CN102347864A - System and method for monitoring service quality of content distribution networks - Google Patents
System and method for monitoring service quality of content distribution networks Download PDFInfo
- Publication number
- CN102347864A CN102347864A CN2011103420561A CN201110342056A CN102347864A CN 102347864 A CN102347864 A CN 102347864A CN 2011103420561 A CN2011103420561 A CN 2011103420561A CN 201110342056 A CN201110342056 A CN 201110342056A CN 102347864 A CN102347864 A CN 102347864A
- Authority
- CN
- China
- Prior art keywords
- test
- data
- module
- service
- distributing network
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012360 testing method Methods 0.000 claims abstract description 195
- 238000007405 data analysis Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 57
- 238000013480 data collection Methods 0.000 claims description 22
- 238000012806 monitoring device Methods 0.000 claims description 22
- 230000005540 biological transmission Effects 0.000 claims description 18
- 238000001914 filtration Methods 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 13
- 230000001747 exhibiting effect Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 9
- 238000007619 statistical method Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 241001269238 Data Species 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000002085 persistent effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a system and method for monitoring the service quality of content distribution networks, which are used for efficiently, accurately and timely monitoring the service quality of CDNs (Content Distribution Network) so as to effectively improve the service quality of the CDNs with various domain names. The invention adopts the technical scheme that test tasks are first established for the domain names added with CDN service, and the address and other information of a tested target resource are sent and distributed to the test points of all regions of the whole country through central scheduling. After the CDN service is provided, the test points adopt high-frequency concurrency test to analyze the target resource, and summarize and report test data. Then, an upper data analysis management module processes the reported data, obtains the service conditions of all nodes, and matches and alarms according to abnormal rules.
Description
Technical field
The present invention relates to a kind of monitoring field of computer network services quality; Relate in particular to the system that the operation layer quality of service monitor is provided on content distributing network (CDN); CDN expedite product service status is surveyed, analyzed and reports to the police, thereby reach the purpose that improves internet C DN service quality.
Background technology
Service quality is a kind of security mechanism of network, is that method commonly used comprises classification, mark and priority setting with a kind of technology that solves problems such as network delay and obstruction.But along with the fast development of Internet service, the quality of service requirement of network application no longer is confined to the network control of bottom, content distributing network (CDN) technology is arisen at the historic moment.It is for issuing the special network coverage layer of optimizing of broadband rich-media at traditional I P net.From the angle of broad sense, CDN has represented a kind of network service mode based on quality and order.CDN is a purpose with the service quality that improves Internet service, provides better network application to experience through network edge node to the end user.Yet because the complexity of its reciprocal process and network environment still needn't exist many service quality problems that influence with exempting from application process.
The service quality bottleneck of traditional network application mainly is present in the network problem between end user and application server, however use significantly reduced that route is long after the CDN service, cross operator etc. causes the low main cause of service quality.But, adopt and also to have brought new problem behind the CDN with himself characteristic: quicken that node returns that the source is unusual, the fringe node flow run high run flat, the fringe node service is unusual, domain name mapping covers unusual etc.These problems affect the service quality of network application equally, are concerning end user's business experience, are the problems that can not be ignored.
Along with the development of Internet service, the Internet enterprise progressively shifts the focus of monitoring to concrete service application from original bottom hardware, network condition, like the service quality of contents such as picture, video, dynamic requests.The corresponding website performance monitoring is analyzed also following, some have occurred through the simulation end user, sends the acquisition request data to target resource, and then analyzes network application and the business that obtains the website service quality.Yet much more more this monitor mode is applied to simple web analytics at present; Adopt the mode test target resource of serial; Cause frequency and inefficiency; Lack monitoring analysis means simultaneously to the CDN service feature; Can not carry out effective performance evaluation to quickening node; Can not provide targetedly and to report to the police, and the wrong report that causes of filter test point problem, and not be suitable for the quality of service monitor of CDN.
Summary of the invention
The objective of the invention is to address the above problem; A kind of service quality monitoring system of content-based distributing network is provided; Low to testing efficiency in the existing method of testing; Lack problems such as effectively analysis, type of alarm; From the CDN application aspect; In conjunction with concrete business realizing, to CDN service quality carry out efficiently, accurately, monitoring timely, thereby effectively improve the CDN service quality of each domain name.
The present invention also provides a kind of quality of service monitor method of content-based distributing network; Low to testing efficiency in the existing method of testing; Lack problems such as effectively analysis, type of alarm; From the CDN application aspect; In conjunction with concrete business realizing; To CDN service quality carry out efficiently, accurately, monitoring timely, thereby effectively improve the CDN service quality of each domain name.
Technical scheme of the present invention is: the present invention has disclosed a kind of service quality monitoring system of content-based distributing network, and comprise the system call exhibiting device, be arranged in the monitoring device and the data collection analysis device of a plurality of test machine, wherein:
The system call exhibiting device comprises input/output interface module and task scheduling modules, wherein:
Input/output interface module is used for the domain name resources address and the alarm rule of configuration monitoring object;
Task scheduling modules connects said input/output interface module, generates the test assignment configuration file according to monitored object of importing and alarm rule, and said test assignment configuration file is sent in the monitoring device in said a plurality of test machine;
Monitoring device is set up data with said system call exhibiting device with said data collection analysis device and is connected, and comprises task configuration file parsing module, high frequency concurrent test module and data transmission blocks, wherein:
Task configuration file parsing module is resolved the test assignment configuration file that sends from said task scheduling modules;
High frequency concurrent test module; Connect said task configuration file parsing module; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, said test data comprises time index and fileinfo;
Data transmission blocks connects said high frequency concurrent test module, and said test data is mail to said data collection analysis device;
The data collection analysis device comprises data reception module, data analysis module, alarm analysis module and warning sending module, wherein:
Data reception module receives the said test data of sending from the said data transmission blocks in said a plurality of monitoring devices;
Data analysis module carries out statistical analysis based on said test data to the service quality of the fringe node of content distributing network, obtains quickening domain name and quickens the performance index of node at each;
The alarm analysis module connects said data analysis module, carries out status analysis based on the service quality of the fringe node of said alarm rule of setting and content distributing network, obtains the problem of existence in the content distributing network service;
The warning sending module connects said alarm analysis module, issues the alert signal of delivering newspaper at alarm command.
Embodiment according to the service quality monitoring system of content-based distributing network of the present invention also comprises in the said monitoring device:
The abnormality detection filtering module is connected between said high frequency concurrent test module and the said data transmission blocks, and the processing of test data being carried out abnormality detection and data filter re-sends to said data transmission blocks afterwards.
According to an embodiment of the service quality monitoring system of content-based distributing network of the present invention, said data collection analysis device also comprises:
The data filter module is connected after the said data reception module, and test data is carried out filtration treatment;
Data memory module is connected after the said data filter module, and the test data after the filtration treatment is stored.
The present invention has also disclosed a kind of quality of service monitor method of content-based distributing network, comprising:
The domain name resources address and the alarm rule of configuration monitoring object;
According to monitored object and the alarm rule generation test assignment configuration file of input, and the test assignment configuration file sent to be arranged in a plurality of test machine;
In each test machine, resolve the test assignment configuration file that receives;
According to the test assignment configuration file that parses; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, said test data comprises time index and fileinfo;
From each test machine, gather test data, the service quality of the fringe node of content distributing network is carried out statistical analysis, obtain quickening domain name and quicken the performance index of node at each based on these test datas;
Service quality based on the fringe node of alarm rule of setting and content distributing network is carried out status analysis, obtains the concurrent alert signal of delivering newspaper of problem that exists in the content distributing network service.
According to an embodiment of the quality of service monitor method of content-based distributing network of the present invention, after obtaining the test data that server response back record fringe node returns, gather again after the processing through abnormality detection and data filter.
According to an embodiment of the quality of service monitor method of content-based distributing network of the present invention, after gathering test data through filtration treatment and store.
The present invention contrasts prior art has following beneficial effect: scheme of the present invention is at first to set up test assignment for the domain name of adding the CDN service, through central schedule the information such as target resource address of testing is mail to and is distributed in each regional test point of the whole nation.After the CDN service was provided, test point adopted the high frequency concurrent test that target resource is analyzed, with the test data summarizing and reporting.After this, upper layer data analysis management module is handled reported data, obtains each node service scenario, and mates and report to the police according to exception rules.The contrast prior art, the present invention provides the system of operation layer quality of service monitor on content distributing network (CDN), CDN expedite product service status is surveyed, analyzed and reports to the police, thereby reach the purpose that improves internet C DN service quality.
Description of drawings
Fig. 1 shows the deployment diagram of the service quality monitoring system of content distributing network of the present invention.
Fig. 2 shows the structure chart of first embodiment of the service quality monitoring system of content distributing network of the present invention.
Fig. 3 shows the structure chart of second embodiment of the service quality monitoring system of content distributing network of the present invention.
Fig. 4 shows the flow chart of first embodiment of the quality of service monitor method of content distributing network of the present invention.
Fig. 5 shows the flow chart of second embodiment of the quality of service monitor method of content distributing network of the present invention.
Embodiment
Below in conjunction with accompanying drawing and embodiment the present invention is done further description.
First embodiment of the service quality monitoring system of content distributing network
The deployment architecture of the service quality monitoring system of content distributing network of the present invention as shown in Figure 1, test machine 12 connects the fringe node 10 of content distributing network respectively, these test machine 12 are aggregated into data collection analysis center 14.Data collection analysis center 14 connects data center 16 and dispatch report exhibition centre 18 successively.
Fig. 2 shows the structure of first embodiment of the service quality monitoring system of content distributing network.See also Fig. 2, the service quality monitoring system of the content-based distributing network of present embodiment comprises system call exhibiting device 20, is arranged in the monitoring device 24 and the data collection analysis device 26 of a plurality of test machine.System call exhibiting device 20 connects these monitoring devices 24, and these monitoring devices 24 all are connected to data collection analysis device 26.
System call exhibiting device 20 comprises input/output interface module 200 and task scheduling modules 202.Input/output interface module 200 is used for the domain name resources address and the alarm rule of configuration monitoring object.Task scheduling modules 202 connects input/output interface module 200, generates the test assignment configuration file according to monitored object of importing and alarm rule, and the test assignment configuration file is sent in the monitoring device 24 of each test machine.
Monitoring device 24 comprises task configuration file parsing module 240, high frequency concurrent test module 242 and data transmission blocks 244.Task configuration file parsing module 240 is resolved the test assignment configuration file that sends from task scheduling modules 202.
High frequency concurrent test module 242 connects task configuration file parsing module 240; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, test data comprises time index and fileinfo.High frequency concurrent test administrative mechanism is exactly under the testing requirement of a large amount of channels, adopts the management of effective concurrent mechanism and downloading control, and the bandwidth of avoiding test volume to bring is fought for, and effectively improves concurrency, stability and the accuracy of test.
The high frequency concurrent test mainly through following some realize:
1, monofile restriction: each domain name is chosen a URI and is tested.Same area under one's name file all can represent this domain name quicken the performance condition of node in correspondence, simultaneously situations such as abnormality sign indicating number are had generality.Therefore only choose a URI to substitute the full page face test in the conventional test methodologies, saved unnecessary resource, bandwidth cost, avoid the element problem causes under other domain names in the test of full page face test effect unusual with influence each other.
2, file size limitation: because the startup phenomenon slowly of the Internet resources downloading process that the TCP congestion control mechanism causes, different test file sizes play significant effects to the performance index fluctuation of test.The downloading process time of small documents test is too short, and it is excessive to fluctuate, and is difficult to find and weigh the service quality situation; To tend towards stability after the download of big file test reaches certain hour, but will cause under the Multi-task Concurrency situation bandwidth to fight for.Through the observation analysis of a period of time, to launch 20 threads and test, the enactment document size is that file size is the most stable in the test data of 50~100KB, and can accurately reflect problem under the monitoring URI of the 5KB~5MB situation about analyzing.Therefore; In the high-frequency test management, file size is controlled, chosen the target URI that reaches enough sizes and test, under the situation that big file is only arranged; The size of returning through in Range header field and the downloading process in the HTTP request header is carried out the segmentation downloading control, avoids whole downloads.
3, second rank is concurrent: the serial test will cause testing efficiency low, can't satisfy big test volume demand, and big by the concurrent moment in the cycle concurrency that will cause of duty cycle, bandwidth availability ratio is low.Second rank concurrent with the time in the one-period by being second that unit is divided into a plurality of timeslices, all tests are all assigned in each testing time sheet carry out concurrent test.Owing to carried out file size limitation, can effectively avoid the persistent resources in concurrent to fight for through this method, bandwidth is used the problem of concentrating in the level and smooth test process, thereby improves the stability of overall test amount and test data.
Data transmission blocks 244 connects high frequency concurrent test module 242, and test data is mail to data collection analysis device 26.
Data collection analysis device 26 comprises data reception module 260, data analysis module 262, alarm analysis module 264 and warning sending module 266.Data reception module 260 receives the test data of sending from the data transmission blocks in each monitoring device 24 244.
Data analysis module 262 carries out statistical analysis based on test data to the service quality of the fringe node of content distributing network, obtains quickening domain name and quickens the performance index of node at each.
To the intellectual analysis that quickens node is the analytic statistics that service is carried out to CDN, its objective is the service quality of examination assessment CDN service edge node.This analysis mainly provides the service quality analysis to domain name in the task, and the comprehensive service capability of node.
1, the domain name service quality analysis with the achievement data collected according to target node IP add up; Filter junk data through unusual strobe utility; Thereby obtain average behavior index and the availability number of the file of corresponding task domain name, be used to assess the service quality situation of node domain name granularity at each node.
2, the comprehensive service capability of node needs the situation of comprehensive all test assignments to analyze.Adopt the quartile method to assess at this, to filter the special data that concrete domain name problem is brought.At first carry out the rank scoring for the node service quality situation of each task; Then the precedence data of each task is analyzed with the quartile method; After obtaining the rank score value of 3 branch positions, the final score of this node of backwards calculation is as the comprehensive service capability of node.
Alarm analysis module 264 connects data analysis module 262; Service quality based on the fringe node of alarm rule of setting and content distributing network is carried out status analysis; Comprise the professional relevant single task analysis-by-synthesis relevant, obtain the problem that exists in the content distributing network service with node.Warning sending module 266 connects alarm analysis module 264, issues the alert signal of delivering newspaper at alarm command.
Intelligent alarm mainly comprises performance index and conditional code.
1, performance index need the combined with access zone and quicken node and carry out alarm analysis, rather than traditional single access region.From the framework of CDN service, often adopt the covering relation of multi-to-multi, and network problem often is present between zone and the zone, single zone is considered often smoothly to fall easily unusual, and does not reach alarm threshold value.Simultaneously, there is bigger relation performance index and network behaviour in service, coverage.The network peak period often causes the standard of performance index to glide easily; And himself network condition of remote coverage is relatively poor; Performance index also relatively a little less than; Therefore when performance index are carried out analytic statistics; Need alarm threshold value to be adjusted automatically, reduce wrong report to time period and area information.
2, report to the police often fringe node or the unusual return code of source server of conditional code causes, so the granularity of its analysis only need all occur unusually when quickening node, thereby can be that integrated alarm is carried out in the source with positioning problems then to quickening node.
Preferable, at data collection analysis device 26 data filter module 268 and data memory module 269 are set further.Data filter module 268 is connected after the data reception module 260, and test data is carried out filtration treatment.Data memory module 269 is connected after the data filter module 268, and the test data after the filtration treatment is stored.
Second embodiment of the service quality monitoring system of content distributing network
Fig. 3 shows the structure of second embodiment of the service quality monitoring system of content distributing network.See also Fig. 3, the service quality monitoring system of the content-based distributing network of present embodiment comprises system call exhibiting device 30, is arranged in the monitoring device 34 and the data collection analysis device 36 of a plurality of test machine.System call exhibiting device 30 connects these monitoring devices 34, and these monitoring devices 34 all are connected to data collection analysis device 36.
System call exhibiting device 30 comprises input/output interface module 300 and task scheduling modules 302.Input/output interface module 300 is used for the domain name resources address and the alarm rule of configuration monitoring object.Task scheduling modules 302 connects input/output interface module 300, generates the test assignment configuration file according to monitored object of importing and alarm rule, and the test assignment configuration file is sent in the monitoring device 34 of each test machine.
Monitoring device 34 comprises task configuration file parsing module 340, high frequency concurrent test module 342, abnormality detection filtering module 346 and data transmission blocks 344.Task configuration file parsing module 340 is resolved the test assignment configuration file that sends from task scheduling modules 302.
High frequency concurrent test module 342 connects task configuration file parsing module 340; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, test data comprises time index and fileinfo.High frequency concurrent test administrative mechanism is exactly under the testing requirement of a large amount of channels, adopts the management of effective concurrent mechanism and downloading control, and the bandwidth of avoiding test volume to bring is fought for, and effectively improves concurrency, stability and the accuracy of test.
The high frequency concurrent test mainly through following some realize:
1, monofile restriction: each domain name is chosen a URI and is tested.Same area under one's name file all can represent this domain name quicken the performance condition of node in correspondence, simultaneously situations such as abnormality sign indicating number are had generality.Therefore only choose a URI to substitute the full page face test in the conventional test methodologies, saved unnecessary resource, bandwidth cost, avoid the element problem causes under other domain names in the test of full page face test effect unusual with influence each other.
2, file size limitation: because the startup phenomenon slowly of the Internet resources downloading process that the TCP congestion control mechanism causes, different test file sizes play significant effects to the performance index fluctuation of test.The downloading process time of small documents test is too short, and it is excessive to fluctuate, and is difficult to find and weigh the service quality situation; To tend towards stability after the download of big file test reaches certain hour, but will cause under the Multi-task Concurrency situation bandwidth to fight for.Through the observation analysis of a period of time, to launch 20 threads and test, the enactment document size is that file size is the most stable in the test data of 50~100KB, and can accurately reflect problem under the monitoring URI of the 5KB~5MB situation about analyzing.Therefore; In the high-frequency test management, file size is controlled, chosen the target URI that reaches enough sizes and test, under the situation that big file is only arranged; The size of returning through in Range header field and the downloading process in the HTTP request header is carried out the segmentation downloading control, avoids whole downloads.
3, second rank is concurrent: the serial test will cause testing efficiency low, can't satisfy big test volume demand, and big by the concurrent moment in the cycle concurrency that will cause of duty cycle, bandwidth availability ratio is low.Second rank concurrent with the time in the one-period by being second that unit is divided into a plurality of timeslices, all tests are all assigned in each testing time sheet carry out concurrent test.Owing to carried out file size limitation, can effectively avoid the persistent resources in concurrent to fight for through this method, bandwidth is used the problem of concentrating in the level and smooth test process, thereby improves the stability of overall test amount and test data.
Abnormality detection filtering module 346 is connected between high frequency concurrent test module 342 and the data transmission blocks 344, and the processing of test data being carried out abnormality detection and data filter re-sends to data transmission blocks 344 afterwards.
Data transmission blocks 244 connects abnormality detection filtering module 346, and test data is mail to data collection analysis device 36.
Data collection analysis device 36 comprises data reception module 360, data analysis module 362, alarm analysis module 364 and warning sending module 366.Data reception module 360 receives the test data of sending from the data transmission blocks in each monitoring device 34 344.
Data analysis module 362 carries out statistical analysis based on test data to the service quality of the fringe node of content distributing network, obtains quickening domain name and quickens the performance index of node at each.
To the intellectual analysis that quickens node is the analytic statistics that service is carried out to CDN, its objective is the service quality of examination assessment CDN service edge node.This analysis mainly provides the service quality analysis to domain name in the task, and the comprehensive service capability of node.
1, the domain name service quality analysis with the achievement data collected according to target node IP add up; Filter junk data through unusual strobe utility; Thereby obtain average behavior index and the availability number of the file of corresponding task domain name, be used to assess the service quality situation of node domain name granularity at each node.
2, the comprehensive service capability of node needs the situation of comprehensive all test assignments to analyze.Adopt the quartile method to assess at this, to filter the special data that concrete domain name problem is brought.At first carry out the rank scoring for the node service quality situation of each task; Then the precedence data of each task is analyzed with the quartile method; After obtaining the rank score value of 3 branch positions, the final score of this node of backwards calculation is as the comprehensive service capability of node.
Alarm analysis module 364 connects data analysis module 362; Service quality based on the fringe node of alarm rule of setting and content distributing network is carried out status analysis; Comprise the professional relevant single task analysis-by-synthesis relevant, obtain the problem that exists in the content distributing network service with node.Warning sending module 366 connects alarm analysis module 364, issues the alert signal of delivering newspaper at alarm command.
Intelligent alarm mainly comprises performance index and conditional code.
1, performance index need the combined with access zone and quicken node and carry out alarm analysis, rather than traditional single access region.From the framework of CDN service, often adopt the covering relation of multi-to-multi, and network problem often is present between zone and the zone, single zone is considered often smoothly to fall easily unusual, and does not reach alarm threshold value.Simultaneously, there is bigger relation performance index and network behaviour in service, coverage.The network peak period often causes the standard of performance index to glide easily; And himself network condition of remote coverage is relatively poor; Performance index also relatively a little less than; Therefore when performance index are carried out analytic statistics; Need alarm threshold value to be adjusted automatically, reduce wrong report to time period and area information.
2, report to the police often fringe node or the unusual return code of source server of conditional code causes, so the granularity of its analysis only need all occur unusually when quickening node, thereby can be that integrated alarm is carried out in the source with positioning problems then to quickening node.
Preferable, at data collection analysis device 36 data filter module 368 and data memory module 369 are set further.Data filter module 368 is connected after the data reception module 360, and test data is carried out filtration treatment.Data memory module 369 is connected after the data filter module 368, and the test data after the filtration treatment is stored.
First embodiment of the quality of service monitor method of content distributing network
Fig. 4 shows the step of first embodiment of the quality of service monitor method of content distributing network of the present invention.See also Fig. 4, the detailed step of present embodiment is described below.
Step S10: the domain name resources address and the alarm rule of configuration monitoring object.
Step S11:, and the test assignment configuration file sent to be arranged in a plurality of test machine according to monitored object and the alarm rule generation test assignment configuration file of input.
Step S12: in each test machine, resolve the test assignment configuration file that receives.
Step S13: according to the test assignment configuration file that parses; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, said test data comprises time index and fileinfo.
Step S14: from each test machine, gather test data, the service quality of the fringe node of content distributing network is carried out statistical analysis, obtain quickening domain name and quicken the performance index of node at each based on these test datas.
Preferable, after gathering test data, also store through filtration treatment.
Step S15: the service quality based on the fringe node of alarm rule of setting and content distributing network is carried out status analysis, obtains the concurrent alert signal of delivering newspaper of problem that exists in the content distributing network service.
Second embodiment of the quality of service monitor method of content distributing network
Fig. 5 shows the step of second embodiment of the quality of service monitor method of content distributing network of the present invention.See also Fig. 5, the detailed step of present embodiment is described below.
Step S20: the domain name resources address and the alarm rule of configuration monitoring object.
Step S21:, and the test assignment configuration file sent to be arranged in a plurality of test machine according to monitored object and the alarm rule generation test assignment configuration file of input.
Step S22: in each test machine, resolve the test assignment configuration file that receives.
Step S23: according to the test assignment configuration file that parses; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, said test data comprises time index and fileinfo.
Step S24: after the test data that the record fringe node returns after obtaining the server response, gather again after the processing through abnormality detection and data filter.
Step S25: from each test machine, gather test data, the service quality of the fringe node of content distributing network is carried out statistical analysis, obtain quickening domain name and quicken the performance index of node at each based on these test datas.
Preferable, after gathering test data, also store through filtration treatment.
Step S26: the service quality based on the fringe node of alarm rule of setting and content distributing network is carried out status analysis, obtains the concurrent alert signal of delivering newspaper of problem that exists in the content distributing network service.
The foregoing description provides to those of ordinary skills and realizes or use of the present invention; Those of ordinary skills can be under the situation that does not break away from invention thought of the present invention; The foregoing description is made various modifications or variation; Thereby protection scope of the present invention do not limit by the foregoing description, and should be the maximum magnitude of the inventive features mentioned of load claims.
Claims (6)
1. the service quality monitoring system of a content-based distributing network comprises the system call exhibiting device, is arranged in the monitoring device and the data collection analysis device of a plurality of test machine, wherein:
The system call exhibiting device comprises input/output interface module and task scheduling modules, wherein:
Input/output interface module is used for the domain name resources address and the alarm rule of configuration monitoring object;
Task scheduling modules connects said input/output interface module, generates the test assignment configuration file according to monitored object of importing and alarm rule, and said test assignment configuration file is sent in the monitoring device in said a plurality of test machine;
Monitoring device is set up data with said system call exhibiting device with said data collection analysis device and is connected, and comprises task configuration file parsing module, high frequency concurrent test module and data transmission blocks, wherein:
Task configuration file parsing module is resolved the test assignment configuration file that sends from said task scheduling modules;
High frequency concurrent test module; Connect said task configuration file parsing module; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, said test data comprises time index and fileinfo;
Data transmission blocks connects said high frequency concurrent test module, and said test data is mail to said data collection analysis device;
The data collection analysis device comprises data reception module, data analysis module, alarm analysis module and warning sending module, wherein:
Data reception module receives the said test data of sending from the said data transmission blocks in said a plurality of monitoring devices;
Data analysis module carries out statistical analysis based on said test data to the service quality of the fringe node of content distributing network, obtains quickening domain name and quickens the performance index of node at each;
The alarm analysis module connects said data analysis module, carries out status analysis based on the service quality of the fringe node of said alarm rule of setting and content distributing network, obtains the problem of existence in the content distributing network service;
The warning sending module connects said alarm analysis module, issues the alert signal of delivering newspaper at alarm command.
2. the service quality monitoring system of content-based distributing network according to claim 1 is characterized in that, also comprises in the said monitoring device:
The abnormality detection filtering module is connected between said high frequency concurrent test module and the said data transmission blocks, and the processing of test data being carried out abnormality detection and data filter re-sends to said data transmission blocks afterwards.
3. the service quality monitoring system of content-based distributing network according to claim 1 is characterized in that, said data collection analysis device also comprises:
The data filter module is connected after the said data reception module, and test data is carried out filtration treatment;
Data memory module is connected after the said data filter module, and the test data after the filtration treatment is stored.
4. the quality of service monitor method of a content-based distributing network comprises:
The domain name resources address and the alarm rule of configuration monitoring object;
According to monitored object and the alarm rule generation test assignment configuration file of input, and the test assignment configuration file sent to be arranged in a plurality of test machine;
In each test machine, resolve the test assignment configuration file that receives;
According to the test assignment configuration file that parses; Based on high frequency concurrent test administrative mechanism; Obtain the object edge node of respective regions through dns resolution after; Destination address is mail in simulation HTTP request; Obtain the test data that server response back record fringe node returns, said test data comprises time index and fileinfo;
From each test machine, gather test data, the service quality of the fringe node of content distributing network is carried out statistical analysis, obtain quickening domain name and quicken the performance index of node at each based on these test datas;
Service quality based on the fringe node of alarm rule of setting and content distributing network is carried out status analysis, obtains the concurrent alert signal of delivering newspaper of problem that exists in the content distributing network service.
5. the quality of service monitor method of content-based distributing network according to claim 4 is characterized in that, after the test data that the record fringe node returns after obtaining the server response, gathers after the processing through abnormality detection and data filter again.
6. the quality of service monitor method of content-based distributing network according to claim 3 is characterized in that, after gathering test data, also stores through filtration treatment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110342056 CN102347864B (en) | 2011-11-02 | 2011-11-02 | System for monitoring service quality of content distribution networks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110342056 CN102347864B (en) | 2011-11-02 | 2011-11-02 | System for monitoring service quality of content distribution networks |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102347864A true CN102347864A (en) | 2012-02-08 |
CN102347864B CN102347864B (en) | 2013-10-30 |
Family
ID=45546172
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110342056 Expired - Fee Related CN102347864B (en) | 2011-11-02 | 2011-11-02 | System for monitoring service quality of content distribution networks |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102347864B (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102624570A (en) * | 2012-04-27 | 2012-08-01 | 杭州东信北邮信息技术有限公司 | Monitoring system and method for detecting availability of web server |
CN102932204A (en) * | 2012-11-09 | 2013-02-13 | 北京奇虎科技有限公司 | Monitoring method and monitoring system of content delivery network |
CN102938716A (en) * | 2012-12-06 | 2013-02-20 | 网宿科技股份有限公司 | Content distribution network acceleration test method and device |
CN103793318A (en) * | 2012-10-29 | 2014-05-14 | 百度在线网络技术(北京)有限公司 | Method and device for distributed testing of module stability |
CN104584000A (en) * | 2012-07-20 | 2015-04-29 | 蓝凯股份有限公司 | Tag latency monitoring and control system for enhanced web page performance |
CN104735550A (en) * | 2013-12-19 | 2015-06-24 | 北京四达时代软件技术股份有限公司 | Method and device for managing performance of VCDN system |
CN104767682A (en) * | 2014-01-08 | 2015-07-08 | 腾讯科技(深圳)有限公司 | Routing method and system as well as routing information distributing method and device |
CN106130816A (en) * | 2016-06-24 | 2016-11-16 | 腾讯科技(深圳)有限公司 | A kind of content distributing network monitoring method, monitoring server and system |
CN106412063A (en) * | 2016-09-29 | 2017-02-15 | 赛尔网络有限公司 | CDN node detection and resource scheduling system and method in education network |
CN106656611A (en) * | 2016-12-28 | 2017-05-10 | 成都网丁科技有限公司 | CDN quality evaluation system |
CN107094096A (en) * | 2017-04-19 | 2017-08-25 | 北京云端智度科技有限公司 | A kind of adaptive CDN business diagnosis monitoring systems |
CN108206769A (en) * | 2017-12-26 | 2018-06-26 | 中国移动通信集团江苏有限公司 | Method, apparatus, equipment and the medium of screen quality alarm |
CN108847984A (en) * | 2018-06-27 | 2018-11-20 | 北京云端智度科技有限公司 | A kind of CDN global load balancing strategy of the health algorithm based on SNMP |
CN108964967A (en) * | 2018-02-23 | 2018-12-07 | 云智慧(北京)科技有限公司 | Method and system for intelligently monitoring and analyzing CDN acceleration service |
CN109547289A (en) * | 2018-12-04 | 2019-03-29 | 杭州安恒信息技术股份有限公司 | A kind of method and system of intelligent scheduling visitor flow |
CN109639533A (en) * | 2019-01-08 | 2019-04-16 | 深圳市网心科技有限公司 | A kind of test method, system and the terminal device of subdispatch strategy |
CN109688023A (en) * | 2018-12-04 | 2019-04-26 | 成都知道创宇信息技术有限公司 | A method of the CDN monitoring availability disposed in a manner of anycast |
CN110768852A (en) * | 2018-07-25 | 2020-02-07 | 贵州白山云科技股份有限公司 | Method and device for testing cloud network nodes |
CN110855516A (en) * | 2019-10-15 | 2020-02-28 | 厦门美柚股份有限公司 | CDN quality detection system and method |
US10666533B2 (en) | 2012-07-20 | 2020-05-26 | Oracle International Corporation | Tag latency monitoring and control system for enhanced web page performance |
CN111884869A (en) * | 2020-05-21 | 2020-11-03 | 网宿科技股份有限公司 | Method, device and system for monitoring network quality |
CN111934924A (en) * | 2020-07-31 | 2020-11-13 | 深圳市高德信通信股份有限公司 | CDN network deployment management system |
CN112688825A (en) * | 2019-10-18 | 2021-04-20 | 上海哔哩哔哩科技有限公司 | CDN node test method and device and computer equipment |
CN113760639A (en) * | 2020-10-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Monitoring method, monitoring device, computing equipment and medium |
CN115473871A (en) * | 2022-09-19 | 2022-12-13 | 广州市百果园网络科技有限公司 | Domain name local resolution method and device, equipment, medium and product thereof |
CN117241259A (en) * | 2023-11-15 | 2023-12-15 | 长沙时代跳动科技有限公司 | Mobile Internet-based app service management platform and data processing method thereof |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008022339A2 (en) * | 2006-08-18 | 2008-02-21 | Akamai Technologies, Inc. | Method of data collection in a distributed network |
CN101741643A (en) * | 2009-12-24 | 2010-06-16 | 北京世纪互联宽带数据中心有限公司 | Content delivery network node detecting method and system |
CN102065142A (en) * | 2010-12-23 | 2011-05-18 | 网宿科技股份有限公司 | File downloading based scheduling method and system for content delivery network (CDN) |
-
2011
- 2011-11-02 CN CN 201110342056 patent/CN102347864B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008022339A2 (en) * | 2006-08-18 | 2008-02-21 | Akamai Technologies, Inc. | Method of data collection in a distributed network |
CN101741643A (en) * | 2009-12-24 | 2010-06-16 | 北京世纪互联宽带数据中心有限公司 | Content delivery network node detecting method and system |
CN102065142A (en) * | 2010-12-23 | 2011-05-18 | 网宿科技股份有限公司 | File downloading based scheduling method and system for content delivery network (CDN) |
Cited By (42)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102624570A (en) * | 2012-04-27 | 2012-08-01 | 杭州东信北邮信息技术有限公司 | Monitoring system and method for detecting availability of web server |
CN102624570B (en) * | 2012-04-27 | 2015-04-15 | 杭州东信北邮信息技术有限公司 | Monitoring system and method for detecting availability of web server |
US10666533B2 (en) | 2012-07-20 | 2020-05-26 | Oracle International Corporation | Tag latency monitoring and control system for enhanced web page performance |
CN104584000B (en) * | 2012-07-20 | 2020-03-20 | 蓝凯股份有限公司 | Tag latency monitoring and control system for enhanced web page performance |
CN104584000A (en) * | 2012-07-20 | 2015-04-29 | 蓝凯股份有限公司 | Tag latency monitoring and control system for enhanced web page performance |
CN103793318A (en) * | 2012-10-29 | 2014-05-14 | 百度在线网络技术(北京)有限公司 | Method and device for distributed testing of module stability |
CN102932204B (en) * | 2012-11-09 | 2015-05-20 | 北京奇虎科技有限公司 | Monitoring method and monitoring system of content delivery network |
CN102932204A (en) * | 2012-11-09 | 2013-02-13 | 北京奇虎科技有限公司 | Monitoring method and monitoring system of content delivery network |
CN102938716B (en) * | 2012-12-06 | 2016-06-01 | 网宿科技股份有限公司 | Content distribution network acceleration test method and device |
CN102938716A (en) * | 2012-12-06 | 2013-02-20 | 网宿科技股份有限公司 | Content distribution network acceleration test method and device |
CN104735550A (en) * | 2013-12-19 | 2015-06-24 | 北京四达时代软件技术股份有限公司 | Method and device for managing performance of VCDN system |
CN104735550B (en) * | 2013-12-19 | 2019-02-22 | 北京四达时代软件技术股份有限公司 | A kind of performance management method and device of VCDN system |
CN104767682A (en) * | 2014-01-08 | 2015-07-08 | 腾讯科技(深圳)有限公司 | Routing method and system as well as routing information distributing method and device |
CN104767682B (en) * | 2014-01-08 | 2018-10-02 | 腾讯科技(深圳)有限公司 | The method and apparatus of method for routing and system and distributing routing information |
CN106130816B (en) * | 2016-06-24 | 2018-12-28 | 腾讯科技(深圳)有限公司 | A kind of content distributing network monitoring method, monitoring server and system |
CN106130816A (en) * | 2016-06-24 | 2016-11-16 | 腾讯科技(深圳)有限公司 | A kind of content distributing network monitoring method, monitoring server and system |
CN106412063A (en) * | 2016-09-29 | 2017-02-15 | 赛尔网络有限公司 | CDN node detection and resource scheduling system and method in education network |
CN106412063B (en) * | 2016-09-29 | 2019-08-13 | 赛尔网络有限公司 | CDN node detection and resource scheduling system and method in education network |
CN106656611A (en) * | 2016-12-28 | 2017-05-10 | 成都网丁科技有限公司 | CDN quality evaluation system |
CN107094096A (en) * | 2017-04-19 | 2017-08-25 | 北京云端智度科技有限公司 | A kind of adaptive CDN business diagnosis monitoring systems |
CN108206769A (en) * | 2017-12-26 | 2018-06-26 | 中国移动通信集团江苏有限公司 | Method, apparatus, equipment and the medium of screen quality alarm |
CN108206769B (en) * | 2017-12-26 | 2020-07-17 | 中国移动通信集团江苏有限公司 | Method, apparatus, device and medium for filtering network quality alarms |
CN108964967A (en) * | 2018-02-23 | 2018-12-07 | 云智慧(北京)科技有限公司 | Method and system for intelligently monitoring and analyzing CDN acceleration service |
CN108847984A (en) * | 2018-06-27 | 2018-11-20 | 北京云端智度科技有限公司 | A kind of CDN global load balancing strategy of the health algorithm based on SNMP |
CN110768852A (en) * | 2018-07-25 | 2020-02-07 | 贵州白山云科技股份有限公司 | Method and device for testing cloud network nodes |
CN109547289A (en) * | 2018-12-04 | 2019-03-29 | 杭州安恒信息技术股份有限公司 | A kind of method and system of intelligent scheduling visitor flow |
CN109688023A (en) * | 2018-12-04 | 2019-04-26 | 成都知道创宇信息技术有限公司 | A method of the CDN monitoring availability disposed in a manner of anycast |
CN109547289B (en) * | 2018-12-04 | 2020-10-16 | 杭州安恒信息技术股份有限公司 | Method, storage device and system for intelligently scheduling visitor flow |
CN109688023B (en) * | 2018-12-04 | 2021-10-12 | 成都知道创宇信息技术有限公司 | Method for monitoring availability of CDN (content delivery network) deployed in anycast mode |
CN109639533A (en) * | 2019-01-08 | 2019-04-16 | 深圳市网心科技有限公司 | A kind of test method, system and the terminal device of subdispatch strategy |
CN110855516B (en) * | 2019-10-15 | 2021-10-29 | 厦门美柚股份有限公司 | CDN quality detection system and method |
CN110855516A (en) * | 2019-10-15 | 2020-02-28 | 厦门美柚股份有限公司 | CDN quality detection system and method |
CN112688825B (en) * | 2019-10-18 | 2022-04-05 | 上海哔哩哔哩科技有限公司 | CDN node test method and device and computer equipment |
CN112688825A (en) * | 2019-10-18 | 2021-04-20 | 上海哔哩哔哩科技有限公司 | CDN node test method and device and computer equipment |
CN111884869A (en) * | 2020-05-21 | 2020-11-03 | 网宿科技股份有限公司 | Method, device and system for monitoring network quality |
CN111934924A (en) * | 2020-07-31 | 2020-11-13 | 深圳市高德信通信股份有限公司 | CDN network deployment management system |
CN111934924B (en) * | 2020-07-31 | 2023-05-12 | 深圳市高德信通信股份有限公司 | CDN network deployment management system |
CN113760639A (en) * | 2020-10-19 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Monitoring method, monitoring device, computing equipment and medium |
CN115473871A (en) * | 2022-09-19 | 2022-12-13 | 广州市百果园网络科技有限公司 | Domain name local resolution method and device, equipment, medium and product thereof |
CN115473871B (en) * | 2022-09-19 | 2023-08-04 | 广州市百果园网络科技有限公司 | Domain name local resolution method and device, equipment, medium and product thereof |
CN117241259A (en) * | 2023-11-15 | 2023-12-15 | 长沙时代跳动科技有限公司 | Mobile Internet-based app service management platform and data processing method thereof |
CN117241259B (en) * | 2023-11-15 | 2024-01-19 | 长沙时代跳动科技有限公司 | Mobile Internet-based app service management platform and data processing method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN102347864B (en) | 2013-10-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102347864B (en) | System for monitoring service quality of content distribution networks | |
US20200034216A1 (en) | Router management by an event stream processing cluster manager | |
US9043317B2 (en) | System and method for event-driven prioritization | |
Picoreti et al. | Multilevel observability in cloud orchestration | |
CN110460682A (en) | A kind of data processing method, device, system and storage medium | |
CN101707632A (en) | Method for dynamically monitoring performance of server cluster and alarming real-timely | |
US9231982B2 (en) | Data transfer for network interaction fraudulence detection | |
US20100054128A1 (en) | Near Real-Time Alerting of IP Traffic Flow to Subscribers | |
CN109962790A (en) | A kind of network quality monitoring method, device, electronic equipment and storage medium | |
US8977746B2 (en) | Systems and methods for scalable network monitoring | |
US20100250310A1 (en) | Monitoring organizational information for fast decision making | |
CN104202220A (en) | Pressure test method and pressure test device | |
CN104735088A (en) | Server node adjusting method and device in CDN (content delivery network) | |
CN103945219A (en) | Network side video quality monitoring system | |
CN112491719A (en) | Network node selection method, equipment and storage medium | |
CN107357804A (en) | The analysis system and method for internet finance massive logs | |
CN108235353A (en) | A kind of monitoring system of the urban rail system based on LTE-M communications | |
EP3078180A1 (en) | Performance metric of a system conveying web content | |
CN108964967A (en) | Method and system for intelligently monitoring and analyzing CDN acceleration service | |
CN105530137B (en) | Data on flows analysis method and data on flows analysis system | |
CN114430383B (en) | Detection node screening method and device, electronic equipment and storage medium | |
US8935285B2 (en) | Searchable and size-constrained local log repositories for tracking visitors' access to web content | |
CN105794150A (en) | Method for measuring end-to-end internet application performance | |
US9218205B2 (en) | Resource management in ephemeral environments | |
CN107634881A (en) | A kind of network or video traffic detection system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C56 | Change in the name or address of the patentee | ||
CP02 | Change in the address of a patent holder |
Address after: 200030 Shanghai city Xuhui District Xietu Road No. 2899 Building 5 floor A Kuangchi Cultural Square Patentee after: WANGSU SCIENCE & TECHNOLOGY Co.,Ltd. Address before: 200030 Shanghai Xuhui District Xietu Road No. 2669 15 Floor Patentee before: WANGSU SCIENCE & TECHNOLOGY Co.,Ltd. |
|
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20131030 |