A method and system for testing bandwidth of edge computing nodes

Abstract

The present invention discloses a method and system for testing the bandwidth of edge computing nodes, which determines whether the remaining computing resources of edge computing nodes meet the minimum resource requirements of the verification application; if they meet, computing resources are allocated according to the computing resource allocation request of the verification application service; if the computing resource allocation of the verification application service is successful, broadband resources are allocated according to the link bandwidth resource allocation request of the verification application service, and if the allocation fails, a reallocation judgment is made; when the computing resources and link bandwidth resources requested by the verification application service are successfully allocated, the comprehensive performance of the upstream and downstream bandwidth rates is tested based on a self-compiled test script to see whether they meet the standards. This method first determines whether the redundant resources meet the basic test requirements, and then performs the test after the allocation is satisfied. It can conduct a comprehensive and complete quality test on the node bandwidth for different predefined thresholds of the deployed service types.

Description

Technical Field

[0001] The present invention relates to the field of edge computing technology, and in particular to a method and system for testing bandwidth of an edge computing node. Background Art

[0002] At present, there are many types of traditional edge computing node bandwidths, and the quality varies. Whether it is third-party testing software or engineers testing themselves, the ways that can be tested are usually very limited. In most cases, there are only simple channel bandwidth stress tests and packet loss rates, etc. It is usually difficult to fully test the bandwidth quality of the edge computing node bandwidth itself. The testing method proposed in this invention solves this problem well. It can conduct a comprehensive and complete quality test on the node bandwidth for different predefined thresholds of the deployed business type. Summary of the invention

[0003] To this end, the present invention provides an edge computing node bandwidth testing method and system to solve the problem that traditional edge computing node bandwidth testing methods are limited and cannot perform comprehensive and complete quality testing of node bandwidth.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] According to a first aspect of an embodiment of the present invention, a method for testing bandwidth of an edge computing node is proposed, the method comprising:

[0006] Determine whether the remaining computing resources of the edge computing node meet the minimum resource requirements of the verification application;

[0007] If satisfied, computing resources are allocated according to the computing resource allocation request of the verification application business;

[0008] If the computing resource allocation of the verification application service is successful, broadband resource allocation is performed according to the link bandwidth resource allocation request of the verification application service. If the allocation fails, a reallocation judgment is performed;

[0009] When the computing resources and link bandwidth resources requested by the application service are successfully allocated, the comprehensive performance of the upstream and downstream bandwidth rates is tested based on the self-compiled test script to see if they meet the requirements.

[0010] Furthermore, the reallocation judgment includes:

[0011] Compare the preset verification application business computing resource threshold with the remaining computing resources of the currently applied allocation node, cancel the computing resource node request that is less than the verification application business resource threshold, and do not perform subsequent resource allocation operations;

[0012] Sort the computing resource requests for verifying the application business requests from largest to smallest, and make a judgment on the allocation of computing resource requests in sequence;

[0013] If the verification application service calculation resource allocation is successful, then the link bandwidth resource allocation requested by the verification application service is performed;

[0014] If at this time, the allocation of one of the computing resources or link bandwidth resources of the verification application service fails, the verification application service application that failed to be allocated will be revoked, and the allocation failure information will be returned to the edge cloud platform.

[0015] Furthermore, the method further comprises:

[0016] The resource tests for verifying application services are divided into three categories: single-line single thread, single-line multi-thread, and multi-line multi-thread. The three types of application tests request computing resources and bandwidth resource matching from small to large;

[0017] If the application business computing resources and bandwidth resource allocation are verified successfully, three types of bandwidth rate application scenario verification will be carried out according to the requirements and the test will be performed according to the preset test process.

[0018] Furthermore, the test process includes:

[0019] Prepare the test environment;

[0020] Use the self-compiled test scripts of the corresponding services to test whether the comprehensive performance of the line uplink and downlink rates meets the standards;

[0021] If the test passes, the test results are recorded and a test report is generated. If the test fails, the operator is informed to investigate the cause and handle the problem.

[0022] Furthermore, the comprehensive performance of the upstream and downstream bandwidth rates is tested based on the self-compiled test script to see whether it meets the standards, including:

[0023] The comprehensive performance is calculated based on the comprehensive performance calculation model, and the comprehensive performance calculation model is:

[0024] N=[(A11*4 / 10+A12*2 / 10+A13*4 / 10)*1 / 4+(A21*4 / 10+A22*2 / 10+A23*4 / 10)*3 / 4] / A3*P1+(10 -B1) / 10*P2+(0.05-C1) / 0.05*P3+(10-D1) / 10*P4+(0.05-E1) / 0.05*P5+(5000-F1) / 5000*P6;

[0025] Among them, A11 is the average bandwidth rate within the set minute calculated for downstream HTTP, A12 is the average bandwidth rate within the set minute calculated for downstream FTP, A13 is the average bandwidth rate within the set minute calculated for downstream P2P, A21 is the average bandwidth rate within the set minute calculated for upstream HTTP, A22 is the average bandwidth rate within the set minute calculated for upstream FTP, A23 is the average bandwidth rate within the set minute calculated for upstream P2P, A3 is the speed limit value for allocated resources, B1 is the average delay within the set minute, C1 is the average packet loss rate within the set minute, D1 is the average first packet time within the set minute, E1 is the average retransmission rate within the set minute, and F1 is the average home page opening time for a preset number of times;

[0026] Among them, P1-P6 are business weight constants, and each weight value is pre-set into the script according to different businesses.

[0027] Furthermore, the comprehensive performance of the upstream and downstream bandwidth rates is tested based on the self-compiled test script to see whether it meets the standards, including:

[0028] When the comprehensive performance index N is greater than 80%, the bandwidth rate is actually available and meets the basic standard. When N is greater than 90%, a comprehensive rating is given based on the service type.

[0029] Furthermore, the edge cloud platform manages edge computing node servers, and each edge computing node server communicates with an Internet client terminal via Internet dedicated line bandwidth or PPPOE bandwidth.

[0030] According to a second aspect of an embodiment of the present invention, a system for testing bandwidth of an edge computing node is proposed, the system comprising:

[0031] The test resource allocation module is used to determine whether the remaining computing resources of the edge computing node meet the minimum resource requirements of the verification application;

[0032] If satisfied, computing resources are allocated according to the computing resource allocation request of the verification application business;

[0033] If the computing resource allocation of the verification application service is successful, broadband resource allocation is performed according to the link bandwidth resource allocation request of the verification application service. If the allocation fails, a reallocation judgment is performed;

[0034] The test module is used to verify whether the computing resources and link bandwidth resources requested by the application service are successfully allocated, and then test whether the comprehensive performance of the upstream and downstream bandwidth rates meets the standards based on the self-compiled test script.

[0035] According to a third aspect of an embodiment of the present invention, a computer storage medium is proposed, wherein the computer storage medium contains one or more program instructions, and the one or more program instructions are used to be executed by an edge computing node bandwidth testing system as described in any of the above methods.

[0036] The present invention has the following advantages:

[0037] The present invention proposes a method and system for testing the bandwidth of edge computing nodes, which determines whether the remaining computing resources of the edge computing nodes meet the minimum resource requirements of the verification application; if they meet, the computing resources are allocated according to the computing resource allocation request of the verification application service; if the computing resource allocation of the verification application service is successful, the broadband resources are allocated according to the link bandwidth resource allocation request of the verification application service, and if the allocation fails, a reallocation judgment is made; when the computing resources and link bandwidth resources requested by the verification application service are successfully allocated, the comprehensive performance of the upstream and downstream bandwidth rates is tested based on the self-compiled test script to see whether they meet the standards. This method first determines whether the redundant resources meet the basic test requirements, and then performs the test after the allocation is satisfied. It can perform a comprehensive and complete quality test on the node bandwidth for different predefined thresholds of the deployed service types; and due to the different types and qualities of the edge computing bandwidth, there are many bandwidths with different qualities that can match different services well. This test method elementizes the key data points of bandwidth quality, and through the weight matching adaptation service model, it can directly verify whether the deployment of different services can meet the adaptation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0039] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0040] Figure 1 A schematic diagram of a flow chart of a method for testing bandwidth of an edge computing node provided in Embodiment 1 of the present invention;

[0041] Figure 2 A schematic diagram of a test flow of an edge computing node bandwidth test method provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0042] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] like Figure 1 As shown, this embodiment proposes a method for testing the bandwidth of an edge computing node, based on an edge cloud system, the edge cloud system includes an edge cloud platform, an edge computing node server, and an Internet client terminal, the edge cloud platform manages the edge computing node server, and each edge computing node server communicates with the Internet client terminal through an Internet dedicated line bandwidth or a PPPOE bandwidth. The method includes:

[0045] S100, determining whether the remaining computing resources of the edge computing node meet the minimum resource requirements of the verification application;

[0046] S200: If satisfied, computing resources are allocated according to the computing resource allocation request of the verification application service;

[0047] S300, if the computing resource allocation of the verification application service is successful, then the broadband resource allocation is performed according to the link bandwidth resource allocation request of the verification application service, and if the allocation fails, then a reallocation judgment is performed;

[0048] S400: When it is verified that the computing resources and link bandwidth resources requested by the application service are allocated successfully, whether the comprehensive performance of the upstream and downstream bandwidth rates meets the standards is tested based on the self-compiled test script.

[0049] The reallocation judgment includes:

[0050] S410, comparing the preset verification application service computing resource threshold with the remaining computing resources of the currently applied allocation node, revoking the computing resource node request that is less than the verification application service resource threshold, and not performing subsequent resource allocation operations;

[0051] S420, sort the computing resource requests of the verification application service requests from large to small, and perform the computing resource method in the above steps S100-S300 in sequence to make allocation judgments. The resource test of the verification application is divided into three categories: single-line single thread, single-line multi-thread, and multi-line multi-thread. The above three application test requests computing resources and bandwidth resource matching from small to large;

[0052] S430, if the verification application service calculation resource allocation is successful, then verify the link bandwidth resource allocation requested by the application service;

[0053] S440. If at this time, the allocation of one of the computing resources or link bandwidth resources of the verification application service fails, the verification application service application that failed to be allocated will be revoked, and the allocation failure information will be returned to the edge cloud platform.

[0054] If there is a problem with the test resources of the node itself, it will affect the normal test process. Therefore, this embodiment will first determine whether the redundant resources meet the basic test requirements. After the allocation is satisfied, the following test model will be executed. Usually, there will be multiple available resources on an edge node, both for computing and bandwidth. Therefore, if the original request to allocate test resources is unsuccessful, the system will try to allocate other redundant test resources of this node, and determine whether to continue to try to allocate resources or terminate and return failure information based on the custom script. In addition, in order to avoid the situation of insufficient node resources or the situation where the resources allocated to the test are not satisfied, it is usually implemented through interface communication with the resource feedback of the edge cloud platform.

[0055] If the application service computing resources and bandwidth resource allocation are verified successfully, three types of bandwidth rate application scenario verifications are performed according to the requirements and the test is performed according to the preset test process. Figure 2 As shown, the test process includes the following steps:

[0056] Prepare the test environment;

[0057] Use the self-compiled test scripts of the corresponding services to test whether the comprehensive performance of the line uplink and downlink rates meets the standards;

[0058] If the test passes, the test results are recorded and a test report is generated. If the test fails, the operator is informed to investigate the cause and handle the problem.

[0059] In this embodiment, the comprehensive performance of the uplink and downlink bandwidth rates is tested based on the self-compiled test script to see whether they meet the standards, specifically including:

[0060] The comprehensive performance is calculated based on the comprehensive performance calculation model, and the comprehensive performance calculation model is:

[0061] N=[(A11*4 / 10+A12*2 / 10+A13*4 / 10)*1 / 4+(A21*4 / 10+A22*2 / 10+A23*4 / 10)*3 / 4] / A3*P1+(10 -B1) / 10*P2+(0.05-C1) / 0.05*P3+(10-D1) / 10*P4+(0.05-E1) / 0.05*P5+(5000-F1) / 5000*P6;

[0062] Among them, A11 is the average bandwidth rate of downstream HTTP within 5 minutes, A12 is the average bandwidth rate of downstream FTP within 5 minutes, A13 is the average bandwidth rate of downstream P2P within 5 minutes, A21 is the average bandwidth rate of upstream HTTP within 5 minutes, A22 is the average bandwidth rate of upstream FTP within 5 minutes, A23 is the average bandwidth rate of upstream P2P within 5 minutes, A3 is the allocated resource speed limit value, B1 is the average delay within 5 minutes, C1 is the average packet loss rate within 5 minutes, D1 is the average first packet time within 5 minutes, E1 is the average retransmission rate within 5 minutes, and F1 is the average home page opening time for 20 times.

[0063] Among them, P1-P6 are service weight constants, and each weight value is pre-set into the script according to different services. The weight value is pre-set into the script according to different services. Taking Class A services as an example, the pre-set bandwidth rate weight is P1: 0.6 (the ratio of uplink and downlink rates is 3:1, and the ratio of HTTP, FTP, and P2P protocols is 4:2:4); the delay weight is P2: 0.2; the packet loss rate weight is P3: 0.1; the first packet time and retransmission rate are P4 and P5: both are 0.05; the home page opening time is P6: 0.05.

[0064] Calculation standard: Based on comprehensive performance measurement and business logic requirements, the actual availability ratio of edge cloud resources is evaluated. N greater than 80% is the basic availability ratio standard. After N is greater than 90%, a comprehensive rating is given based on the business type. The calculated values ​​of A11, A12, A13, A21, A22, and A23 shall not be higher than A3. If higher, the values ​​shall be equal to A3.

[0065] Example 2

[0066] Corresponding to the above-mentioned embodiment 1, this embodiment proposes an edge computing node bandwidth testing system, the system comprising:

[0067] The test resource allocation module is used to determine whether the remaining computing resources of the edge computing node meet the minimum resource requirements of the verification application;

[0068] If satisfied, computing resources are allocated according to the computing resource allocation request of the verification application business;

[0069] If the computing resource allocation of the verification application service is successful, broadband resource allocation is performed according to the link bandwidth resource allocation request of the verification application service. If the allocation fails, a reallocation judgment is performed;

[0070] The test module is used to verify whether the computing resources and link bandwidth resources requested by the application service are successfully allocated, and then test whether the comprehensive performance of the upstream and downstream bandwidth rates meets the standards based on the self-compiled test script.

[0071] The functions performed by each component in the edge computing node bandwidth test system provided by the embodiment of the present invention have been described in detail in the above embodiment 1, so they will not be described in detail here.

[0072] Example 3

[0073] Corresponding to the above embodiment, this embodiment proposes a computer storage medium, which contains one or more program instructions, and the one or more program instructions are used to be executed by an edge computing node bandwidth testing system as the method of embodiment 1.

[0074] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for testing bandwidth of edge computing nodes, characterized in that: The method comprises: Determine whether the remaining computing resources of the edge computing node meet the minimum resource requirements of the verification application; If satisfied, computing resources are allocated according to the computing resource allocation request of the verification application business; If the computing resource allocation of the verification application service is successful, broadband resource allocation is performed according to the link bandwidth resource allocation request of the verification application service. If the allocation fails, a reallocation judgment is performed; When the computing resources and link bandwidth resources requested by the application service are successfully allocated, the comprehensive performance of the upstream and downstream bandwidth rates is tested based on the self-compiled test script to see if they meet the requirements; Test the comprehensive performance of upstream and downstream bandwidth rates based on the self-compiled test script to see if they meet the standards, including: The comprehensive performance is calculated based on the comprehensive performance calculation model, and the comprehensive performance calculation model is: N=[(A11*4 / 10+A12*2 / 10+A13*4 / 10)*1 / 4+(A21*4 / 10+A22*2 / 10+A23*4 / 10)*3 / 4] / A3*P1+(10 -B1) / 10*P2+(0.05-C1) / 0.05*P3+(10-D1) / 10*P4+(0.05-E1) / 0.05*P5+(5000-F1) / 5000*P6; Among them, A11 is the average bandwidth rate within the set minute calculated for downstream HTTP, A12 is the average bandwidth rate within the set minute calculated for downstream FTP, A13 is the average bandwidth rate within the set minute calculated for downstream P2P, A21 is the average bandwidth rate within the set minute calculated for upstream HTTP, A22 is the average bandwidth rate within the set minute calculated for upstream FTP, A23 is the average bandwidth rate within the set minute calculated for upstream P2P, A3 is the speed limit value for allocated resources, B1 is the average delay within the set minute, C1 is the average packet loss rate within the set minute, D1 is the average first packet time within the set minute, E1 is the average retransmission rate within the set minute, and F1 is the average home page opening time for a preset number of times; Among them, P1-P6 are business weight constants, and each weight value is pre-set into the script according to different businesses.

2. A method for testing edge computing node bandwidth according to claim 1, characterized in that: The reallocation judgment includes: Compare the preset verification application business computing resource threshold with the remaining computing resources of the currently applied allocation node, cancel the computing resource node request that is less than the verification application business resource threshold, and do not perform subsequent resource allocation operations; Sort the computing resource requests for verifying the application business requests from largest to smallest, and make a judgment on the allocation of computing resource requests in sequence; If the verification application service calculation resource allocation is successful, then the link bandwidth resource allocation requested by the verification application service is performed; If at this time, the allocation of one of the computing resources or link bandwidth resources of the verification application service fails, the verification application service application that failed to be allocated will be revoked, and the allocation failure information will be returned to the edge cloud platform.

3. The edge computing node bandwidth testing method according to claim 1, characterized in that: The method further comprises: The resource tests for verifying application services are divided into three categories: single-line single thread, single-line multi-thread, and multi-line multi-thread. The three types of application tests request computing resources and bandwidth resource matching from small to large; If the application business computing resources and bandwidth resource allocation are verified successfully, three types of bandwidth rate application scenario verification will be carried out according to the requirements and the test will be performed according to the preset test process.

4. The edge computing node bandwidth testing method according to claim 1, characterized in that: The testing process includes: Prepare the test environment; Use the self-compiled test scripts of the corresponding services to test whether the comprehensive performance of the line uplink and downlink rates meets the standards; If the test passes, the test results are recorded and a test report is generated. If the test fails, the operator is informed to investigate the cause and handle the problem.

5. The edge computing node bandwidth testing method according to claim 1, characterized in that: Test the comprehensive performance of upstream and downstream bandwidth rates based on the self-compiled test script to see if they meet the standards, including: When the comprehensive performance index N is greater than 80%, the bandwidth rate is actually available and meets the basic standard. When N is greater than 90%, a comprehensive rating is given based on the service type.

6. The edge computing node bandwidth testing method according to claim 1, characterized in that: The edge cloud platform manages edge computing node servers, and each edge computing node server communicates with the Internet client terminal through the Internet dedicated line bandwidth or PPPOE bandwidth.

7. An edge computing node bandwidth testing system, characterized in that: The system comprises: The test resource allocation module is used to determine whether the remaining computing resources of the edge computing node meet the minimum resource requirements of the verification application; If satisfied, computing resources are allocated according to the computing resource allocation request of the verification application business; If the computing resource allocation of the verification application service is successful, broadband resource allocation is performed according to the link bandwidth resource allocation request of the verification application service. If the allocation fails, a reallocation judgment is performed; The test module is used to verify that the computing resources and link bandwidth resources requested by the application service are successfully allocated, and then test whether the comprehensive performance of the upstream and downstream bandwidth rates meets the standards based on the self-compiled test script; Test the comprehensive performance of upstream and downstream bandwidth rates based on the self-compiled test script to see if they meet the standards, including: The comprehensive performance is calculated based on the comprehensive performance calculation model, and the comprehensive performance calculation model is: N=[(A11*4 / 10+A12*2 / 10+A13*4 / 10)*1 / 4+(A21*4 / 10+A22*2 / 10+A23*4 / 10)*3 / 4] / A3*P1+(10 -B1) / 10*P2+(0.05-C1) / 0.05*P3+(10-D1) / 10*P4+(0.05-E1) / 0.05*P5+(5000-F1) / 5000*P6; Among them, A11 is the average bandwidth rate within the set minute calculated for downstream HTTP, A12 is the average bandwidth rate within the set minute calculated for downstream FTP, A13 is the average bandwidth rate within the set minute calculated for downstream P2P, A21 is the average bandwidth rate within the set minute calculated for upstream HTTP, A22 is the average bandwidth rate within the set minute calculated for upstream FTP, A23 is the average bandwidth rate within the set minute calculated for upstream P2P, A3 is the speed limit value for allocated resources, B1 is the average delay within the set minute, C1 is the average packet loss rate within the set minute, D1 is the average first packet time within the set minute, E1 is the average retransmission rate within the set minute, and F1 is the average home page opening time for a preset number of times; Among them, P1-P6 are business weight constants, and each weight value is pre-set into the script according to different businesses.

8. A computer storage medium, characterized in that: The computer storage medium includes one or more program instructions, and the one or more program instructions are used to be executed by an edge computing node bandwidth testing system according to any one of claims 1 to 6.

Images