YOU ARE DOWNLOADING DOCUMENT

Please tick the box to continue:

Transcript
Page 1: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

User-Perceived Performance Measurement on the Internet

Bill Tice

Thomas Hildebrandt

CS 6255

November 6, 2003

Page 2: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Introduction

The Internet is different from LANs– Diversely administered– Users are relatively distant from the network

administrators– IP is the only service provided by the network– SNMP or something like it? No…

Page 3: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Overview

Why user-perceived performance measurement is important and also difficult

Existing solutions to the global network measurement problem– NIMI– E2E piPEs– Client-side proxies and other solutions

Page 4: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Performance Measurement on the Internet

IP was designed around the end-to-end argument: certain functions are not required at low levels of a system [1]

As a result, we have a “dumb network” with no built-in performance measurement architecture

The tools we can count on are limited

Page 5: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Performance Measurement on the Internet: Example Tools

Packet Internet Groper (ping) – Useful to test connectivity and RTT between hosts

Traceroute – Provides an approximation of the network topology in the forward direction

Iperf – Measures TCP and UDP performance, including bandwidth, delay jitter and packet loss

Page 6: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Performance Measurement on the Internet

Ping and traceroute rely on ICMP, which is increasingly being blocked by network administrators

Active measurement based on the use of common network services is more robust and perhaps more realistic– DNS queries– HTTP requests

Page 7: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Performance Measurement Architectures

There have been projects to create measurement architectures either by deployment at nodes within domains or at the users– NIMI– E2E pIPEs– AMP, Medusa Proxy, Liston Proxy, Network

Weather Service …

Page 8: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI(National Internet Measurement Infrastructure)

Software system for building network measurement infrastructures

Diversely administered Facilitate many kinds of measurements Extensible and Modular

Page 9: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Architecture

Measurement servers (probes)– 2 daemons: nimid and scheduled– Measurement Modules

Page 10: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Architecture

Configuration Point of Contact (CPOC)– Configuration and Control Servers– Several per domain– Delegation of configuration access

Page 11: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Architecture

Measurement Client (MC)– Only ‘user’ point of contact with NIMI system– Measurement requests

Page 12: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Architecture

Data Analysis Client (DAC)– Data Collection– Post-Processing– Run at central location or at MC

Page 13: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Measurement Modules

NIMI has no knowledge of measurements– Plug-ins

Wrapped for a standard API Current Modules

– traceroute, treno, zing, mflect, traffic, ftp

Page 14: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Measurements

Request Received from MC– Access Control List

scheduled creates pending measurement Results sent to DAC by nimid All communications encrypted

Page 15: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Deployment

35 hosts (as of 2001)– Research laboratories and Universities

Georgia Tech

Dead?

Page 16: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Difficulties

Laboratory Conditions– High bandwidth– Dedicated Resources– Not representative of Internet as a whole

Page 17: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Difficulties

Meaningful data for User Perceived measurements– Not widely distributed

Page 18: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Difficulties

Hosts administration difficulties– Tools requiring privileged access– Updates

Page 19: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NIMI Difficulties

Difficult to distribute– What’s in it for me?– Not attractive to average user

Page 20: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

E2E piPEs

End-to-end Performance Improvement Performance Environment System– A framework to indicate performance capabilities

and locate performance problems along the path between two computers connected by the Abilene network

Page 21: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

E2E piPEs Architecture

Page 22: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

E2E piPEs Architecture

Page 23: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

OWAMP

One-Way Active Measurement Protocol: An Internet2 project

A UDP-based protocol to precisely measure network characteristics:

– Loss– Delay– Jitter

http://owamp.internet2.edu/ - Under construction

Page 24: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

E2E piPEs Status

“The initial deployment, which includes the Abilene backbone network and two campuses only, is scheduled for Fall 2003.”

“piPEfitters” are still developing the system – one suggestion is to place PMPs at the end hosts.

Page 25: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Other Tools: Proxy-Based

Liston Proxy– Between browser and the Web– Handles DNS resolution and content requests– Logs information of interest

DNS responsiveness Response time

Page 26: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Proxy-Based Tools

Medusa Proxy– Cool name– Monitors performance

DNS Akamai edge servers vs. origin servers

Page 27: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Proxy-Based Disadvantages

Privacy issues Overhead Limited Scope

Page 28: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Distributed Tools

AMP Network– Distributed physical nodes– High Performance Computing (HPC)

Network measurement, not user-perceived

Page 29: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Distributed Tools Disadvantages

Wide Distribution– Need large amounts of diverse data– How to do it

Updates Security

Page 30: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Applications

Network Weather Service– Predicting network performance for

applications– Can be run by user to predict their

performance

Page 31: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

Applications

Lots– Zing– Ping– IPerf– Traceroute

Page 32: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

NM Applications Disadvantages

Limited Scope Generally Stateless

Page 33: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

User-Perceived Performance Measurement: Why?

Because the Internet was designed following the end-to-end principle, end-to-end performance is ultimately the most meaningful to measure

It is difficult to deploy a measurement architecture in the Internet backbone

Network users see end-to-end performance directly and could be effectively used as monitor points

Page 34: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

User-Perceived Measurement: How?

The infrastructure– NIMI-like plug-in measurement modules– Standardized communication between

components

Page 35: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

User-Perceived Measurement: How?

Distribution– Have to make it something users want to run

Page 36: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

User-Perceived Measurement: How?

Processing– Centralized data collection and post-processing

Page 37: User-Perceived Performance Measurement on the Internet Bill Tice Thomas Hildebrandt CS 6255 November 6, 2003.

References

[1] J.H. Saltzer, D.P. Reed, and D.D. Clark. “End to End Arguments in System Design.” http://web.mit.edu/Saltzer/www/publications/endtoend/endtoend.txt

[2] Vern Paxson, Andrew Adams, and Matt Mathis. “Experiences with NIMI.” In Proceedings of Passive and Active Measurement, 2000. http://citeseer.nj.nec.com/paxson00experiences.html

[3] Internet2. E2E piPEs. http://e2epi.internet2.edu/E2EpiPEs/e2epipe_index.html

[4] Richard Liston and Ellen Zegura. “Using a Proxy to Measure Client-Side Web Performance.” Proceedings of the 6th International Web Caching and Content Distribution Workshop, Boston, MA, June 1999. http://www.cc.gatech.edu/~liston/pubs/proxy_wcw01.ps.gz

Network Weather Service http://www.npaci.edu/envision/v15.2/nws.html


Related Documents