Observations from Routerlevel Traces

1
Observations from Router-level Traces

• Lisa Amini
• IBM T. J. Watson Research Center
• Joint with Henning Schulzrinne, Aurel Lazar
• Columbia University

2
Context

• Near-term issues facing service providers for
  Web-facing applications
• Mirrored servers
• where to place servers?
• which network access providers?
• how many connection points?
• how many servers to deploy?
• where to direct clients?
• End-to-end routing behavior/delay vs.
  connectivity
• AS level focus

3
Beyond Connectivity

• Inter-domain (AS) routing tables
• Aggregation
• Policy-based routing
• Oregon Route Server

Transit Networks
B
A
E
D
C
Autonomous Systems
Stub Networks
4
Traceroute

• Router-level end-to-end probing
• Traceroute.org website
• AS lookup via Routing Arbiter Database (RADB)
• Round trip time (RTT)
• Loose source-routing
• Artifacts

5
D1 Dataset

• 189 sites
• Random pairings
• Forward and reverse paths
• Poisson arrivals
• Mean time between probes 10 minutes
• 220,551 measurements
• 5 days
• 1/3 US sites, 2/3 non-US (31 countries)

• Zhang, Duffield, Paxson, Shenker

6
Router-level Path Length

• mean16.45, std. dev.4.39

7
AS Path Length

• mean6.47, std. dev.2.33

8
AS Degree Frequency

• Faloutsos3 -0.97 (or higher) correlation
  coefficient
• 98 of nodes represented

0.97 correlation coefficient required discarding
31 of nodes
9
Which is correct?
10
AS Frequency
0.97 correlation coefficient required discarding
10 of nodes
11
Response Time Prediction

• Does path length predict delay?

mean RTT263ms Correlation coefficient 0.31
Correlation coefficient 0.27
12
AS Properties

• Can we predict delay based on AS path properties?
• Ranked each AS according to
• AS edge degree
• AS frequency
• Calculated mean RTT per path length
• Grouped by top 5, 6-10, 10-20 ASs

13
Influence of Path Properties
High edge degree AS?
14
High Frequency AS?
15
High Edge Degree AS?
High edge degree AS in 2 AS hops?
16
Backbone AS?
17
Backbone AS in 2 AS hops?
18
AS Affinity?
19
Route Asymmetry

• Paxson, 1995
• Path(A,B) ? Path(B,A)
• Issues
• Ping triangulation
• Congestion Avoidance
• Internet mapping

A
B
20
AS Hop Differences
11755 paired, unique routes 57 routes were
AS-path asymmetric Compare with 30 based on
1995 data 74 asymmetric from first AS hop
Number of Routes
Number of AS hop differences
21
Traceroute Issues

• AS assignment
• Chang, Jamin, Willinger

AS6
AS5
AS7
AS1
AS2
AS3
AS4
22
BGP AS Path

• Can we predict forward and reverse end-to-end
  metrics from BGP AS_PATH?
• Looking Glass Probing
• 92 Sites
• 8372 unique path measurements
• 2202 fully paired (BGP forward and reverse,
  traceroute forward and reverse)

23
AS Hop Differences
47 of forward paths correctly predicted by
reverse traceroute 49 of forward paths
correctly predicted by reverse BGP AS_PATH 69
of forward paths correctly predicted by forward
BGP AS_PATH 34 asymmetry between
forward/reverse BGP AS_PATH
24
Summary

• BGP routing tables provide complete view from
  single location.
• Aggregation
• Filtering
• End-to-end probing from points throughout network
  can provide insights beyond connectivity
• Limited view of connectivity
• Traceroute issues with noise, node assignment
• BGP AS_PATH inaccurate as path predictor

25
Discard Criteria

• Origin traceroute server not responding
• Incomplete traceroute output
• Internal use only node address (e.g., 10.x.x.x,
  172.16.x.x-172.32.x.x ranges)
• Route did note terminate in target AS
• Intermediate node did not respond to ICMP echo
• No matching reverse probe for same time period

26
What can we conclude?

• Results are for RTT only
• Negative results for
• Path Length
• AS degree, AS frequency, Backbone, hops from
  origin
• High delay as result of transient conditions
  (congestion)