Stochastic Modeling of Packet Delay in Open Flow
- Slides: 56
Stochastic Modeling of Packet Delay in Open. Flow SDNs Dr. Muhammad Usman Ilyas Post-doc + Ph. D + MS (Michigan State U), MS (LUMS), BE (NUST) usman. Ilyas@seecs. edu. pk, usman@ieee. org Applied Network & Data Science Research (AN-DASH) Lab School of Electrical Engineering and Computer Science (SEECS) National University of Science and Technology (NUST) Islamabad, Pakistan 1
Team Members Uzzam Javed MS Student SEECS-NUST, Pakistan Azeem Iqbal MS Student SEECS-NUST, Pakistan 2
Center of NUST campus 3
School of Electrical Engineering & Computer Science SEECS 4
School of Electrical Engineering & Computer Science SEECS 5
nust. edu. pk 6
seecs. nust. edu. pk 7
andash. seecs. nust. edu. pk 8
Ongoing Research projects at ANDASH Lab Networking and Security 1. Packet delay model in Open. Flow SDNs (OF@TEIN) 2. Open. Stack fault resilience to network errors Microsoft Research – Azure 4 research . 9
Ongoing Research projects at ANDASH Lab Networking and Security 1. Packet delay model in Open. Flow SDNs (OF@TEIN) 2. Open. Stack fault resilience to network errors Microsoft Research – Azure 4 research 3. 4. Anomaly detection in Open. Stack PLUMgrid Inc. , Sunnyvale, CA Link de-anonymization in Ims (Tor network) Cloud-mobile Applications 1. Mobile crowdsensing to map road and traffic conditions Microsoft Research – Azure 4 research http: //craters. azurewebsites. net 2. 3. Activity recognition and tracking by smartphones HEC funding MAC protocol for vehicular networks (SKKU, Suwon, S. Korea) Social media / networks 1. Word cloud segmentation based on sub-topics 10
Network Planes Data Plane Forward traffic according to the logic implemented at the control plane. 11
Network Planes Control Plane Control plane is the brain of the network, contains logic forwarding traffic. Control plane of each switch learns structure of network by communicating with peer planes in connected switches. Control Plane Control Plane 12
Network Planes Management Plane Used to manage and configure network devices. Control Plane Control Plane 13
Implementation in Traditional Networks In traditional networks all three planes reside within the firmware of switches and routers. Makes the management of large networks difficult. 14
Open. Flow Software Defined Networking (SDN) is an paradigm that decouples control plane from data plane. Provides a control plane abstraction for the whole network (AS). Net Apps Northbound API Network Controller Open. Flow protocol Secure Channel Flow Table Pipeline Data Plane 16
Open. Flow Virtually separated planes interact through different APIs (interfaces). Open. Flow is an interface to communicate between the control plane and the data plane promoted by Open Networking Foundation (ONF). Net Apps Northbound API Network Controller Open. Flow protocol Secure Channel Flow Table Pipeline Data Plane 17
Separation of Control Plane across H/W Comp. Install table entry, send packet SDN Controller Most features go here This gets smaller, turns into controller to switch chip translator Control Plane CPU Packet / Network Processor 0 C->p 3 Table miss, send to controller dst port 0 E 5 0 A 1 0 C 3 0 A->0 C 0 A->0 E http: //colindixon. com/wp-content/uploads/2014/05/odl-meetup. pdf 18
Advantages of SDN Enables innovation by providing freedom from vendor lock-in. Improves network visibility by providing a global view. üTraffic steering. üSecurity enforcement. Makes network management simple Reduce operational cost of network. Simpler switches. 19
Open. Flow Switch Entry http: //www. slideshare. net/Cameroon 45/ppt-4515906 21
Research Objectives Analyzing the performance of Open. Flow SDN. Model A) packet processing delay of a single Open. Flow SDN router B) end-to-end path delay in Open. Flow SDNs. Assess the accuracy of delay modeling in mininet. 23
Prior State-of-the-art Limitation of Queuing Theory approach: Assumes Poisson arrival process for packets and exponential distribution for traffic. In reality Ethernet traffic has been found to be selfsimilar(fractal) in nature. Cannot be accurately modeled with Poisson process. Leland, Will E. , et al. "On the self-similar nature of Ethernet traffic (extended version). " Networking, IEEE/ACM Transactions on 2. 1 (1994): 1 -15. 24
Prior State-of-the-art Some works used simulations to verify the derived model. Interaction of multiple switches were not considered. Limitation of Network Calculus approach used: A relatively new alternative to classical queueing theory. It has two branches Deterministic Network Calculus (DNC) and Stochastic Network Calculus (SNC). DNC only provides worst-case bounds on performance metrics. The models build using Network Calculus used DNC, whose result are far from practical use. Ref: Ciucu, Florin, and Jens Schmitt. "Perspectives on network calculus: no free lunch, but still good value. " Proceedings of the ACM SIGCOMM 2012 conference on Applications, technologies, architectures, and protocols for computer communication. ACM, 2012. 25
Prior State-of-the-art Jarschel, Michael, et al. "Modeling and performance evaluation of an openflow architecture. " Proceedings of the 23 rd international teletraffic congress. International Teletraffic Congress, 2011. Proposed a basic model forwarding speed and blocking probability for an Open. Flow switch and a controller using queueing theory. Azodolmolky, Siamak, et al. "An analytical model for software defined networking: A network calculus-based approach. " Global Communications Conference (GLOBECOM), 2013 IEEE, 2013 Delay and queue length boundaries are modeled using Network Calculus. 27
Prior State-of-the-art Bozakov, Zdravko, and Amr Rizk. "Taming SDN controllers in Heterogeneous hardware environments. " Software Defined Networks (EWSDN), 2013 Second European Workshop on. IEEE, 2013. A simple model for control message processing using Network Calculus. Chilwan, Ameen, et al. "ON MODELING CONTROLLERSWITCH INTERACTION IN OPENFLOW BASED SDNS. ” A more accurate model using queueing theory but evaluated using simulations. 28
Measurements Controlled traffic generation using traffic generator. Delay measurements will include the following components: Clock synchronization ensured using NTP 1. 2. 3. 4. Processing delay on a each switch. Queuing delay on each switch. Transmission delay on each switch. Link propagation delay. 29
Evaluation Parameters Following possible measurement scenarios will be considered: Based on traffic: Packet size Traffic distribution Rate TCP/UDP Variable switching load Open. Flow Parameters: Single field matching Multiple field matching Matching on a range of IP's/Port numbers Changing the number of actions Hard time out/ Soft time out Comparison between reactive and proactive forwarding. 30
Platform 1 - Mininet C 0 Controller SDN emulator To study the delay in Open. Flow SDN switches in an SDN emulator. Open. Flow Switch H 1 S 1 H 2 Virtual Hosts Mininet Virtual Machine 31
Platform 2 – Laboratory setup Experimentation on lab scale testbed of Open. Flow SDN switches. Enabling Open. Flow on a Mikrotik Router. Board 750 GL router, for experimentation. Controller Open. Flow switches Mikrotik Router. Board 750 GL switches Host 1 Host 2 32
Platform 3 – GENI Testbed An Internet scale network testbed infrastructure, spanning across the US. Experimentation on widely distributed resources. To explore behavior of Open. Flow switches at scale. http: //groups. geni. net/geni/wiki/Geni. Newcomers. Welcome 33
Platform 4 - OF@TEIN Risdianto, Aris Cahyadi, and Jong. Won Kim. "Prototyping Media Distribution Experiments over OF@ TEIN SDN-enabled Testbed. " Proceedings of the Asia-Pacific Advanced Network 38 (2014) 34
Platform 4 - OF@TEIN is a an Open. Flow enabled testbed spread over seven countries. Project was launched in July 2012, through Korean Government funding. Deployed on TEIN 4 (Trans-Eurasia Information Network 4). Managed by Consortium of Korean universities International collaboration sites Led by Gwangju Institute of Science & Technology (GIST), S. Korea. 35
Some Initial Results for Single Switch Three platforms were used to analyze the round trip time delay. OF@TEIN results pending due to ongoing migration to Open. Stack. Using Distributed Internet Traffic Generator (D-ITG) for all platforms. 1, 000 packets were generated with a constant rate of 10, 000 pkt/s from one host to another. Size of packet was kept constant to 1, 500 bytes. TCP protocol was used. All platforms were using Open v. Switch (OVS) and Open. Flow 1. 0 enabled switches. Each platform was tested for reactive and proactive forwarding scenario. 36
Single Router Delay 37
Mininet Traffic was generated on a single switch with external controller (POX). Timeout for switch’s flow table entry was set to 1 second. Open. Flow switch was invoked as L 2 learning switch through controller. 38
Mininet 39
Mininet Traffic was generated on a single switch. Entries on the switch were pre-loaded before the flows were generated. 40
Mininet 41
Laboratory Setup Traffic was generated on a single switch, Mikro. Tik Router. Board 750 GL. Controller (POX) was running in one system, which invoked Open. Flow switch to act as a L 2 learning switch. Timeout for flow table entry was set to 1 second. 42
Laboratory Setup 43
Laboratory Setup Traffic was generated on a single switch, Mikro. Tik Router. Board 750 GL. The entries on the switch were proactively added before the flows were generated. 44
Laboratory Setup 45
GENI Testbed Traffic was generated on a single switch on GENI testbed. Controller (POX) was running in Utah, while switch and hosts were located in California. Timeout for switch’s flow table entry was set to 1 second. Open. Flow switch was invoked to act as L 2 learning switch. 46
GENI Testbed 47
GENI Testbed Traffic was generated on a single switch on GENI testbed. The switch and hosts were all located in California. The entries on the switch were proactively added before the flows were generated. 48
GENI Testbed 49
End-to-end Delays 50
Some Initial Results for End-to-End measurements Three platforms were used to analyze the round trip time delay. 1, 000 packets were generated with a constant rate of 10, 000 pkt/s from one host to another. Size of packet was kept constant to 1, 500 bytes. TCP protocol was used. All platforms were using Open v. Switch (OVS) enabled switches. 51
Mininet Traffic was generated on two switches with external controller(POX). Timeout for switch’s flow table entry was set to 1 second. Open. Flow switch was invoked as L 2 learning switch through controller. 52
Mininet 53
Mininet Traffic was generated on two switches. The entries on the switch were proactively added before the flows were generated. 54
Mininet 55
Laboratory Setup Traffic was generated through two Mikro. Tik Router. Board 750 GL switches. Controller (POX) was running in one system, which invoked Open. Flow switches to act as a L 2 learning switch. Timeout for switch’s flow table entry was set to 1 second. 56
Laboratory Setup 57
Laboratory Setup Traffic was generated through two Mikro. Tik Router. Board 750 GL switches. The entries on the switch were proactively added before the flows were generated. 58
Laboratory Setup 59
Thank You 60
- Propagation delay
- Inertial delay and transport delay
- Plc timers
- Stochastic process modeling
- Dnodal
- Modeling role modeling theory
- Dimensional modeling vs relational modeling
- 영국 beis
- Vhdl data flow modeling
- Data flow modeling in verilog examples
- S o f t w a r e f o r t r a f f i c
- Stochastic rounding
- Stochastic programming
- Stochastic process model
- Stochastic optimization tutorial
- Stochastic inventory model example
- Put call parity formula
- Stochastic vs dynamic
- Absorbing stochastic matrix
- Stochastic regressors
- Non stochastic theory of aging
- A first course in stochastic processes
- Stochastic process introduction
- Stochastic progressive photon mapping
- Agent a chapter 2
- Non stochastic variable
- Logistic regression stochastic gradient descent
- Stochastic process
- Stochastic process
- Stochastic process
- Stochastic process
- Random process
- Guided, stochastic model-based gui testing of android apps
- Stochastic specification of prf
- Stochastic uncertainty
- Components of time series analysis
- Stochastic vs probabilistic
- Stochastic vs probabilistic
- Stochastic calculus
- Stationary stochastic process
- Stochastic vs probabilistic
- Stochastic process
- Stochastic slow
- Gradient descent
- Dn0jx
- Stochastic gradient langevin dynamics
- Tsne vs pca
- Stochastic rounding
- Deterministic and stochastic inventory models
- Stochastic regressors
- Pathophysiology of atelectasis
- Venturi mask 50 percent
- Fraction of inspired oxygen
- Laminar vs turbulent
- Internal versus external flow
- Energy naturally flows from warmer matter to cooler matter
- Flow of energy vs flow of matter