CN115914039B - Network performance monitoring device and monitoring method thereof - Google Patents
Network performance monitoring device and monitoring method thereof Download PDFInfo
- Publication number
- CN115914039B CN115914039B CN202211467154.2A CN202211467154A CN115914039B CN 115914039 B CN115914039 B CN 115914039B CN 202211467154 A CN202211467154 A CN 202211467154A CN 115914039 B CN115914039 B CN 115914039B
- Authority
- CN
- China
- Prior art keywords
- network
- monitoring
- user
- performance
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 187
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012806 monitoring device Methods 0.000 title claims abstract description 14
- 230000006399 behavior Effects 0.000 claims abstract description 39
- 238000004088 simulation Methods 0.000 claims abstract description 29
- 230000001934 delay Effects 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 59
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 230000010365 information processing Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 5
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000009960 carding Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims description 3
- 230000037431 insertion Effects 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 34
- 230000003247 decreasing effect Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a network performance monitoring device and a monitoring method thereof, which belong to the field of network performance monitoring, and the invention comprises a user side simulation monitoring module: in the non-working time period of the user, simulating the real behavior of the user, performing service access on the network to be monitored, calculating access time delays of different nodes of the network to be monitored in the simulated access process, and monitoring the network side by the network monitoring module: in the working time period of the user, capturing network data packets of the user accessing the network to be monitored, restoring the access behaviors of different nodes of the network, calculating the time delay of the user accessing of the different nodes in the process, and running a monitoring module by a server-side function: capturing functions executed when a network to be monitored runs, and time consumed by executing different functions, and monitoring the execution efficiency and execution times of the system functions; the invention solves the problem of poor user experience by combining the performance problem perceived by the user with the network monitoring index.
Description
Technical Field
The invention relates to a network performance monitoring device and a monitoring method thereof, belonging to the technical field of network performance monitoring.
Background
Network performance monitoring provides a means to explore network characteristics in a practical environment, and is a process of collecting data from network devices, decoding the data, and analyzing the data. It collects some specific index data from the network and feeds it back to the monitor. These data can be used to analyze network performance, learn network operation dynamics, diagnose possible problems, and even predict "metrics" where problems may occur. This technology is now widely used in commercial and scientific fields. In the business field, network performance monitoring plays an important role in network performance analysis, anomaly monitoring, link state monitoring, capacity planning and the like as part of network management. In the scientific research field, the network performance monitoring technology is a necessary premise and means for realizing specific modeling and analysis.
In the continuous running process of the network, the problem of network performance abnormality caused by network time delay can occur, and the existing monitoring means for network performance are mostly used for monitoring and judging whether the network is time delay or not from the perspective of the network. Rather than from the perspective of the user's real experience. For example, when an end user accesses a network, network data needs to sequentially pass through a plurality of links, and from the perspective of the network, the time delay of each link is normal, but from the perspective of user use experience, the time delay of all links is added up, and the access of the network may be abnormal. Therefore, the existing monitoring means for network performance are more than the time delay upper limit indicating how high the network can reach, the overall state of the network based on user experience cannot be reflected, and the problem of poor user experience cannot be really solved.
Therefore, the existing monitoring of network performance is inconvenient to organically combine the performance problem felt by the user with the network monitoring index, so that the user experience effect is poor.
Disclosure of Invention
The invention aims to solve the technical problems that: the network performance monitoring device and the network performance monitoring method can effectively solve the problem that the existing monitoring of the network performance in the background technology is inconvenient to organically combine the performance problem felt by a user with the network monitoring index, so that the user experience effect is poor.
The technical scheme adopted by the invention is as follows: a network performance monitoring apparatus, comprising;
The user side simulation monitoring module: simulating the real behavior of a user in a non-working period of the user, performing service access on the network to be monitored, and calculating access time delays of different nodes of the network to be monitored in the simulated access process;
The client simulation monitoring module has a client framework program which is locally and long-term resident and executed, and the framework program can send out an execution result under the condition of being unobstructed with the network operation performance analysis management module. In the architecture of the user side simulation monitoring module, the user side simulation monitoring module directs the client side framework program to independently access different network nodes and generate monitoring data. And the monitoring result data is stored in a local file, and the local result data is deleted after the monitoring result data is successfully reported to the network operation performance analysis management module by the client framework program under the condition of unobstructed network.
The network side monitoring module: capturing network data packets of the network to be monitored accessed by the user in a user working time period, restoring access behaviors of different nodes of the network, and calculating time delays of the user access of the different nodes in the process;
The whole flow is that a network monitoring instruction is sent out by a network operation performance analysis management module and is sent to different network end monitoring modules. The network operation performance analysis management module sets monitoring rules, and starts and stops of each network end monitoring module are scheduled according to the rules. After the network monitoring module is started, the current butted network access original mirror image data is acquired, restored into system service access data, the time delay of each access node is analyzed, and the time delay performance data is sent to the network operation performance analysis management module.
The server-side function operation monitoring module: capturing functions executed when a network to be monitored runs, and time consumed by executing different functions, and monitoring the execution efficiency and execution times of the system functions;
Network operation performance analysis management module: the method comprises the steps of setting a network operation performance monitoring model and a corresponding reference threshold, receiving time delay data of different nodes of a monitored network transmitted by a user side simulation monitoring module and a network side monitoring module, calculating the overall operation performance of the network according to the network operation performance monitoring model and the set reference threshold, calling data collected by a server side function operation monitoring module under the condition that the network operation performance is found to be reduced, finding out the function with the longest time consumption in the time range of system performance reduction, executing the operation data, and analyzing network performance faults.
The network operation performance analysis management module relates to two parts of main line processes, namely operation configuration and control of each module of the system, and operation performance analysis of a network to be monitored:
The system operation configuration and control comprises first monitoring fingerprint and corresponding resources and the like of a node monitored by a network side, and comprises start-stop states and the like monitored by a server side; the operation performance monitoring model configuration comprises typical access node types of a user access network, recommended delay performance thresholds and mapping relations between each node of the network to be monitored and the typical access node types.
The performance of each node access and the overall operation performance of the network can be calculated by referring to the operation performance monitoring model, the user side active node access time delay data and the network side node access time delay data. If at some time, a trend of decreasing network performance score occurs, the network operator may choose to take the following actions within the time frame of the decreasing network performance:
a. Checking the times and time delays of all execution functions of the network, sorting according to the times and time delays, checking possible function execution reasons, and feeding back the problems to research and development personnel;
b. And checking specific node performance which causes system performance degradation, referring to traditional network environment monitoring data, checking network operation environment data which may cause abnormal specific node performance, and guiding the restoration of local operation performance problems.
For operation performance analysis, operation performance analysis based on node access time delay is a core function of the performance monitoring module. Setting performance baselines for different access behaviors by distinguishing typical access behaviors of the network, calculating performance values of single access nodes, and calculating operation performance values of the whole network by giving different weights to the access performance values in the validity period.
In network performance monitoring, a user side performs analog access monitoring, particularly a large number of analog accesses, can bring a certain extra load to a network, and the network side performs mirror image data analysis, and although the network is not pressurized, the network cannot monitor under the condition of non-working time or network downtime, and the network performance monitoring has advantages and disadvantages. Therefore, in different scenes, different monitoring means should be selected:
In the invention, under the condition that no real user accesses the network in a non-working period, the user side simulation monitoring module is started, the simulation service access is actively and periodically initiated by simulating the real behavior of the user, and the network can be continuously monitored under the condition that no real user accesses the network by analyzing the data of the simulation access, and the abnormal problem of the network is found before the user, and no extra load is caused to the network when the user uses the network.
In the working time period, a network end monitoring module is started under the scene that a user uses a network, a network operation performance monitoring model is built according to the actual access behavior of the user to the network, the operation performance and access rule of the network are analyzed from network mirror image data, the overall performance state of the network, particularly the operation performance in the service peak time period, can be monitored in real time, and the normal operation of the network is not influenced. The stability and reliability of the network function can be effectively measured and intuitively embodied by using the model.
Therefore, the invention integrates two means to obtain the user access delay data with real network performance, not only can discover problems and risks at the first time, but also can take account of different scenes to start the most suitable monitoring means, and reduces the influence of the network performance monitoring device on the network.
Preferably, the network performance monitoring device further includes an information acquisition module and an information processing module, the information acquisition module is used for acquiring network delay data and tolerance of a user to node access delay, the information processing module receives the network delay data and tolerance of the user to node access delay, and carries out carding classification according to network behavior used by the user, establishes a network performance monitoring model for user performance experience for different types of network behaviors, sets different index parameter thresholds according to the tolerance of the user to node access delay, and sends the result to the network performance analysis management module. For user experience standard, namely tolerance, the invention collects information in a questionnaire mode.
In the invention, the user can set different index parameter thresholds for different types of network accesses by himself.
Preferably, the network performance monitoring device further comprises an information feedback module, wherein the information feedback module acquires a real-time delay result, and performs unified evaluation on the network performance in a user view angle by combining with a network operation performance monitoring model, and archives and feeds back the result in a log form.
Preferably, the network operation performance analysis management module is provided with a start-stop state of the server-side function operation monitoring module, after the server-side function operation monitoring module receives a start instruction, the server-side monitoring program starts to collect basic information of a related function, calculates execution time of the function, locally stores result data, and transmits the data to the network operation performance analysis management module in real time in a network connected state, preferably, logic of the function execution time is that current system time T1 is obtained when the function is triggered to start execution, and when the function execution is finished, a difference value between the current system time T2, T2 and T1 is obtained, namely the current function execution time.
In the invention, the current system time is acquired when the execution of each function of the network is started, and the function ending time is acquired before each function normally exits and abnormally exits.
Preferably, the network side monitoring module restores complete node access behaviors based on the filtered and collected mirror image data of the network access in real time, and calculates the access time delay of the network.
Preferably, the server-side function operation monitoring module performs byte code insertion on the network to be monitored, counts the execution times and time efficiency of the system function, and sends the data to the network operation performance analysis management module.
Preferably, the function captured by the server-side function operation monitoring module includes the following steps:
pcap_ lookupdev (): the network card device list is used for searching a network card of a host where the current monitoring module is located and displaying the network card device list in an enumeration mode;
pcap_open_live (): the method comprises the steps of opening a specified local network card to enable network card data to directly flow into a kernel;
pcap_ setfilter (): the method comprises the steps of setting a filtering rule of a network data packet;
pcap_loop (): and the callback function is used for continuously acquiring the network original data packet meeting the condition.
A method for monitoring a network performance monitoring device, comprising the steps of:
S1, when in application, a user does not work in a period of time: the network is actively monitored through a user side simulation monitoring module, the access behavior of a real user is simulated, the delay information of the corresponding access and module is obtained, and the monitoring result is fed back to a network operation performance analysis management module; user working time period: the network end monitoring module is used for identifying the network access behavior of the user from a large amount of network data, monitoring the end-to-end time delay of the access behavior and feeding back the monitoring result to the network operation performance analysis management module;
S2, a server-side function operation monitoring module is used for researching the operation performance of a server-side network function, monitoring and counting time delays executed by different functions of a network can be carried out, and related data are sent to a network operation performance analysis management module for fault diagnosis and analysis;
s3, using a network operation performance analysis management module, receiving network access time delay information sent by a user side simulation monitoring module/a network side monitoring module, calculating network operation performance according to an operation performance monitoring evaluation model, finding out reasons of a function execution abnormal layer when the performance is abnormal, and meanwhile, performing parameter configuration and operation control on each module by the network operation performance analysis management module.
The invention has the beneficial effects that: compared with the prior art, the invention has the following effects:
1) According to the invention, the user side simulation monitoring module is started under the condition that no real user accesses the network in the non-working time period, the simulation service access is actively and periodically initiated by simulating the real behavior of the user, and the network can be continuously monitored under the condition that no real user accesses the network in the following time period and the holiday period by analyzing the data of the simulation access, so that the problem of network abnormality is discovered before the user, and no extra load is caused to the network when the user uses the network, and the consumption of network load resources is reduced as much as possible;
2) According to the invention, the network end monitoring module is started in the scene that the user uses the network in the working time period, the network operation performance monitoring model is built according to the actual access behavior of the user to the network, the operation performance and access rule of the network are analyzed from the network mirror image data, the overall performance state of the network, especially the operation performance in the service peak time period, can be monitored in real time, and the normal operation of the network is not influenced. The stability and reliability of the network function can be effectively measured and intuitively embodied by using the model;
3) The invention can automatically discover the condition of network operation performance reduction at the first time in the stage of long-term operation after deployment, discover the condition of network unavailability or service provision interruption, and play a role in real-time monitoring on network performance. The invention is beneficial supplement, practice and innovation exploration of the traditional network operation performance monitoring mechanism, can combine the performance problem perceived by the user with the network monitoring index, solves the problem of poor user experience, and ensures that the information system operation maintenance has better continuous service improvement capability.
Drawings
FIG. 1 is a system block diagram of a network performance monitoring apparatus of the present invention;
fig. 2 is a flowchart of an application method of the network performance monitoring apparatus of the present invention.
In the figure, 1, a user side simulation monitoring module; 2. a network end monitoring module; 3. the server-side function operation monitoring module; 4. a network operation performance analysis management module; 5. an information acquisition module; 6. an information processing module; 7. and the information feedback module.
Detailed Description
The invention will be further described with reference to the accompanying drawings and specific examples.
Example 1: as shown in fig. 1-2, a network performance monitoring apparatus includes;
user side simulation monitoring module 1: simulating the real behavior of a user in a non-working period of the user, performing service access on the network to be monitored, and calculating access time delays of different nodes of the network to be monitored in the simulated access process;
The client simulation monitoring module 1 has a local client framework program which resides and executes for a long time, and the framework program can send out an execution result under the condition of being unobstructed with the network operation performance analysis management module 4. In the architecture of the client side simulation monitoring module 1, the client side simulation monitoring module 1 directs client side framework programs to independently access different network nodes and generate monitoring data. The monitoring result data are stored in a local file, and the client side framework program is successfully reported to the network operation performance analysis management module 4 and then deletes the local result data under the condition that the network is unobstructed;
network side monitoring module 2: capturing network data packets of the network to be monitored accessed by the user in a user working time period, restoring access behaviors of different nodes of the network, and calculating time delays of the user access of the different nodes in the process;
The whole flow is as follows: and the network operation performance analysis management module 4 sends out a network monitoring instruction and sends the network monitoring instruction to different network end monitoring modules 2. The network operation performance analysis management module 4 sets monitoring rules, and starts and stops of each network end monitoring module 2 are scheduled according to the rules. After the network side monitoring module 2 is started, the current butted network access original mirror image data is acquired, restored into system service access data, the time delay of each access node is analyzed, and the time delay performance data is sent to the network operation performance analysis management module 4;
Server-side function operation monitoring module 3: capturing functions executed when a network to be monitored runs, and time consumed by executing different functions, and monitoring the execution efficiency and execution times of the system functions;
network operation performance analysis management module 4: the method comprises the steps of setting a network operation performance monitoring model and corresponding reference thresholds, receiving time delay data of different nodes of a monitored network transmitted by a user side simulation monitoring module 1 and a network side monitoring module 2, calculating the overall operation performance of the network according to the network operation performance monitoring model and the set reference thresholds, calling data collected by a server side function operation monitoring module 3 under the condition that the network operation performance is found to be reduced, finding out the function with the longest time consumption in the time range of system performance reduction, executing the operation data, and analyzing network performance faults. The time consumed by the network behavior performed by the user is within the index threshold value data, the network performance can be considered to be in a normal state, and if the time exceeds the index threshold value, the network performance is considered to be abnormal;
the network operation performance analysis management module 4 relates to two parts of main line processes, namely operation configuration and control of each module of the system, and operation performance analysis of a network to be monitored:
The system operation configuration and control comprises first monitoring fingerprint and corresponding resources and the like of a node monitored by a network side, and comprises start-stop states and the like monitored by a server side; the operation performance monitoring model configuration comprises typical access node types of a user access network, recommended delay performance thresholds and mapping relations between each node of the network to be monitored and the typical access node types;
the performance of each node access and the overall operation performance of the network can be calculated by referring to the operation performance monitoring model, the user side active node access time delay data and the network side node access time delay data. If at some time, a trend of decreasing network performance score occurs, the network operator may choose to take the following actions within the time frame of the decreasing network performance:
a. Checking the times and time delays of all execution functions of the network, sorting according to the times and time delays, checking possible function execution reasons, and feeding back the problems to research and development personnel;
b. checking specific node performance which causes system performance degradation, referring to traditional network environment monitoring data, checking network operation environment data which may cause abnormal specific node performance, and guiding the restoration of local operation performance problems;
For operation performance analysis, operation performance analysis based on node access time delay is a core function of the performance monitoring module. Setting performance baselines for different access behaviors by distinguishing typical access behaviors of a network, calculating performance values of single access nodes, and calculating operation performance values of the whole network by giving different weights to the access performance values in the validity period;
In network performance monitoring, a user side performs analog access monitoring, particularly a large number of analog accesses, can bring a certain extra load to a network, and the network side performs mirror image data analysis, and although the network is not pressurized, the network cannot monitor under the condition of non-working time or network downtime, and the network performance monitoring has advantages and disadvantages. Therefore, in different scenes, different monitoring means should be selected:
In the invention, under the condition that no real user accesses the network in a non-working period, the user side simulation monitoring module 1 is started, the simulation service access is actively and periodically initiated by simulating the real behavior of the user, and the network can be continuously monitored under the condition that no real user accesses the network by analyzing the data of the simulation access, and the network abnormality problem is discovered before the user, and no extra load is caused to the network when the user uses the network. The consumption of network load resources is reduced as much as possible;
In the working time period, the network end monitoring module 2 is started under the scene that the user uses the network, the network operation performance monitoring model is built according to the actual access behavior of the user to the network, the operation performance and access rule of the network are analyzed from the network mirror image data, the overall performance state of the network, particularly the operation performance in the service peak time period, can be monitored in real time, and the normal operation of the network is not influenced. The stability and reliability of the network function can be effectively measured and intuitively embodied by using the model.
Therefore, the invention integrates two means to obtain the user access delay data with real network performance, not only can discover problems and risks at the first time, but also can take account of different scenes to start the most suitable monitoring means, and reduces the influence of the network performance monitoring device on the network. Meanwhile, in the stage of long-term operation after deployment, the invention can automatically discover the condition of network operation performance reduction at the first time, discover the condition of network unavailability or service provision interruption, and play a role in real-time monitoring on network performance; the method can combine the performance problem perceived by the user with the network monitoring index, guide the solution of the problem of poor user experience, and enable the network operation maintenance to have better continuous service improvement capability.
Therefore, the invention is beneficial supplement, practice and innovation exploration of the traditional network operation performance monitoring mechanism, can combine the performance problem perceived by the user with the network monitoring index, solves the problem of poor user experience, and ensures that the information system operation maintenance has better continuous service improvement capability.
The network performance monitoring device further comprises an information acquisition module 5 and an information processing module 6, wherein the information acquisition module 5 is used for acquiring network delay data and tolerance of a user to node access delay, the information processing module 6 receives the network delay data and the tolerance of the user to the node access delay, carries out carding classification according to the network behaviors used by the user, establishes a network operation performance monitoring model for user performance experience for different types of network behaviors, sets different index parameter thresholds according to the tolerance of the user to the node access delay, and sends the result to the network operation performance analysis management module 4.
For the user experience standard, namely tolerance, the method selects a questionnaire mode to collect information, and a time-consuming index questionnaire is prepared on a first page of the system. In the invention, the user can set different index parameter thresholds for different types of network accesses by himself. The operation performance analysis based on the network access time delay is the core of performance monitoring. By distinguishing typical access behaviors of the network, setting a network operation performance monitoring model for different access behaviors, calculating performance values of single access network nodes, and giving different weights to the access performance values in the validity period, calculating the operation performance value of the whole network.
For a network operation performance monitoring model, the core implementation logic is as follows:
Setting the operation performance value of a single node as P, wherein the range is 0-1, and the lower the value is, the worse the performance is; the higher the number, the better the performance. If the single node fails to open, the node opening performance value p=0 can be considered; if the single opening is successful and the opening time is smaller than the parameter threshold, the page opening performance value is 1; if a single node opens successfully, but the time is greater than the parameter threshold, then the single node opening performance value may be considered to be:
Because the condition that the single node is opened may have the instant jitter of the network and the network is composed of a plurality of nodes, the node access data of nearly N times can be selected for a certain network, and different weights are given to the node access data to consider the overall operation performance of the network. If M access time points in the near N accesses are more than T minutes from the current time, indicating that the data is not time-efficient and should be discarded, then the number of valid accesses is N-M. The specific values of N and T are set by the user. The performance values of each single page access are P1, P2 and … … Pn-m, the weight of P1 is highest, and the weight of Pn-m is lowest.
Setting the operation performance value of the network as S, ranging from 0 to 100, wherein the lower the value is, the worse the performance is, the higher the value is, and the better the performance is. According to the principle, the calculation method of the network operation performance value is that if the values of P1, P2 and … … Pn-m are all 0, the S value is 0, which means that the network cannot be accessed and serious faults possibly occur; if any one of the P1, P2, … … Pn-m values is not 0, then:
Wherein, px is a single node access performance value, n-m is the effective access times, and y is an algorithm adjustment parameter with a value range not smaller than 0. When the y value is 0, the weight of each effective access is the same; the larger the value of y, the higher the node access weight closest to the current detection time, and the lower the weight of the remote access node. And in the allowed numerical range, the value of y can be flexibly set by a user. It should be noted here that the same system to be monitored preferably adopts the same algorithm adjustment value at different times among different systems to be monitored, so that comparison analysis is facilitated.
The network performance monitoring device further comprises an information feedback module 7, wherein the information feedback module 7 acquires real-time delay results, and the network performance is uniformly evaluated in a user view angle by combining a network operation performance monitoring model, and the results are archived and fed back in a log form. And the network performance can be conveniently known by the user in real time. The evaluation mode of the network is carried out by calculating the operation performance value of the whole network, and the network performance is summarized in the set values.
The network operation performance analysis management module 4 is provided with a start-stop state of the server-side function operation monitoring module 3, after the server-side function operation monitoring module 3 receives a start instruction, a server-side monitoring program starts to collect basic information of related functions, calculates execution time of the functions, locally stores result data, and transmits the result data to the network operation performance analysis management module 4 in real time in a network connected state, wherein logic of the function execution time is that current system time T1 is obtained when the function is triggered to start execution, and when the function execution is finished, a difference value between the current system time T2 and the current system time T2 is obtained, namely the current function execution time.
In the invention, the current system time is acquired when the execution of each function of the network is started, and the function ending time is acquired before each function normally exits and abnormally exits.
The network side monitoring module 2 restores complete node access behaviors based on the filtered and collected mirror image data of the network access in real time, and calculates access time delay of the network.
The server-side function operation monitoring module 3 performs byte code insertion on the network to be monitored, counts the system function execution times and time efficiency, and sends data to the network operation performance analysis management module 4.
The functions captured by the server-side function operation monitoring module 3 include the following:
pcap_ lookupdev (): the network card device list is used for searching a network card of a host where the current monitoring module is located and displaying the network card device list in an enumeration mode;
pcap_open_live (): the method comprises the steps of opening a specified local network card to enable network card data to directly flow into a kernel;
pcap_ setfilter (): the method comprises the steps of setting a filtering rule of a network data packet; the original network data packet has larger flow, and does not need to be completely captured, so that the filtering rule of the network data packet needs to be set through the function.
Pcap_loop (): and the callback function is used for continuously acquiring the network original data packet meeting the condition. In the callback function, the operation logic of data packet analysis, storage, forwarding and the like can be triggered.
The specific implementation is as follows: firstly, a network switch directly connected with a network to be monitored is found, switch setting is adjusted, and data generated by a port used by network access is copied to a mirror image data port; secondly, connecting a mirror image port with a network card where a monitoring module host computer is positioned by using a network cable; and finally, capturing and filtering the network data through a data acquisition module deployed by the monitoring module host.
By performing bypass interception and capturing on the real-time access data of the network, the normal operation of the network is not affected.
Example 2: as shown in fig. 2, a monitoring method of a network performance monitoring device includes the following steps:
S1, when in use, the user does not work in a period of time: the network is actively monitored through the user side simulation monitoring module 1, the access behavior of a real user is simulated, the delay information of the corresponding access and module is obtained, and the monitoring result is fed back to the network operation performance analysis management module 4; user working time period: the network end monitoring module 2 is used for identifying the network access behavior of a user from a large amount of network data, monitoring the end-to-end time delay of the access behavior and feeding back the monitoring result to the network operation performance analysis management module 4;
s2, a server-side function operation monitoring module 3 is used for researching the operation performance of a server-side network function, monitoring and counting time delays executed by different functions of a network can be carried out, and related data are sent to a network operation performance analysis management module 4 for fault diagnosis and analysis;
S3, using the network operation performance analysis management module 4 to receive network access time delay information sent by the user side simulation monitoring module 1/the network side monitoring module 2, calculating the network operation performance according to the operation performance monitoring evaluation model, finding out reasons of a function execution abnormal layer when the performance is abnormal, and meanwhile, using the network operation performance analysis management module 4 to perform parameter configuration and operation control on each module.
The foregoing is merely illustrative of the present invention, and the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the scope of the present invention, and therefore, the scope of the present invention shall be defined by the scope of the appended claims.
Claims (8)
1. A network performance monitoring device, characterized in that: comprising the following steps:
User side simulation monitoring module (1): simulating the real behavior of a user in a non-working period of the user, performing service access on the network to be monitored, and calculating access time delays of different nodes of the network to be monitored in the simulated access process;
Network side monitoring module (2): capturing network data packets of the network to be monitored accessed by the user in a user working time period, restoring access behaviors of different nodes of the network, and calculating time delays of the user access of the different nodes in the process;
the server-side function operation monitoring module (3): capturing functions executed when a network to be monitored runs, and time consumed by executing different functions, and monitoring the execution efficiency and execution times of the system functions;
Network operation performance analysis management module (4): the method comprises the steps of setting a network operation performance monitoring model and corresponding reference thresholds, receiving time delay data of different nodes of a monitored network transmitted by a user side simulation monitoring module (1) and a network side monitoring module (2), calculating the overall operation performance of the network according to the network operation performance monitoring model and the set reference thresholds, calling data collected by a server side function operation monitoring module (3) under the condition that the network operation performance is found to be reduced, finding out the function with the longest time consumption in the time range of system performance reduction, executing the operation data, and analyzing network performance faults.
2. A network performance monitoring apparatus according to claim 1, wherein: the system comprises a network access delay analysis management module (4), an information acquisition module (5) and an information processing module (6), wherein the network access delay analysis module is used for acquiring network delay data and the tolerance of a user to node access delay, the information processing module (6) is used for receiving the network delay data and the tolerance of the user to the node access delay, carrying out carding classification according to the network using behaviors of the user, establishing a network operation performance monitoring model for user performance experience for different types of network behaviors, setting different index parameter thresholds according to the tolerance of the user to the node access delay, and sending the result to the network operation performance analysis management module (5).
3. A network performance monitoring apparatus according to claim 2, wherein: the system also comprises an information feedback module (7), wherein the information feedback module (7) acquires a real-time delay result, and is combined with a network operation performance monitoring model to uniformly evaluate the network performance in a user view angle, and the result is archived and fed back in a log form.
4. A network performance monitoring apparatus according to claim 3, wherein: the network operation performance analysis management module (4) is provided with a start-stop state of the server-side function operation monitoring module (3), after the server-side function operation monitoring module (3) receives a start-up instruction, a server-side monitoring program starts to collect and acquire basic information of related functions, calculates execution time of the related functions, locally stores result data, and transmits the data to the network operation performance analysis management module (4) in real time in a network connection state, wherein the logic of the function execution time is as follows: and acquiring the current system time T1 when the function is triggered to start executing, and acquiring the difference value between the current system time T2, T2 and T1 when the function execution is finished, namely the current function execution time.
5. The network performance monitoring apparatus and the monitoring method thereof according to claim 4, wherein: the network end monitoring module (2) restores complete node access behaviors based on the mirror image data of the network real-time access acquired by filtering, and calculates the access time delay of the network.
6. The network performance monitoring apparatus of claim 5, wherein: the server-side function operation monitoring module (3) carries out byte code insertion on the network to be monitored, counts the execution times and time efficiency of the system function, and sends data to the network operation performance analysis management module (4).
7. The network performance monitoring apparatus of claim 6, wherein: the function grabbed by the server-side function operation monitoring module (3) comprises the following steps:
pcap_ lookupdev (): the network card device list is used for searching a network card of a host where the current monitoring module is located and displaying the network card device list in an enumeration mode;
pcap_open_live (): the method comprises the steps of opening a specified local network card to enable network card data to directly flow into a kernel;
pcap_ setfilter (): the method comprises the steps of setting a filtering rule of a network data packet;
pcap_loop (): and the callback function is used for continuously acquiring the network original data packet meeting the condition.
8. A method of monitoring a network performance monitoring apparatus according to any one of claims 1 to 7, comprising the steps of:
S1, when in use, the user does not work in a period of time: the network is actively monitored through a user side simulation monitoring module (1), the access behavior of a real user is simulated, the delay information of the corresponding access and module is obtained, and the monitoring result is fed back to a network operation performance analysis management module (4); user working time period: the network end monitoring module (2) is used for identifying the behavior of a user accessing the network from a large amount of network data, monitoring the end-to-end time delay of the access behavior and feeding back the monitoring result to the network operation performance analysis management module (4);
S2, a server-side function operation monitoring module (3) is used for researching the operation performance of a server-side network function, monitoring and counting the time delay executed by different functions of the network, and sending relevant data to a network operation performance analysis management module (4) for fault diagnosis and analysis;
S3, using a network operation performance analysis management module (4), receiving network access time delay information sent by the user side simulation monitoring module (1)/network side monitoring module (2), calculating network operation performance according to a network operation performance monitoring model, finding out reasons of a function execution abnormal layer when the performance is abnormal, and meanwhile, using the network operation performance analysis management module (4) to perform parameter configuration and operation control on each module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211467154.2A CN115914039B (en) | 2022-11-22 | 2022-11-22 | Network performance monitoring device and monitoring method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211467154.2A CN115914039B (en) | 2022-11-22 | 2022-11-22 | Network performance monitoring device and monitoring method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115914039A CN115914039A (en) | 2023-04-04 |
| CN115914039B true CN115914039B (en) | 2024-05-14 |
Family
ID=86487672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211467154.2A Active CN115914039B (en) | 2022-11-22 | 2022-11-22 | Network performance monitoring device and monitoring method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115914039B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420344A (en) * | 2008-12-12 | 2009-04-29 | 北京邮电大学 | Network performance automatic evaluation method based on Java and database |
| CN105045700A (en) * | 2015-07-08 | 2015-11-11 | 国网辽宁省电力有限公司信息通信分公司 | Method for monitoring user experience index of application system in real time |
| CN108259266A (en) * | 2017-12-19 | 2018-07-06 | 广州供电局有限公司 | Web site performance monitoring method and system |
| CN108965024A (en) * | 2018-08-01 | 2018-12-07 | 重庆邮电大学 | A kind of virtual network function dispatching method of the 5G network slice based on prediction |
| CN111597099A (en) * | 2020-05-19 | 2020-08-28 | 山东汇贸电子口岸有限公司 | Non-invasive simulation method for monitoring application running quality deployed on cloud platform |
| CN112910720A (en) * | 2021-05-06 | 2021-06-04 | 成都云智天下科技股份有限公司 | Intelligent network scheduling method and system based on user experience quantitative index |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8274905B2 (en) * | 2006-08-22 | 2012-09-25 | Embarq Holdings Company, Llc | System and method for displaying a graph representative of network performance over a time period |
| US10939312B2 (en) * | 2016-05-20 | 2021-03-02 | 7Signal Solutions, Inc. | System and method for distributed network performance management |
-
2022
- 2022-11-22 CN CN202211467154.2A patent/CN115914039B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101420344A (en) * | 2008-12-12 | 2009-04-29 | 北京邮电大学 | Network performance automatic evaluation method based on Java and database |
| CN105045700A (en) * | 2015-07-08 | 2015-11-11 | 国网辽宁省电力有限公司信息通信分公司 | Method for monitoring user experience index of application system in real time |
| CN108259266A (en) * | 2017-12-19 | 2018-07-06 | 广州供电局有限公司 | Web site performance monitoring method and system |
| CN108965024A (en) * | 2018-08-01 | 2018-12-07 | 重庆邮电大学 | A kind of virtual network function dispatching method of the 5G network slice based on prediction |
| CN111597099A (en) * | 2020-05-19 | 2020-08-28 | 山东汇贸电子口岸有限公司 | Non-invasive simulation method for monitoring application running quality deployed on cloud platform |
| CN112910720A (en) * | 2021-05-06 | 2021-06-04 | 成都云智天下科技股份有限公司 | Intelligent network scheduling method and system based on user experience quantitative index |
Non-Patent Citations (1)
| Title |
|---|
| 一种高速校园网络性能监测系统的设计与实现;王龙;;信息与电脑(理论版);20101015(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115914039A (en) | 2023-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5949976A (en) | Computer performance monitoring and graphing tool | |
| CN107508722B (en) | Service monitoring method and device | |
| CN108964995A (en) | Log correlation analysis method based on time shaft event | |
| CN102075384A (en) | Performance test system and method | |
| CN102355368B (en) | Fault processing method of network equipment and system | |
| CN102158360A (en) | Network fault self-diagnosis method based on causal relationship positioning of time factors | |
| CN108399114A (en) | A kind of system performance testing method, apparatus and storage medium | |
| CN101197621A (en) | Method and system for remote diagnosing and locating failure of network management system | |
| CN104574219A (en) | System and method for monitoring and early warning of operation conditions of power grid service information system | |
| CN111970151A (en) | Flow fault positioning method and system for virtual and container network | |
| CN116719664B (en) | Application and cloud platform cross-layer fault analysis method and system based on micro-service deployment | |
| CN112350854A (en) | Flow fault positioning method, device, equipment and storage medium | |
| CN110113205A (en) | A kind of network troubleshooting system and its working method based on software defined network technology | |
| CN214314723U (en) | Intelligent power distribution station monitoring system based on 5G cloud control platform | |
| CN117811898A (en) | FTTR equipment fault repairing method and device | |
| CN115914039B (en) | Network performance monitoring device and monitoring method thereof | |
| CN110969082B (en) | Clock synchronous test inspection method and system | |
| CN114285780B (en) | Radar network testing system and testing method based on priority queue | |
| CN114374600A (en) | Network operation and maintenance method, device, equipment and product based on big data | |
| CN114726708A (en) | Network element equipment fault prediction method and system based on artificial intelligence | |
| CN114066181A (en) | Intelligent state evaluation system for thermal equipment | |
| CN112711510A (en) | Automatic adaptation method and system for monitoring service continuity operation | |
| CN116225944B (en) | Software testing system and method for presetting networking environment | |
| CN114090382B (en) | Health inspection method and device for super-converged cluster | |
| CN114422392B (en) | Intelligent risk monitoring system and risk monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |