1 Network Topology Measurement Yang Chen CS 8803.

1

Network Topology Measurement

Yang Chen

CS 8803

2

Outline

• Big Picture

• ISP Topology Measurement

• Statistical Results

• Problems & Solutions

3

Heuristics for Internet Map Discovery

R. Govindan and H. Tangmunarunkit

INFOCOM 2000

4

Why do we need the topology?

• Understand the macroscopic properties of the Internet physical structure

• Network management

• Topology-aware algorithms

• Simulation and topology generation tools

5

On-going efforts

• CAIDA Skitter • Router View

6

Fundamental: traceroute

Prober sends packets with successively increased TTL.A router responds with ICMP time exceeded when the probe is with TTL=1

7

Fundamental: traceroute

Geographic info can help on building up the topology.

* Data from http://www.linkwan.com/vr/

8

Fundamental: Tree => map

1)Source routing2)Multiple Vantage points

9

Address scan space

• BGP tables• Route Table• Database• Informed Random Address Probing

– A response from some IP address is considered as a sign that some prefix P of A must contain addressable nodes;

– If P is an addressable prefix, the neighboring prefixes of P are also considered as possibly addressable. (128.8/16 and 128.10/16 are neighbors of 128.9/16)

10

Some results

• 150,000 interfaces and nearly 200,000 links• Findings related to source route

– Simulation demonstrated that In relatively sparse random networks, a few source route capable nodes (< 5%) are sufficient to discover 90% of the links. In fact, there are 8% routers support source route.

– Source route discovered links do not skew the qualitative conclusion on the network statistics.

11

For example: degree distribution

Similar observation on hop-pair distribution

12

Measuring ISP Topologies with Rocketfuel

N.Spring, R. Mahajan and D. Wetherall

ACM Sigcomm 2002

13

ISP network infrastructure

Access Router

Access Router

Backbone Router

Backbone Link

14

ISP topology measurement

• An old story: the blinds and the elephant

ISP

Traceroute

15

ISP topology measurement

Traceroute Server

16

Focusing on one ISP – Directed probingNetwork Next Hop M/LP/Weight Path * 192.9.9.0 204.212.44.128 0 234 266 237 3561 701 90 i * 205.238.48.3 0 2914 1 90 i * 144.228.240.93 0 1239 701 90 i * 204.70.4.89 0 3561 1 90 i * 194.68.130.254 0 5459 5413 1 90 i *> 134.24.127.3 0 1740 701 90 i * 202.232.1.8 0 2497 701 90 i * 158.43.133.48 0 1849 702 701 90 i * 131.103.20.49 0 1225 2548 1 90 i

blackrose.org (Ann Arbor) 204.212.44.128 through AS234 Verio (MAE-WEST) 205.238.48.3 through AS2914 Sprint (Stockton) 144.228.240.93 through AS1239 MCI (San Francisco) 204.70.4.89 through AS3561 LINX (London) 194.68.130.254 through AS5459 CERFnet (San Diego) 134.24.127.3 through AS1740 IIJ (Japan) 202.232.1.8 through AS2497 PIPEX (London) 158.43.133.48 through AS1849 IAGnet (Chicago) 131.103.20.49 through AS1225

* BGP table source: RouteView project

17

Focusing on one ISP – Directed probing

• Traceroutes to dependent prefixes: All traceroutes to these prefixes from any vantage point should transit the ISP. Dependent prefixes can be readily identified from the BGP table. All AS-paths for the prefix would contain the number of the AS being mapped.

• Traceroutes from insiders: We call a traceroute server located in a dependent prefix an insider. Traceroutes from insiders to any prefix should transit the ISP.

• Traceroutes that are likely to transit the ISP based on some AS-path are called up/down traces.

18

Path/Query reduction

Share Ingress Share egress

Same next-hop AS number

19

Impacts of directed probing

1) Fraction of useful but pruned traces from 0.1 to 7%2) Unnecessary traces around 6% over all the ISPs

*Comparison based on Skitter data

20

Impacts of ingress reduction

Overall, ingress reduction keeps only 12% of the traces chosen by directed probing.

The number of vantage points that share an ingress by rank

21

Impacts of egress reduction

The number of dependent prefixes that share an egress by rank

Overall, egress reduction keeps only 18% of the Dependent prefix traceschosen by directed probing.

22

Impacts of next-hop reduction

Overall, Next-hop AS reduction Reduces the number of traces to 5% of those chosen by directed probing.

23

POP sizes analysis

24

Power Law

• Complementary cumulative distribution function (CCDF) P(X>x)

• Pareto Distribution

• Power Law

k

x

xxXP

min

)( kxxXP )(

)ln()ln( xCy

25

Router degree distribution

26

Peering structure

27

Difficulties in topology discovery

• Shared media

• Backup links

• Router Identification and annotation

• Alias resolution

• Completeness Validation

Currently, none of them is completely solved!

28

POP hierarchy

Naming convention, DNS information and neighbor inferring

29

Backbone topology

AT&T

Level 3

30

Alias Problem

OR

31

Alias: is it a big deal?

32

Alias resolution

• Send a packet with unreachable port to certain interfaces which are possible alias. The corresponding ICMP port unreachable response will contain the source address.

• IP identifier

33

Completeness validation

• Comparison with Router Views

• Comparison with Skitter

• IP address space– Search prefixes of ISP’s address space for

additional IP addresses

• Validation with ISPs– Is “Good” enough?

34

In Search of Path Diversity in ISP Networks

P. Teixeira, K. Marzullo, S. Savage and G. M. Voelker

IMC 2003

35

Real metric instead of counting links

• Path diversity– Metric that reflects the number of routes

available between two points in the network

• An extreme example

36

Real topology speaks

Inter-PoP Path diversity in the Sprint Network

Inter-PoP Path diversity inferred by Rocketfuel

37

Take a closer look

38

Inaccuracy introduced during probing

• Lack of vantage points– How many points are sufficient?

• Incomplete traceroutes– What can we do if ISP turns off traceroute fun

ctionality?

• Changes in the path of a probe

• Incorrect DNS record

39

Inaccuracy from processing probed links

• Alias Resolution• Adding reverse links

Missed and added links in Rocketfuel PoP topology relative to the number of links in the Sprintreal topology

40

Questions?