CN110213178A - Flow managing method, integrated chip and device - Google Patents
Flow managing method, integrated chip and device Download PDFInfo
- Publication number
- CN110213178A CN110213178A CN201810548610.3A CN201810548610A CN110213178A CN 110213178 A CN110213178 A CN 110213178A CN 201810548610 A CN201810548610 A CN 201810548610A CN 110213178 A CN110213178 A CN 110213178A
- Authority
- CN
- China
- Prior art keywords
- scheduling
- strategy
- flow
- scheduling strategy
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- H04L47/52—Queue scheduling by attributing bandwidth to queues
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/76—Admission control; Resource allocation using dynamic resource allocation, e.g. in-call renegotiation requested by the user or requested by the network in response to changing network conditions
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides a kind of flow managing method, integrated chip and devices, and wherein method realizes to include: the data for receiving at least two flow initiators and sending；Obtain the business demand information of at least two flow initiators, the business demand information refers to the demand information of business corresponding to data that flow initiator to be sent；Scheduling strategy is determined according to the business demand information.Scheduling strategy is determined by the business demand information of flow initiator, rather than uses fixed scheduling strategy, further can promote dispatching efficiency to meet the needs of more various flow initiator for flow initiator bandwidth allocation for greater flexibility.
Description
Technical field
The present embodiments relate to electronic technology field, in particular to a kind of flow managing method, integrated chip and dress
It sets.
Background technique
Traffic management is network-based flow status and traffic management and control strategy, carries out identification classification to data stream, and real
Apply flow control, optimization and the relevant technologies ensured to crucial application.
By taking field programmable gate array (field programmable gate array, FPGA) Cloud Server as an example,
FPGA includes two regions in static zones and dynamic area connected with interface bus, and wherein static zones are the hardware of FPGA system framework
Part, dynamic area are the regions that can be designed.Flow initiator is registered to after dynamic area data being sent to dynamic area, then by quiet
The scheduler module in state area executes traffic management.
The flow initiator for being registered to dynamic area can have very much, such as multiple applications are registered to dynamic area.For scheduling
Flow initiator is its user for module, and the traffic management that scheduler module executes is usually the traffic management of multi-user.At present
The mode of traffic management is balance dispatching, it may be assumed that total bandwidth mean allocation between a plurality of users.
Practice have shown that the implementation of balance dispatching is not able to satisfy the demand of more flow initiator, many users is caused to go out
Existing bandwidth bottleneck, therefore dispatching efficiency is lower.
Summary of the invention
The embodiment of the present invention provides a kind of flow managing method, integrated chip and device, for neatly initiating for flow
Square bandwidth allocation further promotes dispatching efficiency to meet the needs of more various flow initiator.
On the one hand the embodiment of the invention provides a kind of flow managing methods, comprising:
Receive the data of at least two flow initiators transmission；
The business demand information of at least two flow initiators is obtained, the business demand information refers to flow initiator
The demand information of business corresponding to the data to be sent；Scheduling strategy is determined according to the business demand information；
Scheduling is executed using the data that the scheduling strategy sends the flow initiator.
Flow initiator can be the application for arbitrarily having flow to send demand or user.Business demand information refers to flow
The information of the demand of business corresponding to initiator's data to be sent, such as: the demands such as time delay, bandwidth.
In a possible implementation, in the number sent using the scheduling strategy to the flow initiator
Before execution scheduling, which comprises
When the data that the flow initiator sends are scheduled using initial schedule strategy, the initial schedule is waited
Tactful primary scheduling, which executes, to be terminated；The initial schedule strategy used scheduling strategy before being the scheduling strategy.
In a possible implementation, the initial schedule strategy is waited once to dispatch execution end described
Before, the method also includes:
The switching request message from flow initiator is received, the scheduling switching request message request uses the scheduling
Strategy execution scheduling；
Alternatively, determining that using the scheduling strategy, dispatching efficiency lifting capacity is super compared to the initial schedule strategy is used
Cross threshold value.
In a possible implementation, the business demand information for obtaining the flow initiator, according to described in
Business demand information determines that scheduling strategy includes:
It obtains in bandwidth demand, delay requirement and the precedence information in the business demand information of the flow initiator
At least one of；According to the business demand information from scheduling strategy to be selected selection scheduling strategy.
In a possible implementation, the scheduling strategy to be selected include: bandwidth it is excellent enjoy mode, bandwidth enjoys mode
And bandwidth adjustable mode；
The excellent mode of enjoying of the bandwidth is the scheduling strategy successively dispatched from high to low by service priority；
The bandwidth enjoys the scheduling strategy that mode is balance dispatching；
The bandwidth adjustable mode is the scheduling strategy dispatched from high to low according to the weight of flow initiator, in each round
After scheduling, weighted value of the not scheduled flow initiator relative to scheduled flow initiator is improved.
In a possible implementation, the data that the flow initiator is sent using the scheduling strategy
Executing scheduling includes:
The data that the flow initiator sends are sent to the task queue of the flow initiator, by the task queue
It is assigned in task queue grouping corresponding with the scheduling strategy, the scheduling strategy to be used is waited to execute the scheduling mould of scheduling
Block executes scheduling.
In a possible implementation, the data that the flow initiator is sent using the scheduling strategy
Executing scheduling includes:
The data that the flow initiator sends are stored in the task queue of the flow initiator, are closed except described in use
Scheduling strategy executes other scheduler modules except the scheduler module of scheduling, and the scheduling strategy to be used is waited to execute the tune of scheduling
Degree module executes scheduling.
The embodiment of the invention also provides a kind of integrated chips for two aspects, comprising:
Scheduler module, dispatching control module and receiving module；
The receiving module, for receiving the data of flow initiator transmission；
The dispatching control module is needed for obtaining the business demand information of the flow initiator according to the business
Information is asked to determine scheduling strategy；
The scheduler module, the data for using the scheduling strategy to send the flow initiator execute scheduling.
In a possible implementation, the scheduler module is also used in the use scheduling strategy to the stream
Before measuring the data execution scheduling that initiator sends, carried out in the data that the flow initiator sends using initial schedule strategy
When scheduling, waiting the initial schedule strategy once to dispatch execution terminates, and is then sent out using the scheduling strategy the flow
It plays the data just sent and executes scheduling；The initial schedule strategy used scheduling strategy before being the scheduling strategy.
In a possible implementation, the scheduler module is also used to wait in the scheduler module described initial
Scheduling strategy is once dispatched before execution terminates, and receives the switching request message from flow initiator, the scheduling, which switches, asks
Message request is asked to execute scheduling using the scheduling strategy；
Alternatively, the scheduler module, it is also used to before waiting the initial schedule strategy once dispatch and execute and terminate, really
Surely using the scheduling strategy compared to the initial schedule strategy is used, dispatching efficiency lifting capacity is more than threshold value.
In a possible implementation, the dispatching control module, for obtaining the business of the flow initiator
Bandwidth demand, delay requirement in demand information and at least one in precedence information；According to the business demand information
The selection scheduling strategy from scheduling strategy to be selected.
In a possible implementation, the scheduling strategy to be selected include: bandwidth it is excellent enjoy mode, bandwidth enjoys mode
And bandwidth adjustable mode；
The excellent mode of enjoying of the bandwidth is the scheduling strategy successively dispatched from high to low by service priority；
The bandwidth enjoys the scheduling strategy that mode is balance dispatching；
The bandwidth adjustable mode is the scheduling strategy dispatched from high to low according to the weight of flow initiator, in each round
After scheduling, weighted value of the not scheduled flow initiator relative to scheduled flow initiator is improved.
In a possible implementation, the scheduler module, the data hair for sending the flow initiator
Toward the task queue of the flow initiator, the task queue is assigned to task queue corresponding with the scheduling strategy point
In group, the scheduler module for waiting the scheduling strategy to be used to execute scheduling executes scheduling.
In a possible implementation, the scheduler module, the data for sending the flow initiator are deposited
Enter the task queue of the flow initiator, closes other in addition to using the scheduling strategy to execute the scheduler module of scheduling
Scheduler module, the scheduler module for waiting the scheduling strategy to be used to execute scheduling execute scheduling.
The embodiment of the invention provides a kind of flow management devices, including input equipment, output equipment, memory for three aspects
And processor, the memory are suitable for being loaded by the processor for storing program instruction, described program instruction；The input
Equipment, for receiving the data of flow initiator transmission；
Four aspects are stored with a plurality of program in the storage medium and refer to the embodiment of the invention also provides a kind of storage medium
It enables, described program instruction is suitable for being loaded by processor and being executed the traffic management side any one of provided in an embodiment of the present invention
Method.
For five aspects the embodiment of the invention also provides a kind of computer program product, computer program product includes a plurality of journey
Sequence instruction, described program instruction are suitable for being loaded by processor and being executed the traffic management any one of provided in an embodiment of the present invention
Method.
The embodiment of the present invention determines scheduling strategy by the business demand information of flow initiator, rather than uses solid
Fixed scheduling strategy can be for greater flexibility flow initiator bandwidth allocation, thus meet the needs of more various flow initiator, into
One step promotes dispatching efficiency.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly or in background technique below will be implemented the present invention
Attached drawing needed in example or background technique is illustrated.
Fig. 1 is the application system structural schematic diagram of the embodiment of the present invention；
Fig. 2 is the application system structural schematic diagram of the embodiment of the present invention；
Fig. 3 is present invention method flow diagram；
Fig. 4 is Subscriber Queue of embodiment of the present invention schematic diagram；
Fig. 5 is application system of embodiment of the present invention structural schematic diagram；
Fig. 6 is application system of embodiment of the present invention structural schematic diagram；
Fig. 7 is application system of embodiment of the present invention structural schematic diagram；
Fig. 8 is scheduling strategy of embodiment of the present invention scheduling result schematic diagram；
Fig. 9 is scheduling strategy of embodiment of the present invention scheduling result schematic diagram；
Figure 10 is present invention method flow diagram；
Figure 11 is present invention method flow diagram；
Figure 12 is integrated chip of embodiment of the present invention structural schematic diagram；
Figure 13 is flow management device of embodiment of the present invention structural schematic diagram.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
The description and claims of this application and term " first " in above-mentioned attached drawing, " second " etc. are for distinguishing
Different objects, are not use to describe a particular order.
As shown in Figure 1, being application system of embodiment of the present invention structural schematic diagram, the static zones in Fig. 1 can be hardware
Part is also possible to virtual hardware part, can also be with functional module existing for software；Due to for dynamic area,
This part is relatively stable therefore is properly termed as static zones.Dynamic area in Fig. 1 usually can be software realization region,
Be also possible to the hardware realization region of customization, due to being related to user's dynamic change, this part is opposite change it is more therefore can be with
Referred to as dynamic area.
Dynamic area and static zones can independently exist, and the transmitting of data and instruction is carried out using bus interface.It can be with
Understand, if dynamic area and static zones can be used function interface and counted with the Implement of Function Module of software
According to the transmitting with instruction.
N number of user's registration is illustrated in Fig. 1 to dynamic area, then N number of proposed with can be used as flow initiator per family
The transmission demand of data transmits data to dynamic area and waits the relevant functional module scheduling of management and running.
Based on structure shown in figure 1 above, static zones can be subjected to further progress division in embodiments of the present invention,
It is as shown in Figure 2: compared to structure shown in Fig. 1, static zones segmented out management and running functional module and multiple scheduling moulds
Block, different scheduler modules are corresponding with different scheduling strategies；There is M kind scheduling strategy as shown in Figure 2；It should be noted that such as
The scheduling strategy of fruit scheduler module is variable, then scheduler module can usually make in this case only comprising one
The function of scheduler module is realized with software；If the scheduling strategy of scheduler module be it is fixed, usually can be used hard
Part realizes the function of scheduler module.The functional module of management and running is mainly used for the working condition of control scheduler module；It adjusts
Degree module is then used to execute scheduling according to the scheduling strategy of oneself；The process that scheduler module executes scheduling is to be using scheduling strategy
The process of user's offer traffic service.
Based on system structure shown in figure 2 above, the embodiment of the invention provides a kind of flow managing methods, such as Fig. 3 institute
Show, comprising:
301: receiving the data that at least two flow initiators send；
Flow initiator can be the application for arbitrarily having flow to send demand or user.Correspond to Fig. 2 can be it is dynamic
State area receives the data sent from user after receiving user's registration；The data that user sends can first be stored in the corresponding use
In the queue at family.As shown in figure 4, be a schematic diagram of user data queue, user 1 is illustrated in Fig. 4 to user 3, one
The queue of totally 3 users；Each grid represents a scheduling unit, usually can be a data packet, alternatively, completing certain
The set for the data packet dispatched needed for a function, the concrete form embodiment of the present invention do not make uniqueness restriction.Shown in Fig. 44
A queue includes 8 grid, that is to say, that can at most store 8 scheduling units；Wherein if there is filling, it may be assumed that non-empty
It is white, then it represents that corresponding scheduling unit has data to be scheduled.
Before flow initiator sends data, flow initiator can be registered；Such as flow initiator is registered to shown in Fig. 2
Dynamic area, flow initiator is to allow traffic management to know with the presence of some flow initiator in dynamic area registration；Tool
The logon mode of body can be logged in reference to user or the register flow paths such as authentication, the specific register flow path embodiment of the present invention
With no restrictions.
302: obtaining the business demand information of at least two above-mentioned flow initiators, above-mentioned business demand information refers to flow
The demand information of business corresponding to initiator's data to be sent；Scheduling strategy is determined according to above-mentioned business demand information；
Based on being introduced above since data are from least two flow initiators, different flow initiators can have not
Same business demand, can also have identical business demand, the embodiment of the present invention does not make uniqueness restriction to this.
Above-mentioned business demand information refers to the demand information of business corresponding to data that flow initiator to be sent, such as:
The demands such as time delay, bandwidth.Since business demand information is from least two flow initiators, it is therefore possible to there are two types of or two
Kind or more business demand information then can be to maximize and meet business demand information it is thus determined that the process of scheduling strategy
Scheduling strategy is determined for principle, is also possible to determine scheduling strategy as principle preferentially to meet the higher business demand of priority.Tool
The scheduling strategy determination process of body, the present embodiment do not make uniqueness restriction.
303: executing scheduling using the data that above-mentioned scheduling strategy sends above-mentioned flow initiator.
Executing the process of scheduling after scheduling strategy determines is to provide the mistake of traffic service using scheduling strategy for user
Journey will provide for several possible illustrations in subsequent embodiment.
The embodiment of the present invention determines scheduling strategy by the business demand information of flow initiator, rather than uses solid
Fixed scheduling strategy can be for greater flexibility flow initiator bandwidth allocation, thus meet the needs of more various flow initiator, into
The utilization rate of one step lifting system bandwidth.
In a possible implementation, the present embodiment additionally provides the implementation of scheduling strategy switching, specifically such as
Under: before the above-mentioned data sent using above-mentioned scheduling strategy to above-mentioned flow initiator execute scheduling, the above method includes:
When the data that above-mentioned flow initiator sends are scheduled using initial schedule strategy, above-mentioned initial schedule is waited
Tactful primary scheduling, which executes, to be terminated；Above-mentioned initial schedule strategy used scheduling strategy before being above-mentioned scheduling strategy.
In the present embodiment, the data that scheduling strategy in the process of implementation can request user are scheduled, more, example
Such as: scheduling strategy is scheduled as unit of data packet when executing, then primary scheduling, which executes, to be terminated then to refer to as some data
Packet bandwidth allocation, alternatively, some data packet is issued；Correspondingly, primary scheduling, which executes, terminates to refer to data packet
Finishing scheduling.Primary scheduling, which executes, to be terminated to can not be all data packet dispatching knots for some flow initiator herein
Beam.
In the present embodiment, the switching implementation of scheduling strategy had not only been provided, but also the control in the handoff procedure provided
It realizes, it is ensured that the smooth operating that can ensure to dispatch in handoff procedure, switching in time, and avoid the occurrence of chaotic feelings
Condition.
In a possible implementation, the present embodiment additionally provides the implementation of two kinds of switching scheduling strategies, tool
Body is as follows: the above-mentioned initial schedule strategy of above-mentioned waiting once dispatch execution terminate before, the above method further include:
The switching request message from flow initiator is received, above-mentioned scheduling switching request message request uses above-mentioned scheduling
Strategy execution scheduling；
Alternatively, determining that using above-mentioned scheduling strategy, dispatching efficiency lifting capacity is super compared to above-mentioned initial schedule strategy is used
Cross threshold value.
Both the above switches in the implementation of scheduling strategy, the former is filed a request by flow initiator and is adapted to flow
Measure the demand of initiator, the latter need not flow initiator file a request and realize intelligent control.
In a possible implementation, several possible situations of business demand information are additionally provided, specific as follows:
The business demand information of the above-mentioned above-mentioned flow initiator of acquisition, determines that scheduling strategy includes: according to above-mentioned business demand information
It obtains in bandwidth demand, delay requirement and the precedence information in the business demand information of above-mentioned flow initiator
At least one of；According to above-mentioned business demand information from scheduling strategy to be selected selection scheduling strategy.
It should be noted that business demand information can be other demands other than three of the above demand, for example, also
It may include service quality (Quality of Service, QoS) demand, more specifically can also include the demand of packet loss
Deng.Therefore the above citing should not be construed as limiting the uniqueness of the embodiment of the present invention.
The above scheduling strategy to be selected corresponding in Fig. 2 is M scheduling strategy, it may be that flow scheduling equipment can be supported
Whole scheduling strategies.
In a possible implementation, additionally provided based on three of the above business demand information the present embodiment wait recruit
The content of strategy is spent, specific as follows: above-mentioned scheduling strategy to be selected includes: that excellent mode, the bandwidth of enjoying of bandwidth enjoys mode and bandwidth
Adjustable mode；
The excellent mode of enjoying of above-mentioned bandwidth is the scheduling strategy successively dispatched from high to low by service priority；
Above-mentioned bandwidth enjoys the scheduling strategy that mode is balance dispatching；
Above-mentioned bandwidth adjustable mode is the scheduling strategy dispatched from high to low according to the weight of flow initiator, in each round
After scheduling, weighted value of the not scheduled flow initiator relative to scheduled flow initiator is improved.
It will provide for the illustration of the specific scheduling process of three of the above scheduling strategy in subsequent embodiment.This implementation
Example is based on the scheduling strategy provided previously for three kinds of business demand information, since the particular content of business demand information can be with
There are other, therefore scheduling strategy can also be expanded accordingly, the citing of three of the above scheduling strategy should not be construed as to this
The uniqueness of inventive embodiments limits.
The present embodiment additionally provides the data that two kinds of optional implementations are sent in dynamic area management flow initiator, phase
The operating mode of organizational scheduling module should be adjusted.It is specific as follows:
One, above-mentioned to include: to the data execution scheduling that above-mentioned flow initiator sends using above-mentioned scheduling strategy
The data that above-mentioned flow initiator sends are sent to the task queue of above-mentioned flow initiator, by above-mentioned task queue
It is assigned in task queue grouping corresponding with above-mentioned scheduling strategy, above-mentioned scheduling strategy to be used is waited to execute the scheduling mould of scheduling
Block executes scheduling.
As shown in figure 5, the scheduling strategy that scheduler module has oneself to fix, scheduler module and scheduling strategy correspond to a team
Column split, then the task queue of user is assigned to corresponding queued packets by the present embodiment；Different scheduler modules can
With concurrent working.Different scheduler modules in the present embodiment can execute scheduling parallel.It include two queued packets in Fig. 5,
Wherein user 1 is to user 3 in the corresponding queued packets of scheduling strategy 1, and user 4 to user 6 is in the corresponding queue of scheduling strategy 2
In grouping.
Two, above-mentioned to include: to the data execution scheduling that above-mentioned flow initiator sends using above-mentioned scheduling strategy
The data that above-mentioned flow initiator sends are stored in the task queue of above-mentioned flow initiator, are closed except using above-mentioned
Scheduling strategy executes other scheduler modules except the scheduler module of scheduling, and above-mentioned scheduling strategy to be used is waited to execute the tune of scheduling
Degree module executes scheduling.
As shown in fig. 6, the scheduling strategy that scheduler module has oneself to fix, scheduler module and scheduling strategy correspond to entire appoint
Be engaged in queue, one the moment only one scheduler module it is in running order, scheduling is controlled by the functional module of management and running
Whether module is in running order.The scheduler module that only scheduling strategy 1 is shown as in Fig. 6 is in running order, other tune
The corresponding scheduler module of degree strategy does not work.
In both the above implementation, the former can be dispatched with parallel processing, the latter do not have the competition between scheduler module because
This is easier to control the distribution of overall bandwidth.
Following embodiment will be for including static zones and dynamic area in FPGA, and application scenarios include three kinds and are respectively as follows: band
Width is excellent to enjoy mode, and bandwidth enjoys mode and bandwidth adjustable mode, for be illustrated.Compared to using bandwidth average mark
With mode, i.e., for the mode of multi-user equalizing scheduling, and the embodiment of the present invention can be according to the demand of concrete application from three kinds
Selected in scheduling method it is a kind of execute scheduling, these three scheduling methods are respectively: bandwidth is excellent to enjoy mode, i.e., with fixed priority
Mode executes scheduling；Bandwidth enjoys mode, i.e. multi-user equalizing is dispatched；The weighting scheduling of bandwidth adjustable mode, i.e. multi-user.Upper layer
Software application can configure one such scheduling method according to actual needs and execute scheduling, realize dispatching control module
Function, flexibility is high, is able to satisfy a variety of different types of service.
In addition, the demand of user may change in FPGA operational process, therefore the dynamic of mode can be scheduled
State switching.Another scheduling method is switched to from current one of scheduling method；It can not needed in scheduling process
It interrupts, data packet will not lose, and stability is high, and switching scheduling method zero loses.
Based on introducing above, as shown in fig. 7, the present embodiment includes four parts in static zones, except the module of management and running
In addition, also comprising the module of the three kinds of scheduling methods corresponded to, be respectively: bandwidth is excellent to enjoy mode, and bandwidth enjoys mode and band
The module of wide adjustable mode；That is: the module of scheduling is weighted, with the module of Fixed-priority Scheduling Strategy, with multi-user to be mostly used per family
Weigh the module dispatched；Wherein scheduling can also be performed other than which kind of currently used scheduling method of determination in the module of management and running
The control function of pattern switching.It does not need to interrupt current business in scheduling method handoff procedure, also the not additional time opens
Pin.
Three of the above scheduling method is described below respectively:
One, the module application of multi-user equalizing scheduling enjoys mode in bandwidth, i.e., bandwidth needed for each user is essentially identical
Occasion.
As shown in figure 8, the signal of mode is enjoyed for bandwidth, under the scene for applying the bandwidth needed for each user essentially identical,
It is dispatched using multi-user's balanced bandwidth, specific as follows:
Bandwidth is enjoyed under mode, and scheduler sequentially inquires whether each Subscriber Queue has data by way of poll
Etc. to be sent；If current queries are sky to Subscriber Queue, next Subscriber Queue is jumped to；If each Subscriber Queue has
Data latency is sent, dispatching sequence and Subscriber Queue sequence consensus.If some Subscriber Queue are sky, other Subscriber Queue meetings
Obtain bigger bandwidth.In extreme circumstances, if other queues are all sky, single queue can use whole link bands
It is wide.Bandwidth is enjoyed under mode, can be to avoid Subscriber Queue.
3 Subscriber Queue are illustrated in fig. 8, and the result after scheduling illustrates the sequence sent, and wherein the left side is to send
Initial position, which sends at first.
Two, the module application of Fixed-priority Scheduling Strategy enjoys mode in bandwidth is excellent, i.e., some user uses bandwidth and has most
High priority enjoys the good service of low time delay high priority.
Fixed-priority Scheduling Strategy, i.e. bandwidth be excellent to enjoy mode, specific as follows:
Bandwidth is excellent to enjoy under mode, scheduler according in advance be priority policy set by user be scheduled, priority scheduling
The Subscriber Queue of higher top grade dispatches the team of lower priority again after the higher user of priority answers queue no data to be sent
Column.
Application requirement high-bandwidth, low-latency of the Fixed-priority Scheduling Strategy particularly suitable for some user, and other user couple
Business is insensitive to bandwidth and time delay.The user for enjoying highest priority at this time will obtain top quality service.
As shown in figure 9, there are three Subscriber Queue, it is assumed that 1 highest priority of Subscriber Queue has 4 data packets.Subscriber Queue
2 high priorities have 3 data packets.3 lowest priority of Subscriber Queue has 4 data packets.Then according to above-mentioned algorithmic dispatching device
Dispatching sequence are as follows:
1 data packet of Subscriber Queue -> 1 data packet of Subscriber Queue -> 1 data packet of Subscriber Queue -> Subscriber Queue, 1 data packet ->
2 data packets of Subscriber Queue -> 2 data packets of Subscriber Queue -> 2 data packets of Subscriber Queue -> 3 data packets of Subscriber Queue -> Subscriber Queue 3
Data packet -> 3 data packets of Subscriber Queue -> Subscriber Queue, 3 data packet.Result after scheduling illustrates the sequence sent, wherein left
Side is the initial position sent, which sends at first.
Three, multi-user weights the module application dispatched in bandwidth adjustable mode, i.e., each user is inconsistent to bandwidth demand.It answers
User's application for having needs high bandwidth some then under the scene insensitive to bandwidth.
Multi-user, which weights, dispatches i.e. bandwidth adjustable mode, the scene inconsistent to bandwidth demand especially suitable for each user,
Belong to a kind of most flexible scheduling mode, as shown in Figure 10, specific as follows:
1001: bandwidth needed for the type of service applied according to each user generates the initial weight value of each Subscriber Queue；
1002: software application obtains the weighted value of each Subscriber Queue by hardware interface, selects weighted value maximum
Subscriber Queue is scheduled；If the maximum Subscriber Queue of weighted value is greater than 1, according to queue sequence to weighted value maximum
Subscriber Queue be scheduled；
1003: adjustment weighted value, specific adjustment mode are as follows: reducing the weighted value of the Subscriber Queue of selection, that is, reduce
The weighted value for the Subscriber Queue being scheduled in 1002；The weighted value of not scheduled Subscriber Queue can also be increased；
1004: whether all Subscriber Queue data to be sent have all been sent completely, or whether are switched to other tune
Degree mode, if be it is no, return to 1002.
The weighted value that Subscriber Queue can be adjusted in above 1003 specifically may is that handle chooses queue weighted value to subtract always
Weight obtains intermediate weights value, and intermediate weights value is then added the current weighted value of each Subscriber Queue as next round tune again
The weighted value of degree.After above 1003 are repeatedly executed, if all data to be sent are sent, weight will all be
0.Assuming that current, there are three users, respectively correspond user 0, user 1, and user 2.Initial weight value is 1,5,1 respectively, then each wheel is adjusted
The weighted value and intermediate weights value of degree calculate as shown in table 1 below.
Table 1: multi-user weights scheduling instance
The functional module of management and running in the embodiment of the present invention, can execute the switching of 3 kinds of scheduling methods, as shown in table 2.
Table 2: pattern switching list
| Scheduling method before switching | Scheduling method after switching |
| Fixed-priority Scheduling Strategy | Multi-user weights scheduling |
| Fixed-priority Scheduling Strategy | Multi-user equalizing scheduling |
| Multi-user weights scheduling | Fixed-priority Scheduling Strategy |
| Multi-user weights scheduling | Multi-user equalizing scheduling |
| Multi-user equalizing scheduling | Fixed-priority Scheduling Strategy |
| Multi-user equalizing scheduling | Multi-user weights scheduling |
Based on being described above, the mode of switching can be global switching, it may be assumed that an only scheduler module operation, scheduling
The corresponding module work of scheduling method after the functional module control switching of management, other module from service；Alternatively, can be with
It is the scheduling carried out using Subscriber Queue as granularity, it may be assumed that Subscriber Queue is moved on into the corresponding task queue of scheduling method after switching
Grouping.
The functional module of management and running mainly guarantees when there is service switching, stable and seamless from current tune
Pattern switching is spent to new scheduling method.As shown in figure 11, detailed process includes:
1101: based on three kinds of scheduling methods above, under any scheduling method, executing: having detected whether that switching is adjusted
Spend the request of strategy；
1102: if not switching the request of scheduling strategy, continuing to execute 1101；If there is asking for switching scheduling strategy
It asks, into 1103；
1103: whether detection epicycle scheduling has been completed, it may be assumed that successively inquires whether each Subscriber Queue is completed this current wheel
Scheduling；If yes then enter 1104, the scheduling that each Subscriber Queue completes this current wheel is otherwise waited for, subsequently into 1104；
1104: confirming that each Subscriber Queue completes the scheduling of this current wheel, execute and be switched to asking for switching scheduling strategy
Seek specified scheduling strategy.
It, can be by the way of hard handover in 1104, it may be assumed that open scheduling plan specified by the request of switching scheduling strategy
Slightly corresponding scheduler module, closes other scheduler modules, to realize the switching of scheduling strategy.In running order scheduling mould
Block can be scheduled the data of each Subscriber Queue of dynamic area.
It it is only labelled with multi-user in Figure 11 weights and dispatch this branch, other scheduling methods similar are no longer gone to live in the household of one's in-laws on getting married one by one in this
It states.
The embodiment of the invention also provides a kind of integrated chips, as shown in figure 12, comprising:
Scheduler module 1201, dispatching control module 1202 and receiving module 1203；
Above-mentioned receiving module 1203, for receiving the data of at least two flow initiators transmission；
Above-mentioned dispatching control module 1202, for obtaining the business demand information of at least two flow initiators, institute
State the demand information of business corresponding to the data that business demand information refers to that flow initiator to be sent；Believe according to the business demand
It ceases and determines scheduling strategy；
Above-mentioned scheduler module 1201, the data for using above-mentioned scheduling strategy to send above-mentioned flow initiator execute tune
Degree.
In the integrated chip shown in Figure 12, module number shown in receiving module 1203 and scheduler module 1201 should not be managed
Solution is the limitation to the embodiment of the present invention.
In the present embodiment, dispatching control module 1202 is accomplished that the function of management and running, can refer to and hereinbefore close
In the explanation of management and running, details are not described herein.Receiving module 1201 can be located at dynamic area, which can have
There is store function to be used to the data that temporarily storage flow initiator sends.Scheduler module 1201 is to execute the module of scheduling, can
To correspond to some scheduling strategy, opened when dispatching control module 1202 determines the scheduling strategy, at this time the scheduler module
1201 can be the hardware module of FPGA, be also possible to existing functional module in a software form；The scheduler module 1201 can also
To support a variety of scheduling strategies, scheduling strategy determined by dispatching control module 1202, the at this time scheduling are executed a moment
Module 1201 can be the hardware module of FPGA, be also possible to existing functional module in a software form；
In a possible implementation, above-mentioned scheduler module 1201 is also used to state scheduling strategy in use to upper
Before the data execution scheduling for stating flow initiator transmission, initial schedule strategy is used in the data that above-mentioned flow initiator sends
When being scheduled, waiting above-mentioned initial schedule strategy once to dispatch execution terminates, then using above-mentioned scheduling strategy to above-mentioned stream
The data that amount initiator sends execute scheduling；Above-mentioned initial schedule strategy is used before being above-mentioned scheduling strategy to dispatch plan
Slightly.
In a possible implementation, above-mentioned scheduler module 1201 is also used to wait in above-mentioned scheduler module 1201
Above-mentioned initial schedule strategy once dispatch execution terminate before, receive the switching request message from flow initiator, above-mentioned tune
Degree switching request message request executes scheduling using above-mentioned scheduling strategy；
Alternatively, above-mentioned scheduler module 1201, is also used to that above-mentioned initial schedule strategy is being waited once to dispatch execution end
Before, determine that using above-mentioned scheduling strategy, dispatching efficiency lifting capacity is more than threshold value compared to above-mentioned initial schedule strategy is used.
In a possible implementation, above-mentioned dispatching control module 1202, for obtaining above-mentioned flow initiator's
Bandwidth demand, delay requirement in business demand information and at least one in precedence information；According to above-mentioned business demand
Information selection scheduling strategy from scheduling strategy to be selected.
In a possible implementation, above-mentioned scheduling strategy to be selected include: bandwidth it is excellent enjoy mode, bandwidth enjoys mode
And bandwidth adjustable mode；
The excellent mode of enjoying of above-mentioned bandwidth is the scheduling strategy successively dispatched from high to low by service priority；
Above-mentioned bandwidth enjoys the scheduling strategy that mode is balance dispatching；
Above-mentioned bandwidth adjustable mode is the scheduling strategy dispatched from high to low according to the weight of flow initiator, in each round
After scheduling, weighted value of the not scheduled flow initiator relative to scheduled flow initiator is improved.
In a possible implementation, above-mentioned scheduler module 1201, the number for sending above-mentioned flow initiator
According to the task queue for being sent to above-mentioned flow initiator, above-mentioned task queue is assigned to task corresponding with above-mentioned scheduling strategy team
In column split, the scheduler module 1201 for waiting above-mentioned scheduling strategy to be used to execute scheduling executes scheduling.
In a possible implementation, above-mentioned scheduler module 1201, the number for sending above-mentioned flow initiator
According to the task queue for being stored in above-mentioned flow initiator, close except executed using above-mentioned scheduling strategy scheduling scheduler module 1201 it
Other outer scheduler modules 1201, the scheduler module 1201 for waiting above-mentioned scheduling strategy to be used to execute scheduling execute scheduling.
It is a kind of schematic block diagram for flow management device that another embodiment of the application provides referring to Figure 13, Figure 13.Such as figure
Flow management device in the present embodiment shown in 13 may include: one or more processors 1301；One or more input
Equipment 1302, one or more output equipments 1303 and memory 1304.Above-mentioned processor 1301, input equipment 1302, output
Equipment 1303 and memory 1304 are connected by bus 1305.Memory 1302 is for storing computer program, the computer journey
Sequence includes program instruction, and processor 1301 is used to execute the program instruction of the storage of memory 1302.Wherein, processor 1301 is matched
It sets for calling the program instruction to execute the dispatch control method in preceding method embodiment.Input equipment 1302 then can be used for
The data sent from flow initiator are received, the request of flow initiator can also be further received.Output equipment 1303 is then
Can be after processor 1301 execute scheduling controlling, the data of transmitted traffic initiator.It is understood that if flow is initiated
The data just sent only need to execute processing in flow management device, do not need to feed back, then output equipment 1303 is not
Need to send processing result or forwarding data.
Alleged processor 1301 can be central processing unit (Central Processing in the embodiment of the present application
Unit, CPU), which can also be other general processors, digital signal processor (Digital Signal
Processor, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components etc..General processor can be microprocessor or the processor can also
To be any conventional processor etc..
Input equipment 1302 may include radio-frequency antenna, interface hardware, program interface etc., and output equipment 1303 can wrap
Include radio-frequency antenna, interface hardware, program interface etc..Method in the embodiment of the present invention, which may be implemented, in the input equipment 1302 implements
About the function of receiving data in example.
The memory 1304 may include read-only memory and random access memory, and provide instruction to processor 1301
And data.The a part of of memory 1304 can also include nonvolatile RAM.For example, memory 1304 may be used also
To cache the data of flow initiator transmission.
In the specific implementation, processor 1301, input equipment 1302 described in the embodiment of the present application, output equipment 1303
Scheduling controlling function described by any means provided by the embodiments of the present application can be performed；Details are not described herein.
The embodiment of the invention also provides a kind of storage medium, a plurality of program instruction is stored in above-mentioned storage medium, on
Program instruction is stated to be suitable for being loaded by processor and being executed flow managing method any one of provided in an embodiment of the present invention.
The embodiment of the invention also provides a kind of computer program product, computer program product includes that a plurality of program refers to
It enables, above procedure instruction is suitable for being loaded by processor and being executed flow managing method any one of provided in an embodiment of the present invention.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and method and step can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function.
It is apparent to those skilled in the art that for convenience and simplicity of description, the equipment of foregoing description
It with the specific work process of module, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, method and apparatus, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, said units
It divides, is possible logical function partition, there may be another division manner in actual implementation, such as multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling, direct-coupling or communication connection of opinion can be through some interfaces, the INDIRECT COUPLING of device or unit
Or communication connection, it can be electrical property, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.In addition, each functional unit in each embodiment of the application can integrate in one processing unit, it is also possible to each
Unit physically exists alone, and can also be integrated in one unit with two or more units.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.Above-mentioned computer program
Product includes one or more computer instructions.When loading on computers and executing above-mentioned computer program instructions, all or
Partly generate the process or function above-mentioned according to the embodiment of the present invention.Above-mentioned computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.Above-mentioned computer instruction can store in computer readable storage medium
In, or transmitted by above-mentioned computer readable storage medium.Above-mentioned computer instruction can be from a web-site, meter
Calculation machine, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (digital subscriber
Line, DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or number
It is transmitted according to center.Above-mentioned computer readable storage medium can be any usable medium that computer can access either
The data storage devices such as server, the data center integrated comprising one or more usable mediums.Above-mentioned usable medium can be
Magnetic medium, (for example, floppy disk, hard disk, tape), optical medium are (for example, digital versatile disc (digital versatile
Disc, DVD)) or semiconductor medium (such as solid state hard disk (solid state disk, SSD)) etc..
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, the process
Relevant hardware can be instructed to complete by computer program, which can be stored in computer-readable storage medium, should
Program is when being executed, it may include such as the process of above-mentioned each method embodiment.And storage medium above-mentioned includes: read-only memory
(read-only memory, ROM) or random access memory (random access memory, RAM), magnetic or disk
Etc. the medium of various program storage codes.
Claims (14)
1. a kind of integrated chip characterized by comprising
Scheduler module, dispatching control module and receiving module；
The receiving module, for receiving the data of at least two flow initiators transmission；
The dispatching control module, for obtaining the business demand information of at least two flow initiators, the business is needed
The demand information of business corresponding to the data for asking information to refer to that flow initiator to be sent；It determines and adjusts according to the business demand information
Degree strategy；
The scheduler module, the data for using the scheduling strategy to send the flow initiator execute scheduling.
2. integrated chip according to claim 1, which is characterized in that
The scheduler module is also used to executing scheduling to the data that the flow initiator sends using the scheduling strategy
Before, when the data that the flow initiator sends are scheduled using initial schedule strategy, wait the initial schedule strategy
Primary scheduling, which executes, to be terminated, and then executes scheduling using the data that the scheduling strategy sends the flow initiator；It is described
Initial schedule strategy used scheduling strategy before being the scheduling strategy.
3. integrated chip according to claim 2, which is characterized in that
The scheduler module is also used to wait the initial schedule strategy once to dispatch execution end in the scheduler module
Before, the switching request message from flow initiator is received, the scheduling switching request message request uses the scheduling strategy
Execute scheduling；
Alternatively, the scheduler module, it is also used to that the initial schedule strategy is being waited once dispatch before execution terminates, determining makes
With the scheduling strategy compared to the initial schedule strategy is used, dispatching efficiency lifting capacity is more than threshold value.
4. integrated chip according to claim 1, which is characterized in that
The dispatching control module, the bandwidth demand in business demand information, time delay for obtaining the flow initiator need
Ask and precedence information at least one of；According to the business demand information from scheduling strategy to be selected selection scheduling plan
Slightly.
5. integrated chip according to claim 4, which is characterized in that
The scheduling strategy to be selected includes: that excellent mode, the bandwidth of enjoying of bandwidth enjoys mode and bandwidth adjustable mode；
The excellent mode of enjoying of the bandwidth is the scheduling strategy successively dispatched from high to low by service priority；
The bandwidth enjoys the scheduling strategy that mode is balance dispatching；
The bandwidth adjustable mode is the scheduling strategy dispatched from high to low according to the weight of flow initiator, is dispatched in each round
Afterwards, weighted value of the not scheduled flow initiator relative to scheduled flow initiator is improved.
6. according to integrated chip described in claim 2 to 5 any one, which is characterized in that
The scheduler module, the data for sending the flow initiator are sent to the task queue of the flow initiator,
The task queue is assigned in task queue grouping corresponding with the scheduling strategy, the scheduling strategy to be used is waited to hold
The scheduler module of row scheduling executes scheduling；Alternatively,
The scheduler module, the data for sending the flow initiator are stored in the task queue of the flow initiator,
Other scheduler modules in addition to using the scheduling strategy to execute the scheduler module of scheduling are closed, the scheduling plan to be used is waited
The scheduler module for slightly executing scheduling executes scheduling.
7. a kind of flow managing method characterized by comprising
Receive the data of at least two flow initiators transmission；
The business demand information of at least two flow initiators is obtained, the business demand information refers to that flow initiator will send out
The demand information of business corresponding to the data sent；Scheduling strategy is determined according to the business demand information；
Scheduling is executed using the data that the scheduling strategy sends the flow initiator.
8. method according to claim 7, which is characterized in that use the scheduling strategy to the flow initiator described
The data of transmission execute before scheduling, which comprises
When the data that the flow initiator sends are scheduled using initial schedule strategy, the initial schedule strategy is waited
Primary scheduling, which executes, to be terminated；The initial schedule strategy used scheduling strategy before being the scheduling strategy.
9. method according to claim 8, which is characterized in that wait the initial schedule strategy once to dispatch execution described
Before end, the method also includes:
The switching request message from flow initiator is received, the scheduling switching request message request uses the scheduling strategy
Execute scheduling；
Alternatively, determining using the scheduling strategy compared to the initial schedule strategy is used, the dispatching efficiency lifting capacity is set to be more than
Threshold value.
10. method according to claim 7, which is characterized in that the business demand information for obtaining the flow initiator,
Determine that scheduling strategy includes: according to the business demand information
It obtains in bandwidth demand, delay requirement and the precedence information in the business demand information of the flow initiator extremely
One item missing；According to the business demand information from scheduling strategy to be selected selection scheduling strategy.
11. method according to claim 10, which is characterized in that the scheduling strategy to be selected, which includes: that bandwidth is excellent, enjoys mode, band
Width enjoys mode and bandwidth adjustable mode；
The excellent mode of enjoying of the bandwidth is the scheduling strategy successively dispatched from high to low by service priority；
The bandwidth enjoys the scheduling strategy that mode is balance dispatching；
The bandwidth adjustable mode is the scheduling strategy dispatched from high to low according to the weight of flow initiator, is dispatched in each round
Afterwards, weighted value of the not scheduled flow initiator relative to scheduled flow initiator is improved.
12. according to claim 8 to 11 any one the method, which is characterized in that described to use the scheduling strategy to institute
The data for stating flow initiator transmission execute scheduling and include:
The data that the flow initiator sends are sent to the task queue of the flow initiator, the task queue is distributed
Into task queue corresponding with scheduling strategy grouping, the scheduler module for waiting the scheduling strategy to be used to execute scheduling is held
Row scheduling；
Alternatively, the data that the flow initiator sends to be stored in the task queue of the flow initiator, closing, which removes, uses institute
Other scheduler modules except the scheduler module of scheduling strategy execution scheduling are stated, the scheduling strategy to be used is waited to execute scheduling
Scheduler module executes scheduling.
13. a kind of flow management device, which is characterized in that described including input equipment, output equipment, memory and processor
Memory is suitable for being loaded by the processor for storing program instruction, described program instruction；
The input equipment, for receiving the data of flow initiator transmission；
The processor instructs for loading described program and executes the traffic management side as described in any one of claim 1 to 6
Method.
14. a kind of storage medium, which is characterized in that be stored with a plurality of program instruction, described program instruction in the storage medium
Suitable for as processor loads and executes the flow managing method as described in any one of claim 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810548610.3A CN110213178B (en) | 2018-05-31 | 2018-05-31 | Flow management method, integrated chip and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810548610.3A CN110213178B (en) | 2018-05-31 | 2018-05-31 | Flow management method, integrated chip and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110213178A true CN110213178A (en) | 2019-09-06 |
| CN110213178B CN110213178B (en) | 2022-08-12 |
Family
ID=67778866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810548610.3A Active CN110213178B (en) | 2018-05-31 | 2018-05-31 | Flow management method, integrated chip and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110213178B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112583739A (en) * | 2019-09-30 | 2021-03-30 | 华为技术有限公司 | Scheduling method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020073129A1 (en) * | 2000-12-04 | 2002-06-13 | Yu-Chung Wang | Integrated multi-component scheduler for operating systems |
| CN101459699A (en) * | 2008-12-25 | 2009-06-17 | 华为技术有限公司 | Method and apparatus for network address conversion |
| CN101938403A (en) * | 2009-06-30 | 2011-01-05 | 中国电信股份有限公司 | Assurance method of multi-user and multi-service quality of service and service access control point |
| CN102300326A (en) * | 2010-06-28 | 2011-12-28 | 中兴通讯股份有限公司 | Scheduling method of multi-user multi-input multi-output (MIMO) communication system and base station |
| CN103476062A (en) * | 2012-06-06 | 2013-12-25 | 华为技术有限公司 | Data flow scheduling method, equipment and system |
| CN104717158A (en) * | 2015-03-02 | 2015-06-17 | 中国联合网络通信集团有限公司 | Method and device for adjusting bandwidth scheduling strategy |
| CN107196877A (en) * | 2016-03-14 | 2017-09-22 | 华为技术有限公司 | The method and its network equipment of control of network flow quantity |
| CN107483363A (en) * | 2017-08-15 | 2017-12-15 | 无锡职业技术学院 | A kind of Weight Round Robin device and method of layering |
-
2018
- 2018-05-31 CN CN201810548610.3A patent/CN110213178B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020073129A1 (en) * | 2000-12-04 | 2002-06-13 | Yu-Chung Wang | Integrated multi-component scheduler for operating systems |
| CN101459699A (en) * | 2008-12-25 | 2009-06-17 | 华为技术有限公司 | Method and apparatus for network address conversion |
| CN101938403A (en) * | 2009-06-30 | 2011-01-05 | 中国电信股份有限公司 | Assurance method of multi-user and multi-service quality of service and service access control point |
| CN102300326A (en) * | 2010-06-28 | 2011-12-28 | 中兴通讯股份有限公司 | Scheduling method of multi-user multi-input multi-output (MIMO) communication system and base station |
| CN103476062A (en) * | 2012-06-06 | 2013-12-25 | 华为技术有限公司 | Data flow scheduling method, equipment and system |
| CN104717158A (en) * | 2015-03-02 | 2015-06-17 | 中国联合网络通信集团有限公司 | Method and device for adjusting bandwidth scheduling strategy |
| CN107196877A (en) * | 2016-03-14 | 2017-09-22 | 华为技术有限公司 | The method and its network equipment of control of network flow quantity |
| CN107483363A (en) * | 2017-08-15 | 2017-12-15 | 无锡职业技术学院 | A kind of Weight Round Robin device and method of layering |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112583739A (en) * | 2019-09-30 | 2021-03-30 | 华为技术有限公司 | Scheduling method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110213178B (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110662238B (en) | Reinforced learning scheduling method and device for burst request under edge network | |
| US8539498B2 (en) | Interprocess resource-based dynamic scheduling system and method | |
| US8799547B2 (en) | Data packet processing method for a multi core processor | |
| CN110505099A (en) | A kind of service function chain dispositions method based on migration A-C study | |
| US11627636B2 (en) | Wireless communication network communications through session communication proxies | |
| CN108810903A (en) | A kind of configuration of data transmission and data transmission method and device | |
| AU2015354779B2 (en) | Apparatus and method for allocating resources using prioritization of requests and updating of requests | |
| EP3701740B1 (en) | Resource management in cloud radio access networks | |
| US7394808B2 (en) | Method and apparatus for implementing scheduling algorithms in a network element | |
| CN108600299A (en) | Calculating task discharging method and system between distributed multi-user | |
| CN113742111B (en) | Micro-service RPC adaptive scheduling method and related device | |
| CN105791371B (en) | A kind of cloud storage service system and method | |
| KR20210064033A (en) | Apparatus and method using a decentralized game approach for radio and computing resource allocation in co-located edge computing | |
| CN110199262A (en) | For the capacity scaling of working application based on cloud | |
| CN107168794A (en) | The treating method and apparatus of request of data | |
| CN111143036A (en) | Virtual machine resource scheduling method based on reinforcement learning | |
| CN110213178A (en) | Flow managing method, integrated chip and device | |
| Ma et al. | Chronos: Meeting coflow deadlines in data center networks | |
| CN100477630C (en) | Queue dispatching method and apparatus in data network | |
| Ma et al. | Maximizing container-based network isolation in parallel computing clusters | |
| CN116782249A (en) | Edge computing unloading and resource allocation method and system with user dependency relationship | |
| US20230070690A1 (en) | Virtual channel starvation-free arbitration for switches | |
| CN108632162A (en) | A kind of array dispatching method and forwarding unit | |
| CN107332786B (en) | A kind of dispatching method ensureing data flow deadline under service chaining environment | |
| US10853138B2 (en) | Scheduling resource usage |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |