Server, server management method and apparatus, computer device, and medium

Abstract

Disclosed are a server, a server management method and apparatus, a computer device, and a medium, relating to the technical field of computers. The server comprises a chassis and a plurality of server units; the plurality of server units are all located in the chassis, and any two server units among the plurality of server units are connected; the plurality of server units have a first networking mode and a second networking mode, the first networking mode and the second networking mode are both used for describing connection relationships between the plurality of server units, and the connection relationships described by the first networking mode and the second networking mode are different. The server can be applicable to different service scenes, and the networking requirements of different service scenes are met.

Description

Server, server management method and device, computer equipment and medium

[0001] This application claims priority to Chinese patent application No. 202410128412.7 filed on January 29, 2024, entitled “Server, server management method and device, computer equipment and medium,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present application relates to the field of computer technology, and in particular to a server, a server management method and apparatus, computer equipment, and a medium. Background Art

[0003] Mobile network operators or wireless service providers need to deploy servers to provide users with various services such as telephone services.

[0004] In the related art, a server includes a chassis and a plurality of server units located in the chassis. The plurality of server units are connected according to a set network topology to form a corresponding network architecture.

[0005] However, the network architecture corresponding to the server is single and cannot meet the networking requirements in different business scenarios.

[0006] Summary of the Invention

[0007] The present application provides a server, a server management method and apparatus, computer equipment and media, and the server can meet the networking requirements in different business scenarios.

[0008] In a first aspect, the present application provides a server comprising a chassis and multiple server units. The multiple server units are located in the chassis. Any two of the multiple server units are connected, i.e., a connection channel exists between any two server units. The multiple server units have a first networking mode and a second networking mode, wherein the first networking mode and the second networking mode are both used to describe the connectivity relationship between the multiple server units, and the connectivity relationships described by the first networking mode and the second networking mode are different.

[0009] Here, the connectivity relationship indicates whether the connection channel between each two server units is enabled. When the connection channel between two server units is enabled, the two server units can use it for data transmission; when the connection channel between two server units is not enabled, the two server units cannot use it for data transmission. The difference in connectivity relationships described in the first networking mode and the second networking mode means that the activation status of at least one connection channel is different in the first networking mode and the second networking mode.

[0010] In this application, in different business scenarios, multiple server units in the server can adopt different networking methods, so as to meet the networking requirements in different business scenarios.

[0011] In one possible embodiment, the first networking mode is a dual-star networking mode, and the second networking mode is a fully interconnected networking mode. For the fully interconnected networking mode, the connection channels between each server unit are enabled, while for the dual-star networking mode, the two server units serve as the first switching unit and the second switching unit, the connection channel between the first switching unit and the second switching unit, and the connection channel between the first switching unit and the server units other than the first switching unit and the second switching unit are enabled, the connection channel between the second switching unit and the server units other than the first switching unit and the second switching unit is enabled, and the connection channels between each server unit other than the first switching unit and the second switching unit are not enabled. It can be seen that the connectivity relationships described in the dual-star networking mode and the fully interconnected networking mode are different.

[0012] When multiple server units adopt a dual-star network, it can be applied to low-traffic business scenarios, and the traffic of each server unit is aggregated and forwarded by the first switching unit or the second switching unit. When multiple server units adopt a fully interconnected network, it can be applied to high-traffic business scenarios. In some high-traffic scenarios, the first switching unit, the second switching unit and other server units can directly access the external network to realize data transmission and reception. In other high-traffic scenarios, the first part of the server units can directly access the external network, and the other server units do not need to directly access the external network, but access the external network through the first part of the server units, but data can be directly transmitted between each server unit.

[0013] Optionally, the chassis includes multiple connection interfaces, and each of the multiple server units is connected to one of the multiple connection interfaces. The multiple server units include a first switching unit, a second switching unit, and at least two business units. The first business unit of the at least two business units includes multiple ports, and the multiple ports include a first port connected to the first switching unit, a second port connected to the second switching unit, and a third port connected to the second business unit. The first business unit and the second business unit are any two business units of the at least two business units. That is, each port of the first business unit is respectively connected to each server unit except the first business unit, so that there is a connection between any two server units in the server.

[0014] When the first business unit is connected to different connection interfaces among the multiple connection interfaces, the arrangement position of the first port of the first business unit among the multiple ports of the first business unit remains unchanged, and the arrangement position of the second port of the first business unit among the multiple ports of the first business unit remains unchanged. In this way, no matter which connection interface the first business unit is connected to, it can be connected to the first switching unit through the same port and to the second switching unit through the same port at the same time, thereby achieving normalization of the business units. In this case, after the positions of the first switching unit and the second switching unit are determined, the business units can be plugged in and out arbitrarily, reducing operational difficulty and facilitating improved server networking efficiency.

[0015] Optionally, the business unit can directly access the external network, or needs to access the external network through other server units that can directly access the external network.

[0016] Optionally, the server further includes a backplane located in the chassis and connected to the plurality of server units. By connecting the server units via the backplane, wiring can be simplified, further improving server networking efficiency.

[0017] In some examples, the backplane is an optical backplane. In other examples, the backplane is an electrical backplane. During implementation, the appropriate backplane type can be selected as needed.

[0018] Optionally, at least one of the first switching unit and the second switching unit includes: a first mainboard, a first control module, a first interconnection module and a first network module, the first control module, the first interconnection module and the first network module are all carried by the first mainboard, and the first control module is electrically connected to the first interconnection module and the first network module respectively.

[0019] In a possible implementation, the business unit includes a second mainboard, a second control module, and a second interconnection module. The second control module and the second interconnection module are carried by the second mainboard, and the second control module is electrically connected to the second interconnection module.

[0020] In another possible embodiment, the business unit includes a third mainboard, a third control module, a third interconnection module and a third network module, the third control module, the third interconnection module and the third network module are all carried by the third mainboard, and the third network module is electrically connected to the third interconnection module and the third control module respectively.

[0021] Optionally, the multiple connection interfaces are arranged in an array, such as a one-dimensional array. The connection interface connected to the first switching unit and the connection interface connected to the second switching unit are two connection interfaces located in the middle of the multiple connection interfaces. That is, the server units connected to the two connection interfaces located in the middle serve as the first switching unit and the second switching unit. In this way, the signal routing distance between the first switching unit and the second switching unit and each business unit is shorter, the loss is reduced, and it is beneficial to improve signal quality.

[0022] Optionally, the server further comprises a first management unit, the first management unit being connected to the plurality of server units respectively, and the first management unit being used to control the networking mode of the plurality of server units. By setting up the first management unit, the networking mode of the plurality of server units can be automatically controlled.

[0023] Optionally, the server is a blade server, the server unit is a card-type server unit, and the connection interface is a slot. Blade servers have low costs.

[0024] In a second aspect, the present application provides a server management method that can be used to control the server networking mode of the first aspect. The method includes: obtaining information about multiple server units; determining a target networking mode based on the server unit information, wherein the target networking mode indicates the connectivity relationship between the multiple server units; and configuring connection channels between the multiple server units based on the target networking mode.

[0025] Optionally, the information of the server unit includes the type of the server unit, and the type of the server unit includes a service node and a switching node.

[0026] Optionally, the information of the server unit further includes a location of the server unit, where the location of the server unit is used to indicate a connection interface to which the server unit is connected.

[0027] Optionally, determining the target networking mode based on the information of the server units includes: when the multiple server units are all business units, determining the target networking mode to be a fully interconnected network; or, when the multiple server units include two switching units and multiple business units, determining the target networking mode to be a dual-star network; or, when the multiple server units include two switching units and multiple business units and the positions of the two switching units are target positions, determining the target networking mode to be a dual-star network.

[0028] In a third aspect, the present application provides a server management device. The server management device has the function of implementing the method described in the second aspect or any optional embodiment of the second aspect. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the above functions.

[0029] In a fourth aspect, a computer device is provided. The computer device includes a processor and a memory. The memory is used to store software programs and modules. The processor implements the method of the second aspect or any possible implementation of the second aspect by running or executing the software programs and / or modules stored in the memory.

[0030] Optionally, there are one or more processors and one or more memories.

[0031] Optionally, the memory may be integrated with the processor, or the memory may be provided separately from the processor.

[0032] In the specific implementation process, the memory can be a non-transitory memory, such as a read-only memory (ROM), which can be integrated on the same chip as the processor or be set on different chips. This application does not limit the type of memory and the setting method of the memory and the processor.

[0033] In a fifth aspect, a computer program product is provided, wherein the computer program product includes computer program code, and when the computer program code is executed by a computer, the computer executes the method in the second aspect or any possible implementation of the second aspect.

[0034] In a sixth aspect, the present application provides a computer-readable storage medium, which is used to store program codes executed by a processor, wherein the program codes include methods for implementing the above-mentioned second aspect or any possible implementation of the second aspect.

[0035] In the seventh aspect, the present application provides a chip comprising a processor, the processor being configured to call and execute instructions stored in a memory from the memory, so that a computer device equipped with the chip executes the method in the above-mentioned second aspect or any possible implementation of the second aspect.

[0036] In an eighth aspect, the present application provides another chip. The other chip includes an input interface, an output interface, a processor, and a memory. The input interface, the output interface, the processor, and the memory are connected via an internal connection path. The processor is configured to execute code in the memory. When the code is executed, the processor is configured to perform the method described in the second aspect or any possible implementation of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] FIG1 is a schematic diagram of the structure of a server provided in an embodiment of the present application;

[0038] FIG2 is a schematic diagram of a connection relationship between the various server units of the server in FIG1;

[0039] FIG3 is a schematic diagram of another connection relationship between the server units of the server in FIG1 ;

[0040] FIG4 is a schematic diagram of the structure of another server provided in an embodiment of the present application;

[0041] FIG5 is a schematic diagram of a connection relationship between the various server units of the server in FIG4;

[0042] FIG6 is a schematic diagram of another connection relationship between the server units of the server in FIG4;

[0043] FIG7 is a schematic diagram of another connection relationship between the server units of the server in FIG4;

[0044] FIG8 is a schematic diagram of another connection relationship between the server units of the server in FIG4;

[0045] FIG9 is a schematic structural diagram of a server unit provided in an embodiment of the present application;

[0046] FIG10 is a schematic structural diagram of another server unit provided in an embodiment of the present application;

[0047] FIG11 is a schematic structural diagram of another server unit provided in an embodiment of the present application;

[0048] FIG12 is a schematic structural diagram of another server provided in an embodiment of the present application;

[0049] 13 is a flow chart of a server management method provided in an embodiment of the present application;

[0050] FIG14 is a schematic diagram of a server management device provided in an embodiment of the present application;

[0051] FIG15 is a schematic structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0053] An embodiment of the present application provides a server comprising a chassis and a plurality of server units. The plurality of server units are located in the chassis. Any two of the plurality of server units are connected. The plurality of server units have a first networking mode and a second networking mode, wherein the first networking mode and the second networking mode are both used to describe a connectivity relationship between the plurality of server units, and the connectivity relationships described by the first networking mode and the second networking mode are different.

[0054] Here, the connectivity relationship indicates whether the connection channel between each two server units is enabled. When the connection channel between two server units is enabled, the two server units can use it for data transmission; when the connection channel between two server units is not enabled, the two server units cannot use it for data transmission. The difference in connectivity relationships described in the first networking mode and the second networking mode means that the activation status of at least one connection channel is different in the first networking mode and the second networking mode.

[0055] In the embodiment of the present application, each connection channel is connected to a port of a server unit at each end. Activating a connection channel means that both server units connected to the connection channel have enabled the port to which the connection channel is connected. If either of the two server units connected to the connection channel has disabled the port to which the connection channel is connected, the connection channel is not activated.

[0056] In the embodiment of the present application, the first networking mode and the second networking mode are applicable to different business scenarios. Therefore, different networking modes can be selected in different business scenarios to meet the networking requirements in different business scenarios.

[0057] In some embodiments, the server is a blade server, and accordingly, the server unit is a card-type (also called blade-type) server unit, and the connection interface is a slot. A blade server is a server that can plug multiple card-type server units into a standard height chassis and is a low-cost server platform that can achieve high availability high density (HAHD). In other embodiments, the server is a rack-mounted server, and the connection interface is a fiber optic interface or a network port.

[0058] The following will take a blade server as an example to illustrate the structure and working principle of the server provided in the embodiment of the present application.

[0059] Figure 1 is a schematic diagram of the structure of a server provided in an embodiment of the present application. As shown in Figure 1, the server is a blade server, which includes a chassis 11 and multiple server units 12. For a blade server, the server unit 12 can also be called a node or a blade.

[0060] Optionally, the blade server includes 2N server units 12. N is a positive integer, for example, 2, 3, 4, or 8. FIG1 illustrates an example where N is 4. That is, in FIG1 , there are 8 server units 12. Accordingly, the chassis 11 includes 8 slots, and each server unit 12 is inserted into a slot, thereby being disposed in the chassis 11.

[0061] Any two server units 12 are connected, that is, there is a connection channel between each two server units 12. The multiple server units 12 have a first networking mode and a second networking mode, wherein the first networking mode and the second networking mode are both used to describe the connectivity relationship between the multiple server units 12, and the connectivity relationships described by the first networking mode and the second networking mode are different.

[0062] In the embodiment of the present application, the multiple server units 12 include a first switching unit, a second switching unit, and at least two business units. That is, there are two switching units in the server, and all other switching units except the two switching units are business units. The multiple ports of the first business unit include a first port connected to the first switching unit, a second port connected to the second switching unit, and a third port connected to the second business unit. Here, the first business unit and the second business unit are any two business units of the at least two business units.

[0063] When the first business unit is connected to different connection interfaces, the arrangement position of the first port of the first business unit among the multiple ports of the first business unit remains unchanged, and the arrangement position of the second port of the first business unit among the multiple ports of the first business unit remains unchanged.

[0064] Assume that a first service unit has X ports arranged sequentially along a certain direction, where X is an integer greater than 2. When the first service unit is connected to one connection interface of the chassis, the i-th port of the first service unit is connected to the first switching unit, i.e., the i-th port is the first port, and the j-th port of the first service unit is connected to the second switching unit, i.e., the j-th port is the second port. When the first service unit is connected to another connection interface of the chassis, the i-th port of the first service unit is still connected to the first switching unit, and the j-th port of the first service unit is connected to the second switching unit. In this way, regardless of which connection interface the first service unit is connected to, it can connect to the first switching unit and the second switching unit through the same port, thereby achieving service unit normalization.

[0065] Figure 2 is a schematic diagram illustrating the connectivity between the various server units of the server in Figure 1. For example, in Figure 2, the chassis includes eight slots, namely slots 1 through 8; each server unit includes seven ports, namely A0...A6. The server units connected to slots 4 and 5 are the first switching unit and the second switching unit, respectively. Regardless of which slot the server unit is connected to other than slots 4 and 5, port A0 of the server unit is connected to the first switching unit connected to slot 4. In this case, after determining the positions of the first and second switching units, the service units can be plugged in arbitrarily, reducing operational difficulty and facilitating improved server networking efficiency.

[0066] Table 1 Double star network

[0067] The corresponding connectivity relationships in Figure 2 are shown in Table 1. Using the connection method shown in Figure 2, the server units in the server form a dual-star network. This dual-star network can be applied to low-traffic business scenarios, where traffic from each server unit 12 is aggregated and forwarded by the first switching unit or the second switching unit.

[0068] Figure 3 is a schematic diagram of another connectivity relationship between the server units in the server shown in Figure 1. The dotted lines in Figure 3 represent connections between business units. As shown in Figure 3, based on Figure 2, the ports of each business unit that are not connected to the first and second switching units are interconnected to ensure that each business unit has connectivity to every other business unit. The connectivity relationship between the server units after this connection is shown in Table 2. Using the connection method shown in Figure 3, the server units in the server form a fully interconnected network. A fully interconnected network can be applied in high-traffic business scenarios. All server units, including the first and second switching units, can directly access the external network to transmit and receive data. Alternatively, some server units can directly access the external network, while others do not, but instead access the external network through server units that can directly access the external network. For example, the first and second switching units can directly access the external network, while other server units access the external network through the first and second switching units. In another example, the first switching unit, the second switching unit, and another server unit can directly access the external network, while the other server units access the external network through these three server units.

[0069] Table 2 Fully interconnected network

[0070] FIG4 is a schematic diagram of the structure of another server provided in an embodiment of the present application. The difference from the embodiment shown in FIG1 is that the number of server units 12 in the server is four. The four server units 12 are located in a chassis 11.

[0071] Figure 5 is a schematic diagram illustrating the connectivity between the various server units in the server shown in Figure 4. In Figure 5, the chassis includes four slots, slots 1 through 4; each server unit 12 includes three ports, A0, A2, and Slots 2 and 3. The server units 12 connected to slots 2 and 3 are the first and second switching units, respectively. Regardless of which slot a server unit 12 is connected to, port A0 on the server unit 12 is always connected to the first switching unit connected to slot 2.

[0072] The corresponding connectivity relationship of Figure 5 is shown in Table 3. Using the connection method shown in Figure 5, the server units in the server form a dual-star network, which is suitable for low-traffic business scenarios.

[0073] Table 3 Dual-star network

[0074] FIG6 is a schematic diagram of another connectivity relationship between the various server units of the server in FIG4 . The dotted lines in FIG6 represent the connections between business units. As shown in FIG6 , based on FIG5 , the ports of each business unit that are not connected to the first switching unit and the second switching unit are interconnected to ensure that each business unit has a connection to other business units. The connectivity relationship between the various server units after connection is shown in Table 4. Using the connection method shown in FIG6 , the various server units in the server form a fully interconnected network, which is suitable for high-traffic business scenarios.

[0075] Table 4 Fully interconnected network

[0076] Figure 7 is a schematic diagram illustrating another alternative connectivity relationship between the server units in the server shown in Figure 4. As shown in Figure 7, the connectivity relationship differs from that in Figure 5 in that slots 1 and 4 connect to the first and second switching units, respectively, while the server units connected to the other slots are service units. The corresponding connectivity relationship in Figure 7 is shown in Table 5. Using the connection method shown in Figure 7, the server units in the server form a dual-star network, which is suitable for low-traffic business scenarios.

[0077] Table 5 Dual-star network

[0078] Figure 8 is a schematic diagram illustrating another alternative connectivity relationship between the server units in the server shown in Figure 4. The dashed lines in Figure 8 represent connections between service units. As shown in Figure 8 , based on the configuration shown in Figure 7 , the ports of each service unit that are not connected to the first switching unit and the second switching unit are interconnected to ensure that each service unit has a connection to every other service unit. The connectivity relationship between the server units after this connection is shown in Table 4.

[0079] In some examples, when multiple connection interfaces of a server are arranged in an array (typically a one-dimensional array), the server units 12 connected to two connection interfaces located in the middle of the multiple connection interfaces are used as the first switching unit and the second switching unit. For example, in Figure 2, the server units 12 connected to slots 4 and 5 are used as the first switching unit and the second switching unit. For another example, in Figure 5, the server units 12 connected to slots 2 and 3 are used as the first switching unit and the second switching unit. This is because the distance between the slots in the middle and the other slots is shorter, and the shorter the signal routing distance, the lower the loss. Therefore, using the server units 12 connected to the two connection interfaces located in the middle as the first switching unit and the second switching unit is beneficial to improving signal quality. In other embodiments, as long as the signal quality requirements are met, the server units 12 connected to any two connection interfaces can be selected as the first switching unit and the second switching unit. For example, in Figure 7, the server units 12 connected to slots 1 and 4 are used as the first switching unit and the second switching unit.

[0080] In the related art, different types of servers are usually used for business scenarios with large traffic and business scenarios with small traffic. For example, blade servers are used in business scenarios with large traffic, while rack servers are used in business scenarios with small traffic. The use of two different types of servers is not conducive to system maintenance. The server provided in the embodiment of the present application is not only applicable to business scenarios with large traffic, but also to business scenarios with small traffic, and can meet the needs of different communication business scenarios, such as meeting the 5G communication business scenario of the cloud core network. When the server adopts a dual-star network, the connection channel between the first switching unit and the second switching unit and the connection channel between the first switching unit and the server unit other than the first switching unit and the second switching unit are enabled, the connection channel between the second switching unit and the server unit other than the first switching unit and the second switching unit is enabled, and the connection channel between each server unit other than the first switching unit and the second switching unit is not enabled. The dual-star network can be used to carry control plane services, and the control panel service is characterized by small traffic and multiple ports. When the server adopts a fully interconnected network, the connection channels between each server unit are all enabled. Fully interconnected networking can be used to carry user-plane services. User-plane services are characterized by high traffic volume, requiring each server unit to be able to directly connect to the network edge (provider edge, PE) device without going through a switch to connect to the PE device. It can be seen that the server provided in the embodiment of the present application can be used in different scenarios according to needs, and different networking modes can be obtained by simply swapping two switching units (i.e., the aforementioned first switching unit and second switching unit) and two service units. The networking mode is simple, easy to maintain, and low in cost.

[0081] The structure of the server unit is exemplarily described below.

[0082] Figure 9 is a schematic diagram of the structure of a server unit provided in an embodiment of the present application. As shown in Figure 9, the server unit 12 includes a first mainboard 901, a first control module 902, a first interconnection module 903, and a first network module 904. The first control module 902, the first interconnection module 903, and the first network module 904 are all supported by the first mainboard 901, and the first network module 904 is electrically connected to the first interconnection module 903 and the first control module 902, respectively.

[0083] The first interconnection module 903 is used to connect to other server units in the server. The first network module 904 is used to connect to upper-layer devices (not shown), such as a carrier's switch, to connect to an external network. The first control module 902 is used to process data received by the first network module 904 and send the data to the external network through the first network module 904.

[0084] Optionally, the first interconnect module 903 includes an interface card comprising a plurality of first side ports and at least one second side port, wherein the plurality of first side ports are configured to connect to the same connection interface, and the at least one second side port is configured to connect to the first network module 904. For example, in FIG9 , the number of first side ports is equal to or less than the number of second side ports, and each first side port is connected to a second side port, thereby enabling data from other server units to be sent to an external network, or data from an external network to be sent to a corresponding server unit. In other embodiments, the number of first side ports is less than the number of second side ports, and each second side port is respectively connected to a respective first side port. Such an interface card may also be referred to as a mesh card. Such an interface card also includes a switch chip configured to selectively connect the first side port to one or more second side ports.

[0085] Optionally, the first network module 904 may include a network card or a network processor (NP), etc. The embodiment of the present application does not limit the type of the network card, and a suitable network card can be selected according to actual needs.

[0086] Optionally, the first control module 902 includes one or more processors. For example, in FIG9 , two processors are included, namely CPU1 and CPU2. The embodiment of the present application does not limit the type of processor, and the type can be selected according to actual needs.

[0087] In low-traffic business scenarios, the first and second switching units need to aggregate traffic from various business units, employing the structure shown in Figure 9. Network modules are installed in the first and second switching units to connect to upper-layer devices, eliminating the need for additional switches in the server and reducing costs.

[0088] Figure 10 is a schematic diagram of the structure of another server unit provided in an embodiment of the present application. As shown in Figure 10, the server unit 12 includes a second mainboard 1001, a second control module 1002, and a second interconnection module 1003. The second control module 1002 and the second interconnection module 1003 are supported by the second mainboard 1001, and the second control module 1002 and the second interconnection module 1003 are electrically connected.

[0089] The second control unit 1002 includes one or more processors, for example, two processors, CPU 1 and CPU 2, as shown in Figure 10. The second interconnection module 1003 includes multiple ports, each of which is electrically connected to a respective processor.

[0090] For details about second interconnect module 1003, see the aforementioned first interconnect module 903. In Figure 10, second interconnect module 1003 can connect each first side port to each processor. This ensures that data received by second interconnect module 1003 from other server units can be forwarded to any processor, and data received by second interconnect module 1003 from any processor can be forwarded to any server unit. It should be noted that the figure only shows one first side port, omitting the other first side ports.

[0091] In other embodiments, the second interconnect module 1003 can connect each first side port to any processor, and the processors can be connected to each other. For example, assume there are seven first side ports, three of which are connected to CPU1, and the remaining four are connected to CPU2. In this way, through data forwarding between the processors, data received by the second interconnect module 1003 from other server units can be forwarded to any processor, and data received from any processor can be forwarded to any server unit.

[0092] In low-traffic business scenarios, since the traffic of the business unit is forwarded by the first switching unit and the second switching unit, the business unit can adopt the structure shown in Figure 10, without the need for a network module, thereby saving the network card inside the server. This business unit can be called a centralized switching business unit.

[0093] Figure 11 is a schematic diagram of the structure of another server unit provided in an embodiment of the present application. As shown in Figure 11, the server unit 12 includes a third mainboard 1101, a third control module 1102, a third interconnection module 1103, and a third network module 1104. The third control module 1102, the third interconnection module 1103, and the third network module 1104 are all supported by the third mainboard 1101, and the third network module 1104 is electrically connected to the third interconnection module 1103 and the third control module 1102, respectively.

[0094] Optionally, the third interconnection module 1103 and the third control module 1102 are related to the first interconnection module 903 and the first control module 902, and detailed descriptions are omitted here. The third network module 1104 includes but is not limited to a network processor (NP), etc., which is used to accelerate data processing.

[0095] In some high-traffic business scenarios, each business unit has a high-traffic data transmission demand. In order to reduce latency, each business unit needs to be able to exchange data directly with the external network. In this case, each business unit can adopt the structure in Figure 11 and the third network module 1104 is connected to the external network, that is, each business unit includes a network module, so that the external network can be accessed directly through the network module. In other high-traffic business scenarios, only some business units need to directly access the external network. Such business units can adopt the structure in Figure 11 and the third network module 1104 includes an output interface connected to the external network; while other business units do not need to directly access the external network, but need to directly transmit data with other server units. Such business units can adopt the structure in Figure 11 and the third network module 1104 does not include an output interface connected to the external network. In these two high-traffic business scenarios, data can be directly transmitted between each server unit. Such business units can be called distributed business units, which is conducive to reducing latency.

[0096] In an embodiment of the present application, the control module (such as the aforementioned first control module 902, the second control module 1002 or the third control module 1102) may also include a memory for storing received data and intermediate data generated during data processing.

[0097] In one possible implementation, as shown in Figures 9 to 11, the server further includes a backplane 13, through which the server units 12 are connected. In this embodiment of the present application, the backplane is provided with a plurality of connection channels, one end of each connection channel being used to connect to a port of a server unit in one connection interface, and the other end being used to connect to a port of a server unit in another connection interface.

[0098] In some examples, the backplane is an optical backplane. In this case, the aforementioned connection interface is an optical interface, and the interconnection modules in each server unit include an optical module, which interfaces with the optical interface to achieve a connection between the server unit and the optical backplane. The optical module is used to convert electrical signals in the server unit into optical signals and transmit them to other server units via the optical backplane and / or convert optical signals from the optical backplane into electrical signals and process the electrical signals. Due to the high transmission speed of the optical backplane, using an optical backplane to connect the various server units can help reduce latency.

[0099] Optionally, the optical backplane is implemented using multiple optical fibers, each optical fiber being a connection channel. Alternatively, the optical backplane is implemented using an optical waveguide, wherein the optical waveguide has multiple optical transmission channels, each optical transmission channel being a connection channel.

[0100] In other examples, the backplane is an electrical backplane. In this case, the connection interface is an electrical interface, and the interconnect modules in each server unit include an electrical connector, such as an RJ45 connector. The electrical connector mates with the electrical interface, thereby connecting the server unit to the electrical backplane.

[0101] Optionally, the electrical backplane may be a printed circuit board, and the transmission channel may be a conductor in the circuit board. The technology of using an electrical backplane to connect various server units is mature and helps to reduce costs.

[0102] In other embodiments, the server units 12 may be directly connected to each other via a cable, with one end of the cable plugged into one server unit 12 and the other end of the cable plugged into another server unit.

[0103] Figure 12 is a schematic diagram of the structure of another server provided in an embodiment of the present application. As shown in Figure 12, in addition to the chassis 11 and the server units 12, the server also includes a first management unit 14, which is connected to each server unit 12. The first management unit 14 is used to manage each server unit 12 in the server, for example, to control the networking of multiple server units 12 in the server. For details on how the first management unit 14 controls the networking of multiple server units 12, please refer to the method embodiments below, and a detailed description is omitted here.

[0104] In some examples, the first management unit 14 is connected to each server unit 12 via the aforementioned backplane 13. In this case, the backplane 13 also includes a channel for connecting the first management unit 14 and each server unit 12. In other examples, the first management unit 14 is connected to each server unit 12 via other connection structures, including but not limited to an inter-integrated circuit (I2C) bus, a serial peripheral interface (SPI) bus, or a network cable.

[0105] Optionally, the server further includes a second management unit 15, which is connected to each server unit 12 in the server. The second management unit 15 can serve as a backup unit for the first management unit 14 to improve server reliability. The connection between the second management unit 15 and each server unit 12 can be similar to the connection between the first management unit 14 and each server unit 12.

[0106] Optionally, the second management unit 15 is electrically connected to the first management unit 14 to achieve data synchronization between the first management unit 14 and the second management unit 15. Optionally, the second management unit 15 is connected to the first management unit 14 via an I2C bus, an SPI bus, a network cable, or a universal asynchronous receiver / transmitter (UART), etc., which is not limited in this application.

[0107] The embodiment of the present application further provides a method for managing a blade server, which can be executed by a computer device, the computer device being the aforementioned first management unit or second management unit. As shown in FIG13 , the method includes steps 1301 to 1303 .

[0108] 1301: Get information about each server unit in the chassis.

[0109] The information of the server unit includes the type of the server unit. In some examples, the type of the server unit can be a switching unit or a service unit.

[0110] The type of a server unit can be obtained in either of the following two ways:

[0111] Method 1: The server unit stores the type of the server unit. After each server unit is connected to the corresponding connection interface and powered on, each server unit will send its own type to the first management unit, so that the first management unit can obtain the type of each server unit.

[0112] Method 2: arranging a detection pin in the slot, and determining the type of the server unit inserted into the slot by the level of the detection pin.

[0113] In some examples, there is one detection pin. After the server unit is inserted into the slot, if the level of the detection pin is a first level, the server unit is determined to be a service unit; if the level of the detection pin is a second level, the server unit is determined to be a switching unit. The first level is greater than or less than the second level.

[0114] In other examples, there are multiple detection pins. After a server unit is inserted into a slot, if the levels of multiple detection pins are a first level combination, the server unit is determined to be a service unit; if the levels of multiple detection pins are a second level combination, the server unit is determined to be a switch unit. For example, if there are three detection pins, the first level combination is 110, and the second level combination is 101, where 1 indicates that the level of the detection pin is high, and 0 indicates that the level of the detection pin is low.

[0115] It should be noted that in other embodiments, the types of server units may include switching units, centralized switching service units, and distributed service units. That is, service units are further divided into two types to more accurately determine the target networking mode based on the information of the server units.

[0116] Optionally, the server unit information also includes location information of the server unit. The location information is used to indicate the connection port to which the server unit is connected, for example, it can be an identifier of the connection port. When the connection port is a slot, the identifier of the connection port is the slot identifier.

[0117] When the server unit information is obtained using method 1, the correspondence between the type of the received server unit and the receiving port can be recorded. For example, the type of the server unit received at connection port 1 is a business unit, and the type of the server unit received at connection port 2 is a switching unit. When the server unit information is obtained using method 2, the type of the server unit in each slot can also be determined based on the level of the detection pin in each slot.

[0118] 1302: Determine the target networking mode according to the information of the server unit.

[0119] Optionally, the target networking mode is a dual-star networking or a fully interconnected networking.

[0120] In some examples, the first management unit pre-stores a networking policy that indicates the correspondence between server unit characteristics and networking methods. The server unit characteristics describe combinations of server unit types. For example, a first combination corresponds to a first networking method, a second combination corresponds to a second networking method, and a third combination corresponds to a third networking method. Accordingly, in step 1302, a target networking method is determined based on the acquired server unit information and the networking policy.

[0121] Exemplarily, step 1302 may include the following two steps:

[0122] The first step is to determine the characteristics of the server unit according to the information of the server unit; the second step is to determine the target networking mode according to the determined characteristics of the server unit and the networking strategy.

[0123] In the second step, the networking mode corresponding to the determined characteristics of the server unit in the networking policy is determined as the target networking mode. That is, the characteristics of the server unit are searched in the networking policy, and the networking mode corresponding to the found characteristics of the server unit is determined as the target networking mode.

[0124] In some examples, server unit characteristics are converted from server unit information. For example, server unit characteristics include the number of service units and the number of switching units, which can be obtained by counting the number of service units and the number of switching units based on the server unit type. In other examples, server unit information is the server unit characteristics. For example, server unit information includes the type of server unit corresponding to each connection interface, and this server unit information can be directly used as the server unit characteristics.

[0125] In a first possible implementation, the characteristics of the server unit include at least one of the number of service units and the number of switching units. That is, there are the following three situations:

[0126] First, the characteristics of the server unit only include the number of business units.

[0127] In the networking strategy, when the number of business units is the number of server units contained in the server, the corresponding networking mode is fully interconnected networking; and when the number of business units is the difference between the number of server units contained in the server and 2, the corresponding networking mode is dual-star networking.

[0128] For example, assuming that the number of server units included in the server is 8 and the characteristic of the server unit is 8, it means that the number of business units is the number of server units included in the server, and the corresponding networking mode is full interconnection networking.

[0129] For another example, assuming that the number of server units included in the server is 8 and the characteristic of the server unit is 6, the number of business units is the difference between the number of server units included in the server and 2, and the corresponding networking mode is dual-star networking.

[0130] Second, the characteristics of the server unit include only the number of switching units.

[0131] In the networking strategy, the networking mode corresponding to the number of switching units being 0 is a fully interconnected networking, and the networking mode corresponding to the number of switching units being 2 is a dual-star networking.

[0132] The third type of server unit characteristics include the number of business units and the number of switching units.

[0133] In the networking strategy, the first combination corresponds to a fully interconnected network; the second combination corresponds to a dual-star network. In the first combination, the number of service units is the number of server units in the server, and the number of switching units is 0. In the second combination, the number of service units is the number of server units in the server minus 2, and the number of switching units is 2.

[0134] For example, assuming that the number of server units contained in the server is 8 and the characteristics of the server unit are {8, 0}, it means that the number of business units is the number of server units contained in the server and the number of switching units is 0, and the corresponding networking mode is fully interconnected networking.

[0135] For another example, assuming that the number of server units contained in the server is 8 and the characteristics of the server units are {6, 2}, it means that the number of business units is the number of server units contained in the server minus 2 and the number of switching units is 2, and the corresponding networking mode is dual-star networking.

[0136] In the third case, the target networking mode can be matched more accurately.

[0137] In other words, in the first possible implementation, when the information of the server unit indicates that all server units are business units, the target networking mode is determined to be a fully interconnected network; and when the information of the server unit indicates that multiple server units include two switching units and multiple business units, the target networking mode is determined to be a dual-star network.

[0138] When the types of server units are divided into switching units, centralized switching service units and distributed service units, step 1302 includes determining the target networking mode as fully interconnected networking when the information of the server units indicates that all server units are distributed service units; or determining the target networking mode as dual-star networking when the information of the server units indicates that multiple server units include two switching units and multiple centralized switching service units.

[0139] In a second possible implementation, the characteristics of the server units are used to indicate the number and location of at least one type of server units. In this implementation, searching for a target networking mode in combination with the location and type of the server units can reduce the possibility of networking errors.

[0140] Exemplarily, the characteristics of the server unit can be in any of the following four ways:

[0141] First, the characteristics of the server unit only include the number and location of the business units.

[0142] In the networking strategy, when the number of business units is the number of server units contained in the server, the corresponding networking mode is fully interconnected networking; and when the number of business units is the difference between the number of server units contained in the server and 2 and the location of the business unit is the target location, the corresponding networking mode is dual-star networking.

[0143] For example, assuming that the number of server units contained in the server is 8 and the characteristics of the server unit are {8, slots 1-8}, it means that the number of business units is the number of server units contained in the server, and the corresponding networking mode is fully interconnected networking. Since the number of business units is the number of server units contained in the server, it means that all positions are business units, so the step of matching the positions of business units can be omitted. During implementation, the positions of business units can also be matched. In this case, in the networking strategy, when the number of business units is the number of server units contained in the server and the position of the server unit is the target position (for example, slots 1-8), the corresponding networking mode is fully interconnected networking.

[0144] For another example, assuming that the number of server units contained in the server is 8, the target positions are slots 1-3 and slots 6-8, and the characteristics of the server units are {8, slots 1-3 and slots 6-8}, it means that the number of business units is the difference between the number of server units contained in the server and 2, and the position of the business unit is the target position. The corresponding networking method is dual-star networking.

[0145] The second type, server unit, is characterized by only the number and location of switching units.

[0146] In the networking strategy, when the number of switching units is 0, the corresponding networking mode is fully interconnected. When the number of switching units is 2 and the switching units are located at the target location, the corresponding networking mode is dual-star networking. Here, the target location is the middle of the multiple connection ports of the chassis.

[0147] For example, assuming that the server contains 8 server units, the target positions are slots 4 and 5, and the characteristics of the server units are {2, slot 4 and slot 5}, it means that the number of switching units is 2 and the position of the switching units is the target position, and the corresponding networking mode is dual-star networking.

[0148] The third type of server unit characteristics include the number and location of business units and the number and location of switching units.

[0149] In the networking strategy, the first combination corresponds to a fully interconnected network; the second combination corresponds to a dual-star network. In the first combination, the number of service units is the number of server units in the server, and the number of switching units is 0. In the second combination, the number of service units is the number of server units in the server minus 2, and the service unit locations are the first target locations. The number of switching units is 2, and the switching unit locations are the second target locations.

[0150] For example, assuming that the number of server units contained in the server is 8 and the characteristics of the server unit are {8, 0}, it means that the number of business units is the number of server units contained in the server and the number of switching units is 0, and the corresponding networking mode is fully interconnected networking.

[0151] For another example, assuming that the number of server units contained in the server is 8, and the characteristics of the server units are {6, slots 1-3 and slots 6-8}, {2, slot 4 and slot 5}, it means that the number of business units is the number of server units contained in the server minus 2 and the position of the business unit is the first target position, the number of switching units is 2 and the position of the switching unit is the second target position, and the corresponding networking mode is dual-star networking.

[0152] Fourthly, the characteristic of the server unit is an array (or a set), and each element in the array is used to indicate the type of the server unit to which the corresponding connection interface is connected.

[0153] If there are two types of server units, each element can be represented by 1 bit. When the element is 1, it indicates that the type of the server unit is the first type. When the element is 2, it indicates that the type of the server unit is the second type.

[0154] In the networking strategy, the first combination corresponds to a fully interconnected network; the second combination corresponds to a dual-star network. In the first combination, each server unit connected to a connection interface is a service unit. In the second combination, the server unit corresponding to the first target location is a service unit, and the server unit at the second target location is a switching unit.

[0155] For example, assuming the server contains 8 server units, 1 indicates that the server unit type is a business unit, and 0 indicates that the server unit type is a switching unit. If the server unit characteristics are {1, 1, 1, 0, 0, 1, 1, 1}, it means that the server units corresponding to the first target positions (slots 1-3 and slots 6-8) are all business units, and the server units corresponding to the second target positions (slots 4 and 5) are switching units. The target networking mode is determined to be fully interconnected.

[0156] For another example, if the characteristics of the server unit are {1, 1, 1, 1, 1, 1, 1}, it means that the server unit connected to each connection interface is a business unit, and the target networking mode is determined to be a fully interconnected networking.

[0157] In other words, in the second possible implementation, when the information of the server unit indicates that all server units are business units, the target networking mode is determined to be fully interconnected networking; and when the information of the server unit indicates that multiple server units include two switching units and multiple business units, and the positions of the two switching units are the target positions, the target networking mode is determined to be dual-star networking.

[0158] If there are three types of server units, each element can be represented by 2 bits, and the value combination of these 2 bits corresponds to a type of server unit. The corresponding method of the value combination and the type of server unit can be set according to actual needs and is not limited in this embodiment of the application.

[0159] 1303: Configure the connection channels between the server units according to the target networking mode.

[0160] In this way, the corresponding connectivity relationship in the target networking mode can be achieved.

[0161] In 1303 , configuration information may be sent to each server unit according to the target networking mode. The configuration information is used to configure a connection channel corresponding to the server unit, such as enabling or disabling the connection channel.

[0162] When the target networking mode is dual-star networking, the connection channels between the first switching unit and other server units are enabled, the connection channels between the second switching unit and other server units are enabled, and the connection channels between server units other than the first switching unit and the second switching unit are disabled.

[0163] When the target networking mode is full interconnection, all connection channels are enabled.

[0164] In the embodiment of the present application, by obtaining information of each server unit, automatic networking of the server units can be achieved, thereby reducing maintenance difficulty and reducing networking costs.

[0165] Optionally, the method further includes: outputting prompt information when the target networking mode corresponding to the information of the multiple server units is not determined.

[0166] For example, if the networking mode corresponding to the determined characteristics of the server unit does not exist in the networking strategy, it means that the target networking mode does not exist, and a prompt message can be output. The prompt message can be used to remind the user to replace the server unit.

[0167] The embodiments of the present application do not limit the method for outputting the prompt information. For example, the prompt information can be output via a display device, or via an audible or visual alarm. When the prompt information is output via a display device, the embodiments of the present application do not limit the content of the prompt information. For example, the prompt information can include: "The server unit is an unknown combination" or "Networking error", etc. This can improve the localizability of networking errors and improve network maintenance efficiency.

[0168] If the characteristics of the server unit also include the location of the server unit, then when the networking policy does not contain a networking mode corresponding to the determined characteristics of the server unit, the output prompt information indicates the location of the server unit that needs to be replaced. For example, the prompt information may include: "Please replace the server unit in slot 1."

[0169] Figure 14 is a block diagram of a server management device provided in an embodiment of the present application. The management device can be implemented as all or part of a server management unit through software, hardware, or a combination of both. As shown in Figure 14, the management device 1400 includes an acquisition unit 1401, a determination unit 1402, and a connection unit 1403.

[0170] Among them, the acquisition unit 1401 is used to obtain information of multiple server units; the determination unit 1402 is used to determine the target networking mode based on the information of the server units, and the target networking mode is used to indicate the connectivity relationship between the multiple server units; the connection unit 1403 is used to enable the connection channel between the multiple server units according to the target networking mode.

[0171] Optionally, the determination unit 1402 is used to determine that the target networking mode is a fully interconnected networking when the multiple server units are all business units; or, when the multiple server units include two switching units and multiple business units, determine that the target networking mode is a dual-star networking; or, when the multiple server units include two switching units and multiple business units, and the positions of the two switching units are at the target position, determine that the target networking mode is a dual-star networking.

[0172] It should be noted that the server management device provided in the above embodiment only uses the division of the above functional units as an example to illustrate the management of the server. In actual applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. In addition, the server management device provided in the above embodiment and the server management method embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0173] In some embodiments, a computer device is further provided, which may be the aforementioned first management unit or second management unit. The computer device includes a processor and a memory, wherein the memory is used to store software programs. The processor runs or executes the software programs stored in the memory, thereby enabling the computer device to implement the server management method provided in the above method embodiment.

[0174] Figure 15 exemplifies a possible architecture diagram of a computer device 1500. As shown in Figure 15 , computer device 1500 includes a memory 1501, a processor 1502, a communication interface 1503, and a bus 1504. Memory 1501, processor 1502, and communication interface 1503 are interconnected via bus 1504.

[0175] Memory 1501 can be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). Memory 1501 can store programs. When the program stored in memory 1501 is executed by processor 1502, processor 1502 and communication interface 1503 are used to execute the server management method. Memory 1501 can also store data sets. For example, a portion of the storage resources in memory 1501 is divided into a data storage module for storing server unit information and networking policies.

[0176] The processor 1502 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits.

[0177] Processor 1502 may also be an integrated circuit chip with signal processing capabilities. During implementation, some or all of the functions of the signal processing device of the present application may be performed by hardware integrated logic circuits or software instructions within processor 1502. The aforementioned processor 1502 may also be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. It may implement or execute the various methods disclosed in the above-described embodiments of the present application. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present application may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules within the decoding processor. The software modules may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 1501. Processor 1502 reads information from memory 1501 and, in conjunction with its hardware, performs some of the functions of the server management device of the embodiments of the present application.

[0178] The communication interface 1503 uses a transceiver module such as, but not limited to, a transceiver to implement communication between the computer device 1500 and other devices or communication networks. For example, information (such as the information of the aforementioned server unit) can be obtained through the communication interface 1503.

[0179] The bus 1504 may include a path for transmitting information between various components of the computer device 1500 (eg, the memory 1501 , the processor 1502 , and the communication interface 1503 ).

[0180] In some embodiments, a computer-readable storage medium is also provided, which stores computer instructions. When the computer instructions stored in the computer-readable storage medium are executed by an optical communication device, the optical communication device executes the server management method provided by the above method embodiment.

[0181] In some embodiments, a computer program product is also provided, which includes one or more computer program instructions. When the computer program instructions are loaded and run by a computer, the computer executes the server management method provided by the above method embodiment.

[0182] In some embodiments, a chip is also provided, including a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call and run the computer instructions from the memory to execute the server management method provided by the above method embodiment.

[0183] Unless otherwise defined, the technical or scientific terms used herein shall have the usual meaning understood by persons of ordinary skill in the field to which this application belongs. The words "first", "second", "third" and similar terms used in the patent application specification and claims of this application do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one" or "a" do not indicate a quantity limitation, but rather indicate the existence of at least one. Words such as "include" or "comprising" mean that the elements or objects appearing before "include" or "comprising" cover the elements or objects listed after "include" or "comprising" and their equivalents, and do not exclude other elements or objects. "A and / or B" means that there are the following three situations: the first, A; the second, B; the third, A and B.

[0184] The above is only an embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A server, characterized in that: The server comprises: a chassis and a plurality of server units, wherein the plurality of server units are all located in the chassis, and any two of the plurality of server units are connected; The multiple server units have a first networking mode and a second networking mode, wherein the first networking mode and the second networking mode are both used to describe the connectivity relationship between the multiple server units, and the connectivity relationships described by the first networking mode and the second networking mode are different.

2. The server according to claim 1, wherein: The chassis includes a plurality of connection interfaces, and each of the plurality of server units is connected to one of the plurality of connection interfaces; The multiple server units include a first switching unit, a second switching unit, and at least two business units, the first business unit of the at least two business units includes a plurality of ports, the plurality of ports include a first port connected to the first switching unit, a second port connected to the second switching unit, and a third port connected to the second business unit, the first business unit and the second business unit are any two business units of the at least two business units; Among them, when the first business unit is connected to different connection interfaces among the multiple connection interfaces, the arrangement position of the first port of the first business unit among the multiple ports of the first business unit remains unchanged, and the arrangement position of the second port of the first business unit among the multiple ports of the first business unit remains unchanged.

3. The server according to claim 2, wherein: The multiple connection interfaces are arranged in an array, and the connection interface connected to the first switching unit and the connection interface connected to the second switching unit are two connection interfaces located in the middle of the multiple connection interfaces.

4. The server according to any one of claims 1 to 3, characterized in that: The first networking mode is a dual-star networking mode, and the second networking mode is a fully interconnected networking mode.

5. The server according to claim 2, wherein: At least one of the first switching unit and the second switching unit includes: A first mainboard, a first control module, a first interconnection module and a first network module, wherein the first control module, the first interconnection module and the first network module are all carried by the first mainboard, and the first control module is electrically connected to the first interconnection module and the first network module respectively.

6. The server according to claim 2, wherein: The business unit includes a second mainboard, a second control module and a second interconnection module, the second control module and the second interconnection module are carried by the second mainboard, and the second control module is electrically connected to the second interconnection module; or, The business unit includes a third mainboard, a third control module, a third interconnection module and a third network module. The third control module, the third interconnection module and the third network module are all carried by the third mainboard, and the third network module is electrically connected to the third interconnection module and the third control module respectively.

7. The server according to any one of claims 1 to 6, characterized in that: The server further includes a first management unit, which is connected to the multiple server units respectively and is used to control the networking mode of the multiple server units.

8. The server according to any one of claims 1 to 7, characterized in that: The server is a blade server.

9. A server management method, characterized in that: The method comprises: Get information about multiple server units in a chassis; Determining a target networking mode according to information of the plurality of server units, wherein the target networking mode is used to indicate a connectivity relationship between the plurality of server units; According to the target networking mode, connection channels between the multiple server units are configured.

10. The method according to claim 9, characterized in that The information of the server unit includes the type of the server unit, or the information of the server unit includes the type of the server unit and the location of the server unit.

11. The method according to claim 9 or 10, characterized in that The determining of the target networking mode according to the information of the server unit includes: When the plurality of server units are all business units, determining that the target networking mode is a fully interconnected networking; or, When the multiple server units include two switching units and multiple service units, determining that the target networking mode is a dual-star networking; or, When the multiple server units include two switching units and multiple service units, and the two switching units are located at target locations, the target networking mode is determined to be a dual-star networking mode.

12. A server management device, characterized in that: The device comprises: An acquisition unit, used to acquire information of multiple server units; a determining unit, configured to determine a target networking mode based on the information of the server unit, wherein the target networking mode is used to indicate a connectivity relationship between the plurality of server units; A connection unit is used to configure connection channels between the multiple server units according to the target networking mode.

13. The device according to claim 12, characterized in that The information of the server unit includes the type of the server unit, or the information of the server unit includes the type of the server unit and the location of the server unit.

14. The device according to claim 12 or 13, characterized in that The determination unit is used to determine that the target networking mode is a fully interconnected networking when the multiple server units are all business units; or, when the multiple server units include two switching units and multiple business units, determine that the target networking mode is a dual-star networking; or, when the multiple server units include two switching units and multiple business units, and the positions of the two switching units are at the target position, determine that the target networking mode is a dual-star networking.

15. A computer device, characterized in that: The computer device includes a processor and a memory, the memory is used to store a software program, and the processor runs or executes the software program stored in the memory, so that the computer device implements the method according to any one of claims 9 to 11.

16. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store program codes executed by a processor, where the program codes include instructions for implementing the method according to any one of claims 9 to 11.

Images