M.Sc. seminar about Internet Measurement Presentation in English You can watch the video at: http://www.aparat.com/v/8pcO0

1. Internet Traffic Measurement
Amir Hossein Mandegar
Dr. B. Akbari
September 2011
Computer Engineering and IT Department

2. Internet Traffic Measurement 2
Outline
 Why ?
 Tools
 Challenges
 Applications

3. Internet Traffic Measurement 3
Why Measure ?
 Although Internet works, it is far from being ideal
 Measurements of various aspects of it will:
 Help us to better understand why it works the way it does
 Help us to diagnose known problems and lead us one step
closer to their solutions
 Help us to design new features that the Internet should
provide to enable next-generation application requirements
Simply put, “Internet Measurements is key to the
design of the next-generation Internet”

4. Internet Traffic Measurement 4
What to Measure ?
 Physical Properties
 Devices (routers, NAT boxes, firewalls, switches),
Links (wired, wireless)
 Topology Properties
 Various levels – Autonomous Systems (AS),
Points of Presence (PoP), Routers, Interfaces
 Traffic Properties
 Delays (Transmission, Propagation, Queuing,
Processing etc.), Losses, Throughput, Jitter

5. Internet Traffic Measurement 5
Outline
 Why ?
 Tools
 Challenges
 Applications

6. Internet Traffic Measurement 6
Measurement Tools
 Active Measurement
 Passive Measurement
 Fused/Combined Measurement
 Inference Measurement
 Others

7. Internet Traffic Measurement 7
Active Measurement Tools
 Methods that involve adding traffic to the network for the
purposes of measurement
Ping: Sends ICMP ECHO_REQUEST and captures ECHO_REPLY
 Useful for measuring RTTs
 Only sender needs to be under experiment control
Traceroute: Ping nodes with incremental TTL from one
 Find Hops between source and destination node
 Only sender needs to be under experiment control
 There is some care about the result

8. Internet Traffic Measurement 8
Active Measurement Load
 Active Measurement inserts considerable load on
network links if attempting a large-scale topology
discovery
 Optimizations reduce this load considerably
 If single source is used, instead of going from source to
destination, a better approach is to retrace from destination
to source
 If multiple sources and multiple destinations are used,
sharing information among these would bring download
considerably

9. Internet Traffic Measurement 9
Passive Measurement
 Capture traffic generated by other users and
applications
 Routeview collects BGP views (routing tables) from
a large set of ASes
 OSPF LSAs can processed to generate router
graphs within an AS

10. Internet Traffic Measurement 10
Fused Measurement
 Active Measurement +
 Passive Measurement +
 Fused Measurement mixed method to use
benefits of each method.
 Less Traffic Load
 Less Required Storage
 More information for decision

11. Internet Traffic Measurement 11
Inference Measurment
 Measurement Limitations
 Direct access impossible
 Topology and link out of reach
 How to solve ?
 End-to-End Measurement
 Tomography: process of inferring network topology, delays,
packet losses etc. using only end-to-end measurements

12. Internet Traffic Measurement 12
Outline
 Why ?
 Tools
 Challenges
 Applications

13. Internet Traffic Measurement 13
Measurement Level
 Bit & Bytes (useless)
 Packets (High volume)
 High volume but valuable data for offline & generate traffic
 Flow (limited to flows)
 Protocols (Specific Protocol)
 TCP, UDP, IP, RTP, ..
 Application (Known applications)
 HTTP, DNS, MAIL, VOIP, ...
 SNMP

14. Internet Traffic Measurement 14
Hidden Pieces - Middleboxes
 Firewalls – provide security
 Traffic Shapers – assist in traffic management
 Proxies – improve performance
 NAT boxes – utilize IP address space efficiently
Each of these impedes visibility of network
components.
Example:
 firewalls may block active probing requests
 NATs hide away the no. of hosts and the structure of the
network on the other side

15. Internet Traffic Measurement 15
Trace Challenges
 Payload Privacy
 Encryption
 Sanitization
 Reduction Techniques (OC-48, 50% utilization,
155MBps)
 TCP: Syn/Fin/Rst
 Uni-direction Analysis
 Sampling Techniques

16. Internet Traffic Measurement 16
Outline
 Why ?
 Tools
 Challenges
 Applications

17. Internet Traffic Measurement 17
Bandwidth Measurment
 Bandwidth Measurement
 Amount of data the network can transmit per unit time
 Three kinds of bandwidth
 capacity: max throughput a link can sustain,
 available bandwidth: capacity – used bandwidth
 bulk transfer capacity: rate that a new single long-lived TCP
connection would obtain over a path

18. Internet Traffic Measurement 18
Path Provisioning by Traceroute
 Suppose the path between A and D is to be
determined using traceroute
A
X Y
D
B C

19. Internet Traffic Measurement 19
Traceroute Process
A
X Y
D
B C
Dest = D
TTL = 1
B: “time
exceeded”

20. Internet Traffic Measurement 20
Traceroute Process
A
X Y
D
B C
Dest = D
TTL = 2
C: “time
exceeded”

21. Internet Traffic Measurement 21
Traceroute Process
A
X Y
D
B C
Dest = D
TTL = 3
D: “echo
reply”

22. Internet Traffic Measurement 22
Traceroute issues
 Path Asymmetry (Destination -> Source need
not retrace Source -> Destination)
 Unstable Paths and False Edges
 Aliases
 Measurement Load

23. Internet Traffic Measurement 23
Unstable Paths and False Edges
Inferred path: A -> B -> Y
A
X Y
D
B C
Dest = D
TTL = 1
B: “time
exceeded”
Dest = D
TTL = 2
Y: “time
exceeded”

24. Internet Traffic Measurement 24
Aliases
 IP addresses are for interfaces and not
routers
 Routers typically have many interfaces, each
with its own IP address
 IP addresses of all the router interfaces are
aliases
 Traceroute results require resolution of
aliases if they are to be used for topology
building

25. Internet Traffic Measurement 25
Video Quality Measurment
 Subjective Evaluation
 Variety cause of user experience
 Need many user to vote
 Objective Evaluation
 Data Metrics (PSNR)
 Picture Metrics (MPQM ,SSIM)
 Packet/Bit stream Metrics (Loss)
 Full/Reduced/Non Reference
 Visible/Invisible distortion

26. Internet Traffic Measurement 26
Video Quality Measurment
 GOP
 Frames (P, I, B)
 Slices

27. Internet Traffic Measurement 27
Video Quality Measurment
 Stream should be packetized
 TS(DVB) vs RTP(IPTV)
 Passive Measurement
 Deep Packet Inspection
 Resilience and Error correction
 Quality Estimation (Fuzzy, NN, ...)

28. Thank You!