Uli Harder

GILK: A Dynamic Instrumentation Tool for the Linux Kernel

This paper describes a dynamic instrumentation tool for the Linux Kernel which allows a stock Linux kernel to be modified while in execution, with instruments implemented as kernel modules. The Intel x86 architecture poses a particular problem, due to variable length instructions, which this paper addresses for the first time. Finally we present a short case study illustrating its use in understanding i/o behaviour in the kernel. The source code is freely available for download.

Observing Internet Worm and Virus Attacks with a Small Network Telescope

A network telescope is a portion of IP address space dedicated to observing inbound internet traffic. The purpose of a network telescope is to detect and log malicious traffic which originates from internet worms and viruses. In this paper, we investigate the statistical properties of observed traffic from a passive Class C telescope over a total of three months. We observe that only a few IP sources and destination ports are responsible for the majority of the traffic. We also demonstrate various ways to visualise the traffic profile from a telescope. We show that specific profiles can identify and distinguish portscans, hostscans and distributed denial-of-service (DDOS) attacks. Looking at the inter-arrival time of packets, the power spectrum and the detrended fluctuation analysis of the observed traffic, we show that there is very little sign of long-range dependence. This is in stark contrast to other network traffic and presents exciting possibilities for identifying malicious traffic purely from its traffic profile.

Network traffic behaviour in switched Ethernet systems

Measurements on a high-performance Ethernet are shown to match well a truncated Cauchy probability distribution, with a much better fit over smaller file/request sizes than the commonly used Pareto distribution. We observe self-similar characteristics in the traffic at both file servers and at a CPU server elsewhere in the network, which targets, predominantly, file and web servers. This suggests propagation of self-similarity. A simulation model of a single server with Poisson arrivals and Cauchy service demands yields a departure process that follows a power law and matches closely the observed traffic. The simulation is also used to investigate the link between the power laws in the request size distribution and the network traffic by using Levy distributions for the request sizes. This suggests a link between file/request size distribution and self-similarity in traffic, leading to the possibility of using conventional queueing network performance models with processor sharing queueing discipline. This idea is further supported by an additional simulation experiment and suitable models are proposed.

Fluid Queue Models of Battery Life

We investigate how a power-save mode affects the battery life of a device subject to stochastically determined charging and discharging periods. We use a multi-regime fluid queue, imposing a threshold at some value. When the power level falls below the threshold, (for example, 20% of charge remaining) a power-save mode is entered and the rate of discharge decreased. An expression for the Laplace transform of the battery lifes probability density function is found and inverted numerically in particular instances. We show the life of battery can be significantly improved by the introduction of the power-saving threshold.

Simulation of a Peer to Peer Market for Grid Computing

In this paper we investigate the market economy of a Peer-to-Peer network for Grid Computing. We present a simulation of P2P network where nodes either require or offer resources, which can be thought as CPU time for example. We examine the market behaviour of the P2P network for Erdős-Renyi and Barabasi-Albert networks types of different sizes ranging from 4,096 nodes to 1,048,576 nodes. We find that utilisation and market behaviour depend on the network type but not the size. Similarly, different price update algorithms have little effect on the price development, which is more determined by the network type. We also measure the average buffer size and number of messages in the system. For the Barabasi-Albert network, we find that the buffer size of each node has an effect on the price development in the system. The results are useful to guide designers of P2P Grid computing systems, like the Global Open Grid.

A likelihood based framework for assessing network evolution models tested on real network data

This paper presents a statistically sound method for using likelihood to assess potential models of network evolution. The method is tested on data from five real networks. Data from the internet autonomous system network, from two photo sharing sites and from a co-authorship network are tested using this framework.

Computer Performance Evaluation: Modelling Techniques and Tools

This paper considers the M/G/1 queue with regularly varying service requirement distribution. It studies the effect of the service discipline on the tail behavior of the waitingor sojourn time distribution, demonstrating that different disciplines may lead to quite different tail behavior. The orientation of the paper is methodological: We outline three different methods of determining tail behavior, illustrating them for service disciplines like FCFS, Processor Sharing and LCFS. This paper is dedicated to the memory of Vincent Dumas, a dear friend and gifted young mathematician.

Energy consumption in the office

In this paper we present measurements of energy usage of standard office computing equipment. Using a data trace lasting for all of March 2012 we analyse the energy use of office equipment such as desktop computers, a printer and a fridge. The interest in a more detailed knowledge of the energy usage patterns of these appliances is driven by the desire to manage, and if possible reduce, the energy consumption of computing equipment in a university department. The reason behind this can be financial to reduce electricity costs and/or environmental to reduce the carbon foot print of an office environment. We analyse the data and show simple autoregressive time series models to predict the energy usage of appliances. We also show that its feasible to accurately approximate the power consumption of a desktop computer using the CPU utilisation information. We describe a future set-up where we plan to monitor the energy usage of a student lab.

A More Realistic Peer-to-Peer Grid Market Model

In this paper we investigate the behaviour of a peer to peer driven Grid computing network. We present mean field approximation of the simulation model and show that it captures the essence of the model. In contrast to earlier work we limit the budget of the nodes and observe the consequences for the price development. We also show that the proposed peer to peer network scales much better than a central server approach. By allowing the agents in the simulation to hibernate and change the price individually only using local information the price development of the model becomes stable. Lastly we investigate the distribution of the times the agents wait to sell or buy resources.

A markovian futures market for computing power

In this paper we describe aspects of a market model for Grid computing. In particular we concentrate on Grid computing provided by a peer-to-peer network architecture. In this network nodes can either buy or sell computing power in exchange for money. Building on previous publications we develop a mathematical market model using Markov chains. The behaviour of each agent in the market is described by a Markov chain of decisions on buying, selling or holding. Considering the contributions of all agents, we calculate the global Markov chain of the market state as a whole, by making use of a concept of market pressure that reduces the state space of the entire market model. We show that the Markov chain model describes the market behaviour seen in a simulation extremely well. In a similar way to other perishable commodity markets like fish and electricity, we also provide a model for trading future contracts on the purchase and sale of computing power in this market. Using Markov Decision Processes we derive an optimal trading strategy. This work introduces a pioneer mathematical model for future global peer-to-peer Grid computing architectures like MaGoG (Middleware for activating the Global open Grid), where we have derived a global transition probability matrix that determines the behaviour of the market by summing up the contributions of different kinds of market participants.