Wide-area network (WAN) accelerators operate by compressing redundant network traffic from point-to-point communications, enabling higher effective bandwidth. Unfortunately, while network bandwidth is scarce and expensive in the developing world, current WAN accelerators are designed for enterprise use, and are a poor fit in these environments. We present Wanax, a WAN accelerator designed for developing-world deployments. It uses a novel multiresolution chunking (MRC) scheme that provides high compression rates and high disk performance for a variety of content, while using much less memory than existing approaches. Wanax exploits the design of MRC to perform intelligent load shedding to maximize throughput when running on resource-limited shared platforms. Finally, Wanax exploits the mesh network environments being deployed in the developing world, instead of just the star topologies common in enterprise branch offices. 1

We investigate the confrontation of load splitting and caching in high-performance parallel network forwarding systems. Our study demonstrates that hash-based load splitting schemes tend to significantly improve the temporal locality of the address stream submitted to a single routing engine (RE), which in turn greatly facilitates caching as a means of increasing system performance. We also show that the impact of locality on the efficiency of load balancing cannot be ignored: load balancing in a parallel forwarding system cannot be studied in isolation from the caching issues.

This paper addresses the problem of optimal traffic engineering in a connectionless autonomous system. Based on Nonlinear Control Theory, the approach taken in this paper provides a family of optimal adaptation laws. These laws enable each node in the network to independently distribute traffic among any given set of next-hops in an optimal way, as measured by a given global utility function of a general form. This optimal traffic distribution is achieved with minimum information exchange between neighboring nodes. Furthermore, this approach not only allows for optimal multiple forwarding paths but also enables multiple Classes of Service; e.g., classes of service defined in the DiffServ architecture. Moreover, the proposed decentralized control scheme enables optimal traffic redistribution in the case of link failures. Suboptimal control laws are also presented in an effort to reduce the computational burden imposed on the nodes of the network. Finally, an implementation of these laws with currently available technology is discussed.

Content-based naming (CBN) enables content sharing across similar files by breaking files into positionindependent chunks and naming these chunks using hashes of their contents. While a number of research systems have recently used custom CBN approaches internally to good effect, there has not yet been any mechanism to use CBN in a general-purpose way. In this paper, we demonstrate a practical approach to applying CBN without requiring disruptive changes to end systems. We develop CZIP, a CBN compression scheme which reduces data sizes by eliminating redundant chunks, compresses chunks using existing schemes, and facilitates sharing within files, across files, and across machines by explicitly exposing CBN chunk hashes. CZIPaware caching systems can exploit the CBN information to reduce storage space, reduce bandwidth consumption, and increase performance, while content providers and middleboxes can selectively encode their most suitable content. We show that CZIP compares well to standalone compression schemes, that a CBN cache for CZIP is easily implemented, and that a CZIP-aware CDN produces significant benefits. 1

Active routers allow computation to be performed within the network by processing packets when they pass through the routers. We design and implement a cluster-based active router system that provides multimedia stream transcoding service. The performance of the system is evaluated with three different load balancing schemes. We evaluate the out-of-order phenomenon and analyze the tradeoff between this phenomenon and the processing speed. We present a stream-based round robin algorithm for the transcoding service offered in the router and demonstrate its superiority over the conventional round-robin scheme. The main design criteria are to minimize the total transcoding time and maintain the order of media units for each outgoing stream. 1.

Abstract — This paper studies load balancing for multipath Internet routing. We focus on hash-based load balancing algorithms that work on the flow level to avoid packet reordering which is detrimental for the throughput of transport layer protocols like TCP. We propose a classification of hash-based load balancing algorithms, review existing ones and suggest new ones. Dynamic algorithms can actively react to load imbalances which causes route changes for some flows and thereby again packet reordering. Therefore, we investigate the load balancing accuracy and flow reassignment rate of load balancing algorithms. Our exhaustive simulation experiments show that these performance measures depend significantly on the traffic properties and on the algorithms themselves. As a consequence, our results should be taken into account for the application of load balancing in practice. I.

Workload distribution is critical to the performance of network processor based parallel forwarding systems. Scheduling schemes that operate at the packet level, e.g., round-robin, cannot preserve packet-ordering within individual TCP connections. Moreover, these schemes create duplicate information in processor caches and therefore are inefficient in resource utilization. Hashing operates at the flow level and is naturally able to maintain per-connection packet ordering; besides, it does not pollute caches. A pure hash-based system, however, cannot balance processor load in the face of highly skewed flow-size distributions in the Internet; usually, adaptive methods are needed. In this paper, based on measurements of Internet traffic, we examine the sources of load imbalance in hash-based scheduling schemes. We prove that under certain Zipf-like flow-size distributions, hashing alone is not able to balance workload. We introduce a new metric to quantify the effects of adaptive load balancing on overall forwarding performance. To achieve both load balancing and efficient system resource utilization, we propose a scheduling scheme that classifies Internet flows into two categories: the aggressive and the normal, and applies different scheduling policies to the two classes of flows. Compared with most state-of-the-art parallel forwarding schemes, our work exploits flow-level Internet traffic characteristics.

Abstract—The sharing of caches among proxies is an important technique to reduce Web traffic, alleviate network bottlenecks, and improve response time of document requests. Most existing work on cooperative caching has been focused on serving misses collaboratively. Very few have studied the effect of cooperation on document placement schemes and its potential enhancements on cache hit ratio and latency reduction. In this paper, we propose a new document placement scheme which takes into account the contentions at individual caches in order to limit the replication of documents within a cache group and increase document hit ratio. The main idea of this new scheme is to view the aggregate disk space of the cache group as a global resource of the group and uses the concept of cache expiration age to measure the contention of individual caches. The decision of whether to cache a document at a proxy is made collectively among the caches that already have a copy of this document. We refer to this new document placement scheme as the Expiration Age-based scheme (EA scheme for short). The EA scheme effectively reduces the replication of documents across the cache group, while ensuring that a copy of the document always resides in a cache where it is likely to stay for the longest time. We report our study on the potentials and limits of the EA scheme using both analytic modeling and trace-based simulation. The analytical model compares and contrasts the existing (ad hoc) placement scheme of cooperative proxy caches with our new EA scheme and indicates that the EA scheme improves the effectiveness of aggregate disk usage, thereby increasing the average time duration for which documents stay in the cache. The trace-based simulations show that the EA scheme yields higher hit rates and better response times compared to the existing document placement schemes used in most of the caching proxies. Index Terms—Cooperative Web caching, document placement, distributed caching. 1

The load balancer is a fundamental building block for implementing high-throughput applications on multi-core architectures (e.g., network processors). In this paper, we consider two canonical load balancing schemes in the context of packet processing systems: (1) packet-level load balancing that determines the mapping of a packet to processor independently for each packet; and (2) flow-level load balancing that maps a flow to a processor and directs all subsequent packets of that flow to the mapped processor. By identifying the application, system, and trace characteristics that affect their relative performance, we address the fundamental question: under what operating conditions, should one choose packet-level load balancing over flow-level load balancing, and vice versa? 1

While cooperative DNS resolver systems, such as Co-DNS, have demonstrated improved reliability and performance over standard approaches, their security has been weaker, since any corruption or misbehavior of a single resolver can easily propagate throughout the system. We address this weakness in a new system called Confi-DNS, which augments the cooperative lookup process with configurable policies that utilize multi-site agreement and per-site lookup histories. Not only does Confi-DNS provide better security than cooperative approaches, but for up to 99.8 % of unique lookups, ConfiDNS exceeds the security of standard DNS resolvers. ConfiDNS provides these benefits while retaining the other benefits of CoDNS, such as incremental deployability, higher reliability, and improved performance, in some cases faster than CoDNS. 1