Virtual server, its computer and program to be executed by computer

The present invention relates to a virtual server, its computer, and a program for the computer to execute, in particular, because the virtual server, the computer, and the computer that form a virtual single storage area in the network execute. About the program.

For example, Patent Documents 1 to 4 are known as techniques for virtually sharing files using a plurality of clients and servers. In addition, in the server / client system, there is a system that saves the data generated by each client in the server and uses the shared data in each client, but if the server fails, the business using the network There is a problem that it becomes difficult to continue.

There is a technology for duplicating hardware in order to increase the tolerance of server failures, but there is a problem that the cost of the server increases. Further, NAS (Network Attached Storage) that centralizes storage and provides file sharing access from a network is known, but there is a problem that the cost increases because a dedicated device equipped with a storage function is required. In this case, hardware duplication is required in the NAS device to ensure reliability and availability, so if highly reliable hardware is installed in this part, the cost will be even higher. There is a problem.

Furthermore, a device such as hardware RAID that prevents data loss even if one of the DISKs fails by making it redundant to write data to multiple hard disks is known, but dedicated hardware for controlling redundancy Since it is necessary to equip the hardware and a plurality of disks, there is a problem that the cost is also high.

<patcit num="1"><text>Japanese Unexamined Patent Publication No. 2003-186727</text></patcit><patcit num="2"><text>Japanese Unexamined Patent Publication No. 11-45203</text></patcit><patcit num="3"><text>Japanese Unexamined Patent Publication No. 10-3421</text></patcit><patcit num="4"><text>Japanese Patent Application Laid-Open No. 2003-6032</text></patcit>

<p> The present invention has been made in view of the above problems, and provides a virtual server capable of realizing an inexpensive and highly reliable storage system, a computer thereof, and a program for the computer to execute. With the goal.</p>

<p> In order to solve the above-mentioned problems and achieve the object, the present invention relates to a virtual server constructed by a plurality of computers connected to each other via a network and storage means connected to each computer. A single virtual storage area is configured by using the storage means connected to each computer, and the single virtual storage area is displayed on the network. As a result, by realizing a virtual server using a plurality of low-cost computers, the load can be distributed to the plurality of computers, and an inexpensive and highly reliable storage system can be provided.</p><p> Further, according to a preferred embodiment of the present invention, it is desirable to display the server that manages the single virtual storage area together with the single virtual storage area on the network. As a result, the external device can access the virtual server with the same operation feeling as that of a normal server without being particularly conscious of where the virtual server actually exists.</p><p> Further, according to a preferred embodiment of the present invention, each of the storage means has a specific area, forms the single virtual storage area in each of the specific areas, and is connected via the network. When there is a request to write data from an external device, or when a request to write data occurs on one computer, each computer writes the same data to each specific area in substantially real time, and the above-mentioned It is desirable to keep the same data in each specific area. As a result, by writing data to a specific area of the storage means of the own machine, it is possible to prevent data loss due to redundancy in writing data to a specific area of another computer.</p><p> Further, according to a preferred embodiment of the present invention, when a data read request or a read request of the own machine is generated from an external device connected via the network, each of the computers is specified. It is desirable to read data from each area at its own timing. As a result, each computer can read data in a specific area in the storage means of its own machine at its own timing, and can read data at high speed.</p><p> Further, according to a preferred embodiment of the present invention, the storage means comprises a disk device, the disk device has a plurality of areas, and the specific area is allocated to one of the plurality of areas. Is desirable. This makes it possible to effectively utilize the resources of the disk device.</p><p> Further, according to a preferred embodiment of the present invention, it is desirable that the storage means is composed of a plurality of disk devices, and the specific area is allocated to the entire area of the disk device. As a result, the operational safety of the system can be maintained, and hot swap can be configured.</p><p> Further, according to a preferred embodiment of the present invention, if there is a computer in which a failure has occurred among the computers, it is desirable to configure the virtual server with a computer other than the one in which the failure has occurred. As a result, even during the period when the failed computer is separated and repair work is performed, the business can be continued on another computer, the burden on the user is reduced as much as possible, and a virtual server with improved availability is provided. be able to. Here, the failure includes not only the case where the computer fails and actually fails, but also the case where the data of the computer cannot be accessed when the computer is undergoing maintenance work (the same applies hereinafter). ..</p><p> Further, according to a preferred embodiment of the present invention, when an error occurs in the specific area of the computer, another computer can perform data in the specific area in response to a request from the computer in which the error occurs. It is desirable to perform recovery. This facilitates data recovery and allows immediate return to the virtual server.</p><p> Further, according to a preferred embodiment of the present invention, it is desirable that each computer is configured to be able to centrally manage the power supply of the computers constituting the virtual server. As a result, by managing the power of other computers via the network, it is possible to centrally manage the power ON / OFF according to the operating status of multiple computers that make up the virtual server, resulting in low power consumption. The efficiency and reliability of the virtual server can be improved.</p><p> Further, according to a preferred embodiment of the present invention, each computer executes the first mode of detecting that the power switch is turned on by the user and supplying power to each part in the computer, and the RAID function. It is desirable to have a second mode in which power is supplied only to the portion of the above, and a third mode in which power is supplied only to the portion for communicating via the network. As a result, it is possible to energize only the parts necessary for operating the system, and it is possible to further reduce the power consumption.</p><p> In order to solve the above-mentioned problems and achieve the object, the present invention is connected to one or more other computers, each of which has a storage means, via a network, and utilizes the storage means and its own storage means. The computers constituting the virtual server in the network are provided with display means for displaying a single virtual storage area configured by using the storage means connected to each computer on the network. It is characterized by.</p><p> Further, according to a preferred embodiment of the present invention, it is desirable that the display means display a server that manages the single virtual storage area together with the single virtual storage area on the network.</p><p> Further, according to a preferred embodiment of the present invention, the storage means having a specific area constituting the single virtual storage area, an interface for connecting to the network, and an external device connected via the network. When a data write request is generated from, or when a data write request is generated by the own machine, the other computer is requested to write the data, and the data is written to the specific area. It is characterized by including one writing means and a second writing means for writing the data to the specific area when a data writing request is received from the other computer.</p><p> Further, according to a preferred embodiment of the present invention, the first and second writing means may perform exclusive processing when another writing request is made while writing data to the specific area. desirable.</p><p> Further, according to a preferred embodiment of the present invention, it is desirable to provide a reading means for reading data from a specific area of the storage means at a unique timing.</p><p> Further, according to a preferred embodiment of the present invention, it is desirable to provide a power management means for centrally managing the power supply of the computers constituting the virtual server.</p><p> Further, according to a preferred embodiment of the present invention, the power management means executes a first mode of detecting that the power switch is turned on by the user and supplying power to each part in the computer, and a backup operation. It is desirable to transition between the second mode in which power is supplied only to the part for communication and the third mode in which power is supplied only to the part for communicating via the network.</p><p> In order to solve the above-mentioned problems and achieve the object, the program to be executed by the computer of the present invention is connected to one or more other computers, each having a storage means, via a network, and the storage means. A single virtual storage area configured by using the storage means connected to each computer is provided on the network to the computers that configure the virtual server in the network by using the storage means of the own machine. It is characterized in that a display process for displaying is executed.</p><p> Further, according to a preferred embodiment of the present invention, in the display step, it is desirable to display the server that manages the single virtual storage area together with the single virtual storage area on the network.</p><p> Further, according to a preferred embodiment of the present invention, further, when a data write request is generated from an external device connected to the computer via the network, or when a data write request is generated by the own machine. The first writing step of requesting the other computer to write the data, and writing the data to a specific area of the storage means of the own machine constituting the single virtual storage area, and the other When a data write request is received from the computer, it is desirable to have the computer execute the second writing step of writing the data to the specific area.</p><p> Further, according to a preferred embodiment of the present invention, in the first and second writing steps, if there is another writing request while writing data to the specific area, exclusive processing may be performed. desirable.</p><p> Further, according to a preferred embodiment of the present invention, it is further desirable to have a computer execute a reading step of reading data from a specific area of the storage means at a unique timing.</p><p> Further, according to a preferred embodiment of the present invention, it is further desirable to have the computer execute a power management step of centrally managing the power supply of the computer constituting the virtual server.</p><p> Further, according to a preferred embodiment of the present invention, in the power management step, a first mode of detecting that the power switch is turned on by the user and supplying power to each part in the computer and a backup operation are executed. It is desirable to transition between the second mode in which power is supplied only to the part for communication and the third mode in which power is supplied only to the part for communicating via the network.</p>

<p> According to the present invention, a single virtual storage area is configured by using the storage means connected to each computer, and a single virtual storage area is displayed on the network. By implementing a virtual server using a low-cost computer, the load can be distributed to multiple computers, and a virtual server, that computer, and a virtual server that can provide an inexpensive and highly reliable storage system, and It has the effect of making it possible to provide a program for a computer to execute.</p>

Hereinafter, an example in which the virtual server according to the present invention, the computer thereof, and a program for executing the computer are applied will be described in detail with reference to the drawings. The present invention is not limited to this embodiment. In addition, the components in the following examples include those that can be easily assumed by those skilled in the art or those that are substantially the same.

[Overall configuration of virtual server]

FIG. 1 is a diagram showing a configuration of a virtual server 100 according to an embodiment of the present invention. In FIG. 1, the virtual server 100 and the external device 20 ... Are connected to each other in the network 10. The virtual server 100 is constructed by connecting a plurality of computers 200A, B, and C, for example, three computers 200A, B, and C to each other via a network 10.

Each of the computers 200A, B, and C is provided with a normal startup LED 206 and a standby LED 207 that display a display for identifying the startup state (mode). Hereinafter, when it is not necessary to distinguish between computers 200A, B, and C, they are referred to as computer 200. The network 10 can be configured by, for example, a LAN (local area network). The network 10 is not limited to wired, but may be wireless.

Disk devices 300A, B, and C, which are storage means, are connected to the computers 200A, B, and C, respectively. The disk device may be either an internal type or an external type. Hereinafter, when it is not necessary to distinguish the disk devices 300A, B, and C, they are referred to as the disk device 300. The disk devices 300A, B, and C are the first areas 301A, B, and C in which the OS (for example, Windows (registered trademark) OS, Unix (registered trademark), Linux (registered trademark), etc.) and applications are stored, respectively. And the second area (hereinafter referred to as "specific area") 302A, B, C, which is an area dedicated to RAID, and the third area 303A, B, C, which stores machine-specific information of computers 200A, B, C. have.

The specific areas 302A, B, and C constitute a virtual single storage area (virtual storage area) 400 shared by the computers 200A, B, and C. In the following description, RAID1 will be described, but the present invention is not limited to this, and RAID0,2,3,4,5 can also be applied. The allocation of this area is an example, and the allocation of the area of the disk device 300 is not particularly limited.

The first feature of the virtual server 100 according to this embodiment is that the server is virtually configured by computers 200A, B, and C connected via the network 10.

The second feature of the virtual server 100 according to this embodiment is that the virtual storage area 400 is configured by using the disk devices 300A, B, and C of the computers 200A, B, and C in the virtual server 100. It is in. Data in a plurality of specific areas 302A, 302B, and 302C constituting the virtual storage area 400 can be shared by the computers 200A, B, and C. That is, each computer 200A, B, and C can write the same data to the specific areas 302A, 302B, and 302C, respectively, and can hold the same data in each specific area 302A, 302B, 302C (RAID 1 function).

The third feature of the virtual server 100 according to this embodiment is that even if any one of the plurality of specific areas 302A, 302B, and 302 constituting the virtual storage area 400 fails, the data in the remaining specific areas remains. The point is that the data in the specific area where the failure occurred can be restored and the availability of the data can be improved.

The fourth feature of the virtual server 100 according to the present embodiment is that each of the computers 200A, B, and C recognizes the specific areas 302A, 302B, and 302C as a single virtual storage area 400. Specifically, in each of the computers 200A, B, and C, the specific areas 302A, 302B, and 302C are displayed on the user interface (display device 205) as a single virtual storage area 400. The user can write or read a file on this disk area by looking at the display of this user interface.

The fifth feature of the virtual server 100 according to this embodiment is that the specific areas 302A, 302B, and 302C of the computers 200A, B, and C constituting the virtual server 100 are used as a single virtual storage area with respect to the external device 20. (Disk space) The point is to display it as 400. Specifically, the external device 20 displays the specific areas 302A, 302B, and 302C of the computers 200A, B, and C constituting the virtual server 100 on the user interface as a single virtual storage area 400. The user can write or read a file on this disk area by looking at the display of this user interface.

The sixth feature of the virtual server 100 according to this embodiment is that the computers 200A, B, and C in the virtual server 100 are the computers 200A, B, B, in order to reduce power consumption, high efficiency, and high reliability. The point is that the power supply of C is centrally managed.

In the configuration of FIG. 1, the first area 301, the specific area 302, and the third area 303 are assigned to one disk device 300, but the storage means is configured by a plurality of disk devices, and the specific area 302 is designated. It may be assigned to a disk device physically different from the first area 301 and the second area 303.

FIG. 2 is a diagram showing a configuration example of the virtual server 100 when the first area 301 and the third area 303 are allocated to the first disk device 310 and the specific area 302 is allocated to the second disk device 311. That is, the storage means of this embodiment may be composed of a single disk device or a plurality of disk devices. It is desirable that the disk devices 310 and 311 be hot-swappable.

[Computer Configuration]

FIG. 3 is a block diagram showing the configuration of the computer 200. The computer 200 can be configured by, for example, a PC (personal computer) or a WS (workstation). As shown in FIG. 3, the computer 200 includes a LAN controller 201 for connecting to the network 10, a control unit 202 for controlling the operation of each part of the computer, a power supply control device 203 for controlling the power supply device 208, and a keyboard. An input device 204 consisting of a mouse, tablet, etc., a display device 205 consisting of an LCD or CRT, a normal startup LED 206 that lights up when in the normal startup state, a standby LED 207 that lights up when in the standby state, and a computer. It is equipped with a power supply device 208 that supplies power to each part of the above.

The LAN controller 201 is composed of a LAN card or the like connected to the network 10 and has a Wake up LAN function. The control unit 202 is mounted on the main board and stores a ROM (Read Only Memoly) for storing programs and data, a RAM (Random Access Memory) for temporarily storing data, and a ROM or disk device for storing programs and data. It consists of a CPU that reads and executes from 300.

The control unit 202 functions as a data management unit 221 that controls writing / reading of data to the disk device 300 by executing a program, for example. The data management unit 221 has a RAID function. Specifically, the data management unit 221 has a function of (1) displaying a single virtual storage area 400 and a server that manages it on the network 100, and (2) a data write request from the external device 20. A function of requesting the other computer to write the data and writing the data to the specific area 302 of the disk device 300, (3). A function to write the data to the specific area 302 of the disk device 300 when a data write request is received from another computer 200, (4) When there is a data read request from the external device 300, or the own machine It has a function of reading data from a specific area 302 of the disk device 300 at a unique timing when a data read request generated in the above is generated.

Further, the control unit 202 manages the power inside the computer by executing a program, for example, and also manages the power of the computers 200A, B, and C constituting the virtual server 100 centrally via the network 10. Functions as part 222.

The power management unit 222 controls the power control device 203, and changes the start state (normal start state, standby state, power off state) of the computer 200 based on the start information input from the power control device 203. The power management unit 222 sends a special power ON / OFF signal to the other computers 200 constituting the virtual server 100.

Further, when the user gives an instruction to select a JOB for executing the power off provided on the JOB operation screen of the computer, the power management unit 222 receives the power OFF command by software processing and notifies the power control device 203. To do. In response to this, the power supply control device 203 performs the same processing as when the power supply SW is turned off.

The power supply control device 203 is mounted on a power supply board or the like, and can be configured by, for example, a CPU, a ROM in which firmware is stored, a port control unit for communicating with a LAN controller 201 or the like, or the like. The power control device 203 controls the control of the power supply device 208, ON / OFF of the first and second switches 209 and 210, and the lighting of the power status display LED 20 according to the instruction of the power management unit 222. Further, the power control device 203 detects ON / OFF of the power switch, which is a mechanical switch pressed by the user, and a special power ON / OFF signal input via the network 200.

The power supply 208 is connected to a commercial power source and performs AC-DC conversion to generate a DC power source for the computer. The power supply device 208 supplies power to each part of the computer 200 via the power supply lines 231, 232 according to the control of the power supply control unit 203. The power supply line 231 is a line to which power is constantly supplied, and power is supplied as long as the power supply device 208 is connected to a commercial power supply even when the power supply switch is OFF. A LAN controller 201 and a power controller 203 are connected to the power line 231. As a result, even when the power switch is turned off, it is possible to communicate with another computer via the network 10. The power supply line 232 is supplied with power according to the control of the power supply control device 203. A control unit 202, an input device 204, a display device 205, and a disk device 300 are connected to the power supply line 232. The power supply line 203 connected to the input device 204 and the display device 205 is provided with first and second switches 209 and 210.

[How to display virtual storage area 300 and virtual server 100]

FIG. 4 is a diagram showing an example of management device information displayed on the display devices 203A, B, and C in the computers 200A, B, and C constituting the virtual server 100. The example shown in the figure shows the case of the computer 200A. In the figure, the name "A group", the management device name "common data area (virtual storage area 400)", the free space "900MB", the name "computer 1 (computer 200A)", and the management device name "CD-R". (Not installed) , the name Computer 1 (Computer 200A) , the management device name DISK , and the free space 1500MB are displayed. Here, group A indicates a group constituting the virtual server 100, and specific areas 302A, B, and C are displayed as a single disk area (shared data area) in each computer 200A, B, and C. .. In the example shown in the figure, each specific area 302A, B, C is 900MB, and each computer 200A, B, C is displayed as a single disk area of 900MB. As a result, when displaying the specific areas 302A, B, and C from the application, the user can access with the same operation feeling as the own DISK without being particularly conscious of where the actual data is. it can.

FIG. 5 is a diagram showing an example of computer list information on the network displayed on the display device of the external device 20. In the figure, the computer name "Computer 1 (Computer 200A)", the group name "A group", the management device name "DISK1 (disk device 300A)", the computer name "Computer 2 (Computer 200B)", and the group name " Group A, management device name "DISK2 (disk device 300B)", computer name "computer 3 (computer 200C)", group name "A group", management device name "DISK3 (disk device 300C)", computer name "Server A (virtual server 100)", group name "A group", management device name "common data area (virtual storage area 400)", computer name "external 1 (external device 20)", and computer name "external" 2 (external device 20) is displayed.

In this way, the virtual server 100 that manages the common data area (virtual storage area 400) appears to be added on the network 10. As a result, the user of the external device 20 can access the virtual server 100 with the same operation feeling as that of a normal server without being particularly conscious of where the substance of the virtual server 100 is. In each of the computers 200A, B, and C constituting the virtual server 100, the same function as the general-purpose server may be implemented as the server function.

[Data writing / reading operation]

The operation of each computer 200A, B, C writing / reading data to the specific areas 302A, B, C of the disk devices 300A, B, C will be described. FIG. 6 is a flowchart for explaining the outline of the operation of the computers 200A, B, and C writing / reading data to the specific areas 302A, B, and C of the disk devices 300A, B, and C.

In FIG. 6, when data update occurs in any one of the computers 200A, B, and C ([Yes] in A1), the computer 200 occupies the specific area 302 and writes the data. Is notified to another computer 200 (A2). When all the computers 200 that received the notification are ready (Yes in A3), each computer 200 starts updating data in its specific area 302 (A4). When the data update is completed on all computers 200 (A5 "Yes"), the data update is completed. On the other hand, if no data update occurs in any of the computers 200A, B, C ([No] in A1), each computer 200A, B, C will have its own timing in each specific area 302A, B, C. Read with (A6 "No").

FIG. 7 is a schematic diagram for explaining the operation of each computer 200A, B, C to write / read data to the specific areas 302A, B, C of the disk devices 300A, B, C. The figure describes the operation when the computer 200A updates the data on the disk device 300A. In the figure, the file system call 252 and the specific area file module 253 are one function of the data management unit 221 described above.

During the writing process, the specific area file modules 253A, B, and C of the computers 200A, B, and C perform data redundancy by updating the data in real time. During the redundancy process, each computer 200A, B, and C excludes other file update requests over the network 10 at the command level at the lowest layer of the file system for all the computers 200 that make up the virtual server 100. To process.

The reading process can be sequentially performed on each computer 200A, B, and C. When reading a file, the specific area file modules 2531A, B, and C of each computer 200A, B, and C can read the files of the specific areas 302A, B, and C, respectively, at their own timings.

In the computer 200A, when the application 251A requests to write the file to the specific area 302, the file system call 252A requests the specific area file module 253A to write the file to the specific area 302. The specific area file module 253A transmits a file and a time stamp to the specific area file modules 253B and C of the computers 200B and C, and requests writing. Then, the specific area file modules 253A, B, and C write the same file to the specific areas 302A, B, and C of the disk devices 300A, B, and C substantially at the same time. Here, the case where the data write / read request is generated in the application 251A has been described, but the same processing is performed when the data write / read request is generated from the external device 20.

[Operation / recovery operation when an error occurs]

The operation when an error occurs in the computers 200A, B, and C, and the recovery operation thereof will be described.

1. When the virtual server does not operate normally Figure 8 is a diagram for explaining the processing when a problem occurs in any of the computers 200A, B, and C. If any of the computers 200A, B, or C has a problem, disconnect the computer 200 and continue the RAID system with the remaining computers 200.

In FIG. 8, for example, when the computer 200A fails, the computer 200A is disconnected and the remaining computers 200B and C continue the RAID system.

2. When an error occurs in the specific area 302 in the read process Figure 9 shows the case where an error occurs in the read process in the specific areas 302A, B, C of the disk devices 300A, B, C of the computers 200A, B, C. It is a figure for demonstrating the process of.

If an error occurs during the reading process in the specific area 302A, B, or C of any one of the computers 200A, B, or C, the reading process is continued in the specific area 302 of the other computer 200, and then the failure occurs. Does not access the specific area 302.

In FIG. 9, for example, when a disk error occurs in the reading process of the specific area 302A from the application A of the computer 200A, the reading process is performed from the specific areas 302A and 302B of the other computer 200B or 200C to continue the processing. To do. After that, the specific area 302A is not accessed.

3. When an error occurs in the specific area 302 in the write process Figure 10 shows the case where an error occurs in the write process in the specific areas 302A, B, C of the disk devices 300A, B, C of the computers 200A, B, C. It is a figure for demonstrating the process of. If an error occurs in the write process in the specific area 302A, B, or C of any one of the computers 200A, B, and C, the write process is continued in the specific area 302 of the other computer 200, and then the failure is identified. Do not access area 302.

In FIG. 10, for example, in the writing process from the application A of the computer 200A, if a disk error occurs in the specific area 302A, and if the processing is successful in the other specific areas 302B and C, the writing process is performed. Continue and do not access the specific area 302A thereafter.

In the above read processing and write processing, application A continues processing assuming that a sector error has occurred in the specific area 302 of the disk device 300, but normally, when a physical disk error occurs, Even if the area is divided, the entire disk will be affected as long as the same disk device is used, so a system error may occur in the future. Therefore, the countermeasures 2 and 3 above are effective in the case of the configuration shown in FIG. 2 in which the specific area 302 is physically allocated to another disk.

4. Recovery of the specific area FIG. 11 is a flowchart for explaining the procedure for recovering the specific area 302. When recovering the specific area 302, the block transfer of the entire area of the specific area 302 is used from the computer 200 in which the specific area 302 is normal.

In FIG. 11, the computer 200 wishing to return to the RAID system notifies all the computers in which the RAID system is operating normally of the return request (A11). Upon receiving the notification, the computer 200 temporarily prohibits access to a specific area of its own machine (A12). One of the notified computers 200 copies the entire area of the specific area 302 of its own machine to the specific area 302 of the computer 200 wishing to return to the RAID system by using block transfer (A13). After this, boot the RAID system on all computers 200 (A14).

FIG. 12 is a diagram showing a specific example of recovery of the specific area 302. In FIG. 12, for example, when an error occurs in the specific area 302C of the computer 200C and a return to the RAID system is desired, the computer 200C notifies the computers 200A and B of the return request. Upon receiving the notification, the computers 200A and B temporarily prohibit access to the specific areas 302A and B of their own machine. The computer 200A or 200B copies the data of all the areas of the specific area 302A and B of the own machine to the specific area 302C of the computer 200C. As a result, all computers 200A, B, and C can access the specific areas 302A, B, and C.

In addition, in case all the computers 200A, B, and C of the virtual server 100 fail in the specific areas 302A, B, and C (in the case of an earthquake or fire), the data center 500 connected to the external network is virtual. The data in the specific area 302 of the server 100 may be backed up.

FIG. 13 is a flowchart illustrating a procedure for recovering the virtual server 100 using the data center 500. In FIG. 13, first, access to the specific area 302 of all the computers 200 for constructing the virtual server 100 is prohibited (A21), and the data center 500 sets one specific area 302 of the computers 200 constituting the virtual server 100. Restore (A22). The computer 200 that has restored the specific area 302 copies the specific area 302 to the specific area 302 of another computer 200 (A23). After this, boot the RAID system on all computers 200 (A24).

FIG. 14 is a diagram showing a specific example of recovering the specific area 302 using the data center 500. In FIG. 14, first, when recovering the specific areas 302A, B, and C of all the computers 200A, B, and C of the virtual server 100, access to the specific areas 302A, B, and C of the computers 200A, B, and C is prohibited. Then, the data center 500 restores the specific area 302C of the computer 200C. The computer 200C copies the specific area 302C to the specific areas 302A and B of the computers 200A and B. As a result, all computers 200A, B, and C can access the specific areas 302A, B, and C. A removable disk may be used as a backup destination.

[Computer power state transition]

FIG. 15 is a diagram showing a transition of the power state of the computer 200. In FIG. 15, (1) in the normal startup state (first mode), the computer 200 is normally started in a state where the power switch is turned on by the user and power is supplied to each part of the computer 200. It is in a state. (2) The standby state (second mode) is a state in which the computer 200 is started, but is a power saving state in which power is supplied only to the part for executing the backup operation (RAID function), and the backup operation. This is a state in which the power supply to unnecessary parts such as the input device 204 and the display device 205 is cut off. (3) In the power off state (third mode), power is supplied to parts other than the LAN controller 201 and the power control device 203 while power is supplied only to the part for communication via the network 10. It is in a disconnected state.

When the power switch is turned on by the user, the power control device 203 causes the power supply device 208 to start supplying power from the power supply line 232. As a result, power is supplied to the control unit 202, and the power management unit 222 is activated. The power management unit 222 turns on the first and second switches 209 and 210 via the power control device 203 based on the start information (starting by turning on the power switch) input from the power control device 203. As a result, power is supplied to each part of the computer 200, and the computer 200 is in the normal startup state (1).

When the power switch is turned off by the user or when the power OFF command is received, the power control device 203 stops the power supply from the power line 232 to the power supply device 208. As a result, the supply of power to other than the LAN controller 201 and the power control device 203 is cut off, and the power is turned off.

The special power ON is a function that changes the power from the power off state to the standby state via the network 10. When the computer 200 is in the power off state and a special power ON signal is input to the power control device 203 via the network 10, the power control device 203 supplies power to the power supply device 208 from the power supply line 232. To start. As a result, power is supplied to the control unit 202, and the power management unit 222 is activated. The power management unit 222 turns off the first and second switches 209 and 210 via the power control device 203 based on the start information (starting by turning on the special power supply) input from the power control device 203. As a result, the standby state is set, power is supplied to the parts (control unit 202, disk device 300, etc.) necessary for executing the backup operation (RAID function), and it is not necessary to execute the backup operation. The power supply to the input device 204, the display device 205, etc. is cut off.

The special power off is a function that changes the power from the standby state to the power off state via the network 10. When the computer 200 is in the standby state and a special power OFF signal is input via the network 10, the power management unit 222 stops the power supply from the power line 232 via the power control device 203. .. As a result, the power is turned off.

[Operation at startup]

A case where the power switch of only one computer 200 is turned on to start the RAID system when the computers 200A, B, and C are in the power off state will be described. Here, the operation when the power switch of the computer 200A is turned on will be described. The same operation is performed when the power switch of the computers 200B and C is turned on, so the description thereof is omitted here.

FIG. 16 is a flowchart for explaining the operation of turning on the power switch of only one computer 200 and starting the RAID system when the computers 200A, B, and C are in the power-off state, and FIG. 17 is a flowchart. It is explanatory drawing for demonstrating the operation which turn on the power switch of only one computer 200 and start a RAID system when the computer 200A, B, and C are in the power-off state.

In FIG. 16, when the computers 200A, B, and C are in the power-off state (S1), and when the power switch is turned on by the user in the computer 200A (S2), the power control device 203 is changed to the power supply device 208. Start supplying power from the power line 232 (S3). As a result, power is supplied to the control unit 202, and the power management unit 222 is activated. The power management unit 222 determines the start condition based on the start information (start by turning on the power switch) input from the power control device 203 (S4). In this case, since it is started by turning on the power switch, the power management unit 222 turns on the first and second switches 209A and 210A via the power control device 203, and turns on the input device 204 and the display device 205. Supply power (S5). Then, the power management unit 222 transmits a special power ON signal to the computers 200B and C (S6). After that, the data management unit 221 is started (S7). The power management unit 222 lights the normal start-up LED 206 via the power control device 203 (S8). In this way, it is in the normal startup state (S9).

On the other hand, in the computers 200B and C in the power-off state (S11), when the power management device 203 receives the special power ON signal (S12), the power control device 203 sends the power supply 208 to the power supply line 232. Start supply (S13). As a result, power is supplied to the control unit 202, and the power management unit 222 is activated. The power management unit 222 determines the start condition based on the start information (start by turning on the special power supply) input from the power control device 203 (S14). In this case, the power management unit 222 determines the start condition by turning on the special power supply. 222 turns off the first and second switches 209 and 210 via the power control device 203, and does not supply power to the input device 204 and the display device 205 (S15). Then, the data management unit 221 is started (S16). The power management unit 222 lights the standby LED 207 via the power control device 203 (S17). In this way, the computers 200B and C are put into the standby state (S18). After this, the RAID system can be used.

After that, in the computers 200B and C, when the power switch is turned on (S21), the power control device 203 notifies the power management unit 222 that the power switch is turned on. The power management unit 222 turns on the first and second switches 209 and 210 via the power control device 203 to supply power to the input device 204 and the display device 205 (S22). After that, the power management unit 222 lights the normal start LED 206 via the power control devices 203B and C (S23). In this way, it is in the normal startup state (S24).

[Operation when the power is turned off (or when the power off command is issued)]

The operation of turning off the power when one of the computers 200A, B, and C is in the normal startup state and the other computer is in the standby state will be described. Here, the operation when the power switch of the computer 200A is turned off (or when the power off command is issued) when the computer 200A is in the normal startup state and the computers B and C are in the standby state will be described. The same operation is performed when the power switch of the computers 200B and C is turned off (or when the power off command is issued), so the description thereof is omitted here.

FIG. 18 is for explaining the operation when the power switch of the computer 200A is turned off or the power off command is issued when the computer 200A is in the normal startup state and the computers B and C are in the standby state. It is a flowchart. FIG. 19 is for explaining the operation when the power switch of the computer 200A is turned off or the power off command is issued when the computer 200A is in the normal startup state and the computers B and C are in the standby state. It is explanatory drawing.

In FIG. 18, in the computer 200A, when the power switch is turned off (or a power OFF command is issued by software processing) when the computer is in the normal startup state (S31) (S32), the power control device 203 is set to the power switch. Notifies the power management unit 222 of the OFF. The power management unit 203 inquires the computers 200B and C about the power supply status and determines the termination condition (S33).

If there is a computer in the normal startup state, the power management unit 222 turns off the first and second switches 209 and 210 via the power control device 203 to supply power to the input device 204 and the display device 205. Cut off the supply (S34). Then, the power supply control unit 222 turns off the normal start LED 206 and turns on the standby LED 207 (S35, S36) via the power control device 203, and enters the standby state (S37).

On the other hand, when there is no computer in the normally activated state, the power management unit 222 transmits a special power OFF signal to the computers 200B and C (S41). Then, the power management unit 222 stops the supply of power from the power line 231 of the power supply device 208 via the power control device 203 (S42), turns off the normal start LED (S43), and powers the power supply. It goes into the OFF state (S44).

In addition, the computers 200B and C in the standby state (S51) respond to the inquiry from the computer 200A (S52), and when a special power OFF signal is received via the network 10 (S53), the power management unit 222 sends the power management unit 222. , The power supply from the power supply line 232 is stopped (S54) via the power control device 203, and the standby LED 207 is turned off (S55) to turn off the power (S56).

As described above, according to the present embodiment, a plurality of computers 200A, B, C connected to each other via the network 10 and disk devices 300A, B, B connected to the respective computers 200A, B, C, respectively. In the virtual server 100 equipped with, C, a single virtual storage area 400 is configured by using the disk devices 300A, B, and C connected to the computers 200A, B, and C, respectively, and on the network 10. Since a single virtual storage area 400 is to be displayed, the load can be distributed to multiple computers by realizing a virtual server using multiple low-cost computers, which is inexpensive and reliable. It is possible to provide a high-quality storage system.

The virtual server according to the present invention is useful when realizing a storage system on a network with a low-cost configuration.

<figref num="1">It is a figure which shows the structure of the virtual server which concerns on one Example of this invention.</figref><figref num="2">It is a figure which shows the modification of the virtual server.</figref><figref num="3">It is a block diagram which shows the structure of the computer of FIG.</figref><figref num="4">It is a figure which shows an example of the management device information displayed on the display device in the computer which constitutes a virtual server .</figref><figref num="5">It is a figure which shows an example of the computer list information on the network which is displayed on the display device in an external device.</figref><figref num="6">It is a flowchart for demonstrating the outline of the operation of writing / reading data to a specific area of a disk apparatus by a computer.</figref><figref num="7">It is a schematic diagram for demonstrating the operation which each computer writes and reads data with respect to the specific area of a disk apparatus.</figref><figref num="8">It is a figure for demonstrating the processing when a trouble occurs in any of the computers.</figref><figref num="9">It is a figure for demonstrating the process when an error occurs in the read process in a specific area of a disk device of a computer.</figref><figref num="10">It is a figure for demonstrating the process when an error occurs in the write process in a specific area of a disk device of a computer.</figref><figref num="11">It is a flowchart for demonstrating the procedure for recovering a specific area.</figref><figref num="12">It is a figure which shows the specific example of the recovery of a specific area.</figref><figref num="13">It is a flowchart for demonstrating the procedure for recovering a network RAID system using a data center.</figref><figref num="14">It is a figure which shows the specific example of recovering a specific area using a data center.</figref><figref num="15">It is a figure which shows the transition of the power state of a computer.</figref><figref num="16">It is a flowchart for demonstrating the operation which turns on the power switch of only one computer, and starts a RAID system when each computer is in a power-off state.</figref><figref num="17">It is explanatory drawing for demonstrating the operation which turns on the power switch of only one computer, and starts a RAID system when each computer is in a power-off state.</figref><figref num="18">It is a flowchart for demonstrating the operation when the power switch of the computer is turned off (or when the power-off command is issued) when a computer is in a normal startup state, and another computer is in a standby state.</figref><figref num="19">It is explanatory drawing for demonstrating the operation when the power switch of the computer is turned off (or when the power-off command is issued) when a computer is in a normal startup state, and another computer is in a standby state. ..</figref>

Code description

10 Network 20 External device 100 Virtual server 200 Computer 201 LAN controller 202 Control unit 203 Power control device 204 Input device 205 Display device 206 Normal startup LED 207 Standby LED 208 Power supply device 209 1st switch 210 2nd switch 221 Data management unit 222 Power management unit 231, 232 Power line 301 1st area 302 Specific area 303 3rd area 310 1st disk device 311 2nd disk device