Download ECE 794 Routing in Wired and Wireless Networks

End-to-End Routing Behavior in
the Internet
Vern Paxson
Presented by Sankalp Kohli and Patrick Wong
Idea


Previous studies of routing protocols explain
routing behavior only qualitatively
Use end-to-end measurement to determine:



Route pathologies
Route stability
Route symmetry
Definitions


Virtual path: network level abstraction of
“direct link” between two hosts. At the
network layer, it is realized by a single
route.
Autonomous system (AS): collection of
routers and hosts controlled by a single
administrative entity.
Routing Protocols


Interior Gateway Protocol (IGP): routing
protocol for entities within the same AS.
Border Gateway Protocol (BGP): for
inter-AS routing. Each AS keeps a routing
table with reachable hosts and
corresponding costs. Upon detected
changes, only affected part of routing
table is shared.
Methodology

Run Network Probes Daemon (NPD) on a
number of Internet sites (37)
Methodology


Key property (N2 scale)
2
 Use N sites to measure N Internet paths
Each NPD site periodically measure the route to
another NPD site, by using traceroute
Methodology

Two sets of experiments


D1 – measure each virtual path between two NPD’s
with a mean interval of 1-2 days, Nov-Dec 1994 –
maintains the average load of one measurement per
two hours
D2 – measure each virtual path using a bimodal
distribution inter-measurement interval, Nov-Dec
1995




60% with mean of 2 hours (burst)
40% with mean of 2.75 days (to measure longer term
behavior)
Measurements in D2 were paired
Measure A=>B and then B<= A
Methodology

Links traversed during D1 and D2
Methodology

Exponential sampling



Only 37 sites?!



Unbiased sampling – measures instantaneous signal with equal
probability
PASTA principle – Poisson Arrivals See Time Averages
Argue that sampled AS’s are on half of the Internet routes
If we weight each AS by its likelihood of occurring in an AS
path, then the AS’s sampled by routes we measured comprised
about half of the Internet AS’s by weight
Confidence intervals for probability that an event
occurs
Limitations



Just a small subset of Internet paths
Just two points at a time
Difficult to say why has something
happened, only with end-to-end
measurements


Possible fixes: something more robust than
traceroute or multiple measurement requests
5%-8% of time couldn’t connect to NPD’s


Introduces bias toward underestimation
D2 Pairing helps correct the underestimation
Routing Pathologies





Persistent routing loops
Temporary routing loops
Erroneous routing
Connectivity altered mid-stream
Temporary outages (> 30 sec)
Routing Loops & Erroneous Routing

Routing Loops:




Persistent routing loops (10 in D1 and 50 in D2)



Forwarding Loop
Information Loop
Traceroute Loop
Several hours long (e.g., > 10 hours)
It is not confined to single router
Erroneous routing (one in D1)

A route UK=>USA goes through Israel
Route Changes

Connectivity change in mid-stream (10 in D1
and 155 in D2)



Route changes during measurements
Recovering bimodal: (1) 100’s msec to seconds; (2)
order of minutes
Route fluttering


Rapid route oscillation
Very little fluttering was seen and only happened
within the AS.
Example of Route Fluttering
wustl (St. Loutis) to umann(Mannheim, Germany)
Solid: 17 hops, dotted: 29 hops
Problems with Fluttering


Asymmetry
Path properties difficult to predict


This confuses RTT estimation in TCP, may trigger
false retransmission timeouts
Packet reordering

TCP receiver generates DUPACK’s, may trigger
spurious fast retransmits
Infrastructure Failures


“host unreachable” from router well inside
the network.
0.21% in D1, estimate availability rate 99.8%.
This dropped to 99.5% in D2.
NPD’s unreachable due to many
hops (6 in D2)


Unreachable more than 30 hops
Path length not necessary correlated with
distance


1500 km end-to-end route of 3 hops
3 km (MIT – Harvard) end-to-end route of 11
hops
Temporary Outages


Sequence of traceroute packets lost
due to temporary loss of connectivity or
heavy congestion.
In D1(D2), 55% (43%) had 0 losses, 44%
(55%) had 1 to 5 losses, and 0.96%
(2.2%) had 6 or more.
Distribution of Long Outages (>30
sec )
Time-of-Day patterns


Temporary outages: min (0.4%) occurred
during the 1:00-2:00 h, max (8.0%) during the
15:00-16:00 h.
Infrastructure failures: min (1.2%) at 9:0010:00 h, peak during 15:00-16:00 h.
Pathology Summary
Routing Stability

Two definitions of stability:

Prevalence: likelihood to observe a
particular route


Steady state probability that a virtual path at an
arbitrary point in time uses a particular route
Persistence: how long a route remains
unchanged

Affects utility of storing state in routers
Routing Stability

Routing Prevalence


Let r be the steady-state probability that a
VP uses route r at an arbitrary time, and k
the number of times we observe the route.
Due to PASTA, an unbiased estimator of r
can be computed as  r  k n
The prevalence of the dominant route is
analyzed.

r

Routing Prevalence

In general, Internet paths are strongly
dominated by a single route, especially if
observed at higher granularity.
Routing Persistence



The notion of persistence depends on what is
deemed persistent.
A series of measurements are undertaken to
classify routes according to their alternation
frequency.
Conclusion: routing changes occur over a wide
range of time scales, i.e., from minutes to days
Routing Symmetry

Sources of Routing Asymmetry



Link cost metrics
“hot potato” routing problem due to the
competing providers.
“cold potato”
Routing Symmetry

Analysis of Routing Symmetry



Measurements were paired to ensure that an
asymmetry is actually being captured.
Asymmetry is quite common (49% on a city
granularity, 30% AS granularity).
Size of Asymmetries

Majority confined to one hop (one city or AS)
Summary




Pathologies doubled during 1995
Asymmetry is quite common
Paths heavily dominated by a single route
Over 2/3 of Internet paths are reasonable
stable (> days). The other 1/3 varies over
many time scales