CN101009655B - Traffic scheduling method and device - Google Patents
Traffic scheduling method and device Download PDFInfo
- Publication number
- CN101009655B CN101009655B CN200710003485XA CN200710003485A CN101009655B CN 101009655 B CN101009655 B CN 101009655B CN 200710003485X A CN200710003485X A CN 200710003485XA CN 200710003485 A CN200710003485 A CN 200710003485A CN 101009655 B CN101009655 B CN 101009655B
- Authority
- CN
- China
- Prior art keywords
- user
- bandwidth
- formation
- scheduling
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
- H04L47/62—Queue scheduling characterised by scheduling criteria
- H04L47/621—Individual queue per connection or flow, e.g. per VC
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The disclosed flow-schedule method in this case comprises: taking the user information of exact business in information flow as the sequence element to configure into queue of exact business, wherein, one queue matching one exact business; according to the exact business and user information in queue, allocating bandwidth for element in queue. It also discloses a flow-schedule device. This invention simplifies circuit and management work well, reduces data error, and improves schedule efficiency.
Description
Technical field
The present invention relates to the flow scheduling technical field of network, relate in particular to a kind of traffic scheduling method and device.
Background technology
Influence each other and mutually promote between internet that develops rapidly (Internet) and the user's request that improves constantly.Nowadays, the user extends to business fields, broadband such as Internet access at a high speed, video telephone, video request programs from low speed business such as traditional phone, fax, telegrams gradually to the demand of communication.Therefore, the network traffics that day by day all increase, and user's requirement more and more higher to service quality all propose more and more higher requirement to router performance and service quality (QoS) as the Internet nucleus equipment.
Prior art adopts flow scheduling (TM) technology that network traffics are dispatched for guaranteeing the QoS performance of Internet at present, to reduce the message dropping rate, to reduce message transfer delay and time delay shake.So-called scheduling refers to the reference factor of router based on some, allocates to sent the transmission rate of information flow, and under the situation of network congestion, guarantees the fairness that sends.Information flow can be video flowing, audio stream or data flow etc.
Referring to Fig. 1, Fig. 1 is the schematic diagram of existing Pyatyi flow scheduling scheme.This Pyatyi scheduling scheme carries out flow scheduling based on stream (Flow), user (user), Virtual Local Area Network, queue priority (class) and these five reference factors of port (port) respectively.In order to realize scheduling, the information flow that existing flow scheduling scheme needed to receive before scheduling is classified according to certain rule, so that adopt suitable dispatching algorithm to realize scheduling to inhomogeneous information flow.Existing flow scheduling scheme is classified as same class respectively with the message data that has identical sources Internet protocol (IP) address, purpose IP address, source port number, destination slogan, protocol number and COS in the information flow usually, be same stream, and based on formation of a stream division, what wherein discharge in each formation is exactly each the message data information that belongs to same stream.
Existing flow scheduling scheme is carried out flow scheduling based on stream, and this scheduling is dispatched corresponding to the level V among Fig. 1.In the scheduling of level V level, router is according to the message data information in the formation, search the scheduling parameter relevant with this message data information, calculate scheduling result based on scheduling parameter, promptly calculate and to be the bandwidth of this queue assignment, for the different different priority of formation configuration, distribute corresponding bandwidth, this scheduling can adopt absolute priority (SP) or weight repeating query dispatching algorithms such as (WRR) to realize.The reference factor of fourth stage scheduling is the user.Therefore the corresponding a plurality of streams of user's possibility, if the situation of this user's total bandwidth above the bandwidth of user's purchase appears distributing in the level V scheduling result, are dispatched by the fourth stage so that distribute to the bandwidth that user's total bandwidth is no more than this user's purchase so; Can adopt dummy clock shaping (SHVC) algorithm to realize this grade scheduling.The reference factor of third level scheduling is a Virtual Local Area Network, and this grade scheduling is adjusted the bandwidth of distributing to individual queue by vlan network planning; Can adopt Weighted Fair Queuing (WFQ) algorithm to realize this grade scheduling.The reference factor of second level scheduling is queue priority (class), by this level scheduling, guarantees that the information flow with higher priority goes out team earlier; Can adopt absolute priority (SP) algorithm to realize this grade scheduling.The reference factor of first order scheduling is port (port), and the effect of this grade scheduling is that the flow to outbound port carries out shaping, so that information flow sends more equably; Can adopt the WFQ algorithm to realize this grade scheduling.
The inventor finds that under study for action prior art is a kind of flow scheduling technology of data driven type.So-called data-driven refers to, and the network node of being responsible for flow scheduling just carries out flow scheduling when receiving message data.The circuit of realizing scheduling at first needs to carry out above-mentioned traffic classification according to the data that receive, then for guaranteeing the requirement of flow control, need from corresponding scheduling parameter table, search the scheduling parameter of each item number of adding formation earlier, and then calculate scheduling result based on scheduling parameter according to correspondence.Because adding the length and the content of the real data of formation changes at any time, be difficult to prediction in advance, and, if existing flow scheduling scheme needs accurately each user service flow of control, the so required number of queues of setting up may be bigger, as existing 4k user, each user has 8 streams, so existing flow scheduling scheme need set up 32k formation to realize flow scheduling, and to carry out flow scheduling to numerous formation like this, its complexity that realizes circuit will inevitably be higher, and be difficult to realize scheduling at a high speed.And if by simplifying the measure of the second level, the third level or level Four scheduling, simplify the complexity of circuit as far as possible, the dispatching effect that obtains so will be difficult to satisfy the requirement of network.
Therefore, the problem that existing flow scheduling scheme exists is, carries out flow scheduling based on the data that receive, and the complexity that causes circuit to be realized is higher.
Summary of the invention
The embodiment of the invention provides a kind of traffic scheduling method, simplifies the complexity that the flow scheduling circuit is realized.
A kind of traffic scheduling method comprises:
Will with concrete professional user information corresponding in the type of service under the information flow, be configured in the concrete professional corresponding queues as queue element (QE), one of them formation corresponding one concrete professional;
According to the concrete business of formation correspondence and the user profile in the formation, for the user of the element correspondence in the formation distributes bandwidth; Described for the user distributes bandwidth, the number of times of the chance by the transmission data that provide for the user of the element correspondence in the formation in the unit interval embodies.
The embodiment of the invention also provides a kind of flow scheduling device, simplifies the complexity that the flow scheduling circuit is realized.
A kind of flow scheduling device comprises: queue element (QE) configuration module and bandwidth allocation module; Wherein,
The queue element (QE) configuration module, be used for with information flow under the concrete professional user information corresponding of type of service, be configured in the concrete professional corresponding queues as queue element (QE), will dispose user profile and with concrete professional corresponding queues information output;
Bandwidth allocation module is used to receive the described queuing message from the queue element (QE) configuration module, according to the concrete business of formation correspondence and the user profile in the formation, for the user of the element correspondence in the formation distributes bandwidth; Described for the user distributes bandwidth, the number of times of the chance by the transmission data that provide for the user of the element correspondence in the formation in the unit interval embodies.
Traffic scheduling method that the embodiment of the invention provides and device, according to the concrete delineation of activities formation that provides by operator, the user profile of the concrete business that customization is corresponding with formation is as the element of forming this formation, and carry out flow scheduling based on user profile in the formation and corresponding concrete business, because the kind of the concrete business that operator provides is limited, and concrete professional bandwidth is normally fixed, therefore, the number of queues that can mark off is not too large, and owing to number of users in the formation and concrete professional parameters such as bandwidth can be predicted, therefore when carrying out flow scheduling, can only need bandwidth according to the concrete business corresponding with formation, for the user that user profile identified in the formation distributes this bandwidth, need to carry out traffic classification in the existing flow scheduling scheme of comparing according to the real data that is difficult to predict, distribute the way of bandwidth by searching the correlative flow parameter more afterwards, the flow scheduling scheme of the embodiment of the invention is easier to realize.And, owing to carry out flow scheduling based on concrete business, the concrete professional user of concrete business and customization is configured and operator also is based on when the network planning, this flow scheduling strategy that just makes the embodiment of the invention and the operator relevant configuration when the network planning can be corresponding, therefore makes scheduling result can satisfy network demand more.As seen, adopt the flow scheduling scheme of the embodiment of the invention, when guaranteeing that scheduling result can satisfy network demand, can effectively simplify the circuit complexity of flow scheduling.
Description of drawings
Fig. 1 is the schematic diagram of existing Pyatyi flow scheduling scheme;
Fig. 2 is the flow chart of the flow scheduling overall plan that provides of the embodiment of the invention;
Fig. 3 is the structural representation of the flow scheduling device that provides of the embodiment of the invention;
Fig. 4 is the schematic diagram that carries out flow scheduling in the embodiment of the invention 1 based on concrete business;
Fig. 5 is a queue element (QE) discharging schematic diagram in the embodiment of the invention;
Fig. 6 is the schematic diagram that the embodiment of the invention 2 is carried out flow scheduling.
Embodiment
For making embodiment of the invention technical scheme and advantage clearer, describe in further detail below in conjunction with accompanying drawing.
Different with the existing flow scheduling scheme of mentioning in the background technology is, the traffic scheduling method that the embodiment of the invention provides is not based on the real data that receives and carries out flow scheduling, and the concrete business that is based on user and customization is carried out flow scheduling, therefore, whether there is actual business datum and uncorrelated in flow scheduling process in the embodiment of the invention and the formation, the user profile of scheduling result for sending by certain speed also is the user chance that once sends data is provided.
Referring to Fig. 2, Fig. 2 is the flow chart of the flow scheduling overall plan that provides of the embodiment of the invention.This flow process may further comprise the steps:
Step 201, according to the concrete business of type of service under the information flow, divide and concrete professional corresponding queues.
In the existing network business, type of service is usually nothing more than three classes under the information flow: video traffic, audio service and data service.The kind of the concrete business of type of service also is limited under the information flow that operator provided, and as for audio service, it is the concrete business of 64k byte per second (b/s), 128kb/s or 256kb/s etc. that operator can provide basic rate.The present invention is based on concrete business and divide formation, only providing a basic rate as operator is the audio service of 64kb/s, also be one based on the formation number that this audio service marked off so, and the pairing concrete business of this formation promptly is that basic rate is the audio service of 64kb/s.
Further, in the practical application, because the available concrete business of operator is normally multiple, correspondingly, the formation that marks off also has a plurality of.The process of dividing formation can be: the type of service that can provide operator is classified earlier, as is divided into video traffic, audio service and data service, can determine type of service under the information flow-rate by this classification; And then the concrete business of every kind of type of service that can provide based on operator is divided formation, mention that as above-mentioned the concrete business of audio stream has three kinds, correspondingly, based on these three kinds concrete business, can mark off and these three kinds concrete professional 3 corresponding respectively formations; In addition, if the concrete business of the available video flowing of operator is 1Mb/s, 2Mb/s and 4Mb/s, so similarly, can mark off 3 formations again based on these three kinds of concrete business; If the concrete business of the data flow that provides is 256kb/s, 1Mb/s and 10Mb/s, so similarly, also can mark off 3 formations based on these three kinds of concrete business.
The user profile at this place can be user ID (ID) information, as phone number of user etc.In the practical application,, be the audio service of 64kb/s as basic rate if the user has bought a concrete professional service, so can with this user ID as with this concrete professional corresponding queues in element, be configured in this formation.
The situation that may occur in the practical application comprises: a plurality of users have bought the service of same concrete business, so with this concrete professional corresponding queues in, the id information that these a plurality of users can occur, the corresponding element forming this formation of each user ID, distribute numbering for these a plurality of user ID, each user ID is configured to position corresponding with numbering in this formation according to numbering; Perhaps, operator provides multiple concrete business, and user bought the service of a plurality of concrete business, so with a plurality of concrete professional corresponding respectively individual queue in an identical element can appear, user ID information that promptly should a plurality of concrete business of purchase.
Certainly, the situation that actual capabilities occur can't be limited to above-mentioned several, but the basic way that forms formation among the present invention can be above-mentioned based on concrete delineation of activities formation, and will be somebody's turn to do concrete professional corresponding user ID and add this formation as composition corresponding queues element.
Step 203, according to the concrete business of formation correspondence and the user profile in the formation, for the user of the element correspondence in the formation distributes bandwidth.
The flow scheduling strategy of the embodiment of the invention carries out based on user profile and corresponding concrete business, rather than based on actual reception to information flow carry out.Because the concrete business that operator provides, its required bandwidth is more fixing, therefore, when carrying out flow scheduling, in the existing relatively flow scheduling scheme, need by search with formation in the corresponding flow parameter of actual message data, calculate this way of scheduling result, the specific implementation of the scheduling strategy of the embodiment of the invention is comparatively simple and easy.Relevant this advantage of the present invention will elaborate hereinafter.
In actual applications, if formation based on concrete delineation of activities, can not need to carry out above-mentioned steps 201 more so, and only need when queue element (QE) have change, the deployment queue element gets final product.
The embodiment of the invention also provides a kind of flow scheduling device based on above-mentioned traffic scheduling method.Referring to Fig. 3, Fig. 3 is the structural representation of this device embodiment, comprising: queue element (QE) configuration module 301 and bandwidth allocation module 302; Wherein,
Queue element (QE) configuration module 301, be used for with information flow under the concrete professional user information corresponding of type of service, be configured in the concrete professional corresponding queues as queue element (QE), will dispose user profile and with concrete professional corresponding queues information output;
Receiver module is used to receive the described queuing message from the queue element (QE) configuration module, sends described queuing message to first distribution module;
First distribution module, be used to receive described queuing message, according to the bandwidth parameter of the concrete business corresponding,, user profile is exported as bandwidth allocation information by this bandwidth respective rate for the pairing user of each element in this formation distributes corresponding bandwidth with formation.
First distribution module specifically can comprise:
Formation bandwidth allocation module and user bandwidth distribution module; Wherein,
The formation bandwidth allocation module is used for the product according to element number in the bandwidth parameter of the concrete business corresponding with the formation user and the formation, is this queue assignment bandwidth, sends the information of user ID to the user bandwidth distribution module by this bandwidth respective rate;
The user bandwidth distribution module, be used to receive above-mentioned information from the formation bandwidth allocation module, to dispatch out team with described information user information corresponding, give user in this formation with the allocated bandwidth of distributing to this formation, user profile is exported as bandwidth allocation information by the bandwidth respective rate that the user gets.
Second distribution module is used to receive the above-mentioned user ID of first distribution module, judges the data whether this user in the formation exists needs to send, if, keep the bandwidth of distributing to this user, by this bandwidth respective rate user totem information is exported; Otherwise, discharge the bandwidth of distributing to this user; Above-mentioned judgement can identify based on pre-configured valid data and realize;
The 3rd distribution module, be used to receive described user ID from first distribution module or second distribution module, same user's bandwidth addition will be distributed in the individual queue, and the bandwidth sum that obtains is limited in the pre-set threshold, by the corresponding speed of the total bandwidth that will distribute to this user this user ID is exported afterwards.
The flow scheduling device of the embodiment of the invention also can further comprise based on above-mentioned structure shown in Figure 3:
The queue scheduling module, be used to receive above-mentioned information, according to type of service under the information flow-rate, for the type of service corresponding queues that real-time is higher is distributed higher priority from bandwidth allocation module, and according to described priority, the scheduling result of the formation that priority is higher is preferentially exported.
Below in conjunction with two embodiment the flow scheduling scheme that the embodiment of the invention provides is elaborated.
Because the scheduler object of the embodiment of the invention is not a real data, but the user ID one by one of composition formation, therefore, the scheduling result that obtains also is a user ID, after follow-up data transmission unit is received this user ID, data cell with this user's certain-length sends again, and this also is that what why to say that the embodiment of the invention dispatches out is not real data, but the reason of the chance that once sends data is provided for the user.As seen, send same user ID how many times in the unit interval, just can determine how many bandwidth of the actual use of this user is, otherwise, if know therefore, in the embodiment of the invention, for what of actual bandwidth the user distribute, embody by the chance that provides how many times to send data for this user.
Embodiment 1:
Referring to Fig. 4, Fig. 4 is the schematic diagram that carries out flow scheduling in the embodiment of the invention 1 based on concrete business.The flow scheduling of present embodiment is three grades of scheduling, and the reference factor of scheduling is respectively user and concrete business, formation total bandwidth and queue priority.Dispatching owing to the Pyatyi of subsequent embodiment 2 is to increase two-level scheduler to carry out on three grades of scheduled basis of embodiment 1, and therefore, for corresponding with embodiment 2, the numbering of the scheduling progression identical with reference factor among the embodiment 2 is also identical among the maintenance embodiment 1.In the present embodiment, the information flow that establishing operator provides comprises: video flowing, audio stream and data flow, and wherein, the concrete business of the video flowing that is provided comprises: 1Mb/s, 2Mb/s and 4Mb/s; The concrete business of audio stream comprises: 64k byte per second (b/s), 128kb/s and 256kb/s; The concrete business of data flow comprises: 256kb/s, 1Mb/s and 10Mb/s.Next, the scheduling at different levels of present embodiment are described successively.
The level V scheduling:
In this level scheduling,, need earlier based on concrete delineation of activities dequeue for realizing the flow scheduling of the embodiment of the invention.The process of dividing formation can be: the type of service of information flow on the network that is provided according to operator at present at first, the information flow that may receive is classified, and can be divided into aforesaid video flowing, audio stream and data flow; And then according to operator at the above-mentioned concrete business that each class business is provided, mark off 9 formations as shown in Figure 4; Afterwards, each concrete professional user ID information of customization as the element in the corresponding queues, is configured in this formation, referring to Fig. 5 according to numbering, what discharge in each formation is associated user's id information, is different from the message data information of discharging in the formation of existing flow scheduling scheme.
The reference factor of level V scheduling is user and concrete professional.In this level scheduling, since in each formation the user bought is identical concrete business, therefore, the User Priority of forming each element correspondence of this formation in each formation can be identical, and the maximum bandwidth that will be got also can be identical, that is to say that the pairing user of each element sends the equal-opportunity of data in the formation.So-called maximum bandwidth i.e. the speed of the pairing concrete business of this formation.
In addition, if honored guest's level user can be thought of as this user so and open up a formation separately, the way that disposes this formation can be with reference to above-mentioned related description.
Fourth stage scheduling:
The reference factor of this grade scheduling is the formation total bandwidth.Specifically, in the scheduling of this level, for the principle of each formation configuration schedules parameter can be, the total bandwidth of distributing to this formation is the product of the user corresponding with each element of the element number in this formation maximum bandwidth that can be assigned with.Therefore, in the scheduling of this level, for the total bandwidth of each queue assignment can be this formation the maximum bandwidth that can be assigned to.Consider the bandwidth that may surpass output port for the total bandwidth sum of all queue assignment, when scheduling, can be the weight of each queue assignment bandwidth, if promptly port bandwidth is 10M, and the total bandwidth sum of all queue assignment has 20M, and the total bandwidth of establishing certain formation that the principle according to above-mentioned configuration schedules parameter calculates is 2M, and then the weight of correspondence is 0.5 by for this queue assignment bandwidth the time, can get the bandwidth that actual this formation obtains is 1M, guarantees scheduling fairness with this.Realizing scheduling, when promptly calculating scheduling result,, can adopt different dispatching algorithms for different types of service.As, for audio service, can adopt existing SHVC algorithm computation scheduling result; For video traffic or data service etc., can select to adopt existing WFQ algorithm or WRR algorithm computation scheduling result according to actual conditions.And the bandwidth of distributing to certain formation embodies by the chance that provides how many times to send data for the user in this formation, send the how many times user ID in other words in unit interval, the user ID at this place be not limited in the formation which or which, because all User Priorities are identical in the same formation, therefore the user of each element correspondence obtains the probability equal of chance, correspondingly, the scheduling result of the fourth stage is exactly the user ID that sends according to the corresponding speed of the total bandwidth of distributing to individual queue, so-called corresponding speed refers to has known the total bandwidth of distributing to formation, send the length of data so based on the user at every turn, just can know to send what user ID in the unit interval.
Further, above-mentioned level V scheduling can be carried out on the basis of fourth stage scheduling, has been scheduling to each queue assignment after the total bandwidth at the fourth stage, and repeating query (RR) mechanism is adopted in the level V scheduling, to distribute to the total bandwidth of this formation, mean allocation is given each user in this formation.Should be embodied in for each user's mean allocation bandwidth: determine that according to the total bandwidth of formation all users in this formation send the number of times of data in the unit interval; The number of times of these transmission data is pro rata distributed user to each element correspondence in this formation.Be about to this formation sends user ID in the unit interval number of times and all give the user of each element correspondence, as the user ID number that can send in this formation unit interval is 10,000,1,000 users are arranged in this formation, each user has the chance of 10 transmission data in the unit interval so, correspondingly, the level V scheduling result is exactly this user ID by the output of the corresponding speed of the bandwidth of distributing to each user, for the explanation of corresponding speed with above related content is similar.Fourth stage scheduling can realize alternately with the level V scheduling.
Also need to prove, if the concrete class of business that operator provides is more, and the relation of the speed between some concrete business may be the multiple relation, in above-mentioned each concrete business corresponding with video flowing, the speed of the concrete business of 2Mb/s obviously is 2 times of speed of the concrete business of 1Mb/s, and that actual purchase has a user of concrete business of higher rate is less, like this under the situation, too many and reduce and offer the resource of a formation again for fear of the number of queues that marks off, adoptable way is: in the concrete professional corresponding queues of 1Mb/s, dispose to two elements in this formation buying concrete this professional user ID of 2Mb/s, in a formation two identical elements may appear promptly, concrete way can be for this user distributes two numberings, and this user ID information configuration is numbered corresponding respectively positions with two that distribute in this formation; So when level V is scheduling to each element repeating query in each formation and distributes bandwidth, the user of this purchase higher rate business can be assigned to the bandwidth corresponding with this formation for twice, like this, both can guarantee that distributing this user's bandwidth was the bandwidth that this user buys, reduce number of queues again, and then save the circuit resource of realizing scheduling.
About the explanation of level V and fourth stage scheduling so far can come to an end.
First order scheduling:
The reference factor of this grade scheduling is a service priority, and the purpose of this grade scheduling is for the real-time demand according to different service types, higher priority is given the formation that real-time is had relatively high expectations.
Scheduling result based on fourth stage scheduling, first order scheduling further is in above-mentioned three kinds of business, the audio service corresponding queues that real-time is had relatively high expectations is distributed higher priority, under the situation that guarantees the individual queue bandwidth, make the user in the higher formation of priority can obtain good quality of service, be about to the scheduling result output of the higher formation of priority, this scheduling result also is certain user ID.
This level scheduling can be adopted existing SP dispatching algorithm when specific implementation, calculate scheduling result, promptly based on traffic performance, for individual queue is distributed priority.
The explanation of relevant first order scheduling so far can come to an end.
Embodiment 2:
Referring to Fig. 6, Fig. 6 is the schematic diagram that the embodiment of the invention 2 is carried out flow scheduling.For better scheduling performance and parameter are provided, present embodiment on above-mentioned three grades of scheduled basis, increases third level scheduling and second level scheduling based on embodiment illustrated in fig. 4, forms the prioritization scheme of a Pyatyi scheduling.Wherein,, therefore do not give unnecessary details, mainly the third level shown in Figure 6 and the second level are dispatched and elaborate because level V shown in Figure 5, the fourth stage and first order scheduling are identical with the scheduling of above-mentioned identical progression numbering shown in Figure 3.
Third level scheduling:
The reference factor of this grade scheduling is user's valid data.By the above-mentioned explanatory note of dispatching about the fourth stage as can be known, the scheduling result of fourth stage scheduling is the user ID that sends according to the corresponding speed of the total bandwidth of distributing to individual queue, coming provides the chance that sends data for the user, and do not consider the bandwidth whether user's reality be assigned with in use, whether the valid data that are the user exist, as user's purchase is certain telephone service, obviously, the user can not use this telephone service all the time, therefore, if the user takies the bandwidth of this telephone service correspondence always, so obviously can cause the waste of bandwidth resources.The effect of this third level scheduling is, discharges the user's who distributes not occupied bandwidth resources, will offer in other words not use the chance of professional user's transmission data to abandon.When specific implementation, can identify by pre-configured valid data, promptly adopt the amount of information of a bit (bit) to indicate the user whether to have the valid data of needs transmission, if indication exists, then keep the bandwidth of distributing to this user, be about to this user ID output, if indication does not exist, the bandwidth resources that then will distribute to this user discharge, and this that promptly abandons the user sends the chance of data, make a plurality of users can the shared bandwidth resource.
Second level scheduling:
The reference factor user of this grade scheduling.A user may customize a plurality of concrete business, and the effect of this grade scheduling is that the total bandwidth that will distribute to a user is limited in the pre-set threshold, and this threshold value can be the bandwidth of the actual customization of user, or operator is user configured bandwidth.Because fourth stage dispatching office is distributed to the bandwidth that the bandwidth of each element in each formation is the concrete business of correspondence, that is to say it is that this concrete professional user of customization can obtainable maximum bandwidth, therefore, if a customization a plurality of concrete business, so the 4th or the scheduling result of level V in, if will distribute to this user's bandwidth addition in the individual queue, the situation that resulting bandwidth sum has surpassed the bandwidth of the actual customization of this user appears so probably, dispatch by the second level, can the bandwidth sum that the user obtains be limited, specific practice can be: the total bandwidth parameter information that pre-configured user buys; User ID information based in the individual queue calculates the total bandwidth that same user gets; Total bandwidth that this user is got and pre-configured total bandwidth parameter information compare, if the former is greater than the latter, then can reduce the total bandwidth of distributing to this user according to each concrete professional pairing formation bandwidth weighting of this customization.
Another exercising result of second level scheduling is to the 4th or the scheduling result of the third level, carries out traffic shaping based on the user, that is, the speed that makes the user send information flow meets the service traffics model.This grade scheduling can adopt existing GCRA algorithm to realize, specific practice can be: overlap independently flow parameter based on the concrete business configuration one of each customization in advance, so that each user is carried out traffic shaping independently, wherein, flow parameter can comprise: this concrete professional average speed, the maximum rate that may reach etc.; Then, the maximum rate of flow parameter is dark as bucket, and calculate this in conjunction with the markers that sent last time and send the token that data can be used, if token number enough sends a unit data, this user can be sent the chance output of data so, if token number does not enough send a unit data, the chance that so this user is sent data abandons; Afterwards, the Mean Speed of concrete business is dark as bucket, and calculate this available token number in conjunction with the markers that sent data last time, if token number enough sends a unit data, this user can be sent the chance output of data so, can real data be sent the designation data transmitting element, if token number does not enough send a unit data, the chance that so this user is sent data abandons.Through the computing of above-mentioned GCRA algorithm, can send the speed do adjustment preferably of data to the user, make the speed that sends data level and smooth as far as possible.Therefore,, can guarantee to distribute in the fourth stage scheduling fairness of bandwidth, realize bandwidth resources sharing between the user through second level scheduling.And,, therefore, can guarantee that each user gets under the situation of suitable bandwidth, the key property of the transmission data of each port of assurance equipment because operator carries out the bandwidth planning of network usually according to number of users.
The explanation of relevant second level scheduling so far comes to an end.
In addition, above-mentioned third level scheduling can be arranged in after fourth stage scheduling or the second level scheduling, because the effect of this grade is to filter out the chance that invalid user sends data, therefore, be arranged in after the fourth stage scheduling, can reduce follow-up transinformation, improve the operational efficiency of circuit, and effectively reduce the performance requirement that pairing circuit is dispatched in the second level.Also need to prove, if just will not having the user ID of valid data when level V is dispatched picks out from formation, may cause so dispatching and still need according to whether existing the monitored results of valid data to carry out to the user, the above-mentioned relatively need user ID that customization is specifically professional is configured to the way in the formation, may not be easy.Therefore, in actual applications, recommend to adopt the 4th or second level scheduling after carry out the way that the third level is dispatched.
In order to make the speed that sends data more even, even the traffic shaping better effects if in actual applications, also can increase the traffic shaping of one-level based on port, relevant traffic shaping based on port can adopt comparatively ripe prior art, does not repeat them here.
In sum, traffic scheduling method that the embodiment of the invention provides and device, according to the concrete delineation of activities formation that provides by operator, the user profile of the concrete business that customization is corresponding with formation is as the element of forming this formation, and carry out flow scheduling based on user profile in the formation and corresponding concrete business, because the kind of the concrete business that operator provides is limited, and concrete professional bandwidth is normally fixed, therefore, the number of queues that can mark off is not too large, and owing to number of users in the formation and concrete professional parameters such as bandwidth can be predicted, therefore when carrying out flow scheduling, can only need bandwidth according to the concrete business corresponding with formation, for the user that user profile identified in the formation distributes this bandwidth, need to carry out traffic classification according to the real data that is difficult to predict in the existing flow scheduling scheme of comparing, distribute the way of bandwidth by searching the correlative flow parameter more afterwards, the flow scheduling scheme of the embodiment of the invention is easier to realize.And, owing to carry out flow scheduling based on concrete business, the concrete professional user of concrete business and customization is configured and operator also is based on when the network planning, this flow scheduling strategy that just makes the embodiment of the invention and the operator relevant configuration when the network planning can be corresponding, therefore makes scheduling result can satisfy network demand more.As seen, adopt the flow scheduling scheme of the embodiment of the invention, when guaranteeing that scheduling result can satisfy network demand, can effectively simplify the circuit complexity of flow scheduling, dispatcher software configuration management work reduces the data dispatching probability of makeing mistakes, and improves dispatching efficiency.
Further, because the flow scheduling strategy of the embodiment of the invention can be corresponding with the relevant configuration of operator when the network planning, therefore can also make the software parameter that carries out flow scheduling dispose more easy.
In addition, because the flow scheduling strategy of the embodiment of the invention does not relate to real data, scheduling is carried out based on the customer parameter that can predict and concrete professional bandwidth parameter, resulting scheduling result provides the chance that user sends data in fact, the chance of these transmission data is sent to data transmission unit, indicate this data transmission unit according to scheduling result, promptly send data according to information such as certain speed and priority, therefore, say in principle, adopt the flow scheduling strategy of the embodiment of the invention, can not cause loss of data or data to send the situation of makeing mistakes because scheduling makes mistakes, therefore, can effectively guarantee reliability of data transmission and correctness, service quality is provided.
Claims (18)
1. a traffic scheduling method is characterized in that, comprising:
Will with concrete professional user information corresponding in the type of service under the information flow, be configured in the concrete professional corresponding queues as queue element (QE), one of them formation corresponding one concrete professional;
According to the concrete business of formation correspondence and the user profile in the formation, for the user of the element correspondence in the formation distributes bandwidth; Described for the user distributes bandwidth, the number of times of the chance by the transmission data that provide for the user of the element correspondence in the formation in the unit interval embodies.
2. method according to claim 1 is characterized in that, described user profile is the user ID id information.
3. method according to claim 1 and 2 is characterized in that, described will with concrete professional user information corresponding in the type of service under the information flow, the step that is configured in the concrete professional corresponding queues as queue element (QE) comprises:
With one or more described user profile each element, be configured in the described formation as described formation.
4. method according to claim 3 is characterized in that, described with one or more described user profile each element as described formation, the step that is configured in the described formation comprises:
Same user profile is disposed to two elements in the described formation at least.
5. method according to claim 1 and 2 is characterized in that, described user for the element correspondence in the formation distributes the step of bandwidth to comprise:
According to the bandwidth parameter of the concrete business corresponding, for the pairing user of each element in this formation distributes corresponding bandwidth with formation.
6. method according to claim 5 is characterized in that, described is that the pairing user of each element distributes the step of corresponding bandwidth to comprise in this formation:
The bandwidth parameter of the pairing concrete business of described formation and the element number in the formation are multiplied each other, draw the total bandwidth of distributing to this formation;
Described total bandwidth is pro rata distributed to the corresponding respectively user of each element in this formation.
7. method according to claim 6 is characterized in that, the step that the described total bandwidth that will distribute to this formation is pro rata distributed to the corresponding respectively user of each element in this formation comprises:
Give the corresponding respectively user of each element in this formation with the total bandwidth mean allocation of distributing to this formation;
Perhaps, the resulting bandwidth of weight of correspondence when multiply by described total bandwidth into this queue assignment bandwidth, mean allocation are given the corresponding respectively user of each element in this formation.
8. method according to claim 6 is characterized in that, the described step that described total bandwidth is pro rata distributed to the corresponding respectively user of each element in this formation specifically comprises:
Determine that according to described total bandwidth all users in this formation send the number of times of data in the unit interval; The number of times of these transmission data is pro rata distributed user to each element correspondence in this formation.
9. method according to claim 5 is characterized in that, described user for the element correspondence in the formation distributes the step of bandwidth further to comprise:
Judge the data whether user exists needs to send, if keep the bandwidth of distributing to this user; Otherwise, discharge the bandwidth of distributing to this user.
10. method according to claim 5 is characterized in that, described user for the element correspondence in the formation distributes the step of bandwidth further to comprise:
If have same user profile in a plurality of formations, then will distribute to this user's bandwidth addition in the individual queue, and the bandwidth sum that obtains is limited in the pre-set threshold.
11. method according to claim 5 is characterized in that, described is that this method further comprised after the pairing user of each element distributed corresponding bandwidth in this formation:
Carrying out traffic shaping according to described concrete business handles.
12. method according to claim 1 is characterized in that, after described user for the element correspondence in the formation distributed bandwidth, this method further comprised:
According to type of service under the information flow, for the type of service corresponding queues that real-time is higher is distributed higher priority.
13. a flow scheduling device is characterized in that, comprising: queue element (QE) configuration module and bandwidth allocation module; Wherein,
The queue element (QE) configuration module, be used for with information flow under the concrete professional user information corresponding of type of service, be configured in the concrete professional corresponding queues as queue element (QE), will dispose user profile and with concrete professional corresponding queues information output;
Bandwidth allocation module is used to receive the described queuing message from the queue element (QE) configuration module, according to the concrete business of formation correspondence and the user profile in the formation, for the user of the element correspondence in the formation distributes bandwidth, bandwidth allocation information is exported; Described for the user distributes bandwidth, the number of times of the chance by the transmission data that provide for the user of the element correspondence in the formation in the unit interval embodies.
14. device according to claim 13 is characterized in that, described bandwidth allocation module comprises: the receiver module and first distribution module; Wherein,
Receiver module is used to receive the described queuing message from the queue element (QE) configuration module, sends described queuing message to first distribution module;
First distribution module, be used to receive described queuing message, according to the bandwidth parameter of the concrete business corresponding,, user profile is exported as bandwidth allocation information by this bandwidth respective rate for the pairing user of each element in this formation distributes corresponding bandwidth with formation;
Described user profile is user ID.
15. device according to claim 14 is characterized in that, described first distribution module comprises:
Formation bandwidth allocation module and user bandwidth distribution module; Wherein,
Described formation bandwidth allocation module, be used for product according to element number in the bandwidth parameter of the concrete business corresponding and the formation with the formation user, be this queue assignment bandwidth, send the information of user ID to described user bandwidth distribution module by this bandwidth respective rate;
Described user bandwidth distribution module, be used to receive described information from the formation bandwidth allocation module, to dispatch out team with described information user information corresponding, with the allocated bandwidth of distributing to this formation pairing user of each element in this formation, user profile is exported as bandwidth allocation information by the bandwidth respective rate that the user gets.
16. device according to claim 14 is characterized in that, described bandwidth allocation module further comprises:
Second distribution module is used to receive the described user ID that first distribution module is exported, and judges the data whether this user in the formation exists needs to send, if, keep the bandwidth of distributing to this user, by this bandwidth respective rate user totem information is exported; Otherwise, discharge the bandwidth of distributing to this user.
17. device according to claim 16 is characterized in that, described bandwidth allocation module further comprises:
The 3rd distribution module, be used to receive described user ID from described first distribution module or described second distribution module, same user's bandwidth addition will be distributed in the individual queue, and the bandwidth sum that obtains is limited in the pre-set threshold, by the corresponding speed of the total bandwidth of distributing to this user this user ID is exported afterwards.
18. device according to claim 13 is characterized in that, described device further comprises:
The queue scheduling module, be used to receive described bandwidth allocation information from bandwidth allocation module, according to type of service under the information flow, for the type of service corresponding queues that real-time is higher is distributed higher priority, and according to described priority, the scheduling result of the formation that priority is higher is preferentially exported.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200710003485XA CN101009655B (en) | 2007-02-05 | 2007-02-05 | Traffic scheduling method and device |
| PCT/CN2007/071409 WO2008095397A1 (en) | 2007-02-05 | 2007-12-29 | Traffic scheduling method and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200710003485XA CN101009655B (en) | 2007-02-05 | 2007-02-05 | Traffic scheduling method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101009655A CN101009655A (en) | 2007-08-01 |
| CN101009655B true CN101009655B (en) | 2011-04-20 |
Family
ID=38697796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200710003485XA Active CN101009655B (en) | 2007-02-05 | 2007-02-05 | Traffic scheduling method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN101009655B (en) |
| WO (1) | WO2008095397A1 (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101009655B (en) * | 2007-02-05 | 2011-04-20 | 华为技术有限公司 | Traffic scheduling method and device |
| CN101772083A (en) * | 2008-12-30 | 2010-07-07 | 华为技术有限公司 | Method, device and system for allocating bandwidth |
| CN101499973B (en) * | 2009-03-11 | 2012-05-23 | 中兴通讯股份有限公司 | Method for implementing full line high speed scheduling service flow by switch |
| CN102137464B (en) * | 2010-01-25 | 2014-09-10 | 中兴通讯股份有限公司 | Base station system and transmitting method of Abis port data thereof |
| CN102300261B (en) * | 2010-06-25 | 2014-02-12 | 普天信息技术研究院有限公司 | Method for carrying out capacity assignment on HS-DSCH (high-speed downlink shared channel) |
| CN103024456B (en) | 2011-09-27 | 2016-02-24 | 腾讯科技（深圳）有限公司 | A kind of Online Video player method and video playback server |
| CN103379038B (en) * | 2012-04-12 | 2018-08-03 | 南京中兴新软件有限责任公司 | A kind of device and method of flow scheduling |
| US8804523B2 (en) | 2012-06-21 | 2014-08-12 | Microsoft Corporation | Ensuring predictable and quantifiable networking performance |
| CN102857440A (en) * | 2012-08-17 | 2013-01-02 | 杭州华三通信技术有限公司 | Data processing method and switchboard |
| CN103023812B (en) * | 2012-11-23 | 2018-07-31 | 上海寰创通信科技股份有限公司 | A kind of multi-user's balanced bandwidth configuration method |
| CN103037415B (en) * | 2012-12-12 | 2016-07-06 | 深信服网络科技（深圳）有限公司 | Network analysis method and system |
| US20140226571A1 (en) * | 2013-02-13 | 2014-08-14 | Qualcomm Incorporated | Apparatus and method for enhanced application coexistence on an access terminal in a wireless communication system |
| CN105159781B (en) * | 2015-08-25 | 2018-11-27 | 广东欧珀移动通信有限公司 | Adjust the method, apparatus and intelligent terminal of intelligent terminal application network speed |
| CN105591970A (en) * | 2015-08-31 | 2016-05-18 | 杭州华三通信技术有限公司 | Traffic control method and device |
| CN107404454B (en) * | 2016-05-18 | 2021-08-03 | 中国移动通信集团广东有限公司 | Call quality adjusting method and device |
| CN108243119B (en) * | 2016-12-26 | 2023-07-11 | 中兴通讯股份有限公司 | Scheduling method and device for improving RB resource utilization rate |
| CN110868357A (en) * | 2018-08-27 | 2020-03-06 | 中兴通讯股份有限公司 | Network flow control method, VTEP device and storage medium |
| CN109246023A (en) * | 2018-11-16 | 2019-01-18 | 锐捷网络股份有限公司 | Flow control methods, the network equipment and storage medium |
| CN113906720B (en) * | 2019-06-12 | 2024-05-10 | 华为技术有限公司 | Traffic scheduling method, traffic scheduling device and storage medium |
| CN111565323B (en) * | 2020-03-23 | 2022-11-08 | 视联动力信息技术股份有限公司 | Flow control method and device, electronic equipment and storage medium |
| CN111491015B (en) * | 2020-03-31 | 2022-11-11 | 北京金山云网络技术有限公司 | Preheating task processing method and system, proxy server and service center |
| CN111970544B (en) * | 2020-08-31 | 2022-10-18 | 咪咕视讯科技有限公司 | Downlink flow scheduling policy adjusting method, server and readable storage medium |
| CN114268590B (en) * | 2021-11-24 | 2024-04-30 | 成都安恒信息技术有限公司 | System and method for guaranteeing bandwidth based on VPP |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1422475A (en) * | 2000-02-08 | 2003-06-04 | 天然网络技术有限公司 | Multi-level scheduling method for multiplexing packets in a communications network |
| CN1490993A (en) * | 2003-09-15 | 2004-04-21 | 北京港湾网络有限公司 | Multiservice system realizing method for broadband network cut-in apparatus user |
| CN1524395A (en) * | 2001-05-26 | 2004-08-25 | ���ſ������˾ | Method and apparatus for communications bandwidth allocation |
| US6917590B1 (en) * | 1998-11-13 | 2005-07-12 | Sprint Communications Company L.P. | Method and system for connection admission control |
| CN1842019A (en) * | 2005-03-28 | 2006-10-04 | 华为技术有限公司 | Dynamic control method for service bandwidth |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1501592A (en) * | 2002-11-19 | 2004-06-02 | 电子科技大学 | A novel multiple access method for communication technology |
| ES2229917B1 (en) * | 2003-07-15 | 2006-07-01 | Diseño De Sistemas En Silicio, S.A. | PROCEDURE OF DYNAMIC MANAGEMENT OF RESOURCES OF TELECOMMUNICATIONS SYSTEMS IN FUNCTION OF SERVICE QUALITY AND TYPE OF SERVICE. |
| US7733780B2 (en) * | 2005-12-07 | 2010-06-08 | Electronics And Telecommunications Research Institute | Method for managing service bandwidth by customer port and EPON system using the same |
| CN101009655B (en) * | 2007-02-05 | 2011-04-20 | 华为技术有限公司 | Traffic scheduling method and device |
-
2007
- 2007-02-05 CN CN200710003485XA patent/CN101009655B/en active Active
- 2007-12-29 WO PCT/CN2007/071409 patent/WO2008095397A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6917590B1 (en) * | 1998-11-13 | 2005-07-12 | Sprint Communications Company L.P. | Method and system for connection admission control |
| CN1422475A (en) * | 2000-02-08 | 2003-06-04 | 天然网络技术有限公司 | Multi-level scheduling method for multiplexing packets in a communications network |
| CN1524395A (en) * | 2001-05-26 | 2004-08-25 | ���ſ������˾ | Method and apparatus for communications bandwidth allocation |
| CN1490993A (en) * | 2003-09-15 | 2004-04-21 | 北京港湾网络有限公司 | Multiservice system realizing method for broadband network cut-in apparatus user |
| CN1842019A (en) * | 2005-03-28 | 2006-10-04 | 华为技术有限公司 | Dynamic control method for service bandwidth |
Non-Patent Citations (1)
| Title |
|---|
| 全文. |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2008095397A1 (en) | 2008-08-14 |
| CN101009655A (en) | 2007-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101009655B (en) | Traffic scheduling method and device | |
| CN102130823B (en) | Method and network apparatus for communicating data | |
| CN1781287B (en) | Methods and devices for flexible bandwidth allocation | |
| CN101828361B (en) | Method and arrangement for scheduling data packets in a communication network system | |
| CN103384159B (en) | QOS on bonded channels of a shared access cable network | |
| CN101352007B (en) | Multi-priority multi-color markers for traffic metering | |
| CN107196877A (en) | The method and its network equipment of control of network flow quantity | |
| CN1985482B (en) | Network devices and traffic shaping methods | |
| JP2014187421A (en) | Communication device and packet scheduling method | |
| RU2643666C2 (en) | Method and device to control virtual output queue authorization and also computer storage media | |
| CN103718522A (en) | Scheduling under congestion with traffic load-based scaling | |
| CN101102275B (en) | Method for multi-level dispatching on Ethernet switching chip | |
| CN101127711B (en) | System and process for QoS-based packet scheduling | |
| CN101796773A (en) | Application data flow management in an IP network | |
| US11929911B2 (en) | Shaping outgoing traffic of network packets in a network management system | |
| CN102868638A (en) | Method and system for dynamically regulating bandwidth | |
| CN103354527B (en) | The method of improving service quality, Apparatus and system | |
| CN1625157B (en) | Policing device | |
| CN100592707C (en) | Token bucket parameters computation for guaranteed services in a data network | |
| CN100466593C (en) | Method of implementing integrated queue scheduling for supporting multi service | |
| CN107846341A (en) | Method, relevant apparatus and the system of schedules message | |
| CN107896200A (en) | Message scheduling method compatible with virtual link and packet switching mechanism | |
| US8467401B1 (en) | Scheduling variable length packets | |
| CN1798106B (en) | Method and apparatus for scheduling transmission-link capacity between packet-switched traffic flows | |
| CN100399745C (en) | System and method for scheduling data traffic flows for a communication device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |