Learn More
We describe FAST TCP, a new TCP congestion control algorithm for high-speed long-latency networks, from design to implementation.We highlight the approach taken by FAST TCP to address the four difficulties which the current TCP implementation has at large windows. We describe the architecture and summarize some of the algorithms implemented in our(More)
Network protocols in layered architectures have historically been obtained on an ad hoc basis, and many of the recent cross-layer designs are conducted through piecemeal approaches. They may instead be holisti-cally analyzed and systematically designed as distributed solutions to some global optimization problems. This paper presents a survey of the recent(More)
— We conducted various experiments using FAST TCP on two high-speed networks and uncovered some of the hidden problems affecting high-speed TCP implementations in practice. While FAST TCP achieved good performance in many scenarios, there were also a number of cases, where adverse conditions, both host related and network related, prevented it from(More)
It has been proved theoretically that a network with heterogeneous congestion control algorithms that react to different congestion signals can have multiple equilibrium points. In this paper, we demonstrate this experimentally using TCP Reno and Vegas/FAST. We also show that any desired inter-protocol fairness is in principle achievable by an appropriate(More)
This document specifies extensions to OSPF to support the distributed computation of Maximally Redundant Trees (MRT). Some example uses of the MRTs include IP/LDP Fast-Reroute and global protection or live-live for multicast traffic. The extensions indicate what MRT profile(s) each router supports. Different MRT profiles can be defined to support different(More)
When there is a change in network topology either due to a link going down or due to a new link addition, all the nodes in the network need to get the complete view of the network and re-compute the routes. There will generally be a small time window when the forwarding state of each of the nodes is not synchronized. This can result in transient loops in(More)
Segment routing supports the creation of explicit paths using adjacency-sids, node-sids, and binding-sids. It is important to provide fast reroute (FRR) mechanisms to respond to failures of links and nodes in the Segment-Routed Traffic-Engineered(SR-TE) path. A point of local repair (PLR) can provide FRR protection against the failure of a link in an SR-TE(More)
This document describes an extension to IS-IS protocol [ISO10589], [RFC1195] to add an optional operational capability, that allows tagging and grouping ofthe nodes in an IS-IS domain. This allows simple management and easy control over route and path selection, based on local configured policies. This document describes the protocol extensions to(More)