A network service performance monitoring method, device, equipment and storage medium

Abstract

The application discloses a network service performance monitoring method and device, equipment and a storage medium. The application can combine the response time of each full-network traffic distribution service request, the response time of each full-network network information service request, the response time of each single-user traffic distribution service request and the response time of each single-user network information service request, establish a network service performance evaluation index system to monitor the performance status of the network service, realize fine monitoring of the performance status of each user, and accurately locate performance abnormal problems when the network service performance status is abnormal.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for monitoring network service performance. Background Technology

[0002] Network service performance directly impacts user experience. The network architecture of network services is typically deployed in the order of "traffic distribution service node → server node → network information service node → server node → traffic distribution service node," with the traffic distribution service node being the first node at the network entry point and the last node at the network exit point. Most existing network service performance monitoring methods are limited to monitoring the traffic distribution service node itself. For example, Huawei Cloud's traffic distribution service only provides coarse-grained monitoring items such as concurrent connections and network layer 7 protocols. This means the monitoring results only reflect the overall performance of the network service, failing to provide granular monitoring of individual user performance or accurately pinpoint performance anomalies when they occur. Summary of the Invention

[0003] To overcome the shortcomings of existing technologies, this invention provides a network service performance monitoring method, apparatus, and device, which can establish a network service performance evaluation index system to monitor the performance status of network services, achieve refined monitoring of the performance status of each user, and accurately locate performance anomalies when network service performance is abnormal.

[0004] To address the aforementioned technical problems, in a first aspect, an embodiment of the present invention provides a method for monitoring network service performance, comprising:

[0005] Based on the response time of each network traffic distribution service request, the average response time of the network traffic distribution service is obtained, and based on the response time of each network information service request, the average response time of the network information service is obtained.

[0006] Based on the response time of each individual user traffic distribution service request, the average response time of the individual user traffic distribution service is obtained, and based on the response time of each individual user network information service request, the average response time of the individual user network information service is obtained.

[0007] The traffic distribution service latency index value is obtained based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service.

[0008] The network information service latency index value is obtained based on the average response time of the entire network information service and the average response time of the single user network information service.

[0009] Using the latency index of the traffic distribution service and the latency index of the network information service as network service performance evaluation indicators, the network service performance is monitored to obtain network service performance monitoring results.

[0010] Furthermore, the step of obtaining the average response time of the entire network traffic distribution service based on the response time of each request for the entire network traffic distribution service, and obtaining the average response time of the entire network information service based on the response time of each request for the entire network information service, specifically involves:

[0011] All network traffic distribution service requests are obtained, and all network traffic distribution service requests are divided into several network traffic distribution service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the network traffic distribution service based on the total number of all network traffic distribution service requests in each network traffic distribution service request set and the total number of all network traffic distribution service requests.

[0012] All network information service requests are obtained, and all network information service requests are divided into several network information service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the network information service based on the total number of all network information service requests in each network information service request set and the total number of all network information service requests.

[0013] Furthermore, the average response time of the network-wide traffic distribution service is:

[0014] TotalAvgTime x =(n1) x ·w1 x +n2 x ·w2 x +...+n m x ·w m x +...+n M x ·w M x ) / n totalx ;

[0015] Among them, TotalAvgTime x n1 represents the average response time of the network-wide traffic distribution service. x n2 x ... n m x ... n M xw1 represents the total number of all network traffic distribution service requests in each of the aforementioned network traffic distribution service request sets. x w2 x ... w m x ... w M x Each of these represents a weight corresponding to the total number of network traffic distribution service requests in each of the aforementioned network traffic distribution service request sets, m = {1, 2, ..., M}, where M is the total number of all the aforementioned network traffic distribution service request sets, and n... total x The total number of all network-wide traffic distribution service requests;

[0016] The average response time for the entire network information service is:

[0017] TotalAvgTime y =(n1) y ·w1 y +n2 y ·w2 y +...+n m y ·w m y +...+n M y ·w M y ) / n total y ;

[0018] Among them, TotalAvgTime y n1 represents the average response time of the entire network information service. y n2 y ... n m y ... n M y w1 represents the total number of all network information service requests in each of the aforementioned network information service request sets. y w2 y ... w m y ... w M y Each of these represents a weight corresponding to the total number of network information service requests in each of the aforementioned network information service request sets, m = {1, 2, ..., M}, where M is the total number of all network information service request sets, and n... total y This represents the total number of all network information service requests received across the entire network.

[0019] Furthermore, the step of obtaining the average response time of the single-user traffic distribution service based on the response time of each single-user traffic distribution service request, and obtaining the average response time of the single-user network information service based on the response time of each single-user network information service request, specifically involves:

[0020] All single-user traffic distribution service requests are obtained, and all single-user traffic distribution service requests are divided into several single-user traffic distribution service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the single-user traffic distribution service based on the total number of all single-user traffic distribution service requests in each single-user traffic distribution service request set and the total number of all single-user traffic distribution service requests.

[0021] All single-user network information service requests are obtained, and all single-user network information service requests are divided into several single-user network information service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the single-user network information service based on the total number of single-user network information service requests in each single-user network information service request set and the total number of all single-user network information service requests.

[0022] Furthermore, the average response time of the single-user traffic distribution service is:

[0023]

[0024] Among them, AvgTime x The average response time for the single-user traffic distribution service. These represent the total number of all single-user traffic distribution service requests in each of the aforementioned single-user traffic distribution service request sets. Each of these is a weight corresponding to the total number of single-user traffic distribution service requests in each of the single-user traffic distribution service request sets, where m = {1, 2, ..., M}, and M is the total number of all single-user traffic distribution service request sets. The total number of all single-user traffic distribution service requests;

[0025] The average response time for the single-user network information service is:

[0026]

[0027] Among them, AvgTime y The average response time for the single-user network information service. These represent the total number of all single-user network information service requests in each of the aforementioned single-user network information service request sets. Each of these represents a weight corresponding to the total number of single-user network information service requests in each of the aforementioned single-user network information service request sets, where m = {1, 2, ..., M}, and M is the total number of all the aforementioned single-user network information service request sets. This represents the total number of all single-user network information service requests.

[0028] Furthermore, the latency metric for the traffic distribution service is:

[0029] AverageRound x =AvgTime x / TotalAvgTime x ;

[0030] Among them, AverageRound x TotalAvgTime is the latency metric for traffic distribution services. x AvgTime is the average response time of the network-wide traffic distribution service. x The average response time for the single-user traffic distribution service;

[0031] The network information service latency index value is:

[0032] AverageRound y =AvgTime y / TotalAvgTime y ;

[0033] Among them, AverageRound y TotalAvgTime is the latency metric value for the network information service. y AvgTime is the average response time of the entire network information service. y The average response time for the single-user network information service.

[0034] Furthermore, the step of using the traffic distribution service latency index and the network information service latency index as network service performance evaluation indicators to monitor network service performance and obtain network service performance monitoring results specifically involves:

[0035] When the latency index of the traffic distribution service is greater than the first preset threshold and the latency index of the network information service is not greater than the second preset threshold, the network service performance monitoring result is a network anomaly of the network service.

[0036] When the latency index of the traffic distribution service is not greater than the first preset threshold and the latency index of the network information service is greater than the second preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal.

[0037] When the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is less than the third preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal.

[0038] When the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is not less than the third preset threshold, the network service performance monitoring result is that the firewall and reverse proxy of the network service are abnormal.

[0039] Furthermore, after using the traffic distribution service latency index and the network information service latency index as network service performance evaluation indicators to monitor network service performance and obtain network service performance monitoring results, the method further includes:

[0040] When the network service performance monitoring result indicates that the network service's business program is abnormal, packet capture analysis is performed on the network service's business program.

[0041] When the network service performance monitoring results indicate that the firewall and reverse proxy of the network service are abnormal, packet capture analysis is performed on the firewall and reverse proxy of the network service respectively.

[0042] Secondly, an embodiment of the present invention provides a network service performance monitoring device, comprising:

[0043] The module for obtaining the average response time of the entire network service is used to obtain the average response time of the entire network traffic distribution service based on the response time of each request for the entire network traffic distribution service, and to obtain the average response time of the entire network information service based on the response time of each request for the entire network information service.

[0044] The module for obtaining the average response time of a single-user service is used to obtain the average response time of a single-user traffic distribution service based on the response time of each single-user traffic distribution service request, and to obtain the average response time of a single-user network information service based on the response time of each single-user network information service request.

[0045] The traffic distribution service latency indicator acquisition module is used to obtain the traffic distribution service latency indicator value based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service.

[0046] The network information service latency indicator acquisition module is used to obtain the network information service latency indicator value based on the average response time of the network-wide network information service and the average response time of the single-user network information service.

[0047] The network service performance monitoring module is used to monitor the network service performance by using the traffic distribution service latency index value and the network information service latency index value as network service performance evaluation indicators, and to obtain network service performance monitoring results.

[0048] Thirdly, one embodiment of the present invention provides a network service performance monitoring device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. The memory is coupled to the processor, and the processor implements the network service performance monitoring method as described above when executing the computer program.

[0049] Fourthly, one embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program; wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the network service performance monitoring method described above.

[0050] Fifthly, one embodiment of the present invention provides a computer program product that, when run on a computer, causes the computer to execute the network service performance monitoring method described above.

[0051] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0052] The average response time of the entire network traffic distribution service is obtained based on the response time of each request for the entire network traffic distribution service. Similarly, the average response time of the entire network information service is obtained based on the response time of each request for the entire network traffic distribution service. The average response time of the individual user traffic distribution service is obtained based on the response time of each request for the individual user traffic distribution service. Finally, the latency index value of the traffic distribution service is obtained based on the average response time of the entire network traffic distribution service and the average response time of the individual user traffic distribution service. The response time is used to obtain the network information service latency index value. Using the traffic distribution service latency index value and the network information service latency index value as network service performance evaluation indicators, the network service performance is monitored to obtain network service performance monitoring results. This allows for the establishment of a network service performance evaluation index system by combining the response times of each network-wide traffic distribution service request, each network-wide network information service request, each individual user traffic distribution service request, and each individual user network information service request. This enables refined monitoring of the performance status of individual users and accurate location of performance anomalies when network service performance is abnormal. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating a network service performance monitoring method according to the first embodiment of the present invention;

[0054] Figure 2 This is a schematic diagram of the network architecture of an example SaaS product in the first embodiment of the present invention;

[0055] Figure 3 This is a schematic diagram of a network service performance monitoring device according to the second embodiment of the present invention. Detailed Implementation

[0056] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0057] It should be noted that the step numbers in this document are only for the convenience of explaining the specific embodiments and are not intended to limit the order in which the steps are executed. The method provided in this embodiment can be executed by relevant terminal devices, and the following description uses an operation and maintenance terminal as the execution subject.

[0058] like Figure 1 As shown, the first embodiment provides a network service performance monitoring method, including steps S1 to S5:

[0059] S1. Based on the response time of each network traffic distribution service request, obtain the average response time of the network traffic distribution service, and based on the response time of each network information service request, obtain the average response time of the network information service.

[0060] S2. Based on the response time of each individual user traffic distribution service request, obtain the average response time of the individual user traffic distribution service, and based on the response time of each individual user network information service request, obtain the average response time of the individual user network information service.

[0061] S3. Based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service, obtain the traffic distribution service latency index value.

[0062] S4. Based on the average response time of the entire network information service and the average response time of the single user network information service, obtain the network information service latency index value.

[0063] S5. Using the latency index of traffic distribution service and the latency index of network information service as network service performance evaluation indicators, network service performance is monitored to obtain network service performance monitoring results.

[0064] As an example, the network architecture of network services, such as SaaS (Software as a Service) products, is basically based on... Figure 2 The sequential node deployment shown is in Figure 2 In this context, ELB (Elastic Load Balance) is a traffic distribution service that distributes access traffic to multiple backend servers according to allocation policies; WAF (Web Application Firewall) is a product that specifically protects web applications by implementing a series of security policies for HTTP / HTTPS, essentially a firewall; a reverse proxy is a proxy server that receives connection requests from the internet, forwards the requests to servers on the internal network, and returns the results from the servers to the clients that requested the connection on the internet, in which case the proxy server appears as a single server to the outside world; IIS (Internet Information Services) is a network information service provided by Microsoft that runs on Microsoft Windows.

[0065] Depend on Figure 2 As we can see, the traffic distribution service is the first node at the network ingress and the last node at the network egress. Monitoring results for the traffic distribution service can accurately represent the response time of the entire business chain, reflecting the overall performance of the business. The network information service, as the last node at the business program ingress and the first node at the business program egress, allows monitoring results to accurately pinpoint whether performance anomalies originate from network nodes within the network service or from the business program. The response time of the traffic distribution service to a single user's request reflects the server's processing performance, excluding network latency. The response time of the network information service to a request reflects the processing performance of the business program. The greater the difference between the response times of the traffic distribution service and the network information service for the same request, the worse the processing performance of the firewall and reverse proxy between the traffic distribution service and the network information service.

[0066] In step S1, all network traffic distribution service logs are obtained, and each network traffic distribution service request is extracted from each network traffic distribution service log to obtain all network traffic distribution service requests. The average response time of the network traffic distribution service is calculated based on the response time of each network traffic distribution service request.

[0067] Similarly, obtain all network information service logs across the entire network, extract each network information service request from each log, obtain all network information service requests, and calculate the average response time of the network information service based on the response time of each request.

[0068] In step S2, for any user, all single-user traffic distribution service logs are obtained, and each single-user traffic distribution service request is extracted from each single-user traffic distribution service log to obtain all single-user traffic distribution service requests. The average response time of the single-user traffic distribution service is calculated based on the response time of each single-user traffic distribution service request.

[0069] Similarly, for this user, all single-user network information service logs are obtained, and each single-user network information service request is extracted from each single-user network information service log to obtain all single-user network information service requests. The average response time of the single-user network information service is calculated based on the response time of each single-user network information service request.

[0070] It is understandable that the network-wide traffic distribution service request / network information service request is the sum of the network-wide traffic distribution service request / network information service request data, while the single-user traffic distribution service request / network information service request only corresponds to the calculation of the traffic distribution service / network information service request data of a single user.

[0071] In step S3, the latency index value of traffic distribution service is calculated based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service.

[0072] In step S4, the network information service latency index value is obtained by calculating based on the average response time of the network information service across the entire network and the average response time of the network information service for a single user.

[0073] In step S5, the latency index values ​​of traffic distribution service and network information service are used as network service performance evaluation indicators to monitor the network service performance and obtain the network service performance monitoring results.

[0074] It is understood that the network service performance monitoring method provided in this embodiment can be executed in real time or at regular intervals, thereby monitoring the performance of network services in real time or at regular intervals.

[0075] This embodiment can combine the response time of each network-wide traffic distribution service request, the response time of each network-wide network information service request, the response time of each individual user traffic distribution service request, and the response time of each individual user network information service request to establish a network service performance evaluation index system to monitor the performance status of network services, achieve fine-grained monitoring of the performance status of each user, and accurately locate performance anomalies when network service performance is abnormal.

[0076] In a preferred embodiment, the step of obtaining the average response time of the entire network traffic distribution service based on the response time of each entire network traffic distribution service request, and obtaining the average response time of the entire network information service based on the response time of each entire network information service request, specifically involves: acquiring all entire network traffic distribution service requests, dividing all entire network traffic distribution service requests into several sets of entire network traffic distribution service requests according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the entire network traffic distribution service based on the total number of all entire network traffic distribution service requests in each set and the total number of all entire network traffic distribution service requests; acquiring all entire network information service requests, dividing all entire network information service requests into several sets of entire network information service requests according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the entire network information service based on the total number of all entire network information service requests in each set and the total number of all entire network information service requests.

[0077] In the preferred embodiment, the average response time of the network-wide traffic distribution service is:

[0078] TotalAvgTimex =(n1) x ·w1 x +n2 x ·w2 x +...+n m x ·w m x +...+n M x ·w M x ) / n total x (1);

[0079] Among them, TotalAvgTime x n1 is the average response time for the network-wide traffic distribution service. x n2 x ... n m x ... n M x w1 represents the total number of all network traffic distribution service requests in each network traffic distribution service request set. x w2 x ... w m x ... w M x These are the weights corresponding to the total number of network traffic distribution service requests in each network traffic distribution service request set, m = {1, 2, ..., M}, where M is the total number of all network traffic distribution service request sets, and n is the weight. total x The total number of all network traffic distribution service requests;

[0080] The average response time for network information services across the entire network is:

[0081] TotalAvgTime y =(n1) y ·w1 y +n2 y ·w2 y +...+n m y ·w m y +...+n M y ·w M y ) / n total y (2);

[0082] Among them, TotalAvgTimey n1 represents the average response time of network information services across the entire network. y n2 y ... n m y ... n M y w1 represents the total number of all network information service requests in each set of network information service requests. y w2 y ... w m y ... w M y Let m = {1, 2, ..., M}, where M is the total number of all network information service requests in each set of network information service requests, and n is the weight corresponding to the total number of network information service requests in each set of network information service requests. total y This represents the total number of all network information service requests across the entire network.

[0083] As an example, several preset response time ranges are defined in advance, all network traffic distribution service requests are obtained, the total number of all network traffic distribution service requests is determined, and based on the response time of all network traffic distribution service requests, all network traffic distribution service requests are divided into several network traffic distribution service request sets according to several preset response time ranges, and the total number of all network traffic distribution service requests in each network traffic distribution service request set is determined.

[0084] For several preset response time ranges, the weights corresponding to each preset response time range are predefined. A weighted average algorithm is used to calculate the average response time of the network traffic distribution service based on the total number of all network traffic distribution service requests in each network traffic distribution service request set.

[0085] Similarly, obtain all network information service requests across the entire network, determine the total number of all network information service requests across the entire network, divide all network information service requests across the entire network into several sets of network information service requests across the entire network according to several preset response time ranges, and determine the total number of all network information service requests across the entire network in each set of network information service requests across the entire network.

[0086] A weighted average algorithm is used to calculate the average response time of the entire network information service based on the total number of all network information service requests in each set of network information service requests.

[0087] Since all network traffic distribution service requests and all network information service requests are uniformly divided into datasets according to several predefined preset response time ranges, the total number of all network traffic distribution service request sets is equal to the total number of all network information service request sets.

[0088] Suppose we predefine six preset response time ranges, which are (0,300]ms, (300,500]ms, (500,1000]ms, (1000,2000]ms, (2000,8000]ms, and (8000,+∞]ms, respectively, and predefine the weights corresponding to these six preset response time ranges, which are 300, 500, 1000, 2000, 8000, and 8000, respectively.

[0089] In this case, based on equation (1), the average response time of the network-wide traffic distribution service is:

[0090]

[0091] In equation (3), TotalAvgTime x n1 is the average response time for the network-wide traffic distribution service. x n2 x n3 x n4 x n5 x n6 x n represents the total number of all network traffic distribution service requests in these 6 sets of network traffic distribution service requests. total x This represents the total number of all network traffic distribution service requests.

[0092] Based on equation (2), the average response time of the entire network information service is:

[0093] TotalAvgTime y =(300n1) y +500n2 y +1000n3 y +2000n4 y +8000n5 y +8000n6 y ) / n total y (4);

[0094] In equation (4), TotalAvgTime y n1 represents the average response time of network information services across the entire network. y n2 y n3y n4 y n5 y n6 y Let n be the total number of all network information service requests in each set of network information service requests. total y This represents the total number of all network information service requests across the entire network.

[0095] This embodiment first divides all network traffic distribution service / network information service requests into datasets, and then uses a weighted average algorithm to calculate the average response time of the network traffic distribution service / network information service based on the total number of all network traffic distribution service / network information service requests in each set. This improves the calculation speed of the average response time of the network traffic distribution service / network information service and is beneficial to improving the performance monitoring efficiency of SaaS products.

[0096] In a preferred embodiment, the step of obtaining the average response time of a single-user traffic distribution service based on the response time of each single-user traffic distribution service request, and obtaining the average response time of a single-user network information service based on the response time of each single-user network information service request, specifically involves: acquiring all single-user traffic distribution service requests, dividing all single-user traffic distribution service requests into several single-user traffic distribution service request sets according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the single-user traffic distribution service based on the total number of single-user traffic distribution service requests in each single-user traffic distribution service request set and the total number of single-user traffic distribution service requests in each single-user traffic distribution service request set; acquiring all single-user network information service requests, dividing all single-user network information service requests into several single-user network information service request sets according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the single-user network information service based on the total number of single-user network information service requests in each single-user network information service request set and the total number of single-user network information service requests in each single-user network information service request set.

[0097] In a preferred embodiment, the average response time for the single-user traffic distribution service is:

[0098]

[0099] Among them, AvgTime x Average response time for single-user traffic distribution service. These represent the total number of all single-user traffic distribution service requests in each single-user traffic distribution service request set. These are the weights corresponding to the total number of single-user traffic distribution service requests in each single-user traffic distribution service request set, where m = {1, 2, ..., M}, and M is the total number of all single-user traffic distribution service request sets. The total number of service requests distributed across all single-user traffic;

[0100] The average response time for a single-user network information service is:

[0101]

[0102] Among them, AvgTime y The average response time for a single-user network information service. These represent the total number of all single-user network information service requests in each single-user network information service request set. Let m = {1, 2, ..., M}, where M is the total number of all single-user network information service requests in each single-user network information service request set, and n is the weight corresponding to the total number of single-user network information service requests in each single-user network information service request set. t ′ otal y This represents the total number of all single-user network information service requests.

[0103] As an example, several preset response time ranges are defined in advance, all single-user traffic distribution service requests are obtained, the total number of all single-user traffic distribution service requests is determined, and based on the response time of all single-user traffic distribution service requests, all single-user traffic distribution service requests are divided into several single-user traffic distribution service request sets according to several preset response time ranges, and the total number of all single-user traffic distribution service requests in each single-user traffic distribution service request set is determined.

[0104] For several preset response time ranges, the weights corresponding to each preset response time range are predefined. A weighted average algorithm is used to calculate the average response time of the single-user traffic distribution service based on the total number of all single-user traffic distribution service requests in each single-user traffic distribution service request set.

[0105] Similarly, obtain all single-user network information service requests, determine the total number of all single-user network information service requests, divide all single-user network information service requests into several single-user network information service request sets according to several preset response time ranges, and determine the total number of all single-user network information service requests in each single-user network information service request set.

[0106] A weighted average algorithm is used to calculate the average response time of a single-user network information service based on the total number of all single-user network information service requests in each single-user network information service request set.

[0107] Since all network-wide traffic distribution service requests, all network-wide network information service requests, all single-user traffic distribution service requests, and all single-user network information service requests are uniformly divided into datasets according to several predefined preset response time ranges, the total number of all network-wide traffic distribution service request sets, the total number of all network-wide network information service request sets, the total number of all single-user traffic distribution service request sets, and the total number of all single-user network information service request sets are all equal.

[0108] Suppose we predefine six preset response time ranges, which are (0,300]ms, (300,500]ms, (500,1000]ms, (1000,2000]ms, (2000,8000]ms, and (8000,+∞]ms, respectively, and predefine the weights corresponding to these six preset response time ranges, which are 300, 500, 1000, 2000, 8000, and 8000, respectively.

[0109] In this case, based on equation (5), the average response time of the single-user traffic distribution service is:

[0110]

[0111] In formula (7), AvgTime x Average response time for single-user traffic distribution service. These represent the total number of all single-user traffic distribution service requests in these six single-user traffic distribution service request sets. The total number of service requests distributed across all single-user traffic.

[0112] Based on equation (2), the average response time for a single-user network information service is:

[0113]

[0114] In formula (8), AvgTime y The average response time for a single-user network information service. These represent the total number of all single-user network information service requests within these six single-user network information service request sets. This represents the total number of all single-user network information service requests.

[0115] This embodiment first divides all single-user traffic distribution service / network information service requests into datasets, and then uses a weighted average algorithm to calculate the average response time of single-user traffic distribution service / network information service based on the total number of single-user traffic distribution service / network information service requests in each single-user traffic distribution service / network information service request set and the total number of single-user traffic distribution service / network information service requests. This improves the calculation speed of the average response time of single-user traffic distribution service / network information service and is beneficial to improving the efficiency of network service performance monitoring.

[0116] In the preferred embodiment, the traffic distribution service latency metric is:

[0117] AverageRound x =AvgTime x / TotalAvgTime x (9);

[0118] Among them, AverageRound x TotalAvgTime is the latency metric for traffic distribution services. x AvgTime is the average response time for the network-wide traffic distribution service. x Average response time for single-user traffic distribution service;

[0119] The network information service latency index value is:

[0120] AverageRound y =AvgTime y / TotalAvgTime y (10);

[0121] Among them, AverageRound y TotalAvgTime is a latency metric for network information services. y AvgTime is the average response time for network information services across the entire network. y Average response time for a single-user network information service.

[0122] As an example, when the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service are obtained, the traffic distribution service latency index value is calculated based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service. The traffic distribution service latency index value is:

[0123] AverageRound x =AvgTime x / TotalAvgTimex (9);

[0124] In equation (9), AverageRound x TotalAvgTime is the latency metric for traffic distribution services. x AvgTime is the average response time for the network-wide traffic distribution service. x Average response time for single-user traffic distribution service;

[0125] When the average response time of the entire network information service and the average response time of the single user network information service are obtained, the network information service latency index value is calculated based on the average response time of the entire network information service and the average response time of the single user network information service. The network information service latency index value is:

[0126] AverageRound y =AvgTime y / TotalAvgTime y (10);

[0127] Equation (10), AverageRound y TotalAvgTime is a latency metric for network information services. y AvgTime is the average response time for network information services across the entire network. y Average response time for a single-user network information service.

[0128] It is understandable that the lower the latency index of traffic distribution service, the better the user's performance; the lower the latency index of network information service, the better the user's performance.

[0129] This embodiment combines the response times of each network-wide traffic distribution service request, each network-wide network information service request, each individual user traffic distribution service request, and each individual user network information service request to establish a network service performance evaluation index system to monitor the performance status of network services. This enables refined monitoring of the performance status of each user and accurate location of performance anomalies when network service performance is abnormal.

[0130] In a preferred embodiment, the use of traffic distribution service latency and network information service latency as network service performance evaluation indicators to monitor network service performance and obtain network service performance monitoring results specifically involves: when the traffic distribution service latency is greater than a first preset threshold and the network information service latency is not greater than a second preset threshold, the network service performance monitoring result is a network anomaly; when the traffic distribution service latency is not greater than the first preset threshold and the network information service latency is greater than the second preset threshold, the network service performance monitoring result is a business process anomaly. Normally, when the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is less than the third preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal; when the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is not less than the third preset threshold, the network service performance monitoring result is that the firewall and reverse proxy of the network service are abnormal.

[0131] In a preferred embodiment of this example, the first preset threshold is equal to the second preset threshold.

[0132] As an example, when the traffic distribution service latency index and the network information service latency index are obtained, the traffic distribution service latency index is compared with a first preset threshold, the network information service latency index is compared with a second preset threshold, and the difference between the traffic distribution service latency index and the network information service latency index is compared with a third preset threshold. When the traffic distribution service latency index is greater than the first preset threshold and the network information service latency index is not greater than the second preset threshold, it is considered that the network feedback of the network service is abnormal but the business program feedback is normal, and the network service performance monitoring result is that the network service is abnormal. When the traffic distribution service latency index is not greater than the first preset threshold and the network information service latency index is greater than the second preset threshold, it is considered that the network feedback of the network service is normal but the business program feedback is abnormal, and the network service performance monitoring result is that the business program of the network service is abnormal. When the traffic distribution service latency index is greater than the first preset threshold, the network information service latency index is greater than the second preset threshold, and the difference between the traffic distribution service latency index and the network information service latency index is less than the third preset threshold, it is considered that both the network and the business program of the network service are abnormal, but the abnormal values ​​are close. Figure 2The network service performance anomaly was determined to be caused not by the network entry point, but by a problem with the business program. The network service performance monitoring result indicated an anomaly in the network service's business program. When the traffic distribution service latency index value exceeded the first preset threshold, the network information service latency index value exceeded the second preset threshold, and the difference between the traffic distribution service latency index value and the network information service latency index value was not less than the third preset threshold, it was considered that both the network and business programs of the network service were reporting anomalies, but the differences in the anomaly values ​​were significant. Figure 2 The network service performance anomaly was determined to originate from the network service's firewall and reverse proxy, and the network service performance monitoring results indicated that the network service's firewall and reverse proxy were abnormal.

[0133] This embodiment can combine the response time of each network-wide traffic distribution service request, the response time of each network-wide network information service request, the response time of each individual user traffic distribution service request, and the response time of each individual user network information service request to establish a network service performance evaluation index system to monitor the performance status of network services, achieve fine-grained monitoring of the performance status of each user, and accurately locate performance anomalies when network service performance is abnormal.

[0134] In a preferred embodiment, after using the traffic distribution service latency index and the network information service latency index as network service performance evaluation indicators to monitor the network service performance and obtain the network service performance monitoring results, the method further includes: when the network service performance monitoring result indicates that the network service's business program is abnormal, performing packet capture analysis on the network service's business program; and when the network service performance monitoring result indicates that the network service's firewall and reverse proxy are abnormal, performing packet capture analysis on the network service's firewall and reverse proxy respectively.

[0135] As an example, when the network service performance monitoring result indicates that the business program of the network service is abnormal, packet capture analysis is performed on the business program of the network service. Specifically, a dump can be captured and sent to the R&D terminal, which can then analyze the logic of the business program code and make adjustments and optimizations until the latest obtained traffic distribution service latency index value is not greater than the first preset threshold and the network information service latency index value is not greater than the second preset threshold, meaning that no network service performance abnormality problem has been monitored.

[0136] When the network service performance monitoring results indicate that the firewall and reverse proxy of the network service are abnormal, packet capture analysis is performed on the firewall and reverse proxy of the network service respectively. Specifically, the data packets captured from the firewall and reverse proxy can be sent to the R&D terminal, which will analyze and repair the performance model until the latest obtained traffic distribution service latency index value is not greater than the first preset threshold and the network information service latency index value is not greater than the second preset threshold, that is, no network service performance abnormality problem is detected.

[0137] This embodiment ensures timely handling of network service performance anomalies by performing packet capture analysis on the network service's business program when the network service performance monitoring result indicates an anomaly, and by performing packet capture analysis on the network service's firewall and reverse proxy when the network service performance monitoring result indicates an anomaly.

[0138] Based on the same inventive concept as the first embodiment, the second embodiment provides as follows: Figure 3 The network service performance monitoring device shown includes: a network-wide service average response time acquisition module 21, used to obtain the network-wide traffic distribution service average response time based on the response time of each network-wide traffic distribution service request, and to obtain the network-wide network information service average response time based on the response time of each network-wide network information service request; and a single-user service average response time acquisition module 22, used to obtain the single-user traffic distribution service average response time based on the response time of each single-user traffic distribution service request, and to obtain the single-user network information service average response time based on the response time of each single-user network information service request. The traffic distribution service latency indicator acquisition module 23 is used to obtain the traffic distribution service latency indicator value based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service; the network information service latency indicator acquisition module 24 is used to obtain the network information service latency indicator value based on the average response time of the network information service and the average response time of the single-user network information service; the network service performance monitoring module 25 is used to use the traffic distribution service latency indicator value and the network information service latency indicator value as network service performance evaluation indicators to monitor the network service performance and obtain the network service performance monitoring results.

[0139] In a preferred embodiment, the step of obtaining the average response time of the entire network traffic distribution service based on the response time of each entire network traffic distribution service request, and obtaining the average response time of the entire network information service based on the response time of each entire network information service request, specifically involves: acquiring all entire network traffic distribution service requests, dividing all entire network traffic distribution service requests into several sets of entire network traffic distribution service requests according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the entire network traffic distribution service based on the total number of all entire network traffic distribution service requests in each set and the total number of all entire network traffic distribution service requests; acquiring all entire network information service requests, dividing all entire network information service requests into several sets of entire network information service requests according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the entire network information service based on the total number of all entire network information service requests in each set and the total number of all entire network information service requests.

[0140] In the preferred embodiment, the average response time of the network-wide traffic distribution service is:

[0141] TotalAvgTime x =(n1) x ·w1 x +n2 x ·w2 x +...+n m x ·w m x +...+n M x ·w M x ) / n total x (11);

[0142] Among them, TotalAvgTime x n1 is the average response time for the network-wide traffic distribution service. x n2 x ... n m x ... n M x w1 represents the total number of all network traffic distribution service requests in each network traffic distribution service request set. x w2 x ... w m x ... w M xThese are the weights corresponding to the total number of network traffic distribution service requests in each network traffic distribution service request set, m = {1, 2, ..., M}, where M is the total number of all network traffic distribution service request sets, and n is the weight. total x The total number of all network traffic distribution service requests;

[0143] The average response time for network information services across the entire network is:

[0144] TotalAvgTime y =(n1) y ·w1 y +n2 y ·w2 y +...+n m y ·w m y +...+n M y ·w M y ) / n total y (12);

[0145] Among them, TotalAvgTime y n1 represents the average response time of network information services across the entire network. y n2 y ... n m y ... n M y w1 represents the total number of all network information service requests in each set of network information service requests. y w2 y ... w m y ... w M y Let m = {1, 2, ..., M}, where M is the total number of all network information service requests in each set of network information service requests, and n is the weight corresponding to the total number of network information service requests in each set of network information service requests. total y This represents the total number of all network information service requests across the entire network.

[0146] In a preferred embodiment, the step of obtaining the average response time of a single-user traffic distribution service based on the response time of each single-user traffic distribution service request, and obtaining the average response time of a single-user network information service based on the response time of each single-user network information service request, specifically involves: acquiring all single-user traffic distribution service requests, dividing all single-user traffic distribution service requests into several single-user traffic distribution service request sets according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the single-user traffic distribution service based on the total number of single-user traffic distribution service requests in each single-user traffic distribution service request set and the total number of single-user traffic distribution service requests in each single-user traffic distribution service request set; acquiring all single-user network information service requests, dividing all single-user network information service requests into several single-user network information service request sets according to several preset response time ranges, and using a weighted average algorithm to calculate the average response time of the single-user network information service based on the total number of single-user network information service requests in each single-user network information service request set and the total number of single-user network information service requests in each single-user network information service request set.

[0147] In a preferred embodiment, the average response time for the single-user traffic distribution service is:

[0148]

[0149] Among them, AvgTime x Average response time for single-user traffic distribution service. These represent the total number of all single-user traffic distribution service requests in each single-user traffic distribution service request set. These are the weights corresponding to the total number of single-user traffic distribution service requests in each single-user traffic distribution service request set, where m = {1, 2, ..., M}, and M is the total number of all single-user traffic distribution service request sets. The total number of service requests distributed across all single-user traffic;

[0150] The average response time for a single-user network information service is:

[0151]

[0152] Among them, AvgTime y The average response time for a single-user network information service. These represent the total number of all single-user network information service requests in each single-user network information service request set. Let m = {1, 2, ..., M}, where M is the total number of all single-user network information service requests in each single-user network information service request set. This represents the total number of all single-user network information service requests.

[0153] In the preferred embodiment, the traffic distribution service latency metric is:

[0154] AverageRound x =AvgTime x / TotalAvgTime x (15);

[0155] Among them, AverageRound x TotalAvgTime is the latency metric for traffic distribution services. x AvgTime is the average response time for the network-wide traffic distribution service. x Average response time for single-user traffic distribution service;

[0156] The network information service latency index value is:

[0157] AverageRound y =AvgTime y / TotalAvgTime y (16);

[0158] Among them, AverageRound y TotalAvgTime is a latency metric for network information services. y AvgTime is the average response time for network information services across the entire network. y Average response time for a single-user network information service.

[0159] In a preferred embodiment, the use of traffic distribution service latency and network information service latency as network service performance evaluation indicators to monitor network service performance and obtain network service performance monitoring results specifically involves: when the traffic distribution service latency is greater than a first preset threshold and the network information service latency is not greater than a second preset threshold, the network service performance monitoring result is a network anomaly; when the traffic distribution service latency is not greater than the first preset threshold and the network information service latency is greater than the second preset threshold, the network service performance monitoring result is a business process anomaly. Normally, when the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is less than the third preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal; when the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is not less than the third preset threshold, the network service performance monitoring result is that the firewall and reverse proxy of the network service are abnormal.

[0160] In a preferred embodiment, after using the traffic distribution service latency index and the network information service latency index as network service performance evaluation indicators to monitor the network service performance and obtain the network service performance monitoring results, the method further includes: when the network service performance monitoring result indicates that the network service's business program is abnormal, performing packet capture analysis on the network service's business program; and when the network service performance monitoring result indicates that the network service's firewall and reverse proxy are abnormal, performing packet capture analysis on the network service's firewall and reverse proxy respectively.

[0161] Based on the same inventive concept as the first embodiment, the third embodiment provides a network service performance monitoring device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. The memory is coupled to the processor, and when the processor executes the computer program, it implements the network service performance monitoring method as described in the first embodiment and achieves the same beneficial effects.

[0162] Based on the same inventive concept as the first embodiment, the fourth embodiment provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the network service performance monitoring method as described in the first embodiment, and can achieve the same beneficial effects.

[0163] Based on the same inventive concept as the first embodiment, the fifth embodiment provides a computer program product that, when run on a computer, causes the computer to execute the network service performance monitoring method as described in the first embodiment, and achieves the same beneficial effects.

[0164] In summary, implementing the embodiments of the present invention has the following beneficial effects:

[0165] The average response time of the entire network traffic distribution service is obtained based on the response time of each request for the entire network traffic distribution service. Similarly, the average response time of the entire network information service is obtained based on the response time of each request for the entire network traffic distribution service. The average response time of the individual user traffic distribution service is obtained based on the response time of each request for the individual user traffic distribution service. Finally, the latency index value of the traffic distribution service is obtained based on the average response time of the entire network traffic distribution service and the average response time of the individual user traffic distribution service. The response time is used to obtain the network information service latency index value. Using the traffic distribution service latency index value and the network information service latency index value as network service performance evaluation indicators, the network service performance is monitored to obtain network service performance monitoring results. This allows for the establishment of a network service performance evaluation index system by combining the response times of each network-wide traffic distribution service request, each network-wide network information service request, each individual user traffic distribution service request, and each individual user network information service request. This enables refined monitoring of the performance status of individual users and accurate location of performance anomalies when network service performance is abnormal.

[0166] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

[0167] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

Claims

1. A method for monitoring network service performance, characterized in that, include: Based on the response time of each network traffic distribution service request, the average response time of the network traffic distribution service is obtained, and based on the response time of each network information service request, the average response time of the network information service is obtained. Based on the response time of each individual user traffic distribution service request, the average response time of the individual user traffic distribution service is obtained, and based on the response time of each individual user network information service request, the average response time of the individual user network information service is obtained. Based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service, the traffic distribution service latency index value is obtained, and the traffic distribution service latency index value is: ； in, For traffic distribution service latency metrics, The average response time for the network-wide traffic distribution service. The average response time for the single-user traffic distribution service; Based on the average response time of the entire network information service and the average response time of the single-user network information service, the network information service latency index value is obtained, and the network information service latency index value is: ； in, The latency index value for the aforementioned network information service. The average response time for the entire network information service. The average response time for the single-user network information service; Using the traffic distribution service latency index and the network information service latency index as network service performance evaluation indicators, network service performance is monitored to obtain network service performance monitoring results, including: when the traffic distribution service latency index is greater than a first preset threshold and the network information service latency index is not greater than a second preset threshold, the network service performance monitoring result is a network anomaly of the network service. When the latency index of the traffic distribution service is not greater than the first preset threshold and the latency index of the network information service is greater than the second preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal. When the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is less than the third preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal. When the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is not less than the third preset threshold, the network service performance monitoring result is that the firewall and reverse proxy of the network service are abnormal.

2. The network service performance monitoring method as described in claim 1, characterized in that, The process of obtaining the average response time of the entire network traffic distribution service based on the response time of each request for the entire network traffic distribution service, and obtaining the average response time of the entire network information service based on the response time of each request for the entire network information service, specifically involves: All network traffic distribution service requests are obtained, and all network traffic distribution service requests are divided into several network traffic distribution service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the network traffic distribution service based on the total number of all network traffic distribution service requests in each network traffic distribution service request set and the total number of all network traffic distribution service requests. All network information service requests are obtained, and all network information service requests are divided into several network information service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the network information service based on the total number of all network information service requests in each network information service request set and the total number of all network information service requests.

3. The network service performance monitoring method as described in claim 2, characterized in that, The average response time for the network-wide traffic distribution service is: ； in, The average response time for the network-wide traffic distribution service. These represent the total number of all network traffic distribution service requests in each of the aforementioned network traffic distribution service request sets. These are the weights corresponding to the total number of all network traffic distribution service requests in each of the aforementioned network traffic distribution service request sets. M is the total number of all the aforementioned network-wide traffic distribution service request sets. The total number of all network-wide traffic distribution service requests; The average response time for the entire network information service is: ； in, The average response time for the entire network information service. These represent the total number of all network information service requests in each of the aforementioned network information service request sets. These are the weights corresponding to the total number of all network information service requests in each of the aforementioned network information service request sets. M represents the total number of all network information service request sets. This represents the total number of all network information service requests received across the entire network.

4. The network service performance monitoring method as described in claim 1, characterized in that, The process of obtaining the average response time of the single-user traffic distribution service based on the response time of each single-user traffic distribution service request, and obtaining the average response time of the single-user network information service based on the response time of each single-user network information service request, specifically involves: All single-user traffic distribution service requests are obtained, and all single-user traffic distribution service requests are divided into several single-user traffic distribution service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the single-user traffic distribution service based on the total number of all single-user traffic distribution service requests in each single-user traffic distribution service request set and the total number of all single-user traffic distribution service requests. All single-user network information service requests are obtained, and all single-user network information service requests are divided into several single-user network information service request sets according to several preset response time ranges. A weighted average algorithm is used to calculate the average response time of the single-user network information service based on the total number of single-user network information service requests in each single-user network information service request set and the total number of all single-user network information service requests.

5. The network service performance monitoring method as described in claim 1, characterized in that, After using the traffic distribution service latency index and the network information service latency index as network service performance evaluation indicators to monitor network service performance and obtain network service performance monitoring results, the method further includes: When the network service performance monitoring result indicates that the network service's business program is abnormal, packet capture analysis is performed on the network service's business program. When the network service performance monitoring results indicate that the firewall and reverse proxy of the network service are abnormal, packet capture analysis is performed on the firewall and reverse proxy of the network service respectively.

6. A network service performance monitoring device, characterized in that, include: The module for obtaining the average response time of the entire network service is used to obtain the average response time of the entire network traffic distribution service based on the response time of each request for the entire network traffic distribution service, and to obtain the average response time of the entire network information service based on the response time of each request for the entire network information service. The module for obtaining the average response time of a single-user service is used to obtain the average response time of a single-user traffic distribution service based on the response time of each single-user traffic distribution service request, and to obtain the average response time of a single-user network information service based on the response time of each single-user network information service request. The traffic distribution service latency metric acquisition module is used to obtain the traffic distribution service latency metric value based on the average response time of the network-wide traffic distribution service and the average response time of the single-user traffic distribution service. The traffic distribution service latency metric value is: ； in, For traffic distribution service latency metrics, The average response time for the network-wide traffic distribution service. The average response time for the single-user traffic distribution service; The network information service latency indicator acquisition module is used to obtain the network information service latency indicator value based on the average response time of the entire network information service and the average response time of the single-user network information service. The network information service latency indicator value is: ； in, The latency index value for the aforementioned network information service. The average response time for the entire network information service. The average response time for the single-user network information service; The network service performance monitoring module is used to monitor the network service performance using the traffic distribution service latency index value and the network information service latency index value as network service performance evaluation indicators, and to obtain the network service performance monitoring result, including: when the traffic distribution service latency index value is greater than a first preset threshold and the network information service latency index value is not greater than a second preset threshold, the network service performance monitoring result is a network anomaly of the network service. When the latency index of the traffic distribution service is not greater than the first preset threshold and the latency index of the network information service is greater than the second preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal. When the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is less than the third preset threshold, the network service performance monitoring result is that the business program of the network service is abnormal. When the latency index of the traffic distribution service is greater than the first preset threshold, the latency index of the network information service is greater than the second preset threshold, and the difference between the latency index of the traffic distribution service and the latency index of the network information service is not less than the third preset threshold, the network service performance monitoring result is that the firewall and reverse proxy of the network service are abnormal.

7. A network service performance monitoring device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the memory being coupled to the processor, and the processor implementing the network service performance monitoring method as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program; wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the network service performance monitoring method as described in any one of claims 1 to 5.

Images