IPv6 at the University of Southampton
"... IPv6 research and deployment at the University of Southampton takes part within the Department of Electronics and Computer Science (ECS). The Department has eight research groups; the Pervasive Computing and Networks theme (PCaN) within the Intelligence, Agents, Multimedia group (IAM) is the focus of our IPv6 activity, though the implications of IPv6 are now being considered in a wide number of projects. ..."
"... Dr Tim Chown leads the IPv6 activity in the Pervasive Computing and Networks theme within the Intelligence, Agents, Multimedia (IAM) research group in the Electronics and Computer Science Department at the University of Southampton. ..."
In the recent flury of postings on the RE:EDUCAUSE discussion, Mladen Vouk referenced this work by Phillip Dickens and SABUL.
"High Performance Wide Area Data Transfers Over High Performance Networks"
Dickens, P., Gropp W., and P. Woodward
To Appear: The 2002 International Workshop on Performance Modeling, Evaluation, and Optimization of Parallel and Distributed Systems.
Document: http://www.csam.iit.edu/~pmd/pubs/HiPerf.final.doc
SABUL ( Simple Available Bandwidth Utilization Library )
from DataSpace of the Data Mining Group
Floyd's TCP slow-start and AIMD mods
"... Sally Floyd, as part of her research on high speed TCP, has suggested modifications to TCP slow start and to TCP's AIMD for high delay, bandwidth networks. As part of our Net100 research, we have modified the Linux 2.4.16 Web100 kernel with Sally's slow-start mods. The following graph shows two TCP transfers from ORNL to NERSC (80ms RTT) between two Linux boxes.
Performance Implications of Link Characteristics (pilc)
Performance Implications of Link Characteristics (pilc) Charter, Information, and Links
-- last update May 5, 2002
Advice for Internet Subnetwork Designers
"... This document provides advice to the designers of digital communication equipment, link-layer protocols and packet-switched subnetworks (collectively referred to as subnetworks) who wish to support the Internet protocols but who may be unfamiliar with the Internet architecture and the implications of their design choices on the performance and efficiency of the Internet. ..."
c/o MattZ
Matt Mathis' Papers and Citations
This page has links to presentations and papers by Matt.
-- latest paper noted Apr 2002
Abstract: The Macroscopic Behavior of the TCP Congestion Avoidance Algorithm
"... Abstract: In this paper, we analyze a performance model for the TCP Congestion Avoidance algorithm. The model predicts the bandwidth of a sustained TCP connection subjected to light to moderate packet losses, such as loss caused by network congestion. It assumes that TCP avoids retransmission timeouts and always has sufficient receiver window and sender data. The model predicts the Congestion Avoidance performance of nearly all TCP implementations under restricted conditions and of TCP with Selective Acknowledgements over a much wider range of Internet conditions. ..."
This abstract points to the full paper in postscript format. Also this paper is in the NEC Research Index
TSEG - Weathermap Distribution
"... Please note: Due to the fact that this software relies on an older set of libraries and was written using a different set of development standards than TSEG currently uses, this software is being presented as is, and we will not be supporting this distribution. Also, because we are completely rewriting this software, we will not be accepting patches for this distribution.
Note too, that this software relies on some software libraries that may be difficult to find. We cannot include these libraries in this distribution due to legal reasons. If you find you don't need certain functionality that part of this software provides, you may modify the programs to bypass the need for the older libraries. ..."
This page has links to library requirements, licensing process (for not-for-profits & educational), an example of the software, a link to a discussion board about the software (latest link is 10/15/2002), and a brief message about future development.
In case you all are interested, this is the entry point into the HENP listserv archives. I'd suggest selecting a month viewed by thread.
Here's Sally's page with links to Papers, Talks, Implementations and Experimental Reports, Simulations, and Related work for bulk transfer over high latency/bandwidth networks.
-- last updated August 2002
Here is a good starting point to various information from Tom Dunnigan.
HENP Working Group Meeting Internet2 Spring 2002 Member Meeting
This page lists Tom Hacker and Sylvain Ravot with links to their presentations along with other related presentations.
Please note that the Hacker html points to Jim Williams' presentation -- in the URL just replace Williams with Hacker and that will link you to Tom's slides.
The Effects of Systemic Packets Loss on Aggregate TCP Flows
Tom Hacker's presentation for the HEPN WG session at the Spring 2002 Internet2 Member Meeting. The power point version is available at http://www.internet2.edu/presentations/spring02/20020508-HENP-Hacker.ppt
The HENP Internet2 WGPresentation: High TCP performance over wide area networks
This is a converted power point presentation from the HEMP WG session at the Spring 2002 Internet2 Member Meeting.
Les Cottrell's Report on the I2 HEMP WG mtg 1/2002
"... Results on high throughput & QoS between US & CERN - Sylvain Ravot (Remote)
Performance on high latency*bandwidth networks. Looked at slow start and then congestion avoidance, then went over fast recovery, showed tcptrace illustration. Used UDP to find max bandwidth without loss on CERN Caltech link. LInux TCP estimates initial sshthresh from the previous connection. Showed the effect of overestimating the bw*window size. Worked on reducing slow start time by modifying the slow start increment, did not help much, then modified the congestion avoidance increment. Looked at with simulator with 1/10K loss. Need to limit the max cwnd size. Set initial ssthresh to an appropriate vale for delay & bw of link, initial ssthresh has to be larger than delay*bw product but not too large. Looked at QBSS, does it use all bandwidth available, does it back off? Showed QBSS limits itself OK quickly and does not affect other traffic. But QBSS unable to use maximum of 120Mbps bandwidth even if no other traffic. Probably due to small queue size for the QBSS stream. Could use QBSS with UDP to measure unused bandwidth without affecting production traffic. Tried 2 ways in which Cisco implements load balancing (CEF). Found per packet load balancing works well, per-destination does not work well for one pair. But per packet load balancing resulted in 50% packets being received out of order. Reached 192Mbits/s, 99.8%% ..."
HighSpeed TCP for Large Congestion Windows (IETF Draft)
"... This document proposes HighSpeed TCP, a modification to TCP's congestion control mechanism for use with TCP connections with large congestion windows. The congestion control mechanisms of the current, Standard TCP constrains the congestion windows that can be achieved by TCP in realistic environments. For example, for a Standard TCP connection with 1500-byte packets and a 100 ms round- trip time, achieving a steady-state throughput of 10 Gbps would require an average congestion window of 83,333 segments, and a packet drop rate of at most one congestion event every 5,000,000,000 packet (or equivalently, at most one congestion event every 1 2/3 hours). We do not consider this a realistic condition. To address this limitation of TCP, this document proposes HighSpeed TCP, and solicits experimentation and feedback from the wider community. ..."
-- May 2002
"... ABE (Alternative Best-Effort) is a novel service for IP networks. It provides a low bounded queueing delay service in the Internet. The service is best-effort, and requires no additional charging or usage control. Its goal is to help applications with stringent real time constraints, such as interactive audio. With ABE, it is not required to police how much traffic uses the low delay capability, the service being designed to operate equally well in all traffic scenarios. ..."
This page contains 30 citations related to the terms: XCP, TCP, and Tuning c/o Google. There are some interesting papers listed. -- george
XCP: eXplicit Congestion control Protocol
"... Theory and experiments show that as the per-flow product of bandwidth and latency increases, TCP becomes inefficient and prone to instability, regardless of the queuing scheme. This failing becomes increasingly important as the Internet evolves to incorporate very high-bandwidth optical links and more large-delay satellite links.
To address this problem, we develop a novel approach to Internet congestion control that outperforms TCP in conventional environments, and remains efficient, fair, scalable, and stable as the bandwidth-delay product increases. This new eXplicit Control Protocol, XCP, generalizes the Explicit Congestion Notification proposal (ECN). In addition, XCP introduces the new concept of decoupling utilization control from fairness control. This allows a more flexible and analytically tractable protocol design and opens new avenues for service differentiation. .."
[FAST Protocols for Ultrascale Networks]
The development of robust and stable ultrascale networking, at 100 Gbps and higher speeds in the wide area, is critical to support the new generation of ultrascale computing and Petabyte to Exabyte datasets that promise to drive discoveries in fundamental and applied sciences of the next decade. Continued advances in computing, communication, and storage technologies, combined with the development of national and global Grid systems, hold the promise of providing the required capacities and an effective environment for computing and science.
ADVANCED INFORMATION SYSTEMS TECHNOLOGY (AIST) PROGRAM
NRA-02-OES-04
"... Topic Area 2: Space-Based Communication Networks
A significant challenge for future earth observing satellites will be establishing and maintaining a viable communications network among constellations of satellites operating in diverse orbits. The AIST program will support applied research on space-based communications that supports data transfer from satellite to satellite, or from satellite to ground. Examples include, but are not limited to:
>> Network infrastructure, autonomous network management, and network management tools; and
>> Commercially compatible standards and protocols that will provide connectivity from scientist to instrument (end-to-end) and for distributed information systems in space. ..."
"... Earth Science REASoN - Research, Education and Applications Solutions Network
A Distributed Network of Data and Information Providers For Earth Science Enterprise Science, Applications and Education ..."