JPH0773090A - Computer system and secondary storage device - Google Patents

Abstract

PURPOSE:To provide a computer system which can arrange a file in an optimum place regardless of the type of a secondary storage device. CONSTITUTION:When an instruction for the new storage of the file is given by a command including identification information of the file from a host computer 1, the file management/command management means 23a of the secondary storage device 2 informs a new file address deciding means 26 of it. The new file address deciding means 26 decides an optimum area as the area for registering the new file by considering the characteristic of the file and the constitution of the self secondary storage device among free areas grasped by referring to a disk management table 25b. The address of the decided area is registered in a local file management table 27 by making it correspond to identification information of the file. The file management/command management means 23a stores the file in the decided area of a disk device 29 through a disk device control means 24.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a computer system composed of a host computer and a secondary storage device, and more particularly to a technique for optimally arranging files in the secondary storage device.

[0002]

2. Description of the Related Art As a computer system composed of a host computer and a secondary storage device, a workstation (hereinafter referred to as "WS") adopting an operating system known as UNIX (hereinafter referred to as "OS"). )
There is known a system in which a hard disk device (hereinafter, referred to as "disk device") is connected to.

As a file management technique in such a computer system, there is "UNIX4.3BSD".
The design and implementation of "," published by Maruzen, 1991, is known.

This technique will be described below.

FIG. 24 shows the configuration of this computer system.

In the figure, 1 is a host computer and 2 is a secondary storage device.

In the host computer 1, 20 is an OS, 12
Represents a process of an application program (hereinafter referred to as “AP”) executed by a user managed by the OS 20. That is, the application program executed in the host computer is managed as the process 12 by the OS 20.

Further, in the OS 20, 13 is a file management / buffer management means for managing a buffer used for file management and data transfer at the time of file access.
5 is a file management table that describes information for associating logical addresses of directories and files (addresses inside the OS) with local addresses (local addresses) within the disk device, and 14 is directory information ( A directory management table describing information for associating the names of directories and files with the file management table is shown. Further, 16 is a device driver for converting and controlling a file access request from the file management / buffer management means 13 in accordance with physical characteristics of external devices such as various secondary storage devices, and 30 is for newly writing a file. At this time, file address determining means for determining the local address of the disk device most suitable for writing, 25a is a disk management table for managing the usage status of the disk, and 21 and 22 are communication and data between the host computer and the secondary storage device. The interface control means which controls transfer is shown.

Here, the logical address is a logical address for managing a file in a host computer. The local address (local address in the disk device) is the disk device (secondary storage device).
Is a local address in the disk device for managing data, and even if it is a logical address,
It may be a physical address. For example, SCS
A disk device (SCSI disk) conforming to I (Snall Computer Interface) uses a logical serial number (LBA; Logical Block Address) as a local address. In addition, IDE (Intelligent Device Elect)
In a disk device or the like, a physical address such as a head number, a cylinder number, or a sector number that directly represents a physical storage position is used as a local address.

Next, in the secondary storage device 2, 29 is 1
More than one disk device, 24 is a disk device control means for controlling the disk device 29, and 23 is a disk device that receives and analyzes the read and write commands transmitted from the host computer and creates a disk command specific to the disk device 29. The command management means to be sent to the control means 24 is shown.

The file access processing executed when the process 12 accesses an existing file will be described below.

When the process 12 accesses a file, it issues a file access read / write request (system call) to the OS 20.

Upon receipt of this request, the file management / buffer management means 13 of the OS 20 receives the directory management table 1
4, the position of the file management table is obtained from the file name. Next, the obtained file management table 15 is referred to, the logical address at which the read (or write) request data of the process exists (or the data is registered) is calculated, and converted to a local address. Also, a buffer area required for data transfer is secured.

Next, the OS 20 executes the device driver 16
The access request is made using the calculated local address. Upon receiving this access request, the device driver 16 creates a command in a form that matches the physical characteristics of the secondary storage device 2 in which the file is stored (or stores the file), and the command is generated via the interface control means 21. It is sent to the next storage device 2.

In the secondary storage device 2, the command management means 23
Receives a command via the interface control means 22 and analyzes this command. Then, a disk command specific to the disk device 29 is created based on the analysis result of the command such as access type, access start address, data length, etc., and the disk controller 24 is requested to execute the command. The disk controller 24 controls the disk device 29 based on this command, and executes appropriate data transfer processing.

When the process 12 accesses an existing file, it is necessary to determine at which address in the secondary storage device 2 the file should be stored.

Therefore, when creating a new file, it is necessary to perform the following new registration process prior to the file access (write) process.

That is, when a write request for a new file is requested from the process 12, the file management / buffer management means 13 registers the file name in the directory management table 14 and manages this file in the file management table 15. A data area is secured and its position is registered in the directory management table 14. Next, the file address determination means 30 uses the disk management table 25.
Referring to a, an optimum address, that is, seek is not performed as much as possible based on physical characteristic parameters such as the number of heads, the number of cylinders, and the number of sectors of the disk device set in advance by the user, and useless rotation waiting occurs. The local address of the area that does not occur is determined by a predetermined placement algorithm. Then, the determined local address is registered in the file management table and is associated with the logical address.

With the above new registration processing, in subsequent access, this file access can be performed by the normal file access processing performed by referring to both the directory management table 14 and the file management table 15.

[0020]

DISCLOSURE OF THE INVENTION Problems to be Solved by the Invention
According to the technique described in "Design and Implementation of BSD" (Maruzen, published in 1991), as described above, a secondary storage device such as a disk device is used to determine the optimum address for storing a newly created file. Must be set in advance.

On the other hand, in recent years, in response to the demand for large capacity, high performance, and high reliability, instead of simply connecting one or a plurality of disk devices, the disks are arranged on the array,
Various advanced and complicated secondary storage devices such as a disk array device in which data is divided and arranged in each disk device have appeared.

Therefore, the physical parameters of the secondary storage device are not only the parameters of the disk itself but also the redundancy calculated from the data of a plurality of disk devices in order to realize the array configuration, the data distribution method, and the high reliability. There are various types depending on the architecture of the secondary storage device such as data arrangement. Further, generally, since the host computer and the secondary storage device are distributed independently, it is not possible for the manufacturer to set the parameters of the secondary storage device in advance in the host computer.

Therefore, although the user sets the parameters of the secondary storage device, it is difficult for the user to set all the parameters of these various secondary storage devices in the host computer. In reality, this is often not possible. As a result, it becomes difficult to optimally arrange the files in the secondary storage device having a complicated configuration in the host computer, which causes a problem that the performance of the secondary storage device cannot be effectively used.

Therefore, an object of the present invention is to provide a computer system capable of realizing the optimum placement of files in the secondary storage device without setting the parameters of the secondary storage device in the host computer. To do.

[0025]

[Means for Solving the Problems] To achieve the above object,
The present invention has, for example, a computer and one or a plurality of secondary storage devices connected to the computer, and the secondary storage device is a local address in the secondary storage device. A computer system for managing data stored by a local address, wherein the secondary storage device stores the file configured by one or a plurality of logical blocks, and the local address to specify the local address. When a request is made from the computer for a more requested access to a logical block already stored in the storage means and a storage of a new logical block in the storage means, the storage is requested. A memory for storing logical blocks
A means for determining a local address by a predetermined procedure, a means for storing a logical block requested to be stored at the determined local address, and means for notifying the computer of the determined local address, The computer has a file management table for managing local addresses in which logical blocks constituting a file stored in a secondary storage device are stored in association with each logical block, and a secondary file management table. When accessing the logical block stored in the storage device, the local address of the logical block to be accessed is obtained by referring to the file management table,
Means for requesting the secondary storage device to access the logical block by designating a local address, and in the case of storing a new logical block in the secondary storage device, without specifying the local address, A means for requesting storage of a logical block in the secondary storage device and a local address notified from the secondary storage device are registered in the file management table in association with a new logical block for which storage is requested. There is provided a computer system.

[0026]

According to the computer system of the present invention, when the computer stores a new logical block in the secondary storage device, the computer does not specify the local address of the secondary storage device and Request storage of a logical block from secondary storage. On the other hand, the secondary storage device, when requested by the computer to store a new logical block in the storage means, determines a local address for storing the logical block requested to be stored by a predetermined procedure, The logical block requested to be stored is stored in the determined local address, and the determined local address is notified to the computer. The computer associates the notified local address with a new logical block that has requested storage, and stores the file management table.
When the logical block is registered and the logical block is accessed thereafter, the file management table is referred to, the local address of the logical block to be accessed is designated, and the secondary storage device is requested to access.

As described above, according to the present invention, the local address for storing the logical block forming the file is
Determined by secondary storage. Here, since it is easy for an individual secondary storage device to grasp its own configuration and state, the secondary storage device can determine the optimum storage position of the logical block. Therefore, it is possible to realize the optimum placement of the files in the secondary storage device without setting the parameters of the secondary storage device in the host computer.

[0028]

Embodiments of the computer system according to the present invention will be described below.

First, FIG. 1 shows an example of the hardware configuration of the computer system according to this embodiment.

As shown in the figure, the computer system according to this embodiment comprises a host computer 1 and a secondary storage device 2. The host computer 1 controls an I / O request (I / O request) to a CPU 10 that executes an OS and an application program, a primary storage device 11 used by the CPU 10, and an input / output request to the secondary storage device 2. It is composed of a control unit 9 and an interface 8 to the secondary storage device 2.

On the other hand, the secondary storage device 2 stores an interface 7 for exchanging I / O requests from the host computer 1, a control device 5 for controlling data transfer and internal control of the secondary storage device 2, and data storage. And a buffer device for absorbing a difference in data transfer speed between the disk device 4 and the host computer 1.

However, the hardware configuration of the computer system according to the present embodiment may be other than the configuration shown in FIG.

Next, a method of managing the logical position of a file and the position of the file on the secondary storage device in the computer system according to this embodiment will be described.

As shown in FIG. 2, the logical position of a file is hierarchically managed by a tree structure constructed using directories. This is an OS such as UNIX mentioned above.
This is the method used in.

Here, the file is stored in the actual storage area of the secondary storage device for each block which is a collection of data of a predetermined length. Then, the file is stored on the secondary storage device.
The cull position is managed by managing the logical address of each of the blocks that make up the file and the local address on the secondary storage device corresponding to this logical address. The local location on the secondary storage device is managed by the secondary storage device using the local address of the secondary storage device. Secondary storage device
A local address is called a local address. As described above, the local address may be a physical address that specifies a physical position on the secondary storage device, or may be a logical address that specifies a logical position on the secondary storage device. .

However, the logical position of the file and the position of the file on the secondary storage device may be managed by a method based on such a management method.

When the new file is stored in the secondary storage device 2, as a part of the above-mentioned new registration processing, each of the blocks obtained by dividing the file is subjected to the optimization algorithm and the local storage of the secondary storage device. It is necessary to perform the process of mapping to the address. However, if a plurality of disk devices are connected to the secondary storage device 2, or if the secondary storage device 2 is a so-called RAID (Redundant Arrays of Inex
In the case of a secondary storage device having a complicated configuration in which data is distributed to a plurality of disk devices according to the pensive Disks architecture, it is optimal for the host computer 1 according to the type of secondary storage device used. It is extremely difficult to input various algorithms and various parameters. Therefore, normally, the secondary storage device 2 is made to look like a conventional simple secondary storage device and the conventional algorithm is used. However, in such a case, not only the potential capacity of the secondary storage device cannot be extracted, but in the worst case, lower performance than the conventional case may be expected.

The first embodiment of the present invention will be described below.

FIG. 3 shows the configuration of the computer system according to the first embodiment.

As shown in the figure, the computer system according to the first embodiment has a host computer 1 and a secondary storage device 2.

In the host computer 1, 20 is an OS, 12
Represents a process of an application program managed by the OS 20. The application program executed in the host computer is managed by the OS 20 as the process 12.

In the OS 20, 13 is a file management / buffer management means for managing a buffer used for file management and data transfer at the time of file access.
Reference numeral 5 is a file management table that describes the correspondence between logical addresses of directories and files and local addresses.
Reference numeral 4 denotes a directory management table that describes directory information. Further, 16 is a device driver for converting and controlling a file access request from the file management / buffer management means 13 according to physical characteristics of external devices such as various secondary storage devices, and 18 is a file opened. Open file information notifying means for notifying the secondary storage device 2 of the information, 19 is new file write notifying means for notifying the secondary storage device 2 that a new file will be written, and 17 is determined by the secondary storage device 2. The new file address registration means for receiving the storage address of the new file and registering it in the file management table 15 is shown. Further, in the host computer 1, reference numeral 21 denotes an interface for controlling communication and data transfer with the secondary storage device. -Shows the control means.

The file management table 15 stores file management information provided for each file. The file management information provided for each file is specified via the address of the file management information specified by the file identification number. In UNIX, the file management information is called an i-node, and the file identification number is called an i-node number.

Each file management information is constructed as shown in FIG.

That is, each file management information has entries of mode 151, owner 152, time stamp 153, size 154, block number 155, reference count 156, reference pointer 157, and update flag 158. .

The mode 151 is a file type and the current access mode (read / write, etc.) of the file.
Information is stored, and the owner 152 stores information for identifying the owner of the file and the user group having the access right to the file. Also, the time stamp 153
Stores the time when the file was last accessed, the time when the own file management table was updated, and the like. The size 154 stores the number of bytes of the file, and the number of blocks is 1
54 stores the number of blocks of the file. The reference counter 156 stores the number of times the file is referenced, and the reference pointer 177 stores the logical address of each block of the file and the local address of the secondary storage device in association with each other. In the following, the logical address of a block is the logical block address, and the block secondary storage device
Cull addresses are called local block addresses.

Next, the directory management table 14 also
The directory management information provided for each directory is stored, and each directory management information is stored in the corresponding directory in the file identification number that identifies the file management information corresponding to the file belonging to the corresponding directory in the file management table 15. Information (or a pointer indicating the existing position of the directory management table) for identifying the directory management information corresponding to the directory to which the directory belongs is stored.

Such a directory management table 1
4 and the file management table 15 make it possible to obtain the local block address of each block forming file 5 in the file 5 by designating directories dir1, dir2, dir3 and file5. it can. That is, dir1, di
The directory management table 14 of r2 and dir3 is sequentially scanned, the file identification number of the file management information corresponding to file5 of the file management table 15 is obtained from the directory management information of dir3, and file5 is determined from the file management information of file5. Each block that composes
Get the cull block address.

On the other hand, in the secondary storage device 2, 2
9 is one or more disk devices, 24 is a disk device 29
A disk device control means 23 for controlling the disk device control means 23 for receiving and analyzing the read and write commands sent from the host computer, creating a disk command unique to the disk device 29, and sending it to the disk device control means 24;
Reference numeral 22 is an interface control means for controlling communication and data transfer with the host computer 1, and 27 is a secondary storage device 2.
Local file management table for storing file management information of files stored in the disk device 29 of
Reference numeral 39 is an open file information reception / registration means for receiving information indicating that a file transmitted from the host computer 1 has been opened and registering it in the local file management table 27.
Reference numeral 26 is a new file address determining means for receiving the writing of a new file sent from the host computer 1 and determining the storage address of the new file, and 28 is the address determined by the new file address determining means 26 for the host computer. 1 is a new file address notifying means, and 25b is a disk management table for managing the parameters for determining the configuration of the disk device inside the secondary storage device and the usage status of the disk device.

The configuration of the local file management table 27 and the file management information stored in the local file management table 27 are stored in the file management table of the host computer 1.
Bull 15 and file management information are the same, and the file management information of the same file is specified by the same file identification number.

The file access operation of the computer system according to the first embodiment will be described below.

First, the file management buffer management means 13 previously stores the file management information stored in the local file management table 27 of the secondary storage device 2,
It is loaded in the file management table 15 of the host computer 1. This loading is performed when the host computer is initialized, when a new storage medium is mounted on the secondary storage device, or when the file open processing described below is started.

When an open system call is issued from the AP process 12, the OS 20 performs the file open process shown in FIG.

That is, as shown in the figure, when an open system call is issued (step 101), the OS2
The file management / buffer management means 13 inside 0 analyzes this system call and judges the access mode of the file ((step 102). If the file is opened in the write mode, it is a new file. It is further determined whether or not (step 103). If it is a new file, the file name is registered in the directory management information corresponding to the directory in which the file is created in the directory management table 14, and the file management table 15 is registered. , Secures an area to store file management information for a new file (step 1
04). Further, the file identification number of the secured file management information is registered in the directory management table 14 in the directory management information corresponding to the directory in which the file is created. Then, the file identification number is notified to the process 12 (step 105).

If it is not a new file, the file identification number of the file is acquired from the directory management table 14, and this is notified to the process 12 (step 10).
5).

Next, the file management / buffer management means 1
Reference numeral 3 notifies the open file information notifying means 18 of information such as the local address and file name of the file management information specified by the file identification number unique to this file. The open file information notifying means 18 sends these pieces of information to the device driver 16 and the interface control means 2.
Notification is sent to the secondary storage device 2 via 1 and 22 (step 106).

The open file information reception registration means 39 of the secondary storage device 2 receives these pieces of information, and if the information is for a new file, a new file management is carried out in the local file management table 27. Secure the information area and register the received information.

By the above processing, the management information of the opened file is stored in the file management table 15 of the host computer 1.
And the local file management table 27 of the secondary storage device 2
It is registered in both.

Next, when the file open processing is completed, file read or write processing is executed.

FIG. 6 shows the procedure of file read processing in the OS 20, FIG. 8 shows the procedure of file write processing in the OS 20, and FIG. 9 shows the procedure of file read processing and write processing in the secondary storage device. .

First, the file read processing will be described.

As shown in FIG. 6, when a file read system call (read ()) is issued from the AP (process 12) in the host computer 1 (step 20).
1), file management / buffer management means 13 of OS 20
Refers to the directory management table 14 and acquires the file identification number of the file (indicating the position of the file management information in the file management table 15) (step 202). Next, the file management / buffer management means 13
Obtains information of file management information in the file management table 15 designated by the acquired file identification number.

Now, the AP requests a file read or write in byte units called offset by the file read system call or file write system call. FIG. 7 shows a case where the AP requests to read the offset of n bytes from the file pointer fp provided for the file fd into the user buffer buffer. As shown, this offset is data spanning logical block addresses 1 and 2, that is, two local blocks corresponding to logical blocks 1 and 2 (local block addresses # 11020 and # 11028). ) And need to lead from. The local block is a block on the secondary storage device 2 corresponding to the logical block.

Then, next, the file management / buffer management means 13 determines the logical block address 1 in which the data of the offset requested from the obtained file management information exists.
2 is calculated (step 203). Then, a system buffer is secured as a temporary work area necessary for reading these two relevant logical blocks (step 20).
4). Next, the first logical block address 1 is selected (step 205), this is converted into a local block address # 11020 (step 206), and the data block of this local block address is transferred to the device driver 16. Issue a request. Device driver 16
In response to this request, the command generates a read command unique to the secondary storage device and sends it to the secondary storage device 2 via the interface control means 21 (step 207).

As for the read command, the command management means 23 of the secondary storage device 2 receives the read command through the interface control means 22. The secondary storage device 2, which has received the command, first analyzes this command, as shown in FIG. 9 (step 402). Here, since it is known that the command is a read command (step 403), management information such as the number of accesses described later in the local file management table 27 of the secondary storage device 2 is updated as necessary (step 411), and the disk The data requested from the device 29 is read and transferred to the host computer 1 via the interface control means 22 (step 412). Then, if all the requested data can be transferred correctly, the command management means 23 reports the end to the host computer via the interface control means 22 (step 408).

This end report is received by the device driver 16 of the upper level device 1.

Returning to FIG. 6, when the command end notification is received from the secondary storage device 2 (step 208), the device driver 16 notifies the file management / buffer management means 13 of this. File management / buffer management means 1
3 confirms whether reading of all the logical blocks to be transferred is completed (step 209), and if there is a logical block which has not been transferred yet, selects the following logical block (step 212). repeat. If the transfer of the data of all the logical blocks to the system buffer is completed, the offset data requested by the AP is copied to the user buffer (step 210), and the AP is copied.
A system call completion notification is returned to and the file read processing is completed.

Next, the file write processing will be described focusing on the difference from the read processing described above.

The file write process is roughly divided into the following two processes. One is a new block registration process, and the other is an existing block update process. The former occurs when writing a new file or when adding data to the end of an existing file, and the latter when writing data from the middle of a registered logical block or when recording an existing file (record It occurs when updating in units of data unit).

Now, as shown in FIG. 8, when a write system call is issued from the AP (step 301),
The file management / buffer management means 13 of the OS 20 acquires the file identification number from the directory management table 14 (step 302), and obtains the logical block address to be transferred from the offset as described above (step 30).
3) Secure necessary system buffers (step 3)
04). Further, here, the file management table 15 is referred to, and if the local block address corresponding to the logical block address is not registered, it is determined that this logical block is a new logical block (step 305).

When the file management / buffer management means 13 determines that it is a new logical block, it copies the write data from the user buffer to the system buffer (step 307) and selects the first logical block.
On the other hand, the new file write notifying means 19 generates a new block write request that requests writing of the selected logical block. From this, the device driver 16 generates and issues a new block write command unique to the secondary storage device 2 (step 312).

A file identification number and a logical block address are described in this new block write command.

Now, as shown in FIG. 9, the issued new block write command is received by the command management means 23 of the secondary storage device 2 (step 401) and analyzed (step 402). Then, as a result of the analysis, it is recognized that the command is a new block write command (step 4
03, 404) and the command managing means 23 passes the file unique identification number and the logical block address to the new file address determining means 261. The new file address determining means 26 uses the file unique identification number to determine the local file management table 27 and the disk management table 2.
5b, the local block address for storing this block is determined in consideration of the configuration parameters and physical parameters of the disk device 29 of the secondary storage device 2 (step 405).

The procedure for determining such an optimum local block address will be described later.

Next, the local file management table 27
The determined local block address is registered in association with the logical block address, and the disk management table 25b is set to indicate that the local block is in use.

Next, the data transfer is started, and the host computer 1
The data is transferred from the memory device and the data is written to the disk device 29 according to the determined local block address (step 406). Next, new file address notification means 2
8 transmits the determined local address to the host computer 2 (step 407). Then, when the determination of the local block address of this block and the data transfer are completed, an end notification is sent to the host computer 1 (step 408).

The transmitted local block address is used as the interface control means 21 in the host device.
Also, it is received by the new file address registration means 15 via the device driver 16.

Returning to FIG. 8, the new file address registration means 15 of the host computer 1 is the interface control means 21.
When the local block address is received from the secondary storage device 2 via the device driver 16, the file management / buffer management means 13 is requested to register this local block address. The file management / buffer management means 13 registers this local block address in association with the corresponding logical address of the file management information of the corresponding file in the file management table 15 (step 314). Further, when the file management / buffer management means 13 receives the block transfer end notification from the secondary storage device 2 (step 315), the write processing of the block is ended. If the writing of all the logical blocks has not been completed, the next relevant logical block is selected, and the above processing is repeated until the writing processing of all the logical blocks is completed (step 318).

On the other hand, when it is determined in step 305 that the block to be written is not a new logical block, that is, the write processing to the existing logical block is as follows.

The basic difference between this process and the write process of the new logical block is that the write process to the existing logical block may be updated from the middle of the block, and Is that the local block address is already mapped.

First, when updating from the middle of a logical block, it is necessary to read this logical block once. That is, a block is read from the secondary storage device to the system buffer, new data is transferred from the user buffer to the system buffer, the block of the system buffer is updated, and then this block is written to the secondary storage device. There is.

Therefore, that is, when writing to an existing block, read processing is first performed (step 3).
06). The processing of this step 306 is the same as the processing from the symbols a to b shown in FIG.

Next, since the mapping of the local block address to the existing block has already been completed, when issuing the write command to the secondary storage device 2, the local computer block side specifies the local block address. . For this reason, conversion processing from a logical block to a local block address similar to the read processing is performed (step 310),
After that, an update write command to the secondary storage device is generated and issued (step 311).

On the other hand, in the secondary storage device 2, the data of the block transferred to the specified local block address is written in accordance with the received update write command (step 410 in FIG. 9). At this time, the management information such as the number of times of access, which will be described later, in the local file management table 27 of the secondary storage device 2 is updated if necessary (step 409).

As described above, according to this method, when the file is stored in the secondary storage device, the local address to be stored is determined by the secondary storage device.
It is possible to store the file at an optimum position that matches the configuration parameters unique to the secondary storage device, the physical parameters, and the file access characteristics determined by the AP characteristics of the host computer 1, which is effective for speeding up the files. Is big.

By the way, in addition to the secondary storage device 2 as described in the first embodiment, the host computer 1 has a conventional secondary storage device having no ability to determine the local block address of a new file. It is desirable that even 2 (see FIG. 24) can be connected. That is, it is desirable to configure the host computer 1 so that the conventional secondary storage device shown above can be used interchangeably.

Therefore, as a second embodiment of the present invention, a computer system in which such a conventional secondary storage device can be used interchangeably will be described. FIG. 10 shows the configuration of the computer system according to the second embodiment.

In the computer system according to the second embodiment, the disk management table 25a, the file address determining means 30, the file address determining means 30, and the new file address determining means 26 are provided in the host computer 1 according to the first embodiment. The address determining means selecting means 31 for selecting which of the two is used is added.

The disk management table 25a manages the usage status of disks. File address determining means 30
Determines the local block address of the disk device most suitable for writing when a new logical block is written.

Next, the operation of the computer system according to the second embodiment will be described.

First, at the time of initializing the system, the file management buffer management means 13 of the host computer 1 negotiates with the command management means 23 of the secondary storage device 2 via the device driver 16 to execute the secondary operation. It is determined whether or not the storage device 2 has the ability to determine the local block address of the new file, and the determination result is notified to the address determining means selecting means 31.

Then, the address determining means selecting means 31
If the secondary storage device 2 has the ability to determine the local block address of a new file, the host computer 1
The file address determining means 30 and the disk management table 25a are invalidated. After that, the same operation as in the first embodiment is performed.

On the other hand, the address determining means selecting means 31 is
If the secondary storage device 2 does not have the ability to determine the local block address of the new file, the open file information notifying means 18 and the new file write notifying means 19
Is invalidated, and the same operation as the conventional computer system described above is performed.

Furthermore, in the case where a plurality of secondary storage devices are simultaneously connected and used, the requested secondary storage device stores the new file as a new file each time the AP requests access to the secondary storage device. -Open file information notifying means 18 according to whether or not it has the ability to determine the cull block address.
Then, one of the set of the new file write notification means 19 and the set of the file address determination means 30 and the disk management table 25a is invalidated, and the same operation as the operation of the first embodiment or the conventional operation is performed.

Even when the secondary storage device 2 has the ability to determine the local block address of a new file, the open file information notifying means 18 and the new file write notifying means 19 are disabled and By disabling the new file address determining means 26, the new file address notifying means 28, etc. of the next storage device 2, the same operation as the conventional one can be performed.

As described above, according to the second embodiment, the conventional secondary storage device can also be used in the computer system of the first embodiment. In addition, it is possible to connect multiple secondary storage devices and to attach a new secondary storage device to the previously used secondary storage device, increasing the flexibility and expandability of the computer system configuration. be able to. The third embodiment of the present invention will be described below.

In the third embodiment, unlike the first embodiment, the host computer 1 does not manage the local block address of the file at all.

FIG. 11 shows the configuration of the computer system according to the third embodiment.

As shown in the figure, the host computer 1 includes a directory management table 14 for managing directories and file names and file identification numbers, a buffer management means 13a for managing buffers used for data transfer, and a device driver 16. , The interface control means 21, and the secondary storage device 2 has an interface.
And a command management unit 23a for performing file management and command management, a new address determination unit 26 for mapping a local block address to a logical block of a new file, and file management information. Local file management table 27 to register
And manages the usage status of the disk, and also disk device 2
9, a disk management table 25b in which configuration parameters and physical parameters of 9 are described, and a disk control unit 24.
And a plurality of disk devices.

The host computer 1 and the secondary storage device 2 are commands for notifying that the file is opened from the host computer 1 to the secondary storage device 2 and commands for requesting transfer of specified data in the file together with the file identification number. Is supported. The host computer 1 and the secondary storage device 2 are
Data can be mutually transferred in a form (block unit transfer or byte unit transfer) that meets the request. The interface control means 21 and 22 control such data transfer and command transmission / reception.

The operation of the computer system according to the third embodiment will be described below.

The process 12 issues a system call such as a file open and a file read / write to the OS 20. The OS 20 receives this, the buffer management unit 13a secures a buffer required for data transfer, and generates and issues an open or read / write command to the secondary storage device 2 via the device driver.
The command includes the offset contained in the system call. In issuing this command, the directory management table 14 is referred to, the file identification number of this file is acquired, and the command is transmitted to the secondary storage device 2 together with the command. When an unregistered file is opened, a file identification number is newly assigned, and the assigned file identification number is used together with the command in the secondary storage device 2.
Send to.

In the secondary storage device 2, file management /
The command management means 23a receives and analyzes the command,
If this command is a command requesting the registration of a new logical block, the new file address determining means 26
Ask to determine the storage address. The new file address determining means 26 refers to the disk management table 25b and the local file management table 27, and stores the new logical block in consideration of the configuration parameters and physical parameters of the disk device 29, the access characteristics of the AP, and the like. The local block address is determined and registered in the local file management table 27. Details of determining the local block address will be described later.

File management / command management means 2
If the analyzed command is a command requesting read or write of an existing logical block, 3a refers to the local file management table 27 to obtain the local block address of the logical block to be accessed, and this local Access the data specified by the block address and offset in the command. Then, the read data is transferred to the host computer for the read command, and the transferred data is written for the write command. Data transfer between the host computer 1 and the secondary storage device 2 is performed in units requested by the AP.

As described above, according to the third embodiment, the host computer does not need to consider the configuration, physical characteristics, etc. of the secondary storage device at all, and manages only the file name and file identification number. Good. Therefore, various secondary storage devices and other external devices can be connected to the host computer and used.

The fourth embodiment of the present invention will be described below.

FIG. 12 shows the configuration of the computer system according to the fourth embodiment.

In the computer system according to the fourth embodiment, a plurality of host computers and secondary storage devices 2 according to the third embodiment are connected.

Each host computer 1 and each secondary storage device 2 are connected by a common interface. This interface is, for example, a bus type interface known as a SCSI bus.

The operation of the computer system according to the fourth embodiment is almost the same as that of the third embodiment. However, since the management information of each file is distributed and arranged for each secondary storage device, each host computer 1 manages the secondary storage device that stores each file. This can be realized by each upper-level computer obtaining the information of the stored file from each secondary storage device at an appropriate trigger. Also, in order to prevent different files in the same secondary storage device from being assigned the same file identification number by different host computers, the secondary storage device side monitors and arbitrates double assignment of file identification numbers to new files. . This is because, for example, when a double allocation of a file identification number occurs at the time of requesting the opening of a new file from the host computer, the secondary storage device requests the host computer to reallocate the file identification number. Can be realized by Now, the sequence of command and data transfer via the bus is executed, for example, as shown in FIG. That is, first,
The arbitration is executed to logically connect the specific upper computer 1 and the specific secondary storage device 2, and the command is transferred from the upper computer 1 to the secondary storage device. Then, the host computer sends a message 1 once to release the bus to another device during the pre-processing period (command seek period of the disk device, etc.) for the command of the secondary storage device 2 To release. When the preprocessing is completed, the secondary storage device 2 transmits the message 2 and reconnects the host computer and the bus.
Then, next, the data to be read / written is transferred between the host computer 1 and the secondary storage device 2, and finally, the message 3
The normal storage or abnormal termination of the command is notified to the host computer from the secondary storage device, and the bus is released.

Incidentally, such a bus is composed of the first and second buses.
It can also be used in the examples. When used in the first and second embodiments, the local block address storing the new logical block is also transferred from the secondary storage device 2 to the host computer 1 by the message 3.

As described above, according to the fourth embodiment, each host computer 1 has a file name, its file identification number,
Since it is not necessary to retain information other than the identification of the secondary storage device that stores the file, it is possible to easily connect a plurality of host computers and a plurality of secondary storage devices. Also, since the file management information is held only by the secondary storage device that stores the file, it is possible to easily perform control on the secondary storage device side to maintain the coherency of the file with respect to multiple host devices. You can

Now, the details of the procedure for determining the local block address of each logical block of the file in the above-mentioned secondary storage device will be described.

The procedure described below can be applied to any of the first to fourth embodiments.

In FIG. 14, 24 is a disk device control means, and 29 is a disk device group composed of a plurality of units. The disk device control means 24 includes a disk device group 29.
Is managed as a RAID 5 type disk array. R
The AID5 type disk array is a disk array architecture aiming at high speed disk access and high reliability. In this architecture, data is divided into units called stripes as shown in FIG. As a result, in the access in stripe units, each disk device can be operated completely independently, and the transaction performance that is double the number of disks can be obtained.

Further, a parity group is composed of horizontal data stripe groups (for example, D00, D01, D02), an exclusive OR of these data is calculated, and parity (for example, P0) is set on one disk device. To store. This parity is distributed and arranged in different disk devices for each parity group. By this, by any chance,
Even if one disk device fails, parity can be used to restore the data of the failed disk.

In such a RAID5 type disk array, in order to optimally arrange each logical block, configuration parameters such as the stripe size, the number of disks, and the parity arrangement method are required. However, since these parameters are different for each type of secondary storage device, it is difficult to manage them in the host computer.

On the other hand, if these parameters are not taken into consideration, for example, when the stripe size and the logical block size are the same size, the logical block is not properly arranged at the head of one stripe, that is, the stripe boundary, and straddles two stripes. The situation occurs that they are placed. In this case, even when accessing one logical block, two stripes, that is, two stripes
Since it is necessary to access two disk devices at the same time, the performance is significantly reduced.

Therefore, in this embodiment, the secondary storage device 2 side determines the layout of the logical blocks based on its own configuration parameters. The following is an example of the problems caused by the placement of the logical blocks without considering the configuration parameters, and the placement of the logical blocks performed by the secondary storage device 2 based on its own configuration parameters in order to avoid this. Indicates.

First, the first example will be described with reference to FIG.

In FIG. 15a, as a result of deciding the layout of logical blocks without being aware of stripe boundaries, the data is 0
2 shows a case where the data is to be stored using two stripes, the D ₀₀ stripe of No. 1 and the D ₀₁ stripe of disk 1. In this case, since two disk devices are used for one request from the host computer, two disks, disks 2 and 3, can be used in parallel to process other requests. Become.

Therefore, the secondary storage device of the present embodiment determines the arrangement so that the head of the logical block transferred from the upper-level computer is aligned with the stripe boundary based on its own configuration parameters. Data is stored only in the D ₀₁ stripe of the disk 1 as shown in FIG.
In this case, when the host computer issues a write request for a new logical block with a fixed 8 KB, a maximum of four requests can be processed at the same time, and the processing throughput can be improved.

Next, a second example will be described with reference to FIG.

FIG. 16a shows that a new logical block of 48 KB is arranged considering only the stripe boundary. Here, in the RAID5 type disk array, it is necessary to generate parity. The required parities are P ₀ , P ₁ , and P ₂ , and these can be generated according to the following generation formula, where “*” represents an exclusive OR.

P ₀ New = (D ₀₁ Old * D ₀₂ Old)
* (D ₀₁ New * D ₀₂ New) * P ₀ Old P ₁ New = D ₁₀ New * D ₁₁ New * D ₃₁ New P ₂ New = D ₂₀ Old * D ₂₀ New * P ₂ Old Here, the subscript Old is used. The data (for example, D ₀₁ O
_{ld, D 02 Old, P 0} Old, ... , etc.) is the data that has already been written to disk, subscript New marked with data _{(D 01 New, D 02 New} , ... , etc.) data to be written right now Is. Therefore, in order to generate P ₀ , before writing D ₀₁ New and D ₀₂ New, D ₀₁ Old, D ₀₂ Old, and P ₀ Old are written from the disks 1, 2, and 3.
d must be read and D ₂₀ New must be used to generate P _2.
Prior to writing, write D ₂₀ Old, P from disc 0, 1
₂ Need to lead Old. Read before this write (read modify write process, hereafter "RM
"W process") requires a great deal of processing time.

Therefore, the secondary storage device of this embodiment determines the arrangement according to the following procedure based on its own configuration parameters.

That is, the new file address determining means 26 refers to the local file management table 27 to determine the general address. When adding a logical block to a file, the rough address is the address where this file is currently stored, and if it is the storage of the logical block of a new file, it is the area of the disk currently being used. Address. The rough address of the new logical block is selected in this way. The data that is supposed to be related to the data of the disk area that is currently being used is placed near the data of the disk area that is currently being used. This is because the time required to move the disk head stochastically decreases.

Next, when the general address is determined, the new file address determining means 26 refers to the disk management table 25 to determine the detailed address.

That is, exactly 48 near the general address.
The KB, that is, 6 stripes, is started from the stripe of the disk 0, and an area in which a new logical block can be sequentially arranged is determined as an address for storing a new file. In the case of this example, it can be known by referring to the stripe management table that a total of six consecutive data stripes, excluding the stripe #n of disk 0 to the parity stripe of stripe # n + 1 of disk 3, are unused.

As shown in FIG. 17, the disk management table further comprises a stripe management table and a sector management table.

Here, the stripe management table 1700
Has an entry for each stripe that registers whether the data stripe is a parity stripe, or whether it is in use, unused or partially used.
Further, it is possible to know for each disk whether the entire stripe is in use, unused or partially used. Further, a sector management table 1710 for managing the usage status of the sector is provided for each stripe of each disk. The sector management table 1710 shown in FIG. 17 is for a stripe size of 8 KB, and in this case, one stripe is composed of 16 512 B sectors. With such a configuration, it can be determined whether each sector is in use or unused.

For example, stripe #n of disk # 0
It can be seen that +2 (circled in the figure) has the attribute "010" and is a partially used data stripe. Therefore, referring to the sector management table of the same stripe, it can be seen that sector numbers 0 to 7 in the same stripe are in use and 8 to 15 are unused. Then, from this, it is decided to store the new logical block transferred from the host computer in the continuous area from D ₀₀ to D ₁₃ as shown in FIG. 16b.

Further, in this case, the two parity stripes that need to be generated are P ₀ and P ₁ and are generated by the following generation equations.

P ₀ New = D ₀₀ New * D ₀₁ New * D ₀₂ New P ₁ New = D ₁₀ New * D ₁₁ New * D ₁₃ New According to this generation formula, the parity can be set without reading the data prior to writing. I know that you can ask.

Assuming here that the RMW process takes 1.7 times as long as the W process on average, the RMW process becomes unnecessary 2.2 as compared with the case of storing as shown in FIG. 16a. The new logical block will be stored twice as fast.

As described above, according to the present embodiment, in the secondary storage device, the data transfer length and other related items are related to the parity arrangement method of the RAID type disk array, the stripe size, the number of disks and other parameters. Optimal file storage that considers the positional relationship with other files can be realized.

Although an example of the optimum logical block arrangement in the RAID5 type disk array has been shown above, no matter which disk device (group) is used, its configuration parameters, physical characteristics, logical block size and , It is possible to realize the optimum logical block arrangement that matches the access characteristics of the AP. Further, in the same manner, the optimum arrangement can be realized for a disk device other than the disk array, an optical disk, a tape device, a semiconductor storage device, or the like.

The fifth embodiment of the present invention will be described below.

The fifth embodiment relates to the secondary storage device 2 that can be used in the computer system according to each of the above embodiments.

The main difference between the secondary storage device 2 according to the fifth embodiment and the secondary storage device (see FIG. 3) shown in the first embodiment is that the secondary storage device according to the fifth embodiment is different. The storage device 2 is provided with a plurality of disk device groups.

FIG. 18 shows the structure of the secondary storage device according to the fifth embodiment.

In the figure, 36a1, 36a2, 36a3 are disk device groups, 24a1, 24a2, 24a3 are disk device control means for controlling each disk device group, and 34 is a disk device group for selecting which disk device group to use. A selection means, 35 is a disk device group switching means for switching the disk device group, and 25b1, 25b2, 25b3.
Is a disk management table that manages the configuration parameters, physical characteristics, and usage status of each disk group, and 1800 is a disk group update control means. Since the other parts are the same parts as the parts indicated by the same reference numerals in FIG. 3, the description thereof will be omitted.

The outline of the operation of the secondary storage device according to the fifth embodiment will be described below.

Command management means 23 of the secondary storage device 2
Receives an access request from the host computer 1, and if the request is a request to write a new logical block,
This is notified to the new file address determining means 26, and the new file address determining means 26 receives the local file management table 27 and each disk management table 2
5b1, 25b2, and 25b3, an optimum disk device group is selected and local block addresses are mapped. Then, the disk device group selection means 34 is notified of this, and the disk device group selection means 34 operates the disk device group switching means 35 to select the selected disk device group. The subsequent processing is the same as in the first embodiment.

The selection of the disk device group performed by the new file address determining means 26 is performed in consideration of the transfer length, the characteristics of the access frequency of the file itself, the characteristics of the disk device group, and the like. A more detailed example will be described later.

The disk device group according to the fifth embodiment can be specifically constructed, for example, as shown in FIG.

In the example shown in FIG. 19, the disk device group 1
Is a RAID 1 type disk array device (or mirror disk device), the disk device group 2 is a RAID 3 type disk array device, and the disk device group 3 is a RAID 5 type disk array device.

In this case, it is appropriate to store files that are frequently accessed or files that require high performance in the RAID 1 type disk unit group 1, and large capacity sequential files such as image data are stored in the RAID 3 type disk unit group 2. It is suitable to store in a random file for transactions such as database access in R
It is suitable to store it in the AID5 type disk device group 3.

Therefore, the new file address determining means 2
6 selects the disk device group as follows.

First, the new file address determining means 26
If the command from the host computer requests to update an existing logical block of an existing file,
Select a disk device group that stores existing logical blocks.

On the other hand, when the command from the host computer requests the registration of a new logical block, the new file address determining means 26 first determines in which disk device group this logical block should be registered. , According to the procedure shown in FIG.

That is, first, it is judged whether the file to which the logical block to be written belongs is new or existing (step 2001). If the file is a new file, the characteristics of the file are unknown, so the RAID 1 type disk array (disk Group 1) is selected (step 2006).

On the other hand, if the file to which the logical block to be written belongs is an existing file, the random accessibility of the file is judged (step 200).
2). The local file management table 2 is used for this determination.
7 is used.

That is, as shown in FIG. 21, the reference count field 156 of each file management information of the local file management table is provided with five subfields for access characteristic determination. Here, the first subfield is a field 1561 that stores the address (byte count from the beginning of the file) of the request from the host computer that was referenced last time, and the second subfield is the transfer length (byte count) that was referenced last time. Field 1562 for storing the number of random access times, the third subfield 1536 for indicating the frequency of random access times, and the fourth subfield 156 for indicating the frequency of sequential access times.
The fourth and fifth subfields are a field 1565 that stores the total number of times this file is referenced. The random access count field 1563 and the sequential access count field 1564 are updated by the following process each time the file is accessed. That is, it is determined that the expression present reference address ≦ previous reference address + previous transfer length + α, and if the expression is satisfied, it is determined that this access is sequential, and 1 is added to the sequential access count subfield 1564. If not established, it is determined to be random access, and 1 is added to the random access number subfield 1563. However, the "current reference address" is the position (number of bytes) from the head of the file of the write request of the host computer, and α is a constant for determining the sequentiality. Note that if it is desired to make only completely continuous accesses sequential, α = 0 may be set, and if it is desired to determine the sequentiality with a certain width, α may be set to a certain value. In this way, the randomness / sequentiality is determined every time the file is referenced.

Now, returning to step 2002, the random accessibility of the existing file is judged, that is, the random accessibility is judged to be large or small as follows.

That is, with A and B as appropriate set values,
If the value of the reference count field 1565 of the corresponding file management information is larger than A, the value of the random access count field 1563 / the reference count field 1565.
If the value of B is greater than or equal to B, it is determined that the random accessibility is high, and the value of the reference count field 1565 is greater than A,
If the value of the random access count field 1563 / the value of the reference count field 1565 is less than B, it is determined that the random accessibility is low. Also, the reference count field 1
If the value of 565 is smaller than A, it is determined that the determination cannot be made.
If the reference count is smaller than a certain value A,
This is because the file has just been created, and the sequential / randomness cannot be determined yet.

Next, as a result of this judgment, if the randomness is large, the RAID5 type disk array (disk group 3) is selected (step 2004), and if the judgment cannot be made, the RAID1 type disk array (disk group 1) is selected (step 2004). Step 2006). Here, when the judgment cannot be made, the RAID1 type disk array (disk group 1) is selected because the file just created should be stored in the RAID1 type disk array (disk group 1). is there.

In step 2002, random access ratio = random access count / reference count is constant B.
It is determined whether or not it is greater than (O <B < 1), but the sequential access ratio is determined by the value of the sequential access count field 1564 / reference count field 1565.
You may make a judgment based on the value of,
You may make the determination which considered both.

If it is determined in step 2002 that the randomness is small, the transfer length is determined. That is,
If the data length (transfer length) requested to be written by the command is greater than or equal to a certain value C, it is determined that the transfer length is large and R
Select the AID3 type disk array (disk group 2). When the transfer length is less than a certain value C, RAI
Since the D3 type is inefficient, the RAID1 type is selected.

As described above, an appropriate disk group is selected by determining whether the new file is an existing file, the randomness is large or small, and the transfer length is large or small. Then, a new logical block is written to the selected disk group, and if the selected disk group is different from the disk group in which the existing logical block of the existing file to which the new logical block belongs is stored, The existing logical block is moved to the created disk group, and the file management table is updated according to this. At this time, an update flag 188 indicating the presence / absence of rearrangement of files provided in each file management information of the local file management table 27.
Is set to "updated".

In the above, all new files are
It was decided to write to the RAID 1 type disk array (disk group 1). This is because the access characteristics are unknown. However, the RAID 1 type disk array has the same performance as one disk except that it is highly reliable, and is not suitable for accessing a file having a strong randomness or a file having a strong sequence sealability. Further, since the disk capacity is also limited, it is desirable to reselect a disk group suitable for the access characteristic and move the file at an appropriate timing.

Therefore, the disk group update control means 1800
However, it periodically issues a request to the command management means 23 to reselect the disk group to be stored for each file.

The command management means 23 receives this request,
The update flag 188 of each file management information of the local file management table 27 is referred to. If the update flag is set to "unupdated", the file is a newly created file, so the disk device group selecting means. And then
An attempt is made to reselect a disk group according to the procedure shown in FIG.

If it is determined that the file has a strong randomness or sequentiality, the disk group as described above is selected, and if a disk group other than the RAID 1 type disk array (disk group 1) is selected, The file is moved to the disk group, and the update flag 188 is set to "updated".

If it cannot be determined, the file is placed on the disk group 1 as it is. At this time, the update flag remains "unupdated". Since the access request to this file may be issued from the host computer during the file movement, the update flag is set to "Updating" at this time. In addition, a new file management table is created again as the file is moved, and when the file is completely moved, the file management table is switched to a new one and the old one is deleted. The registration of the logical block after the selection of the disk group to the logical block address may be performed as described above.

By the above processing, the disk group suitable for the access characteristic can be selected.

In the above, RAID is set as the disk group.
Although the example using the 1-type, RAID 3-type, and RAID 5-type disk arrays has been used, a disk group suitable for the access characteristics can be selected by the same procedure even if another device is introduced.

The disk device group according to the fifth embodiment (see FIG. 19) can also be constructed as shown in FIG.

In the example shown in FIG. 22, three disk array devices each having a different stripe size, which is one of the configuration parameters, are set as disk device groups 1, 2, and 3. In this case, to store a relatively small file, in the disk device group 1 with a small stripe size set,
On the contrary, in order to store a sufficiently large file, it is appropriate to register it in the disk device group 3 in which the stripe size is set large. Therefore, if the disk device group is selected according to the file length, the disk group suitable for the characteristics of the file can be selected.

Alternatively, by selecting a disk group in which the transfer length is the stripe size × the number of disks × n according to the transfer length of data, it is possible to efficiently obtain the transfer performance for the number of disks. it can.

Further, the disk device group according to the fifth embodiment (see FIG. 19) can also be constructed as shown in FIG.

In the example shown in FIG. 23, the disk device group 1
The magnetic disk device is used for the disk device group, the optical disk device is used for the disk device group 2, and the tape library device is used for the disk device group 3. In this case, it is desirable to register files that are frequently accessed in the magnetic disk device, files that are not frequently accessed in the optical disk device, and files that are rarely accessed (backup, etc.) in the tape library device.

Therefore, the disk group update control means 1800 issues a request to the command management means 23 to reselect the disk group to be stored for each file at certain fixed time intervals. Then, the command management means 23
In response to this request, the previous reference time of the time stamp 153 of each file management information in the local file management table 27 and the reference count field 1565 are referenced to determine whether or not this file has been recently accessed. Determine if the number is high. If it has not been accessed for a certain period of time, it is an old file and it is inefficient to occupy the space on the high-speed disk, so that the file is moved to an optical disk or the like.

Note that, for example, at night, files stored in another disk device may be copied to the tape library device and backed up.

As described above, according to this embodiment, a plurality of disk device groups can be provided in the secondary storage device, and by changing the configuration thereof, logical block suitable for various access requests and file characteristics can be obtained. There is an effect that mapping to a logical block address can be realized and various forms of storage systems and computer systems can be constructed.

As described above, according to the present embodiment, it is possible to realize the optimum file arrangement in consideration of the configuration parameters and physical parameters peculiar to the secondary storage device and in conformity with the access characteristics of the AP of the host computer. Can realize high-speed file access. Further, this makes it possible to realize a high-performance computer system. Further, not only the secondary storage device of the present invention but also the conventional secondary storage device can be connected to the host computer, so that a flexible computer system can be constructed. Further, since the host computer does not need to consider the configuration and physical characteristics of the secondary storage device, various secondary storage devices can be easily connected to the host device. Further, it is possible to easily construct a distributed file management type computer system in which a plurality of host computers and a plurality of secondary storage devices are connected.

[0177]

As described above, according to the present invention, a computer system capable of realizing optimum placement of files in a secondary storage device without setting parameters of the secondary storage device in a host computer. Can be provided.

[Brief description of drawings]

FIG. 1 is a block diagram showing a hardware configuration of a computer system according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram showing a concept of file management in the embodiment of the present invention.

FIG. 3 is a block diagram showing a configuration of a computer system according to the first embodiment of the present invention.

FIG. 4 is an explanatory diagram showing a configuration of a file management table according to the first embodiment of the present invention.

FIG. 5 is a flowchart showing a procedure of file open processing performed by the OS according to the first embodiment of the present invention.

FIG. 6 is a flowchart showing a procedure of file read processing performed by the OS according to the first embodiment of the present invention.

FIG. 7 is an explanatory diagram showing a relationship between data to be accessed and a logical block.

FIG. 8 is a flowchart showing a procedure of file write processing performed by the OS according to the first embodiment of the present invention.

FIG. 9 is a flowchart showing a procedure of file read / write processing performed by the secondary storage device according to the first embodiment of the present invention.
It is

FIG. 10 is a block diagram showing a configuration of a computer system related to a second example of the present invention.

FIG. 11 is a block diagram showing a configuration of a computer system related to a third example of the present invention.

FIG. 12 is a block diagram showing a configuration of a computer system related to a fourth example of the present invention.

FIG. 13 is a time chart showing a transfer sequence between a host computer and a secondary storage device according to the fourth embodiment of the present invention.

FIG. 14 is an explanatory diagram showing stripes of a disk array device.

FIG. 15 is an explanatory diagram showing how a local address is assigned to a logical block.

FIG. 16 is an explanatory diagram showing how local addresses are assigned to logical blocks.

FIG. 17 is a block diagram showing a configuration of a stripe management table and a sector management table according to an embodiment of the present invention.

FIG. 18 is a block diagram showing the configuration of a secondary storage device according to the fifth embodiment of the present invention.

FIG. 19 is a block diagram showing a first specific structural example of the secondary storage device according to the fifth embodiment of the present invention.

FIG. 20 is a flowchart showing the procedure of disk group selection processing according to the fifth embodiment of the present invention.

FIG. 21 is an explanatory diagram showing the structure of a local file management table according to the fifth embodiment of the present invention.

FIG. 22 is a block diagram showing a second specific configuration example of the secondary storage device according to the fifth embodiment of the present invention.

FIG. 23 is a block diagram showing a third specific configuration example of the secondary storage device according to the fifth embodiment of the present invention.

FIG. 24 is a block diagram showing the configuration of a conventional computer system.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Host computer 2 ... Secondary storage device 12 ... Process 13 ... File management / buffer management means 14 ... Directory management table 15 ... File management table 16 ... Device driver 17・ ・ ・ New file address determining means 18 ・ ・ ・ Open file information notifying means 19 ・ ・ ・ New file write notifying means 20 ・ ・ ・ Operating system 21 ・ ・ ・ Interface control means 22 ・ ・ ・ Interface control means 23 ・ ・ ・Command management means 24 ... Disk device control means 25b ... Disk management table 26 ... New file address determination means 27 ... Local file management table 28 ... New file address notification means 29 ... Disk device

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor ▲ Yoshi ▼ Minoru Tata 2880 Kokufuzu, Odawara City, Kanagawa Stock Company Hitachi Storage Systems Division

Claims (14)

[Claims] 1. A computer, and one or a plurality of secondary storage devices connected to the computer, wherein the secondary storage device comprises:
A computer system that manages data stored by a local address that is a local address in a secondary storage device, wherein the secondary storage device stores a file configured by one or a plurality of logical blocks. Means for executing access to a logical block having a local address requested by the computer, which is already stored in the storage means, and storage of a new logical block in the storage means when the computer requests , Means for deciding a local address to store the logical block requested to be stored by a predetermined procedure, means for storing the logical block requested to be stored at the decided local address, and notifying the computer of the decided local address The computer stores the files stored in the secondary storage device. A file management table for managing a local address in which each logical block to be stored is associated with each logical block and a logical management block that is already stored in the secondary storage device. To determine the local address of the logical block to be accessed, request the secondary storage device to access the logical block of the obtained local address, and to store a new logical block in the secondary storage device. ,
A means for requesting the secondary storage device to store a new logical block without specifying a local address, and the local address notified from the secondary storage device is associated with the new logical block for which storage is requested. And a means for registering in the file management table. 2. A computer and one or a plurality of secondary storage devices connected to the computer, wherein the secondary storage device comprises:
A computer system that manages data stored by a local address that is a local address in a secondary storage device, wherein the secondary storage device stores a file configured by one or a plurality of logical blocks. , A local file management table that manages a local address where a logical block forming a file stored in the storage means is stored in association with a file identifier designating the file and a logical block, and is requested to be stored. If the specified data belongs to a logical block already stored in the storage means, the file, the relative address in the file and the data length are specified, and the local address of the data requested to be accessed by the computer is specified. File identifier, relative address, data length, and the file Means for obtaining from the management table, means for accessing data stored at the obtained local address,
A file identifier and a file in the case where storage of data in the storage means is requested by the computer and the data requested to be stored does not belong to a logical block already stored in the previous storage means. Means for determining a local address for storing a new logical block to which the data requested to be accessed by the computer by designating a relative address and a data length in the predetermined address, and a new logical address for the determined local address. A means for storing the block, a means for deciding a local address for storing the logical block constituting the new file by a predetermined procedure when the storage of the new file in the storage means is requested, And a means for storing the logical block that constitutes the new file requested to be registered at the specified local address. The determined local address has a logical block stored at the local address, and means for registering in the local file management table in association with a file identifier to which the logical block belongs. When accessing the data of the file stored in the storage device, the secondary storage is performed by specifying the file identifier assigned to the file to which the data to be accessed, the relative address in the file of the data to be accessed, and the data length to be accessed. A means for requesting the device to access the data, and a new file identifier is assigned to the file when the data of the new file is stored in the secondary storage device, and the file identifier and the data file to be stored Specify the relative address in the Computer system and having a means for requesting the storage of the new file to the secondary storage device. 3. A secondary storage device for storing data, comprising:
A computer in which one or more secondary storage devices for managing data stored by a local address that is a local address in the secondary storage device are connected, wherein the computer is a file stored in the secondary storage device. A file management table that manages the local addresses in which the respective logical blocks that make up the logical blocks are stored is associated with the respective logical blocks, and the secondary storage device that is connected determines the local addresses that store the logical blocks. Means for determining whether or not it has capability, and a local address of a logical block to be accessed obtained by referring to the file management table when accessing a logical block already stored in the secondary storage device. A means for requesting access to the relevant logical block to the secondary storage device, and a new logical block When performing storage to a secondary storage device having the ability to determine a local address for storing a logical block, requesting the secondary storage device to store a new logical block without specifying a local address. And a request to store a new logical block, the local address notified from the secondary storage device having the ability to determine the local address for storing the logical block is newly requested to be stored. A means for registering in the file management table in association with a logical block and a new logical block is stored in a secondary storage device that does not have the ability to determine a local address for storing the logical block. A means for determining a local address for storing the new logical block by a predetermined procedure, and the determined local address for the file Means for storing in the management table and means for requesting recording of the new logical block to the secondary storage device which does not have the ability to specify the determined local address and determine the local address for storing the logical block. A computer having: 4. A secondary storage device for storing data, comprising:
A computer in which one or more secondary storage devices for managing data stored by a local address that is a local address in the secondary storage device are connected, wherein the computer is a file stored in the secondary storage device. A file management table that manages the local addresses in which the respective logical blocks that make up the logical blocks are stored is associated with the respective logical blocks, and the secondary storage device that is connected determines the local addresses that store the logical blocks. A means for determining whether or not it has the capability, and a local address of data to be accessed obtained by referring to the file management table when accessing a logical block already stored in the secondary storage device And means for requesting access to the logical block to the secondary storage device,
When a new logical block is stored in a secondary storage device that does not have the ability to determine the local address for storing the logical block, the local address for storing the new logical block is determined by a predetermined procedure. Means for storing the determined local address of the logical block in the file management table in association with the logical block, and the determined local address,
A means for requesting the recording of the new logical block to the secondary storage device that does not have the ability to determine the local address for storing the logical block and an ability for determining the local address for storing the logical block in the new file are provided. When storing in the secondary storage device that has, by specifying the file identifier representing the file, the relative address in the file of the data to be accessed and the data length to be accessed,
And a means for requesting the secondary storage device to store the file. 5. A secondary storage device that is connected to a computer and manages data stored by a local address that is a local address within the device itself, and stores a file composed of one or a plurality of logical blocks. Storage means, means for determining a local address to store the logical block requested to be stored by a predetermined procedure when the computer requests storage of a new logical block in the storage means, and the determined local And a means for storing a logical block requested to be stored at an address. 6. A secondary storage device which is connected to a computer and manages data stored by a local address which is a local address in the device itself, and stores a file composed of one or a plurality of logical blocks. A storage unit; a local file management table that manages local addresses, in which the logical blocks that make up the files stored in the storage unit are stored, in association with the files and the respective logical blocks; When it is requested to record data that does not belong to the logical block already stored in the means, the means for determining the local address for storing the new logical block to which the data belongs is determined by a predetermined procedure, and the determined local address The means for storing the new logical block and the determined local address A secondary storage device comprising: a logical block stored at the local address; and means for registering in the local file management table in association with a file to which the logical block belongs. 7. The computer system according to claim 1, 2, 3 or 4, wherein the storage means of the secondary storage device is a disk array device, and a predetermined local address for storing the logical block is set. The computer system characterized in that the means for deciding by a procedure is a means for deciding a local address by which a data belonging to a logical block can be accessed in parallel in a predetermined procedure. 8. The computer system according to claim 1, 2, 3 or 4, wherein the storage means of the secondary storage device is a plurality of storage devices of different types and stores the logical block. The means for determining a local address to be stored by a predetermined procedure determines the local address of the new logical block according to the characteristics of the file to which the new logical block to be recorded belongs and the characteristics of the plurality of storage devices. And computer system. 9. A computer and one or a plurality of secondary storage devices connected to the computer, wherein the secondary storage device is
A method of accessing a file in a computer system that manages data stored at a local address that is a local address in a secondary storage device, the method comprising: file identification information for identifying a file and a file in the secondary storage device. And a step of providing a local file management table that stores the stored local address in association with each other, and the computer records a new file in the secondary storage device.
A step of designating and requesting identification information of the file; a step of the secondary storage device determining a local address for storing the new file requested to be recorded; and a step of the secondary storage device determining the storage medium. And a step of storing the new file in the local address, and a step of storing the new file in the local file management table, in which the secondary storage device associates the determined local address with identification information of the specified file. How to access the file. 10. The file access method according to claim 9, wherein the secondary storage device notifies the computer of the determined local address, and the computer requests recording of the notified local address. Managing the file in association with the file; providing the computer with a file management table that stores the file identification information for identifying the file and the local address where the file is stored in association with each other; When accessing a file stored in the secondary storage device, a step of obtaining a local address managed in association with the file from the file management table, and the computer is already stored in the secondary storage device. Access to the specified file, specify the obtained local address, and specify the secondary storage device. The method further comprises the step of requesting and the step of accessing the file at the local address specified in the request when the secondary storage device is requested to access the file already stored in the secondary storage device. How to access the file. 11. A computer and one or a plurality of secondary storage devices connected to the computer, wherein the secondary storage device is stored by a local address which is a local address in the secondary storage device. A computer system for managing data, wherein the computer associates a local address notified from the secondary storage device with a logical block of data stored at the notified local address of the secondary storage device. A computer system characterized by having a file management table for recording. 12. A computer and one or a plurality of secondary storage devices connected to the computer, wherein the secondary storage device is stored by a local address which is a local address in the secondary storage device. In a computer system for managing data, the computer is a method of storing a file in the secondary storage device, the computer, when newly storing a logical block constituting a file in the secondary storage device, Issue a logical block storage request to the secondary storage device that includes an identifier requesting to determine a local address for storing the logical block in the secondary storage device, the file identifier, and the logical address of the logical block. However, the secondary storage device stores the local address determined in response to the storage request of the logical block in the logical block. In response to the pay request, wherein the issuing to said computer. 13. A computer and one or a plurality of secondary storage devices connected to the computer, wherein the secondary storage device is stored by a local address which is a local address in the secondary storage device. In a computer system for managing data, the computer is a method of accessing data in the secondary storage device, wherein the computer is stored in the secondary storage device when accessing data in a file. Issuing an access request including an identifier of the file, a relative address of the data from the beginning of the file, and a size of the requested data, and the secondary storage device stores the file included in the access request. The identifier, the relative address of the data from the beginning of the file, and the local address corresponding to the size of the requested data. How to access over data, as a response of the result for the access request, and issues a completion status to the computer. 14. A secondary storage device which is connected to a computer and manages data stored by a local address which is a local address in the device, and stores a file composed of one or a plurality of logical blocks. Storage means, means for determining a local address to store the logical block requested to be stored by a predetermined procedure when the computer requests storage of a new logical block in the storage means, and the determined local A secondary storage device comprising means for notifying an address to the computer.