Is determined. The determined load state of the first storage device 10 is transmitted to the management device 30.

  For example, information such as the number of open files, the number of bytes of data written to the opened file, or the number of bytes of data read from the opened file may be notified as information indicating the load state. .

  The notification from the file access status notification module 14 to the management device 30 may be performed, for example, by receiving a notification request from the management device 30. Alternatively, information indicating the load state may be transmitted from the file access state notification module 14 to the management device 30 at a predetermined timing.

  As described above, the first and second storage devices 10 and 20 operate as a main cluster and a sub cluster, respectively. Accordingly, the file access status notification module 14 of the first storage device 10 also manages the file access status of the second storage device 20. Accordingly, the load states of both the first and second storage devices 10 and 20 are notified from the file access state notification module 14 of the first storage device 10 to the management device 30.

  Note that the load state of the second storage device 20 may be managed by the file access state notification module 24 of the second storage device 20.

  The failure notification module 15 notifies the management device 30 of the occurrence of a failure when a failure relating to software or hardware occurs in the first storage device 10.

[Storage system operations]
4 to 13 are schematic diagrams for explaining the operation of the storage system 100 of this embodiment. Below, it demonstrates centering around operation | movement of the management apparatus 30 which is the information processing apparatus which concerns on this embodiment.

  FIG. 4 is a schematic diagram showing the operation of the storage system 100 when the client device 50 opens a predetermined directory in the virtual storage area.

  File access from the client device 50 is executed with respect to the management device 30. A command for listing files under a predetermined virtual directory is issued from the client device 50 to the management device 30 (step 101). The command is received by the file access receiving module 31.

  The file access reception module 31 inquires of the file management module 33 about files under the virtual directory (step 102). The file management module 33 refers to the table 200 (see FIG. 4) stored in the database of the virtual storage area, and returns a list of files managed under the virtual directory. The list of files is transmitted to the client device 50 via the file access response module 32 (step 102).

  For example, a list of received files is displayed on a display or the like by a predetermined application of the client device 50. Thereby, the user of the client device 50 can recognize the files under the virtual directory. For example, the user inputs an instruction to open a predetermined file under the virtual directory to the client device 50.

  As described above, in the present embodiment, the client device 50 is provided up to the directory information of the virtual storage area. Then, a command for opening the directory is transmitted to the management apparatus 30, so that information on files under the directory is transmitted to the client apparatus 50. However, the virtual storage area information may be provided to the client device 50 including information on files under the directory.

  FIG. 5 is a schematic diagram illustrating the operation of the storage system 100 when the client device 50 opens a predetermined file (execution of open access).

  An open access I / O request is transmitted from the client device 50 to the management device 30 (step 201). The I / O request is accepted by the file access acceptance module 31. The actual file path is inquired from the file access receiving module 31 to the file management module 33. That is, the actual file path corresponding to the virtual file path of the file to be opened is inquired (step 202).

  The file management module 33 refers to the table 200 related to the virtual storage area and returns an actual file path corresponding to the virtual file path (step 203). The actual file path is transmitted to the client device 50 via the file access response module 32 (step 204).

  In the present embodiment, an actual path analysis request is transmitted together with the actual file path from the file access response module 32 to the client device 50. In the client device 50, reanalysis processing by the reanalysis module 51 is executed based on the actual file path and the actual path analysis request. By this reanalysis process, open access to the first storage device 10 based on the actual file path is executed (step 205). As a result, the file corresponding to the actual file path is opened in the storage area of the first storage device 10. Typically, a new real file path for file access to the first storage device 10 is generated by the reanalysis process. However, it is not limited to this.

  As described above, in this embodiment, the re-analysis module 51 automatically executes file access to the first storage device 10 based on the actual file path. As the reanalysis module 51, for example, a module for name resolution used for a shortcut or the like is used. For example, such a module is implemented in Windows (registered trademark), and is used for solving DFS (Distributed File System) clients and symbolic links. Such a module can be used as the reanalysis module 51 according to the present embodiment. In addition, the reanalysis module 51 can be realized by inserting a similar module in another OS (Operating System).

  Note that the reanalysis process as described above does not necessarily have to be executed by the client device 50. Based on an arbitrary algorithm, file access to the first storage device 10 may be executed based on the actual file path transmitted from the management device 30.

  As shown in FIG. 5, an IRP operation module 12 hooks an open access I / O request from the client device 50 to the first storage device 10. A copy of the I / O request is sent to the mirroring module 13 and the file access status notification module 14 (step 206). The mirroring described above is executed by the mirroring module 13 (step 207). In addition, the file access status notification module 14 notifies the management device 30 of the status of the file access being executed for the first storage device 10.

  FIG. 6 is a schematic diagram showing the operation of the storage system 100 when the client device 50 newly creates a file.

  An open access (new creation) I / O request is transmitted from the client device 50 to the management device 30 (step 301). For example, a new virtual file I / O request may be transmitted by designating a predetermined virtual directory. There is no need to specify a virtual directory.

  The I / O request is accepted by the file access acceptance module 31. A request for creating a new file is transmitted from the file access receiving module 31 to the file management module 33 (step 302).

  The file management module 33 adds a new record to the database (see FIG. 2) held in itself. At this time, real path name 1 and real path name 2 are newly created according to the table of FIG. 3 in the mirror management module 36.

  That is, a predetermined real file path in the directory 1 or the directory 2 of the first storage device 10 is set as a real address of a newly created file based on the mirror source path name shown in FIG. Also, referring to the path name 1 of the mirror destination, a predetermined real file path in the directory 1 or the directory 2 of the second storage device 20 is set as a real address of a newly created file copy. The set real file path is added to the real path name 1 and real path name 2 fields of the table 200.

  The actual file path newly set by the file management module 33 is returned to the file access reception module 31 (step 303). The actual file path is transmitted to the client device 50 via the file access response module 32 (step 304). Of the actual file paths newly set by the file management module 33, the actual file path for the first storage device 10 may be transmitted to the client device 50.

  In the client device 50, reanalysis processing by the reanalysis module 51 is executed. Then, file access for newly creating a file based on the actual file path transmitted from the management device 30 is executed for the first storage device 10 (step 305). A copy of the newly created I / O request for the file is transmitted from the IRP operation module 12 to the mirroring module 13 and the file access status notification module 14 (step 306). Mirroring is performed by the mirroring module 13 (step 307), and the file access status notification module 14 notifies the management device 30 of the file access status.

  For example, when a plurality of storage devices are set as mirror source file servers, a file server in which a new file is stored is selected. Various methods can be considered as the selection method, but the simplest implementation is a method of creating files in order in a plurality of mirror source storage devices in a round robin manner. In addition, it is also possible to create a new file in a storage device with a low load by checking the state of file access to each of the plurality of storage devices. As a result, load balancing can be executed.

  FIG. 7 is a schematic diagram showing the operation of the storage system 100 when the client device 50 writes data in a file.

  For example, after the file is opened by the operation shown in FIG. 5 and the like, the first storage device 10 executes a predetermined file service for file access from the client device 50. Therefore, as shown in FIG. 7, the client device 50 executes write access to the first storage device 10.

  A write access I / O request is transmitted to the file system 11 of the first storage device 10 (step 401). At this time, the actual file path used to execute the open access to the first storage device 10 (the path based on the actual file path transmitted from the management apparatus 30 at the time of the open access) is used. It is done.

  The file system 11 writes data to a file opened by open access. A copy of the I / O request is sent to the mirroring module 13 and the file access status notification module 14 (step 402). Mirroring is executed by the mirroring module 13 (step 403). As a result, data is also written to the file stored in the storage area of the second storage device 20 at the mirror destination.

  The file access executed after the file is opened is not limited to the write access described above, and various file accesses are executed from the client device 50 to the first storage device 10. Such file access includes, for example, file deletion / renaming as shown below.

  FIG. 8 is a schematic diagram showing the operation of the storage system 100 when the client device 50 deletes a file, renames it, or the like.

  The client device 50 executes file access to the first storage device 10 such as file deletion / renaming. The file access I / O request is transmitted to the file system 11 of the first storage device 10 (step 501).

  A copy of the I / O request is transmitted from the IRP operation module 12 to the mirroring module 13 and the file access status notification module 14, respectively (step 502). The file access status notification module 14 notifies the file management module 33 of the management device 30 that file access such as file deletion / renaming has been executed (step 503).

  The file management module 33 updates the database (see FIG. 2) held by itself based on the notification from the file access state notification module 14. The fact that the update has been completed is returned from the file management module 33 to, for example, the file access status notification module 14 of the first storage device 10.

  When a notification of completion of database update is received, the file system 11 executes access such as file deletion and name change. The mirroring module 13 executes mirroring (step 504), and the file access status notification module 14 notifies the management apparatus 30 of the file access status.

  Thus, in this embodiment, after the database held by the file management module 33 of the management apparatus 30 is updated, access by the file system 11 is executed. Thereby, the consistency between the files stored in the storage areas of the first and second storage devices 10 and 20 and the database can be maintained high. However, the database may be updated after the file system 11 deletes or renames the file, or in parallel therewith.

  FIG. 9 is a schematic diagram illustrating the operation of the storage system 100 that performs load balancing (load distribution) for open access from the client device 50.

  An open access I / O request is transmitted from the client device 50 to the management device 30 (step 601). The I / O request is accepted by the file access acceptance module 31.

  The file access reception module 31 determines whether the open access has a write attribute or a read attribute. This determination is performed by referring to, for example, a flag given to open access. A method for determining whether the open access is the write attribute or the read attribute is not limited. The determined attribute information is transmitted to the file access response module 32. The file access reception module 31 functions as a first determination unit according to the present embodiment.

  An inquiry about the actual file path is made from the file access reception module 31 to the file management module 33 (step 602). The file management module 33 refers to the virtual storage area table 200 and returns an actual file path corresponding to the virtual file path (step 603). The actual file path is transmitted to the file access response module 32.

  The file access response module 32 requests the file access status notification module 14 of the first storage device 10 to notify the file access status (step 604). As a result, the load states of both the first and second storage devices 10 and 20 are notified from the file access state notification module 14 to the file access response module 32.

  The timing at which the notification request for the file access status is transmitted is not limited after the actual file path from the file management module 33 is received. For example, the request transmission may be executed when an open access from the client device 50 is accepted. Alternatively, the request may be periodically transmitted at a predetermined timing regardless of whether or not the client device 50 accesses the file. The file access response module 32 also functions as a second determination unit according to the present embodiment.

  The file access response module 32 selects an actual file path to be transmitted to the client device 50 based on the open access attribute and the load states of the first and second storage devices 10 and 20. The selected real file path is transmitted to the client device 50 (step 605).

  For example, when the open access attribute is the write attribute, the actual file path of the storage area of the first storage device 10 that is the mirror source is transmitted to the client device 50. That is, the path written in the column 230 of the real path name 1 in the table shown in FIG.

  When the open access attribute is the read attribute, the load state information of the first storage device 10 that is the mirror source and the second storage device 20 that is the mirror destination is referred to. The real path file in the storage area of the storage device with the smaller load of the first storage device 10 and the second storage device 20 is transmitted to the client device 50.

  As described above, in this embodiment, it is determined whether the file access to the virtual file path in the virtual storage area held by the management apparatus 30 is a read access or a write access. In the present embodiment, the load states of the first and second storage devices 10 and 20 are determined. Based on these determination results, one of the first and second real addresses is transmitted to the client device 50 in response to file access to the virtual file path. This enables load balancing in the storage system 100.

  The client device 50 that has received the actual file path performs open access to the first storage device 10 or the second storage device 20 (step 606). A copy of the I / O request for the open file is transmitted to the mirroring module 13 and the file access status notification module 14 (step 607). Mirroring is executed by the mirroring module 13 (step 608), and the file access status notification module 14 notifies the management device 30 of the file access status.

  Note that FIG. 9 illustrates an operation when an open access is executed to the first storage device 10. When the real file path of the storage area of the second storage device 20 is transmitted to the client device 50 in step 605, the open file I / O request is transmitted to the file system 21 of the second storage device 20. .

  In this embodiment, the file access reception module 31 functions as a first determination unit, and the file access response module 32 functions as a second determination unit. However, other modules such as the file management module 33 and the file access response module 32 may function as the first determination unit. Further, the file access reception module 31 and the file management module 33 may function as the second determination unit. Furthermore, a module that functions as a first determination unit and a module that functions as a second determination unit may be provided independently.

  FIG. 10 is a schematic diagram showing the operation of the storage system 100 when a storage device as a storage server is newly added. Here, the operation in the case where the third storage device 60 shown in FIG. 10 is added as a mirror-source storage server with the fourth storage device 70 as a mirror destination is illustrated.

  For example, the storage server is added in the following case. For example, there may be a case where video data captured by a camera is directly recorded in a storage and the storage is connected to the storage system 100. A case where storage is added to increase the storage capacity of the storage system 100 is also conceivable. Furthermore, in recent years, some cameras have storage inside, and there are cases where the camera itself is connected to the storage system 100. In addition, for example, the storage system 100 is deleted by a deletion process described later by a storage server in which a problem has occurred. Even when the storage server is recovered after the defect is corrected, the following additional processing operation is executed. Various other cases are conceivable.

  A storage addition request is transmitted from the client device 50 to the management device 30 based on an operation to the client device 50 via a predetermined UI (User Interface) or the like (step 701). The storage addition request is transmitted to the file server management module 34 of the management apparatus 30.

  The file server management module 34 determines whether to set mirroring for the third storage device 60 to be added. For example, the determination is executed based on an instruction from the client device 50. When the third storage device 60 is used as a mirror source storage server as in the present embodiment, a mirroring setting request is transmitted from the file server management module 34 to the mirror management module 36 (step 702).

  The mirror management module 36 updates the mirroring setting information based on the mirroring setting request. For example, the storage server 3 as the third storage device 60 is added to the column 310 of the table shown in FIG. A predetermined directory in the storage area of the third storage device 60 is written in the mirror source path name in the column 320. A predetermined directory in the storage area of the fourth storage device 70 is written in the mirror destination path name in the column 330.

  When the update of the mirroring setting information by the mirror management module 36 is completed, a mirroring setting request is transmitted to the mirroring module 63 of the third storage device 60 (step 703). This mirroring setting request is based on the mirroring setting information updated by the mirror management module 36. The mirroring module 63 performs mirroring based on the received mirroring setting request.

  When the file server management module 34 determines that the mirroring setting is unnecessary for the third storage device 60, the mirroring setting request is not transmitted to the mirror management module 36. For example, when a message indicating that mirroring setting is unnecessary is transmitted from the client device 50, or when the third storage device 60 is a storage server incapable of mirroring setting, a mirroring setting request is not transmitted.

  The file server management module 34 notifies the file management module 33 that a file server has been added (step 704). Upon receiving the notification, the file management module 33 updates the virtual storage area table 200 held by itself. For example, a record including a virtual directory name, a predetermined directory in the storage area of the third storage device 60, and a predetermined directory in the storage area of the fourth storage device 70 is added.

  In this embodiment, the storage addition process is executed by receiving a storage addition request from the client device 50. For example, the management device 30 is provided with a module that detects a new connection of a storage server on the network 40. Detection by this module may be used as a trigger for storage addition processing.

  FIG. 11 is a schematic diagram illustrating an operation of the storage system 100 when a storage device as a storage server is deleted from the storage system 100. FIG. 11 illustrates an operation when the first storage device 10 serving as a mirror source is deleted.

  A storage deletion request is transmitted from the client device 50 to the management device 30 (step 801). The storage deletion request is transmitted to the file server management module 34 of the management apparatus 30.

  For example, the management device 30 is provided with a module that detects whether a storage server is connected to the network 40. This module may detect that the connection of the first storage device 10 to the network 40 is interrupted, and the following operation may be executed by the detection.

  An instruction not to transmit the actual file path on the storage area of the first storage device 10 to be deleted is output from the file server management module 34 to the file access response module 32 (step 802). For example, it is assumed that a predetermined file in the virtual storage area is accessed from the client device 50 and the actual file path in the storage area of the first storage device 10 is output from the file management module 33. Even in such a case, the operation of the file access response module 32 is appropriately set so that an instruction to access the first storage device 10 is not transmitted to the client device 50.

  Further, a mirroring stop request is transmitted from the file server management module 34 to the mirror management module 36 (step 803). The mirror management module 36 updates the mirroring setting information based on the mirroring stop request. For example, information about the first storage device 10 is deleted from the table shown in FIG.

  When updating of the mirroring setting information by the mirror management module 36 is completed, a mirroring stop request is transmitted to the mirroring module 13 of the first storage device 10 (step 804). The mirroring stop request is transmitted after all of the access to the currently mirrored file and the mirrored access are completed.

  The mirroring module 13 of the first storage device 10 cancels the mirroring setting based on the received mirroring stop request.

  The file server management module 34 notifies the file management module 33 that the file server has been deleted (step 805). Upon receiving the notification, the file management module 33 updates the virtual storage area table 200 held by itself. For example, information regarding the first storage device 10 is deleted from the table 200.

  FIG. 12 is a schematic diagram showing the operation of the storage system 100 when a failure occurs in the file server. FIG. 12 illustrates an operation when a failure occurs in the second storage device 20.

  The failure notification module 25 of the second storage device 20 transmits a failure notification to the file server failure detection module 35 of the management device 30 (step 901). Thereby, it is detected that a failure has occurred in the second storage device 20. A heartbeat may be transmitted from the failure notification module 15 to the file server failure detection module 35. The failure of the second storage device 20 may be detected by stopping the reception of the heartbeat.

  The fact that a failure has occurred in the second storage device 20 is transmitted from the file server failure detection module to the 35 file access response module 32 (step 902). For example, an instruction not to transmit the actual file path on the storage area of the second storage device 20 to the client device 50 is output.

  A storage deletion request for deleting the second storage device 20 is transmitted from the file server failure detection module 35 to the file server management module 34 (step 903). Upon receiving the storage deletion request, the file server management module 34 transmits a mirroring stop request to the mirror management module 36 (step 904).

  The mirror management module 36 that has received the mirroring stop request updates the mirroring setting information. When the update is completed, a mirroring stop request is transmitted to the mirroring module 13 of the first storage device 10 that is the mirror source of the second storage device 20 (step 905).

  The mirroring module 13 of the first storage device 10 cancels the mirroring setting based on the received mirroring stop request. Note that a mirroring stop request may be transmitted to the mirroring module 23 of the second storage device 20. The mirroring setting may be canceled by the mirroring module 23.

  The fact that a failure has occurred in the second storage device 20 is transmitted from the file server management module 34 to the file management module 33 (step 906). Upon receiving the notification, the file management module 33 updates the virtual storage area table 200 held by itself. For example, information regarding the second storage device 20 is deleted from the table 200.

  FIG. 13 is a schematic diagram illustrating the operation of the storage system 100 when a failure occurs in the management apparatus 30 that is a file server management server.

  The file server failure detection module 35 of the management device 30 detects a failure that has occurred in the management device 30 (step 1001). The type of failure and the method for detecting the failure are not limited.

  In the present embodiment, it is assumed that the file server management server is redundant, and various data managed by the management device 30 are completely synchronized. When a failure occurs in the management apparatus 30, access to the management apparatus 30 is skipped to other information processing apparatuses that are synchronized.

  For example, by using a Microsoft (registered trademark) NLB (Node Load Balancing) function, when accessing a certain IP address (Internet Protocol Address), it is possible to skip access to an IP address in which no failure has occurred. Become. For example, it is possible to minimize downtime by using this function. Other information processing methods may be used as appropriate.

  As described above, in the storage system 100 according to the present embodiment, the actual file paths of the files stored in the first and second storage devices 10 and 20 are acquired. A virtual storage area having a virtual file path corresponding to the actual file path is held. When there is a file access to the virtual file path, an actual file path corresponding to the virtual file path is transmitted according to the file access. As a result, file access using the actual file path can be performed on the first or second storage device 10 or 20. As a result, the storage system 100 that can handle data with good operability on a file basis can be realized.

  In addition, each storage area of the first and second storage devices 10 and 20 can be virtually seen as one. As a result, the storage system 100 with good operability is realized. In the present embodiment, file access based on the information of the hierarchy in which the file is stored can be performed on the first or second storage device 10 or 20.

  There are two main methods for virtualizing storage areas in a storage system having a plurality of storage devices: block level virtualization and file level virtualization. As block-level virtualization, there is a method in which each storage cluster, for example, SAN, discloses an IF (Interface) as a block device using a protocol such as FC (Fibre Channel) or iSCSI.

  Further, a SAN may be constructed using a storage controller and a storage cluster recognized as a block device. In this method, redundancy is performed at the part where the blocks are integrated, and is maintained by configuring, for example, RAID1 or RAID5.

  In recent years, there is also a virtualization apparatus that implements this redundant portion with a unique algorithm, instead of a fixed block arrangement such as RAID5. However, this method requires the installation of SAN client software on each host.

  In addition, when a failure occurs in the SAN controller that manages the storage, the device that manages the storage block does not exist, so the file cannot be accessed during the failure. Although normally redundant, if the data of the SAN controller is lost or an inconsistency occurs in the event of a disaster, it becomes difficult to recover the data.

  For such block level virtualization, there is a technique called file level virtualization. File-level virtualization is a technique for performing virtualization so that files existing in a plurality of file servers appear to be arranged under one virtual directory.

  There are two file-level virtualization methods: in-band and out-band. The in-band method refers to a method in which control and data access are performed using the same path. The out-of-band method refers to a method in which file access control and data transmission / reception are performed through different paths. In general, the in-band method is often used for file level virtualization.

  As an in-band method of file level virtualization, there is a method of performing file level virtualization across an intermediate device. In this method, since access is concentrated on the intermediate device, the bandwidth of the intermediate device itself becomes a bottleneck. In addition, since the host accesses the intermediate device and then the intermediate device accesses each file server, there is a double step in data transmission, and the throughput is greatly reduced.

  As an out-of-band method of file level virtualization, there is a method in which SAN client file system software is installed in each host and virtualization is performed at that layer. This method, together with SAN, installs a file system on each host, resulting in higher management costs and access to files if data is lost when a storage management server fails. Will not be able to.

  As described above, in the existing method used in SAN or the like, data is managed on a block basis, and when the data in the controller is damaged, there is a possibility that the data cannot be recovered again. Another problem is that it increases the management cost by putting software in the host. In a method of accessing all storage via an intermediate device such as a NAS head, storage management and design are easy, but the problem of reducing the bandwidth remains.

  On the other hand, in recent years, an increasing number of devices can store camera video data directly as a file in a storage. With the recent evolution of IT, there is an era in which broadcasting stations are shifting from tape-based workflows to file-based workflows. Many conventional systems manage data on a block basis. Therefore, the storage in which the video data of the camera is stored cannot be used even if it is connected to the storage system, and the editors can use it only after copying the file to the central storage.

  In addition, since video data has a very large data capacity, there are many cases in which data is put into a USB HDD or NAS to sneaker the material. In such a case, it is also required to use the storage as a member of a file server cluster without file copy. It is also required that the host can read data directly from the storage and access it with a sufficient bandwidth. Also, if file-level virtualization is realized, the number of unnecessary file copies can be reduced.

  As an example of file level virtualization, for example, there is a method of changing the access destination of a file by resolving the global namespace using Microsoft DFS. This method works under limited conditions. For example, it is difficult to store two files on different file servers, such as a branch of a namespace, for example, Dir1 / File1 or Dir1 / File2.

  In Windows (registered trademark) DFS, load balance can be specified, but when Dir1 is accessed immediately after Dir1 / File1 is stored in the file server 1, File1 written by being skipped to Dir1 of another file server 2 is written. There are cases that do not exist. This problem can be attributed to the fact that each file server provides a directory service.

  In the storage system 100 described in the embodiment of the present technology, file-level virtualization can be realized out-of-band. That is, in the storage system 100, it is possible to show a cluster of file servers as one virtual storage out-of-band.

  As a result, speeding up of access from the client device 50 can be realized. Further, load balancing can be executed without requiring complicated processing. In addition, it is possible to realize deletion or addition of a storage server at high speed while maintaining consistency such as mirroring by a simple process.

  In addition, it is not necessary to install predetermined software on the client device 50 that accesses the storage system 100, and management costs can be reduced. Also, by executing the deletion process shown in FIG. 8 and the addition process shown in FIG. 10, it is possible to easily execute storage server recovery and data recovery.

<Modification>
The embodiment according to the present technology is not limited to the embodiment described above, and various modifications are made.

  For example, the number of storage devices as storage servers included in the storage system 100 may be larger. In that case, as a table shown in FIG. 2 or FIG. 3, a table having more records may be used as appropriate.

In addition, this technique can also take the following structures.
(1) An acquisition unit that acquires a real address, which is an address on the storage area in which the file is stored, of a storage device having a storage area in which the file is stored at a predetermined address;
A holding unit for holding a virtual storage area, which is a virtual storage area, having a virtual address corresponding to a real address on the storage area and a virtual address of a file stored in the real address;
An information processing apparatus comprising: a transmission unit that transmits the real address corresponding to the virtual address that is a target of the access request in response to an access request to the virtual address in the virtual storage area.
(2) The information processing apparatus according to (1),
The acquisition unit acquires a real address in each storage area of one or more storage devices,
The information processing apparatus, wherein the virtual storage area has the virtual address corresponding to a real address acquired in each storage area.
(3) The information processing apparatus according to (1) or (2),
The storage area has a plurality of hierarchies,
The real address includes information on a hierarchy in which the file is stored among the plurality of hierarchies.
(4) The information processing apparatus according to (2) or (3),
The virtual storage area stores a first virtual address corresponding to the first real address of the first file stored in the first storage device in a second storage device different from the first storage device. An information processing apparatus commonly used as a second virtual address corresponding to a second real address of a second file that is a copy of the stored first file.
(5) The information processing apparatus according to (4),
A first determination unit that determines whether the access request to the first virtual address is a read access or a write access;
The transmission unit transmits one of the first and second real addresses based on the determination by the first determination unit in response to an access request to the first virtual address. Information processing device.
(6) The information processing apparatus according to (4) or (5),
A second determination unit for determining a load state of each of the first and second storage devices;
The transmission unit transmits one of the first and second real addresses based on a determination by the second determination unit in response to an access request to the first virtual address. Information processing device.

DESCRIPTION OF SYMBOLS 10 ... 1st memory | storage device 20 ... 2nd memory | storage device 30 ... Management apparatus 31 ... File access reception module 32 ... File access response module 33 ... File management module 34 ... File server management module 35 ... File server failure detection module 36 ... Mirror management module 60 ... third storage device 70 ... fourth storage device 100 ... storage system 200 ... table 300 ... table

Claims (9)

An acquisition unit that acquires a real address that is an address on the storage area in which the file is stored in a storage device that has a storage area in which a file is stored at a predetermined address;
A holding unit for holding a virtual storage area, which is a virtual storage area, having a virtual address corresponding to a real address on the storage area and a virtual address of a file stored in the real address;
An information processing apparatus comprising: a transmission unit that transmits the real address corresponding to the virtual address that is a target of the access request in response to an access request to the virtual address in the virtual storage area. The information processing apparatus according to claim 1,
The acquisition unit acquires a real address in each storage area of one or more storage devices,
The information processing apparatus, wherein the virtual storage area has the virtual address corresponding to a real address acquired in each storage area. The information processing apparatus according to claim 1,
The storage area has a plurality of hierarchies,
The real address includes information on a hierarchy in which the file is stored among the plurality of hierarchies. An information processing apparatus according to claim 2,
The virtual storage area stores a first virtual address corresponding to the first real address of the first file stored in the first storage device in a second storage device different from the first storage device. An information processing apparatus commonly used as a second virtual address corresponding to a second real address of a second file that is a copy of the stored first file. The information processing apparatus according to claim 4,
A first determination unit that determines whether the access request to the first virtual address is a read access or a write access;
The transmission unit transmits one of the first and second real addresses based on the determination by the first determination unit in response to an access request to the first virtual address. Information processing device. The information processing apparatus according to claim 4,
A second determination unit for determining a load state of each of the first and second storage devices;
The transmission unit transmits one of the first and second real addresses based on a determination by the second determination unit in response to an access request to the first virtual address. Information processing device. A storage device having a storage area in which a file is stored at a predetermined address, obtains a real address that is an address on the storage area in which the file is stored;
Holding a virtual storage area, which is a virtual storage area, corresponding to a real address on the storage area and having a virtual address which is a virtual address of a file stored in the real address;
An information processing method that transmits the real address corresponding to the virtual address that is a target of the access request in response to an access request to the virtual address on the virtual storage area. A storage device having a storage area in which a file is stored at a predetermined address, obtains a real address that is an address on the storage area in which the file is stored;
Holding a virtual storage area, which is a virtual storage area, corresponding to a real address on the storage area and having a virtual address which is a virtual address of a file stored in the real address;
A program that causes a computer to execute, in response to an access request to the virtual address on the virtual storage area, transmitting the real address corresponding to the virtual address that is a target of the access request. A storage device having a storage area in which a file is stored at a predetermined address;
An acquisition unit for acquiring a real address that is an address on the storage area of the storage device in which the file is stored;
A holding unit for holding a virtual storage area, which is a virtual storage area, having a virtual address corresponding to a real address on the storage area and a virtual address of a file stored in the real address;
An information processing system comprising: a transmission unit that transmits the real address corresponding to the virtual address that is a target of the access request in response to an access request to the virtual address on the virtual storage area .

Images