|
Distributed Systems, Network Protocols & Applications |
Group
Members
Networked games are rapidly evolving from small 4-8 person, one-time play games to large-scale games involving thousands of participants and persistent game worlds. However, like most Internet applications, current networked games are centralized. Players send control messages to a central server and the server sends (relevant) state updates to all active players. This design suffers from the well known robustness and scalability problems of single server designs. For example, high update rates prevent even well provisioned servers from supporting more than several tens of players for first person shooter (FPS) games. In our work, we are exploring a variety of tools to support the design and construction of large-scale distributed online games.
Chaotic Wireless
Until recently, most dense deployments of wireless networks were
in campus-like environments, where experts carefully plan cell
layout. The rapid deployment of cheap 802.11 hardware and other
personal wireless technology (2.4Ghz cordless phones, bluetooth
devices, etc.), however, is quickly changing the wireless
landscape. The resulting dense deployment of wireless networking
equipment in areas such as neighborhoods, shopping malls, and
apartment buildings, differ from campus-like deployments in two
important ways. First, while campus deployments are carefully
planned to optimize coverage and minimize cell overlap, many
recent deployments result from many independent people or
organizations each setting up one or a small number of APs.
This type of spontaneous, unplanned deployment results in highly
variable (including very high) densities of wireless nodes and
APs. Moreover, 802.11 nodes share the spectrum with other
networking technologies (e.g., Bluetooth, UWB) and other uses
(e.g., cordless phones). Second, configuring and managing
wireless networks is difficult, and most users do not have the
skills to deal with even simple tasks such as choosing
parameters such as SSID and channel, let alone more complex
questions such as power control and number and placement of APs.
We have coined the term chaotic networks to refer to this type
of deployments.
Trustworthy Wireless
The emerging use of ubiquitous computing devices has begun
to raise new privacy concerns. In the near future, people, cars, and
homes will have many, if not dozens, of wireless devices that provide rich
and seamless network connectivity. With this new
class of devices, privacy is no longer roughly equivalent to message
confidentiality that current wireless systems provide (e.g., WEP, WPA).
The main added privacy risk is that these devices allow users to be
tracked and profiled. This project explores some of the new forms of
privacy attacks, counter-measures and changes to the system to provide
users more control over their privacy.
It is the core goal of this project to use testbed-based
measurements to improve the understanding of the Internet and shape its
future by characterizing the operation of the current Internet
infrastructure and its
usage patterns.
We believe that a major reason for the limited number of truly distributed applications is that tools and other facilities available to aid the developers of these applications are inadequate. Distributed applications share a common life-cycle and need tools that address each of the stages of this cycle. The goal of our work is to provide the building blocks needed to support each of the stages in the life-cycle of Internet applications.
IrisNet is the first general- purpose software
infrastructure tailored to the unique demands of worldwide sensing
services. IrisNet provides service authors with a very high-level
abstraction of the underlying system, to ease the authoring of new
services.
Shared Passive Network Performance Discovery (SPAND) is a software toolkit that makes it easy for networked applications to report the performance they perceive as they communicate with distant Internet hosts and remember this information for later use.
The Flexible Filter Framework
(F3) allows stateful filters to be written without knowledge of
what other filters are used on the firewall. This flexibility allows the
firewall to evolve more quickly with applications than a traditional
stateful packet filter system. (Work is Patented through
IBM.)
BARWAN
The Barwan project was inspired by the early work on InfoPad. Unlike InfoPad, the Barwan project used off-the-shelf hardware, such as laptops and wireless network interfaces. The project concentrated on software infrastructure to support this environment. In order to handle the slow speed of wireless links and the limited capabilities of some of the mobile nodes, the project used an evolved version of the proxy architecture originally developed for the InfoPad system.
InfoPad was a large interdisciplinary project that included the development of chipsets for mobile terminals, techniques for low power design, user-interfaces for mobile applications, and wireless radio links. The core of the InfoPad design was a wirelessly connected, simple, portable multimedia terminal called the Pad. The Pad had very limited compute capabilities (to conserve power) and served primarily as a dumb terminal. As a result, the Pad could not support workstation style application interfaces such as X Windows and TCP/IP. Instead, it provided a set of interfaces that were better optimized for the Pad’s compute capabilities and the wireless channel by which the Pad communicated. To support applications, the project would need to rewrite them to use the special network I/O interfaces that the Pad supported natively.
