JP2003280950A - File management system - Google Patents

Abstract

An object of the present invention is to store metadata of a file separately from a storage device storing the file data, and to perform dynamic relocation of the file data between the storage devices. Provide a file management system with improved usage efficiency. SOLUTION: A data storage device 50 to 54 storing file data is provided to an access client 5 by a storage device 60 storing free information of a file data storage location and a storage device 61 storing file metadata is a metadata server. 6 is connected. The metadata server collects a token related to the file from the access client, and issues a request to the access client to rewrite the file data of the file to another data storage location in accordance with the space information. Based on the storage location information and the access right information of the file included in the metadata, the access location of the access client is exclusively controlled to change the storage location of the file.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a file management system in a computer. In particular,
The present invention relates to a file management system having a plurality of file data storage devices and capable of dynamically relocating file data between the storage devices.

[0002]

2. Description of the Related Art Various multitasking and multiuser operating systems (OS) used in computers have been developed. These OSs include
A file system for managing data files is provided. This data file is stored and managed in a storage device such as a magnetic disk or magnetic tape.

A general management form of this data file is shown in FIG. The file system 1 shown in FIG. 5 is a program that constitutes a part of the OS of the host computer, receives an access request to the data file from the user through the file access interface 4, and causes the host computer to access the device driver 2
Access a plurality of storage devices 3 connected via the

In the storage device 3, in addition to the data file which is the user data, management information called metadata (i-node) for managing the way of the user data is discretely arranged in a plurality of blocks of each storage device. There is. In FIG.
The storage state of the metadata and the file data is shown in the storage device 3 in a simplified manner. A disk pool is configured by a plurality of storage devices 3 or is configured as a RAID.

In FIG. 5, the file access interface 4 has a network file system (NF).
S) is adopted, and a state in which a plurality of storage devices 3 are incorporated in a file sharing system with other computers is shown.

[0006] Here, the file system 1 of the host computer determines all of the storage devices in which of the plurality of storage devices 3 to store the user data file, and recognizes the storage status. . The device driver 2 or the storage device 3 cannot recognize the storage status at all. Therefore, when the file system 1 receives an access request from the user, the file system 1 accesses the requested data file and returns the result to the user.

In such a file system, in the storage device for storing the data file, the storage location (logical storage location) of the data file recognized by the file system is statically and uniquely determined for each mount point. ing. At the storage location, both the file metadata (i-node) and the file data are placed together.

By arranging them in a predetermined structure, the position of the inode within the storage location can be calculated, and the position of the file data can be known from the information written in the inode. It has become. However, not only the storage location of the metadata but also the storage location of the file data is fixed.

[0009]

On the other hand, in a disk array device such as a RAID configuration, a plurality of physical data storage devices (physical disks) are made to appear as one logical data storage device (logical disk), and the The physical data storage location can be changed without changing the specific data storage location.

When these devices are used as the file data storage location, the storage location can be changed in disk units. However, since the storage device recognizes the stored data only in block units and not in file units, it is not possible to move data in file units.

In the conventional file system described above, the storage location of file data is statically determined for each mount point and cannot be dynamically changed. This causes the following problems. 1) In the file system, when the initially used storage location becomes full, another storage location cannot be used. 2) When a plurality of storage locations such as a disk array are used and the access frequencies are unevenly distributed among the storage devices, the storage locations cannot be rearranged to make the access frequencies even. 3) When high-speed data storage devices and low-speed data storage devices are used together, always consider the entire system, considering the difference in performance between the data storage devices, the importance of each file, and the access frequency. Data cannot be rearranged to maximize performance as.

When a RAID configuration storage device is combined with a conventional file system, the RAID configuration has a function of making a plurality of physical data storage devices logically appear as one data storage device. , Multiple data storage devices can be used for one mount point.

According to this combination, the problems shown in 1) above are solved. However, when the cause of the problem shown in 2) is the uneven access frequency for each file, each data storage device having a RAID configuration does not recognize the file unit at the level of the storage device. , This method cannot handle. Similarly, the problem shown in 3) cannot be solved unless the file unit can be recognized.

Further, in the data storage device having the RAID structure, in the case where a failure occurs in a certain data storage device, in order to automatically restore the data stored in the data storage device, a recovery spare is prepared in advance. It is necessary to prepare the data storage device of or to reserve a spare data storage area. This has a problem that the use efficiency of the data storage device is deteriorated.

Therefore, the present invention is a file management system in a computer having a plurality of data storage devices, in which management information regarding data files is stored in a storage location different from the data storage device in which the data files are stored. It is an object of the present invention to provide a file management system in which file data can be dynamically relocated between data storage devices by managing the data storage devices and the usage efficiency of each data storage device is improved. .

[0016]

In order to solve the above problems, according to the present invention, in a file management system in a computer, management for managing empty information of a file data storage location, file metadata and access right information. The management control unit includes a control unit and a data access unit that accesses the stored file data and rewrites the file data, and the management control unit includes the storage location information of the file included in the metadata and the access right. Based on the information, the data access of the data access means is exclusively controlled to change the storage location of the file.

The file control unit is provided with a plurality of data storage devices so that the file data and the metadata are stored in different data storage devices, and the management control unit allows the token related to the file from the data access unit. The data access means is requested to rewrite the file data of the file to another data storage location according to the availability information.

Further, in the plurality of data storage devices,
When the management control means includes information of different data access speeds and importance information is set for each file, the management control means determines the data access speed according to the importance. A data storage device is selected to change the storage location of the file data, or the plurality of data storage devices include those having different data access speeds, and the management control means includes When the data access frequency is measured and the access value is held, the management control means selects the data storage device having the data access speed according to the data access frequency to store the file data. I decided to change the location.

Further, the plurality of data storage devices are RA
In the ID configuration, when a failure related to one of the data storage devices occurs, the management control unit restores the file data stored in the data storage device from the parity according to the RAID configuration. File data is stored in the other data storage device.

[0020]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of a file management system according to the present invention will be described below with reference to the drawings.

In the conventional file system, as described above, the metadata (i-node) as the file management information and the file data are placed in the same data storage device. In the system, a metadata server that is a metadata management mechanism is provided, and the metadata (i-node) related to the stored file and the file data are arranged on different data storage devices. With this configuration, even if the storage location of the file data is changed, the storage location of the metadata related to the file is not changed and the reference to the metadata related to other files is not affected. Become.

In the file management system of this embodiment,
Furthermore, a plurality of file data storage locations can be assigned to one mount point. This is because the storage location of metadata is different from the storage location of file data, and since there is only one storage location of metadata, even if there are multiple storage locations of file data, it does not affect the reference of metadata. realizable. Which of the plurality of allocated data storage locations has been used and which one should be used next is managed by the metadata management mechanism by holding an index of an unused area.

For each file, which information is used among the plurality of storage locations is held in the metadata for each file. By doing so, it becomes possible to specify, for each file, which of the plurality of storage locations is being used, and the storage location of the file data can be changed by rewriting the storage location information.

In order to dynamically change the file storage location while the system is operating, the above processing must be exclusively performed. If another process references or updates the file while moving the storage location of the file, the integrity of the file contents cannot be maintained.

Therefore, in the file management system of this embodiment, when a token (access permit) is prepared for each file and the data access mechanism for accessing each data storage device refers to or updates the file,
I needed this token. This token is managed by the metadata management mechanism, and the data access mechanism acquires this token from the metadata management mechanism when needed.

When moving the storage location of the file, the metadata management mechanism collects all the tokens from the data access mechanism so that the data access mechanism does not refer to or update the file. I'm going to control it. As a result, the storage location of the file can be moved dynamically.

Next, an example of the file management system of this embodiment will be described with reference to FIG. FIG. 1 shows a schematic block configuration of the file management system of this embodiment.

In the file management system shown in FIG.
An access client 5 as a data access mechanism and a metadata server 6 as a metadata management mechanism are arranged in the file system shown in FIG. Also, a case where a hard disk is used as a data storage device for file data and metadata is shown.
To 54 are managed by the access client 5, and the disks 60 and 61 are managed by the metadata server 6.

The file data FD01 to FD43 are distributed and stored in the disks 50 to 54, respectively. In addition, the disk 60, the disk 5
A free space management index indicating a free status in 0 to 54 is further stored in the disk 61, and metadata MD1 to MD4, which are management information regarding the file data FD01 to FD43, are stored therein.

The file data FD01 to FD43 are
1 in the disk due to the file management system
It is divided into two or more and stored. The division is performed in block units in the file system, and each divided is called an extent. The file data storage location information exists for each extent, and the following information is described in each extent. -Logical block number in the file system of the first block of the extent-Extent length-Storage disk ID-Start position in the storage disk File data having such information is for file data connected to the access client 5. Disk 5
0 to 54, and the metadata (i-node) of each file is stored in a metadata disk 61 different from the disks 50 to 54. The access client 5 and the metadata server 6 are
Data transmission / reception with each disk is performed via a device driver as in the system of FIG. 5, but the disk driver is omitted in FIG. 1 for simplification.

Here, the operational roles of the metadata server 6 and the access client 5 are summarized as follows.

[Operation of Metadata Server] 1) Metadata MD1 to M from the access client 5
If there is a D4 acquisition request, the metadata disk 61
To access the required metadata and return the required metadata to the access client 5. 2) When there is a metadata update request from the access client 5, the metadata disk 61 is accessed, the metadata is rewritten, and the response is returned to the access client 5. 3) When there is a request from the access client 5 to use a new area on the file data disks 50 to 54, refer to the free space management index stored in the disk 60 managed by the metadata server 6 itself. Then, the free space of the file data disk is notified to the access client 5, the free space management index is updated, and, for example, “used” is recorded in the storage space of the disk. 4) When there is a token request from the access client 5, it is confirmed whether another process is using the token. Pass the token if it is not used. When it is in use, a token collection request is sent to the process in use, and after it is returned, it is passed to the original token requester.

[Operation of Access Client] 1) Receive an access request to the files FD01 to FD43 from the user. 2) The metadata server 6 is requested to acquire the metadata related to the file that needs to be accessed. 3) The file data disks 50 to 54 are accessed based on the metadata received from the metadata server 6, and the file data is acquired / updated. 4) When the metadata needs to be updated as a result of access to the file data, the metadata server 6
Send an update request to. 5) Return the response to the access request from the user.

Regarding the operation of the access client 5 and also the data server 6 described above, the case where the access client 5 is a file management system incorporating an operating system has been described, but as shown in FIG.
It can also be realized as an NFS server. Also,
The access client 5 and the metadata server 6 may be placed on different computers, or may coexist on a single computer. Further, the two modules may not be divided and may be integrated as one module.

The data storage device in the system of FIG. 1 need not be a magnetic disk, but may be another storage device such as a magnetic tape device. Further, in FIG. 1, the free space management index is the metadata MD1 to M.
Although it is stored on a disc different from D4, it may be stored together on the metadata disc 61.

Next, with reference to FIG. 2, description will be given of a processing flow in the case where the storage location of the desired file data is moved to another storage location in the file management system shown in FIG.

The file management system shown in FIG. 2 is similar to the system shown in FIG. 1, and the same parts are designated by the same reference numerals. In the figure, the flow of information relating to the file data transfer process is indicated by an arrow, and the respective flows are labeled with (a) to (h).

Then, the movement of the file data will be described according to the information flows (a) to (h), and the processing is performed as follows.

(A) The metadata server 6 collects the token relating to the file moved from the access client 5 in order to perform the exclusive control. In FIG. 2, the file data FD01 stored in the disk 50 is being moved. The collected token is for this file data FD01.

(B) The metadata server 6 issues a transfer request for the file data FD01 to the access client 5.

(C) The access client 5 requests the metadata server 6 to acquire a free space in order to know the free space of the disk to which the file data is moved.

(D) The metadata server 6 refers to the free space management index stored in the disk 60 on the basis of the free space acquisition request, and searches for a free space in the file data transfer destination disk.

(E) The metadata server 6 notifies the access client 5 of the storage location A of the unused space.

(F) The access client 5 receives the empty space storage location A notified from the metadata server 6.
The file data FD01 is copied to.

(G) Upon completion of copying the file data to the destination, the access client 5 requests the metadata server 6 to update the metadata. In FIG. 2, it is assumed that the management information related to the file data FD01 is stored in the metadata MD2 stored in the disc 61.

(H) The metadata server 6 rewrites the storage location information in the metadata MD2 of the file data FD01 and records that the file data FD01 is stored in the new storage location A.

As the file data is moved, the "storage disk ID" and the "start position in the storage disk" are rewritten in the metadata indicating the storage location information of the file data as described above. For example, disk 5
Assuming that the ID of 0 is 0 and the ID of the disk 52 is 2,
"File ID of storage disk"
Is changed from 0 to 2. Also, the file data FD0
The write start position of 1 is 1 and the position of storage location A is 2
, The “start position in the storage disk” is 1
Changed from 2 to 2.

As described above, the file data transfer processing in the file management system is completed.

By configuring the file management system shown in FIG. 1, it is possible to dynamically and automatically change the file data storage location for each file. According to this system configuration, when the storage capacity of the connected data storage device becomes full and additional data storage devices are added, the stored file data can be equally divided into both data storage devices. It enables flexible operation of the data storage device.

When the data storage device becomes old, a new data storage device is added, and the files on the old data storage device are gradually moved to the new data storage device. Can be moved to a new data storage device to replace the data storage device.

The basic case has been described above in which the file management system according to the present embodiment dynamically changes the storage location of file data among a plurality of data storage devices. Next, a case will be described in which the file management system shown in FIG. 1 is used to dynamically relocate file data among a plurality of data storage devices to improve the usage efficiency of each data storage device. .

As a first embodiment, in consideration of the access frequency to each file stored in a plurality of data storage devices, the files are stored between the data storage devices so that the bias of access to the data storage devices is reduced. Relocate data dynamically.

Therefore, the measured access count of each file is held in the metadata for the stored file. In addition, the number of accesses for each mount point and the number of accesses for each data storage device are held in the metadata server 6. If these access counts are held, the degree of access frequency bias among the data storage devices can be calculated based on the access counts.

Then, a threshold value is set in advance so that the bias in access frequency among the data storage devices can be discriminated.
For example, among files using a data storage device with high access frequency, a file whose deviation from the average access frequency is equal to or higher than a set threshold value is detected. Relocate the detected file to a data storage device with low access frequency. When rearranging the file, the file is moved according to the processing procedures (a) to (h) described with reference to FIG. By this file movement, it is possible to equalize the uneven access frequency among the data storage devices in the dynamic state of the system.

As described above, since the access frequency can be discriminated by holding the access frequency,
It is possible to correct load concentration due to uneven access frequency among a plurality of data storage devices, and further to improve throughput of the entire system by load distribution in a system with a high load.

Next, as a second embodiment, a plurality of data storage devices have different data access speeds, and
A case will be described where the files stored in the respective data storage devices have different importance levels.

For example, a plurality of data storage devices having different data access speeds may be used in a mixed manner, such as the seek time of a magnetic disk device. Therefore, the level of access speed for each data storage device is registered in advance in the metadata server 6. Then, for each file, the importance of the file can be registered by the user. The importance information is stored in the corresponding metadata of each file.

Then, a file having a high degree of importance is preferentially assigned to a data storage device having a high data access speed when the data arrangement is determined according to the degree of importance. A data storage device having a low data access speed is assigned to a less important file.

Further, even after the data is arranged, the importance of each file is re-examined at regular intervals so that the file of relatively high importance is stored in the data storage device of high access speed. Are relocated to a data storage device with a slow access speed. When rearranging this file, the processing procedure (a) described with reference to FIG.
The file is moved according to steps (h) to (h).

By this movement and relocation, files having high importance are concentrated and stored in the data storage device having high access speed, and files having low importance are collected in the data storage device having low access speed. Become. Therefore, even if a low-cost data storage device group is used, it becomes possible to increase the data access speed for files of high importance.

Similarly, even in an environment in which a data storage device with a high access speed and a data storage device with a slow access speed coexist, the less important files are placed in the slower data storage device, and new files or important files are stored at high speed. It should be placed in the device.

As a result, the apparent access performance becomes closer to that of the high-speed data storage device, and on the other hand, the cost can be reduced as compared with the case where all of the plurality of data storage devices are composed of only the high-speed data storage device. become. In addition, since the data storage device having a low access speed generally has low power consumption, energy saving can be realized.

Further, in the second embodiment, the file storage allocation is performed according to the access speed of the data storage device according to the importance of each file, but in the third embodiment, the importance of each file is increased. A case will be described in which the number of times of access for each file is taken into consideration, instead of the frequency, as in the first embodiment.

As in the case of the second embodiment, the metadata server 6 is set in advance to determine whether the access speed of each data storage device is high or low.
Register in. At the same time, the number of accesses for each file is recorded in the same manner as in the first embodiment.
Then, the access frequency of each file is checked at regular intervals. If the access frequency is higher than a preset threshold value, the data storage device is moved to a data storage device having a high data access speed, and if the access frequency is lower than the threshold value, it is moved to a data storage device having a low data access speed. As a result, files that are frequently accessed are concentrated in the data storage device that has a high access speed, and files that are infrequently accessed are collected in the data storage device that have a low access speed.

In this way, even in an environment in which a data storage device with a high access speed and a data storage device with a slow access speed coexist, older files are placed in the slower data storage device and frequently accessed files are faster. Can be placed in any data storage device.

By arranging each file in such a manner, the apparent access performance becomes closer to that of the high-speed data storage device, while the cost is lower than that of the case where all the data storage devices are composed of only the high-speed data storage device. Can be cheaper. In addition, generally, the data storage device having a slower access speed consumes less power, so that the energy saving effect can be improved.

The embodiment described above is for a case where a plurality of file data are divided and stored in a plurality of data storage devices connected to the file management system. Therefore, in the fourth embodiment, a case has been described in which a plurality of data storage devices connected to the file management system have a RAID configuration.

FIG. 3 shows a file management system having a plurality of data storage devices having a RAID configuration. The basic configuration of this file management system is the same as the system shown in FIG. 3, the same parts as those in FIG. 1 are designated by the same reference numerals. File management system has 5
Data storage devices 50 to 54 are connected,
In the fourth embodiment, the disk 50 which is a data storage device
The plurality of file data stored in
It is composed of ID5.

In the embodiment of the file management system shown in FIG. 3, RAID with 2 stripes and 1 parity is used.
It is composed of 5. Each file is divided into blocks, and each block is stored in any of all disks. However, based on the basic concept of RAID 5, blocks and parity within the same stripe must be stored on separate disks.

In the embodiment of FIG. 3, for example, the file F0
The same stripe of (parity PF00, block B
F00, block BF01) and (parity PF01, block BF02, block BF03). If the blocks and parity in this are placed on the same disk,
File data cannot be recovered when a failure occurs. The access client determines these block layout positions, calculates the parity, and updates the parity. Also in the case of the fourth embodiment, the processing procedures (a) to (h) described with reference to FIG. 2 can be applied to the movement or relocation of the RAID-configured file.

Therefore, FIG. 4 shows the case where a device failure occurs in the disk connected to the file management system. The configuration of the file management system shown in FIG. 4 is similar to the system configuration shown in FIG. 3, and the same parts are designated by the same reference numerals. Then, a case where a device failure occurs in a portion related to the disk 52 is shown.

Here, FIG. 4 shows the recovery work of the block of the failed disk, and the movement of each block is shown by an arrow. Each block BF01, BF10, BF03, and BF30 stored on the disk 52
Are moved to free areas of other disks. The moving procedure at this time is performed in the same manner as the above-described processing procedures (a) to (h).

The disk to which each block is moved may be any disk as long as it satisfies the condition that it is a disk different from other blocks and parity in the same stripe. In the example of FIG. 4, the blocks BF01 and BF10 are
On disk 53, and blocks BF03 and BF30
Shows the state of being copied to the disk 54, respectively. These results are recorded in the management information of the corresponding metadata.

In the fourth case, it suffices that there is a free area for storing the file data placed on the failed disk somewhere on the disk other than the failed disk. In addition, a maximum of [(number of disks)-(number of RAID stripes) -1] device failure can be tolerated, so that not only the efficiency of use of the disks is increased, but also the failure resistance is increased.

Although the fourth embodiment shows the case of the RAID5 configuration, the file management system of the present embodiment is also applicable to the RAID configurations other than RAID5.
The same applies.

In the file management system to which the data storage device having the RAID structure is connected, when the data storage device fails, the file data can be restored based on the parity information of the RAID, and the restored data can be stored in the RAID.
The data is stored in a free area on another data storage device not included in the ID stripe. At this time, the file data restored from the original storage location is moved to the new storage location according to the above-mentioned processing procedures (a) to (h), and the file storage location information is changed. This allows the RAID
In the case where a storage device failure occurs, the recovery of RAID data can be realized in the dynamic state of the system without requiring a data storage device dedicated to recovery and a data storage area dedicated to recovery. (Supplementary Note 1) Free space information of a file data storage location, management control means for managing file metadata and access right information, and data access means for accessing the stored file data and rewriting the file data. The management control means changes the storage location of the file by exclusively controlling the data access of the data access means based on the storage location information of the file and the access right information included in the metadata. A file management system characterized by performing. (Supplementary Note 2) The file management system according to Supplementary Note 1, wherein the file management system has a plurality of data storage devices, and the file data and the metadata are stored in the different data storage device. (Supplementary Note 3) The management control unit collects a token related to the file from the data access unit, and requests the data access unit to rewrite the file data of the file to another data storage location according to the availability information. The file management system according to appendix 2, wherein the file management system is issued. (Supplementary Note 4) The management control unit updates the metadata by receiving a notification of completion of rewriting the file data from the data access unit.
File management system described in. (Supplementary Note 5) The management control unit equalizes the access frequencies among the data storage devices according to the access frequency to the file included in the access information.
4. The file management system according to attachment 3, wherein the storage location of the file data is changed. (Supplementary Note 6) The plurality of data storage devices include those having different data access speeds, and the management control means sets importance information for each file. The file management system according to appendix 3, wherein the storage location of the file data is changed by selecting the data storage device having the data access speed according to the importance. (Supplementary Note 7) The management control means stores the file data having high importance in the data storage device having a high data access speed and the file data having low importance in the storage device having a low data access speed. The file management system according to appendix 6, characterized in that: (Supplementary Note 7) The plurality of data storage devices include those having different data access speeds, and the management control means measures a data access frequency for each file and holds an access value. 4. The file management system according to appendix 3, wherein the management control means selects the data storage device having the data access speed according to the data access frequency and changes the storage location of the file data. (Supplementary Note 8) The management control means transfers the file data having a high data access frequency to the data storage device having a high data access speed, and the file data having a low data access frequency to the storage device having a low data access speed. The file management system according to appendix 7, wherein the storage location is changed. (Supplementary note 9) The file management system according to Supplementary note 3, wherein the plurality of data storage devices have a RAID configuration. (Supplementary Note 10) When a failure related to one of the data storage devices has occurred, the management control unit is configured to control the R data of the file data stored in the data storage device.
10. The file management system according to attachment 9, wherein the file data restored from the parity having the AID configuration is stored in the other data storage device. (Supplementary Note 11) The management control unit updates the metadata upon receiving a notification of completion of rewriting the file data from the data access unit.
The file management system described in 0.

[0077]

As described above, according to the present invention, regarding the storage of a file recognized by the file management system, the management information (metadata) related to the file and the file data are set as separate storage locations, and the management information is stored. Since the file data and the file data are managed separately, the file data storage location can be dynamically and automatically changed for each file, and a plurality of data storage devices can be added when a necessary data storage device is added or replaced. The data storage device can be flexibly operated, for example, by dividing the file evenly.

Further, it is possible to easily correct the load concentration due to the uneven access frequency among a plurality of data storage devices, and to improve the throughput of the entire system.

Further, even in an environment in which a data storage device with a high access speed and a data storage device with a slow access speed coexist, files of high importance are placed on a disk of high data access speed, and files of low importance are of high data access speed. Can be placed on a slow disk,
Even with a low-cost data storage device group, the data access speed can be increased for files of high importance.

In addition, even in an environment in which a data storage device with a high access speed and a data storage device with a slow access speed coexist, older and unused files are placed in the slower data storage device, and new files and frequently accessed files are faster. It can be placed in any data storage device, and the apparent access performance is closer to that of a high-speed data storage device, while the cost can be lower than that of configuring everything with only a high-speed data storage device. It is possible to save energy.

RAID using multiple data storage devices
Also in the configuration, it is not necessary to prepare a spare data storage device or a spare data storage area in order to recover from the device failure, whereby the usage efficiency of the data storage device can be improved.

[Brief description of drawings]

FIG. 1 is a diagram illustrating a configuration example of a file management system according to the present embodiment.

FIG. 2 is a diagram illustrating a procedure of processing relating to movement of file data.

FIG. 3 is a diagram illustrating an arrangement of file data when a RAID configuration is realized.

FIG. 4 is a diagram illustrating a recovery process when a device failure occurs in a RAID configuration.

FIG. 5 is a diagram illustrating a configuration example of a conventional file system.

[Explanation of symbols]

1 ... File system 2 ... Device driver 3, 50-54, 60, 61 ... Data storage device 4 ... File access interface 5 ... Access client 6 ... Metadata server

   ─────────────────────────────────────────────────── ─── Continued front page    F-term (reference) 5B065 BA01 CC03 CH18                 5B082 CA05 CA11

Claims (5)

[Claims] 1. Free information of a file data storage location,
Management management means for managing metadata and access right information of the file, and data access means for accessing the stored file data and rewriting the file data, wherein the management control means is A file management system for changing the storage location of the file by exclusive control of data access of the data access means based on the storage location information of the file included in the data and the access right information. 2. A plurality of data storage devices are provided, and the file data and the metadata are stored in the different data storage device, and the management control means collects a token related to the file from the data access means. 2. The file management system according to claim 1, wherein the data access unit issues a rewrite request for file data of the file to another data storage location according to the free space information. 3. The plurality of data storage devices include those having different data access speeds, and the management control means sets importance information for each file. 3. The file management system according to claim 2, wherein the storage location of the file data is changed by selecting the data storage device having the data access speed according to the degree of importance. 4. The plurality of data storage devices include those having different data access speeds, and the management control means measures a data access frequency for each file and holds an access value. 3. The file management according to claim 2, wherein the management control unit changes the storage location of the file data by selecting the data storage device having the data access speed according to the data access frequency. system. 5. The plurality of data storage devices are RAID
When a failure related to one of the data storage devices is configured, the management control unit, for the file data stored in the data storage device, restores the file data restored from the parity according to the RAID configuration, The data is stored in the other data storage device.
File management system described in.