CN113742902B - Multi-parameter performance modeling evaluation method based on network algorithm - Google Patents
Multi-parameter performance modeling evaluation method based on network algorithm Download PDFInfo
- Publication number
- CN113742902B CN113742902B CN202110955293.9A CN202110955293A CN113742902B CN 113742902 B CN113742902 B CN 113742902B CN 202110955293 A CN202110955293 A CN 202110955293A CN 113742902 B CN113742902 B CN 113742902B
- Authority
- CN
- China
- Prior art keywords
- flow
- curve
- arrival
- calculating
- hit
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 title claims description 19
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000009795 derivation Methods 0.000 claims description 7
- 238000009825 accumulation Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 8
- 230000002860 competitive effect Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a multi-parameter performance modeling evaluation method based on network calculation, which is mainly used for analyzing a typical scene of a software defined network and constructing a model for a packet forwarding process of an OpenFlow switch based on network calculation. Introducing a plurality of performance influence parameters, including an arrival flow parameter, a competitive flow parameter, a switch processing rate and a flow table hit rate, and carrying out function deduction based on a least addition algebra operation to respectively calculate the forwarding delay boundaries of the flows of the hit and miss flow tables. The method can evaluate the performance of the OpenFlow switch after being applied to the real network environment by presetting related network state parameters and substituting the related network state parameters into a mode of calculating a relation function, and can observe the influence degree of different parameters on the performance by controlling variables so as to provide guidance for the performance optimization and flow control of the switch.
Description
Technical Field
The invention belongs to the technical field of network performance evaluation, and relates to a multi-parameter forwarding delay performance modeling evaluation method based on network algorithm, which is mainly designed for an OpenFlow switch in a software defined network; and more particularly to flow analysis, network algorithm-based model construction, and multi-parameter derivation methods for typical scenarios in software-defined networks.
Background
The network performance evaluation is an important work for guiding network structure optimization and equipment management, and can verify the correctness, the effectiveness and the reliability of a network optimization strategy. The traditional performance evaluation scheme simulates a real network environment by constructing a simulation platform and obtains a measurement result, but has the problems of high experimental cost, slow progress, poor feasibility and the like, and the simulation experiment cannot deeply analyze the influence of different optimization strategies on specific performance parameters and cannot explain the influence relation among different parameters, so that a scientific network performance modeling evaluation method is particularly important.
The software defined network separates the control plane and the data plane, improves the flexibility of network management and configuration, and also creates a performance bottleneck for the network. Performance evaluation for OpenFlow switches in a software defined network is an important research direction for optimizing software defined networks. The OpenFlow switch carries out packet forwarding according to the flow table, and different flows have competition of forwarding resources in the switch. The new mode of centralized management of multiple switches by a single controller further exacerbates this resource competition and introduces more network performance influencing factors, which makes performance assessment difficult. In view of this problem, the existing modeling evaluation method is mostly based on queuing theory, and uses "X/Y/Z" symbols to represent the distribution of packet inter-arrival times, the distribution of forwarding service times, and the forwarding service provision number. However, the queuing theory model highly depends on specific distribution assumptions, the evaluation result only reflects the average state under the obeying probability distribution, and the uncertainty of packet arrival in the real network and the dynamic characteristics of the network are desalted, so that the application range of the corresponding evaluation model and the reliability of the evaluation result are greatly reduced.
The network algorithm is a network performance analysis tool based on a minimum addition algebra structure, and the arrival characteristics of the flow and the service characteristics of the system are extracted by recording the input and output cumulative functions of the network system in a period of time. Document 1 (Azodolmky S, nejabat R, pazouki M, et al analytical model for Software Defined Networking: A network calculus-based application [ C ]. GLOBECOM, 2013:1397-1402.) has an initial meaning in applying network algorithms to the analysis of the forwarding delays of software-defined networks for the first time. Researchers have failed to deeply analyze the impact of the controller on packet forwarding, simply define it as a linear function, and differentiated services provided by the switch to traffic for different flow table hits have also failed to be embodied in the proposed model. Document 2 (Lin C T, wu C M, huang M, et al Performance Evaluation for SDN Deployment: an Approach Based on Stochastic Network Calculus [ J ]. China Communications,2016, supplement (1): 98-106.) proposes a stochastic network calculus model from which the expression of the arrival flow function in exponential and lognormal distributions is derived. However, researchers have failed to demonstrate how to further analyze packet forwarding delays using this function, with limited practical implications. Document 3 (Koohanestani a K, osgouei a G, saidi H, et al an Analytical Model for Delay Bound of OpenFlow Based SDN using Network Calculus [ J ]. Journal of Network and Computer Applications,2017, 96:31-38.) uses a network algorithm modeling to analyze the impact of switch flow table buffer space on packet forwarding delay in detail. However, there are many delay influencing parameters besides the buffer space of the flow table, and the analysis of the influencing parameters by the model is still imperfect.
The invention establishes a network calculation model by analyzing the packet forwarding action of a typical scene of a software defined network and introducing a plurality of performance influence parameters, wherein the introduced parameters comprise an arrival flow parameter, a competitive flow parameter, a switch processing rate and a flow table hit rate, and further establishes a relation function of each parameter and forwarding delay through calculation and deduction. Compared with the existing method, the method has the advantages that the analysis of the delay influence parameters is more comprehensive, the hit conditions of the flow are finely distinguished, the more accurate performance boundary value can be obtained, and a reliable reference basis is provided for the application and optimization of the OpenFlow switch.
Disclosure of Invention
The invention aims to provide a method for evaluating the performance of an OpenFlow switch and accurately calculating the forwarding delay boundary of the switch according to a plurality of state parameters in a software defined network. The method can evaluate the performance of the equipment before the switch is applied to the actual network, improves the management efficiency, realizes the control of network influence parameters and guides the network optimization.
The technical scheme of the invention is as follows: a multi-parameter performance modeling evaluation method based on network algorithm comprises the main steps of OpenFlow switch packet forwarding scene analysis, network algorithm model construction and multi-parameter deduction based on minimum addition algebra operation, and the method comprises the following steps:
step 1, analyzing a packet forwarding flow in a typical scene, including a packet processing link, a flow table hit condition and an influence of a controller on packet forwarding and an influence of a QoS queue on packet output in an OpenFlow switch, establishing a network algorithm model, and defining parameters of the switch;
step 2, the characteristic attribute of the arriving flow is definitely included in the hit state of the flow table and the output queue, so that the flow arriving at the OpenFlow switch is distinguished; setting a target flow and defining parameters of the flow;
step 3, deducing an arrival curve of a flow arriving at the switch according to the flow hypothesis and the feature distinction, wherein the flow comprises a hit flow table and a miss flow table;
and 4, stripping the competition interference of forwarding resources of different flows in the OpenFlow switch according to the packet forwarding flow in a typical scene, deducing equivalent service curves of the flows of the hit flow table and the flows of the miss flow table in each module of the switch, and calculating the forwarding time delay of the flows by combining the arrival curves.
The specific steps of the step 1 comprise:
step 1.1, analyzing a packet forwarding flow, dividing an OpenFlow switch into a flow table query module, a packet scheduling module and a QoS output queue, and establishing a controller and OpenFlow switch model by using an abstract form of a waiting queue-server;
step 1.2, adding trend lines of the flow into a network calculation model according to the packet forwarding flow so as to represent the processing process of the packet and the resource competition condition of different flows;
step 1.3, defining parameters of the switch, including processing rates of each module of the OpenFlow switch: flow table lookup module processing rate d 1 Packet scheduling module processing rate d 2 Processing rate of output queue iController processing rate d C 。
The specific steps of the step 2 include:
step 2.1, the characteristic attributes used for distinguishing the flows include a flow table hit state and an output queue, wherein the flow table hit state determines whether the packet needs to be processed by the controller, and the output queue determines the QoS service obtained by the packet. According to the flow distinguishing, the flow of the output queue i is selected as the target flow without losing generality, and the parts of the hit and miss flow tables are respectively analyzed, so that the other output queues except the i are j;
step 2.2, defining parameters of the streams, including arrival rate and burst amount of each stream of the data plane: arrival rate ρ of traffic f Burst quantity sigma of flow f f The control plane contends for the arrival rate and burst size of the flow: arrival rate ρ of competing streams O Burst quantity sigma of competing stream O 。
The specific steps of the step 3 include:
and 3.1, calculating an arrival curve alpha (t) of each flow according to an input accumulation function A (t) of each flow arriving at the OpenFlow switch. Where t represents a time span, a (t) represents an accumulated amount of variation of the arrival traffic with time, and metering is performed using the number of packets that arrive. According to the requirement of formula (1) [0, t]Any point in time s within the interval should satisfy this equation, thereby yielding an arrival curve α (t) for the corresponding stream. Arrival curve alpha of flow f f (t) can be simplified as represented by formula (2):
A(t)-A(s)≤α(t-s),0≤s≤t (1)
α f (t)=σ f +ρ f t,t≥0 (2)
step 3.2, summing the arrival curves of the flows of the calculation hit and miss flow tables, respectively, according to the arrival curve composition rule of (3), wherein α totalf Refers to the arrival curve of the composite part:
α f ~(σ f ,ρ f )→α totalf ~(∑σ f ,∑ρ f ) (3)
the specific steps of the step 4 include:
step 4.1, accumulating the function A according to the output of each module * (t) calculating a service curve beta (t). Wherein A is * (t) represents an accumulated amount of output traffic over time, and is measured using the number of packets output. According to equation (4), calculate the service of the corresponding moduleCurve beta (t), comprising a flow table lookup module service curve beta 1 Packet scheduling module service curve beta 2 Output queue i service curveController service curve beta C . The service curve can be represented simply as equation (5), where r represents the maximum output rate of the corresponding module and b represents the maximum time interval for packet waiting:
β(t)=r(t-b) + ,t≥0 (5)
wherein if t > b then (t-b) + Otherwise (t-b) + =0;
Step 4.2, stripping the resource competition influence of the flow of the non-output queue i and the flow of the missed flow table at the flow table query module according to the FCFS equivalent service curve deduction method of the formula (6), and calculating the equivalent service curve of the flow of the hit flow table at the module
β eq,1 (t,s)={β(t)-α 2 (t-s)} + ,0≤s<t (6)
Step 4.3, calculating the arrival curve alpha of the flow sent back by the controller at the packet scheduling module according to the characteristic limit rule of the output flow and in combination with the step (8) R :
Step 4.4, calculating the arrival curve of the hit stream of the non-output queue i at the packet scheduling module according to equation (9)
Step 4.5, stripping the resource competition influence of the hit flow of the flow sent back by the controller and the non-output queue i at the packet scheduling module according to the FCFS equivalent service curve deduction method of the formula (6), and calculating the equivalent service curve of the flow of the hit flow table at the module
Step 4.6, bandwidth allocated to each flow of the hit and miss flow tables according to the QoS output queue Calculating equivalent service curve of hit flow in the module +.>
Step 4.7, converting the service curves of the three modules into the equivalent service curves of the whole OpenFlow switch system by least convolution operation based on the deduction results of the formulas (7), (10) and (11)
Step 4.8, calculating a hit stream arrival curveAnd equivalent service curve->The maximum horizontal distance between them, i.e. the Delay boundary value Delay of the switch for the flow hitting the flow table H :
The delay boundary values for the flows missing the flow table are derived as follows:
step 4.9, stripping the resource competition influence of the flow of the output queue j and the flow of the hit flow table at the flow table query module according to the FCFS equivalent service curve derivation method of the formula (6), and calculating the equivalent service curve of the flow of the miss flow table at the module
Step 4.10, stripping the resource competition influence of the competition flow of the control plane at the controller, and calculating the equivalent service curve of the flow of the missed flow table at the controller
wherein ,equivalent service curves at the flow table lookup module for the portion of the missed flow table for the other output queues j, which can be calculated by equation (16); />For the characteristic parameters of the burst quantity of the arrival curve of the partial stream at the arrival controller, the calculation can be obtained by the formula (17):
step 4.11, stripping the resource contention influence of the flow of the hit flow table and the flow of the output queue j sent back by the controller at the packet scheduling module, and calculating the service curve of the flow of the miss flow table at the module
wherein ,equivalent service curves at the controller for the portion of the miss stream table for output queue j are available as in equation (15):
step 4.12, calculating the equivalent service curve of the missed flow in the module according to the bandwidth allocation of the QoS output queue
Step 4.13, calculating the equivalent service curve of the flow of the missed flow table across the entire OpenFlow switch system based on the derivation of formulas (14), (15), (18), (20)
Step 4.14, calculating the missed stream arrival curve in the same way as in equation (13)And equivalent service curve->And (5) obtaining the maximum horizontal distance between the two streams, and obtaining the time delay boundary of the stream passing through the switch by the missing stream table.
The invention has the main beneficial effects that: the packet forwarding delay boundary of the OpenFlow switch can be calculated by constructing a network algorithm model by combining flow parameters and switch parameters in the network. The flows of the hit and miss flow table are calculated differently, and the dimension of performance evaluation is enriched. The invention can evaluate the performance before the switch is applied to the real network environment, is helpful for judging whether the switch deployment strategy is reasonable, objectively reflects the influence of a plurality of parameters on the time delay performance, and provides guidance for the performance optimization and flow control of the OpenFlow switch.
Drawings
Fig. 1 is a "waiting queue-server" abstract example of network operations.
Fig. 2 is an OpenFlow switch model based on network calculus.
Fig. 3A and 3B are effects of arrival rate and burst size of streams hitting the stream table on latency boundaries, wherein: FIG. 3A is a diagram showing the latency boundary impact of a stream hitting a stream table; fig. 3B is a delay bound impact of a flow of the missed flow table.
Fig. 4A and 4B are effects of arrival rate and burst size of streams of a missed stream table on delay boundaries, wherein: FIG. 4A is a diagram showing the latency boundary impact of a stream hitting a stream table; fig. 4B is a delay bound impact of a flow of the missed flow table.
Fig. 5A and 5B are effects of arrival rate and burst size of streams at a control plane on delay boundaries, wherein: FIG. 5A is a flow latency boundary impact scenario for a hit flow table; fig. 5B is a delay bound impact of a flow of the missed flow table.
Detailed Description
The invention provides a multi-parameter performance modeling evaluation method based on network algorithm. The method establishes an OpenFlow switch model by utilizing a network algorithm principle, clarifies resource competition relation of different flows, clarifies a target flow and a plurality of parameters affecting the packet forwarding performance of the switch, further derives an arrival curve and an equivalent service curve of the target flow through least algebraic operation, and obtains a delay boundary of the flow passing through the whole switch system. The key steps involved in the process of the present invention are described in detail below.
1. Abstract modeling
As shown in fig. 1, the network algorithm may abstract the study as a "wait queue-server" combination. Wherein, the waiting queue represents the buffer space of the system, records the arrival condition of the packet and generates an input cumulative function A (t); the "server" represents the processing function of the system, records the processing condition of the packet, and generates an output cumulative function A * (t)。
Because the OpenFlow switch provides different forwarding services for the traffic hitting and missing the flow table, the invention selects to calculate the time delay boundaries of the two flows respectively for enriching the performance evaluation dimension of the switch. Therefore, the OpenFlow switch cannot be simply abstracted into a set of "waiting queue-servers". In a typical scenario, the forwarding process inside the switch is analyzed in detail, each functional module is respectively abstracted into a waiting queue-server, and resource competition relations of different flows are clarified, so that each parameter affecting the performance is clarified, and the target flow is established. The specific implementation steps are as follows:
1.1 exemplary scene analysis
In a software-defined network, the forwarding paths of packets are uniformly calculated by a controller and issued to the involved OpenFlow switches. When the packet arrives at the switch, the flow table is first queried, and the flow table entry is matched according to the message information of the packet header. Normally, the matching can be successfully performed, and the forwarding operation is obtained. And then, executing a forwarding operation, sending the packet to a corresponding output queue, and finally executing an output operation. And the unsuccessfully matched Packet is encapsulated into a Packet-in message and sent to the controller, and the controller performs route calculation. After the calculation is completed, the controller sends back a Flow-mod message and a Packet-out message again to guide the exchanger to update the Flow table so as to realize successful matching.
Based on the above OpenFlow switch packet forwarding process flow, the inside of the switch can be divided into three modules: flow table inquiry module, packet dispatch module, qoS output queue. The three modules and the controller are respectively abstracted into a waiting queue-server, and an OpenFlow switch model as shown in fig. 2 is constructed. The relevant parameters of the switch include: processing rate of the three modules and processing rate of the controller.
1.2 establishing a target flow
The characteristic attributes for differentiation of flows include a flow table hit status, which determines whether a packet needs to be processed by a controller, and an output queue, which determines QoS services obtained by the packet, thereby differentiating flows. The competition situation of different streams at each module of the switch is as shown in fig. 2, and the stream of the output queue i is selected as the target traffic without losing generality, and the parts of the hit and miss stream tables are analyzed respectively. The relevant parameters of the streams include the arrival rate and burst size of the individual streams at the data plane, and the arrival rate and burst size of competing streams at the control plane.
2. Minimum addition algebraic operation
The least algebraic operation specific to network operations simplifies the function derivation process. The core operation rule used in the function deduction process is as follows:
minimum addition convolution operation:
the least adding deconvolution operation:
3. function derivation
In order to enrich the performance evaluation dimension of the switch, the invention respectively carries out function deduction on the streams of the hit and miss stream tables, deduces respective arrival curves and equivalent service curves, and further calculates the forwarding delay boundary of the two streams. The specific implementation steps are as follows:
3.1 arrival Curve
The arrival curve α (t) of the flow is calculated from the input accumulation function a (t) of each flow to the OpenFlow switch. Where t represents a time span, a (t) represents an accumulated amount of variation of the arrival traffic with time, and metering is performed using the number of packets that arrive. According to the requirement of formula (1) [0, t]Any point in time s within the interval should satisfy this equation, thereby yielding an arrival curve α (t) for the corresponding stream. Arrival curve alpha of flow f f (t) can be simplified as represented by formula (2):
A(t)-A(s)≤α(t-s),0≤s≤t (1)
α f (t)=σ f +ρ f t,t≥0 (2)
step 3.2 summing the arrival curves of the streams of the computed hit and miss flow tables, respectively, according to the arrival curve composition rule of equation (3), wherein α totalf Refers to the arrival curve of the composite part:
α f ~(σ f ,ρ f )→α totalf ~(∑σ f ,∑ρ f ) (3)
3.2 delay boundary values for streams hitting the stream table
According to the output accumulating function A of each module * (t) calculating a service curve beta (t). Wherein A is * (t) represents an accumulated amount of output traffic over time, and is measured using the number of packets output. According to formula (4), calculating service curve beta (t) of corresponding module, including flow table inquiry module service curve beta 1 Packet scheduling module service curve beta 2 Output queue i service curveController service curve beta C . The service curve can be represented simply as equation (5), where r represents the maximum output rate of the corresponding module and b represents the maximum time interval for packet waiting:
β(t)=r(t-b) + ,t≥0 (5)
wherein if t > b then (t-b) + Otherwise (t-b) + =0;
Stripping the resource competition influence of the flow of the non-output queue i and the flow of the missed flow table at the flow table query module according to the FCFS equivalent service curve deduction method of the formula (6), and calculating the equivalent service curve of the flow of the hit flow table at the module
β eq,1 (t,s)={β(t)-α 2 (t-s)} + ,0≤s<t (6)
Calculating the arrival curve alpha of the flow sent back by the controller at the packet scheduling module according to the characteristic limit rule of the output flow and in combination with (8) R :
Calculating an arrival curve of hit streams of the non-output queue i at the packet scheduling module according to equation (9)
According to the derivation method of the FCFS equivalent service curve of the formula (6), the resource competition influence of the flow sent back by the stripping controller and the hit flow of the non-output queue i at the packet scheduling module is calculated, and the equivalent service curve of the flow of the hit flow table at the module is calculated
Bandwidth allocated for flows of hit and miss flow tables, respectively, according to QoS output queuesCalculating equivalent service curve of hit flow in the module +.>
Based on the deduction results of formulas (7), (10) and (11), the service curves of the three modules are converted into equivalent service curves of the flow of the hit flow table through the whole OpenFlow switch system through least convolution operation
Calculating hit flow arrival curvesAnd equivalent service curve->The maximum horizontal distance between them, i.e. the Delay boundary value Delay of the switch for the flow hitting the flow table H :
3.3 time delay boundary values of streams missing from the stream table
Stripping the resource competition influence of the flow of the output queue j and the flow of the hit flow table at the flow table query module according to the FCFS equivalent service curve deduction method of the formula (6), and calculating the equivalent service curve of the flow of the hit flow table at the module
Stripping the resource competition effect of the competition flow of the control plane at the controller, and calculating the equivalent service curve of the flow of the missed flow table at the controller
wherein ,equivalent service curves at the flow table lookup module for the portion of the missed flow table for the other output queues j, which can be calculated by equation (16); />For the characteristic parameters of the burst quantity of the arrival curve of the partial stream at the arrival controller, the calculation can be obtained by the formula (17):
stripping the resource competition influence of the flow of the hit flow table and the flow of the output queue j sent back by the controller at the packet scheduling module, and calculating the service curve of the flow of the miss flow table at the module
wherein ,equivalent service curves at the controller for the portion of the miss stream table for output queue j are available as in equation (15):
according to the bandwidth allocation of QoS output queue, calculating equivalent service curve of missed flow in the module
Calculating an equivalent service profile of the flow of the missed flow table through the entire OpenFlow switch system based on the deductions of formulas (14), (15), (18), (20)
Calculating the miss stream arrival curve in the same manner as in equation (13)And equivalent service curve->And (5) obtaining the maximum horizontal distance between the two streams, and obtaining the time delay boundary of the stream passing through the switch by the missing stream table.
4. Evaluation of use cases
In order to show the specific implementation effect of this patent, this patent uses the performance parameters of Beacon OpenFlow controller and standard virtual switch OpenvSwitch to carry out test experiments.
4.1 parameter variation Range
This patent has adopted the flow parameter change scope of general settlement in the OpenFlow switch performance evaluation, includes: the arrival rate of the flow of the hit and miss flow table, the burst size of the flow of the hit and miss flow table, the arrival rate of the control plane contention flow, the burst size of the control plane contention flow, the processing rate of each module of the switch, and the controller processing rate. For specific parameter values, reference is made to the following table:
table 1 simulation experiment parameter settings
Part of the parameter settings are referred to document [1]. Substituting the derived function under different flow parameter values, and generating a time delay boundary calculation result by using Matlab. The calculation results of this experiment are shown in fig. 3A to 5B.
4.2 evaluation results
Experiments are carried out on a Beacon OpenFlow controller and a standard virtual switch OpenvSwitch, and the method is carried out on a hit stream, an miss stream and a control plane competitive stream respectively, and the test results refer to fig. 3A to 5B.
The test result accurately quantifies the influence degree of different parameters on the forwarding delay boundary of the flow of the hit and miss flow table, which shows that the invention can comprehensively evaluate the forwarding performance of the OpenFlow switch and provide guidance for further optimization and flow control of the switch.
The description of the exemplary embodiments presented above is merely illustrative of the technical solution of the present invention and is not intended to be exhaustive or to limit the invention to the precise form described. Obviously, many modifications and variations are possible in light of the above teaching to those of ordinary skill in the art. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application to thereby enable others skilled in the art to understand, make and utilize the invention in various exemplary embodiments and with various alternatives and modifications. It is intended that the scope of the invention be defined by the following claims and their equivalents.
Claims (4)
1. The multi-parameter forwarding delay performance modeling evaluation method based on network algorithm is characterized by comprising the following steps of:
step 1, analyzing a packet forwarding flow in a typical scene, including a packet processing link, a flow table hit condition and an influence of a controller on packet forwarding and an influence of a QoS queue on packet output in an OpenFlow switch, establishing a network algorithm model, and defining parameters of the switch;
step 2, the characteristic attribute of the arriving flow is definitely included in the hit state of the flow table and the output queue, so that the flow arriving at the OpenFlow switch is distinguished; setting a target flow and defining parameters of the flow;
step 3, deducing an arrival curve of a flow arriving at the switch according to the flow hypothesis and the feature distinction, wherein the flow comprises a hit flow table and a miss flow table;
step 4, stripping the competition interference of forwarding resources of different flows in the OpenFlow switch according to the packet forwarding flow in a typical scene, deducing equivalent service curves of the flows of the hit flow table and the flows of the miss flow table in each module of the switch, and calculating the forwarding time delay of the flows by combining the arrival curves;
the specific steps of the step 4 include:
step 4.1, accumulating the function A according to the output of each module * (t) calculating a service curve β (t); wherein A is * (t) represents an accumulated amount of output traffic over time, and is metered using the number of packets output; according to formula (4), calculating service curve beta (t) of corresponding module, including flow table inquiry module service curve beta 1 Packet scheduling module service curve beta 2 Output queue i service curveController service curve beta C The method comprises the steps of carrying out a first treatment on the surface of the The service curve is simplified as equation (5), where r represents the maximum output rate of the corresponding module and b represents the maximum time interval for packet waiting:
β(t)=r(t-b) + ,t≥0 (5)
wherein, if t>b is (t-b) + Otherwise (t-b) + =0;
Step 4.2, stripping the resource competition influence of the flow of the non-output queue i and the flow of the missed flow table at the flow table query module according to the FCFS equivalent service curve deduction method of the formula (6), and calculating the equivalent service curve of the flow of the hit flow table at the module
β eq,1 (t,s)={β(t)-α 2 (t-s)} + ,0≤s<t (6)
Step 4.3, calculating the arrival curve alpha of the flow sent back by the controller at the packet scheduling module according to the characteristic limit rule of the output flow and in combination with the step (8) R :
Step 4.4, calculating the arrival curve of the hit stream of the non-output queue i at the packet scheduling module according to equation (9)
Step 4.5, stripping the resource competition influence of the hit flow of the flow sent back by the controller and the non-output queue i at the packet scheduling module according to the FCFS equivalent service curve deduction method of the formula (6), and calculating the equivalent service curve of the flow of the hit flow table at the module
Step 4.6, bandwidth allocated to each flow of the hit and miss flow tables according to the QoS output queue Calculating equivalent service curve of hit flow in the module +.>
Step 4.7, converting the service curves of the three modules into the equivalent service curves of the whole OpenFlow switch system by least convolution operation based on the deduction results of the formulas (7), (10) and (11)
Step 4.8, calculating a hit stream arrival curveAnd equivalent service curve->The maximum horizontal distance between them, i.e. the Delay boundary value Delay of the switch for the flow hitting the flow table H :
Step 4.9, stripping the resource competition influence of the flow of the output queue j and the flow of the hit flow table at the flow table query module according to the FCFS equivalent service curve derivation method of the formula (6), and calculating the equivalent service curve of the flow of the miss flow table at the module
Step 4.10, stripping the resource competition influence of the competition flow of the control plane at the controller, and calculating the equivalent service curve of the flow of the missed flow table at the controller
wherein ,calculating an equivalent service curve of a part of the missed flow table of the other output queues j at the flow table query module through a formula (16); />Characteristic parameters of the burst quantity of the arrival curve at the arrival controller for the partial stream, by the formula (17)And (3) calculating:
step 4.11, stripping the resource contention influence of the flow of the hit flow table and the flow of the output queue j sent back by the controller at the packet scheduling module, and calculating the service curve of the flow of the miss flow table at the module
wherein ,equivalent service curves at the controller for the portion of the miss stream table for output queue j are available as in equation (15):
step 4.12, calculating the equivalent service curve of the missed flow in the module according to the bandwidth allocation of the QoS output queue
Step 4.13 based on(14) Calculating equivalent service curves of the flow of the missed flow table through the whole OpenFlow switch system according to the deduction results (15), (18) and (20)
Step 4.14, calculating the missed stream arrival curve in the same way as in equation (13)And equivalent service curve->And (5) obtaining the maximum horizontal distance between the two streams, and obtaining the time delay boundary of the stream passing through the switch by the missing stream table.
2. The network-algorithm-based multi-parameter forwarding delay performance modeling evaluation method according to claim 1, wherein the specific steps of step 1 include:
step 1.1, analyzing a packet forwarding flow, dividing an OpenFlow switch into a flow table query module, a packet scheduling module and a QoS output queue, and establishing a controller and OpenFlow switch model by using an abstract form of a waiting queue-server;
step 1.2, adding trend lines of the flow into a network calculation model according to the packet forwarding flow so as to represent the processing process of the packet and the resource competition condition of different flows;
step 1.3, defining parameters of the switch, including processing rates of each module of the OpenFlow switch: flow table lookup module processing rate d 1 Packet scheduling module processing rate d 2 Processing rate of output queue iController processing rate d C 。
3. The network algorithm-based multi-parameter forwarding delay performance modeling evaluation method according to claim 1 or 2, wherein the specific steps of step 2 include:
step 2.1, the characteristic attribute used for distinguishing the flow comprises a flow table hit state and an output queue, wherein the flow table hit state determines whether a packet needs to be processed by a controller or not, and the output queue determines QoS service obtained by the packet; according to the flow distinguishing, the flow of the output queue i is selected as the target flow without losing generality, and the parts of the hit and miss flow tables are respectively analyzed, so that the other output queues except the i are j;
step 2.2, defining parameters of the streams, including arrival rate and burst amount of each stream of the data plane: arrival rate ρ of traffic f f Burst quantity sigma of flow f f The control plane contends for the arrival rate and burst size of the flow: arrival rate ρ of competing streams o Burst quantity sigma of competing stream o 。
4. The network-algorithm-based multi-parameter forwarding delay performance modeling evaluation method according to claim 3, wherein the specific steps of step 3 include:
step 3.1, calculating an arrival curve alpha (t) of each flow according to an input accumulation function A (t) of each flow arriving at the OpenFlow switch; where t represents a time span, a (t) represents an accumulated amount of variation of the arrival traffic with time, and metering is performed using the number of packets that arrive; according to the requirement of formula (1) [0, t]Any point in time s within the interval should satisfy the equation, thereby yielding an arrival curve α (t) for the corresponding stream; arrival curve alpha of flow f f (t) is simplified to be represented by formula (2):
A(t)-A(s)≤α(t-s),0≤s≤t (1)
α f (t)=σ f +ρ f t,t≥0 (2)
step 3.2, summing the arrival curves of the flows of the calculation hit and miss flow tables, respectively, according to the arrival curve composition rule of (3), wherein α totalf Refers to the arrival curve of the composite part:
α f ~(σ f ,ρ f )→α totalf ~(∑σ f ,∑ρ f ) (3)。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110955293.9A CN113742902B (en) | 2021-08-19 | 2021-08-19 | Multi-parameter performance modeling evaluation method based on network algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110955293.9A CN113742902B (en) | 2021-08-19 | 2021-08-19 | Multi-parameter performance modeling evaluation method based on network algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113742902A CN113742902A (en) | 2021-12-03 |
CN113742902B true CN113742902B (en) | 2023-08-04 |
Family
ID=78731800
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110955293.9A Active CN113742902B (en) | 2021-08-19 | 2021-08-19 | Multi-parameter performance modeling evaluation method based on network algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113742902B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114244680B (en) * | 2021-12-17 | 2023-06-27 | 网络通信与安全紫金山实验室 | End-to-end deterministic transmission control method, device, equipment and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105553845A (en) * | 2016-01-19 | 2016-05-04 | 重庆邮电大学 | Software defined network route selection method |
CN106330555A (en) * | 2016-08-29 | 2017-01-11 | 南京市产品质量监督检验院 | OpenFlow switch performance parameter measurement method based on KPLS algorithm |
CN106571883A (en) * | 2016-07-04 | 2017-04-19 | 长春理工大学 | Random network calculation method for satellite network performance evaluation |
CN109714275A (en) * | 2019-01-04 | 2019-05-03 | 电子科技大学 | A kind of SDN controller and its control method for access service transmission |
CN112491619A (en) * | 2020-11-25 | 2021-03-12 | 东北大学 | Self-adaptive distribution technology for service customized network resources based on SDN |
CN112671673A (en) * | 2020-12-28 | 2021-04-16 | 广州西麦科技股份有限公司 | SDN-based flow control system and method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10015048B2 (en) * | 2014-12-27 | 2018-07-03 | Intel Corporation | Programmable protocol parser for NIC classification and queue assignments |
-
2021
- 2021-08-19 CN CN202110955293.9A patent/CN113742902B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105553845A (en) * | 2016-01-19 | 2016-05-04 | 重庆邮电大学 | Software defined network route selection method |
CN106571883A (en) * | 2016-07-04 | 2017-04-19 | 长春理工大学 | Random network calculation method for satellite network performance evaluation |
CN106330555A (en) * | 2016-08-29 | 2017-01-11 | 南京市产品质量监督检验院 | OpenFlow switch performance parameter measurement method based on KPLS algorithm |
CN109714275A (en) * | 2019-01-04 | 2019-05-03 | 电子科技大学 | A kind of SDN controller and its control method for access service transmission |
CN112491619A (en) * | 2020-11-25 | 2021-03-12 | 东北大学 | Self-adaptive distribution technology for service customized network resources based on SDN |
CN112671673A (en) * | 2020-12-28 | 2021-04-16 | 广州西麦科技股份有限公司 | SDN-based flow control system and method |
Non-Patent Citations (1)
Title |
---|
软件定义网络中的动态负载均衡与节能机制;鲁垚光等;《计算机学报》;第43卷(第10期);第1969-1982页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113742902A (en) | 2021-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Stiliadis et al. | Design and analysis of frame-based fair queueing: A new traffic scheduling algorithm for packet-switched networks | |
Wrege et al. | Deterministic delay bounds for VBR video in packet-switching networks: fundamental limits and practical trade-offs | |
Scharbarg et al. | A probabilistic analysis of end-to-end delays on an AFDX avionic network | |
US8966492B2 (en) | Service provision quality control device | |
CN102711129B (en) | The determination method and device of net planning parameter | |
CN110708259A (en) | Information-agnostic Coflow scheduling system capable of automatically adjusting queue threshold and scheduling method thereof | |
CN112532409A (en) | Network parameter configuration method and device, computer equipment and storage medium | |
CN113742902B (en) | Multi-parameter performance modeling evaluation method based on network algorithm | |
CN112202644B (en) | Collaborative network measurement method and system oriented to hybrid programmable network environment | |
CN101132362A (en) | Network traffic generating method and system thereof | |
US20050055196A1 (en) | Wireless network hybrid simulation | |
CN109714795A (en) | A kind of method for managing resource, resource management system and device based on SDN network slice | |
CN117082008B (en) | Virtual elastic network data transmission scheduling method, computer device and storage medium | |
EP1842332B1 (en) | A method and apparatus for calculating bandwidth requirements | |
Yang et al. | Analyzing worst-case delay performance of IEC 61850-9-2 process bus networks using measurements and network calculus | |
Ruan et al. | Machine intelligence in supervising bandwidth allocation for low-latency communications | |
US9887928B2 (en) | System and method for identifying performance characteristics in asynchronous networks | |
Jiang et al. | Correlation coefficient analysis of the age of information in multi-source systems | |
Harmantzis et al. | Effective bandwidths and tail probabilities for Gaussian and stable self-similar traffic | |
Siddikov et al. | Hybrid Model management of Information messages in multiservice networks | |
Lu et al. | Asymptotic blocking probabilities in loss networks with subexponential demands | |
CN108540323A (en) | The method for predicting router processing speed based on minimum plus deconvolution | |
CN116232845A (en) | Distributed network configuration model middle stream reservation method based on reinforcement learning | |
US8031721B2 (en) | Method and apparatus for marking and scheduling packets for transmission | |
Tang et al. | Improving multiprocessor real-time systems with bursty inputs under Global EDF using shapers |
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 |