Resource dynamic adjustment method and device, electronic equipment and storage medium

By acquiring and analyzing network configuration items before and after virtual machine migration, predicting and selecting the optimal target computing node, the problem that the DRS solution does not consider network load, minimizing network load after virtual machine migration, and ensuring network stability .

CN118972390AActive Publication Date: 2024-11-15CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1

Patent Information

Application Number
CN202410989374.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-15
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

The existing dynamic resource scheduling (DRS) scheme does not consider the impact of virtual machine scheduling on the business from the network aspect, which may lead to increased network load of computing nodes after cloud host creation, resulting in problems such as network delay, packet loss and jitter.

Method used

By obtaining the configuration items of each computing node in the virtual network where the virtual machine to be migrated, predict the network load of each computing node after the migration, and determining the optimal target computing node based on the network load, in order to minimize the network load caused by virtual machine migration. The specific methods include obtaining the network element feature values ​​in the control plane and forwarding plane configuration items, using a logic programming engine for deductive reasoning, predicting network load, and selecting the target computing node with the minimum load for migration.

Benefits of technology

It effectively reduces the impact of virtual machine migration on network load, avoids network delay, packet loss and jitter problems, and ensures network stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118972390A_ABST
    Figure CN118972390A_ABST
Patent Text Reader

Abstract

The invention discloses a method for dynamically adjusting resources. The method comprises the following steps: acquiring configuration items of computing nodes in a virtual network where a to-be-migrated virtual machine is located; based on the configuration item, obtaining the value of each network element contained in the configuration item of a first computing node where the to-be-migrated virtual machine is currently located; and based on the respective value of each network element element, respectively predicting network loads of the virtual machine to be migrated to a plurality of second computing nodes in the virtual network, and according to the network loads of the second computing nodes, determining a final migrated target computing node of the virtual machine to be migrated. And respectively predicting network loads for migrating the virtual machine to be migrated to a plurality of second computing nodes through respective values of the network element elements, and selecting one of the plurality of second computing nodes as a target computing node for final migration of the virtual machine to be migrated according to the network loads of the second computing nodes. The target computing node serves as an optimal migration scheduling node of the virtual machine to be migrated, and the network load caused by migration of the virtual machine to be migrated is minimized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method and device for dynamic resource adjustment, an electronic device, and a storage medium. Background Art

[0002] Dynamic Resource Scheduler (DRS) dynamically balances system resource utilization based on system resource utilization. DRS dynamically migrates virtual machines on computing nodes with excessively high CPU utilization to computing nodes with relatively low CPU utilization based on the CPU utilization of the system computing nodes, thereby ensuring that virtual machines can run efficiently on computing nodes with low CPU utilization.

[0003] The DRS solution specifically includes: 1. Set up a host with DRS enabled, and the virtual machines on it will be dynamically migrated; 2. Set measurement rules: the host with DRS enabled exceeds the threshold for three consecutive (configurable) checks, triggering DRS optimization scheduling; 3. Selection of virtual machines to be migrated: select the virtual machine with the lowest resource utilization to migrate, and only migrate one virtual machine at a time; 4. Selection of the target host: select the host with the lowest resource utilization as the target host, and the resource utilization of the target host plus the resource utilization of the migrated virtual machine must not exceed the threshold, etc.

[0004] Although the above adjustment method can realize resource scheduling, when scheduling and allocating virtual machine instances, the DRS solution does not consider the impact of virtual machine scheduling on the business from the network perspective. It may cause the network load of the computing node to increase after the cloud host creation and scheduling is completed, resulting in network delays, packet loss, jitter, etc. for the cloud host or the entire computing node after the cloud host is created. Summary of the invention

[0005] The present disclosure provides a method, device, electronic device and storage medium for dynamic resource adjustment. The main purpose is to solve the problem that the DRS solution does not consider the impact of virtual machine scheduling on the business from the network aspect, which may increase the network load of the computing node after the cloud host is created and scheduled, resulting in network delay, packet loss, jitter and other problems of the cloud host or the entire computing node after the cloud host is created.

[0006] According to a first aspect of the present disclosure, a method for dynamic resource adjustment is provided, comprising:

[0007] Obtaining configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of a control plane configuration item and a forwarding plane configuration item;

[0008] Based on the configuration item, obtaining respective values ​​of each network element contained in the configuration item of the first computing node where the virtual machine to be migrated is currently located;

[0009] Based on the respective values ​​of the network elements, the network loads of the virtual machines to be migrated to the second computing nodes in the virtual network are predicted respectively, and the target computing node for the final migration of the virtual machines to be migrated is determined according to the network loads of the second computing nodes.

[0010] In some embodiments, the predicting, based on the respective values ​​of the respective network element components, the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated includes:

[0011] Based on the logic programming engine, deductive reasoning is used for the values ​​of each of the network elements to respectively predict the network load of the virtual machine to be migrated to each of the second computing nodes.

[0012] In some embodiments, obtaining the configuration items of each computing node in the virtual network where the virtual machine to be migrated is located includes:

[0013] Determine a control plane network element abstract data set and a forwarding plane network element abstract data set, wherein the control plane network element abstract data set and the forwarding plane network element abstract data set are obtained by modeling the control plane configuration items and the forwarding plane configuration items of the virtual network where the virtual machine to be migrated is located;

[0014] The obtaining, based on the configuration item, respective values ​​of each network element included in the configuration item of the virtual machine to be migrated includes:

[0015] A network snapshot of each computing node of the virtual network where the virtual machine to be migrated is located is collected, where the network snapshot is the value of each network element included in the control plane configuration item and / or the forwarding plane configuration item.

[0016] In some embodiments, the logic programming engine adopts a deductive reasoning method for the values ​​of each of the network elements to respectively predict the network load of the virtual machine to be migrated to each of the second computing nodes, including:

[0017] According to the preset conversion relationship between different network element elements and logical programming engine semantic values, the values ​​of the network element elements in the network snapshot are converted into corresponding logical programming engine semantic values;

[0018] The semantic values ​​of each of the logic programming engines are deductively reasoned to respectively predict the network load of migrating the virtual machine to be migrated to the plurality of the second computing nodes.

[0019] In some embodiments, the method of using deductive reasoning to predict the network load of migrating the virtual machine to be migrated to the plurality of second computing nodes includes:

[0020] Substituting each of the logical programming engine semantic values ​​into the forwarding plane network element abstract data set and the control plane network element abstract data set respectively;

[0021] Based on the forwarding plane network element abstract data set and the control plane network element abstract data set substituted into the logic programming engine semantic values, the network load function is inferred and solved to predict the network load of the virtual machine to be migrated to each of the second computing nodes.

[0022] In some embodiments, determining the target computing node for final migration of the to-be-migrated virtual machine according to the network load of each second computing node includes:

[0023] The second computing node corresponding to the minimum network load is used as the target computing node for final migration of the virtual machine to be migrated.

[0024] In some embodiments, the logic programming engine adopts a deductive reasoning method for the values ​​of each of the network elements to respectively predict the network load of the virtual machine to be migrated to each of the second computing nodes, including:

[0025] Based on the converted logical programming engine semantic value corresponding to the value of the network element in the network snapshot of a target computing node, the network load function is inferred and solved to obtain the network load of the virtual machine to be migrated to each of the second computing nodes.

[0026] In some embodiments, determining the target computing node for final migration of the to-be-migrated virtual machine according to the network load of each second computing node includes:

[0027] Reversely solving the global optimal solution of the network load function being greater than or equal to a preset network load threshold, and obtaining a logic programming engine semantic value corresponding to the optimal solution;

[0028] From the logic programming engine semantic values ​​corresponding to each computing node, a semantic value matching the logic programming engine semantic value corresponding to the optimal solution is selected, and a second computing node corresponding to the selected semantic value is used as the target computing node for final migration of the virtual machine to be migrated.

[0029] In some embodiments, determining a control plane network element abstract data set and a forwarding plane network element abstract data set includes:

[0030] In response to a migration instruction of a virtual machine to be migrated, obtaining a control plane configuration item and a forwarding plane configuration item of a virtual network where the virtual machine to be migrated is located;

[0031] Formal modeling is performed on the network element elements in the control plane configuration item and the forwarding plane configuration item respectively to obtain the control plane network element abstract data set and the forwarding plane network element abstract data set.

[0032] In some embodiments, after determining the target computing node to which the virtual machine to be migrated is finally migrated according to the network load of each second computing node, the method further includes:

[0033] Migrating the virtual machine to be migrated from the first computing node to the target computing node;

[0034] The overall network load is monitored through the network visualization system, and the migration ends when the network load is detected to be less than the preset disturbance threshold.

[0035] In some embodiments, monitoring the overall network load through a network visualization system and ending the migration after monitoring that the network load is less than a preset disturbance threshold includes:

[0036] Monitor the traffic of each computing node in the virtual network and analyze the network load usage of each computing node;

[0037] The network visualization system built based on Prometheus performs a global preview of the network load and the network snapshot;

[0038] Monitoring whether the network load is less than the preset disturbance threshold;

[0039] When it is determined that the network load is less than the preset disturbance threshold, the migration of the virtual machine to be migrated is completed.

[0040] According to a second aspect of the present disclosure, a device for dynamically adjusting resources is provided, including:

[0041] A first acquisition unit is used to acquire configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of a control plane configuration item and a forwarding plane configuration item;

[0042] A second acquisition unit, configured to acquire, based on the configuration item, respective values ​​of each network element contained in the configuration item of the first computing node where the virtual machine to be migrated is currently located;

[0043] A prediction unit, configured to respectively predict the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated based on the respective values ​​of each network element;

[0044] The determining unit is used to determine the target computing node to which the virtual machine to be migrated is finally migrated according to the network load of each second computing node.

[0045] In some embodiments, the prediction unit is further used to predict the network load of the virtual machine to be migrated to each of the second computing nodes by using deductive reasoning on the values ​​of each of the network elements based on a logic programming engine.

[0046] In some embodiments, the first acquisition unit is further used to determine a control plane network element abstract data set and a forwarding plane network element abstract data set, wherein the control plane network element abstract data set and the forwarding plane network element abstract data set are obtained by modeling the control plane configuration items and the forwarding plane configuration items of the virtual network where the virtual machine to be migrated is located;

[0047] The second acquisition unit is further used to collect network snapshots of each computing node of the virtual network where the virtual machine to be migrated is located, and the network snapshots are respective values ​​of each network element included in the control plane configuration item and / or the forwarding plane configuration item.

[0048] In some embodiments, the prediction unit includes:

[0049] A conversion module, used to convert the values ​​of the network element elements in the network snapshot into corresponding logic programming engine semantic values ​​according to the preset conversion relationship between different network element elements and logic programming engine semantic values;

[0050] The first prediction module is used to predict the network load of migrating the virtual machine to be migrated to multiple second computing nodes through deductive reasoning of the semantic values ​​of each of the logic programming engines.

[0051] In some embodiments, the first prediction module is further configured to:

[0052] Substituting each of the logical programming engine semantic values ​​into the forwarding plane network element abstract data set and the control plane network element abstract data set respectively;

[0053] Based on the forwarding plane network element abstract data set and the control plane network element abstract data set substituted into the logic programming engine semantic values, the network load function is inferred and solved to predict the network load of the virtual machine to be migrated to each of the second computing nodes.

[0054] In some embodiments, the determining unit is further configured to use the second computing node corresponding to the minimum network load as the target computing node for final migration of the virtual machine to be migrated.

[0055] In some embodiments, the prediction unit further includes:

[0056] The second prediction unit is used to infer and solve the network load function based on the converted logical programming engine semantic value corresponding to the value of the network element in the network snapshot of a target computing node, so as to obtain the network load of the virtual machine to be migrated to each of the second computing nodes.

[0057] In some embodiments, the determining unit is further configured to:

[0058] Reversely solving the global optimal solution of the network load function being greater than or equal to a preset network load threshold, and obtaining a logic programming engine semantic value corresponding to the optimal solution;

[0059] From the logic programming engine semantic values ​​corresponding to each computing node, a semantic value matching the logic programming engine semantic value corresponding to the optimal solution is selected, and a second computing node corresponding to the selected semantic value is used as the target computing node for final migration of the virtual machine to be migrated.

[0060] In some embodiments, the first acquiring unit is further configured to:

[0061] In response to a migration instruction of a virtual machine to be migrated, obtaining a control plane configuration item and a forwarding plane configuration item of a virtual network where the virtual machine to be migrated is located;

[0062] Formal modeling is performed on the network element elements in the control plane configuration item and the forwarding plane configuration item respectively to obtain the control plane network element abstract data set and the forwarding plane network element abstract data set.

[0063] In some embodiments, the apparatus further comprises:

[0064] A migration unit, configured to migrate the virtual machine to be migrated from the first computing node to the target computing node after determining the target computing node to be finally migrated of the virtual machine to be migrated according to the network load of each second computing node;

[0065] The monitoring unit is used to monitor the overall network load through the network visualization system, and the migration ends when it is detected that the network load is less than a preset disturbance threshold.

[0066] In some embodiments, the monitoring unit is further configured to:

[0067] Monitor the traffic of each computing node in the virtual network and analyze the network load usage of each computing node;

[0068] The network visualization system built based on Prometheus performs a global preview of the network load and the network snapshot;

[0069] Monitoring whether the network load is less than the preset disturbance threshold;

[0070] When it is determined that the network load is less than the preset disturbance threshold, the migration of the virtual machine to be migrated is completed.

[0071] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0072] at least one processor; and

[0073] a memory communicatively connected to the at least one processor; wherein,

[0074] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0075] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0076] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described in the first aspect above.

[0077] The method, device, electronic device and storage medium for dynamic resource adjustment provided by the present disclosure obtain configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of control plane configuration items and forwarding plane configuration items; based on the configuration items, obtain the respective values ​​of each network element contained in the configuration items of the first computing node where the virtual machine to be migrated is currently located; based on the respective values ​​of each network element, respectively predict the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated, and determine the target computing node for the final migration of the virtual machine to be migrated according to the network load of each second computing node. The embodiment of the present disclosure predicts the network load of migrating the virtual machine to be migrated to multiple second computing nodes according to the respective values ​​of each network element, and selects one from multiple second computing nodes as the target computing node for the final migration of the virtual machine to be migrated according to the network load of the second computing node, and the target computing node serves as the optimal migration scheduling node for the virtual machine to be migrated, minimizing the network load caused by the migration of the virtual machine to be migrated.

[0078] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0080] Figure 1 A schematic diagram of a flow chart of a method for dynamic resource adjustment provided by an embodiment of the present disclosure;

[0081] Figure 2 A flowchart of another method for dynamic resource adjustment provided by an embodiment of the present disclosure;

[0082] Figure 3 A flowchart of another method for dynamic resource adjustment provided by an embodiment of the present disclosure;

[0083] Figure 4 A flowchart of another method for dynamic resource adjustment provided by an embodiment of the present disclosure;

[0084] Figure 5 A flowchart of another method for dynamic resource adjustment provided by an embodiment of the present disclosure;

[0085] Figure 6 A flowchart of another method for dynamic resource adjustment provided by an embodiment of the present disclosure;

[0086] Figure 7 A schematic diagram of the structure of a device for dynamically adjusting resources provided by an embodiment of the present disclosure;

[0087] Figure 8 A schematic diagram of the structure of another device for dynamically adjusting resources provided by an embodiment of the present disclosure;

[0088] Fig. 9 A schematic block diagram of an exemplary electronic device provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0089] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0090] The following describes the method, device, electronic device and storage medium for dynamic resource adjustment according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0091] Figure 1 A flowchart of a method for dynamic resource adjustment provided by an embodiment of the present disclosure.

[0092] like Figure 1As shown, the method comprises the following steps:

[0093] Step 101, obtaining configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of control plane configuration items and forwarding plane configuration items.

[0094] The virtual machine migration scheduling server (hereinafter referred to as the server) receives a migration instruction initiated by the virtual machine to be migrated; or, after monitoring the existence of the virtual machine to be migrated, the server synchronously obtains the configuration items of the virtual network where the virtual machine to be migrated is located. The configuration items described in the embodiment of the present application include but are not limited to at least one of the control plane configuration items and the forwarding plane configuration items.

[0095] In some embodiments, the control plane configuration items described in the embodiments of the present disclosure include but are not limited to: one or more of network element elements such as routing protocols, Neutron configuration items, etc.; the forwarding plane configuration items include but are not limited to: one or more of network element elements such as flow tables, session tables, routing tables, and network ACL configuration items.

[0096] Step 102: Based on the configuration item, obtain the respective values ​​of each network element contained in the configuration item of the first computing node where the virtual machine to be migrated is currently located.

[0097] Install the virtual network collection module (ovs-exporter) on all computing nodes of the virtual network where the virtual machine to be migrated is located, and set the collection cycle, for example, 5 minutes, to collect network attribute information such as computing node network accessibility, bandwidth fluctuation, number of new sessions and number of concurrent sessions, configure the ovs-exporter plug-in to connect to prometheus, and form a computing node network snapshot through data governance. Based on the deployment of the ovs-exporter plug-in on the computing node, the collection and visualization of the T+0 computing node network indicator information is realized.

[0098] In an embodiment of the present application, when obtaining the respective values ​​of each network element contained in the configuration item of the first computing node where the virtual machine to be migrated is currently located, the virtual network collection module in the first computing node is used to collect the respective values ​​of each network element of the first computing node.

[0099] The server collects real-time network snapshots of multiple computing nodes, which are recorded as (j, k, l...), where j represents the real-time network snapshot of one computing node, k represents the real-time network snapshot of another computing node, and so on.

[0100] In some embodiments, the network snapshot may be presented in a table.

[0101] In the specific application process, the collected network snapshot can be the specific values ​​of each network element contained in the forwarding plane configuration items and the control plane configuration items. For example, a network snapshot of a computing node can include: one or more specific values ​​of the network element elements such as the flow table / routing table / ACL / session table of the computing node, and one or more specific values ​​of the network element elements such as the flow table, session table, routing table and network ACL configuration items of the computing node.

[0102] Step 103, based on the respective values ​​of the respective network element elements, respectively predict the network load of the virtual machine to be migrated to each second computing node in the virtual network, and determine the target computing node to which the virtual machine to be migrated will eventually migrate according to the network load of each second computing node.

[0103] When executing the migration of the virtual machine to be migrated, in order to minimize the network load caused by the migration of the virtual machine to be migrated, it is necessary to predict the network load of the virtual machine to be migrated to each second computing node in the virtual network respectively, and determine a minimum network load from all network loads, and determine the second computing node corresponding to the minimum network load as the target computing node for the final migration of the virtual machine to be migrated.

[0104] The method for dynamic resource adjustment provided by the present disclosure obtains configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of control plane configuration items and forwarding plane configuration items; based on the configuration items, obtains the respective values ​​of each network element contained in the configuration items of the first computing node where the virtual machine to be migrated is currently located; based on the respective values ​​of each network element, predicts the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated, and determines the target computing node to which the virtual machine to be migrated is finally migrated according to the network load of each second computing node. The embodiment of the present disclosure predicts the network load of migrating the virtual machine to be migrated to multiple second computing nodes according to the respective values ​​of each network element, and selects one from multiple second computing nodes as the target computing node to which the virtual machine to be migrated is finally migrated according to the network load of the second computing node. The target computing node serves as the optimal migration scheduling node for the virtual machine to be migrated, minimizing the network load caused by the migration of the virtual machine to be migrated.

[0105] The present application also provides a method for dynamically adjusting resources, which can be implemented in the following ways but is not limited to: Figure 2 As shown, including:

[0106] Step 201, determine a control plane network element abstract data set and a forwarding plane network element abstract data set, wherein the control plane network element abstract data set and the forwarding plane network element abstract data set are obtained by modeling the control plane configuration items and the forwarding plane configuration items of the virtual network where the virtual machine to be migrated is located.

[0107] The server performs formal modeling of network forwarding plane behavior based on forwarding plane configuration items (flow table / routing table / ACL / session table and other network element elements). Specifically, it means: converting the network element elements in the forwarding plane configuration items into a forwarding plane network element abstract data set according to the formal modeling method. For example, the forwarding plane network element abstract data set here can be expressed as A(x, y, z), where x, y, and z represent a forwarding plane configuration item, such as a flow table, ACL, and session table respectively; similarly, the control plane configuration items where the virtual machines to be migrated are located are also converted into the corresponding control plane network element abstract data set B(a, b, c) in a similar manner;

[0108] Among them, the forwarding plane network element abstract data set A(x, y, z) and the control plane network element abstract data set B(a, b, c) are equivalent to the data framework set built with specific values ​​to be filled in. Later, the values ​​of the corresponding data of the network snapshot will be filled in as the values ​​of x, y, z in A(x, y, z) and the values ​​of a, b, c in B(a, b, c).

[0109] Define how network components in OpenStack forward messages as rules to form formal specifications, extract real-time network configuration from the existing network to build configuration snapshots, and transform virtual network environment / network snapshot / component forwarding behavior into satisfiability problem solving, including:

[0110] Network control plane modeling: Convert the control plane message forwarding logic into a formal model based on routing protocols and OpenStack network environment configuration.

[0111] Network forwarding plane modeling: Based on the forwarding plane configuration (routing table, network ACL configuration, etc.), the forwarding plane behavior of network components is converted into a formal model.

[0112] In the embodiments of the present disclosure, the formal model is a technology based on mathematical form, which is used to divide and analyze the system, can effectively describe the system parameters that dynamically change in the system, use mathematical equations and functions to describe various system behaviors, and build effective computer models to achieve simulation and analysis effects. The core of the formal model is a system description, such as quantitative description, graphical description, text-based description, and graphic-based description.

[0113] Step 202, collecting a network snapshot of each computing node of the virtual network where the virtual machine to be migrated is located, wherein the network snapshot is a value of each network element included in the control plane configuration item and / or the forwarding plane configuration item;

[0114] Install the virtual network collection module (ovs-exporter) on all computing nodes of the virtual network where the virtual machine to be migrated is located, and set the collection cycle, for example, 5 minutes, to collect network attribute information such as computing node network accessibility, bandwidth fluctuation, number of new sessions and number of concurrent sessions, configure the ovs-exporter plug-in to connect to prometheus, and form a computing node network snapshot through data governance. Based on the deployment of the ovs-exporter plug-in on the computing node, the collection and visualization of the T+0 computing node network indicator information is realized.

[0115] The server collects real-time network snapshots of multiple computing nodes, which are recorded as (j, k, l...), where j represents the real-time network snapshot of one computing node, k represents the real-time network snapshot of another computing node, and so on.

[0116] In some embodiments, the network snapshot may be presented in a table.

[0117] In the specific application process, the collected network snapshot can be the specific values ​​of each network element contained in the forwarding plane configuration items and the control plane configuration items. For example, a network snapshot of a computing node can include: one or more specific values ​​of the network element elements such as the flow table / routing table / ACL / session table of the computing node, and one or more specific values ​​of the network element elements such as the flow table, session table, routing table and network ACL configuration items of the computing node.

[0118] For ease of understanding, take the specific value in the routing table as an example, assuming that the specific value in the routing table may be: 255.255.255.255. The above is only an illustrative example, and the embodiments of the present disclosure do not limit the specific values ​​corresponding to the network element elements.

[0119] Step 203: Based on the logic programming engine, a deductive reasoning method is used for the values ​​of each of the network elements to respectively predict the network load of the virtual machine to be migrated to each of the second computing nodes.

[0120] When performing this step, you can use but are not limited to Figure 3 The method shown comprises:

[0121] Step 2031, according to the preset conversion relationship between different network element elements and logical programming engine semantic values, the values ​​of the network element elements in the network snapshot are converted into corresponding logical programming engine semantic values.

[0122] The server calls the logic programming pydatalog engine to execute: according to the pre-set conversion relationship between different network element elements and pydatalog semantic values, the values ​​of the network element elements in the network snapshots of each computing node collected are converted into corresponding pydatalog semantic values.

[0123] Taking the example of step 202, the number 255.255.255.255 in the routing table contained in the network snapshot can be converted into a numerical value. Specifically, 255.255.255 can be mapped into a 32-bit binary number.

[0124] It should be clear that the above examples are merely illustrative descriptions and are not limitations on the conversion form and specific numerical values ​​of semantic values.

[0125] Step 2032: Deductively reasoning each of the logical programming engine semantic values ​​to predict the network load of migrating the virtual machine to be migrated to the plurality of second computing nodes.

[0126] Based on the above preparations for "network knowledge modeling" and "network attribute modeling", the main focus is on the processing plan for the migration of the virtual machine to be migrated. The migration plan can be implemented in the following two ways:

[0127] Method 1: Figure 4 As shown, specifically including:

[0128] Step 301, respectively substitute each of the logical programming engine semantic values ​​into the forwarding plane network element abstract data set and the control plane network element abstract data set;

[0129] Method 1 is the forward reasoning method.

[0130] The network load problem is converted into a multi-sort first-order logic formula. After the migration action is triggered by the virtual machine to be migrated, the network snapshot of the migration target node is used as an input parameter. Based on the knowledge graph deductive reasoning / forward reasoning (discovering new facts based on rules), the pydatalog engine is used to solve the overall load of the virtual network after the virtual machine migration.

[0131] The server substitutes the pydatalog semantic values ​​corresponding to the values ​​of the network element elements in the network snapshot of each computing node obtained by conversion into the corresponding forwarding plane network element abstract data set and the control plane network element abstract data set respectively.

[0132] Step 302, based on the forwarding plane network element abstract data set and the control plane network element abstract data set substituted into the logic programming engine semantic value, infer and solve the network load function, and respectively predict the network load of the virtual machine to be migrated to each of the second computing nodes.

[0133] The specific implementation process of the server solving the network load function (equation f(A, B)) based on pydatalog semantic value reasoning is as follows: the pydatalog semantic value corresponding to the value of the network element in the network snapshot of a computing node is substituted into A(x, y, z) and B(a, b, c) as the input parameter, that is, the pydatalog semantic value is used as the specific numerical value of the corresponding x, y, z, a, b, c to calculate the value of the function f(A, B). The calculated value of the function f(A, B) represents the network load of migrating the virtual machine to be migrated to the second computing node.

[0134] Step 303: Use the second computing node corresponding to the minimum network load as the target computing node for final migration of the virtual machine to be migrated.

[0135] Method 2: Figure 5 As shown, specifically including:

[0136] Step 401, based on the converted pydatalog semantic value corresponding to the value of the network element in the network snapshot of a target computing node, infer and solve the network load function to obtain the network load of the virtual machine to be migrated to each of the second computing nodes.

[0137] The second method is the reverse solution method, which encodes the expected network load and the network model parameters to be solved into logical equations, converts them into satisfiability problems, and uses the SMT solver to search for qualified network model parameters for the next round of deductive reasoning until the network load results converge to the global optimal solution, and obtains the optimal solution for the migration node network parameters, that is, the optimal migration node.

[0138] The server infers and solves the equation f(A, B) based on the converted pydatalog semantic value corresponding to the value of the network element in the network snapshot of a computing node, and obtains the network load after the virtual machine is migrated to the computing node.

[0139] Step 402, reversely solving the global optimal solution of the network load function being greater than or equal to a preset network load threshold, and obtaining a logic programming engine semantic value corresponding to the optimal solution.

[0140] Reversely solve the global optimal solution of the network load function that is greater than or equal to a preset network load threshold, and obtain the pydatalog semantic value corresponding to the optimal solution.

[0141] Step 403, select a semantic value that matches the logic programming engine semantic value corresponding to the optimal solution from the logic programming engine semantic values ​​corresponding to each computing node, and use the second computing node corresponding to the selected semantic value as the target computing node for the final migration of the virtual machine to be migrated.

[0142] It is determined whether the network load obtained in step 401 is greater than a preset network load threshold value P; if so, a reverse satisfiability solution method is adopted to solve the equation f(A, B)<=P.

[0143] Specifically, the solution process of this equation is to use the SMT solver to search for a qualified formal model input parameter set for the next round of deductive reasoning until the network load result converges to the global optimal solution, and then obtain the optimal migration node network parameters, that is, obtain the pydatalog semantic value corresponding to the optimal solution of f(A,B); based on the pydatalog semantic value corresponding to the optimal solution, select the semantic value that best matches the optimal solution from the pydatalog semantic values ​​corresponding to each computing node, and use the second computing node corresponding to the selected semantic value as the target computing node to which the virtual machine to be migrated will be migrated.

[0144] Specifically, a network visualization system is built based on Prometheus to achieve dynamic management of network snapshots and visual monitoring of network load. The overall network load is monitored through the network visualization system, and the migration ends when the network load is less than the preset disturbance threshold. Figure 6 As shown, including:

[0145] Step 501 , monitor the traffic of each computing node in the virtual network and analyze the network load usage of each computing node.

[0146] Use ovs-exporter to monitor computing node traffic and analyze network resource usage.

[0147] Step 502: The network visualization system built based on Prometheus performs a global preview of the network load and the network snapshot.

[0148] Access the network visualization system through Prometheus to achieve a global preview of network resources.

[0149] Step 503, monitoring whether the network load is less than the preset disturbance threshold;

[0150] Step 504: When it is determined that the network load is less than the preset disturbance threshold, the migration of the virtual machine to be migrated is completed.

[0151] The embodiments of the present application have the following beneficial effects:

[0152] This proposal proposes a method for dynamically adjusting resources in Openstack using network monitoring technology. This method supports monitoring of computing node traffic and network node traffic, analyzes specific services, and dynamically adjusts network resources to reduce the risk of the network becoming a bottleneck.

[0153] Specifically:

[0154] 1. Use ovs-exporter to monitor the computing node traffic, analyze the network resource usage, and access the network visualization platform through prometheus to achieve a global preview of network resources;

[0155] 2. Use network modeling technology to formally model the network control plane, forwarding plane and network snapshot;

[0156] 3. Perform virtual machine scheduling migration simulation analysis through deductive reasoning, calculate the optimal migration scheduling node through forward reasoning / post-item solution, and minimize the network load caused by virtual machine migration.

[0157] Corresponding to the above-mentioned resource dynamic adjustment method, the present invention also provides a resource dynamic adjustment device. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, the details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be repeated in the present invention.

[0158] Figure 7 A schematic diagram of a device for dynamically adjusting resources provided by an embodiment of the present disclosure is shown in FIG. Figure 6 As shown, including:

[0159] A first acquisition unit 61 is used to acquire configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of a control plane configuration item and a forwarding plane configuration item;

[0160] A second acquisition unit 62 is used to acquire, based on the configuration item, the respective values ​​of each network element contained in the configuration item of the first computing node where the virtual machine to be migrated is currently located;

[0161] A prediction unit 63, configured to respectively predict the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated based on the respective values ​​of the respective network element elements;

[0162] The determining unit 64 is configured to determine a target computing node to which the virtual machine to be migrated is ultimately migrated according to the network load of each second computing node.

[0163] The apparatus, electronic device and storage medium for dynamic resource adjustment provided by the present disclosure obtain configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of control plane configuration items and forwarding plane configuration items; based on the configuration items, obtain the respective values ​​of each network element contained in the configuration items of the first computing node where the virtual machine to be migrated is currently located; based on the respective values ​​of each network element, respectively predict the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated, and determine the target computing node for the final migration of the virtual machine to be migrated according to the network load of each second computing node. The embodiment of the present disclosure predicts the network load of migrating the virtual machine to be migrated to multiple second computing nodes according to the respective values ​​of each network element, and selects one from multiple second computing nodes as the target computing node for the final migration of the virtual machine to be migrated according to the network load of the second computing node. The target computing node serves as the optimal migration scheduling node for the virtual machine to be migrated, minimizing the network load caused by the migration of the virtual machine to be migrated.

[0164] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the prediction unit 63 is further used to use deductive reasoning on the values ​​of each network element based on a logic programming engine to predict the network load of the virtual machine to be migrated to each second computing node.

[0165] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the first acquisition unit 61 is further used to determine a control plane network element abstract data set and a forwarding plane network element abstract data set, wherein the control plane network element abstract data set and the forwarding plane network element abstract data set are obtained by modeling the control plane configuration items and the forwarding plane configuration items of the virtual network where the virtual machine to be migrated is located;

[0166] The second acquisition unit 62 is further used to collect network snapshots of each computing node of the virtual network where the virtual machine to be migrated is located, and the network snapshots are respective values ​​of each network element included in the control plane configuration item and / or the forwarding plane configuration item.

[0167] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the prediction unit 63 includes:

[0168] The conversion module 631 is used to convert the value of the network element in the network snapshot into the corresponding logic programming engine semantic value according to the preset conversion relationship between different network element elements and logic programming engine semantic values;

[0169] The first prediction module 632 is used to predict the network load of migrating the virtual machine to be migrated to multiple second computing nodes through deductive reasoning of the semantic values ​​of each of the logical programming engines.

[0170] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the first prediction module 632 is further used for:

[0171] Substituting each of the logical programming engine semantic values ​​into the forwarding plane network element abstract data set and the control plane network element abstract data set respectively;

[0172] Based on the forwarding plane network element abstract data set and the control plane network element abstract data set substituted into the logic programming engine semantic values, the network load function is inferred and solved to predict the network load of the virtual machine to be migrated to each of the second computing nodes.

[0173] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the determining unit 64 is further configured to use the second computing node corresponding to the minimum network load as the target computing node for final migration of the virtual machine to be migrated.

[0174] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the prediction unit 63 further includes:

[0175] The second prediction unit 633 is used to infer and solve the network load function based on the converted logical programming engine semantic value corresponding to the value of the network element in the network snapshot of a target computing node, and obtain the network load of the virtual machine to be migrated to each of the second computing nodes.

[0176] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the determining unit 64 is further used for:

[0177] Reversely solving the global optimal solution of the network load function being greater than or equal to a preset network load threshold, and obtaining a logic programming engine semantic value corresponding to the optimal solution;

[0178] From the logic programming engine semantic values ​​corresponding to each computing node, a semantic value matching the logic programming engine semantic value corresponding to the optimal solution is selected, and a second computing node corresponding to the selected semantic value is used as the target computing node for final migration of the virtual machine to be migrated.

[0179] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the first acquisition unit 61 is further used for:

[0180] In response to a migration instruction of a virtual machine to be migrated, obtaining a control plane configuration item and a forwarding plane configuration item of a virtual network where the virtual machine to be migrated is located;

[0181] Formal modeling is performed on the network element elements in the control plane configuration item and the forwarding plane configuration item respectively to obtain the control plane network element abstract data set and the forwarding plane network element abstract data set.

[0182] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the device also includes:

[0183] A migration unit 65, configured to migrate the virtual machine to be migrated from the first computing node to the target computing node after determining the target computing node to which the virtual machine to be migrated is finally migrated according to the network load of each second computing node;

[0184] The monitoring unit 66 is used to monitor the overall network load through the network visualization system, and the migration ends when it is detected that the network load is less than a preset disturbance threshold.

[0185] Furthermore, in a possible implementation of the embodiment of the present disclosure, as Figure 8 As shown, the monitoring unit 66 is also used for:

[0186] Monitor the traffic of each computing node in the virtual network and analyze the network load usage of each computing node;

[0187] The network visualization system built based on Prometheus performs a global preview of the network load and the network snapshot;

[0188] Monitoring whether the network load is less than the preset disturbance threshold;

[0189] When it is determined that the network load is less than the preset disturbance threshold, the migration of the virtual machine to be migrated is completed.

[0190] It should be noted that the above explanation of the method embodiment is also applicable to the device of the embodiment of the present disclosure, and the principle is the same, which is no longer limited in the embodiment of the present disclosure.

[0191] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0192] Fig. 9A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0193] like Fig. 9 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 702 or a computer program loaded from a storage unit 708 to a RAM (Random Access Memory) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An I / O (Input / Output) interface 705 is also connected to the bus 704.

[0194] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0195] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as a method for dynamic resource adjustment. For example, in some embodiments, the method for dynamic resource adjustment may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to execute the aforementioned resource dynamic adjustment method in any other appropriate manner (for example, by means of firmware).

[0196] Various embodiments of the systems and techniques described above in this article can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs, which may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, which may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0197] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0198] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory, Erasable Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory, Portable Compact Disk Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0199] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0200] The systems and techniques described herein may be implemented in a computing system that includes a backend component (e.g., as a data server), or a computing system that includes a middleware component (e.g., an application server), or a computing system that includes a frontend component (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0201] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0202] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0203] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0204] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for dynamic resource adjustment, characterized in that: include: Obtaining configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of a control plane configuration item and a forwarding plane configuration item; Based on the configuration item, obtaining respective values ​​of each network element contained in the configuration item of the first computing node where the virtual machine to be migrated is currently located; Based on the respective values ​​of the network elements, the network loads of the virtual machines to be migrated to the second computing nodes in the virtual network are predicted respectively, and the target computing node for the final migration of the virtual machines to be migrated is determined according to the network loads of the second computing nodes.

2. The method according to claim 1, characterized in that The predicting, based on the respective values ​​of the respective network element components, the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated comprises: Based on the logic programming engine, deductive reasoning is used for the values ​​of each of the network elements to respectively predict the network load of the virtual machine to be migrated to each of the second computing nodes.

3. The method according to claim 2, characterized in that The step of obtaining configuration items of each computing node in the virtual network where the virtual machine to be migrated is located includes: Determine a control plane network element abstract data set and a forwarding plane network element abstract data set, wherein the control plane network element abstract data set and the forwarding plane network element abstract data set are obtained by modeling the control plane configuration items and the forwarding plane configuration items of the virtual network where the virtual machine to be migrated is located; The obtaining, based on the configuration item, respective values ​​of each network element included in the configuration item of the virtual machine to be migrated includes: A network snapshot of each computing node of the virtual network where the virtual machine to be migrated is located is collected, where the network snapshot is the value of each network element included in the control plane configuration item and / or the forwarding plane configuration item.

4. The method according to claim 3, characterized in that The method of using a deductive reasoning method based on the logic programming engine to predict the network load of each of the virtual machines to be migrated to each of the second computing nodes includes: According to the preset conversion relationship between different network element elements and logical programming engine semantic values, the values ​​of the network element elements in the network snapshot are converted into corresponding logical programming engine semantic values; The semantic values ​​of each of the logic programming engines are deductively reasoned to respectively predict the network load of migrating the virtual machine to be migrated to the plurality of the second computing nodes.

5. The method according to claim 4, characterized in that The method of using deductive reasoning to predict the network load of migrating the virtual machine to be migrated to the plurality of second computing nodes includes: Substituting each of the logical programming engine semantic values ​​into the forwarding plane network element abstract data set and the control plane network element abstract data set respectively; Based on the forwarding plane network element abstract data set and the control plane network element abstract data set substituted into the logic programming engine semantic values, the network load function is inferred and solved to predict the network load of the virtual machine to be migrated to each of the second computing nodes.

6. The method according to claim 5, characterized in that The determining, according to the network load of each second computing node, a target computing node for final migration of the to-be-migrated virtual machine comprises: The second computing node corresponding to the minimum network load is used as the target computing node for final migration of the virtual machine to be migrated.

7. The method according to claim 3, characterized in that The method of using a deductive reasoning method based on the logic programming engine to predict the network load of each of the virtual machines to be migrated to each of the second computing nodes includes: Based on the converted logical programming engine semantic value corresponding to the value of the network element in the network snapshot of a target computing node, the network load function is inferred and solved to obtain the network load of the virtual machine to be migrated to each of the second computing nodes.

8. The method according to claim 7, characterized in that The determining, according to the network load of each second computing node, a target computing node for final migration of the to-be-migrated virtual machine comprises: Reversely solving the global optimal solution of the network load function being greater than or equal to a preset network load threshold, and obtaining a logic programming engine semantic value corresponding to the optimal solution; From the logic programming engine semantic values ​​corresponding to each computing node, a semantic value matching the logic programming engine semantic value corresponding to the optimal solution is selected, and a second computing node corresponding to the selected semantic value is used as the target computing node for final migration of the virtual machine to be migrated.

9. The method according to claim 3, characterized in that: Determining the control plane network element abstract data set and the forwarding plane network element abstract data set includes: In response to a migration instruction of a virtual machine to be migrated, obtaining a control plane configuration item and a forwarding plane configuration item of a virtual network where the virtual machine to be migrated is located; Formal modeling is performed on the network element elements in the control plane configuration item and the forwarding plane configuration item respectively to obtain the control plane network element abstract data set and the forwarding plane network element abstract data set.

10. The method according to any one of claims 1 to 9, characterized in that After determining the target computing node to which the virtual machine to be migrated is finally migrated according to the network load of each second computing node, the method further includes: Migrating the virtual machine to be migrated from the first computing node to the target computing node; The overall network load is monitored through the network visualization system, and the migration ends when the network load is detected to be less than the preset disturbance threshold.

11. The method according to claim 10, characterized in that The overall network load is monitored by the network visualization system, and the migration ends after the network load is detected to be less than a preset disturbance threshold, including: Monitor the traffic of each computing node in the virtual network and analyze the network load usage of each computing node; The network visualization system built based on Prometheus performs a global preview of the network load and the network snapshot; Monitoring whether the network load is less than the preset disturbance threshold; When it is determined that the network load is less than the preset disturbance threshold, the migration of the virtual machine to be migrated is completed.

12. A device for dynamically adjusting resources, characterized in that: include: A first acquisition unit is used to acquire configuration items of each computing node in the virtual network where the virtual machine to be migrated is located; the configuration items include at least one of a control plane configuration item and a forwarding plane configuration item; A second acquisition unit, configured to acquire, based on the configuration item, respective values ​​of each network element contained in the configuration item of the first computing node where the virtual machine to be migrated is currently located; A prediction unit, configured to respectively predict the network load of each second computing node in the virtual network to which the virtual machine to be migrated is migrated based on the respective values ​​of each network element; The determining unit is used to determine the target computing node to which the virtual machine to be migrated is finally migrated according to the network load of each second computing node.

13. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

14. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

15. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 11.

Citation Information

Patent Citations

  • Method for migrating virtual machine and resource scheduling platform

    CN104102523A

  • Virtual machine migration method, cloud computing management platform and storage medium

    CN111381928A

  • Migration method and device of virtual machine in cloud computing environment and computer equipment

    CN111611048A

  • Virtual machine migration and management method, server and computer readable storage medium

    CN112445571A

  • Virtual machine migration method and device, electronic equipment and storage medium

    CN114035906A

Cited By

  • Traffic migration method and device, computer equipment and computer readable storage medium

    CN119520439A