Reducing cache lookup and publish overhead through locality awareness in P2P web caching

Peer-to-Peer (P2P) Web caching has been a hot research topic in recent years as it can create scalable and robust designs for decentralized Internet-scale applications. However, many P2P Web caching systems suffer expensive overheads such as lookup and publish messages, and lack of locality awareness. In this paper we present the development of a locality aware P2P cache system to overcome these limitations by using routing table locality, aggregation and soft state. The experiments show that our P2P cache system improves the performance of index operations through the reduction of the amount of information processed by nodes, the reduction of the number of index messages sent by nodes, and the improvement of the locality of cache pointers.

Cache and replica lookup, indexing and synchronization in P2P environments

The major outcomes of this research project were the development of a set of decentralized algorithms to index, locate and synchronize replicated information in a networked environment. This study exploits the application specific design constraints of networked systems to improve performance, instead of relying on data structures and algorithms best suited to centralized systems.

Adjacency cache : an efficient P2P web cache indexing and lookup system

This paper describes the design and evaluation of an efficient per-to-peer (P2P) web cache indexing and lookup system, which can be used to integrate the resources of locally available web pages into globally addressable index using a distributed hash table. The salient feature of the indexing system’s design is the efficient dissemination of cache index information using a next-url index which allows cache clients to determine ahead of time whether linked content is also available at a remote cache. In addition, conventional optimizations such as in browser caching and batching of index write requests are also used. These optimizations are evaluated using trace-driven simulation and the results show that these design trade-offs improve cache lookup performance.

A locality aware cache diffusion system

Web caching is a widely deployed technique to reduce the load to web servers and to reduce the latency for web browsers. Peer-to-Peer (P2P) web caching has been a hot research topic in recent years as it can create scalable and robust designs for decentralized internet-scale applications. However, many P2P web caching systems suffer expensive overheads such as lookup and publish messages, and lack locality awareness. In this paper, we present the development of a locality aware cache diffusion system that makes use of routing table locality, aggregation, and soft state to overcome these limitations. The analysis and experiments show that our cache diffusion system reduces the amount of information processed by nodes, reduces the number of index messages sent by nodes, and improves the locality of cache pointers.

CAFS : a novel lightweight cache-based scheme for large-scale intrusion alert fusion

In this paper, we present some practical experiences on implementing an alert fusion mechanism from our project. After investigation on most of the existing alert fusion systems, we found the current body of work alternatively weighed down in the mire of insecure design or rarely deployed because of their complexity. As confirmed by our experimental analysis, unsuitable mechanisms could easily be submerged by an abundance of useless alerts. Even with the use of methods that achieve a high fusion rate and low false positives, attack is also possible. To find the solution, we carried out analysis on a series of alerts generated by well-known datasets as well as realistic alerts from the Australian Honey-Pot. One important finding is that one alert has more than an 85% chance of being fused in the following five alerts. Of particular importance is our design of a novel lightweight Cache-based Alert Fusion Scheme, called CAFS. CAFS has the capacity to not only reduce the quantity of useless alerts generated by intrusion detection system, but also enhance the accuracy of alerts, therefore greatly reducing the cost of fusion processing. We also present reasonable and practical specifications for the target-oriented fusion policy that provides a quality guarantee on alert fusion, and as a result seamlessly satisfies the process of successive correlation. Our experiments compared CAFS with traditional centralized fusion. The results showed that the CAFS easily attained the desired level of simple, counter-escapable alert fusion design. Furthermore, as a lightweight scheme, CAFS can easily be deployed and excel in a large amount of alert fusions, which go towards improving the usability of system resources. To the best of our knowledge, our work is a practical exploration in addressing problems from the academic point of view. Copyright © 2011 John Wiley & Sons, Ltd.

A cooperative cache architecture in support of caching multimedia objects in MANETs

This paper presents a cooperative caching architecture suitable for continuous media (CM) proxy caching in MANET environments. The proposed scheme introduces an application manager component, which is interposed between traditional Internet CM applications and the network layer. The application manager transparently performs data location and service migration of active CM streaming sessions so as to exploit nearby data sources based on the dynamic topology of a MANET. We propose two data location schemes - Cache-State - a link-state based scheme and Reactive - an on-demand scheme. Since service migration can occur frequently, the application manager uses soft-state signaling techniques to communicate between remote application managers by translating hard-state application signaling, such as Real Time Streaming Protocol (RTSP) into soft-state messages. The proposed schemes are evaluated through simulation studies using the NS simulator. Simulation studies show that both Cache-State and Reactive schemes demonstrate significant QoS improvements and reduced bandwidth consumption.

A flexible receiver-driven cache replacement scheme for continuous media objects in best-effort networks

In this paper, we investigate the potential of caching to improve quality of reception (QoR) in the context of continuous media applications over best-effort networks. Specifically, we investigate the influence of parameters such as loss rate, jitter, delay and area in determining a proxy's cache contents. We propose the use of a flexible cost function in caching algorithms and develop a framework for benchmarking continuous media caching algorithms. The cost function incorporates parameters in which, an administrator and or a client can tune to influence a proxy's cache. Traditional caching systems typically base decisions around static schemes that do not take into account the interest of their receiver pool. Based on the flexible cost function, an improvised Greedy Dual (GD) algorithm called GD-multi has been developed for layered multiresolution multimedia streams. The effectiveness of the proposed scheme is evaluated by simulation-based performance studies. Performance of several caching schemes are evaluated and compared with those of the proposed scheme. Our empirical results indicate GD-multi performs well despite employing a generalized caching policy.

A cache-based mobility-aware scheme for real-time continuous media delivery in wireless networks

Providing real-time or continuous media (CM) application services in wireless networks poses a significant challenge, as it requires timely delivery of data in a best-effort network. In this paper, we propose a cache-based scheme for mobility-aware, CM applications. The proposed scheme exploits a previously proposed caching strategy to complement Mobile-IP by placing services closer to migrated mobile nodes. The central idea of this work is based on the migration of sessions in order to facilitate uninterrupted delivery of CM in mobile environments. The performance of the proposed scheme is investigated by simulation studies. In particular, the effect of the proposed scheme on several QoS parameters under varying conditions of mobility and CM data is measured.

Cache and carry : hoarding behavior of arctic fox

Food-hoarding animals are expected to preferentially cache items with lower perishability and/or higher consumption time. We observed arctic foxes (Alopex lagopus) foraging in a greater snow goose (Anser caerulescens atlanticus) colony where the main prey of foxes consisted of goose eggs, goslings, and lemmings (Lemmus and Dicrostonyx spp.). We recorded the number of prey consumed and cached and the time that foxes invested in these activities. Foxes took more time to consume a goose egg than a lemming or gosling but cached a greater proportion of eggs than the other prey type. This may be caused by the eggshell, which presumably decreases the perishability and/or pilfering risk of cached eggs, but also increases egg consumption time. Arctic foxes usually recached goose eggs but rarely recached goslings or lemmings. We tested whether the rapid-sequestering hypothesis could explain this recaching behavior. According to this hypothesis, arctic foxes may adopt a two-stage strategy allowing both to maximize egg acquisition rate in an undefended nest and subsequently secure eggs in potentially safer sites. Foxes spent more time carrying an egg and traveled greater distances when establishing a secondary than a primary cache. To gain further information on the location and subsequent fate of cached eggs, we used dummy eggs containing radio transmitters. Lifespan of primary caches increased with distance from the goose nest. Secondary caches were generally located farther from the nest and had a longer lifespan than primary caches. Behavioral observations and the radio-tagged egg technique both gave results supporting the rapid-sequestering hypothesis.

AMC: an adaptive multi-level cache algorithm in hybrid storage systems

Hybrid storage systems that consist of flash-based solid state drives (SSDs) and traditional disks are now widely used. In hybrid storage systems, there exists a two-level cache hierarchy that regard dynamic random access memory (DRAM) as the first level cache and SSD as the second level cache for disk storage. However, this two-level cache hierarchy typically uses independent cache replacement policies for each level, which makes cache resource management inefficient and reduces system performance. In this paper, we propose a novel adaptive multi-level cache (AMC) replacement algorithm in hybrid storage systems. The AMC algorithm adaptively adjusts cache blocks between DRAM and SSD cache levels using an integrated solution. AMC uses combined selective promote and demote operations to dynamically determine the level in which the blocks are to be cached. In this manner, the AMC algorithm achieves multi-level cache exclusiveness and makes cache resource management more efficient. By using real-life storage traces, our evaluation shows the proposed algorithm improves hybrid multi-level cache performance and also increases the SSD lifetime compared with traditional multi-level cache replacement algorithms.