Title :
Improving scalability of network emulation through parallelism and abstraction
Author :
Kiddle, Cameron ; Simmonds, Rob ; Unger, Brian
Author_Institution :
Dept. of Comput. Sci., Calgary Univ., Alta., Canada
Abstract :
One approach to network emulation involves simulating a virtual network with a real-time network simulator and providing an I/O interface that enables interaction between real hosts and the virtual network. This allows real protocols and applications to be tested in a controlled and repeatable environment. To reflect conditions of large networks such as the Internet it is important that the emulation environment be scalable. This paper examines improvements in scalability of the virtual network achieved through the use of parallel discrete event simulation and simulation abstraction. Using just parallel simulation techniques, real-time emulation performance of nearly 50 million packet transmissions per second is achieved on 128 processors for a network model consisting of about 20,000 nodes. Using both parallel simulation and abstraction techniques, real-time emulation performance of nearly 500 million packet transmissions per second is achieved on 128 processors for a network model consisting of about 200,000 nodes.
Keywords :
computer networks; discrete event simulation; protocols; I/O interface; emulation environment; network emulation; network model; parallel discrete event simulation; parallel simulation; protocols; real-time emulation performance; real-time network simulator; simulation abstraction; virtual network; Computational modeling; Computer simulation; Discrete event simulation; Emulation; Parallel processing; Protocols; Scalability; Telecommunication traffic; Testing; Traffic control; Fluid; Parallel Discrete Event Simulation; Scalable Network Emulation; Simulation Abstraction;
Conference_Titel :
Simulation Symposium, 2005. Proceedings. 38th Annual
Print_ISBN :
0-7695-2322-6
DOI :
10.1109/ANSS.2005.26