Benjie Chen

Span: An energy-efficient coordination algorithm for topology maintenance in Ad Hoc wireless networks

This paper presents Span, a power saving technique for multi-hop ad hoc wireless networks that reduces energy consumption without significantly diminishing the capacity or connectivity of the network. Span builds on the observation that when a region of a shared-channel wireless network bag a sufficient density of nodes, only a small number of them need be on at any time to forward traffic for active connections. Span is a distributed, randomized algorithm where nodes make local decisions on whether to sleep, or to join a forwarding backbone as a coordinator. Each node bases its decision on an estimate of how many of its neighbors will benefit from it being awake, and the amount of energy available to it. We give a randomized algorithm where coordinators rotate with time, demonstrating how localized node decisions lead to a connected, capacity-preserving global topology. Improvement in system lifetime due to Span increases as the ratio of idle-to-sleep energy consumption increases, and increases as the density of the network increases. For example, our simulations show that with a practical energy model, system lifetime of an 802.11 network in power saving mode with Span is a factor of two better than without. Span integrates nicely with 802.11—when run in conjunction with the 802.11 power saving mode, Span improves communication latency, capacity, and system lifetime.

The click modular router

Clicks is a new software architecture for building flexible and configurable routers. A Click router is assembled from packet processing modules called elements. Individual elements implement simple router functions like packet classification, queuing, scheduling, and interfacing with network devices. A router configurable is a directed graph with elements at the vertices; packets flow along the edges of the graph. Several features make individual elements more powerful and complex configurations easier to write, including pull connections, which model packet flow drivn by transmitting hardware devices, and flow-based router context, which helps an element locate other interesting elements. Click configurations are modular and easy to extend. A standards-compliant Click IP router has 16 elements on its forwarding path; some of its elements are also useful in Ethernet switches and IP tunnelling configurations. Extending the IP router to support dropping policies, fairness among flows, or Differentiated Services simply requires adding a couple of element at the right place. On conventional PC hardware, the Click IP router achieves a maximum loss-free forwarding rate of 333,000 64-byte packets per second, demonstrating that Clicks modular and flexible architecture is compatible with good performance.

A low-bandwidth network file system

Users rarely consider running network file systems over slow or wide-area networks, as the performance would be unacceptable and the bandwidth consumption too high. Nonetheless, efficient remote file access would often be desirable over such networks---particularly when high latency makes remote login sessions unresponsive. Rather than run interactive programs such as editors remotely, users could run the programs locally and manipulate remote files through the file system. To do so, however, would require a network file system that consumes less bandwidth than most current file systems.This paper presents LBFS, a network file system designed for low-bandwidth networks. LBFS exploits similarities between files or versions of the same file to save bandwidth. It avoids sending data over the network when the same data can already be found in the servers file system or the clients cache. Using this technique in conjunction with conventional compression and caching, LBFS consumes over an order of magnitude less bandwidth than traditional network file systems on common workloads.

Span: an energy-efficient coordination algorithm for topology maintenance in ad hoc wireless networks

This paper presents Span, a power saving technique for multi-hop ad hoc wireless networks that reduces energy consumption without significantly diminishing the capacity or connectivity of the network. Span builds on the observation that when a region of a shared-channel wireless network has a sufficient density of nodes, only a small number of them need be on at any time to forward traffic for active connections. Span is a distributed, randomized algorithm where nodes make local decisions on whether to sleep, or to join a forwarding backbone as a coordinator. Each node bases its decision on an estimate of how many of its neighbors will benefit from it being awake, and the amount of energy available to it. We give a randomized algorithm where coordinators rotate with time, demonstrating how localized node decisions lead to a connected, capacity-preserving global topology. Improvement in system lifetime due to Span increases as the ratio of idle-to-sleep energy consumption increases. Our simulations show that with a practical energy model, system lifetime of an 802.11 network in power saving mode with Span is a factor of two better than without. Additionally, Span also improves communication latency and capacity.

Ivy: a read/write peer-to-peer file system

Ivy is a multi-user read/write peer-to-peer file system. Ivy has no centralized or dedicated components, and it provides useful integrity properties without requiring users to fully trust either the underlying peer-to-peer storage system or the other users of the file system.An Ivy file system consists solely of a set of logs, one log per participant. Ivy stores its logs in the DHash distributed hash table. Each participant finds data by consuiting all logs, but performs modifications by appending only to its own log. This arrangement allows Ivy to maintain meta-data consistency without locking. Ivy users can choose which other logs to trust, an appropriate arrangement in a semi-open peer-to-peer system.Ivy presents applications with a conventional file system interface. When the underlying network is fully connected, Ivy provides NFS-like semantics, such as close-to-open consistency. Ivy detects conflicting modifications made during a partition, and provides relevant version information to application-specific conflict resolvers. Performance measurements on a wide-area network show that Ivy is two to three times slower than NFS.

Programming language optimizations for modular router configurations

Networking systems such as Ensemble, the x-kernel, Scout, and Click achieve flexibility by building routers and other packet processors from modular components. Unfortunately, component designs are often slower than purpose-built code, and routers in particular have stringent efficiency requirements. This paper addresses the efficiency problems of one component-based router, Click, through optimization tools inspired in part by compiler optimization passes. This pragmatic approach can result in significant performance improvements; for example, the combination of three optimizations reduces the amount of CPU time Click requires to process a packet in a simple IP router by 34%. We present several optimization tools, describe how those tools affected the design of Click itself, and present detailed evaluations of Clicks performance with and without optimization.

Brief announcement: building data structures on untrusted peer-to-peer storage with per-participant logs

L is a technique for building multi-user distributed data structures out of untrusted peer-to-peer distributed hash tables (DHTs). L uses multiple logs, one log per participant, to store changes to the data structure. Each participant finds data by consulting all logs, but performs modifications by appending only to its own log. This decentralized structure allows L to maintain meta-data consistency without locking and to isolate users’ changes from each other, an appropriate arrangement for unreliable users. Applications use L to maintain consistent data structures. L interleaves multiple logs deterministically so that decentralized clients can agree on the order of completed operations, even if those operations were issued concurrently. When the data structure is quiescent, L guarantees that clients agree on the state of the data structure. L optionally provides mutual exclusion for applications that need to ensure atomicity for multistep operations. The Ivy file system, built on top of L, demonstrates that L’s consistency guarantees are useful and can be used and implemented efficiently. Regular submission. The first three authors are students. Please consider paper for brief announcement as well.