Newsletter Downloads
Guest editor's foreword
Performance 2005, the 24-th International Symposium on Computer Performance, Modeling, Measurements and Evaluation, was held in Juan-les-Pins, France, on October 3-7, 2005. In addition to the main technical program, a poster session was organized so ...
Extinction probability in peer-to-peer file diffusion
Recent measurement studies [8] have shown that peer-to-peer (P2P) file sharing applications are the major traffic source in the Internet. P2P applications, such as eDonkey, Kazaa, or BitTorrent, form overlay networks on the application layer and offer ...
Analysis of peer-to-peer file dissemination amongst users of different upload capacities
In recent years, overlay networks have proven an effective way of disseminating a file from a single source to a group of end users via the Internet. A number of algorithms and protocols have been suggested, implemented and studied. In particular, much ...
The GAIA sensor: an early DDoS detection tool
Distributed Denial of Service (DDoS) attacks are a major network security threat. Most recent host-based DDoS detection mechanisms are dedicated to a particular set of attacks, focusing either on the recent dynamic of the traffic, or on its long range ...
Probability of connection in regular stochastic networks
In this paper, we report experiments we did on network reliablity with the BDD-based exact method we present in [1].
Bounding transient and steady-state dependability measures through algorithmic stochastic comparison
We are interested in bounding dependability measures like point and steady-state availability and reliability of systems modelled by very large Markov chains which are not numerically tractable. We suppose that the state space is divided into two ...
On checkpointing and heavy-tails in unreliable computing environments
In this paper, we discuss checkpointing issues that should be considered whenever jobs execute in unreliable computing environments. Specifically, we show that if proper check-pointing procedures are not properly implemented, then under certain ...
Improving distributed system performance using machine availability prediction
In a distributed system, a set of networked machines provides a highly available service to remote clients. Traditional distributed systems like AFS [2] make a clear distinction between clients and servers. Client machines may be poorly administered, ...
Buffer overflow calculations in a batch arrival queue
In this paper numerical calculations of the buffer overflow time in a batch arrival queueing system are presented. The results indicate that an auto-correlated input stream, heavy-tailed batch size or service time distribution have a critical influence ...
Evaluating caching policies for online auctions
Auction sites have grown rapidly in the last couple of years and recent statistics indicate that eBay carries about 50 million items for sale at any time on its site [2]. Our previous work showed that the workload of online auction sites is ...
Perfect simulation of index based routing queueing networks
Markovian queueing networks models are widely used for performance evaluation of computer systems, production lines, communication networks and so on. Routing strategies allocate clients to queues after the end of service. In many situations such as ...
From switching theory to "queueing" theory
Queueing theory is generally known as the theory to study the performance of queues. In this extended abstract, we are interested in another aspect of queueing theory, the theory to construct queues. Our interest in constructing queues originates from ...
Cross-layer power control in wireless networks
We introduce a power control algorithm that exploits queue length information to achieve maximum data throughput in single-hop CDMA wireless networks. The algorithm operates in real-time, i.e., executes a single iteration per data transmission. A ...