Performance%20Limitations%20of%20ADSL%20Users:%20A%20Case%20Study

1
Performance Limitations of ADSL UsersA Case
Study

• Matti Siekkinen, University of Oslo
• Denis Collange, France Télécom RD
• Guillaume Urvoy-Keller, Ernst W. Biersack,
• Institut Eurecom
• PAM
• April 6, 2007

2
Outline

• Introduction
• Motivation
• Techniques for root cause analysis of TCP
  throughput
• Measurement setup
• Analysis results
• Conclusions

3
Introduction

• What?
• Analyzed 24h packet trace from France Telecoms
  ADSL access network
• Studied throughput limitations experienced by
  clients
• Why?
• Knowing throughput limitations (performance) is
  useful
• ISPs want satisfied clients
• Need to know whats going on before things can be
  improved
• How?
• Root Cause Analysis of TCP Throughput
• Analysis and inference of the reasons that
  prevent a given TCP connection from achieving a
  higher throughput.
• Passive traffic analysis
• Why TCP?
• TCP typically over 90 of all traffic

4
Background

• On the characteristics and origins of Internet
  flow rates by Zhang et al. (SIGCOMM 2002)
• Pioneering research work
• Congestion is not always the cause for throughput
  limitations

5
Limitation Causes for TCP Throughput

• Application
• The application does not even attempt to use all
  network resources
• E.g. streaming applications and bursty
  applications (Web browsing)
• Transport layer
• TCP receiver
• Receiver advertized window limits the rate
• max amount of outstanding bytes min(cwnd,rwnd)
• Flow control
• Configuration issue
• default receiver advertized window is set too low
• window scaling is not enabled
• TCP protocol
• Ramp-up period in slow start and congestion
  avoidance
• Network layer
• Congestion at a bottleneck link

6
Measurement Setup
Internet
access network
collect network

• Two pcap probes here

• 24 hours of traffic on March 10, 2006
• Passively capture all TCP/IP headers analyze
  offline
• 290 GB of TCP traffic
• 64 downstream, 36 upstream
• Observed packets from 3000 clients, analyze only
  1335
• Excluded clients did not generate enough traffic
  for RCA

7
Warming up

• Connections
• Size distribution highly skewed
• Use only 1 of the flows for RCA
• Represent gt 85 of all traffic
• Clients
• Heavy-hitters 15 of clients generate 85-90 of
  traffic (up down)
• Low access link utilization

8
Results of Limitation Analysis
contains most bytes
contains some bytes

• Few active clients overall
• Application limitation dominates
• Network limitation by distant bottleneck also
  experienced

9
Application analysisApplication limited traffic
other
eDonkey

• Quite stable and symmetric volumes
• Vast majority of all traffic
• eDonkey and other dominate

P2P
10
Application analysisSaturated access link

• No recognized P2P
• Asymmetric port 80/8080 downstream
• Real Web traffic?

11
Impact of Limitation Causes

• How far from optimal (access link saturation) are
  we?
• Main observations
• Very low downlink utilization for application
  limited traffic
• Utilization lt 20 during 65 of application
  limited periods of traffic
• Uplink utilization lt 50 during most of
  application and network limited uploads

12
Connecting the evidence

• Most clients performance limited by applications
• Very low link utilizations for application
  limited traffic
• Most of application limited traffic seems to be
  P2P
• Peers often have asymmetric uplink and downlink
  capacities
• P2P applications/users enforce upload rate limits
• ? Poor aggregate download performance

uploading clients
Internet
downloading client
Low downlinkutilization
Low uplink capacityrate limiter
13
Conclusions

• Analyzed 24h packet trace from France Telecoms
  ADSL access network
• Studied throughput limitations experienced by
  clients
• Majority of clients mostly throughput limited by
  applications
• P2P clients throttle upload rate
• Too much?
• Asymmetric link capacities
• Impact and implications
• ISP traffic is mostly application limited traffic
• Things can change dramatically with
• More intelligent P2P clients
• Caches

14
For the future

• Play with time scale
• Extended case study on ADSL clients
• We saw a day, what about a week?
• Could we do things on-line?
• Improving RCA techniques
• Short connections
• Non FIFO traffic (e.g. wireless)

15
Thank you for your attention
16
Backup slides
17
Our approach (suppress)

• Analyze passive traffic measurements
• Capture and store all TCP/IP headers, analyze
  later off-line
• Observe traffic only at a single measurement
  point
• Applicable in diverse situations
• E.g. at the edge of an ISPs network
• Know all about clients downloads and uploads
• Bidirectional packet traces
• Connection level analysis

18
Scope (suppress)

• Study long lived TCP connections
• Short connections are another topic
• Dominated by slow start?
• Assume FIFO scheduling
• Necessary for link capacity estimations with
  packet dispersion techniques
• Reasonable assumption for most traffic
• May not hold for cable modem and 802.11 access
  networks

19
Warming up

• Applications
• Port based
• identification
• Connections
• Size distribution highly skewed
• Use only 1 of them for RCA
• Represent gt 85 of all traffic
• Clients
• Heavy-hitters 15 of clients generate 85-90 of
  traffic (up down)
• Low access link utilization
• Why?

gt5 of traffic each
20
Client-level root cause analysis

• Limitation causes for clients
• Application
• Saturated access link
• Network limitation due to distant bottleneck link
• TCP configuration

• Connection-level RCA
• ALPs
• network limited BTPs during which utilization gt
  90
• network limited BTPs during which utilization lt
  90
• download (local problem) BTPs limited by TCP
  layer

• Extend the InTraBase framework

21
Results of Limitation Analysis
contains most bytes
similar
contains some bytes

• Few active clients overall
• Application limitation dominates
• Network limitation by distant bottleneck also
  experienced

22
Application analysisDistant bottleneck link

• Diverse mixture
• Cause is not necessarily due to clients behavior

23
Impact of Limitation Causes

• How far from optimal (access link saturation) are
  we?
• Main observations
• Uplink utilization lt 50 during most of
  application and network limited uploads
• Very low downlink utilization for application
  limited traffic
• Utilization lt 20 during 65 of ALPs

24
Impact of Limitation Causes
How far from optimal (access link saturation) are
we?
upstream
downstream

• Very low downlink utilization for application
  limited traffic