Performance Working Group, Face-to-Face Meeting, 5-Oct-09
Internet2 Fall Member Meeting in San Antonio
Welcome
Carla Hunt welcomed the group. Co-Chair Chris Hawkinson participated via the phone bridge.
Community Updates
- Presented by Aaron Brown, Internet2
ION Service
* ION service is now production with Ciena monitoring.
* There will be a demonstration of the ION service during the week here at Fall Member Meeting.
pS Performance Toolkit 3.1
* Regular active latency tests and archiving.
* Vastly improved administrative web GUI.
perfSONAR-PS 3.1
* perfSONAR-BUOY adds OWAMP support.
* Stability and performance enhancements across all services.
http://software.internet2.edu
* It's the one-stop shop for Internet2's software.
* Includes BWCTL, OWAMP, pS-PS RPMs.
* There are plans to package NDT and other tools as well.
Internet2 Staff
In the next few weeks, Andy Lake will be transitioning to a job at ESnet, and Rich Carlson will begin working Department Of Energy's Office Of Science. We thank both for all their hard work and wish them well in their respective endeavors. Both will be remaining within the Internet2 community and we look forward to working with them in the future.
Recent release of the Network Performance Toolkit
- Presented by Jason Zurawski, Internet2
http://www.internet2.edu/presentations/fall09/20091005-PerfWG-zurawski.pdf
For discussion:
- Guidelines for scheduling measurement tests (previous wg discussion lead by Joe Metzger)
Geant's experiences with PERTs
- Presentation by Victor Reijs, HEAnet
Victor provided an overview of:
- Why is e2e performance hard?
- What is a PERT?
- Brief history of the PERT
- What is eduPERT?
- GN2 PERT experience feedback
- Challenges for eduPERT
- Why you should have a PERT
See:
http://www.internet2.edu/presentations/fall09/20091005-performance-reijs.pdf
Questions and Comments:
Is the PERT concept something we could implement here in the US?
Argument in 2001 was that "we don't have the tools." But now we do have them.
It would be great to add this human network.
Tools can help us identify performance problems, but we can use help in knowing how to isolate them? What's the decision tree?
It was agreed there is lots of potential, and this could add to the value of the Internet2 network.
Concerns: How are we going to fund such an effort? If it is an extra service that's part of the network, maybe that could be sold. Could help to build value for R&E networking. But what is the value a user will put on it?
Suggestion: identify network engineers at Tier-2 sites, who need to understand this troubleshooting anyhow to handle LHC requirements, and use them as a cadre from which a PERT could grow. Use a ticketing system and integrate it with Geant's ticketing system.