Networking Research Overview for CPSC 699

Download Report

Transcript Networking Research Overview for CPSC 699

Broadband Wireless Network
Applications and Performance
Carey Williamson
Professor/iCORE Senior Research Fellow
Department of Computer Science
University of Calgary
September 21, 2001
1
Background Information
r Education:
m
m
B.Sc.(Hon.), Computer Science, U.Sask., 1985
Ph.D., Computer Science, Stanford U., 1992
r Experience:
m Dept of Computer Science, U.Sask., 1991-2001
m Adjunct Scientist, TRLabs Saskatoon, 1991-2001
r Research Areas:
m
Computer Networks, Performance Evaluation
r Professional Service/Memberships:
m ACM (SIGMETRICS, SIGCOMM), IEEE, SCS
September 21, 2001
2
Internet Protocol Stack
r
Application: supporting network
applications and end-user services
m
r
Transport: end to end data transfer
m
r
IPv4, IPv6, BGP, RIP, routing protocols
Data Link: hop by hop frames,
channel access, flow/error control
m
r
TCP, UDP
Network: routing of datagrams
from source to destination
m
r
FTP, SMTP, HTTP, DNS, NTP
PPP, Ethernet, IEEE 802.11b
Application
Transport
Network
Data Link
Physical
001101011...
Physical: raw transmission of bits
September 21, 2001
3
Research Interests
r Network Traffic Measurement
r Workload Characterization
r Traffic Modeling
r Network Simulation
r Web Performance
r Adaptive Network Applications
September 21, 2001
4
Network Traffic Measurement
r Collect and analyze packet-level traces
from a live network
September 21, 2001
5
Network Traffic Measurement
r Collect and analyze packet-level traces
from a live network, using special equipment
September 21, 2001
6
Network Traffic Measurement
r Collect and analyze packet-level traces
from a live network, using special equipment
September 21, 2001
7
Network Traffic Measurement
r Collect and analyze packet-level traces
from a live network, using special equipment
r Process traces, statistical analysis
r Diagnose performance problems
(network, protocol, application)
September 21, 2001
8
Workload Characterization
r Try to understand the salient features of
network, protocol, application, and user
behaviour on the Internet
r Example: Web server workloads [Arlitt96]
m
m
m
m
Zipf-like document referencing behaviour
Lots of “one-time” referencing of documents
Heavy-tailed file size distributions
Self-similar network traffic profile
September 21, 2001
9
Traffic Modeling
r Construct programs and statistical models
that capture the empirically-observed
network traffic behaviours
r Allows flexible, controlled, repeatable
generation of workloads for experiments
r Examples:
m
m
m
m
Web client workload model
MPEG compressed video model
Self-similar Ethernet LAN traffic model
Synthetic Web proxy workload generator
September 21, 2001
10
Network Simulation
r Use computer simulation to study the
packet-level behaviour of the Internet, its
protocols, its applications, and its users
r Examples:
m
m
m
Improving Web performance over ADSL
Understanding the effects of user mobility on
Mobile IP routing and protocol performance
Studying the design, scalability, and
performance of Web server and Web proxy
caching architectures
September 21, 2001
11
Web Performance
r Explore techniques to improve the
performance and scalability of the Web
r Examples:
m
m
m
m
m
Clustered Web servers
Load balancing policies
Web prefetching strategies
Web proxy caching architectures
Improvements to HTTP and TCP protocols
September 21, 2001
12
Adaptive Network Applications
r Explore design of Internet-based network
applications (or protocols) that can adapt
their behaviour (automatically) to make
appropriate use of available resources
r Examples:
m
m
m
m
m
Web content for Java-enabled phones
Multicast support for mobile users
Location-aware routing optimizations
Wireless-aware TCP protocol
File system support for mobile users
September 21, 2001
13
Summary of Research Plan
r Broadband Wireless Networks Lab (UofC)
r Experimental Laboratory for Internet
Systems and Applications (UofS/UofC,CFI)
r Research Team:
m
Four full-time research staff (Web, perf. eval.,
simulation, wireless, traffic modeling, network
measurement) plus 6-10 graduate students
r Research Collaborations:
m UofC, UofA, UofS, TRLabs, CS/ECE
m Nortel? HP? Cisco? Agilent? Compaq? Others?
r Do cool, “hands on”, industrially-relevant,
applied, practical, and exciting stuff!!
September 21, 2001
14