JP7363520B2 - Power control device, information processing system, and power control method - Google Patents

Description

The present invention relates to a power supply control device, an information processing system, and a power supply control method.

FIG. 1 shows an example of the configuration of a conventional information processing system. The information processing system in FIG. 1 includes servers 101-1 to 101-N (N is an integer of 2 or more). Each server 101-i (i=1 to N) includes a CPU (Central Processing Unit) 111-i and a BMC (Baseboard Management Controller) 112-i. Each server 101-i further includes a PCH (Platform Controller Hub) 113-i and a NIC (Network Interface Controller) 114-i.

The CPU 111-i executes predetermined information processing, and the BMC 112-i manages and monitors the server 101-i. The CPU 111-i is sometimes called a processor. The PCH 113-i manages data paths and supports the functions of the CPU 111-i. The NIC 114-i is a communication interface circuit. The BMC 112-i is connected to the management network 102, and the NIC 114-i is connected to the business network 103. Management network 102 and business network 103 are communication networks.

In the information processing system shown in FIG. 1, WOL (Wake on LAN) may be used when powering on the servers 101-1 to 101-N. When turning on the power using WOL, a WOL packet targeting each server 101-i to be started is sent out on the business network 103 by broadcast while the power to each server 101-i is turned off. . Then, when the NIC 114-i of each server 101-i receives the WOL packet, the server 101-i is powered on.

In connection with power control of information processing systems, remote power controllers that remotely control the power of computer devices and other electronic devices are known (for example, see Patent Document 1).

Japanese Patent Application Publication No. 2000-214961

In recent years, in information processing systems used for applications such as cloud computing, AI (Artificial Intelligence), HPC (High Performance Computing), and data centers, processing is often distributed over a large number of servers ranging from hundreds to tens of thousands of servers. is increasing. In such a distributed processing environment, many servers are used for multiple purposes, and therefore, multiple servers are grouped and operated for each purpose.

In the information processing system of FIG. 1, even when each server 101-i is powered off, the NIC 114-i is powered on in order to receive WOL packets. The state in which the power is turned on is sometimes referred to as the power-on state. Further, a state in which the power is cut off is sometimes referred to as a power-off state.

If the number of servers 101-i is a few, the power consumption of the NIC 114-i is trivial, but if the number of servers 101-i is in the tens of thousands, the power consumption of the NIC 114-i becomes negligible. It becomes too big.

Note that this problem occurs not only when WOL is used, but also when a plurality of information processing apparatuses are powered on using other power-on instructions.

In one aspect, the present invention aims to reduce power consumption of an information processing system in which a plurality of information processing devices are powered on using a power-on instruction.

In one proposal, the power control device includes a storage section and a control section. The storage unit stores a common address common to the plurality of information processing devices and an address of a management device that manages each of the plurality of information processing devices in association with each other.

When the control unit receives the first power-on instruction including the common address, the control unit uses the address of a specific management device that manages a specific information processing device among the plurality of information processing devices that is associated with the common address. Then, a second power-on instruction is sent to the specific management device. The second power-on instruction is a power-on instruction that instructs to turn on the power of a specific information processing device.

According to one embodiment, it is possible to reduce power consumption of an information processing system in which a plurality of information processing apparatuses are powered on using a power-on instruction.

FIG. 1 is a configuration diagram of a conventional information processing system. FIG. 2 is a functional configuration diagram of a power supply control device. It is a flowchart of power supply control processing. FIG. 1 is a configuration diagram of an information processing system according to an embodiment. FIG. 2 is a configuration diagram of a server. It is a functional block diagram of BMC. FIG. 3 is a diagram showing a group table. FIG. 3 is a diagram showing a WOL packet. FIG. 3 is a diagram showing an address list. 3 is a flowchart illustrating a specific example of power supply control processing. It is a flowchart of a 1st table generation process. It is a flowchart of a 2nd table generation process. FIG. 3 is a diagram showing a first group setting screen. It is a figure which shows a control information setting screen. It is a flowchart of a 3rd table generation process. It is a figure which shows the 2nd group setting screen. It is a flowchart of the 4th table generation process. It is a figure which shows the 3rd group setting screen. It is a hardware configuration diagram of BMC.

Hereinafter, embodiments will be described in detail with reference to the drawings.

As described above, when WOL is used in a large-scale information processing system, the power consumption of the NIC 114-i shown in FIG. 1 increases. In order to reduce power consumption, when the server 101-i is powered off, the NIC 114-i is also powered off, making it difficult to receive WOL packets.

Security issues may also arise when using WOL. The management network 102 is a communication network used for management and maintenance of the server 101-i. Therefore, the management network 102 is physically completely separated from the business network 103, and network traffic is limited.

On the other hand, the business network 103 is a communication network used by the server 101-i for business purposes, and has very large network traffic. Further, in order to block unauthorized access from outside, strong security measures are taken on the business network 103. As described above, since the business network 103 is very sensitive to security, it is not desirable for broadcast packets such as WOL packets to be sent onto the business network 103, even if the usage is limited.

If the management network 102 is used for management and maintenance purposes, it can be used in a somewhat closed environment, so transmission of broadcast packets such as WOL packets is permitted. However, since the NIC 114-i is not connected to the management network 102, the transmitted WOL packet is not recognized.

FIG. 2 shows an example of the configuration of the power supply control device according to the embodiment. The power supply control device 201 in FIG. 2 includes a storage section 211 and a control section 212.

The storage unit 211 stores a common address common to a plurality of information processing devices and an address of a management device that manages each of the plurality of information processing devices in association with each other. The control unit 212 performs power control processing based on the information stored in the storage unit 211. An information processing device is sometimes called a computer.

FIG. 3 is a flowchart illustrating an example of power control processing performed by the power control device 201 of FIG. 2. First, the control unit 212 receives a first power-on instruction including a common address (step 301). Next, the control unit 212 uses the address of a specific management device that manages a specific information processing device among the plurality of information processing devices, which is associated with the common address, to issue a second power-on instruction to a specific one. It is transmitted to the management device (step 302). The second power-on instruction is a power-on instruction that instructs to turn on the power of a specific information processing device.

According to the power control device 201 of FIG. 2, it is possible to reduce power consumption of an information processing system in which a plurality of information processing apparatuses are powered on using a power-on instruction.

FIG. 4 shows a configuration example of an information processing system including the power supply control device 201 of FIG. 2. As shown in FIG. The information processing system in FIG. 4 is used for cloud computing, AI, HPC, data centers, etc., and includes a terminal device 401 and servers 402-1 to 402-N (N is an integer of 2 or more). Servers 402-1 to 402-N are examples of information processing devices. Among these, the server 402-1 corresponds to the power control device 201 in FIG. 2.

Each server 402-i (i=1 to N) includes a CPU 411-i, a BMC 412-i, a PCH 413-i, and a NIC 414-i. The CPU 411-i executes predetermined information processing. BMC 412-i is an example of a management device, and manages and monitors server 402-i. The PCH 413-i manages data paths and supports the functions of the CPU 411-i. NIC414-i is a communication interface circuit. NIC414-i is an example of a communication unit.

The BMC 412-i is connected to a management network 403, and the NIC 414-i is connected to a business network 404. The management network 403 and the business network 404 are, for example, LANs (Local Area Networks).

The terminal device 401 broadcasts one WOL packet to the management network 403, targeting a group of servers 402-i designated by the user, while the server 402-i is powered off. As a result, the power of the plurality of servers 402-i belonging to the group to be started is turned on. When the server 402-i is powered off, the NIC 414-i is also powered off, and when the server 402-i is powered on, the NIC 414-i is also powered on. A WOL packet whose activation target is a group is an example of a first power-on instruction.

FIG. 5 shows an example of the configuration of the server 402-i in FIG. 4. The server 402-i in FIG. 5 includes a PHY 501, a LAN connector 502, and a LAN connector 503 in addition to the CPU 411-i, BMC 412-i, PCH 413-i, and NIC 414-i. The server 402-i also includes a memory (not shown), an auxiliary storage device, an I/O (Input/Output) device, a cooling fan, a power supply device, and the like.

PHY 501 is a circuit for implementing physical layer functions. LAN connector 502 is connected to management network 403, and LAN connector 503 is connected to business network 404.

BMC412-i includes NIC511 and NIC512. NIC511 and NIC512 are communication interface circuits. The NIC 511 is connected to the PHY 501, and the PHY 501 is connected to the LAN connector 502. NIC512 is connected to NIC414-i. The BMC 412-i receives packets from the management network 403 via the NIC 511, and sends the packets to the management network 403. The BMC 412-i communicates with the NIC 414-i via the NIC 512 using NC-SI (Network Controller Sideband Interface).

NIC414-i includes PHY513 and is connected to PCH413-i. PCH413-i is connected to CPU411-i. The PHY 513 is a circuit for implementing physical layer functions. The NIC 414-i receives packets from the business network 404 via the PHY 513, and sends the packets to the business network 404.

FIG. 6 shows an example of the functional configuration of the BMC 412-1 in FIG. 4. BMC 412-1 in FIG. 6 includes a storage unit 601 and a control unit 602 in addition to NIC 511 and NIC 512. Storage unit 601 and control unit 602 correspond to storage unit 211 and control unit 212 in FIG. 2, respectively.

The storage unit 601 stores a group table 611. The group table 611 contains, for each group of servers 402-i, the MAC (Media Access Control) address of the NIC 414-i included in each of the plurality of servers 402-i and the IP (Internet Protocol) address of the BMC 412-i. recorded. The MAC address of the NIC 414-i and the IP address of the BMC 412-i are recorded in association with the group MAC address. The group MAC address is an example of a common address, and is a MAC address common to multiple servers 402-i belonging to the group.

FIG. 7 shows an example of the group table 611. The group table 611 in FIG. 7 includes a first table 701 and a second table 702. Each entry in the first table 701 corresponds to each server 402-i and includes a group name, MAC address, IP address, and control information. The group name is the identification information of the group, the MAC address is the MAC address of the NIC 414-i included in the server 402-i, and the IP address is the IP address of the BMC 412-i included in the server 402-i. .

The control information is information indicating whether to permit power-on of the server 402-i using a WOL packet that targets a group. The server 402-i that is permitted to be powered on is an example of a specific information processing device. The BMC 412-i of the server 402-i that is permitted to be powered on is an example of a specific management device.

Each entry in the second table 702 includes a group name and a group MAC address. The MAC address, IP address, and control information in the first table 701 are associated with the group MAC address in the second table 702 via the group name.

For example, three servers 402-i belong to the group with group name “A”. The MAC addresses of the entries for those servers 402-i are "AA:AA:AA:00:00:01", "AA:AA:AA:00:00:02", and "AA:AA:AA:00". :00:03”. Further, the IP addresses of the entries for these servers 402-i are "192.168.0.11", "192.168.0.12", and "192.168.0.13".

The control information for the entries “192.168.0.11” and “192.168.0.12” is set to “permit”, and the control information for the entry “192.168.0.13” is set to “permit”. The information is set to "not allowed". The group MAC address of the server 402-i belonging to the group with the group name "A" is "AA:AA:AA:FF:FF:FF".

Similarly, three servers 402-i also belong to the group with group name "B". The group MAC address of the server 402-i belonging to the group with the group name "B" is "BB:BB:BB:FF:FF:FF". The group with the group name "A+B" includes three servers 402-i that belong to the group with the group name "A" and three servers 402-i that belong to the group with the group name "B". The group MAC address of the server 402-i belonging to the group with the group name "A+B" is "FF:FF:FF:FF:FF:FF".

FIG. 8 shows an example of a WOL packet that targets a group. The WOL packet in FIG. 8 includes a destination MAC address and an activation target MAC address. “FF:FF:FF:FF:FF:FF” of the destination MAC address represents broadcast. The activation target MAC address "AA:AA:AA:FF:FF:FF" represents the group MAC address of the group with the group name "A". The WOL packet includes 16 identical activation target MAC addresses.

Note that the terminal device 401 can also transmit a WOL packet that targets a single server 402-i. In this case, as the activation target MAC address, the MAC address of the NIC 414-i included in the activation target server 402-i is used instead of the group MAC address.

When the BMC 412-1 receives the WOL packet from the terminal device 401, the control unit 602 extracts the activation target MAC address from the received WOL packet. When the activation target MAC address is a group MAC address, the control unit 602 searches the group table 611 for an entry for each server 402-i in the group corresponding to the group MAC address.

Next, the control unit 602 selects an entry whose control information is set to "permit" from among the searched entries, and extracts an IP address from the selected entry. Then, the control unit 602 generates an address list 612 including the extracted IP addresses and stores it in the storage unit 601.

FIG. 9 shows an example of the address list 612. The address list 612 in FIG. 9 contains the IP addresses of two entries whose control information is set to "permit" among the entries for the three servers 402-i with the group name "A" shown in FIG. Contains.

Next, the control unit 602 uses each IP address included in the address list 612 to perform control to turn on the power of the server 402-i including the BMC 412-i indicated by the IP address.

If the IP address indicates a BMC 412-i in another server 402-i, the control unit 602 generates a power-on instruction with that IP address as the destination and sends it to the BMC 412-i. The power-on instruction sent to the other server 402-i is an example of a second power-on instruction.

As the power-on instruction, for example, an IPMI (Intelligent Platform Management Interface) command or an instruction based on Redfish (registered trademark) can be used. Upon receiving the power-on instruction, the BMC 412-i powers on the server 402-i. As a result, the power of the NIC 414-i in the server 402-i is also turned on.

On the other hand, if the IP address indicates the BMC 412-1 in the server 402-1, which is the own server, the control unit 602 turns on the power of the server 402-1. As a result, the power of the NIC 414-1 in the server 402-1 is also turned on.

According to the information processing system shown in FIG. 4, the user can use the conventional WOL environment as is by simply specifying a group. Further, by simply transmitting one WOL packet including the group MAC address, multiple servers 402-i can be powered on, improving convenience for the user.

Since the WOL packet is received by the BMC 412-1 that manages the server 402-1, it is possible to turn off the power to the NIC 414-i of each server 402-i before the WOL packet is transmitted. Therefore, the power consumption of each server 402-i is reduced compared to the conventional case. When a large number of servers 402-i belong to a group, the effect of reducing power consumption becomes even greater.

By providing control information in the group table 611, it becomes possible to set for each server 402-i whether or not to permit power-on using a WOL packet targeting a group.

Furthermore, by transmitting the WOL packet using the management network 403, there is no need to send the WOL packet to the business network 404, and the security of the business network 404 is improved.

FIG. 10 is a flowchart showing a specific example of power control processing performed by the BMC 412-1 in FIG. First, the control unit 602 receives a WOL packet from the terminal device 401 (step 1001). The control unit 602 extracts the activation target MAC address from the received WOL packet, and searches the group table 611 for the entry of the server 402-i corresponding to the activation target MAC address (step 1002).

If the activation target MAC address is a group MAC address, the control unit 602 searches the group table 611 for an entry for each server 402-i that corresponds to the group MAC address. On the other hand, if the activation target MAC address is the MAC address of the NIC 414-i included in a single server 402-i, the control unit 602 selects an entry for the server 402-i corresponding to that MAC address from the group table 611. search for.

Next, the control unit 602 selects an entry whose control information is set to "permit" from among the searched entries, and generates an address list 612 including the IP address of the selected entry (step 1003). ). When the activation target MAC address is a group MAC address, an address list 612 including a plurality of IP addresses is generated. On the other hand, if the activation target MAC address is the MAC address of the NIC 414-i included in a single server 402-i, an address list 612 containing a single IP address is generated.

Next, the control unit 602 selects one IP address from the address list 612 (step 1004), and determines whether the selected IP address is the IP address of the BMC 412-1 in the server 402-1, which is the own server. It is checked whether or not (step 1005). If the selected IP address is that of BMC 412-1 (step 1005, YES), control unit 602 powers on server 402-1 (step 1006).

On the other hand, if the selected IP address is the IP address of BMC 412-i in another server 402-i (step 1005, NO), control unit 602 transmits a power-on instruction to that BMC 412-i ( Step 1008). Upon receiving the power-on instruction, the BMC 412-i powers on the other server 402-i.

Next, the control unit 602 checks whether the selected IP address is the last IP address in the address list 612 (step 1007). If the selected IP address is not the last IP address (step 1007, NO), the control unit 602 repeats the processing from step 1004 onward for the next IP address. If the selected IP address is the last IP address (step 1007, YES), the control unit 602 ends the process.

Next, a method for generating the group table 611 will be described with reference to FIGS. 11 to 18. Before receiving the WOL packet from the terminal device 401, the control unit 602 transmits a data request to the BMC 412-i of the other server 402-i. When a response to the data request is received from the BMC 412-i that received the data request, the control unit 602 generates a group table 611 that associates the IP address of the BMC 412-i with a group MAC address, and stores it in the storage unit 601. Store in. Group table 611 includes a first table and a second table.

FIG. 11 is a flowchart illustrating an example of the first table generation process. In the first table generation process, the group table 611 is automatically generated without the user inputting any setting information.

First, the control unit 602 broadcasts an arrival confirmation packet to the management network 403 (step 1101). As the arrival confirmation packet, for example, a ping having a broadcast destination address can be used. In addition to the server 402-i, various devices (not shown) are connected to the management network 403. Therefore, the BMC 412-i of the server 402-i and a device (not shown) receive the arrival confirmation packet and transmit a response to the BMC 412-1.

Next, the control unit 602 transmits a data request to the transmission source that transmitted the response to the arrival confirmation packet (step 1102). Since this data request is sent to determine whether the sender is the BMC 412-i, the type of data requested is arbitrary. As the data request, for example, an IPMI command such as Get Device ID or a data request based on Redfish (registered trademark) can be used.

Next, the control unit 602 determines that the source that sent the response to the data request is the BMC 412-i, and generates a first table that includes the IP address of the source and the IP address of the BMC 412-1. (Step 1103). As a result, the IP addresses of BMC412-1 to BMC412-N are set in the first table.

Next, the control unit 602 transmits a data request requesting a host name, group name, and MAC address to the BMC 412-i indicated by each IP address in the first table, and sends the requested data to the BMC 412-i. (step 1104). However, BMC 412-1 is excluded from the destination of data requests.

The host name is the name of the server 402-i including the BMC 412-i, the group name is the group name of the group to which the server 402-i belongs, and the MAC address is the name of the NIC 414-i included in the server 402-i. i's MAC address. The BMC 412-i stores host names and group names in advance, and the NIC 414-i stores MAC addresses in advance.

The BMC 412-i that has received the data request acquires the MAC address from the NIC 414-i via the NIC 512. Then, the BMC 412-i transmits the stored host name and group name and the acquired MAC address to the control unit 602 as a response to the data request. Upon receiving the response, the control unit 602 sets the group name and MAC address included in the received response to the corresponding IP address entry in the first table.

Further, the control unit 602 obtains the MAC address from the NIC 414-1 via the NIC 512. Then, the control unit 602 sets the group name stored in the BMC 412-1 and the acquired MAC address in the entry including the IP address of the BMC 412-1.

Next, the control unit 602 sets "permit" as control information for each entry in the first table (step 1105). Next, the control unit 602 assigns a group MAC address to each group name in the first table, and generates a second table (step 1106).

FIG. 12 is a flowchart illustrating an example of the second table generation process. In the second table generation process, the user inputs setting information indicating a group name and the range of IP addresses of the BMC 412-i, and a group table 611 is generated based on the setting information.

As a method for inputting the setting information, for example, a web user interface or CLI (Command Line Interface) provided by the BMC 412-i can be used. When using a web user interface, a user can input setting information on a web screen. When using the CLI, the user can log in to the BMC 412-i using telnet or the like and input setting information using commands. The user may input the setting information by selecting an option displayed on the screen, or may directly input the setting information.

First, the user inputs setting information indicating the group name and the IP address range of the BMC 412-i from the terminal device 401. Then, the terminal device 401 transmits the input setting information to the BMC 412-1, and the control unit 602 receives the setting information (step 1201).

FIG. 13 shows an example of the first group setting screen displayed by the terminal device 401 using the web user interface in step 1201. The start IP address and end IP address represent the range of IP addresses of the BMC 412-i. The user inputs the group name "A" and the group name "B", as well as the starting IP address and ending IP address for each group. When the user presses the OK button 1301, the input setting information is sent to the BMC 412-1, and when the user presses the Cancel button 1302, the input setting information is deleted.

Next, the control unit 602 transmits a data request similar to step 1102 in FIG. 11 to the IP addresses included in the range based on the range of IP addresses of each group included in the received configuration information ( Step 1202). However, BMC 412-1 is excluded from the destination of data requests. If the configuration information includes a start IP address and an end IP address as shown in FIG. 13, a data request is sent to each IP address in the range from the start IP address to the end IP address.

Next, the control unit 602 determines that the source that sent the response to the data request is the BMC 412-i, and generates a first table that includes the IP address of the source and the group name included in the configuration information. (Step 1203). If the IP address of BMC 412-1 is included in the IP address range of any group, control unit 602 adds an entry including the IP address of BMC 412-1 to the first table.

Next, the control unit 602 transmits a data request requesting the MAC address of the NIC 414-i to the BMC 412-i indicated by each IP address in the first table, and sends the MAC address of the NIC 414-i to the BMC 412-i. (step 1204). However, BMC 412-1 is excluded from the destination of data requests. The method for acquiring the MAC address of the NIC 414-i is the same as step 1104 in FIG. 11. The control unit 602 sets the acquired MAC address in the corresponding IP address entry in the first table.

If an entry including the IP address of the BMC 412-1 exists, the control unit 602 acquires the MAC address from the NIC 414-1 via the NIC 512. Then, the control unit 602 sets the acquired MAC address in the entry including the IP address of the BMC 412-1.

Next, the control unit 602 requests the terminal device 401 for control information of each entry in the first table, obtains the control information input by the user, and sets it in the first table (step 1205 ).

FIG. 14 shows an example of a control information setting screen displayed by the terminal device 401 using the web user interface in step 1205. The control information setting screen in FIG. 14 displays the group name, MAC address, and IP address of each entry in the first table, as well as control information selection buttons. The user can input control information for each entry by selecting either "permit" or "not allow." When the user presses the OK button 1401, the input control information is sent to the BMC 412-1, and when the user presses the Cancel button 1402, the input control information is deleted.

Next, the control unit 602 assigns a group MAC address to each group name in the first table, and generates a second table (step 1206).

In step 1205, the control unit 602 can also set the control information of all entries in the first table to "permit" without requesting the control information from the terminal device 401.

FIG. 15 is a flowchart illustrating an example of the third table generation process. In the third table generation process, the user inputs a keyword indicating a host name or group name as setting information, and a group table 611 is generated based on the setting information.

First, the user inputs a keyword indicating a host name or group name as setting information from the terminal device 401. Then, the terminal device 401 transmits the input setting information to the BMC 412-1, and the control unit 602 receives the setting information (step 1501).

FIG. 16 shows an example of the second group setting screen displayed by the terminal device 401 using the web user interface in step 1501. The user inputs keywords for each of group name "A" and group name "B". The keyword “HOST_A” is a character string included in the host name of the server 402-i that belongs to the group with the group name “A”. The keyword “HOST_B” is a character string included in the host name of the server 402-i that belongs to the group with the group name “B”. The user may input a character string included in a group name as a keyword instead of a character string included in a host name.

When the user presses the OK button 1601, the input setting information is sent to the BMC 412-1, and when the user presses the Cancel button 1602, the input setting information is deleted.

Next, the control unit 602 broadcasts the arrival confirmation packet to the management network 403 (step 1502). Next, the control unit 602 transmits a data request requesting a host name and group name to the transmission source that sent the response to the arrival confirmation packet, and acquires the requested data from the transmission source (step 1503).

Next, the control unit 602 determines that the source that sent the requested data is the BMC 412-i, and specifies the BMC 412-i that sent the host name or group name that includes the keyword of the received configuration information. Then, the control unit 602 generates a first table including the IP address of the identified BMC 412-i and the acquired group name (step 1504).

If the host name or group name of the server 402-1 includes the keyword of the configuration information, the control unit 602 adds an entry including the IP address of the BMC 412-1 to the first table.

Next, the control unit 602 performs steps 1505 to 1507. The processing from step 1505 to step 1507 is similar to the processing from step 1204 to step 1206 in FIG.

FIG. 17 is a flowchart illustrating an example of the fourth table generation process. In the fourth table generation process, the user inputs setting information indicating a group name to the automatically searched list of servers 402-i, and a group table 611 is generated based on the setting information.

First, the control unit 602 broadcasts an arrival confirmation packet to the management network 403 (step 1701). Next, the control unit 602 transmits a data request requesting the MAC address of the NIC 414-i to the transmission source that sent the response to the arrival confirmation packet, and acquires the MAC address of the NIC 414-i from the transmission source ( Step 1702).

Next, the control unit 602 determines that the source that transmitted the MAC address of the NIC 414-i is the BMC 412-i, and creates a first table containing the IP address of the source and the IP address of the BMC 412-1. Generate (step 1703). The MAC address received from the sender is set in the entry including the sender's IP address.

Further, the control unit 602 obtains the MAC address from the NIC 414-1 via the NIC 512. Then, the control unit 602 sets the acquired MAC address in the entry including the IP address of the BMC 412-1.

Next, the control unit 602 requests the terminal device 401 for setting information indicating the group name and control information of each entry in the first table, obtains the setting information input by the user, and The table is set (step 1704).

FIG. 18 shows an example of the third group setting screen displayed by the terminal device 401 using the web user interface in step 1704. The group setting screen in FIG. 18 displays a list of servers 402-i corresponding to each entry in the first table. The list of servers 402-i includes a host name and IP address, as well as a group name input field and a control information selection button. The user inputs control information for each server 402-i by inputting the group name of each server 402-i and selecting either "permit" or "disallow".

When the user presses the OK button 1801, the input setting information is sent to the BMC 412-1, and when the user presses the Cancel button 1802, the input setting information is deleted.

Next, the control unit 602 assigns a group MAC address to each group name in the first table, and generates a second table (step 1705).

In step 1704, the control unit 602 can also set the control information of all entries in the first table to "permit" without requesting the control information from the terminal device 401.

According to the first to fourth table generation processes, by checking whether there is a response to the data request, it is possible to determine whether or not the source that sent the response is the BMC 412-i. Therefore, it becomes possible to exclude the IP addresses of devices other than the server 402-i, set only the IP address of the BMC 412-i in the group table 611, and associate it with the group MAC address.

The configuration of the power supply control device 201 in FIG. 2 is merely an example, and some components may be omitted or changed depending on the use or conditions of the power supply control device 201. The configurations of the information processing systems in FIGS. 1 and 4 are merely examples, and some components may be omitted or changed depending on the use or conditions of the information processing system.

The configuration of the server 402-i in FIG. 5 is only an example, and some components may be omitted or changed depending on the configuration or conditions of the information processing system. The configuration of the BMC 412-1 in FIG. 6 is only an example, and some components may be omitted or changed depending on the configuration or conditions of the server 402-i.

The flowcharts in FIGS. 3, 10 to 12, 15, and 17 are only examples, and some of the processes may be omitted or changed depending on the configuration or conditions of the power control device 201 or the information processing system. . For example, if the server 402-1 does not belong to any group and is excluded from the WOL packet activation targets, the processes of steps 1005 and 1006 in FIG. 10 can be omitted.

The group table 611 shown in FIG. 7, the WOL packet shown in FIG. 8, and the address list 612 shown in FIG. 9 are only examples. Or change depending on conditions. When powering on the server 402-i registered in the group table 611 is always permitted, the control information in the group table 611 can be omitted.

The group setting screens shown in FIGS. 13, 16, and 18 and the control information setting screen shown in FIG. 14 are merely examples, and other types of group setting screens and control information setting screens may be used.

FIG. 19 shows an example of the hardware configuration of an information processing device (computer) used as the BMC 412-i in FIGS. 4 to 6. BMC 1901 in FIG. 19 includes a CPU 1911, a memory 1912, a communication interface circuit 1913, and a communication interface circuit 1914. These components are hardware and are connected to each other by signal lines.

The memory 1912 is, for example, a semiconductor memory such as Read Only Memory (ROM), Random Access Memory (RAM), or flash memory, and stores programs and data used for processing. Memory 1912 can be used as storage unit 601 in FIG. Memory 1912 can also store the IP address of BMC 412-i and the host name and group name of server 402-i.

The CPU 1911 (processor) manages and monitors the server 402-i by executing programs using the memory 1912, for example. The CPU 1911 also operates as the control unit 602 in FIG. 6 by executing programs using the memory 1912.

An operator or user can store programs and data in a portable recording medium (not shown) and load them into the memory 1912 for use. As the portable recording medium, a memory device, a flexible disk, an optical disk, a magneto-optical disk, etc. are used. The portable recording medium may be a Compact Disk Read Only Memory (CD-ROM), a Digital Versatile Disk (DVD), a Universal Serial Bus (USB) memory, or the like.

Thus, the computer-readable storage medium that stores the programs and data used for processing is a physical (non-transitory) storage medium, such as the memory 1912 or a portable storage medium.

The communication interface circuit 1913 and the communication interface circuit 1914 correspond to the NIC 511 and NIC 512 in FIG. 5, respectively. BMC 1901 can receive programs and data from an external device via communication interface circuit 1913, load them into memory 1912, and use them.

Note that the configuration of the BMC 1901 in FIG. 19 is only an example, and some components may be omitted or changed depending on the configuration or conditions of the information processing system.

Having described the disclosed embodiments and their advantages in detail, those skilled in the art will appreciate that various modifications, additions, and omissions may be made without departing from the scope of the invention as clearly set forth in the claims. Dew.

Regarding the embodiment described with reference to FIGS. 2 to 19, the following additional notes are further disclosed.
(Additional note 1)
a storage unit that stores a common address common to a plurality of information processing devices in association with an address of a management device that manages each of the plurality of information processing devices;
When a first power-on instruction including the common address is received, an address of a specific management device that manages a specific information processing device among the plurality of information processing devices that is associated with the common address is used. , a control unit that transmits to the specific management device a second power-on instruction instructing to turn on the power of the specific information processing device;
A power supply control device comprising:
(Additional note 2)
The storage unit further stores control information indicating whether to permit power-on of each of the plurality of information processing devices according to the first power-on instruction;
If the storage unit stores control information indicating that power-on of the specific information processing device is permitted in accordance with the first power-on instruction, the control unit transmits the second power-on instruction to the second power-on instruction. The power control device according to supplementary note 1, characterized in that the power control device transmits data to a specific management device.
(Additional note 3)
Each of the plurality of information processing devices includes a communication unit,
The power control device according to appendix 1 or 2, wherein the specific management device powers on a communication unit included in the specific information processing device when receiving the second power-on instruction.
(Additional note 4)
Before receiving the first power-on instruction, the control unit transmits a data request to a management device that manages each of the plurality of information processing devices, and transmits a data request from the management device that manages each of the plurality of information processing devices to the management device that manages each of the plurality of information processing devices. Any one of appendices 1 to 3, characterized in that when a response to the data request is received, an address of a management device that manages each of the plurality of information processing devices is stored in the storage unit in association with the common address. The power supply control device according to item 1.
(Appendix 5)
An information processing device system comprising a plurality of information processing devices and a power supply control device,
The power supply control device includes:
a storage unit that stores a common address common to the plurality of information processing devices in association with an address of a management device that manages each of the plurality of information processing devices;
When a first power-on instruction including the common address is received, an address of a specific management device that manages a specific information processing device among the plurality of information processing devices that is associated with the common address is used. , a control unit that transmits to the specific management device a second power-on instruction instructing to turn on the power of the specific information processing device,
When the specific management device receives the second power-on instruction, the specific management device powers on the specific information processing device.
An information processing system characterized by:
(Appendix 6)
The storage unit further stores control information indicating whether to permit power-on of each of the plurality of information processing devices according to the first power-on instruction;
If the storage unit stores control information indicating that power-on of the specific information processing device is permitted in accordance with the first power-on instruction, the control unit transmits the second power-on instruction to the second power-on instruction. The information processing system according to supplementary note 5, characterized in that the information is transmitted to a specific management device.
(Appendix 7)
Each of the plurality of information processing devices includes a communication unit,
7. The information processing system according to appendix 5 or 6, wherein the specific management device powers on a communication unit included in the specific information processing device when receiving the second power-on instruction.
(Appendix 8)
Before receiving the first power-on instruction, the control unit transmits a data request to a management device that manages each of the plurality of information processing devices, and transmits a data request from the management device that manages each of the plurality of information processing devices to the management device that manages each of the plurality of information processing devices. Any one of appendices 5 to 7, characterized in that when a response to the data request is received, an address of a management device that manages each of the plurality of information processing devices is stored in the storage unit in association with the common address. The information processing system according to item 1.
(Appendix 9)
receiving a first power-on instruction including a common address common to the plurality of information processing devices, which is stored in association with an address of a management device that manages each of the plurality of information processing devices;
A step that instructs to turn on the power of the specific information processing device using an address of a specific management device that manages a specific information processing device among the plurality of information processing devices that is associated with the common address. 2. Sending a power-on instruction to the specific management device;
A power control method characterized in that processing is executed by a computer.
(Appendix 10)
The process of transmitting the second power-on instruction to the specific management device includes control information indicating whether or not to permit power-on of each of the plurality of information processing devices according to the first power-on instruction. The power source according to appendix 9, wherein when the first power-on instruction indicates that power-on of the specific information processing device is permitted, the second power-on instruction is transmitted to the specific management device. Control method.
(Appendix 11)
Each of the plurality of information processing devices includes a communication unit,
11. The power control method according to appendix 9 or 10, wherein the specific management device, when receiving the second power-on instruction, powers on a communication unit included in the specific information processing device.
(Appendix 12)
Before receiving the first power-on instruction, transmitting a data request to a management device that manages each of the plurality of information processing devices;
When a response to the data request is received from a management device that manages each of the plurality of information processing devices, storing an address of the management device that manages each of the plurality of information processing devices in association with the common address;
12. The power supply control method according to any one of appendices 9 to 11, wherein the computer further executes the process.

101-1 to 101-N, 402-1 to 402-N Server 102, 403 Management network 103, 404 Business network 111-1 to 111-N, 411-1 to 411-N, 1901 CPU
112-1~112-N, 412-1~412-N BMC
113-1~113-N, 413-1~413-N PCH
114-1~114-N, 414-1~414-N, 511, 512 NIC
201 Power control device 211, 601 Storage unit 212, 602 Control unit 401 Terminal device 501, 513 PHY
502, 503 LAN connector 611 Group table 612 Address list 701 First table 702 Second table 1301, 1401, 1601, 1801 OK button 1302, 1402, 1602, 1802 Cancel button 1902 Memory 1903, 1904 Communication interface circuit

Claims (6)

a storage unit that stores a common address common to a plurality of information processing devices in association with an address of a management device that manages each of the plurality of information processing devices;
When a first power-on instruction including the common address is received, an address of a specific management device that manages a specific information processing device among the plurality of information processing devices that is associated with the common address is used. , a control unit that transmits to the specific management device a second power-on instruction instructing to turn on the power of the specific information processing device;
A power supply control device comprising: The storage unit further stores control information indicating whether to permit power-on of each of the plurality of information processing devices according to the first power-on instruction;
If the storage unit stores control information indicating that power-on of the specific information processing device is permitted in accordance with the first power-on instruction, the control unit transmits the second power-on instruction to the second power-on instruction. The power control device according to claim 1, wherein the power control device transmits the information to a specific management device. Each of the plurality of information processing devices includes a communication unit,
3. The power control device according to claim 1, wherein the specific management device powers on a communication unit included in the specific information processing device when receiving the second power-on instruction. Before receiving the first power-on instruction, the control unit transmits a data request to a management device that manages each of the plurality of information processing devices, and transmits a data request from the management device that manages each of the plurality of information processing devices to the management device that manages each of the plurality of information processing devices. 4. When a response to a data request is received, an address of a management device that manages each of the plurality of information processing devices is stored in the storage unit in association with the common address. 2. The power supply control device according to item 1. An information processing device system comprising a plurality of information processing devices and a power supply control device,
The power supply control device includes:
a storage unit that stores a common address common to the plurality of information processing devices in association with an address of a management device that manages each of the plurality of information processing devices;
When a first power-on instruction including the common address is received, an address of a specific management device that manages a specific information processing device among the plurality of information processing devices that is associated with the common address is used. , a control unit that transmits to the specific management device a second power-on instruction instructing to turn on the power of the specific information processing device,
When the specific management device receives the second power-on instruction, the specific management device powers on the specific information processing device.
An information processing system characterized by: receiving a first power-on instruction including a common address common to the plurality of information processing devices, which is stored in association with an address of a management device that manages each of the plurality of information processing devices;
A step that instructs to turn on the power of the specific information processing device using an address of a specific management device that manages a specific information processing device among the plurality of information processing devices that is associated with the common address. 2. Sending a power-on instruction to the specific management device;
A power control method characterized in that processing is executed by a computer.

Images