Network traffic engineering
Toolbox, hybrid IP/MPLS optimisation method and fairness
Fabian Skiv ´ee
Research Unit in Networking EECS Department University of Li `ege
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Outline
1 Introduction
2 A toolbox of TE methods 3 A new hybrid IP/MPLS method 4 Fairness in MPLS networks 5 Conclusion
Outline
1 Introduction
Introduction MPLS principles
2 A toolbox of TE methods
3 A new hybrid IP/MPLS method
4 Fairness in MPLS networks
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Introduction MPLS principles
Introduction
Today, most operators overprovision their network.
But increasing demand and quality of service requirements means this approach is less and less tenable economically. Traffic Engineering (TE) involves adapting the routing of traffic to the network conditions, with the joint goals of good user performance and efficient use of network resources.
MPLS principles
Multi Protocol Label Switching (MPLS) allows to establish tunnels (LSPs, label switched paths) in the topology, along explicit routes (e.g. using RSVP-TE).
Routing is not only destination-based any more LSPs can be bandwidth guaranteed
Advantages
We can freely choose the path and the granularity of these LSPs
These are independent from each other
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion Objectives Architecture Applications
Outline
1 Introduction 2 A toolbox of TE methods Objectives Architecture Applications3 A new hybrid IP/MPLS method
4 Fairness in MPLS networks
Toolbox objectives
Lots of research in TE domain but not used by operators because of their integration and usage complexity. Our TOTEM toolbox has two objectives:
Allow researchers to promote their new TE methods and compare them with other existing ones.
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion Objectives Architecture Applications
Architecture requirements
The architecture must meet several requirements: Minimise new algorithm integration effort Be interoperable with existing tools
Allow the integration of algorithms written in multiple languages
Allow different execution modes
on-line in a real network off-line for simulation purposes
Toolbox integration
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion Objectives Architecture Applications
Toolbox architecture
MPLS config IGP config BGP config Topology Link load SNMP Netflow traces Traffic Matrix BGP dump Create a model of the netwok Methods repositoryIGP metric optimiser
LSP path computation Backup LSP path computation BGP decision process simulation Simulation Scenario CONTROL
Optimise and simulate
Link load analysis Path delay analysis Inter domain traffic analysis Analyse report BGP routing table
Toolbox applications
Analyse link load associated with a traffic matrix Simulate link failure
Compare link load based on several traffic matrices Optimise the IP metric
Compute near-optimal MPLS full mesh using DAMOTE Compute hybrid IP/MPLS solution using SAMTE Simulate inter-domain routing using C-BGP simulator Compute traffic matrix from netflow monitoring data Generate topology and traffic matrix using Topgen generator
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Objective
Hybrid IP/MPLS routing models SAMTE
Simulations
Re-optimisation strategy for dynamic TE
Outline
1 Introduction
2 A toolbox of TE methods
3 A new hybrid IP/MPLS method
Objective
Hybrid IP/MPLS routing models SAMTE
Simulations
Re-optimisation strategy for dynamic TE
4 Fairness in MPLS networks
Objective
Objective: find a small number of LSPs to optimize a given operational need like minimize max load, load balancing,... Advantages
Scalable: just a few LSPs, i.e. not a full mesh
Incremental: you know exactly which traffic will be routed on the LSPs
Generic: you can combine different LSPs for different objectives such as delay, max load,...
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Objective
Hybrid IP/MPLS routing models SAMTE
Simulations
Re-optimisation strategy for dynamic TE
Hybrid IP/MPLS routing models
1 2 3 4 5 6 F2,5 F2,6 F1,6 LSP 2 2 2 2 1 2 2 2 1 2 3 4 5 6 F2,5 F2,6 F1,6 LSP 2 2 2 2 1 2 2 2 1 2 3 4 5 6 F2,5 F2,6 F1,6 LSP 2 2 2 2 1 2 2 2
Overlay Basic IGP Shortcut IGP shortcut
All flows entering
the network at
node 2 and exiting it at node 6 will be forwarded on the LSP
All flows exiting the network at node 6 will be forwarded on the LSP (if they cross node 2 before)
All flows crossing node 2 and then node 6 will be for-warded on the LSP
SAMTE : hybrid IP/MPLS method
Compute a solution of K LSPs to optimise your objective Generate a ”candidate path list” with P shortest path for each pair origin/destination.
Based on simulated annealing meta heuristic
Initial solution : Generate a set of K LSPs at random Neigbourhood : replace a LSP of the solution by a LSP of the candidate list
Objective functions (bottleneck) : minimize maximum link utilisation load balancing (combined with shortest path)
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Objective
Hybrid IP/MPLS routing models SAMTE
Simulations
Re-optimisation strategy for dynamic TE
Simulated annealing execution
0.4 0.45 0.5 0.55 0.6 0.65 0.7 0.75 0 2000 4000 6000 8000 10000
Maximum link load
Simulated annealing execution
Current solution Best solution Temperature
G ´
EANT network
Summary European research network 30 countries and 26 national networks 23 nodes 38 linksIntroduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Objective
Hybrid IP/MPLS routing models SAMTE
Simulations
Re-optimisation strategy for dynamic TE
Minimize maximum link utilisation on GEANT
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0 5 10 15 20 25 Link load
Link load with differents number of LSPs
Maximum link load Mean link load Std of the link load Percentile 10 of the link load
Comparaison with other TE methods
Method #LSP Max Per10 Mean Std CPU time
in % in % in % in % MCNF 506 41.9 - - - ¿ 2 days SPF-G ´EANT 0 70.7 23.0 7.1 11.5 0 SPF-InvCap 0 46.3 22.3 6.9 9.6 0 IGP-WO 0 45.1 22.2 7.2 9.6 315 s DAMOTEα=2 506 41.9 16.1 8.5 7.5 2.5 s G ´EANT + SAMTEfML 4 42.1 24.5 7.5 10.7 1.0 s G ´EANT + SAMTEfLB 12 42.5 18.9 7.8 8.4 3.1 s G ´EANT + SAMTEfLB 23 42.5 16.5 7.8 8.0 13.8 s
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Objective
Hybrid IP/MPLS routing models SAMTE
Simulations
Re-optimisation strategy for dynamic TE
Description
Objective : When and how to re-engineer (update the set of LSPs) the network according to traffic evolution ? Maximize the operational objective
Minimize the number of re-optimisations
Simulations done on one month of traffic matrices of Geant (computed with Netflow)
Two strategies evaluated
The utopic strategy: At the beginning of each period of 15 minutes, we consider that the next traffic matrix is known exactly (which is obviously impossible) and SAMTE is used to set up 5 new LSPs to replace the former 5. [Reference] The TM-max strategy: we build TM-max which is a traffic matrix composed of the maximal traffic over one month for each pair. Then TM-max will be used as input to SAMTE to compute 5 LSPs for the next month. [Proposition]
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Objective
Hybrid IP/MPLS routing models SAMTE
Simulations
Re-optimisation strategy for dynamic TE
Comparison of the two strategies
-10 0 10 20 30 40 50 30/04 07/05 14/05 21/05 28/05 04/06 % Time Summary Worst max load:
66.9 % - TM-max 45.2 % - each TM ⇒48 % of increasing Average increase : 3.8 % Each TM rerouting In average 3.5 % of the pairs 1.6 % of the volume Maximum 11.46% of the pairs 25.3% of the volume
Outline
1 Introduction
2 A toolbox of TE methods
3 A new hybrid IP/MPLS method
4 Fairness in MPLS networks
Objectives Max-min fairness Distributed algorithm Simulation
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion Objectives Max-min fairness Distributed algorithm Simulation
Objectives
Our goal : sharing the available bandwidth among all the LSPs according to their weights
The classical max-min rate allocation policy has been accepted as an optimal network bandwidth sharing criterion among user flows.
Extension with a weight : WPMM (Weighted Proportional Max-Min)
Weighted Proportional Max-min fairness
Notations L : a set of links S : a set of LSPs Each LSPs has : a reserved rate RRs a fair rate FRs a maximal rate MRs a weight wsA fair share allocates a LSP with a ”small” demand what it wants, and distributes unused resources evenly to the ”big” LSPs according to their weights
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion Objectives Max-min fairness Distributed algorithm Simulation
Proposed distributed WPMM algorithm
Periodically, the ingress sends a PATH packet
Each router computes a local fair share for the LSP and updates a new RSVP field (called ER, explicit rate) if its local fair rate is less than the actual fair rate
Upon receiving a PATH packet, the egress router sends a RESV packet.
Each router updates its information with the RESV parameters.
Simulation
For stabilizing 90% of the LSPs, our solution takes 4 iterations (16 with Hou’s one). In the worst topology (among 63
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Outline
1 Introduction
2 A toolbox of TE methods
3 A new hybrid IP/MPLS method
4 Fairness in MPLS networks
Conclusion
The toolbox is now really pertinent for researchers and operators. It could become a tool to accelerate the developement of recent traffic engineering methods The proposed hybrid IP/MPLS method is a scalable and very flexible method to traffic engineer a network
Other contraints could be added, like resilience, combination with IP-FRR, re-optimisation strategy This work, characterised by its pragmatic approach, focuses on real needs in current high speed networks
Introduction A toolbox of TE methods A new hybrid IP/MPLS method Fairness in MPLS networks Conclusion
Publications
G. Leduc, H. Abrahamsson, S. Balon, S. Bessler, M. D’Arienzo, O. Delcourt, J. Domingo-Pascual, S. Cerav-Erbas, I. Gojmerac, X. Masip, A. Pescap `e, B. Quoitin, S. P. Romano, E. Salvadori, F. Skiv ´ee, H. T. Tran, S. Uhlig, and H. ¨Umit. An open source traffic engineering toolbox. To appear in Computer
Communications, 2005. (18 pages)
F. Skiv ´ee, S. Balon, O. Delcourt, J. Lepropre, and G. Leduc. Architecture d’une boˆıte `a outils d’algorithmes d’ing ´enierie de trafic et application au r ´eseau G ´EANT. Actes de Colloque Francophone sur l’Ing ´enierie des Protocoles (CFIP), pages 317-332, Bordeaux, France, 29 Mar.-1 Avr. 2005. Herm `es Lavoisier. F. Skiv ´ee and G. Leduc. A Distributed Algorithm for Weighted Max-Min Fairness in MPLS Networks. Proc. of 11th IEEE International Conference on
Telecommunications (ICT’2004), 1-6 Aug. 2004, Fortaleza, Brazil, J. Neuman de
Souza, P. Dini, P. Lorenz (eds.), Telecommunications and Networking, LNCS, 3124, pp. 644-653, Springer Verlag.
S. Balon, F. Skiv ´ee, G. Leduc. Comparing traffic engineering objective functions.
Proc. of the 1sh ACM CoNEXT student workshop, October 24-27, 2005,
Submitted papers
S. Balon, O. Delcourt, J. Lepropre, F. Skiv ´ee and G. Leduc. A traffic engineering toolbox and its application to the GEANT network. IEEE eTransactions on
Network and Service Management. (11 pages)
F. Skiv ´ee, S. Balon and G. Leduc. A scalable heuristic for hybrid IGP/MPLS traffic engineering - Case study on the GEANT network. IEEE International