CN104580012B - A kind of selection method and device of content delivery network node - Google Patents

A kind of selection method and device of content delivery network node Download PDF

Info

Publication number
CN104580012B
CN104580012B CN201310478535.5A CN201310478535A CN104580012B CN 104580012 B CN104580012 B CN 104580012B CN 201310478535 A CN201310478535 A CN 201310478535A CN 104580012 B CN104580012 B CN 104580012B
Authority
CN
China
Prior art keywords
network
node
service
network service
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
Application number
CN201310478535.5A
Other languages
Chinese (zh)
Other versions
CN104580012A (en
Inventor
饶明
曾东方
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Tencent Computer Systems Co Ltd
Original Assignee
Shenzhen Tencent Computer Systems Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Tencent Computer Systems Co Ltd filed Critical Shenzhen Tencent Computer Systems Co Ltd
Priority to CN201310478535.5A priority Critical patent/CN104580012B/en
Publication of CN104580012A publication Critical patent/CN104580012A/en
Application granted granted Critical
Publication of CN104580012B publication Critical patent/CN104580012B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

A kind of selection method of content delivery network node, including:When receive for the request of first network services selection node when, the flow information of the second network service in multiple nodes is obtained respectively, according to the historical traffic information of the second network service, determine the network flow peak value of the second network service in given statistics duration, the maximum network bandwidth of multiple nodes is obtained respectively, using the maximum network bandwidth of multiple nodes and the difference of the network flow peak value of the second network service as available network bandwidth, node is selected according to the available network bandwidth.The selection method and device of the above distribution network node, node bandwidth can be efficiently used, and works as the node for possessing a large amount of first network services after first network services, be not in that data traffic significantly falls sharply and causes network load unbalanced, to be more favorable for CDN network operation.

Description

A kind of selection method and device of content delivery network node
Technical field
The present invention relates to the selection methods and device of field of communication technology more particularly to a kind of content delivery network node.
Background technology
According to statistics, the flow for being up to 60% in mobile Internet at present comes from Online Video service, plays video content Opposite display word, the basic contents such as picture need to occupy massive band width, and conventional the Internet service provider faces more and more Bandwidth pressure.
In the prior art, content distributing network (CDN, Content are generally used when Online Video service provider provides service Delivery Network) technology come solve the problems, such as present in video playing play response speed it is not fast enough, due to CDN nets Geographical location can significantly improve connection when particular video frequency is accessed close to user and efficient cache caching technologies in network And broadcasting speed, and the pressure of data center (DC, Data Center) server, effective load sharing can be alleviated.
But in the prior art, the calling system in CDN is not added with order video and live video the scheduling of differentiation above, It can lead to occur a large amount of live streaming connections in metropolitan area point (OC, Outside Center) server of offer current video service.By After successful connection is broadcast live i.e. can not switching server characteristic, the data traffic into OC servers can not effectively be switched to it His server is likely to occur the case where OC servers can not provide service for former business at flow peak.Also, possess a large amount of The OC servers of live streaming connection will occur data traffic after live streaming and significantly fall sharply, and cause network load unbalanced, no It is run conducive to CDN network.Furthermore live video business needs operation and maintenance personnel real in the bandwidth usage of each OC servers When control, human cost consumption is big, and OC server bandwidths are difficult to be utilized effectively.
Invention content
In view of this, the present invention provides a kind of selection method and device of content delivery network node, section can be efficiently used Point bandwidth.
The selection method of content delivery network node provided in an embodiment of the present invention, including:
When receive for the request of first network services selection node when, obtain the second network service in multiple nodes respectively Flow information;According to the historical traffic information of the second network service, determine described second in given statistics duration The network flow peak value of network service;The maximum network bandwidth of the multiple node is obtained respectively;Respectively by the multiple node Maximum network bandwidth and the second network service network flow peak value difference as available network bandwidth;According to described Available network bandwidth selects node.
The selection device of content delivery network node provided in an embodiment of the present invention, including:
Acquiring unit, for when receive for the request of first network services selection node when, obtain multiple nodes respectively In the second network service flow information;Determination unit, according to the historical traffic information of the second network service, determine to The network flow peak value of the second network service in fixed statistics duration;The acquiring unit is additionally operable to obtain respectively described The maximum network bandwidth of multiple nodes;The determination unit is additionally operable to the multiple section for respectively obtaining the acquiring unit The maximum network bandwidth of point and the difference of the network flow peak value of the second network service are as available network bandwidth;Selection is single Member, the available network bandwidth for being determined according to the determination unit select node.
The selection method and device of content delivery network node provided in an embodiment of the present invention, obtain second in multiple nodes The flow information of network service determines further according to the historical traffic information of the second network service in given statistics The network flow peak value of the second network service in long, according to the difference of the maximum network bandwidth and the network flow peak value of each node Value can determine the available network bandwidth of first network service in each node, and node is selected according to the available network bandwidth, that , can be simultaneous according to the second network service history flow in determining statistics duration when for first network services selection node Being calculated under the premise of caring for network bandwidth used in the service of the second network in egress can also be first network service distribution Available network bandwidth can efficiently use node bandwidth, and work as the node for possessing a large amount of first network services in first network Be not in that data traffic significantly falls sharply and causes network load unbalanced, to be more favorable for CDN network after service Operation.
For the above and other objects, features and advantages of the present invention can be clearer and more comprehensible, preferred embodiment cited below particularly, And coordinate institute's accompanying drawings, it is described in detail below.
Description of the drawings
Fig. 1 is first embodiment schematic diagram of the selection method of content delivery network node in the embodiment of the present invention;
Second embodiment schematic diagram of the selection method of content delivery network node in Fig. 2 embodiment of the present invention;
Fig. 3 is a network service history total flow of the selection method of content delivery network node in the embodiment of the present invention Curve graph;
Fig. 4 is the history of a first network service of the selection method of content delivery network node in the embodiment of the present invention Flow curve figure;
Fig. 5 is that another network service history of the selection method of content delivery network node in the embodiment of the present invention always flows Measure curve graph;
Fig. 6 is that another first network service of the selection method of content delivery network node in the embodiment of the present invention is gone through History flow curve figure;
Fig. 7 is to dispatch system structure diagram in the embodiment of the present invention;
Fig. 8 is first embodiment schematic diagram of the selection device of content delivery network node in the embodiment of the present invention;
Fig. 9 is second embodiment schematic diagram of the selection device of content delivery network node in the embodiment of the present invention;
Figure 10 is a kind of server architecture schematic diagram provided in an embodiment of the present invention.
Specific implementation mode
Further to illustrate that the present invention is the technological means and effect realized predetermined goal of the invention and taken, below in conjunction with Specific implementation mode, structure, feature and its effect according to the present invention is described in detail as after in attached drawing and preferred embodiment.
Referring to Fig. 1, one embodiment packet of the selection method of content delivery network node in the embodiment of the present invention It includes:
101, when receive for the request of first network services selection node when, obtain the second network in multiple nodes respectively The flow information of service;
Interior joint of the embodiment of the present invention is the cross-connection point of signal in network, is the slotting joint of business point, can be clothes Business device can also be server cluster, provide the computer room etc. of business.Network can be CDN network.
Scheduling system receive for the request of first network services selection node when, obtain the second net in multiple nodes respectively The flow information of network service.
102, according to the historical traffic information of the second network service, second network in given statistics duration is determined The network flow peak value of service;
The historical traffic information can be multiple historical traffic information, every day such as before current date this second The historical traffic information of network server.The network flow peak value of the second network service refers to being somebody's turn to do in the given duration Second network services occupied network flow maximum value.In the present embodiment, comprehensive multiple historical traffics determine second network The network flow peak value of service more can accurately obtain the network flow peak value of the second network service.
103, the maximum network bandwidth of multiple node is obtained respectively;
The network bandwidth upper limit value of each node is obtained respectively.
104, respectively by the difference of the maximum network bandwidth of multiple node and the network flow peak value of the second network service Value is used as available network bandwidth;
The summation of first network service and the occupied bandwidth of the second network service cannot exceed maximum network bandwidth, calculate most The network flow peak value of big network bandwidth and the second network service, then can get the available net of first network service in each node Network bandwidth.
105, node is selected according to the available network bandwidth.
According to the available network bandwidth of each node, for the corresponding section of request selecting of the first network services selection node Point.
In the embodiment of the present invention, scheduling system obtains the flow information of the second network service in multiple nodes, further root According to the historical traffic information of the second network service, the network flow of the second network service in given statistics duration is determined Peak value can determine first network in each node according to the difference of the maximum network bandwidth of each node and the network flow peak value The available network bandwidth of service selects node according to the available network bandwidth, then, for first network services selection node When, network used in the service of the second network can be taken into account according to the second network service history flow in statistics duration is being determined It is the available network bandwidth of first network service distribution to be calculated under the premise of bandwidth in egress, can efficiently use section Point bandwidth, and work as the node for possessing a large amount of first network services after first network services, be not in data traffic Significantly fall sharply and cause network load unbalanced, to be more favorable for CDN network operation.
Referring to Fig. 2, second embodiment packet of the selection method of content delivery network node in the embodiment of the present invention It includes:
201, when receive for the request of first network services selection node when, obtain the second network in multiple nodes respectively The flow information of service;
First network service in the embodiment of the present invention can be live video service, can be live audio service, Can be the network service of other request selecting nodes, first network service once starts in some node, then can not replace it His node, and the node that can only start herein continues to complete follow-up service, the second network service can be except live video service Except other network services, such as video on demand service, On-demand audio service, there may be multiple simultaneously in the same node Second network service.Node is the cross-connection point of signal in network, is the slotting joint of business point, can be server, also may be used To be server cluster, provide the computer room etc. of business.
The present embodiment be described below in by first network service be live video for, the second network service regards for program request For frequency.
Scheduling system receive for the request of live video services selection node when, obtain respectively in multiple nodes except live streaming Other networks service is occupied in the flow information of other network services except Video service, namely the multiple nodes of acquisition Bandwidth information, the video on demand service flow such as obtained are 5,000,000,000.
202, the duration by the current first network service is determined as given statistics duration;
The duration of the live video service currently carried out can be broadcast recording the specific of the live video service It puts inquiry in the list of time to obtain, e.g., the live video service currently carried out is that the tennis singles final of sports channel is straight Video service is broadcast, then can find the duration of the live video service in the TV guide table of sports channel.
The duration of the current live video service is determined as given statistics duration, e.g., the current live video The duration of service is from 12 points to 15 point, then given statistics duration is also 12 points to 15 points.
203, in preset measurement period, multiple history of the second network service in the given statistics duration are counted Flow information;
Measurement period can be self-defined according to system statistics situation, such as can be to count the program request daily using day as the period The historical traffic information of Video service can also be the historical traffic letter for counting the video on demand service weekly using week as the period Breath.
In preset measurement period, multiple historical traffics of the video on demand service in the given statistics duration are counted Information, e.g., today are Thursday, and timing statistics are 12 points to 15 points, then count 12 points to 15 points of Wednesday (i.e. the previous day of Thursday) The flow information of the video on demand service counts flow information of 12 points of the previous Wednesday to 15 points of video on demand service, system Flow information of 12 points of the previous Wednesday to 15 points of video on demand service again is counted, and so on, count order video clothes Multiple historical traffic information of business.
Since the service that node provides might have multiple, the flow of the video on demand service needs to be superimposed many networks clothes The flow value of business, multiple flow value superpositions, which may be brought, calculates the big problem of error, so the system given in preset measurement period The flow that the overall network flow of the all-network service counted in timing length subtracts the live video service obtains the order video The flow of service is more accurate.
Concrete example illustrates that current time is by taking September 8 days as an example, then network service history total flow information can count it The flow information on the 1st of September on the same day of the previous day September 7 days and last week.Fig. 3-6 is please referred to, September net on the 7th has been recorded in Fig. 3 The peak value of network service history total-flow-rate curve figure, network service history total flow is 7157M (million), appears in September 7 days 23: 46 Point, and September 23 points of 59 minutes network service history total flows on the 7th are 6664M.September live video on the 7th clothes have been recorded in Fig. 4 The historical traffic curve graph of business, the historical traffic peak value of live video service are 940M, appear in 20 points of September 7 days 47 minutes, and 9 The historical traffic of the moon 23 points of live video services in 59 minutes on the 7th is 345M.It is total that September network service history on the 1st has been recorded in Fig. 5 Flow curve figure, the peak value of network service history total flow are 7534M, appear in 23 points of September 1 day 46 minutes, and 23 points of September 1 day 59 points of network service history total flow is 6717M.The historical traffic curve of September live video service on the 1st has been recorded in Fig. 6 Figure, the historical traffic peak value of live video service are 1286M, appear in 17 points of September 1 day 06 minute, and 23 points of September 1 day 59 minutes The historical traffic of live video service is 423M.The historical traffic of video on demand service is that network service history total flow subtracts directly Broadcast the historical traffic peak value of Video service.
204, most according to the maxima and minima of the second network service historical traffic in given statistics duration Big difference determines the flow amount of increase of the second network service;
Include multiple timing statistics points in given statistics duration, and the order video of each timing statistics point takes The historical traffic value of business is not quite similar, then in the given statistics duration, the historical traffic shape of multiple video on demand service At a curve, the peak value of the curve is the maximum value of the historical traffic in the given statistics duration, and the paddy of the curve Value is the minimum value of the historical traffic in the given statistics duration, which goes through in given statistics duration The difference of the maxima and minima of history flow is the flow amount of increase of the video on demand service.In this way, in preset statistics week In phase, the flow amount of increase of multiple video on demand service is obtained, maximum value therein is determined as to the stream of the video on demand service Amount of increase is measured, the influence to video on demand service is preferably minimized by the bandwidth distributed for live video service.
It should be understood that being not limited to the video on demand service historical traffic in given statistics duration in the present embodiment Maxima and minima flow amount of increase of the maximum difference as the video on demand service, can also be by the video on demand service The mean difference of the maxima and minima of historical traffic is determined as the stream of the video on demand service in given statistics duration Measure amount of increase.
205, the flow amount of increase is added with the current network flow of the second network service, obtains the net of the second service Network peak flow;
The network flow peak value of the video on demand service refers in the given duration, occupied by the video on demand service Network flow maximum value.The flow amount of increase is added with the current network flow of the video on demand service, the program request is obtained and regards The network flow peak value of frequency.
206, the maximum network bandwidth of multiple node is obtained respectively;
The network bandwidth upper limit value of each node is obtained respectively.The execution sequence of step 206 can not be retouched by the present embodiment The limitation stated can execute before any one step.
207, respectively by the difference of the maximum network bandwidth of multiple node and the network flow peak value of the second network service Value is used as available network bandwidth;
The summation of bandwidth occupied by live video service and video on demand service cannot exceed maximum network bandwidth, calculate most The network flow peak value of big network bandwidth and video on demand service device then can get can be used for live video service in each node Network bandwidth.
208, select the maximum node of the available network bandwidth as destination node in multiple node.
According to the available network bandwidth of each node, for the corresponding section of request selecting of the live video services selection node Point.In order to ensure that the live video service obtains better network flow resource, then the available net is selected in multiple node The maximum node of network bandwidth is as destination node.
If there are the maximum bandwidths that multiple nodes are current first traffic assignments to be equal, believed according to the IP address of user Breath, the small node of the source IP addresses of the preferential chosen distance request is as destination node.
In the embodiment of the present invention, scheduling system obtains the flow information of video on demand service in multiple nodes, further root According to the historical traffic information of the video on demand service, the network flow of the video on demand service in given statistics duration is determined Peak value obtains the flow amount of increase of multiple video on demand service specially in preset measurement period, by maximum value therein It is determined as the flow amount of increase of the video on demand service, by the bandwidth distributed for live video service to the shadow of video on demand service Sound is preferably minimized, which is added with the current network flow of the video on demand service, obtains the net of the second service Network peak flow can determine straight in each node according to the difference of the maximum network bandwidth of each node and the network flow peak value The available network bandwidth for broadcasting Video service selects the maximum node of the available network bandwidth as target in multiple node Node, then, it, can be according to the video on demand service history in determining statistics duration when for live video services selection node Flow, it can also be live video service to be calculated under the premise of taking into account network bandwidth used in video on demand service in egress The available network bandwidth of distribution can efficiently use node bandwidth, and work as the node for possessing a large amount of live video services straight Be not in that data traffic significantly falls sharply and causes network load unbalanced, to be more favorable for after broadcasting Video service CDN network is run.
Below with the scheduling system in a detailed applications scene description the present embodiment, referring to Fig. 7,
Scheduling system 301 includes:Historical information unit 302, unit of video information 303, data acquisition unit 304, prediction Decision package 305, CDN schedulers 306, the libraries IP;
Wherein, historical information unit 302, the historical traffic information for counting second network service;
Unit of video information 303, when for the duration of the current first network service to be determined as given statistics It is long;
Data acquisition unit 304, the flow information for counting first network service and the second network service;
Forecast and decision unit 305 determines first for the flow information in conjunction with first network service and the second network service The available network bandwidth of network service;
CDN schedulers 306, the schedulable bandwidth for being obtained according to forecast and decision unit 305, in conjunction with the ip of user 307 The location informations such as address for the first network services selection and are dispatched to most suitable target OC nodes 308;
The libraries IP 309, the IP address information for storing user.
Scheduling system 301 sends traffic order to user 307, the target OC nodes 308 for notifying user 307 to cut, user Target OC nodes 308 in 307 access CDN network.
Referring to Fig. 8, one embodiment packet of the selection device of content delivery network node in the embodiment of the present invention It includes:
Acquiring unit 401, for when receive for the request of first network services selection node when, obtain multiple sections respectively The flow information of second network service in point;
Determination unit 402, according to the historical traffic information of the second network service, determining should in given statistics duration The network flow peak value of second network service;
Acquiring unit 401 is additionally operable to obtain the maximum network bandwidth of multiple node respectively;
Determination unit 402, be additionally operable to the maximum network bandwidth of the multiple node for respectively obtaining the acquiring unit 401 with The difference of the network flow peak value of the second network service is as available network bandwidth;
Selecting unit 403, the available network bandwidth for being determined according to determination unit 402 select node.
The each unit of the selection device of content delivery network node realizes the process of respective function in the embodiment of the present invention, asks Referring to the detailed description of aforementioned one embodiment shown in FIG. 1, details are not described herein again.
In the embodiment of the present invention, acquiring unit 401 obtains the flow information of the second network service in multiple nodes, further According to the historical traffic information of the second network service, determination unit 402 determines second network in given statistics duration The network flow peak value of service determines single 402 just according to the difference of the maximum network bandwidth and the network flow peak value of each node It can determine that the available network bandwidth of first network service in each node, selecting unit 403 are selected according to the available network bandwidth Node, then, it, can be according to the second network service history in determining statistics duration when for first network services selection node Flow, it can also be first network service to be calculated under the premise of taking into account network bandwidth used in the service of the second network in egress The available network bandwidth of distribution, can efficiently use node bandwidth, and when possessing the nodes of a large amount of first network services the Be not in that data traffic significantly falls sharply and causes network load unbalanced, to be more favorable for after one network services CDN network is run.
Referring to Fig. 9, second embodiment packet of the selection device of content delivery network node in the embodiment of the present invention It includes:
Acquiring unit 501, for when receive for the request of first network services selection node when, obtain multiple sections respectively The flow information of second network service in point;
Determination unit 502, according to the historical traffic information of the second network service, determining should in given statistics duration The network flow peak value of second network service;
Acquiring unit 501 is additionally operable to obtain the maximum network bandwidth of multiple node respectively;
Determination unit 502, be additionally operable to the maximum network bandwidth of the multiple node for respectively obtaining the acquiring unit 501 with The difference of the network flow peak value of the second network service is as available network bandwidth;
Selecting unit 503, the available network bandwidth for being determined according to determination unit 502 select node.
Further, it is determined that unit 502, it is additionally operable to the duration of the current first network service being determined as this to give Statistics duration.
The selection device of content delivery network node in the present embodiment, can further include:
Statistic unit 504, in preset measurement period, counting second network clothes in the given statistics duration Multiple historical traffic information of business.
Further, it is determined that unit 502, it is additionally operable to according to the second network service the history stream in given statistics duration The maximum difference of the maxima and minima of amount determines the flow amount of increase of the second network service;
The selection device of content delivery network node in the present embodiment, can further include:
Computing unit 505 is obtained for the flow amount of increase to be added with the current network flow of the second network service The network flow peak value.
Further, selecting unit 503 are additionally operable to select the maximum node of the available network bandwidth in multiple node As destination node.
Selecting unit 503 is additionally operable to the small node of source internet protocol address of the preferential chosen distance request as mesh Mark node.
The each unit of the selection device of content delivery network node realizes the process of respective function in the embodiment of the present invention, asks Referring to earlier figures 1, the detailed description of one embodiment and second embodiment shown in Fig. 2, details are not described herein again.
In the embodiment of the present invention, acquiring unit 501 obtains the flow information of the second network service in multiple nodes, determines single Member 502 further according to the historical traffic information of the second network service, determines second network in given statistics duration The network flow peak value of service, specially determination unit 502 obtain multiple second network services in preset measurement period Flow amount of increase, maximum value therein is determined as to the flow amount of increase of the second network service, will be first network service distribute Bandwidth and the influence to the second network service is preferably minimized, computing unit 505 is by the flow amount of increase and the second network service Current network flow be added, obtain the network flow peak value of the second service, determination unit 502 is according to the maximum web of each node The difference of network bandwidth and the network flow peak value can determine the available network bandwidth of first network service in each node, choosing Select unit 503 selects the maximum node of the available network bandwidth as destination node in multiple node, then, it is being first When network services selection node, the second network can be taken into account according to the second network service history flow in statistics duration is being determined It is the available network band of first network service distribution to be calculated under the premise of network bandwidth used in service in egress Width can efficiently use node bandwidth, and work as the node for possessing a large amount of first network services after first network services, Be not in that data traffic significantly falls sharply and causes network load unbalanced, to be more favorable for CDN network operation.
It is a kind of server architecture schematic diagram provided in an embodiment of the present invention referring to Figure 10, Figure 10.The server 600 can be because Configuration or performance are different and generate bigger difference, may include one or more central processing units (central Processing units, CPU) 622 (for example, one or more processors) and memory 632, one or more Store the storage medium 630 (such as one or more mass memory units) of application program 642 or data 644.Wherein, it deposits Reservoir 632 and storage medium 630 can be of short duration storage or persistent storage.The program for being stored in storage medium 630 may include One or more modules (diagram is not shown), each module may include to the series of instructions operation in server.More Further, central processing unit 622 could be provided as communicating with storage medium 630, and storage medium is executed on server 600 Series of instructions operation in 630.Server 600 can also include one or more power supplys 626, one or more Wired or wireless network interface 650, one or more input/output interfaces 658, and/or, one or more operations System 641, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..Above-mentioned Fig. 1 And the server architecture shown in Fig. 10 can be based on by the step performed by server described in embodiment illustrated in fig. 2.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment weight Point explanation is all difference from other examples, and the same or similar parts between the embodiments can be referred to each other. For device class embodiment, since it is basically similar to the method embodiment, so fairly simple, the related place ginseng of description See the part explanation of embodiment of the method.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to Non-exclusive inclusion, so that process, method, article or device including a series of elements are not only wanted including those Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or device Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that There is also other identical elements in process, method, article or device including the element.
One of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment can pass through hardware It completes, relevant hardware can also be instructed to complete by program, the program can be stored in a kind of computer-readable In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The above described is only a preferred embodiment of the present invention, be not intended to limit the present invention in any form, though So the present invention has been disclosed as a preferred embodiment, and however, it is not intended to limit the invention, any technology people for being familiar with this profession Member, without departing from the scope of the present invention, when the technology contents using the disclosure above make a little change or modification For the equivalent embodiment of equivalent variations, as long as be without departing from technical solution of the present invention content, it is right according to the technical essence of the invention Any simple modification, equivalent change and modification made by above example, in the range of still falling within technical solution of the present invention.

Claims (10)

1. a kind of selection method of content delivery network node, which is characterized in that including:
When receive for the request of first network services selection node when, obtain the stream of the second network service in multiple nodes respectively Measure information;
According to the historical traffic information of the second network service, the second network service in given statistics duration is determined Network flow peak value;
The maximum network bandwidth of the multiple node is obtained respectively;
The maximum network bandwidth of the multiple node and the difference of the network flow peak value of the second network service are made respectively For the available network bandwidth of first network service in each node in the multiple node;
Node is selected according to the available network bandwidth.
2. according to the method described in claim 1, it is characterized in that, described believe according to the historical traffic of the second network service It ceases, includes before the network flow peak value of determining the second network service in given statistics duration:
The duration that presently described first network services is determined as the given statistics duration;
In preset measurement period, multiple historical traffics of the second network service in the statistics given statistics duration Information.
3. according to the method described in claim 1, it is characterized in that, described believe according to the historical traffic of the second network service Breath determines that the network flow peak value of the second network service in given statistics duration includes:
According to the maximum difference of the second network service maxima and minima of historical traffic in given statistics duration, Determine the flow amount of increase of the second network service;
The flow amount of increase is added with the current network flow of the second network service, obtains the network flow peak value.
4. according to the method described in claim 1, it is characterized in that, being that the request selecting is corresponding according to the available network bandwidth Node includes:
Select the maximum node of the available network bandwidth as destination node in the multiple node.
5. method according to any one of claims 1 to 4, which is characterized in that the method further includes:
The small node of the source internet protocol address asked described in preferential chosen distance is as destination node.
6. a kind of selection device of content delivery network node, which is characterized in that including:
Acquiring unit, for when receive for the request of first network services selection node when, obtain respectively in multiple nodes The flow information of two network services;
Determination unit determines described the in given statistics duration according to the historical traffic information of the second network service The network flow peak value of two network services;
The acquiring unit is additionally operable to obtain the maximum network bandwidth of the multiple node respectively;
The determination unit is additionally operable to the net of the maximum network bandwidth by the multiple node and the second network service respectively Available network bandwidth of the difference of network peak flow as first network service in each node in the multiple node;
Selecting unit, the available network bandwidth for being determined according to the determination unit select node.
7. device according to claim 6, which is characterized in that
The determination unit, when being additionally operable to the duration that presently described first network services being determined as the given statistics It is long;
Described device further includes:
Statistic unit, in preset measurement period, counting the second network service in the given statistics duration Multiple historical traffic information.
8. device according to claim 6, which is characterized in that
The determination unit is additionally operable to the maximum value according to the second network service historical traffic in given statistics duration With the maximum difference of minimum value, the flow amount of increase of the second network service is determined;
Described device further includes:
Computing unit obtains described for the flow amount of increase to be added with the current network flow of the second network service Network flow peak value.
9. device according to claim 6, which is characterized in that
The selecting unit is additionally operable to select the maximum node of the available network bandwidth as target in the multiple node Node.
10. according to claim 6 to 9 any one of them device, which is characterized in that
The selecting unit is additionally operable to the small node of the source internet protocol address asked described in preferential chosen distance as target Node.
CN201310478535.5A 2013-10-14 2013-10-14 A kind of selection method and device of content delivery network node Active CN104580012B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310478535.5A CN104580012B (en) 2013-10-14 2013-10-14 A kind of selection method and device of content delivery network node

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310478535.5A CN104580012B (en) 2013-10-14 2013-10-14 A kind of selection method and device of content delivery network node

Publications (2)

Publication Number Publication Date
CN104580012A CN104580012A (en) 2015-04-29
CN104580012B true CN104580012B (en) 2018-08-07

Family

ID=53095232

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310478535.5A Active CN104580012B (en) 2013-10-14 2013-10-14 A kind of selection method and device of content delivery network node

Country Status (1)

Country Link
CN (1) CN104580012B (en)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105554125B (en) * 2015-04-24 2018-12-18 美通云动(北京)科技有限公司 A kind of method and its system for realizing webpage fit using CDN
CN105262698B (en) 2015-10-28 2019-03-01 华为技术有限公司 A kind of methods, devices and systems of load balancing
CN106936733B (en) * 2015-12-31 2020-08-28 北京金山云网络技术有限公司 Bandwidth resource allocation method and device
CN106230633A (en) * 2016-08-01 2016-12-14 中体彩科技发展有限公司 The Forecasting Methodology of newly-increased high frequency sports lottery ticket game data flow and device
CN106357776B (en) * 2016-09-23 2019-06-28 北京奇虎科技有限公司 A kind of choosing method and device of the transfer resource of flow data
CN107171839B (en) * 2017-05-19 2019-12-06 上海幻电信息科技有限公司 Bandwidth flow cost control method
CN107846614B (en) * 2017-10-19 2020-09-11 北京奇艺世纪科技有限公司 Video traffic scheduling method and device and electronic equipment
CN107911723B (en) * 2017-11-20 2020-04-07 中央电视台 Method, server and distribution equipment for distributing video traffic by multiple network paths
CN110198344A (en) 2019-05-05 2019-09-03 网宿科技股份有限公司 A kind of resource regulating method and system
CN110661862A (en) * 2019-09-20 2020-01-07 网宿科技股份有限公司 Method for preheating resource file and central management system
CN111343006B (en) * 2020-02-12 2023-01-03 咪咕文化科技有限公司 CDN peak flow prediction method, device and storage medium
CN113839795B (en) * 2020-06-23 2023-01-20 北京金山云网络技术有限公司 Peak eliminating processing method and device for CDN node, electronic equipment and storage medium
CN114448808A (en) * 2020-11-02 2022-05-06 阿里巴巴集团控股有限公司 Peak clipping method and device and electronic equipment
CN114697224B (en) * 2020-12-28 2024-04-26 北京金山云网络技术有限公司 Data processing method and device, electronic equipment and storage medium
CN113596538A (en) * 2021-06-30 2021-11-02 深圳市酷开网络科技股份有限公司 Equipment control method and device, electronic equipment and storage medium
CN113950056A (en) * 2021-10-20 2022-01-18 中国联合网络通信集团有限公司 Bandwidth allocation method, device and storage medium
CN114245221B (en) * 2021-12-14 2023-09-05 北京达佳互联信息技术有限公司 Interaction method and device based on live broadcasting room, electronic equipment and storage medium
CN117319322B (en) * 2023-12-01 2024-02-27 成都睿众博芯微电子技术有限公司 Bandwidth allocation method, device, equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101242432A (en) * 2008-02-28 2008-08-13 蓝汛网络科技(北京)有限公司 An Internet content distribution method, system and device
CN102664879A (en) * 2007-01-26 2012-09-12 日本电气株式会社 Video distribution system and video distribution method
CN103166985A (en) * 2011-12-09 2013-06-19 上海盛霄云计算技术有限公司 Global load balancing scheduling method and data transmission method and device and system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2456026A (en) * 2007-12-26 2009-07-01 Contendo Inc CDN balancing and sharing platform

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102664879A (en) * 2007-01-26 2012-09-12 日本电气株式会社 Video distribution system and video distribution method
CN101242432A (en) * 2008-02-28 2008-08-13 蓝汛网络科技(北京)有限公司 An Internet content distribution method, system and device
CN103166985A (en) * 2011-12-09 2013-06-19 上海盛霄云计算技术有限公司 Global load balancing scheduling method and data transmission method and device and system

Also Published As

Publication number Publication date
CN104580012A (en) 2015-04-29

Similar Documents

Publication Publication Date Title
CN104580012B (en) A kind of selection method and device of content delivery network node
US9070139B2 (en) Estimating unique impressions in an online video distribution system
US8364820B2 (en) Data center resource usage and cost determination
WO2020143164A1 (en) Network resource allocation method and device
CN105872837B (en) User's recommended method and device
CN109901927A (en) Intelligent Task dynamic scheduling system and its method
MX2015006471A (en) Method and apparatus for controlling utilization in a horizontally scaled software application.
CN103561354B (en) Method and device for calculating and processing video smoothness
CN106464733B (en) The method and device of virtual resource in a kind of adjustment cloud computing
CN109962790A (en) A kind of network quality monitoring method, device, electronic equipment and storage medium
WO2009081412A2 (en) System and method for a cdn balancing and sharing platform
CN111432247B (en) Traffic scheduling method, traffic scheduling device, server and storage medium
CN104980417B (en) A kind of UGC document distribution method and equipment
Tadakamalla et al. Characterization of IoT workloads
CN109379620A (en) Audio-video way to play for time and device
CN110460879A (en) A kind of video request dispatching method, device, server and storage medium
CN103002329B (en) Device and method for predicting reach-frequency table data of network video advertisements
CN113079062B (en) Resource adjusting method and device, computer equipment and storage medium
CN113301085A (en) Scheduling method, device, equipment and storage medium
CN108809752A (en) A kind of adaptive process monitoring method, apparatus of network flow, NPB equipment and medium
WO2017198007A1 (en) Method and apparatus for determining routing policy
CN108536525A (en) A kind of host dispatching method and device
Samant et al. Towards quality-assured data delivery in cloud-based iot platforms for smart cities
US11871263B2 (en) System and method for 5G mobile network management
CN108667873B (en) Shunting method, shunting device, electronic equipment and readable storage medium

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