Configuration method and device of center node

Abstract

The invention provides a central node configuration method and device, the method is applied to a data center, the data center comprises M central nodes, the data center corresponds to N branch mechanisms, each branch mechanism corresponds to x priority central nodes in the M central nodes, each central node and each branch mechanism are configured with bandwidths, and the M is an integer greater than or equal to 1. The method comprises the following steps: in response to the increase of a new branch mechanism, obtaining the sum of bandwidths of corresponding branch mechanisms when each center node serves as x priority center nodes; determining the bandwidth utilization rate of each central node according to the sum of the bandwidths of the central nodes and the bandwidth of each central node; and based on the bandwidth utilization rate of each center node, determining x priority center nodes corresponding to the new branch mechanism from the M center nodes. Through the bandwidth utilization rate when the center node serves as each priority center node, the maximum flow condition of the center node can be obtained, load balancing is fully achieved, and the processing efficiency of the data center is improved.

Description

Technical Field

[0001] This application relates to the technical field of gateway cluster load adaption, and particularly to a method for configuring a central node, a device for configuring a central node, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Software Defined Networking (SDN) is a new type of network architecture that can separate the control plane and data plane of network devices, enabling the control plane to run as an independent upper-layer application, uniformly scheduling all network resources, and achieving flexible control of network traffic. Software Defined Wide Area Network (SD-WAN) products are developed based on SDN technology. SD-WAN product users may set multiple central nodes in a data center and then specify a primary central node and a backup central node for each branch. In this way, each branch can execute the business of the branch through the specified primary central node. Once a failure occurs between a certain branch and the specified primary central node, the branch can switch to the specified backup central node and continue to execute the business of the branch through the specified backup central node, realizing stable operation of the business.

[0003] With the continuous increase of business, new branches will join the data center. Currently, the main method is to manually specify a primary central node and a backup central node for the new branch in the data center. However, the method of manually specifying central nodes is inefficient. Moreover, due to the real-time change of the business traffic of branches, the operating states of each central node are also constantly changing. The currently manually specified relatively idle primary central node and backup central node may experience business backlog at the next moment due to the sudden increase in the real-time traffic of other branches in the central node, thereby reducing the business processing efficiency of the data center. It can be seen that in the scenario of specifying central nodes for new branches, achieving load balancing of each central node in the data center is an urgent problem to be solved currently. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method for configuring a central node, a device for configuring a central node, a computer device, a computer-readable storage medium, and a computer program product to improve the configuration efficiency of the central node.

[0005] To solve the above technical problems, the embodiments of this application provide the following technical solutions:

[0006] In a first aspect, the present application provides a method for configuring a central node, which is applied to a data center. The data center includes M central nodes, and the data center corresponds to N branches. Each branch corresponds to x priority central nodes in the M central nodes, and each central node and each branch is configured with bandwidth. The method includes: in response to the addition of a new branch, obtaining the sum of the bandwidths of the branches corresponding to each central node when it is used as x priority central nodes; determining the bandwidth utilization of each central node based on the sum of the bandwidths of each central node and the bandwidth of each central node; and determining the x priority central nodes corresponding to the new branch from the M central nodes based on the bandwidth utilization of each central node.

[0007] Compared with the prior art, the configuration method of the central node provided in the first aspect of the present application, when it is necessary to specify central nodes of various priorities for a new branch among multiple central nodes, by calculating the bandwidth utilization rate of each central node as all priority central nodes of other branches, and then selecting several central nodes with higher bandwidth utilization rate in turn as the priority central nodes of the new branch. In this way, there is no need to manually specify the priority central node. In addition, the bandwidth corresponding to each branch is fixed. Even if the traffic of the branch changes in real time, it will not exceed the preset bandwidth limit. Therefore, the maximum traffic situation of the central node can be obtained through the bandwidth utilization rate of the central node as the central node of each priority. Even if multiple branches switch central nodes due to link failures, the worst situation can be taken into account, and the central nodes of various priorities with relatively ample bandwidth can be selected for the new branch, so as to fully realize load balancing and improve the processing efficiency of the data center.

[0008] In other embodiments provided in the present application, the bandwidth utilization of each central node also includes the bandwidth utilization of x-1, ..., 1 priority central nodes, with the priority decreasing from low to high; based on the bandwidth utilization of each central node, x priority central nodes corresponding to the new branch are determined from the M central nodes, including: when the bandwidth utilization does not exceed a preset threshold, x priority central nodes corresponding to the new branch are determined from the M central nodes in the order of x, x-1, ..., 1.

[0009] First, select a central node for the new branch among the bandwidth utilization rates of x priority central nodes. If the bandwidth utilization rate of some nodes exceeds the preset threshold, resulting in insufficient available central nodes for selection, then select a central node for the new branch among the bandwidth utilization rates of the x - 1 priority central nodes except the lowest - priority ones. Decrease the priority in this way until a central node is selected for the new branch. Since, except for the highest - priority central node, other priority central nodes will not be used by the corresponding branches temporarily, selecting central nodes by decreasing the priority in this way can select central nodes with more sufficient bandwidth in practice for the new branch, improving the accuracy of central node selection.

[0010] In other embodiments provided by the present application, to determine x priority central nodes corresponding to the new branch from M central nodes in the order of x, x - 1, …, 1, it includes: in the case of x, x - 1, …, or 1, based on the remaining bandwidth of the central nodes, determine x priority central nodes corresponding to the new branch from M central nodes.

[0011] Under the same priority, if there are too many available central nodes, selection can be made according to the remaining bandwidth of the central nodes. Since the remaining bandwidth is relatively simple in value compared to the bandwidth utilization rate, it is relatively convenient to make a selection numerically, which can improve the selection efficiency of the central nodes.

[0012] In other embodiments provided by the present application, to determine x priority central nodes corresponding to the new branch from M central nodes based on the remaining bandwidth of the central nodes, it includes: in the order of x, x - 1, …, 1, based on the remaining bandwidth of the central nodes, determine x priority central nodes corresponding to the new branch from M central nodes.

[0013] When the remaining bandwidth of the same group of priorities is the same, continue to reduce the lowest priority, and then select a central node according to the remaining bandwidth of the reduced priority, which can achieve the efficient determination of the optimal central node.

[0014] In other embodiments provided by the present application, to determine x priority central nodes corresponding to the new branch from M central nodes in the order of x, x - 1, …, 1 based on the remaining bandwidth of the central nodes, it includes: in the order of x, x - 1, …, 1, based on the remaining bandwidth of the central nodes, determine y central nodes from M central nodes; if y is greater than x, then according to the identifier (ID) of each central node, determine x priority central nodes corresponding to the new branch from y central nodes.

[0015] If the central node still cannot be determined based on the remaining bandwidth in descending order of priority, the central node is determined according to the ID of the central node. Through the ID, the central node that joined the data center earlier can be selected, so that the selection of the central node is carried out according to the same standard, avoiding randomly assigning central nodes to new branches in the data center, making the planning of each central node in the data center orderly and fully utilized, and improving the utilization rate of each central node in the data center.

[0016] In other embodiments provided by the present application, the bandwidth utilization rate of each central node further includes the bandwidth utilization rates as the x - 1, …, 1 priority central nodes, and the priorities decrease from low to high; based on the bandwidth utilization rate of each central node, determining x priority central nodes corresponding to the new branch from the M central nodes includes: generating a data group for each central node, the data group including the threshold state, the remaining bandwidth corresponding to the x priority central nodes, the remaining bandwidth corresponding to the x - 1 priority central nodes, …, the remaining bandwidth corresponding to the 1 priority central node, and the ID. And when the bandwidth utilization rates corresponding to the x priorities do not exceed the preset threshold, the threshold state is x + 1; when the bandwidth utilization rates corresponding to the x priorities exceed the preset threshold, but the bandwidth utilization rates corresponding to the x - 1 priorities do not exceed the preset threshold, the threshold state is x; …; when the bandwidth utilization rates corresponding to the 2 priorities exceed the preset threshold, but the bandwidth utilization rates corresponding to the 1 priority do not exceed the preset threshold, the threshold state is 1; sorting each central node in descending order according to the order of each parameter in the data group; and sequentially determining the first x central nodes in the sorting as the x priority central nodes of the new branch.

[0017] Through the data group of the central node, the various priorities and bandwidth values involved in the central node can be effectively sorted. Furthermore, sorting each central node according to the data group can effectively separate the relevant calculations and selections of the central node, improving the accuracy of the central node selection.

[0018] In other embodiments provided by the present application, x = 3; obtaining the sum of the bandwidths of the branches corresponding to each central node when it is the x priority central nodes includes: obtaining the sum of the bandwidths of the branches corresponding to each central node when it is the high - priority central node, the medium - priority central node, and the low - priority central node; based on the bandwidth utilization rate of each central node, determining x priority central nodes corresponding to the new branch from the M central nodes includes: based on the bandwidth utilization rate of each central node, determining the high - priority central node, the medium - priority central node, and the low - priority central node corresponding to the new branch from the M central nodes.

[0019] Configure central nodes with high, medium, and low priorities for the new branch office. While ensuring that the branch office can achieve primary and standby switching, it is also possible to set multiple priorities in a more numerous and uncomplicated manner to determine the redundancy of the bandwidth utilization rate of the central nodes, improving the accuracy and efficiency of central node selection.

[0020] In other embodiments provided by the present application, the method further includes: if the bandwidth utilization rate of a central node as the highest priority central node exceeds a preset threshold, add a new central node; determine the new central node as the highest priority central node for some branch offices corresponding to the central node whose bandwidth utilization rate exceeds the preset threshold; according to the bandwidth utilization rates of multiple central nodes as x priority central nodes for some branch offices, determine x - 1 priority central nodes other than the highest priority for some branch offices.

[0021] Through the bandwidth utilization rate of the highest priority central node, it is possible to accurately and conveniently determine whether a central node is overloaded. Thus, when it is determined that a certain central node is overloaded, a new central node can be quickly added. Moreover, reselecting central nodes of each priority for the branch offices that exceed the load can maximize the load balancing of the data center.

[0022] In other embodiments provided by the present application, the method further includes: if the bandwidth utilization rate of a central node as x priority central nodes does not exceed the preset utilization rate, delete the central node with the bandwidth utilization rate not exceeding the preset utilization rate from the data center; determine the target branch offices corresponding to the deleted central node; according to the bandwidth utilization rates of the central nodes other than the deleted central node among multiple central nodes as x priority central nodes for the branch offices other than the target branch offices, determine x priority central nodes for the target branch offices.

[0023] Through the bandwidth utilization rates of all priority central nodes, it is possible to quickly determine relatively idle central nodes, realizing the efficient contraction of data center nodes. Moreover, reselecting central nodes for the branch offices originally corresponding to the contracted central nodes based on the bandwidth utilization rates of each priority can maximize the load balancing of the data center.

[0024] The second aspect of the present application provides a configuration device for a central node. The device is applied to a data center, which includes M central nodes. The data center corresponds to N branch offices. Each branch office corresponds to x priority central nodes among the M central nodes. Bandwidth is configured for each central node and each branch office. The device includes: an acquisition module, configured to, in response to the addition of a new branch office, acquire the sum of the bandwidths of the branch offices corresponding to each central node when each central node serves as one of the x priority central nodes; a determination module, configured to determine the bandwidth utilization rate of each central node according to the sum of the bandwidths of each central node and the bandwidth of each central node; a configuration module, configured to determine x priority central nodes corresponding to the new branch office from the M central nodes based on the bandwidth utilization rate of each central node.

[0025] The third aspect of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the method in the first aspect.

[0026] The fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the first aspect are implemented.

[0027] The fifth aspect of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method in the first aspect are implemented.

[0028] The configuration device for a central node provided in the second aspect of the present application, the computer device provided in the third aspect, the computer-readable storage medium provided in the fourth aspect, and the computer program product provided in the fifth aspect have the same or similar beneficial effects as the method for configuring a central node provided in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features, and advantages of the exemplary embodiments of the present application will become easily understandable. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner. The same or corresponding reference numerals represent the same or corresponding parts, where:

[0030] Figure 1 is a schematic diagram of the application scenario of the method for configuring a central node in an embodiment of the present application;

[0031] Figure 2 is a schematic flowchart of the method for configuring a central node in an embodiment of the present application Figure 1 ;

[0032] Figure 3 is a schematic diagram of the corresponding relationship between each central node and each branch office in the data center in an embodiment of the present application;

[0033] Figure 4 Schematic flowchart of the configuration method for the central node in the embodiment of the present application Figure 2 ;

[0034] Figure 5 Schematic structure of the configuration device for the central node in the embodiment of the present application Figure 1 ;

[0035] Figure 6 Schematic structure of the configuration device for the central node in the embodiment of the present application Figure 2 ;

[0036] Figure 7 Schematic structural diagram of the computer device in the embodiment of the present application. Detailed implementation manners

[0037] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be completely conveyed to those skilled in the art.

[0038] It should be noted that unless otherwise specified, the technical terms or scientific terms used in the present application should have the ordinary meanings understood by those skilled in the art to which the present application belongs.

[0039] Currently, when it is necessary to specify central nodes with various priorities among multiple central nodes in the data center for a new branch, it is mainly specified manually. However, the efficiency of manual specification is low, and moreover, it is impossible for humans to obtain the traffic status of each central node in real time, which is likely to lead to incorrect specification and unable to achieve the maximum load balancing of the data center.

[0040] In view of this, the embodiments of the present application provide a configuration method for a central node, a configuration device for a central node, a computer device, a computer-readable storage medium, and a computer program product. By calculating the bandwidth utilization rate when each central node serves as the central node with various priorities for each branch, central nodes with various priorities are specified for the newly added branch. Since the bandwidth has been pre-configured before the central node and the branch are put into use and is relatively fixed, and the bandwidth utilization rate calculation considers the central node as the central node with various priorities, it can cover the situation where the current link between each branch and the corresponding central node fails and switches to the next central node, and can determine a central node with more abundant resources for the new branch, maximizing the load balancing of the data center and improving the processing efficiency of the data center.

[0041] It should be noted here that all components, data, and related processing methods involved in this application are authorized by users or fully authorized by all parties, and the collection, use, and processing of relevant data comply with relevant laws, regulations, and standards of relevant countries and regions.

[0042] First, the application scenario of the configuration method for the central node provided in the embodiments of this application will be described.

[0043] Figure 1 For the application scenario schematic diagram of the configuration method for the central node in the embodiments of this application, see Figure 1 As shown, this scenario may include: a data center.

[0044] The data center includes M central nodes. The data center corresponds to N branch offices. Each branch office corresponds to x priority central nodes among the M central nodes. Each central node and each branch office are configured with bandwidth.

[0045] In practical applications, the values of M and N can be determined according to specific circumstances. x can be any integer greater than or equal to 2. For example: x = 3. This means that each branch office corresponds to 3 priority central nodes among the M central nodes, namely high-priority central nodes, medium-priority central nodes, and low-priority central nodes. For example: The high-priority central node corresponding to branch office 1 is central node 1, the medium-priority central node corresponding to it is central node 2, and the low-priority central node corresponding to it is central node 3. In this way, branch office 1 normally communicates with central node 1. When the link between branch office 1 and central node 1 is abnormal, branch office 1 communicates with central node 2. When the link between branch office 1 and central node 2 is abnormal, branch office 1 communicates with central node 3 again. The relationship between other branch offices and central nodes is similar and will not be elaborated here.

[0046] Each branch office is involved in different business contents. The branch office sends a business request to the central node so that the central node processes the business request to generate a business response, and then sends the business response back to the branch office to implement the corresponding business of the branch office. The specific content of the business is not limited here.

[0047] For each central node in the data center, bandwidth is configured, that is, the maximum traffic that the central node is allowed to process per unit time. If the traffic received by the central node in real time exceeds the preset bandwidth, the received traffic either queues up for processing or is discarded.

[0048] For the branch office, bandwidth is also pre-configured, that is, the maximum traffic that the branch office is allowed to send and receive per unit time. The branch office sends and receives traffic in real time according to the preset bandwidth.

[0049] Generally speaking, multiple priority central nodes may be designated for a branch, and the same central node may also be designated for different branches, that is, one central node corresponds to multiple branches. Therefore, the bandwidth configured for the central node is generally greater than the bandwidth set for the branch. For example: the bandwidth of the central node is 100 Gbps, and the bandwidth of the branch is 1 Gbps. Moreover, the bandwidths configured between different central nodes can be the same or different. The bandwidths configured between different branches can be the same or different. All of these need to be determined according to the actual situation.

[0050] The configuration method of the central node provided by the embodiments of the present application will be described in detail below.

[0051] Figure 2 The flowchart of the configuration method of the central node in the embodiments of the present application Figure 1 is shown in Figure 2 and may include:

[0052] S21: In response to the addition of a new branch, obtain the sum of the bandwidths of the branches corresponding to each central node when it is the x - priority central node.

[0053] The addition of a new branch here may mean that a branch corresponding to a new service needs to be connected to the data center, or it may mean that an existing branch is disconnected from the original central node and needs to be re - connected to a new central node.

[0054] In either of the above cases, the data center will receive an addition signal. After receiving the addition signal, in response to the addition signal, the data center performs relevant bandwidth calculations on each existing central node in the data center to determine each priority central node for the new branch.

[0055] For each central node, it is necessary to first determine the bandwidths of the branches corresponding to the central node when it is the various priority central nodes corresponding to the existing branches, and then calculate the sum of these bandwidths.

[0056] Figure 3 The schematic diagram of the corresponding relationship between each central node and each branch in the data center in the embodiments of the present application is shown in Figure 3As shown, assume that the data center includes central node 1, central node 2, central node 3, and central node 4. Central node 1 is the high-priority central node corresponding to branch 1, central node 2 is the medium-priority central node corresponding to branch 1, and central node 3 is the low-priority central node corresponding to branch 1. Central node 2 is the high-priority central node corresponding to branch 2, central node 3 is the medium-priority central node corresponding to branch 2, and central node 4 is the low-priority central node corresponding to branch 2. The bandwidths of central node 1, central node 2, central node 3, and central node 4 are all 100 Gbps, and the bandwidths of branch 1 and branch 2 are both 10 Gbps.

[0057] For central node 1, as the high-priority node of branch 1, the sum of the bandwidths is 10 Gbps.

[0058] For central node 2, as the medium-priority node of branch 1 and the high-priority node of branch 2, the sum of the bandwidths is 20 Gbps.

[0059] For central node 3, as the low-priority node of branch 1 and the medium-priority node of branch 2, the sum of the bandwidths is 20 Gbps.

[0060] For central node 4, as the low-priority node of branch 2, the sum of the bandwidths is 10 Gbps.

[0061] S22: Determine the bandwidth utilization rate of each central node according to the sum of the bandwidths of each central node and the bandwidth of each central node.

[0062] Each central node has a total bandwidth, and the connected branches will occupy the total bandwidth according to the preset bandwidth. Each central node may correspond to multiple branches (regardless of which type of priority central node the branch regards the central node as). Therefore, a part of the bandwidth in each central node will be occupied by the corresponding branches. Coupled with the fact that the bandwidths corresponding to each central node may be different, the operating state of the central node can be determined through the bandwidth utilization rate.

[0063] Still referring to Figure 3 As shown, the preset bandwidths of central node 1, central node 2, central node 3, and central node 4 are all 100 Gbps.

[0064] For central node 1, the sum of the bandwidths as the high-priority node of branch 1 is 10 Gbps, and the bandwidth utilization rate is 10%.

[0065] For central node 2, the sum of the bandwidths as the medium-priority node of branch 1 and the high-priority node of branch 2 is 20 Gbps, and the bandwidth utilization rate is 20%.

[0066] For the central node 3, the sum of the bandwidths as a low-priority node of the branch 1 and a medium-priority node of the branch 2 is 20 Gbps, and the bandwidth utilization rate is 20%.

[0067] For the central node 4, the sum of the bandwidths as a low-priority node of the branch 2 is 10 Gbps, and the bandwidth utilization rate is 10%.

[0068] S23: Determine x priority central nodes corresponding to the new branch from the M central nodes based on the bandwidth utilization rate of each central node.

[0069] The bandwidth utilization rate corresponding to each central node as the priority central node has been calculated. The lower the bandwidth utilization rate, the more idle the operating state of the central node. Therefore, based on the ascending order of the bandwidth utilization rates corresponding to each central node, select the top x central nodes as the priority nodes corresponding from high to low for the new branch.

[0070] Still referring to Figure 3 As shown, the bandwidth utilization rate of the central node 1 is 10%, the bandwidth utilization rate of the central node 2 is 20%, the bandwidth utilization rate of the central node 3 is 20%, and the bandwidth utilization rate of the central node 4 is 10%.

[0071] Sorted in ascending order of the bandwidth utilization rate, they are: central node 1, central node 4 (tied with central node 1), central node 2, central node 3 (tied with central node 2). At this time, it is necessary to select three priority central nodes of high, medium, and low for the new branch. Furthermore, the central node 1 and the central node 4 can be used as the high-priority central node and the medium-priority central node of the new branch respectively, and either the central node 2 or the central node 3 can be used as the low-priority central node of the new branch.

[0072] As can be seen from the above content, the configuration method of the central node provided in the embodiment of the present application, when it is necessary to specify central nodes of various priorities for a new branch among multiple central nodes, calculates the bandwidth utilization rate of each central node as all priority central nodes of other branches, and then selects several central nodes with higher bandwidth utilization rate in turn as the priority central nodes of the new branch. In this way, there is no need to manually specify the priority central nodes. In addition, the bandwidth corresponding to each branch is fixed. Even if the traffic of the branch changes in real time, it will not exceed the preset bandwidth limit. Therefore, the maximum traffic situation of the central node can be obtained through the bandwidth utilization rate of the central node when it is used as the central node of each priority. Even if multiple branches switch central nodes due to link failures, the worst situation can be taken into account, and the central nodes of various priorities with relatively ample bandwidth can be selected for the new branch, so as to fully realize load balancing and improve the processing efficiency of the data center.

[0073] Furthermore, as a Figure 2 As a refinement and extension of the method shown, an embodiment of the present application also provides a method for configuring a central node.

[0074] Figure 4 The following is a flow chart of the configuration method of the central node in the embodiment of the present application. Figure 2 , see Figure 4 As shown, the method may include:

[0075] S41: In response to the addition of a new branch, the sum of the bandwidths of the branches corresponding to each central node when the central node is used as an x-priority central node is obtained.

[0076] When it is necessary to specify central nodes of different priorities for new branches, for each central node in the data center, it is necessary to obtain not only the sum of the bandwidths of the branches corresponding to it when it is a central node of x priorities, but also the sum of the bandwidths of the branches corresponding to it when it is a central node of x-1 priorities (excluding the lowest priority among the x priorities), and the sum of the bandwidths of the branches corresponding to it when it is a central node of x-2 priorities (excluding the lowest and second lowest priorities among the x priorities), and so on, and finally the sum of the bandwidths of the branches corresponding to it when it is a central node of 1 priority (the highest priority among the x priorities). In this way, each central node corresponds to a sum of x bandwidths.

[0077] The x bandwidths corresponding to the central node are obtained in descending order according to the priorities, so as to provide a further selection method when the bandwidth parameters of the central node as the x-priority central node do not meet or cannot be selected.

[0078] Still see Figure 3As shown, for a clearer display, Table 1 below shows the sum of the bandwidths of the branches corresponding to each central node when it is the central node of each priority level.

[0079] Table 1

[0080]

[0081] S42: Determine the bandwidth utilization rate of each central node according to the sum of the bandwidths of each central node and the bandwidth of each central node.

[0082] Each central node corresponds to x sums of bandwidths. Correspondingly, through the bandwidth of this central node, x bandwidth utilization rates are calculated.

[0083] When specifically calculating the bandwidth utilization rate, for each sum of bandwidths of each central node, the bandwidth of the central node can be subtracted from the sum of the bandwidths first to obtain the remaining bandwidth, and then the remaining bandwidth can be divided by the bandwidth of the central node to obtain the bandwidth utilization rate.

[0084] Still referring to Figure 3 As shown, based on the above Table 1, continue the calculation to obtain Table 2. Table 2 shows the bandwidth utilization rates of each central node when it is the corresponding central node of each priority level.

[0085] Table 2

[0086]

[0087] S43: Determine x priority central nodes corresponding to the new branch from the M central nodes based on the bandwidth utilization rate of each central node.

[0088] If the bandwidth utilization rate is relatively high, it means that in the worst case, that is, when the branches that are the central nodes of each priority level all switch to this central node, if this central node is selected as the priority central node of the new branch, it will increase the burden on this central node, and it may also cause the business of the new branch to be unable to be efficiently executed due to insufficient bandwidth. Therefore, it is necessary to exclude the bandwidth utilization rates of some central nodes with high bandwidth utilization rates that are the bandwidth utilization rates of x priority central nodes, and the bandwidth utilization rates of central nodes with low bandwidth utilization rates that are the bandwidth utilization rates of less than x priority central nodes can be considered.

[0089] Specifically, the above step S43 may include:

[0090] Step A1: When the bandwidth utilization rate does not exceed the preset threshold, determine x priority central nodes corresponding to the new branch from the M central nodes in the order of x, x - 1,..., 1.

[0091] The preset threshold here can be set according to actual needs and is not specifically limited here.

[0092] That is to say, on the basis of obtaining the respective bandwidth utilization rates corresponding to each central node as the priority central node including different levels, first exclude the central nodes corresponding to the bandwidth utilization rates lower than the preset threshold among the respective bandwidth utilization rates when each central node is the central node including all priorities, and then select the respective priority central nodes from the remaining central nodes.

[0093] For a clearer display, Table 3 below shows the bandwidth utilization rates corresponding to each central node.

[0094] Table 3

[0095]

[0096]

[0097] Assume that the preset threshold is 80%. The bandwidth utilization rate of central node 1 as the high, medium, and low priority central nodes is 90%, exceeding the preset threshold of 80%. Therefore, select the respective priority central nodes for the new branch among central nodes 2, 3, and 4.

[0098] If the bandwidth utilization rates of each central node as the high, medium, and low priority central nodes mostly exceed the preset threshold, and the remaining central nodes are not enough to meet the selection of the respective priority central nodes for the new branch, the central nodes corresponding to the bandwidth utilization rates that do not exceed the preset threshold can be selected from the bandwidth utilization rates when the remaining central nodes are the high and medium priority central nodes. If there are still not enough to select, continue to reduce the priority, that is, select the central nodes corresponding to the bandwidth utilization rates that do not exceed the preset threshold from the bandwidth utilization rates when the remaining central nodes are the high priority central nodes.

[0099] Continue to refer to Table 3. Assume that the preset threshold is 50%. The bandwidth utilization rates of central nodes 1, 2, 3, and 4 as the high, medium, and low priority central nodes all exceed the preset threshold. Then check whether the bandwidth utilization rates of central nodes 1, 2, 3, and 4 as the high and medium priority central nodes exceed the preset threshold. Central node 4 does not exceed, and central node 4 can be determined as the high priority central node of the new branch. At this time, the medium and low priority central nodes are still missing. Then check whether the bandwidth utilization rates of central nodes 1, 2, and 3 as the high priority central node exceed the preset threshold. Central nodes 2 and 3 do not exceed, and central nodes 2 and 3 can be determined as the medium and low priority central nodes of the new branch.

[0100] In some cases, in the selection of the bandwidth utilization rates corresponding to certain priority central nodes, these bandwidth utilization rates do not exceed the preset threshold and may even be the same. At this time, selection can be made based on the remaining bandwidth.

[0101] Specifically, the above step A1 may include:

[0102] Step A11: In the case of x, x - 1, …, or 1, determine x priority central nodes corresponding to the new branch based on the remaining bandwidth of the central node.

[0103] Among the bandwidth utilization rates of the central nodes corresponding to the x priority central nodes, if the number of bandwidth utilization rates exceeding the preset threshold exceeds the number of each priority central node selected for the new branch, further selection is required, and the selection criterion is the remaining bandwidth.

[0104] Alternatively, among the bandwidth utilization rates of the central nodes corresponding to the x priority central nodes, if the number of bandwidth utilization rates exceeding the preset threshold is insufficient to provide the number of each priority central node selected for the new branch, selection needs to be made among the bandwidth utilization rates of the central nodes corresponding to x - 1 priority central nodes. And among the bandwidth utilization rates of the central nodes corresponding to x - 1 priority central nodes, if the number of bandwidth utilization rates exceeding the preset threshold exceeds the remaining number of each priority central node selected for the new branch, further selection is also required, and the selection criterion is also the remaining bandwidth.

[0105] Select the central nodes in the above - mentioned manner until the selection of the central nodes is completed.

[0106] For a clearer display, Table 4 below shows the bandwidth utilization rate and the remaining bandwidth corresponding to each central node.

[0107] Table 4

[0108]

[0109] Assume that the preset threshold is 95%. The bandwidths corresponding to central nodes 1, 2, 3, and 4 as high, medium, and low - priority central nodes do not exceed the preset threshold. The remaining bandwidths corresponding to central nodes 1, 2, 3, and 4 as high, medium, and low - priority central nodes can be sorted from high to low, and select the central nodes 3, 2, and 4 with higher rankings as the high, medium, and low - priority central nodes corresponding to the new branch.

[0110] In some cases, the remaining bandwidths corresponding to each central node as high, medium, and low - priority central nodes are also substantially the same, and the selection of the priority central nodes can be based on the remaining bandwidths corresponding to each central node as high, medium, and priority central nodes.

[0111] Specifically, the above step A11 may include:

[0112] Step A111: Determine x priority central nodes corresponding to the new branch from the M central nodes in the order of x, x - 1, ……, 1, based on the remaining bandwidth of the central nodes.

[0113] Still taking Table 4 as an example, assume that high - priority and medium - priority central nodes need to be selected for the new branch, the preset threshold is 85%. Select central node 3 as the high - priority central node for the new branch from the bandwidth utilization rates corresponding to central nodes 1, 2, 3, and 4 when they are high, medium, and low - priority central nodes. The bandwidth utilization rates and remaining bandwidths of central nodes 2 and 4 are the same. At this time, it is necessary to select central node 4 as the medium - priority central node for the new branch from the remaining bandwidths when central nodes 2 and 4 are high - and medium - priority central nodes.

[0114] In some cases, until all the priority central nodes of the new branch cannot be selected based on the remaining bandwidth of each central node as a high - priority central node. At this time, selection can be made according to the ID of each central node.

[0115] The ID here can refer to the ID configured by the data center for the central node, or it can refer to the ID specifically configured for the central node when selecting the priority central node, such as: 1, 2, 3, 4, etc.

[0116] Specifically, the above - mentioned step A111 may include:

[0117] Step A1111: Determine y central nodes from the M central nodes in the order of x, x - 1, ……, 1, based on the remaining bandwidth of the central nodes.

[0118] Step A1112: If y is greater than x, determine x priority central nodes corresponding to the new branch from the y central nodes according to the ID of each central node.

[0119] That is to say, first select the corresponding priority central nodes in the order of decreasing priority from low - priority according to the bandwidth utilization rate not exceeding the preset threshold, and then select the corresponding priority central nodes in the order of decreasing priority from low - priority according to the remaining bandwidth. If the number of all selected priority central nodes at this time is greater than the actual required number (the remaining bandwidths corresponding to the last several selected central nodes are the same), selection needs to be made according to the central node ID.

[0120] When sorting y central nodes according to their IDs, ascending order or descending order can be used. When sorting in ascending order, the finally selected central nodes are generally those that joined the data center earlier. When sorting in descending order, the finally selected central nodes are generally those that joined the data center later. Which central nodes in the sorting to specifically select can be determined according to actual requirements.

[0121] The above is a method for determining each priority central node from multiple central nodes. In addition, tuples of each central node can be generated first, that is, data groups characterized by various relevant parameters, and then based on the sorting of the data groups, corresponding multiple central nodes are selected as each priority central node.

[0122] Specifically, step S43 above may include:

[0123] S431: Generate a data group for each central node.

[0124] Among them, the data group includes the threshold state, the remaining bandwidth corresponding to x priority central nodes, the remaining bandwidth corresponding to x - 1 priority central nodes,..., the remaining bandwidth corresponding to 1 priority central node, and the ID.

[0125] Moreover, when the bandwidth utilization rate corresponding to x priorities does not exceed the preset threshold, the threshold state is x + 1. When the bandwidth utilization rate corresponding to x priorities exceeds the preset threshold, but the bandwidth utilization rate corresponding to x - 1 priorities does not exceed the preset threshold, the threshold state is x,..., when the bandwidth utilization rate corresponding to 2 priorities exceeds the preset threshold, but the bandwidth utilization rate corresponding to 1 priority does not exceed the preset threshold, the threshold state is 1.

[0126] Taking the determination of high-priority central nodes, medium-priority central nodes, and low-priority central nodes for a new branch as an example, assume that the data center includes central nodes a1, a2, ……, corresponding to branches b1, b2, ……. The bandwidth of each central node is 100 Gbps, and the bandwidth of each branch is 10 Gbps. The remaining bandwidth of central node a1 when it is a high-, medium-, and low-priority central node is c1 (bandwidth utilization rate is c1 / 00 * 100%), the remaining bandwidth when it is a high- and medium-priority central node is d1 (bandwidth utilization rate is d1 / 00 * 100%), and the remaining bandwidth when it is a high-priority central node is e1 (bandwidth utilization rate is e1 / 00 * 100%). If c1 / 00 * 100% is less than the preset threshold, then the data group of central node a1 is (4, c1, d1, e1, a1). If c1 / 00 * 100% is greater than the preset threshold and d1 / 00 * 100% is less than the preset threshold, then the data group of central node a1 is (3, c1, d1, e1, a1). If c1 / 00 * 100% and d1 / 00 * 100% are greater than the preset threshold and e1 / 00 * 100% is less than the preset threshold, then the data group of central node a1 is (2, c1, d1, e1, a1). If c1 / 00 * 100%, d1 / 00 * 100%, and e1 / 00 * 100% are all greater than the preset threshold, then the data group of central node a1 is (1, c1, d1, e1, a1).

[0127] The calculation methods of the data groups of central nodes a2, …… are the same as that of central node a1, and will not be elaborated here.

[0128] At this time, the data groups of each central node are obtained, that is, (threshold state, remaining bandwidth corresponding to high, medium, and low priorities, remaining bandwidth corresponding to high and medium priorities, remaining bandwidth corresponding to high priority, ID)

[0129] S432: Sort each central node in descending order according to the sequence of each parameter in the data group.

[0130] Each central node corresponds to a data group. When sorting each central node, sort each central node in order from largest to smallest according to the threshold state in the data group. For the same threshold state, then sort in descending order according to the remaining bandwidth of the high, medium, and low-priority central nodes. For the same remaining bandwidth of the high, medium, and low-priority central nodes, then sort in descending order according to the remaining bandwidth of the high and medium-priority central nodes. For the same remaining bandwidth of the high and medium-priority central nodes, then sort in descending order according to the remaining bandwidth of the high-priority central nodes. For the same remaining bandwidth of the high-priority central nodes, then sort in descending order according to the ID.

[0131] In this way, the sorting of each central node is obtained.

[0132] S433: Sequentially determine the top x central nodes as the x priority central nodes of the new branch.

[0133] Depending on how many corresponding priority central nodes need to be selected for the new branch, obtain that many central nodes starting from the beginning of the sorting, and use the obtained central nodes as the corresponding priority central nodes. In the above example, the top three sorted central nodes are used as the high-priority central node, medium-priority central node, and low-priority central node of the new branch respectively.

[0134] As more and more new branches are connected to the data center, the processing volume of each central node in the data center will gradually tend to saturation. To avoid slow processing efficiency due to overloaded central nodes, each central node can be detected regularly.

[0135] S441: If the bandwidth utilization rate of a central node as the highest-priority central node exceeds the preset threshold, add a new central node.

[0136] That is to say, every once in a while, obtain the sum of the bandwidths of the branches corresponding to each central node as the highest-priority central node, and then divide the calculated sum by the total bandwidth of the corresponding central node to obtain the bandwidth utilization rate of each central node as the highest-priority central node.

[0137] Next, compare each bandwidth utilization rate with the preset threshold. If it exceeds the preset threshold, it means that the corresponding central node is currently brought by the connected branches. At this time, a new central node needs to be added. If none of the bandwidth utilization rates exceed the preset threshold, it means that each central node can provide sufficient bandwidth to process the data of each branch, and there is no need to add a new central node at this time.

[0138] S442: Determine the new central node as the highest-priority central node of some branches corresponding to the central node whose bandwidth utilization rate exceeds the preset threshold.

[0139] For the central node whose bandwidth utilization rate exceeds the preset threshold, remove the branches corresponding to the bandwidth utilization rate that exceeds the preset threshold, and use the new central node as the high-priority central node of this branch.

[0140] For example, assume that the preset threshold is 80%, the bandwidth of central node a is 100 Gbps, and it serves as the high-priority central node for branch offices b1 (bandwidth 30 Gbps), b2 (bandwidth 30 Gbps), and b3 (bandwidth 30 Gbps). The bandwidth utilization rate of central node a is 90%, exceeding the preset threshold. At this time, any one of branch offices b1, b2, and b3 can be disconnected from central node a and then reconnected to a new central node, and the new central node is used as the high-priority central node corresponding to the disconnected branch office.

[0141] Which one or which several branch structures to specifically select from the central nodes exceeding the preset threshold can be selected according to the priorities, bandwidths, etc. of the branch offices. Specifically selecting branch offices with low priorities and high bandwidths can minimize the impact on the branch offices when the central node switches.

[0142] S443: Determine x - 1 priority central nodes other than the highest priority for some branch offices based on the bandwidth utilization rates of multiple central nodes when they serve as the x priority central nodes for some branch offices.

[0143] While some branch offices are disconnected from the original high-priority central node, they are also disconnected from the original medium-priority central node and low-priority central node, so as to re-determine the medium-priority central node and low-priority central node among the central nodes in the data center except the new central node.

[0144] The reason for re-selecting the medium-priority central node and low-priority central node for some branch offices is that after some branch offices are disconnected from the original high-priority central node, the sorting of the bandwidth utilization rate, etc. of the original high-priority central node in the data center may change. Re-determining the medium-priority central node and low-priority central node for some branch offices can provide the optimal bandwidth environment for some branch offices in the standby state to the greatest extent.

[0145] Taking the new central node as the high-priority central node for some branch offices, calculate the bandwidth utilization rate of each central node in the data center except the new central node (when calculating, some branch offices are not considered), and then based on the bandwidth utilization rate of each central node, determine the medium- and low-priority central nodes for some branch offices. The specific methods for calculating the bandwidth utilization rate and selecting the priority central nodes have been described in detail in the aforementioned steps S41 - S43, and will not be elaborated here. So far, the dynamic update of each central node in the data center and the dynamic update of the high-, medium-, and low-priority central nodes of the branch offices have been completed, ensuring the maximization of the bandwidth utilization of each branch office regardless of whether it is connected to the main or standby central node to the greatest extent.

[0146] Although the data center will connect to new branch offices, in some cases, there will also be some branch offices that need to disconnect from the data center for various reasons. In this way, some central nodes in the data center may be relatively idle. At this time, these relatively idle central nodes can be deleted to improve the utilization rate of each central node in the data center.

[0147] S451: If the bandwidth utilization rate of a central node when it is an x-priority central node does not exceed the preset utilization rate, then delete the central node whose bandwidth utilization rate does not exceed the preset utilization rate from the data center.

[0148] That is to say, every once in a while, obtain the sum of the bandwidths of the branch offices corresponding to each central node when it is a high-priority central node, and then divide the calculated sum by the total bandwidth of the corresponding central node to obtain the bandwidth utilization rate of each central node when it is a high-priority central node.

[0149] Next, compare each bandwidth utilization rate with the preset utilization rate. If each bandwidth utilization rate exceeds the preset utilization rate, it means that the load of the branch offices currently borne by each central node is acceptable and there is no need to reduce the central nodes. If there is a bandwidth utilization rate that does not exceed the preset threshold, it means that the corresponding central node currently connects to fewer branch offices, and this central node can be removed from the data center. For the branch offices originally connected to this central node, it is necessary to re-determine the x-priority central nodes in the data center.

[0150] S452: Determine the target branch offices corresponding to the deleted central node.

[0151] For the deleted central node, it may have been a high-priority central node, or a medium-priority central node, or a low-priority central node of some branch offices before. All branch offices involved in the deleted central node are determined as target branch offices.

[0152] S453: Determine the x-priority central nodes for the target branch offices according to the bandwidth utilization rates of the central nodes other than the deleted central node among multiple central nodes when they are the x-priority central nodes of the branch offices other than the target branch offices.

[0153] For the target branch, the deleted central node is only one of its priority central nodes, and the corresponding other priority central nodes still exist in the data center. Due to the deletion of some central nodes, the corresponding branch needs to connect to other central nodes, which will cause the sorting of each central node in the data center to change in parameters such as bandwidth utilization. In order to select the optimal priority central nodes for the target branch to the greatest extent, the connection with the target branch can be disconnected among the remaining central nodes in the data center, so as to re-determine each priority central node for the target branch among the remaining central nodes in the data center.

[0154] The specific methods for calculating the bandwidth utilization and selecting the priority central nodes have been described in detail in the foregoing steps S41 - S43, and will not be elaborated here. So far, the dynamic update of each central node in the data center and the dynamic update of the high, medium, and low priority central nodes of the branch have been completed, maximizing the bandwidth utilization of the main and backup connections between each branch and the central node.

[0155] So far, the configuration method of the central node provided by the embodiment of the present application has been fully described.

[0156] Based on the same inventive concept, the embodiment of the present application also provides a configuration device for a central node.

[0157] The configuration device of the central node is applied to the data center. The data center includes M central nodes, and the data center corresponds to N branches. Each branch corresponds to x priority central nodes among the M central nodes, and each central node and each branch are configured with bandwidth.

[0158] Figure 5 For the structural schematic of the configuration device of the central node in the embodiment of the present application Figure 1 , see Figure 5 As shown, the device may include: an acquisition module 51, a determination module 52, and a configuration module 53.

[0159] The acquisition module 51 is configured to, in response to the addition of a new branch, acquire the sum of the bandwidths of the branches corresponding to each central node when each central node is used as x priority central nodes.

[0160] The determination module 52 is configured to determine the bandwidth utilization rate of each central node according to the sum of the bandwidths of each central node and the bandwidth of each central node.

[0161] The configuration module 53 is configured to determine x priority central nodes corresponding to the new branch from the M central nodes based on the bandwidth utilization rate of each central node.

[0162] Further, asFigure 5 For the refinement and expansion of the device shown, an embodiment of the present application further provides a configuration device for a central node.

[0163] Figure 6 It is a schematic structure of the configuration device for the central node in the embodiment of the present application Figure 2 , see Figure 6 As shown, the device may include: an acquisition module 61, a determination module 62, a configuration module 63, and an update module 64.

[0164] The acquisition module 61 is configured to, in response to the addition of a new branch, acquire the sum of the bandwidths of the branches corresponding to each central node when each central node is an x - priority central node.

[0165] The determination module 62 is configured to determine the bandwidth utilization rate of each central node according to the sum of the bandwidths of each central node and the bandwidth of each central node.

[0166] The configuration module 63 is configured to determine x priority central nodes corresponding to the new branch from M central nodes based on the bandwidth utilization rate of each central node.

[0167] The bandwidth utilization rate of each central node further includes the bandwidth utilization rates as x - 1, ……, 1 priority central nodes, and the priorities decrease from low to high; in the case of based on the bandwidth utilization rate of each central node, the configuration module 63 is specifically configured to, when the bandwidth utilization rate does not exceed the preset threshold, determine x priority central nodes corresponding to the new branch from M central nodes in the order of x, x - 1, ……, 1.

[0168] The configuration module 63 is specifically configured to, in the case of x, x - 1, ……, or 1, determine x priority central nodes corresponding to the new branch from M central nodes based on the remaining bandwidth of the central node.

[0169] The configuration module 63 is specifically configured to determine x priority central nodes corresponding to the new branch from M central nodes in the order of x, x - 1, ……, 1 based on the remaining bandwidth of the central node.

[0170] The configuration module 63 is specifically configured to determine y central nodes from M central nodes in the order of x, x - 1, ……, 1 based on the remaining bandwidth of the central node; if y is greater than x, then determine x priority central nodes corresponding to the new branch from y central nodes according to the identification ID of each central node.

[0171] The bandwidth utilization rate of each central node also includes the bandwidth utilization rates of the central nodes with priorities from x - 1 to 1, where the priorities decrease from low to high. Based on the bandwidth utilization rate of each central node, the configuration module 63 is specifically used to generate a data group for each central node. The data group includes the threshold status, the remaining bandwidths corresponding to the x priority central nodes, the remaining bandwidths corresponding to the x - 1 priority central nodes, ……, the remaining bandwidth corresponding to the 1 priority central node, and the identification ID. Moreover, when the bandwidth utilization rates corresponding to the x priorities do not exceed the preset threshold, the threshold status is x + 1; when the bandwidth utilization rates corresponding to the x priorities exceed the preset threshold, but the bandwidth utilization rates corresponding to the x - 1 priorities do not exceed the preset threshold, the threshold status is x; ……; when the bandwidth utilization rates corresponding to the 2 priorities exceed the preset threshold, but the bandwidth utilization rate corresponding to the 1 priority does not exceed the preset threshold, the threshold status is 1. Sort each central node in descending order according to the sequence of the parameters in the data group. Determine the x priority central nodes of the new branch from the first x central nodes in the sorted order.

[0172] In the case of x = 3, the acquisition module 61 is specifically used to acquire the sum of the bandwidths of the branches corresponding to each central node when it is the high - priority central node, the medium - priority central node, and the low - priority central node.

[0173] The configuration module 63 is specifically used to determine the high - priority central node, the medium - priority central node, and the low - priority central node corresponding to the new branch from the M central nodes based on the bandwidth utilization rate of each central node.

[0174] The update module 64 is used to, if the bandwidth utilization rate of a central node when it is the highest - priority central node exceeds the preset threshold, add a new central node; determine the new central node as the highest - priority central node of some branches corresponding to the central node whose bandwidth utilization rate exceeds the preset threshold; and determine the x - 1 priority central nodes other than the highest - priority for some branches according to the bandwidth utilization rates of multiple central nodes when they are the x priority central nodes of some branches except some branches.

[0175] The update module 64 is also used to, if the bandwidth utilization rate of a central node when it is the x priority central node does not exceed the preset utilization rate, delete the central node from the data center; determine the target branches corresponding to the deleted central node; and determine the x priority central nodes for the target branches according to the bandwidth utilization rates of the central nodes other than the deleted central node in multiple central nodes when they are the x priority central nodes of some branches except the target branches.

[0176] It should be noted here that the description of the above device embodiments is similar to that of the above method embodiments and has similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0177] Based on the same inventive concept, an embodiment of the present application also provides a computer device.

[0178] Figure 7 For the structural schematic diagram of the computer device in the embodiments of the present application, see Figure 7 As shown, the computer device may include: a memory 71, a processor 72, and a computer program stored on the memory 71. The processor 72 executes the computer program to implement the method in the foregoing embodiments.

[0179] It should be noted here that the description of the above computer device embodiments is similar to that of the above method embodiments and has similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the computer device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0180] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method in the foregoing embodiments is implemented.

[0181] It should be noted here that the description of the above computer-readable storage medium embodiments is similar to that of the above method embodiments and has similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the computer-readable storage medium embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0182] Based on the same inventive concept, an embodiment of the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the method in the foregoing embodiments is implemented.

[0183] It should be noted here that the description of the above computer program product embodiments is similar to that of the above method embodiments and has similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the computer program product embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0184] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for configuring a central node, characterized in that: The method is applied to a data center, the data center includes M central nodes, the data center corresponds to N branches, each branch corresponds to x priority central nodes in the M central nodes, each central node and each branch is configured with bandwidth, and the method includes: In response to the addition of new branches, the sum of the bandwidths of the branches corresponding to each central node when it is used as x priority central nodes is obtained; Determine the bandwidth utilization of each central node according to the sum of the bandwidths of each central node and the bandwidth of each central node; Based on the bandwidth utilization of each central node, x priority central nodes corresponding to the new branch are determined from the M central nodes.

2. The method according to claim 1, characterized in that The bandwidth utilization rate of each central node also includes the bandwidth utilization rates of x-1, ..., 1 priority central nodes, with the priorities decreasing from low to high; the x priority central nodes corresponding to the new branch are determined from the M central nodes based on the bandwidth utilization rate of each central node, including: When the bandwidth utilization rate does not exceed a preset threshold, x priority central nodes corresponding to the new branch are determined from the M central nodes in the order of x, x-1, . . . , 1.

3. The method according to claim 2, characterized in that The step of determining x priority central nodes corresponding to the new branch from the M central nodes in the order of x, x-1, ..., 1 includes: In the case of x, x-1, . . . , or 1, based on the remaining bandwidth of the central node, x priority central nodes corresponding to the new branch are determined from the M central nodes.

4. The method according to claim 3, characterized in that The determining, based on the remaining bandwidth of the central node, x priority central nodes corresponding to the new branch from the M central nodes includes: In the order of x, x-1, . . . , 1, based on the remaining bandwidth of the central node, x priority central nodes corresponding to the new branch are determined from the M central nodes.

5. The method according to claim 4, characterized in that The step of determining x priority central nodes corresponding to the new branch from the M central nodes in the order of x, x-1, ..., 1 based on the remaining bandwidth of the central node comprises: Determine y central nodes from the M central nodes in the order of x, x-1, ..., 1 based on the remaining bandwidth of the central node; If y is greater than x, x priority central nodes corresponding to the new branch are determined from the y central nodes according to the identification ID of each central node.

6. The method according to claim 1, characterized in that The bandwidth utilization rate of each central node also includes the bandwidth utilization rates of x-1, ..., 1 priority central nodes, with the priorities decreasing from low to high; the x priority central nodes corresponding to the new branch are determined from the M central nodes based on the bandwidth utilization rate of each central node, including: Generate a data group for each central node, the data group including a threshold state, a remaining bandwidth corresponding to x priority central nodes, a remaining bandwidth corresponding to x-1 priority central nodes, ..., a remaining bandwidth corresponding to 1 priority central node and an identification ID, and when the bandwidth utilization corresponding to x priorities does not exceed a preset threshold, the threshold state is x+1, when the bandwidth utilization corresponding to x priorities exceeds the preset threshold but the bandwidth utilization corresponding to x-1 priorities does not exceed the preset threshold, the threshold state is x, ..., when the bandwidth utilization corresponding to 2 priorities exceeds the preset threshold but the bandwidth utilization corresponding to 1 priority does not exceed the preset threshold, the threshold state is 1; Sort each central node in descending order according to the order of the parameters in the data group; The x central nodes that are ranked first are determined in sequence as the x priority central nodes of the new branch.

7. The method according to any one of claims 1 to 5, characterized in that x=3; the step of obtaining the sum of the bandwidths of the branches corresponding to each central node as x priority central nodes includes: Obtain the sum of the bandwidths of the branches corresponding to each central node when it is a high-priority central node, a medium-priority central node, and a low-priority central node; The step of determining x priority central nodes corresponding to the new branch from the M central nodes based on the bandwidth utilization of each central node includes: Based on the bandwidth utilization of each central node, a high priority central node, a medium priority central node and a low priority central node corresponding to the new branch are determined from the M central nodes.

8. The method according to any one of claims 1 to 5, characterized in that The method further comprises: If the bandwidth utilization of a central node as the highest priority central node exceeds the preset threshold, a new central node is added; Determine the new central node as the highest priority central node of some branches corresponding to the central nodes whose bandwidth utilization exceeds a preset threshold; According to the bandwidth utilization rates of the multiple central nodes when serving as x priority central nodes excluding the part of the branches, x-1 priority central nodes excluding the highest priority are determined for the part of the branches.

9. The method according to any one of claims 1 to 5, characterized in that The method further comprises: If the bandwidth utilization rate of a central node as the x priority central node does not exceed the preset utilization rate, the central node whose bandwidth utilization rate does not exceed the preset utilization rate is deleted from the data center; Determine the target branch corresponding to the deleted central node; According to the bandwidth utilization rates of the central nodes among the plurality of central nodes except the deleted central node when serving as the x priority central nodes except the target branch, x priority central nodes are determined for the target branch.

10. A central node configuration device, characterized in that: The device is applied to a data center, the data center includes M central nodes, the data center corresponds to N branches, each branch corresponds to x priority central nodes in the M central nodes, each central node and each branch is configured with bandwidth, and the device includes: An acquisition module, used for acquiring the sum of the bandwidths of the branches corresponding to each central node as x priority central nodes in response to the addition of a new branch; A determination module, used to determine the bandwidth utilization of each central node according to the sum of the bandwidths of each central node and the bandwidth of each central node; A configuration module is used to determine x priority central nodes corresponding to the new branch from the M central nodes based on the bandwidth utilization of each central node.

11. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images