OneProbe: Measuring network path quality with TCP data-packet pairs - - PowerPoint PPT Presentation

▶
oneprobe measuring network path quality with tcp data
SMART_READER_LITE
LIVE PREVIEW

OneProbe: Measuring network path quality with TCP data-packet pairs - - PowerPoint PPT Presentation

Nov 29, 2023 5 likes •399 views

OneProbe: Measuring network path quality with TCP data-packet pairs Rocky K. C. Chang Internet Infrastructure and Security Group The Hong Kong Polytechnic University 11 February 2011 ISMA 2011 AIMS-3 AIMS-III, 2011 1 Our group Active

slide-1
SLIDE 1

Rocky K. C. Chang

Internet Infrastructure and Security Group The Hong Kong Polytechnic University 11 February 2011 ISMA 2011 AIMS-3

AIMS-III, 2011 1

OneProbe: Measuring network path quality with TCP data-packet pairs

slide-2
SLIDE 2

Our group

AIMS-III, 2011 2

 Active measurement

 Non-cooperative path-quality measurement methodologies

 OneProbe (RTT, loss, reordering), capacity measurement, loss-pair

measurement, traceroute analysis  Applications

 Longitudinal analysis of network evolution, collaborative diagnosis of

routing and performance problems, impact analysis of submarine cable faults, …

 Activities

 Publications, research proposals, professional services  Work with HARNET, ISPs, data centers, ….  Plan to work with other groups, including CERNET in China

slide-3
SLIDE 3

Outline

AIMS-III, 2011 3

  • 1. Path-quality measurement methodologies
  • 2. Applications
  • Cooperative network measurement (a demo)
  • An impact analysis of a submarine cable fault
  • 3. Conclusions and future works
slide-4
SLIDE 4

AIMS-III, 2011 4

  • 1. Path-quality measurement
slide-5
SLIDE 5

Measuring e2e network paths

5 AIMS-III, 2011

slide-6
SLIDE 6

 Controlling both endpoints

 E.g., one-way delay, OWAMP

, TWAMP

 Controlling one endpoint (non-cooperative measurement)

 Using/hacking existing protocols  E.g., ping, tulip, sting …

 Controlling zero endpoint

 E.g., King

Active measurement models

6 AIMS-III, 2011

slide-7
SLIDE 7

 Controlling both endpoints

 E.g., one-way delay, OWAMP

, TWAMP

 Controlling one endpoint (non-cooperative measurement)

 Using/hacking existing protocols  E.g., ping, tulip, sting …

 Controlling zero endpoint

 E.g., King

Active measurement models

7 AIMS-III, 2011

slide-8
SLIDE 8

(Invalid) assumptions

 Control-path quality = data-path quality

 ICMP

, TCP SYN, TCP RST

 Middleboxes not an issue

 Dropping, rate-limiting, additional latency

 No changes in systems

 Consecutive increment of IPID (e.g., tulip)

 Sampling rate and pattern not an issue

8 AIMS-III, 2011

slide-9
SLIDE 9

(Invalid) assumptions

 Control-path quality = data-path quality

 ICMP

, TCP SYN, TCP RST

 Middleboxes not an issue

 Dropping, rate-limiting, additional latency

 No changes in systems

 Consecutive increment of IPID (e.g., tulip)

 Sampling rate and pattern not an issue

Invalid assumptions beget unreliable measurement.

9 AIMS-III, 2011

slide-10
SLIDE 10

Other problems in practice

 Support only one or two metrics  Round-trip measurement  No control over packet sizes  Not integrated with application protocols

10 AIMS-III, 2011

slide-11
SLIDE 11

Other problems in practice

 Support only one or two metrics  Round-trip measurement  No control over packet sizes  Not integrated with application protocols

Practical issues stifle deployment.

11 AIMS-III, 2011

slide-12
SLIDE 12

Our design principles

 Use normal data packet to measure data-path quality.  Use normal and basic data transmission mechanisms  Integrated into normal application sessions.

12 AIMS-III, 2011

slide-13
SLIDE 13

Our design principles

 Use normal data packet to measure data-path quality.  Use normal and basic data transmission mechanisms  Integrated into normal application sessions.

13 AIMS-III, 2011

Reliable measurement

slide-14
SLIDE 14

HTTP/OneProbe

 Use normal TCP data packet to measure data-path quality.  Use normal and basic TCP data transmission mechanisms

specified in RFC 793.

 Integrated into normal HTTP application sessions.

14 AIMS-III, 2011

OneProbe (TCP) HTTP BitTorrent RTMP

…

Data clocking Path measure- ment

slide-15
SLIDE 15

What does HTTP/OneProbe offer?

 Continuous path monitoring in an HTTP session (stateful

measurement)

 All in one:

 Round-trip time  Loss rate (uni-directional)  Reordering rate (uni-directional)  Capacity (uni-directional)  Loss-pair analysis  …

 "Design and Implementation of TCP Data Probes for Reliable and

Metric-Rich Network Path Monitoring,“ Proc. USENIX Annual Tech. Conf., June 2009.

OneProbe RTT

Forward Loss Reverse Loss Forward Reordering Reverse Reordering Forward Capacity Reverse Capacity

15 AIMS-III, 2011

slide-16
SLIDE 16

16 AIMS-III, 2011

slide-17
SLIDE 17

17 AIMS-III, 2011

slide-18
SLIDE 18

18 AIMS-III, 2011

slide-19
SLIDE 19

OneProbe: the probe design

 Send two back-to-back probe

data packets.

 Capacity measurement  Packet reordering  Determine which packet is lost.

 Similarly for the response

packets

 Each probe packet elicits a

response packet

19 AIMS-III, 2011

slide-20
SLIDE 20

OneProbe: Bootstrapping and continuous monitoring

20 AIMS-III, 2011

slide-21
SLIDE 21

OneProbe: Loss and reordering measurement via response diversity

21 AIMS-III, 2011

slide-22
SLIDE 22

AIMS-III, 2011 22

Discrepancy between ping RTT and OneProbe RTT

slide-23
SLIDE 23

AIMS-III, 2011 23

Highly asymmetric loss rates

slide-24
SLIDE 24

AIMS-III, 2011 24

Impact of configuration changes

slide-25
SLIDE 25

AIMS-III, 2011 25

2.1 Application: Collaborative path- quality measurement

slide-26
SLIDE 26

HARNET measurement (since 1 Jan 2009)

AIMS-III, 2011 26

slide-27
SLIDE 27

Running OneProbe at the 8 Us

AIMS-III, 2011 27

 24x365 probing of the paths to 40+ websites

slide-28
SLIDE 28

AIMS-III, 2011 28

OneProbe@ HKU OneProbe@ CUHK OneProbe@ CityU OneProbe@ PolyU OneProbe@ BU OneProbe@ HKUST OneProbe@ HKIED OneProbe@ LU

40+ web servers selected by the JUCC Planetopus, database, etc

HKU CUHK PolyU CityU BU HKUST LU HKIED

Measurement side User side

slide-29
SLIDE 29

AIMS-III, 2011 29

slide-30
SLIDE 30

AIMS-III, 2011 30

2.2 Application: Impact analysis of submarine cable faults

slide-31
SLIDE 31

Eyjafjallajöekull volcano eruption

AIMS-III, 2011 31

slide-32
SLIDE 32

Path-quality degradation for NOK (Finland) and ENG (in UK)

AIMS-III, 2011 32

slide-33
SLIDE 33

AIMS-III, 2011 33

slide-34
SLIDE 34

Network congestion caused by the volcano ashes?

AIMS-III, 2011 34

 The surges on packet loss and RTT occurred on 14 April

2009.

 But

 The onsets of the path congestion and air traffic disruption do

not entirely match.

 Some of the peak loss rate and RTT occurred on weekends.  Path congestion can still be observed at the end of the

measurement period.

slide-35
SLIDE 35

A SEA-ME-WE 4 cable fault

AIMS-III, 2011 35

 The SEA-ME-WE 4 cable encountered a shunt fault on the

segment between Alexandria and Marseille on 14 April 2010.

 The repair was started on 25 April 2010, and it took four

days to complete.

 During the repair, the service for the westbound traffic to

Europe was not available.

 "Non-cooperative Diagnosis of Submarine Cable Faults,” Proc.

PAM 2011, March 2011.

slide-36
SLIDE 36

The SEA-ME-WE 4 cable

AIMS-III, 2011 36

slide-37
SLIDE 37

A plausible explanation for the network congestion

AIMS-III, 2011 37

 The congestion in the FLAG network was caused by taking

  • n rerouted traffic from the faulty SEA-ME-WE 4 cable.

 FLAG does not use the SEA-ME-WE 4 cable for Hong Kong 

NOKIA, ENG3, and BBC.

 FLAG uses FEA for Hong Kong  NOKIA, ENG3, and BBC  TATA uses different cables between Mumbai and London.

slide-38
SLIDE 38

Conclusions and current works

AIMS-III, 2011 38

 Turning a network protocol into a measurement protocol.  Coming up a novel measurement method is just half a story.  Making it work in the non-cooperative Internet is hard.  Current works

 Expanding OneProbe’s capability (e.g., asymmetric available

bandwidth)

 Applications: fault localizations, SLA measurement, speed test,

net measurement neutrality, correlating with QoE, …

slide-39
SLIDE 39

AIMS-III, 2011 39

  • neprobe.org