CN104994123B - A kind of traffic scheduling method of CDN cloud platforms and CDN cloud platforms - Google Patents
A kind of traffic scheduling method of CDN cloud platforms and CDN cloud platforms Download PDFInfo
- Publication number
- CN104994123B CN104994123B CN201510239257.7A CN201510239257A CN104994123B CN 104994123 B CN104994123 B CN 104994123B CN 201510239257 A CN201510239257 A CN 201510239257A CN 104994123 B CN104994123 B CN 104994123B
- Authority
- CN
- China
- Prior art keywords
- cdn
- platforms
- time
- monitoring
- flow
- 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
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 55
- 238000013442 quality metrics Methods 0.000 claims abstract description 15
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 238000009472 formulation Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 7
- 238000013441 quality evaluation Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 9
- 238000012360 testing method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- VYZAHLCBVHPDDF-UHFFFAOYSA-N Dinitrochlorobenzene Chemical compound [O-][N+](=O)C1=CC=C(Cl)C([N+]([O-])=O)=C1 VYZAHLCBVHPDDF-UHFFFAOYSA-N 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013497 data interchange Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/61—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources taking into account QoS or priority requirements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention relates to the traffic scheduling methods of a kind of CDN cloud platforms and CDN cloud platforms.The CDN cloud platforms include monitoring verifier network, Operation Support System and multiple CDN platforms, the present invention is monitored each CDN platforms by monitoring verifier network in real time, Operation Support System carries out quality evaluation according to the Service Quality Metrics of acquisition to each CDN platforms, is accurately dispatched to service traffics by dispatching algorithm according to assessment result.The present invention provides better service for Internet user, and due to the convergence effect of resource, cost will be lower, can be used for Internet company and voluntarily builds healthy and strong CDN platforms, and the present invention can generate income to traditional PC business and mobile service.
Description
Technical field
The present invention relates to the flow schedulings of network communication technology field more particularly to a kind of CDN cloud platforms and CDN cloud platforms
Method.
Background technology
Main Internet company's overwhelming majority passes through commercial third party CDN (Content Delivery both at home and abroad at present
Network the bearing capacity and access speed of business) are promoted, by third party CDN platforms service user nearby, is on the one hand dropped
On the other hand low bandwidth cost promotes the access speed of user.Commercial third party CDN is also by their professional operation kimonos
Business is generally capable of Internet company and provides preferable support.
However, being serviced using commercial third party CDN platforms, there is also problems.First, commercial third party CDN is flat
Platform is due to cost, it is impossible to ensure the redundancy of sufficient bandwidth and resource, it is inevitable in many emergency cases, especially part
The degradation of the congestion and quality of regional generation business；Secondly as commercial third-party platform is for Internet company, it is one
A platform service, it may also be said to be a black box that cannot intervene, the api interface usually not to standardize at present, then very
Difficulty intervenes the assignment of traffic of third-party platform by dispatching means, especially catastrophe failure, nothing occurs in third-party platform
Method switches in time causes business to be badly damaged；Finally, business redundancy is carried out even with more commercial third party's CDN platforms
Backup also can ensure that business is timely switched according to quality and interruption at any time without good means at present.
Invention content
The technical problem to be solved by the present invention is in view of the deficiencies of the prior art, provide a kind of CDN cloud platforms and CDN clouds
The traffic scheduling method of platform.
The technical solution that the present invention solves above-mentioned technical problem is as follows：A kind of traffic scheduling method of CDN cloud platforms, including
Following steps：
Structure constitutes monitoring verifier network by multiple monitoring nodes, by each monitoring node to the CDN in each monitoring area
The Service Quality Metrics of platform are monitored；
Operation Support System is built,
The service configuration parameters for receiving user, configure flow scheduling strategy；
Service Quality Metrics of each CDN platforms in each region, predetermined amount of time are obtained, and according to configuration flow scheduling
Strategy gives a mark to the service quality of each CDN platforms within a predetermined period of time using pre-defined algorithm, according in predetermined amount of time
The scoring event of each CDN platforms formulates programs；
Flow allocating is carried out according to the programs of formulation.
The beneficial effects of the invention are as follows：The present invention carries out quality evaluation in real time by monitoring means to each CDN platforms, and leads to
It crosses dispatching algorithm accurately to dispatch service traffics, better service is provided for Internet user, due to the convergence of resource
Effect, cost will be lower, can be used for Internet company and voluntarily build healthy and strong CDN platforms, and the present invention is to traditional PC industry
Business and mobile service can generate income.
Based on the above technical solution, the present invention can also be improved as follows.
Further, the monitoring node is the monitoring server in IDC, is laid on operator of each province.
Advantageous effect using above-mentioned further scheme is：Each CDN platforms can be assessed in real time in each monitoring region (ratio
Ru Fen save divides operator) service quality, scheduler program can be instructed first accurately to be dispatched according to quality, by optimal
Assignment of traffic, obtain business optimal service quality.
Further, the Service Quality Metrics include access reject number and object download time delay, wherein the access is refused
Exhausted number representative accesses monitored target, the number of failed download in the unit interval；The object download time delay represents each
The total duration of HTTP is obtained when secondary access object；The tool given a mark to the service quality of each CDN platforms within a predetermined period of time
Body is embodied as：
Wherein, P represents certain CDN platform objects in the predetermined time and downloads the number that time delay ranks the first, μ be the engineering factor and
Its value is not zero, and T represents time coefficient, smaller from a currently closer period corresponding T values, indicates that distance is current more
The ranking of nearly time is more significant to the overall evaluation,It for engineering parameter, is set according to engineering experience, R was represented in the predetermined time
The number of access reject, γ are the engineering factor, are set according to the practical refusal situation of selected CDN platforms.
Advantageous effect using above-mentioned further scheme is：By the algorithm, the index of service quality can be determined
Amount calculates and assessment；Main evaluation metrics are abstracted, mistuning degree caused by fully taking into account individual shakes and time because
Fairness problem caused by element.
Further, being implemented as flow allocating is carried out according to the programs of formulation：The division of IP address library is saved and is transported
Quotient is sought, is scheduled according to the local DNS IP of user, or is scheduled using 302 scheduling strategies.
Advantageous effect using above-mentioned further scheme is：It, can be smart in a comparison by scheduling controlling using the program
Thin granularity, therefore can carry out fine-grained monitoring and allotment to each CDN platforms is realized with this by each CDN platforms
Good partial set is at an optimal CDN cloud platform.
Further, L2 cache cache is equipped in each CDN platforms, when a certain CDN platforms score when being given a mark
It is minimum, switch certain proportion to the CDN platforms by predetermined ratio, ensures cache preliminary fillings.
Advantageous effect using above-mentioned further scheme is：Ensure in certain areas flowed between multiple CDN platforms
It when amount switching, will not occur to be not hit by because of cache, cause a large amount of direct Hui Yuan, great pressure is caused to source station.
Further, further include that each CDN platforms are periodically sent by the specification api interface established with CDN management and running center
Its surplus in each region is to Operation Support System, and before carrying out flow allocating, CDN management and running center is to each CDN platforms
Resource idle condition judged, according to judging result carry out flow allocating.
Advantageous effect using above-mentioned further scheme is：Basic CDN platforms letter is obtained by the specification api interface
Breath, such as data on flows, utilization rate etc., avoid the occurrence of when carrying out flow scheduling, and especially some CDN platform occurs whole
Body failure may cause directly to kill certain if it is not known that each CDN platforms are directly switched in the surplus in each area
The case where one CDN platform.
The technical solution that the present invention solves above-mentioned technical problem is as follows：A kind of CDN cloud platforms, including monitoring verifier network,
Operation Support System and multiple CDN platforms；
The monitoring verifier network is made of multiple monitoring nodes, by each monitoring node to the CDN in each monitoring area
The Service Quality Metrics of platform are monitored, and monitoring result is sent to Operation Support System；
The Operation Support System includes：
User configuration management platform is used to receive the service configuration parameters of user, is configured to flow scheduling strategy；
Flow scheduling platform is used to obtain service quality of each CDN platforms in each region, predetermined amount of time and refers to
Mark, and according to the flow scheduling strategy of configuration using pre-defined algorithm to each CDN platforms service quality within a predetermined period of time into
Row marking formulates programs according to the scoring event of each CDN platforms in predetermined amount of time；
Domain name mapping DNS is used to carry out flow allocating according to the programs that flow scheduling platform is formulated.
Description of the drawings
Fig. 1 is a kind of traffic scheduling method flow chart of CDN cloud platforms of the present invention；
Fig. 2 is three CDN platforms of the present invention Beijing area, 8 hours HTTP time delay comparison diagrams；
Fig. 3 is three CDN platforms of the present invention Beijing area, 8 hours access reject rate comparison diagrams；
Fig. 4 is a kind of flow scheduling system block diagram of CDN cloud platforms of the present invention.
Specific implementation mode
The principle and features of the present invention will be described below with reference to the accompanying drawings, and the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
The present invention includes following main points：
1) Operation Support System is built, for docking Internet user, the business for carrying user accelerates it.
The one-touch of user is supported to reach the standard grade.Operation Support System includes mainly：User configuration management platform, flow scheduling platform and a set of
High-performance domain name mapping DNS；
2) api interface that specification is established with more commercial third party's CDN platforms, can be obtained substantially by this interface
Platform information, such as data on flows, utilization rate etc.；
3) the monitoring node for building national each province operators distribution, it is any when occurring for detecting the quality of service of carrying
Quality fluctuation can manipulate the assignment of traffic of third party's CDN platforms by the intelligent scheduling logic of Operation Support System.
The main thought of this programme is to be docked with multiple commercial third party's CDN platforms, form a resource pool,
In can also include the own CDN node of a part.The resource free time feelings of each platform can be obtained by specification api interface
Condition, while it being placed on by national cloth the monitoring probe (monitoring server in IDC) of main operator of province, with operator of province
The quality of the whole platforms of granularity detection.With certain period (for example one day) with the granularity of operator of province by flow in each CDN
It is allocated with optimal quality in platform, breaking down when some areas of some CDN platform can also find and carry out in time
Flow allocating.It is experimentally confirmed, said program is in the case where choosing three commercialization CDN platforms, the resource pool service of composition
Quality compared with three in optimal promotion 10%, more worst promotion 50% will be complete and by the CDN clouds of this scheme constructs
Evading the failure of an independent CDN platform influences.
As shown in Figure 1, a kind of traffic scheduling method of CDN cloud platforms, includes the following steps：
Structure constitutes monitoring verifier network by multiple monitoring nodes, by each monitoring node to the CDN in each monitoring area
The Service Quality Metrics of platform are monitored.
In the present embodiment, the monitoring node is the monitoring server in IDC, is laid on operator of each province.In the whole nation
Monitoring verifier network is built by main operator of province, at least ensures that there are one the monitoring sections stablized for the main operator of province in the whole nation
Point.By these monitoring nodes, service URL to be monitored is periodically obtained, to respectively represent the access of each operator of province
Quality.Below with a srvice instance explanation.
The entitled www.test.com of certain business domains, business first choice in the switching granularity of DNS accomplish province's operator grade,
I.e. the granularity of View is operator of province.
Using the commercial third party's CDN platforms of A, B, C tri-, three platforms be respectively service creation test.cdna.com,
Test.cdnb.com and test.cdnc.com.
By the monitoring verifier network of structure, in test.cdna.com, test.cdnb.com and test.cdnc.com
A test object carry out every 1 minute 1 time crawl monitoring, monitoring reject rate and download time delay two indices, for example Beijing
Telecommunications is optimal in A platform mass, just by Beijing Telecom flow CNAME to test.cdna.com.
Build Operation Support System, including user configuration management platform, flow scheduling platform and domain name mapping DNS.
Wherein, user configuration management platform receives the service configuration parameters of user, is configured to flow scheduling strategy.
Flow scheduling platform obtains Service Quality Metrics of each CDN platforms in each region, predetermined amount of time, and according to
Configuration flow scheduling strategy gives a mark to the service quality of each CDN platforms within a predetermined period of time using pre-defined algorithm, according to
The scoring event of each CDN platforms formulates programs in predetermined amount of time.
Specifically, the Service Quality Metrics include access reject number and object download time delay, wherein the access is refused
Exhausted number representative accesses monitored target, the number of failed download in the unit interval；The object download time delay represents each
The total duration of HTTP is obtained when secondary access object.
Fig. 2 is three CDN platforms Beijing areas, 8 hours HTTP time delay comparison diagrams.Wherein abscissa is the time, when acquiring total
Between be 8 hours；Ordinate is the time of object download, and what it is in bottom is to rank the first.
Fig. 3 is three CDN platforms Beijing areas, 8 hours access reject rate comparison diagrams.Wherein abscissa is the time, and acquisition is total
Time is 8 hours；Ordinate is access reject rate, and what it is in bottom is to rank the first.
It is implemented as to what the service quality of each CDN platforms within a predetermined period of time was given a mark：
Wherein, P represents in the predetermined time (can be 1 hour) certain CDN platform objects and downloads the number that time delay ranks the first,
For example the acquisition granularity is 1 minute, has 50 times in 60 monitorings of A platforms and ranks the first；μ is the engineering factor, is considered to possible 0 ranking
First, value is not zero, through overtesting, best results when value is 2；T represents time coefficient, when indicating that distance is current closer
Between ranking it is more significant to the overall evaluation；For engineering parameter, set according to engineering experience, in additionDistance is allowed for work as
It is preceding closely denominator to be caused too small excessively；R represents in the predetermined time number of (can be 1 hour) access reject, therefore, if visited
It asks that the number of refusal is relatively more, score will be seriously affected；γ is the engineering factor, according to the practical refusal of selected CDN platforms
Situation is set.
P in formula has the factor of HTTP durations.The principle of formula is, for example 24 hours one inferior qualities of period progress are commented
Estimate, 24 periods can be divided into, and there can be 60 monitorings in each 1 hour period, that is, 1 minute monitoring network is visited
It surveys primary.So for last 1 hour, some CDN platforms ratio in more CDN is all that HTTP total durations are most short if any 50 times
, rank the first for exactly 50 times, P is equal to 50, behind plus μ the case where being the engineering factor, molecule is avoided to be 0.T in denominator is then
It is to take 1, because being the last one hour, and so on, penultimate hour, T is equal to 2, that is to say, that closer from currently
A period it is more important to assessment result.R and r is reflection refusal number.
According to the algorithm above, gives a mark to every 24 hours, select the highest node of somewhere quality score, and right
The flow allocating of operator of corresponding province.(flow allocating can be carried out, but examine according to this algorithm to arbitrary a period of time in engineering
Consider shake and the metering period of quality, most preferably realized for engineering within 24 hours).
On scheduling mechanism, IP address library operator of division province can be scheduled according to the local DNS IP of user,
302 scheduling strategies can also be used.
In carrying out Project Realization, following critical issue can be encountered, we solve in the following way.
1) cache preliminary fillings
According to experiment, there is the advantage of different regions in each third party CDN platforms in resource pool, so, it is desirable that it is each
A third party CDN platforms design the caching cache of two level, and each area is that have more CDN that can cover, therefore work as and carry out
It when the flow of each department switches between each CDN, will not occur to be not hit by because of cache, cause a large amount of direct Hui Yuan, give source station
Cause great pressure.And if one of third-party platform in each area of the currently monitored period all without advantage, can be by
The certain flow of a small amount of proportion switch ensures cache preliminary fillings to this platform.
2) third party's api interface
Above-mentioned technical proposal further includes that each CDN platforms are regular by the specification api interface established with CDN management and running center
Its surplus in each region is sent to Operation Support System, before carrying out flow allocating, CDN management and running center is to each CDN
The resource idle condition of platform is judged, flow allocating is carried out according to judging result.It avoids the occurrence of when carrying out flow scheduling,
Especially there is overall failure in some CDN platform, if it is not known that surplus of each CDN platforms in each area, directly into
Row switching, the case where may causing directly to kill some CDN platform.
Specifically, when carrying out flow scheduling, when especially overall failure occurs in some CDN platform, if it is not known that respectively
A CDN platforms are directly switched in the surplus in each area, the case where may causing directly to kill some CDN platform.Cause
This defines an API, can periodically pass the surplus of each operator of province back by each CDN platforms, can be Json encapsulation, than
Such as：
Wherein area indicates that area, isp indicate that operator, quota indicate surplus (unit Gbps)
{
data:[
{
area:" Beijing ",
isp:"ct",
quota:10
},
{
area:" Hunan ",
isp:"ct",
quota:20
}
]
}
Here is the annotation to some vocabulary.
Cache：The software systems of content are accessed for cache user.
Commercial third party CDN:Profession provides the CDN CDN platforms for accelerating service, for example, domestic blue flood, net place, fast net,
Supreme Being's connection etc..
HTTP GET：The request that some url is downloaded of http encapsulation.
View:DNS systems are the view function that intelligently parsing provides.
IP is dispatched：The method being scheduled by the IP of Local DNS.
302 scheduling：Request is redirected by 302 by control centre and is scheduled.
Json：It is a kind of data interchange format of lightweight.
As shown in figure 4, a kind of CDN cloud platforms, including monitoring verifier network, Operation Support System and multiple CDN platforms；
The monitoring verifier network is made of multiple monitoring nodes, by each monitoring node to the CDN in each monitoring area
The Service Quality Metrics of platform are monitored, and monitoring result is sent to Operation Support System；
The Operation Support System includes：
User configuration management platform is used to receive the service configuration parameters of user, is configured to flow scheduling strategy；
Flow scheduling platform is used to obtain service quality of each CDN platforms in each region, predetermined amount of time and refers to
Mark, and according to the flow scheduling strategy of configuration using pre-defined algorithm to each CDN platforms service quality within a predetermined period of time into
Row marking formulates programs according to the scoring event of each CDN platforms in predetermined amount of time；
Domain name mapping DNS is used to carry out flow allocating according to the programs that flow scheduling platform is formulated.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent replacement, improvement and so on should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of traffic scheduling method of CDN cloud platforms, which is characterized in that include the following steps：
Structure constitutes monitoring verifier network by multiple monitoring nodes, by each monitoring node to the CDN platforms in each monitoring area
Service Quality Metrics be monitored；
Operation Support System is built,
The service configuration parameters for receiving user, configure flow scheduling strategy；
Service Quality Metrics of each CDN platforms in each region, predetermined amount of time are obtained, and according to the flow scheduling plan of configuration
It is slightly given a mark to the service quality of each CDN platforms within a predetermined period of time using pre-defined algorithm, according to each in predetermined amount of time
The scoring event of CDN platforms formulates programs；
Flow allocating is carried out according to the programs of formulation；
The Service Quality Metrics include access reject number and object download time delay, wherein the access reject number represents
Monitored target, the number of failed download are accessed in unit interval；The object download time delay is represented to access each time and is monitored
The total duration of HTTP, the specific implementation given a mark to the service quality of each CDN platforms within a predetermined period of time are obtained when object
For：
Wherein, P represents the number that the object download time delay of certain the CDN platform predetermined time Nei ranks the first, and μ is the engineering factor
And its value is not zero, T represents time coefficient, smaller from a currently closer period corresponding T values, indicates that distance is current
The ranking of nearlyr time is more significant to the overall evaluation,It for engineering parameter, is set according to engineering experience, R represents the predetermined time
The number of interior access reject, γ are the engineering factor, are set according to the practical refusal situation of selected CDN platforms.
2. a kind of traffic scheduling method of CDN cloud platforms according to claim 1, which is characterized in that the monitoring node is
Monitoring server in IDC is laid on operator of each province.
3. a kind of traffic scheduling method of CDN cloud platforms according to claim 1, which is characterized in that according to the allotment of formulation
Scheme carries out being implemented as flow allocating：IP address in IP address library is divided by different operators of province, root
It is scheduled according to the local DNS IP of user, or is scheduled using 302 scheduling strategies.
4. a kind of traffic scheduling method of CDN cloud platforms according to claim 1, which is characterized in that in each CDN platforms
Equipped with L2 cache cache, when a certain CDN platforms score when being given a mark is minimum, switch by predetermined ratio a certain proportion of
Flow ensures cache preliminary fillings to the CDN platforms.
5. a kind of traffic scheduling method of CDN cloud platforms according to claim 1, which is characterized in that further include each CDN platforms
Its surplus in each region, which is periodically sent, by the specification api interface established with CDN management and running center gives operation support system
System, before carrying out flow allocating, CDN management and running center judges the resource idle condition of each CDN platforms, according to judgement
As a result flow allocating is carried out.
6. a kind of CDN cloud platforms, which is characterized in that including monitoring verifier network, Operation Support System and multiple CDN platforms；
The monitoring verifier network is made of multiple monitoring nodes, by each monitoring node to the CDN platforms in each monitoring area
Service Quality Metrics be monitored, and monitoring result is sent to Operation Support System；
The Operation Support System includes：
User configuration management platform is used to receive the service configuration parameters of user, is configured to flow scheduling strategy；
Flow scheduling platform is used to obtain Service Quality Metrics of each CDN platforms in each region, predetermined amount of time, and
The service quality of each CDN platforms within a predetermined period of time is beaten using pre-defined algorithm according to the flow scheduling strategy of configuration
Point, programs are formulated according to the scoring event of each CDN platforms in predetermined amount of time；
Domain name mapping DNS is used to carry out flow allocating according to the programs that flow scheduling platform is formulated；
The Service Quality Metrics include access reject number and object download time delay, wherein the access reject number represents
Monitored target, the number of failed download are accessed in unit interval；The object download time delay is represented to access each time and is monitored
The total duration of HTTP, the specific implementation given a mark to the service quality of each CDN platforms within a predetermined period of time are obtained when object
For：
Wherein, P represents the number that the object download time delay of certain the CDN platform predetermined time Nei ranks the first, and μ is the engineering factor
And its value is not zero, T represents time coefficient, smaller from a currently closer period corresponding T values, indicates that distance is current
The ranking of nearlyr time is more significant to the overall evaluation,It for engineering parameter, is set according to engineering experience, R represents the predetermined time
The number of interior access reject, γ are the engineering factor, are set according to the practical refusal situation of selected CDN platforms.
7. a kind of CDN cloud platforms according to claim 6, which is characterized in that the monitoring node is the monitoring service in IDC
Device is laid on operator of each province.
8. a kind of CDN cloud platforms according to claim 6, which is characterized in that domain name parses DNS, is used for according to stream
Amount dispatching platform formulate programs carry out flow allocating concrete operations be：By the IP address in IP address library by different
Operator of province is divided, and is scheduled according to the local DNS IP of user, or is scheduled using 302 scheduling strategies.
9. a kind of CDN cloud platforms according to claim 6, which is characterized in that be equipped with L2 cache in each CDN platforms
Cache, when a certain CDN platforms score when being given a mark is minimum, it is flat to the CDN to switch a certain proportion of flow by predetermined ratio
Platform ensures cache preliminary fillings.
10. a kind of CDN cloud platforms according to claim 6, which is characterized in that the flow scheduling platform and each CDN platforms
Between establish specification api interface, its surplus in each region that each CDN platforms are periodically sent by api interface, flow scheduling is flat
Platform is judged before carrying out flow allocating by the resource idle condition to each CDN platforms, and flow is carried out according to judging result
Allotment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510239257.7A CN104994123B (en) | 2015-05-12 | 2015-05-12 | A kind of traffic scheduling method of CDN cloud platforms and CDN cloud platforms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510239257.7A CN104994123B (en) | 2015-05-12 | 2015-05-12 | A kind of traffic scheduling method of CDN cloud platforms and CDN cloud platforms |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104994123A CN104994123A (en) | 2015-10-21 |
| CN104994123B true CN104994123B (en) | 2018-10-02 |
Family
ID=54305874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510239257.7A Active CN104994123B (en) | 2015-05-12 | 2015-05-12 | A kind of traffic scheduling method of CDN cloud platforms and CDN cloud platforms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104994123B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105634992B (en) | 2015-12-29 | 2019-01-11 | 网宿科技股份有限公司 | CDN platform adaptive band width control method and system |
| CN105471759B (en) * | 2016-01-11 | 2018-06-01 | 北京百度网讯科技有限公司 | The network traffics dispatching method and device of data center |
| 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 |
| US10897406B2 (en) | 2017-01-22 | 2021-01-19 | Huawei Technologies Co., Ltd. | Scheduling method for content delivery network, and device |
| CN106992938B (en) * | 2017-05-15 | 2020-03-31 | 网宿科技股份有限公司 | Network flow dynamic scheduling and distributing method and system |
| CN107707378B (en) | 2017-06-29 | 2018-11-13 | 贵州白山云科技有限公司 | A kind of CDN covering scheme generation method and device |
| CN109688171B (en) * | 2017-10-18 | 2021-05-25 | 中国电信股份有限公司 | Cache space scheduling method, device and system |
| CN107995042A (en) * | 2017-12-14 | 2018-05-04 | 北京云端智度科技有限公司 | A kind of network quality appraisal procedure |
| CN110401552A (en) * | 2018-04-24 | 2019-11-01 | 贵州白山云科技股份有限公司 | A kind of CDN business automated tuning method and device |
| 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 |
| CN109167674B (en) * | 2018-07-24 | 2021-05-18 | 网宿科技股份有限公司 | Service node scoring method, Domain Name System (DNS) scheduling method and server |
| CN108881516B (en) * | 2018-07-27 | 2021-03-19 | 网宿科技股份有限公司 | Method and device for scheduling multi-CDN service system |
| 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 |
| CN111353658B (en) * | 2018-12-20 | 2023-06-20 | 中央电视台 | Television program production monitoring system and method |
| CN111245684B (en) * | 2020-01-13 | 2021-12-21 | 智者四海（北京）技术有限公司 | Traffic scheduling method and device, electronic equipment and computer readable medium |
| CN112134811B (en) * | 2020-09-30 | 2022-08-09 | 安徽极玩云科技有限公司 | CDN cloud platform flow scheduling method |
| CN113010410A (en) * | 2020-12-08 | 2021-06-22 | 云智慧（北京）科技有限公司 | Method and system for monitoring and evaluating CDN performance based on backbone network |
| CN113179224B (en) * | 2021-04-28 | 2022-10-28 | 北京达佳互联信息技术有限公司 | Traffic scheduling method and device for content distribution network |
| CN115333982B (en) * | 2021-05-11 | 2024-02-09 | 北京金山云网络技术有限公司 | Flow monitoring method, device, equipment and computer readable storage medium |
| CN113766004A (en) * | 2021-07-27 | 2021-12-07 | 深圳市珍爱捷云信息技术有限公司 | Disaster recovery system, method and storage medium based on multi-cloud platform |
| CN113765705A (en) * | 2021-08-12 | 2021-12-07 | 深圳市珍爱捷云信息技术有限公司 | Traffic switching method and traffic management server for cross-public-cloud dual-active structure |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2741895A1 (en) * | 2008-11-17 | 2010-05-20 | Amazon Technologies, Inc. | Request routing and updating routing information utilizing client location information |
| CN101989986A (en) * | 2010-10-28 | 2011-03-23 | 北京瑞汛世纪科技有限公司 | Method for inquiring service node, server and system |
| CN102437965A (en) * | 2012-01-13 | 2012-05-02 | 北京润通丰华科技有限公司 | Method and device for accessing target site |
| CN103986977A (en) * | 2014-04-15 | 2014-08-13 | 上海聚力传媒技术有限公司 | Method and device for preloading video in content distribution network |
| CN104009890A (en) * | 2014-06-10 | 2014-08-27 | 江苏省邮电规划设计院有限责任公司 | Test system and method for network quality in Internet |
| CN104168300A (en) * | 2013-05-17 | 2014-11-26 | 中国电信股份有限公司 | Content acceleration method and system |
-
2015
- 2015-05-12 CN CN201510239257.7A patent/CN104994123B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2741895A1 (en) * | 2008-11-17 | 2010-05-20 | Amazon Technologies, Inc. | Request routing and updating routing information utilizing client location information |
| CN101989986A (en) * | 2010-10-28 | 2011-03-23 | 北京瑞汛世纪科技有限公司 | Method for inquiring service node, server and system |
| CN102437965A (en) * | 2012-01-13 | 2012-05-02 | 北京润通丰华科技有限公司 | Method and device for accessing target site |
| CN104168300A (en) * | 2013-05-17 | 2014-11-26 | 中国电信股份有限公司 | Content acceleration method and system |
| CN103986977A (en) * | 2014-04-15 | 2014-08-13 | 上海聚力传媒技术有限公司 | Method and device for preloading video in content distribution network |
| CN104009890A (en) * | 2014-06-10 | 2014-08-27 | 江苏省邮电规划设计院有限责任公司 | Test system and method for network quality in Internet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104994123A (en) | 2015-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104994123B (en) | A kind of traffic scheduling method of CDN cloud platforms and CDN cloud platforms | |
| CN107465708B (en) | CDN bandwidth scheduling system and method | |
| CN102791032B (en) | Internet wide band distribution and terminal | |
| CN102498696B (en) | Usage policing in data networks | |
| CN105593823B (en) | Method, system and computer readable storage medium for the data packet flows between the virtual machine VM in monitoring data center | |
| US20170142177A1 (en) | Method and system for network dispatching | |
| WO2017045527A1 (en) | Method and apparatus for data analytics management | |
| CN105242956B (en) | Virtual functions service chaining deployment system and its dispositions method | |
| EP3629521B1 (en) | Rating method for service node, domain name system (dns) scheduling method and server | |
| CN107707382B (en) | A kind of intelligent dispatching method and device | |
| CN110381541A (en) | A kind of smart grid slice distribution method and device based on intensified learning | |
| CN105872079B (en) | A kind of link equalization method based on domain name system DNS | |
| CN112512100B (en) | Slice priority-based AMF (advanced metering framework) redirection method and newly-added management network element | |
| EP3278578B1 (en) | Method and system for mtc event management | |
| CN103248561A (en) | Cross-platform and cross-terminal communication method and message system | |
| CN101599908B (en) | Method and equipment for automatically distributing bandwidth | |
| CN102546232B (en) | Multi-topology mapping method of virtual network | |
| EP2996285B1 (en) | Scheduling method, apparatus and system | |
| CN102724103A (en) | Proxy server, hierarchical network system and distributed workload management method | |
| CN104243609B (en) | A kind of information service method for pushing and device | |
| CN109660376A (en) | A kind of mapping method of virtual network, equipment and storage medium | |
| CN104717231A (en) | Pre-distribution processing method and device of content distribution network | |
| WO2015014176A1 (en) | Method, device, scheduling server and system for network allocation | |
| CN105656964B (en) | The implementation method and device of data-pushing | |
| US20220053373A1 (en) | Communication apparatus, communication method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20181219 Address after: 100000 Beijing Chaoyang District Changhui Road Building 5 Floor 5 Unit 503 Patentee after: BEIJING ISURECLOUD TECHNOLOGY CO.,LTD. Address before: 100027 SOHO-Tower 2-C, Wangjing, Chaoyang District, Beijing Patentee before: Duan Liping |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20151021 Assignee: Zhongguancun Technology Leasing Co.,Ltd. Assignor: BEIJING ISURECLOUD TECHNOLOGY CO.,LTD. Contract record no.: X2022110000006 Denomination of invention: A CDN cloud platform and a traffic scheduling method of CDN cloud platform Granted publication date: 20181002 License type: Exclusive License Record date: 20220225 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A CDN cloud platform and a traffic scheduling method of CDN cloud platform Effective date of registration: 20220225 Granted publication date: 20181002 Pledgee: Zhongguancun Technology Leasing Co.,Ltd. Pledgor: BEIJING ISURECLOUD TECHNOLOGY CO.,LTD. Registration number: Y2022980001960 |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: Zhongguancun Technology Leasing Co.,Ltd. Assignor: BEIJING ISURECLOUD TECHNOLOGY CO.,LTD. Contract record no.: X2022110000006 Date of cancellation: 20231008 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20231008 Granted publication date: 20181002 Pledgee: Zhongguancun Technology Leasing Co.,Ltd. Pledgor: BEIJING ISURECLOUD TECHNOLOGY CO.,LTD. Registration number: Y2022980001960 |