A Measurement Study of Internet Delay Asymmetry

1
A Measurement Study of Internet Delay Asymmetry

• Abhinav Pathak Purdue University
• Himabindu Pucha Purdue University
• Ying Zhang University of Michigan
• Y. Charlie Hu Purdue University
• Z. Morley Mao University of Michigan

2
RTT FWD REV
FWD
REV
RTT is easy to measure FWD REV RTT
3
De Facto Internet Delay Metric RTT

• Round Trip Time (RTT) is a widely used network
  metric in server/peer selection
• CDN
• Select closest replica
• Overlay multicast
• Choose a suitable parent/child in the tree
• Internet distance prediction
• Calculate proximity from a landmark

4
Often Times, One-Way Delay is More Relevant

• Examples scenarios
• Multicast streaming applications
• Real-time interactive applications
• Multi-player games
• Internet distance prediction
• Understand routing performance

5
But OWD Measurement is Hard

• OWD measurement requires
• Access to both ends
• No daemon in OS
• Strict time synchronization
• Result OWD is approximated as half of RTT

• Conventional Wisdom
• Delay is symmetric
• FWD REV

6
Outline Questions to Answer

• Does delay asymmetry exist?
• What are reasons for delay asymmetry?
• How dynamic is delay asymmetry?

7
Tools and Testbed

• Tools
• Owping Implements one way active measurement
  protocol (RFC 4656)
• Paris-Traceroute
• Testbed
• Planetlab
• 180 GREN, 25 Commercial nodes
• Trace collection 10 days in April 2007

8
Owping Relies on Time Synchronization

• NTP Two parameters
• Clock drift
• Relative error to a NTP server
• Applied to timestamp on each host
• Error estimate
• Added up to report overall error estimate

9
How Does Owping Work
Server
Client
Connection setup
owampd (resource broker)
owping Control
fork
fork
Request Results
owampd (control)
owping Test Endpoint
fork
OWD Test packets
owampd Test Endpoint
Source http//e2epi.internet2.edu/owamp/
10
NTP Drift and Error Estimate
40 of nodes have Error Estimate gt 20 ms
11
Trace Pruning

• Remove trace if
• NTP error estimate gt 10ms
• Leaves 82 GREN nodes and 12 commercial nodes
• Sum of NTP error estimate gt 3 of RTT for a node
  pair
• Leaves primarily long distant routes

12
GREN Vs Commercial nodes

• Planetlab mostly contains GREN nodes
• GREN Global Research and Education Network
• GREN to GREN (G2G) path properties are different
  from Commercial to Commercial (C2C)
• G2C and C2G properties are close to C2C
• - On the Impact of Research Network Based
  Testbeds on Wide-area Experiments Pucha et.
  al. IMC06
• We consider G2C-C2G-C2C paths only

13
Delay Asymmetry FWD/RTT
Delay fraction for all node pairs
14
Delay Asymmetry Absolute Values
RTT 150 ms FWD 100 ms REV 50 ms
Y (1/2) X (conventional wisdom)
15
Questions to answer

• Does delay asymmetry exist?
• Yes
• What are reasons for delay asymmetry?
• How dynamic is delay asymmetry?

16
Reasons for Asymmetry in OWD

• What are reasons for delay asymmetry
• Temporary congestion in forward or reverse path
• Transient events
• Forward and reverse paths are different
• Path Asymmetry
• Can we correlate delay and path asymmetry?
• Measure path using traceroute
• Need a metric to quantify path asymmetry

17
Metric for Path Asymmetry Path Similarity
Coefficient

• AS level path asymmetry
• A All ASes in forward path
• B All ASes in reverse path
• AS path similarity coefficient A?B / A?B
• Router level path asymmetry
• A All routers in forward path
• B All routers in reverse path
• Router path similarity coefficient A?B /
  A?B

18
Path Asymmetry
20 paths have Router level Similarity coeff. gt
0.6
70 paths have AS level Similarity coeff. gt 0.6
19
Delay Asymmetry Vs Router Level Path Similarity
Coefficient
Delay fraction fluctuatesbetween 0.3 to 0.7
Delay fraction 0.5 when router-level
asymmetry nears unity
20
Questions to answer

• Does delay asymmetry exist?
• Yes
• What are reasons for delay asymmetry?
• Observed good correlation with path asymmetry
• How dynamic is delay asymmetry?

21
Dynamics of Delay Asymmetry
22
Correlating FWD change and RTT change
D
C
B
A
23
Correlating Routing Events and Delay Asymmetry
Change

• Measurement setup
• Traceroute and owping all nodes
• Repeat after every 20 minutes
• Calculate path change
• Inter AS / Intra AS
• Measure reverse path at the same time

24
Correlation Results
80 of Inter AS path change cause FWD to change
by lt 20 ms
80 of Intra AS path change cause FWD to change
by lt 10 ms
25
Delay Dynamics Observations

• Intra AS path change
• More frequent to observe
• Most of the times path changes in both directions
• Fwd Rev delays change simultaneously
• Inter AS path change
• Less frequent
• Two cases
• Only fwd AS path changes
• Both fwd and rev AS paths change
• Delay change is larger in magnitude

26
Questions to answer

• Does there exists delay asymmetry?
• Yes
• What are reasons for delay asymmetry?
• Observed good correlation with path asymmetry
• How dynamic is delay asymmetry?
• Depends on inter/intra AS path change

27
Summary

• Methodology
• Measuring OWD
• Pruning strategy
• Based on error estimates provided by NTP
• Measurement results
• Considerable levels of delay asymmetry
• Delay asymmetry is dynamic
• RTT could change due to FWD change or REV change
  or both
• Analyzing the cause
• Weak correlation between router level asymmetry
  and delay asymmetry
• Delay asymmetry dynamics
• Inter/Intra AS route change effects delay
  asymmetry differently

28
Thank You

• Questions?