Report on IEPM PPDG efforts for PPDG for the quarter October - December 2003

Report prepared by Les Cottrell, January 24, 2004

Collaboration with IEPM, Network Performance Monitoring

Web/Grid Services

The new IEPM-BW Oracle backend database now provides easier ways to search through the IEPM-BW data. We followed this up by providing Grid services access to the data utilizing the GGF NMWG naming recommendations. To demonstrate the utilization we created a web page to interactively access the IEPM-BW data via the Grid services interface. More information on the Grid services access can be found at the IEPM Web Services page. Our next steps will be to provide similar access to the PingER data.Lee anmd Paul Meallor) to discuss and understand the OGSI schema. Following this Warren worked on porting the MAGGIE Web service to an OGSI type grid service using the perl module.

We co-authored and submitted the GGF NMWG recommendation entitled A Hierarchy of Network Performance Characteristics for Grid Applications and Services,

Data Presentation and Visualization

We extended our traceroute visualization tool to add: drill down to view available bandwidth time-series for the selected path; and to allow navigation through the historical archives of traceroutes. We wrote, submitted and had accepted an extended abstract short abstract on Correlating Internet Performance Changes and Route Changes to Assist in Trouble-shooting from an End-user Perspective, that describes this work.

PingER

There is increasing interest from the HENP and other scientific communities to understand and do something about the Digital Divide, i.e. the difference in Internet performance to developing and developed countries. Since 10-20% of HEP collaborators on the major experiments come from countries in developing nations, this is very important to HENP.

We prepared the January 2004 Report of the ICFA-SCIC Monitoring Working Group for ICFA.

In preparation for the WSIS in Geneva and the ICFA/SCIC Digital Divide meeting in Rio de Janiero in Feb 2004, we extended the number of remote sites monitored by about 10%. This was focused on providing better information on the Internet performance to developing countries. We also worked with NIIT Pakistan to successfully install a monitoring node there. This brings the number of countries with monitoring hosts to 13. Early results for NIIT were provided to the director of NIIT for a presentation recommending upgrading their connectivity.

We co-authored a paper for the CERN Courier entitled Developing countries and the global science web
We attended the RSIS and SIS in Geneva:
- With eJDS/ICTP we demonstrated the eJDS and PingER projects at Palexpo, Geneva
As an International Program Advisor we helped organize and attended the Abdus Salam International Center for Theoretical Physics (ICTP) Electronic Journals Distribution System (eJDS) Second Open Round Table on Developing Countries Access to Scientific Knowledge: Quantifying the Digital Divide. We wrote and presented 3 papers:

High speed networking

We attended and exhibited our monitoring projects at the SLAC/FNAL booth at SC2003. In addition, we once again participated in the Bandwidth Challenge. SLAC's challenge, in collaboration with Caltech and LANL, this year was Distributed Particle Physics Analysis using Ultra High Speed TCP on the Grid and it captured the SuperComputing 2003 Bandwidth Challenge award for the most data transferred (6.6TBytes in under 50 minutes)..

We co-authored a paper with LANL and Caltech on Optimizing 10-Gigabit Ethernet in Networks of Workstations, Clusters, and Grids: A Case Study that was accepted and presented at SC2003.

As co-chair of the 2nd Protocols for Fast Long Distance Networks to be held in Chicago in February 2004, we organized a review team, and reviewed and selected papers to be presented.

We started to work on automated fault finding by looking at the IEPM-BW monitoring data. We presented Meaurement and fault finding using MAGGIE and PIPES at the Internet2 Member meeting, Indianapolis Oct.13-16.

Advanced TCP STack Evaluation

With the emergence of many new advanced TCP (FAST, HS, Scalable, LP, H, Bic, Westwood+ ...) stacks that are trying to provide high-, fair-, stable-, responsive-performance on fast long-distance paths without needing to resort to using multiple parallel streams, it is important to evaluate and compare these stacks on high-speed production links to understand their domains of applicability etc. We made measurements on three different length production Internet paths to understand and compare the performance of seven different TCP stacks. We submitted and had accepted by PFLDnet a paper entitled Evaluation of Advanced TCP Stacks on Fast Long-Distance Production Networks.

To facilitate the installation and testing of HSTCP-LP (a fusion of HS-TCP and TCP-LP) Aleksander Kuzmanovic, a student from Rice University, spent 3 fruitful weeks at SLAC assisting with the installation and providing fixes, enhancements as we tested and found out more about the stack on our fast, production links. We also submitted and had accepted by PFLDnet a paper entitled HSTCP-LP: A Protocal for Low-Priority Bulk Data Transfer in High-Speed High-RTT Networks

Proposals

We submitted and had accepted two pre-proposals to the DoE Office of Science:

Measurement and Analysis for the Global Grid and Internet End-to-end performance (MAGGIE) - with LBNL, Internet2, PSC, and U Delaware
INCITE Ultra – New Protocols, Tools, Security, and Testbeds for Ultra High-Speed Networking - with Rice and LANL

We also worked with eJDS on putting together a proposal for PingER funding for IDRC/Canada

IPv6

Following renewed interest in IPv6 to support large numbers of IP addresses that will be needed as more and more objects (phones, soldiers, mines, personal devices etc.) are networked, we revived our IPv6 monitoring effort. Paola prepared a presentation on IPv6 for the Internet2 Joint Techs Workshop in August at Lawrence, Kansas.

Trouble Shooting

We added two Network Problem Case studies. One was on connectivity to Hangzhou China, the other on incorrect routing resulting a reduction of performance by a factor of 5 between SLAC and Caltech.