Lars Rasmusson

Tycoon: An implementation of a distributed, market-based resource allocation system

Distributed clusters like the Grid and PlanetLab enable the same statistical multiplexing efficiency gains for computing as the Internet provides for networking. One major challenge is allocating resources in an economically efficient and low-latency way. A common solution is proportional share, where users each get resources in proportion to their pre-defined weight. However, this does not allow users to differentiate the value of their jobs. This leads to economic inefficiency. In contrast, systems that require reservations impose a high latency (typically minutes to hours) to acquire resources. This paper describes Tycoon, a market based distributed resource allocation system based on proportional share. The key advantages of Tycoon are that it allows users to differentiate the values of their jobs, its resource acquisition latency is limited only by communication delays, and it imposes no manual bidding overhead on users. Experimental results using a prototype implementation of the design are included.

Simulated social control for secure Internet commerce

In this paper we suggest that soft security such as social COIIt.rol has to Ire used to create secure open systems. Social co7Ltrol 7nearls that it is the participants the7nselves who are responsible for the security, as opposed to leaving the security to sonle external or global authority. Social mechanisms don’t deny the. existe7rce of 7nalicious participants. Instead the?/ are aiming at avoiding interaction with them. This 7nakes them more robust than hard security mechnnisms such as passwo7.ds, who reveal everythi7Lg if they are bypassed. We describe our work in progress of constructing a workbench to ru71 sirnulatiorls uf electronic markets. By examining the success of different security mechanisms to avoid 7naliciously behaving actors we hope to gain insight into how to create electronic markets. The idea of creating reputations for the participants is discussed. Finally some legal aspects on using social control and reputation as security mechanisms are discussed.

Agents, self-interest and electronic markets

How free are our software agents to take the best possible care of our interests? How free can we make them? In what sense and to what extent do currently proposed mechanisms and agent behaviors consider self-interest? What current research addresses these issues? What needs to be done? We address these issues in the context of electronic markets, such as consumer goods markets and (future, more fine-grained) markets for electric power or communication bandwidth.

Performance overhead of KVM on Linux 3.9 on ARM cortex-a15

A number of simple performance measurements on network, CPU and disk speed were done on a dual ARM Cortex-A15 machine running Linux inside a KVM virtual machine that uses virtio disk and networking. Unexpected behaviour was observed in the CPU and memory intensive benchmarks, and in the networking benchmarks. The average overhead of running inside KVM is between zero and 30 percent when the host is lightly loaded (running only the system software and the necessary qemu-system-arm virtualization code), but the relative overhead increases when both host and VM is busy. We conjecture that this is related to the scheduling inside the host Linux.

Analytical expressions for Parrondo games

We present some new analytical expressions for the so-called Parrondo effect, where simple coin-flipping games with negative expected value are combined into a winning game. Parrondo games are state-dependent. By identifying the game state variable, we can compute the stationary game state probabilities. Mixing losing games increases the probability of entering into a game state with positive value, as can be seen clearly from our analytical expressions for the Parrondo game value.

BEAMJIT: a just-in-time compiling runtime for Erlang

BEAMJIT is a tracing just-in-time compiling runtime for the Erlang programming language. The core parts of BEAMJIT are synthesized from the C source code of BEAM, the reference Erlang abstract machine. The source code for BEAMs instructions is extracted automatically from BEAMs emulator loop. A tracing version of the abstract machine, as well as a code generator are synthesized. BEAMJIT uses the LLVM toolkit for optimization and native code emission. The automatic synthesis process greatly reduces the amount of manual work required to maintain a just-in-time compiler as it automatically tracks the BEAM system. The performance is evaluated with HiPEs, the Erlang ahead-of-time native compiler, benchmark suite. For most benchmarks BEAMJIT delivers a performance improvement compared to BEAM, although in some cases, with known causes, it fails to deliver a performance boost. BEAMJIT does not yet match the performance of HiPE mainly because it does not yet implement Erlang specific optimizations such as boxing/unboxing elimination and a deep understanding of BIFs. Despite this BEAMJIT, for some benchmarks, reduces the runtime with up to 40%.

Qualitative policies for bandwidth priorities in ad-hoc networks

The Analytic Hierarchic Process (AHP) is used for presenting a method for setting up policies that define priorities among services sharing a limited measure of bandwidth in an ad-hoc radio network. We examine the issue of ensuring the autonomy of the users of the bandwidth, as well as the issue of ensuring that the priority policies result in efficient bandwidth usage even when the priority decisions involve uncertainty about the dynamics of the network and the services.