Pushing up User Performance

Slides: Pushing up
User Performance

[Start Here (html)] [Slide Sorter (html)]


Page 1: Pushing up

Page 2: Pushing up performance

Page 3: The Wizard Gap

Page 4: The Wizard Gap

Page 5: TCP "tuning" requires experts

Page 6: TCP tuning is painful debugging

Page 7: Web100

Page 8: When there is a problem, just ask TCP

Page 9: TCP triage instrument

Page 10: Diagnosing path bottlenecks

Page 11: Diagnosing path bugs

Page 12: Localizing path problems

Page 13: Sender and receiver bottlenecks

Page 14: Web100 Technical Summary

Page 15: Current Web100 status

Page 16: end of part 1

Page 17: Implications to users

Page 18: How well are users doing today?

Page 19: We need independent measures of

Page 20: Earlier plan

Page 21: The current tool transition

Page 22: Passive measurements

Page 23: Window size measurements

Page 24: Observed window sizes

Page 25: Observed window sizes

Page 26: Receiver window sizes

Page 27: Receiver window sizes

Page 28: end of part 2

Page 29: Implications to the network

Page 30: Danger - new load levels

Page 31: Why not before Web100?

Page 32: Problems

Page 33: No deployed queue management

Page 34: No deployed QoS

Page 35: Pervasive broken link layers

Page 36: No models for traffic sharing

Page 37: Shared gigabit problem

Page 38: No SLA quantification

Page 39: New load levels

Page 40: The common theme

Generated by MagicPoint