Server-based Characterization and Inference of Internet Performance - PowerPoint PPT Presentation

1 / 29
About This Presentation
Title:

Server-based Characterization and Inference of Internet Performance

Description:

Earthlink. Darn, it's slow! Why is it. so slow? 14. Related Work. MINC (Caceres et al. 1999) ... San Francisco (AT&T) Indonesia (Indo.net) Sprint PacBell in California ... – PowerPoint PPT presentation

Number of Views:13
Avg rating:3.0/5.0
Slides: 30
Provided by: VenkatPad6
Category:

less

Transcript and Presenter's Notes

Title: Server-based Characterization and Inference of Internet Performance


1
Server-based Characterization and Inference of
Internet Performance
  • Venkat Padmanabhan
  • Lili Qiu
  • Helen Wang
  • Microsoft Research
  • UCLA/IPAM Workshop
  • March 2002

2
Outline
  • Overview
  • Server-based characterization of performance
  • Server-based inference of performance
  • Passive Network Tomography
  • Summary and future work

3
Overview
  • Goals
  • characterize end-to-end performance
  • infer characteristics of interior links
  • Approach server-based monitoring
  • passive monitoring ? relatively inexpensive
  • enables large-scale measurements
  • diversity of network paths

4
Web server
ACKs
ACKs
DATA
clients
5
Research Questions
  • Server-based characterization of end-to-end
    performance
  • correlation with topological metrics
  • spatial locality
  • temporal stability
  • Server-based inference of internal link
    characteristics
  • identification of lossy links

6
Related Work
  • Server-based passive measurement
  • 1996 Olympics Web server study (Berkeley, 1997
    1998)
  • characterization of TCP properties (Allman 2000)
  • Active measurement
  • NPD (Paxson 1997)
  • stationarity of Internet path properties (Zhang
    et al. 2001)

7
Experiment Setting
  • Packet sniffer at microsoft.com
  • 550 MHz Pentium III
  • sits on spanning port of Cisco Catalyst 6509
  • packet drop rate lt 0.3
  • traces up to 2 hours long, 20-125 million
    packets, 50-950K clients
  • Traceroute source
  • sits on a separate Microsoft network, but all
    external hops are shared
  • infrequent and in the background

8
Topological Metrics and Loss Rate
Topological distance is a poor predictor of
packet loss rate. All links are not equal ? need
to identify the lossy links
9
Spatial Locality
  • Do clients in the same cluster see similar loss
    rates?
  • Loss rate is quantized into buckets
  • 0-0.5, 0.5-2, 2-5, 5-10, 10-20, 20
  • suggested by Zhang et al. (IMW 2002)
  • Focus on lossy clusters
  • average loss rate gt 5

Spatial locality ? there may be shared cause for
packet loss
10
Temporal Stability
  • Loss rate again quantized into buckets
  • Metric of interest stability period (i.e., time
    until transition into new bucket)
  • Median stability period 10 minutes
  • Consistent with previous findings based on active
    measurements

11
Putting it all together
  • All links are not equal ? need to identify the
    lossy links
  • Spatial locality of packet loss rate ? lossy
    links may well be shared
  • Temporal stability ? worthwhile to try and
    identify the lossy links

12
Passive Network Tomography
  • Goal determine characteristics of internal
    network links using end-to-end, passive
    measurements
  • We focus on the link loss rate metric
  • primary goal identifying lossy links
  • Why is this interesting?
  • locating trouble spots in the network
  • keeping tabs on your ISP
  • server placement and server selection

13
Web server
Why is it so slow?
ATT
Sprint
CW
Earthlink
UUNET
Darn, its slow!
AOL
Qwest
14
Related Work
  • MINC (Caceres et al. 1999)
  • multicast-based active probing
  • Striped unicast (Duffield et al. 2001)
  • unicast-based active probing
  • Passive measurement (Coates et al. 2002)
  • look for back-to-back packets
  • Shared bottleneck detection
  • Padmanabhan 1999, Rubenstein et al. 2000, Katabi
    et al. 2001

15
Active Network Tomography
S
A
B
Striped unicast probes
Multicast probes
16
Problem Formulation
server
Collapse linear chains into virtual
links (1-l1)(1-l2)(1-l4) (1-p1) (1-l1)(1-l2)
(1-l5) (1-p2) (1-l1)(1-l3)(1-l8)
(1-p5) Under-constrained system of equations
l1
l3
l2
l8
l7
l6
l4
l5
p1
p2
p3
p4
p5
clients
17
1 Random Sampling
  • Randomly sample the solution space
  • Repeat this several times
  • Draw conclusions based on overall statistics
  • How to do random sampling?
  • determine loss rate bound for each link using
    best downstream client
  • iterate over all links
  • pick loss rate at random within bounds
  • update bounds for other links
  • Problem little tolerance for estimation error

server
l1
l3
l2
l8
l7
l6
l4
l5
p1
p2
p3
p4
p5
clients
18
2 Linear Optimization
  • Goals
  • Parsimonious explanation
  • Robust to estimation error
  • Li log(1/(1-li)), Pj log(1/(1-pj))
  • minimize ?Li ?Sj
  • L1L2L4 S1 P1
  • L1L2L5 S2 P2
  • L1L3L8 S5 P5
  • Li gt 0
  • Can be turned into a linear program

server
l1
l3
l2
l8
l7
l6
l4
l5
p1
p2
p3
p4
p5
clients
19
3 Bayesian Inference
  • Basics
  • D observed data
  • sj packets successfully sent to client j
  • fj packets that client j fails to receive
  • T unknown model parameters
  • li packet loss rate of link i
  • Goal determine the posterior P(TD)
  • inference is based on loss events, not loss rates
  • Bayes theorem
  • P(TD) P(DT)P(T)/?P(DT)P(T)dT
  • hard to compute since T is multidimensional

server
l1
l3
l2
l8
l7
l6
l4
l5
(s1,f1)
(s2,f2)
(s3,f3)
(s4,f4)
(s5,f5)
clients
20
Gibbs Sampling
  • Markov Chain Monte Carlo (MCMC)
  • construct a Markov chain whose stationary
    distribution is P(TD)
  • Gibbs Sampling defines the transition kernel
  • start with an arbitrary initial assignment of li
  • consider each link i in turn
  • compute P(liD) assuming lj is fixed for j?i
  • draw sample from P(liD) and update li
  • after burn-in period, we obtain samples from the
    posterior P(TD)

21
Gibbs Sampling Algorithm
  • 1) Initialize link loss rates arbitrarily
  • 2) For j 1 burn-in for each link i
    compute P(liD, li) where li is
    loss rate of link i, and li ?j?i lj
  • 3) For j 1 realSamples for each link
    i compute P(liD, li)
  • Use all the samples obtained at step 3 to
    approximate P(?D)

22
Experimental Evaluation
  • Simulation experiments
  • Internet traffic traces

23
Simulation Experiments
  • Advantage no uncertainty about link loss rate
  • Methodology
  • Topologies used
  • randomly-generated 20 - 3000 nodes, max degree
    5-50
  • real topology obtained by tracing paths to
    microsoft.com clients
  • randomly-generated packet loss events at each
    link
  • a fraction f of the links are good, and the rest
    are bad
  • LM1 good links 0 1, bad links 5 10
  • LM2 good links 0 1, bad links 1 100
  • Goodness metrics
  • Coverage correctly inferred lossy links
  • False positives incorrectly inferred lossy
    links

24
Simulation Results
25
Simulation Results
26
Simulation Results
High confidence in top few inferences
27
Trade-off
Techniques Coverage False Positive Computation
Random sampling High High Low
LP Medium Low Medium
Gibbs sampling High Low High
28
Internet Traffic Traces
  • Challenge validation
  • Divide client traces into two tomography set and
    validation set
  • Tomography data set gt loss inference
  • Validation set gt check if clients downstream of
    the inferred lossy links experience high loss
  • Results
  • false positive rate is between 5 30
  • likely candidates for lossy links
  • links crossing an inter-AS boundary
  • links having a large delay (e.g. transcontinental
    links)
  • links that terminate at clients
  • example lossy links
  • San Francisco (ATT) ? Indonesia (Indo.net)
  • Sprint ? PacBell in California
  • Moscow ? Tyumen, Siberia (Sovam Teleport)

29
Summary
  • Poor correlation between topological metrics
    performance
  • Significant spatial locality and temporal
    stability
  • Passive network tomography is feasible
  • Tradeoff between computational cost and accuracy
  • Future directions
  • real-time inference
  • selective active probing
  • Acknowledgements
  • MSR Dimitris Achlioptas, Christian Borgs,
    Jennifer Chayes, David Heckerman, Chris Meek,
    David Wilson
  • Infrastructure Rob Emanuel, Scott Hogan
  • http//www.research.microsoft.com/padmanab
Write a Comment
User Comments (0)
About PowerShow.com