Interoperable Measurement Frameworks: Joint Monitoring of GEANT

1
Interoperable Measurement FrameworksJoint
Monitoring of GEANT Abilene

• Eric L. Boyd, Internet2

2
American/European Collaboration Goals

• Awareness of ongoing Measurement Framework
  Efforts / Sharing of Ideas (Good / Not
  Sufficient)
• Interoperable Measurement Frameworks (Minimum)
• Common means of data extraction
• Partial path analysis possible along
  transatlantic paths
• Open Source Shared Development (Possibility, In
  Whole or In Part)
• End-to-end partial path analysis for
  transatlantic research communities
• VLBI Onsala, Sweden ?? Haystack, Mass.
• HENP CERN, Switzerland ?? Caltech, Calif.

3
American/European Demonstration Goals

• Demonstrate ability to do partial path analysis
  between Caltech (Los Angeles Abilene router)
  and CERN.
• Demonstrate ability to do partial path analysis
  involving nodes in the GEANT network.
• Compare and contrast measurement of a lightpath
  versus a normal IP path.
• Demonstrate interoperability of piPEs and
  analysis tools such as Advisor and MonALISA

4
Demonstration Details

• Path 1 Default route between LA and CERN is
  across Abilene to Chicago, then across Datatag
  circuit to CERN
• Path 2 Announced addresses so that route between
  LA and CERN traverses GEANT via London node
• Path 3 Lightpath (discussed earlier by Rick
  Summerhill)
• Each measurement node consists of a BWCTL box
  and an OWAMP box next to the router.

5
All Roads Lead to Geneva
6
Transatlantic Lightpath Experiment

• Grew out of a meeting in December with CANARIE,
  GEANT and Internet2
• Decided to setup a basic 1 Gig Lightpath to
  demonstrate technologies and requirements
• Followed KIDS, not KISS that is, keep it
  difficult stupid! -?
• Uses a variety of layer 1, 2, and 3 technologies
• Crosses administrative domains using different
  layers
• Goal - examine the problems, and how one might
  make this dynamic (in some way)!
• Control Plane
• 8 hours of conference calls
• Approximately 300 pieces of email

7
Lightpaths

• A lightpath is a virtual private or dedicated
  unidirectional path with a given service level
  guarantee (i.e., deterministic behavior)
• Extremely low jitter
• Close to light speed latency behavior in glass
• Guaranteed bandwidth
• Extremely low packet loss
• Examples
• WDM
• TDM
• MPLS based techniques (including L2VPN and use of
  CCC)
• Premium IP Service
• ATM CBR PVC
• Any concatenation of two lightpaths should be a
  lightpath lightpaths can be joined end-to-end!

8
(No Transcript)
9
Los Angeles to Chicago

• MPLS L2VPN across Abilene with preference through
  the lightpath
• Setup of vlans, MTUs, IP addressing
• Testing of preference in the lab

10
Chicago to New York

• Layer1 TDM path across CANARIE
• No layer2, layer 3 configuration across CANARIE

11
New York to Amsterdam

• Layer1 TDM path across CANARIE, Internet2, and
  SURFnet
• Layer1 configuration problems encountered on
  TYCO/IEEAF circuit

12
Amsterdam to CERN

• Layer3 Premium IP Service across GEANT
• Setup of vlans, IP addressing

13
Results

• BWCTL http//abilene.internet2.edu/ami/bwctl_stat
  us_eu.cgi/BW/now
• OWAMP http//abilene.internet2.edu/ami/owamp_stat
  us_eu.cgi/now
• MONALISA http//vinci.cacr.caltech.edu8080
• NLANR Advisor

14
Insights (1)

• Even with shared source and a single team of
  developer-installers, inter-administrative domain
  coordination is difficult.
• Struggled with basics of multiple paths.
• IP addresses, host configuration, software
  (support source addresses, etc.)
• Struggled with cross-domain administrative
  coordination issues.
• AA (accounts), routes, port filters, MTUs, etc.
• Struggled with performance tuning measurement
  nodes.
• host tuning, asymmetric routing, MTUs

15
Insights (2)

• Connectivity takes a large amount of coordination
  and effort performance takes even more of the
  same.
• Current measurement approaches have limited
  visibility into lightpaths.
• Having hosts participate in the measurement is
  one possible solution.

16
Insights (3)

• Consider interaction with security lack of
  end-to-end transparency is problematic.
• Security filters are set up based on expected
  traffic patterns
• Measurement nodes create new traffic
• Lightpaths bypass expected ingress points

17
(No Transcript)