CN101931541A - Method for realizing instantaneous rapid large-scale low-cost Internet publishing - Google Patents
Method for realizing instantaneous rapid large-scale low-cost Internet publishing Download PDFInfo
- Publication number
- CN101931541A CN101931541A CN200910148604XA CN200910148604A CN101931541A CN 101931541 A CN101931541 A CN 101931541A CN 200910148604X A CN200910148604X A CN 200910148604XA CN 200910148604 A CN200910148604 A CN 200910148604A CN 101931541 A CN101931541 A CN 101931541A
- Authority
- CN
- China
- Prior art keywords
- internet
- data
- issue
- stream
- scale
- 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.)
- Pending
Links
Images
Abstract
The invention discloses a method for realizing instantaneous rapid large-scale low-cost Internet publishing, belongs to the field of distributed technology and aims to improve the performance of the publishing, reduce the cost of the publishing and achieve instantaneity and large scale and the like by applying the technology in large-scale distributed computing to Internet application. By the method, conditions are provided for full utilization of Internet resources by reforming Internet computer nodes into peer-to-peer points, a large-scale non-central Internet transmission protocol is drawn by using the peer-to-peer points, a large-scale non-central Internet computing cluster is established and a large-scale non-central Internet-based publishing mechanism is established. The method can be instantaneously implemented in the way of directly facing a receiver, and has the advantages of high rate, high data quantity and large scale, and continuous transmission is performed in a stream form, so that the method meets the basic requirements of a user for publishing acquired data and perfects the Internet application.
Description
Technical field
The invention belongs to the application of distributed computing technology and community network in the Internet.Comprising the foundation of large-scale distributed system and the method for utilizing human behavior pattern in community network to carry out the data multicast.
Background technology
Issue is one of human citation form of linking up.In view of the Internet makes the data that can exchange digital form between the mankind by computing equipment each other, issue must be the major issue that internet system need solve.In current internet system, issue is finished by the center type server.Its basic process is as follows: need the user of distributing data at first data to be ready on local computing device; By http protocol [1] data being sent to that the user thinks again may the person of being received on the server of visit; Afterwards, the user can obtain an address of pointing to its data; The client of any identification HTTP can obtain to be transferred to local distributing data by HTTP by this address; If the data of user's expectation oneself issue are visited more widely, can also do similar issue work on other servers or this address is being published on other server; Potential recipient can be by visiting these servers of preserving these data or this data address acquisition publishers' data.The user just is through with at the issue behavior of these data like this.Because server has played function served as bridge between publisher and recipient, therefore this issue can be called indirect issue.
This indirect issue has tangible weak point.At first, distribution effect is poor.The distribution effect difference is not mainly owing to there is directly contact to cause between publisher and the recipient.Desirable data issue should be can contact directly between publisher and recipient.The publisher can directly send to the recipient to data; The recipient can feed back after the acquisition data immediately; The publisher can obtain distribution effect and recipient's suggestion from these feedbacks, thereby increases, reduces, upgrades, improves even finish issue.Yet this desirable issue form does not but exist in the current internet system.Main cause is exactly not contact directly between publisher and the potential recipient; They must come indirect opening relationships by server.The publisher is unable to find out any correlation behaviors such as potential recipient's interest and quantity when distributing data; Usually mainly be whether website according to this server correspondence has enough big accessed amount when selecting a server to issue.But no matter be big server of accessed amount or the little server of accessed amount, whether data publisher can not in time understand institute's distributing data and be obtained by possible recipient; Also can only obtain for recipient's feedback by access server repeatedly; And these feedback informations that come from the recipient only just may begin to obtain after all issue finishes; Because the time of recipient's access server is uncertain, these information still are incomplete.This shows the negative effect that the indirect relation between publisher and the recipient brings the publisher; In general, to influence concerning the publisher all be negative to this indirect published method.
Because the information issue is that publisher and recipient finish jointly, also must consider the influence that this indirect association produces the recipient.Usually concerning the recipient, this indirect relation can bring positive influences.This positive influences are mainly reflected in the recipient to be possessed initiative fully and removes to obtain desired data.Under the current internet environment, the recipient is access server at first, finds the data of needs then according to the index on the server, carries out real data more at last and obtains; This has been avoided recipient's computational resource person of being published to take, suffer the interference of bad data to greatest extent.To recipient's negative effect is that the recipient can not in time obtain may be to its valuable data.Any data all have life cycle, and are perhaps ageing; Postpone to obtain some ageing strong data and can cause recipient's loss.
The second, issue can not directly reflect the Internet of continuous dynamic change, the basic custom of also observing the world not in full conformity with the mankind indirectly.From the angle that the recipient observes external world information, can be divided into usually consciously and unconscious two kinds.What is called refers to the recipient consciously has expection or demand clearly for the data that will obtain; And unconsciously refer to the variation of user around arbitrarily observing, the data that obtain are not in this state explicitly called for.These the two kinds modes that receive external data all exist under the situation of issue and directly issue indirectly.When issuing indirectly, the recipient obtains data by access server, sometimes is to have a definite purpose, and sometimes just at will browses.But this browsing under a static environment carried out; The Internet looks it is a static constant system for the user, unless recipient's active access server.The Internet itself is a system that constantly changes, and this variation all produces by issuing.This dynamically is to be based upon on the basis that publisher and recipient can contact directly.
The 3rd, issue speed is low.On issue speed, it is low that the indirect issue of current internet system also causes issuing speed.In the current internet issuing process, server is in absolute ascendancy, does not promptly have the server issue just can't carry out, and distribution effect is also without any assurance.This requires server to possess enough computational resources.But since usually in the Internet Network Transmission be the main bottleneck that systematic function improves, unilaterally increase the server computational resource and be not sufficient to guaranteed performance and improve thereupon.Under most of situation, between server and publisher, can only set up finite bandwidth and connect, the bandwidth resources that the publisher had and even the bandwidth resources of server all can not make full use of.This is to cause issuing the low immediate cause of speed.
The 4th, the distributing data amount is little.So-called distributing data amount refers to institute's distributing data size for a short time and is subjected to strict restriction.When the distributing data amount is excessive, can be connected to form lasting pressure to the finite bandwidth between publisher and the server, excessive to the long consumption of natural resource of computational resource holding time of server itself.In the environment of a resource anxiety, in order to deal with potential extensive publisher's requirement, have only and dwindle the distributing data amount as far as possible, just can make most of publishers obtain effective service under the strict restriction.Little distributing data must cause internet, applications to enrich degree being limited to, and such as can not carrying out based on multimedia application in a large number, main internet, applications is still based on text or multi-medium data in a small amount.
The 5th, the issue small scale.So-called issue scale refers under the concurrent condition of carrying out of issuing process, the common scale that system possessed that forms of publisher and recipient.In most of the cases, the publisher is unique, and the recipient is most; Some individual cases publisher and recipient are a plurality of; Opposite extreme situations is that the publisher is most, and the recipient is a minority, or even unique or zero.The sort of situation all can be limited by the existing basic structure in the Internet and cause the issue scale too small, under a lot of situations is to issue under the condition of smallest size, promptly have only a publisher (client) and a recipient (server end), concurrent degree is minimum.Little issue scale must cause the decline or the loss of distribution effect.And in most cases, issue and acceptance are worked under asynchronous condition; Even when having only acceptance to carry out, concurrent scale is also low.
The 6th, can not be based on the form issue of stream.The Internet distributing data is made up of multiple heterogeneous data not of uniform size.Because the restriction of current internet structure, such distributing data can not be transferred to the recipient in the mode that continues to flow, and must repeatedly send the recipient in the mode of being interrupted.This at first makes data issues become to have some setbacks, the complete issue of data is affected, finally directly influence distribution effect and user experience.
At last, can not carry out the interactive mode issue.When issuing big relatively data, need continue for some time.Because publisher and recipient's relation is indirect, the whole process no matter data are issued lasts long in the issue mechanism of current internet support, and publisher and recipient can not produce any mutual therebetween.Be not that the recipient is needed even the data that are published comprise, the recipient can not in time exchange with the publisher, and total data still must be transferred on the server, causes the waste to computational resource.Fig. 1 has represented traditional the Internet issue mechanism.
Summary of the invention
Creation purpose of the present invention is to propose a kind of new types of data published method on the internet, make the issue of one of basic function as on the Internet can be directly to carry out immediately in the face of recipient's mode, accomplish that simultaneously speed height, data volume and scale are big, and the form with stream continues transmission, finally satisfy the basic demand that data are obtained in user's issue, improve internet, applications.
The present invention realizes goal of the invention by following technological means:
The first step is set up direct issue mechanism.Directly issue refers to and set up the straight-forward network connection between data publisher and recipient; When distributing data, between publisher and recipient, have only of short duration asynchronous that network delay causes, promptly data are distributed on and approach to carry out under the synchronous situation.The fundamental mode of data is obtained in human observation that such issue feature is perfect on the internet, and promptly the recipient can be the same with daily experience, obtains data on the internet consciously or unconsciously.In either case, whether the recipient possesses the decision of absolute active power and interrupts receiving and be published data or select among being published data.Such issue form also can reflect the constantly brass tacks of change of internet data on any computing node in the Internet; Make the user can realize the essential characteristic of the Internet, and on more real like this Internet, obtain income.Certainly, because directly issue has instantaneity, if can not assist restriction scheme can disturb the recipient to obtain data on the internet with necessity.Usually can adopt to close or switch the issue channel and stop and lose interest in or the invasion of low quality data.
In second step, set up quick issue mechanism.News conference of the present invention is issued with the prestissimo that computing node was allowed.The bandwidth that each computing node had is limited, and this bandwidth has determined a maximum transfer speed that computing node can hold.Because the complexity of the Internet bottom-layer network, real transmission speed in most cases will be lower than the speed that the bandwidth upper limit can be supported, causes bandwidth waste.Issue mechanism of the present invention has solved this problem.Issue mechanism can make full use of the bandwidth between publisher and the recipient, thereby makes the issue can be to carry out than current internet faster speed.Because the present invention has utilized the bandwidth of computing node as far as possible, other parallel internet, applications are affected.The present invention can provide automatic adaptive capacity, and when the bandwidth of finding publisher or recipient's computing node can not satisfy issue or receive requirement, whether system can will make restriction to other application by automatically prompting user; When bandwidth can satisfy issue or receive requirement, system of the present invention also can satisfy restriction taking bandwidth under the prerequisite of issuing or receiving.
In the 3rd step, set up the big data quantity issue mechanism.Issue of the present invention does not have any restriction to being published data volume, to make things convenient for user group's data, can utilize multiple media data to express the meaning of oneself.In numerous heterogeneous datas, the media data size will be much larger than text data; And the media data ability to express is strong, and directly perceived.Issue data on the internet, must cause the distributing data amount to increase, to the lasting pressure increase of computational resource based on Streaming Media.The present invention has improved utilance to the Internet computational resource by the large-scale non-central Internet Internet technology, has solved the problem of big data quantity issue.Though it is pointed out that the present invention distributing data quantitatively not being limited, is being conditional qualitatively.Because stream medium data this also have sequential to require [2] when showing, when playback rate is lower than when showing that speed or stream medium data fragment can not be sent to receiving terminal according to the order of sequence, data display will occur unusually.Usually be published data desired speed when showing and be lower than issue speed.When this condition can't satisfy, can realize by reducing the quality of data.The order of data slot can realize by buffer memory.
In the 4th step, set up the large-scale low-cost issue mechanism.The restriction of scale can not be issued in issue of the present invention.The issue scale refers in an issuing process, and it is under the concurrent state that a plurality of participants are arranged simultaneously, participates in publisher and recipient's total quantity of issue.In current delivery system,, there is not the issue scale strictly speaking, and has only the visit scale because issue is two stages of separating with receiving.For issue, the most general situation is that a data source demand side is to facing a plurality of recipients simultaneously.In other words, recipient's scale is the main determining factor of issue scale.The present invention does not do any restriction to recipient's scale.This is that the optimum efficiency that reaches issue has played the support effect.For the end user, the present invention can make them to issue the data of oneself to any amount of potential user by the computing equipment of oneself.Simultaneously, if distributing data satisfies the Streaming Media sequential when requiring, even also can carry out the data issue of unlimited scale on a common computing equipment.
In the 5th step, set up the streaming issue mechanism.Issue of the present invention provides the issue mechanism based on stream.Be published data regardless of its size, all can be sent on recipient's the computing equipment in stable mode continuously and healthily according to the form that the publisher organizes in advance.This also is the significant improvement to issue, also be best delivery system the effect that should reach.Many new internet, applications can be carried out based on these characteristics.The another one feature of stream is that data can continue to be illustrated on recipient's the equipment, all transmits to finish and just shows and need not all data.This has also set up the basis for interactive issue.
In the 6th step, set up interactive issue mechanism.So-called interactive issue refers in issuing process, can carry out mutual between publisher and the recipient concomitantly, be that to be not only data flow to recipient's one-way process, still a two-way process that is caused by recipient's immediate feedback from the publisher to issuing process.Issue itself is not to have only the so isolated system of publisher, but publisher and recipient's acting in conjunction and an interactive system forming.In such system, be published data and constantly flow to the recipient by the publisher; Meanwhile, distributing data can ceaselessly be illustrated on recipient's the computing equipment; The recipient can produce response to the publisher by observing the data that constantly display; This feedback can be illustrated on publisher's the computing equipment immediately; The publisher can in time adjust distributing data according to recipient's feedback, guarantees that whole issuing process is to carry out under effectively mutual situation.Based on mutual issue mechanism, guaranteed that publisher and recipient can both obtain maximum benefit in this process like this.
Good effect of the present invention is:
In the issue mechanism that the present invention supports, the Internet all is a system that constantly changes for publisher and recipient.For the publisher, itself be exactly the perpetrator that the Internet changes; All changes on the Internet all are that the publisher brings.The recipient can constantly experience the Internet that causes from the publisher and change.Simultaneously, the recipient neither be fully passive in the middle of this changes; Based on support of the present invention, the recipient can directly send feedback to publisher immediately.So just realized the original object of internet system, perfect one of most important basic function on the Internet.Fig. 2 has represented improved the Internet issue mechanism.
Description of drawings
Fig. 1, traditional the Internet issue mechanism;
Fig. 2, improved the Internet issue mechanism.
Embodiment
The first step is transformed into the equity point with the Internet computing node and provides condition for the resource that makes full use of internet.In the large-scale non-central Internet internet system, equity refers between any two computing nodes not only to possess initiatively to the other side sends connection request but also ability that can passive response the other side request.This simple variation makes computational resource in the Internet by participating in the node that calculates from become all in single or minority node.In such distributed frame, there is not the saying of server strictly speaking; As computing capability will be the computing equipment of purpose with the contribution own resource only also far above ordinary node, can be called peer server usually; Still it being called server among the present invention is a saying sanctified by usage, and its mode of operation is different fully with traditional server.The foundation of equity point is the concrete application of reproduction technology in the distributed environment [3] on internet system.This The Application of Technology is to increase to prerequisite with the computational resource that current computing node performance generally strengthens, had.Under such prerequisite, it is not only consumption to system resource that any computing node enters system, also is the contribution to system resource.Based on this thought, distributed frame must be become equation by center type.When a computing node showed as consumption of natural resource, it will initiatively send request to one or more nodes; When a computing node shows as dedicate resources, the request that it will the one or more nodes of passive response sends.Each common computing node cooperatively interacts and offers help each other in common calculation process in the large-scale non-central Internet internet system.For this reason, forming above-mentioned equity point is to utilize the computational resource on all nodes necessary.Different with ordinary node, the target that the peer server that is transformed into by server enters system is the computational resource of contribution self, rather than consume system resources.In this case, as if peer server promptly needs only the pattern work with traditional server as long as the request of passive response ordinary node is just passable.If but server has possessed the ability of the request of initiatively sending, it can initiatively contribute the computational resource of self when ordinary node is not asked; Ordinary node only certain node possess under the prerequisite of data resource or Service Source just can and its contact.Super node or peer server are not to possess such data resource or Service Source at any time; Initiatively participate in calculating to possess such data resource or Service Source rapidly but the strong computing capability that it had can make it, thereby become the utilizable node of ordinary node.In brief, in the large-scale non-central Internet the Internet, no matter be ordinary node or the abundant peer server of computational resource, when moving, for fully rationally utilizing of resource provides precondition in the mode of equity point.
In second step, utilize peer node to formulate the large-scale non-central Internet the Internet transport protocol.Host-host protocol is that the uniqueness according to its computing environment proposes.After the restriction of having broken away from the division center the Internet, new host-host protocol is effectively to utilize computational resource necessary under new the Internet architecture.For common peer node, this party to the agreement's face will guarantee that it obtains the data cell that multiple heterogeneous data is formed, and will adapt to its resource of its characteristic use on the other hand and guarantee that heterogeneous data forms stream.For super node or peer server, this agreement guarantees that weak current can access its reliable support when making full use of its computational resource.When realizing this agreement, be based on existing non-central non-flow data multicast protocol, as BT[4], and the multicast protocol of non-central stream medium data, as BiToS[2] and BASS[5].But these agreements have just been considered the transmission problem of single data in the non-headed construction system, are not perfect host-host protocol.In a large-scale non-central Internet the Internet, a perfect host-host protocol will solve following problem.
1) has the quality that the alternative construction computational resource that flows number of nodes guarantees stream according to stream.In the large-scale non-central Internet internet system, can seek the stream node according to the feature of social network system [6].But because the transmission of stream is a long relatively process of a time, the number of stream node is also ceaselessly changing in this process.This variation or because the user normally adds or leaves to cause, or because the taste of convection current causes.In issuing process, because stream carries out in a particular cluster, as long as the current line node of this group is enough, stream just can form.But form after the stream, can not guarantee that this quantity is constant always.Under the ideal situation, this quantity can increase.This may be because new node adds formation in the group, also may be to cause owing to the expressed implication of stream is welcome to recommend to cause.If this recommended amount is big, one will be disseminated in whole large-scale non-central Internet internet system rapidly at valuable stream on the implication so.Can think that thus valuable circulation does not often need to worry the problem of its stream node number on the implication.Concerning issue, the quantity of stream is also few so usually.Certainly may have such situation, promptly a lot of users reorganize the stream that forms oneself to valuable stream, cause valuable fluxion amount to increase; Yet this simple imitation can make the value of stream descend gradually.More general situation is that the stream influence power that much is published is flat, flows nodes sharing at most in the group; As long as group's scale is not too little, stream still can form.During the worst situation, stream is received the user and interrupts in issuing process, and this number of interruptions to account for whole stream node ratio big so that remaining stream node is not enough to keep the issue fully of stream.The situation of common this interrupt flow can occur after having browsed a period of time in the group in member's convection current.At this time peer server need provide support to the residual stream node.In when search, flow needed stream node and come from the group or outside the group; Its quantity is decided by the popularity degree of searched stream.In addition, can require the node relevant with search node to add during owing to search, this two parts node has formed the support to search stream.Usually search stream is had the many data of stream node and is come the front by popularity degree (amount of the being replicated) ordering according to stream, comes the back and have the few node of stream number of nodes.Can occur flowing in the incipient stage relatively stable and cause the stream node that the trend of minimizing is arranged along with the minimizing of replica node and stream are worth to descend thus at back segment.At this moment need peer server to provide support, guarantee the smooth transmission of stream.When visit, host-host protocol can require visitor or interviewee's neighbor node to become the stream node; These nodes also are among the different groups.According to the knowledge of community network, the interviewee that can become super node in the middle of a group is [7] seldom; And most visits concentrate on these interviewees [7].Therefore, as a rule, the stream that forms based on visit can find enough stream nodes.Small part visit ordinary node and the stream that forms needs peer server to provide support.
2) peer server by specific placement or seek the stream node and form support to weak current.Because the intensity of stream in the large-scale non-central Internet the Internet is to be in the middle of the continuous change, costlyly fail to be convened for lack of a quorum very popular and intensity stabilization, being worth low stream then can be by dying down by force, so need consider the support to weak current in agreement; This is the requirement of system's fairness.This help to weak current can be taked dual mode, promptly supports by the peer server and the more stream of the searching node of specific placement.The support of peer server is similar to the mode among the BASS.Weak current generally is the few relatively stream of node that participates in transmission, and these participation nodes are not isolated the existence.Can more be flowed node by its position at community network.Here there are system recommendation and the artificial dual mode of recommending in fact.No matter be the sort of recommendation, all be the stream node of seeking in community network current influenza interest exploratoryly.In ideal conditions, this searching can bring stable stream node support, has promptly found a plurality of stream nodes to this influenza interest finally.Under the poorest situation, agreement is difficult to search out in community network to the interested node of this weak current, has to seek the peer server of specific placement thus and helps.Because the large-scale non-central Internet the Internet is a resource sharing system in essence, most system actions all are to find the pairing demand of similar behavior in community network, so common this situation probability of happening not high [7].In a privately owned environment, this situation can be very general; But not to be the present invention will pay close attention to for this.After this situation took place, the peer server of specific placement can be carried out effectively this stream and help.
3) according to heterogeneous data character the stream in the transmission is dispatched.After the formation that has enough computational resource supports stream, when concrete transport stream, to consider that scheduling strategy is with efficiency of transmission that improves stream and the performance of improving receiving terminal system.Scheduling strategy puts forward at data character, size in the stream and to the influence that presentation layer causes.Stream among the present invention comprises numerous types of data; These heterogeneous datas have different transmission and show requirement; The size differences of these heterogeneous datas is also very big in addition.At these differences, when the transmission data, should take corresponding strategy to make and make full use of under the prerequisite of computational resource, can consider above-mentioned different factor, take different transmission policys to guarantee that the user obtains more satisfied bandwagon effect.For the data cell in the concrete stream, its descriptor is the most important to whole transmission; By analysis to descriptor, can obtain the basic condition of whole stream, show still that for transport stream stream all has directive function; And descriptor all is the text data little to system pressure usually.Based on above-mentioned cognition, the descriptor of stream will at first be transmitted.Secondly, comprise some text datas again in each stream, these data are that the implication of expression stream is necessary; And these data can not pose a big pressure to transmission yet.Usually after the transmission data of description, can transmit the text data of each data cell.This transmission can be finished very soon.After the descriptor end of transmission and stream Chinese version data began transmission, system just can be the living view roughly of the miscarriage of transmitting at presentation layer, make user's convection current included in have preliminary understanding, and carry out limited interactive operation.Subsequently, system begins to handle the transmission of non-text data, such as picture, Voice ﹠ Video.At this moment transmission policy focuses on according to intrinsic relation between data cell, and remaining non-transmission of textual data in each data cell is put in place.Wherein picture transmission and audio frequency and video are inequality again for these.Picture size is generally also less than audio frequency and video, and picture does not have the requirement of sequential.In scheduling strategy, picture has the priority higher than audio frequency and video.At last, because the large-scale non-central Internet the Internet has high dynamic feature, require a plurality of data cells are transferred in the short as far as possible time on the stream node; But a plurality of data cells have size differences, and this difference may cause when transmission system resource allocation unreasonable.When the order of a big data cell in stream differs too great disparity prior to a little data cell and this size, if will cause small data to wait for the phenomenon of big data according to intrinsic sequential delivery; The behavioral characteristics of system might make the small data of back lose after big transfer of data finishes.This just requires to consider time-sharing operation in scheduling strategy, promptly transmit the period for each data cell in the stream all provides in the unit interval section, avoids occurring the unreasonable of system resource allocation.
4) in transmission course, guarantee the relation between data cell in the stream.Be sequential between data cell in the stream, and this ordinal relation is to destroy because of transmission, cause the user when long-range reception with stream inconsistent at source node.But this relation does not also require that transmission strictly observes the time, and key is can look consistent with the stream on the source node just passable when showing.This relation is actually the structure of knowledge intrinsic between a kind of data cell.From topological relation, can be linear, tree-shaped with netted.But no matter which kind of form all requires host-host protocol to guarantee to duplicate with same form on long-range stream node, thus reflection stream creator's original meaning intactly.Except the topological relation of static state, the author of stream also must specify the dynamic relationship of stream, the context of promptly showing between data cell.For randomly topologically structured, this is equivalent to indicate the traversal order of stream.In issue and access process, must guarantee to flow with this traversal order and on the stream node, show.In search procedure, because not only node of source of stream, can reformulate new static state and dynamic order according to relevant informations such as searching order standards, i.e. search is equivalent to reconfiguring knowledge.
5) take the respective transmissions strategy according to the character of data in the stream.Because brand-new definition has been carried out in convection current of the present invention, thereby there is the several data of different in kind in the stream.Thereby host-host protocol of the present invention must have the ability to differentiate data of different nature and take different transmission meanss.In the large-scale non-central Internet the Internet, mainly need identify whether certain data has sequential in transmission course requirement.Can take the BT algorithm to finish for the data that do not have sequential to require, and the data that have sequential to require take BiToS algorithm and BASS algorithm to realize transmission.
6) data cell in the discriminating stream reduces the network cost to reuse the stream that transmitted.The large-scale non-central Internet internet system is an information sharing system in essence.In this system, popular data can spread in whole system rapidly with the form of stream or duplicate; Non-popular data also can be at the minimum laser propagation effect of auxiliary acquisition down of system.As a rule, there is reusable stream in the system.When issue, exist the possibility of data with existing in the system often to occur in the distributing data.This host-host protocol should have the ability to differentiate to be published among the group whether have the data that had in the stream of issuing on the stream node.If such data have been arranged in the stream node, should be avoided in during transmission on such data and expend transfer resource, as bandwidth etc.; Simultaneously, should utilize such node not contribute for other have the node of data.The general method of differentiating is that the content encoding between comparing data decides.The another one problem is when having mass data on the node, should do suitable index to already present data, reduces to differentiate consumed time.
7) give the means that user's convection current manages.Because the large-scale non-central Internet internet system lacks the scheme of managing resource concentratedly, and appropriate flow management strategy can improve the efficiency of transmission of convection current.For this reason, this agreement has comprised the basic mode of flow management.The management of stream relates generally to the following aspects, i.e. the deletion of the renewal of the inquiry of Liu storage, stream, stream and stream.These aspects are the same with the requirement of general data storage, but specific practice is owing to non-central and high dynamic feature differs greatly.The management of flowing in this agreement is the Decentralization that huge user participates in, rather than the centralization that the minority manager has in the center type structure.Each user be the beneficiary of system data also be the manager of system data.
In the 3rd step, set up the large-scale non-central Internet the Internet and calculate cluster.The present invention has taked to set up the way of efficient cluster and has disperseed computational resources to be organized into cluster one by one these, in each cluster computational resource can obtain fully shared, thereby finish corresponding calculated.What should be noted that a bit is, because each node is all controlled by each user, such cluster is in the middle of the high dynamic change, and promptly each node all may add at any time, also may leave at any time.This brings difficulty for setting up the efficient calculation cluster.The present invention has adopted the efficient operation that data are duplicated [2], netted multicast mechanism [4], dynamically screened node [4] and guarantee cluster based on the routing algorithm means such as [8] of Complex Networks Theory [7] in complex networks system [7].The large-scale non-central Internet the Internet transport protocol is set up with regard to being based on above-mentioned theory.Behind the host-host protocol of having formulated at the large-scale non-central Internet the Internet, the node in the system will form a plurality of calculating clusters that scale does not wait.For peer server among the present invention or super node, its at computing environment be not mutually independent irrelevant each other client, but the resource-sharing calculating cluster that each takes what he needs each other.Host-host protocol is exactly the key mechanism that impels cluster to form.In the large-scale non-central Internet the Internet, have only to form big and small calculating cluster, thereby being transmitted in the mode of stream, data form brand-new internet, applications.
In the 4th step, set up issue mechanism based on the large-scale non-central Internet the Internet.By realization, the formulation of large-scale non-central Internet the Internet transport protocol and the formation of High-Performance Computing Cluster of the Internet equity point, issue mechanism of the present invention just can have been set up.It realizes details at characteristic explain of the present invention below.
1) helps to realize directly issue by cluster.Based on the support of the Internet equity point, any two the Internet computing equipments can be set up network mutually and connect, and either party both can initiatively send data, also can passive reception data.This provides primary condition for direct issue: the publisher can be directly and the recipient connect, and institute's distributing data need not to pass through other computing nodes and directly arrive the recipient.In fact, directly issue is not to set up contact between publisher and all recipients.Because the restriction of the computational resource of publisher own, a publisher can only connect with limited recipient usually.In this case, issue must be by the help of cluster.The publisher forms a cluster with the recipient is common, thereby finishes issuing process as a member.Though just having directly with the minority recipient, publisher itself is connected, because the support of High-Performance Computing Cluster from recipient's angle, still feels directly to have obtained distributing data.
2) utilize Clustering to realize issue fast.Clustering in the large-scale non-central Internet internet system has guaranteed to be distributed under the maximum rate that publisher and recipient's computing equipment allowed carries out.For issue, this cluster comprises publisher and all recipients' computing equipment.Under the support of this Clustering, all computational resources that computing node had that participate in issue have all obtained effective utilization, make distributing data to disseminate with the fastest speed in such environment.
3) utilize the relative stability of cluster to realize the big data quantity issue.Because the many and longer duration of big data quantity issue occupying system resources is so must carry out in a stable environment.The Clustering of large-scale non-central Internet internet system changes over the system of a localized sustained change computing environment of relatively stable even stable continuous enhancing on the whole.Such environment provides primary condition for the big data quantity issue.The publisher continues to send to the recipient to the data organized in such environment, and whether the recipient can look the quality decision of distributing data and continue to add or be present in this issue cluster.Be in the middle of the change that does not stop though the issue cluster is seen from a part, whole issue cluster big upheaval can not occur.Issue except the Clustering of utilizing the large-scale non-central Internet internet system big data quantity, whether the issue cluster stablizes the quality that also is decided by distributing data.The quality here refers to the pouplarity of distributing data.When the distributing data quality was low excessively, issue also can go on.This is that the recipient not only can not increase on the contrary and can descend owing to cross when hanging down when the distributing data quality, and the computational resource that causes participating in issuing gradually reduces; System can't satisfy the required minimum computational resource requirement of this issue when serious, thereby makes the issue failure.The poorest this situation can be assisted by the mechanism of peer server.
4) utilize the strong retractility of cluster to realize extensive issue.The realization of extensive issue directly depends on the Clustering of large-scale non-central Internet the Internet.Because this cluster itself has good retractility, under the situation that the computing node scale progressively increases, system capability can not descend, and can reach a peak value very soon after steadily improving; And under the situation that whole cluster scale does not significantly reduce, keep this peak value.When carrying out in being distributed on such cluster, its scale just is guaranteed.Be that publisher or recipient become a computing node in the cluster; If instant recipient increases, as long as it becomes a computing node in the cluster, it will be the raising or stable the contributing of whole issue cluster computing capability so.Issue is just realized like this, on a large scale.
5) utilize the large-scale non-central Internet the Internet transport protocol to realize the streaming issue.The realization of streaming issue and the host-host protocol of large-scale non-central Internet the Internet are closely related.This agreement has guaranteed that in such computing environment data are not to respond this batch (-type) mode transfer with typical request on the current internet, but transmit in computing node in the mode of continual and steady stream.The streaming issue just becomes possibility like this.
6) utilize the connection between publisher and the recipient to realize interactive issue.On the basis of big data quantity and streaming issue, the publisher can organize distributing data more freely, such as data set being made into the hierarchical structure that possesses multiple choices.The recipient obtains can be notified to the publisher to feedback according to the prompting of distributing data in the process of distributing data, and the publisher can send to the recipient to the data of correlated branch according to its wish.More complicated interactive mode is the ability that distributing data itself possesses the response user feedback, the user can change the mode that data flow arbitrarily in the data of issuing, the data that oneself need in the selection flow data, perhaps direct and publisher gets in touch the more valuable data of acquisition.
List of references:
【1】Hypertext?Transfer?Protocol；http://www.w3.org/Protocols/
【2】Vlavianos?Aggelos，et?al.BiToS：Enhancing?BitTorrent?for?Supporting?Streaming?Applications，INFOCOM?2006，25th?IEEE?International?Conference?on?Computer?Communications?Proceedings，April?2006，Page(s)：1-6
【3】Satyanarayanan?M.，Mullender?S.；Distributed?Systems，an?Advanced?Course，2ndEdition，Wokingham：ACM?Press/Addison-Wesley，1989
【4】Cohen?B.；Incentives?Build?Robustness?in?BitTorrent，in?Workshop?on?Economics?ofPeer-to-Peer?Systems，Berkeley?USA，May?2003
【5】Dana?C.，Li?D.，Harrison?D.，Chuah?C.N.；BASS：BitTorrent?Assisted?Streaming?System?for?Video-on-Demand，Multimedia?Signal?Processing，2005IEEE?7th?Workshop，Page(s)：1-4
【6】Yilei?Shao；Exploring?Social?Networks?in?Computer?Systems，PhD?Dissertation，Princeton?University，June?2007
【7】Newman?M?E?J.；The?Structure?and?Function?of?Complex?Networks，SIAM?Review，2003，45，Page(s)：167-256
【8】Hari?Prasad?Thadakamalla；Decentralized?Algorithms?for?Search?and?Routing?in?Large-Scale?Networks，PhD?Dissertation，Pennsylvania?State?University，December?2007。
Claims (5)
1. method that realizes instantaneous rapid large-scale low-cost Internet issue, it is characterized in that the method for described realization instantaneous rapid large-scale low-cost Internet issue comprises that the Internet computing node is transformed into the equity point provides condition for the resource that makes full use of internet; Utilize the equity point to formulate the large-scale non-central Internet the Internet transport protocol; Set up the large-scale non-central Internet the Internet and calculate cluster; Foundation is based on the issue mechanism of large-scale non-central Internet the Internet.
2. a kind of method that realizes instantaneous rapid large-scale low-cost Internet issue as claimed in claim 1 is characterized in that, describedly the Internet computing node is transformed into the equity point provides condition for the resource that makes full use of internet; Its specific implementation step is as follows:
1) gives between any two computing nodes not only possessing initiatively and send connection request but also ability that can passive corresponding the other side's request to the other side;
2) transforming common server is to possess the initiatively peer server of dedicate resources ability;
3) transform ordinary node for satisfying the reciprocity point that carries out the resource contribution under the condition of self needs.
3. a kind of method that realizes the instantaneous rapid large-scale low-cost Internet issue as claimed in claim 1, it is characterized in that, described utilization equity point is formulated the large-scale non-central Internet the Internet transport protocol, and new host-host protocol is effectively to utilize computational resource necessary under new the Internet architecture; Its specific implementation step is as follows:
1) has the quality that the alternative construction computational resource that flows number of nodes guarantees stream according to stream;
2) peer server by specific placement or seek the stream node and form support to weak current;
3) according to heterogeneous data character the stream in the transmission is dispatched; Descriptor at first is transmitted; Secondly, transmission text data; Subsequently, according to intrinsic relation between data, remaining non-transmission of textual data in each data cell is put in place; At last, a plurality of data cells are transferred in the short as far as possible time on the stream node, and in this process, consider time-sharing operation.
4) in transmission course, guarantee static relation and the dynamic relationship between data cell in the stream; The maintenance of relation does not strictly observe when requiring transmission, can look to get final product with the stream on the source node is consistent when showing; In search procedure, static state of reformulating according to relevant informations such as searching order standards and dynamic order;
5) take the respective transmissions strategy according to the character of data in the stream; Take the BT algorithm for the data that do not have sequential to require; Take BiToS algorithm and BASS algorithm for the data that have sequential to require;
6) data cell in the discriminating stream reduces the network cost to reuse the stream that transmitted;
7) give the means that user's convection current manages; The user can convection current stores, inquiry, renewal and deletion etc.; Change centralized management and be Decentralization.
4. a kind of method that realizes the instantaneous rapid large-scale low-cost Internet issue as claimed in claim 1 is characterized in that, the described large-scale non-central Internet the Internet of setting up calculates cluster, will disperse the computational resource tissue to claim cluster, finishes corresponding calculated; The specific implementation step is as follows:
1) adopts in the complex networks system that data are duplicated, netted multicast mechanism, dynamically screens node and set up cluster based on the routing algorithm of Complex Networks Theory;
2) adopt the large-scale non-central Internet the Internet transport protocol to guarantee the efficient operation of cluster.
5. a kind of method that realizes the instantaneous rapid large-scale low-cost Internet issue as claimed in claim 1 is characterized in that described foundation is based on the issue mechanism of large-scale non-central Internet the Internet; Its specific implementation step is as follows:
1) helps to realize directly issue by cluster; The publisher directly and the recipient connect; Publisher and limited recipient connect; The publisher is as a member, with cluster of the common formation of recipient;
2) utilize Clustering to realize issue fast; Utilize all to participate in the computational resource that computing node had of issue;
3) utilize the relative stability of cluster to realize the big data quantity issue; Utilize Clustering the system of localized sustained change to be changed on the whole the computing environment of relatively stable even stable continuous enhancing; When the quality of data is not high when causing computational resource to satisfy minimum requirements, assist by reciprocity service mechanism;
4) utilize the strong retractility of cluster to realize extensive issue; If instant recipient increases, it is changed into a computing node in the cluster, be the raising or stable the contributing of whole issue cluster computing capability;
5) utilize the large-scale non-central Internet the Internet transport protocol to realize the streaming issue;
6) utilize the connection between publisher and the recipient to realize interactive issue; The recipient is notified to the publisher to feedback according to the prompting of distributing data; The publisher sends to the recipient to the correlated branch data according to recipient's wish; Give the ability that distributing data itself possesses the response user feedback.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910148604XA CN101931541A (en) | 2009-06-25 | 2009-06-25 | Method for realizing instantaneous rapid large-scale low-cost Internet publishing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910148604XA CN101931541A (en) | 2009-06-25 | 2009-06-25 | Method for realizing instantaneous rapid large-scale low-cost Internet publishing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101931541A true CN101931541A (en) | 2010-12-29 |
Family
ID=43370477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910148604XA Pending CN101931541A (en) | 2009-06-25 | 2009-06-25 | Method for realizing instantaneous rapid large-scale low-cost Internet publishing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101931541A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022714A (en) * | 2016-05-10 | 2016-10-12 | 霍兵兵 | APP-software-based employment management system and using method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020038257A1 (en) * | 1994-04-28 | 2002-03-28 | Kuriacose Joseph | Apparatus for transmitting and receiving executable applications as for a multimedia system |
| CN101075904A (en) * | 2006-05-17 | 2007-11-21 | 华为技术有限公司 | Method and system for ensuring service resource performance in P2P network |
| CN101098271A (en) * | 2006-06-29 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Expandable P2P flow media system |
| CN101127784A (en) * | 2007-09-29 | 2008-02-20 | 网秦无限（北京）科技有限公司 | Method and system for quickly obtaining network information service at mobile terminal |
-
2009
- 2009-06-25 CN CN200910148604XA patent/CN101931541A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020038257A1 (en) * | 1994-04-28 | 2002-03-28 | Kuriacose Joseph | Apparatus for transmitting and receiving executable applications as for a multimedia system |
| CN101075904A (en) * | 2006-05-17 | 2007-11-21 | 华为技术有限公司 | Method and system for ensuring service resource performance in P2P network |
| CN101098271A (en) * | 2006-06-29 | 2008-01-02 | 腾讯科技（深圳）有限公司 | Expandable P2P flow media system |
| CN101127784A (en) * | 2007-09-29 | 2008-02-20 | 网秦无限（北京）科技有限公司 | Method and system for quickly obtaining network information service at mobile terminal |
Non-Patent Citations (2)
| Title |
|---|
| 夏仲璞: "基于P2P技术的BT网络研究与测量", 《中国优秀硕士学位论文全文数据库》 * |
| 黄晓明: "P2P环境下的内容分发机制研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022714A (en) * | 2016-05-10 | 2016-10-12 | 霍兵兵 | APP-software-based employment management system and using method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103260050B (en) | Based on the video on-demand system of Google App Engine Cloud platform | |
| Pianese et al. | Pulse, a flexible p2p live streaming system | |
| Fan et al. | Video delivery networks: Challenges, solutions and future directions | |
| CN108124168A (en) | A kind of video sharing method perceived under mobile radio network based on user interest | |
| Chandler et al. | Toward p2p-based multimedia sharing in user generated contents | |
| Kim et al. | Efficient neighbor selection through connection switching for P2P live streaming | |
| CN101808104A (en) | Method for constructing internet operating in streaming manner | |
| Ma et al. | Measurement, modeling and enhancement of BitTorrent-based VoD system | |
| Chang et al. | Social VoD: A social feature-based P2P system | |
| CN101931541A (en) | Method for realizing instantaneous rapid large-scale low-cost Internet publishing | |
| Tian et al. | A novel caching mechanism for peer-to-peer based media-on-demand streaming | |
| Yue et al. | Survey on scheduling technologies of P2P media streaming | |
| CN101262360A (en) | A method and device for real time stream media multi-point transmission | |
| Li et al. | On the source switching problem of Peer-to-Peer streaming | |
| Oliveira et al. | Improving peer neighborhood on P2P video distribution networks using Push/Pull protocol | |
| CN101645911A (en) | Dynamic cluster-based news service method | |
| Xiao et al. | Toward systematical data scheduling for layered streaming in peer-to-peer networks: Can we go farther? | |
| CN101800655A (en) | Peer-to-peer service system establishing method for contributing resources to application of large-scale internet | |
| Wang et al. | Channel-aware peer selection in multi-view peer-to-peer multimedia streaming | |
| Dakshayini et al. | An optimal prefix replication strategy for VoD services | |
| Xue et al. | Churn resilience of distributed content service system on smart terminals network | |
| CN101800670A (en) | Method for building website for actively searching client to realize scale expansion | |
| Shen et al. | The research of a new streaming media network architecture based on the fusion of P2P and CDN | |
| Chung et al. | A fast channel switching system for IPTV based on multi-channel preview | |
| Reddy et al. | Adaptive P2P Live Streaming Model Using Connection Switching to Enhance the QoS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: Seoul Weiyang District 710021 Township marsh in Shaanxi province Xi'an city Changle Xiyuan road room 10A-904 Li Bing Applicant after: Li Bing Address before: 102600 Beijing City, Daxing District Daxing Industrial Development Zone Jinyuan Road No. 24, room D151 Applicant before: Li Bing |
|
| DD01 | Delivery of document by public notice |
Addressee: Li Bing Document name: the First Notification of an Office Action |
|
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20101229 |