Sporadic multiprocessor Linux scheduler

The advent of multicore systems has renewed the interest of research community on real-time scheduling on multiprocessor systems. Real-time scheduling theory for uniprocessors is considered a mature research field, but real-time scheduling theory for multiprocessors is an emerging research field. Being part of this research community I have decided to implement the Sporadic Multiprocessor Linux Scheduler that implements a new real-time scheduling algorithm, which was designed to schedule real-time sporadic tasks on multiprocessor systems. This technical reports describes the implementation of the SMLS.

A complex protocol layer as a linux user-space process

With the current complexity of communication protocols, implementing its layers totally in the kernel of the operating system is too cumbersome, and it does not allow use of the capabilities only available in user space processes. However, building protocols as user space processes must not impair the responsiveness of the communication. Therefore, in this paper we present a layer of a communication protocol, which, due to its complexity, was implemented in a user space process. Lower layers of the protocol are, for responsiveness issues, implemented in the kernel. This protocol was developed to support large-scale power-line communication (PLC) with timing requirements.

Linux based mobile: operating systems

Trabalho de Projeto para obtenção do grau de Mestre em Engenharia Informática e de Computadores

Structure to function studies in UDP-glucose dehydrogenases and nitroreductases

The thesis is divided into two parts corresponding to structural studies on two different proteins. The first part concerns the study of two UDP-glucose dehydrogenases (UGDs) from Sphingomonas elodea ATCC 31461 and Burkholderia cepacia IST 408, both involved in exopolysaccharide production. Their relevance arises because some of these bacterial exopolysaccharides are valuable as established biotechnological products, the former case, whilst others are highly problematic, when used by pathogens in biofilm formation over biological surfaces, as the latter case, namely in the human lungs. The goal of these studies is to increase our knowledge regarding UGDs structural properties, which can potentiate either the design of activity enhancers to respond to the increased demand of useful biofilms, or the design of inhibitors of biofilm production, in order to fight invading pathogens present in several infections. The thesis reports the production and crystallisation of both proteins, the determination of initial phases by single-wavelength anomalous dispersion (SAD) in S. elodea crystals using a seleno-methionine isoform, and phasing of B. cepacia crystals by molecular replacement (MR) using the S. elodea model, as well as the refinement, structural analysis and comparison between the several UGDs structures available during this work.(...)

Multicore Scheduling of Real-Time Irregular Parallel Algorithms in Linux

Face à estagnação da tecnologia uniprocessador registada na passada década, aos principais fabricantes de microprocessadores encontraram na tecnologia multi-core a resposta `as crescentes necessidades de processamento do mercado. Durante anos, os desenvolvedores de software viram as suas aplicações acompanhar os ganhos de performance conferidos por cada nova geração de processadores sequenciais, mas `a medida que a capacidade de processamento escala em função do número de processadores, a computação sequencial tem de ser decomposta em várias partes concorrentes que possam executar em paralelo, para que possam utilizar as unidades de processamento adicionais e completar mais rapidamente. A programação paralela implica um paradigma completamente distinto da programação sequencial. Ao contrário dos computadores sequenciais tipificados no modelo de Von Neumann, a heterogeneidade de arquiteturas paralelas requer modelos de programação paralela que abstraiam os programadores dos detalhes da arquitectura e simplifiquem o desenvolvimento de aplicações concorrentes. Os modelos de programação paralela mais populares incitam os programadores a identificar instruções concorrentes na sua lógica de programação, e a especificá-las sob a forma de tarefas que possam ser atribuídas a processadores distintos para executarem em simultâneo. Estas tarefas são tipicamente lançadas durante a execução, e atribuídas aos processadores pelo motor de execução subjacente. Como os requisitos de processamento costumam ser variáveis, e não são conhecidos a priori, o mapeamento de tarefas para processadores tem de ser determinado dinamicamente, em resposta a alterações imprevisíveis dos requisitos de execução. `A medida que o volume da computação cresce, torna-se cada vez menos viável garantir as suas restrições temporais em plataformas uniprocessador. Enquanto os sistemas de tempo real se começam a adaptar ao paradigma de computação paralela, há uma crescente aposta em integrar execuções de tempo real com aplicações interativas no mesmo hardware, num mundo em que a tecnologia se torna cada vez mais pequena, leve, ubíqua, e portável. Esta integração requer soluções de escalonamento que simultaneamente garantam os requisitos temporais das tarefas de tempo real e mantenham um nível aceitável de QoS para as restantes execuções. Para tal, torna-se imperativo que as aplicações de tempo real paralelizem, de forma a minimizar os seus tempos de resposta e maximizar a utilização dos recursos de processamento. Isto introduz uma nova dimensão ao problema do escalonamento, que tem de responder de forma correcta a novos requisitos de execução imprevisíveis e rapidamente conjeturar o mapeamento de tarefas que melhor beneficie os critérios de performance do sistema. A técnica de escalonamento baseado em servidores permite reservar uma fração da capacidade de processamento para a execução de tarefas de tempo real, e assegurar que os efeitos de latência na sua execução não afectam as reservas estipuladas para outras execuções. No caso de tarefas escalonadas pelo tempo de execução máximo, ou tarefas com tempos de execução variáveis, torna-se provável que a largura de banda estipulada não seja consumida por completo. Para melhorar a utilização do sistema, os algoritmos de partilha de largura de banda (capacity-sharing) doam a capacidade não utilizada para a execução de outras tarefas, mantendo as garantias de isolamento entre servidores. Com eficiência comprovada em termos de espaço, tempo, e comunicação, o mecanismo de work-stealing tem vindo a ganhar popularidade como metodologia para o escalonamento de tarefas com paralelismo dinâmico e irregular. O algoritmo p-CSWS combina escalonamento baseado em servidores com capacity-sharing e work-stealing para cobrir as necessidades de escalonamento dos sistemas abertos de tempo real. Enquanto o escalonamento em servidores permite partilhar os recursos de processamento sem interferências a nível dos atrasos, uma nova política de work-stealing que opera sobre o mecanismo de capacity-sharing aplica uma exploração de paralelismo que melhora os tempos de resposta das aplicações e melhora a utilização do sistema. Esta tese propõe uma implementação do algoritmo p-CSWS para o Linux. Em concordância com a estrutura modular do escalonador do Linux, ´e definida uma nova classe de escalonamento que visa avaliar a aplicabilidade da heurística p-CSWS em circunstâncias reais. Ultrapassados os obstáculos intrínsecos `a programação da kernel do Linux, os extensos testes experimentais provam que o p-CSWS ´e mais do que um conceito teórico atrativo, e que a exploração heurística de paralelismo proposta pelo algoritmo beneficia os tempos de resposta das aplicações de tempo real, bem como a performance e eficiência da plataforma multiprocessador.

How to design and develop There App: A mobile app focused on live video streaming, promoting new social interactions

This work project aims to demonstrate how to design and develop an innovative concept of video streaming app. The project combines technology push and market pull theories into developing a product that is more suitable for the customer needs, with the particularity that there is no other way of seeing any place in the world, live and ondemand. An analysis on the bigger influencers in terms of design-thinking and new product development, as Tim Brown or Paul Trott, lead to a better understanding on how There App should evolve, keeping in mind the customer desires and technical features.

Underwater acoustic modem with streaming video capabilities

Oceans have shown tremendous importance and impact on our lives. Thus the need for monitoring and protecting the oceans has grown exponentially in recent years. On the other hand, oceans have economical and industrial potential in areas such as pharmaceutical, oil, minerals and biodiversity. This demand is increasing and the need for high data rate and near real-time communications between submerged agents became of paramount importance. Among the needs for underwater communications, streaming video (e.g. for inspecting risers or hydrothermal vents) can be seen as the top challenge, which when solved will make all the other applications possible. Presently, the only reliable approach for underwater video streaming relies on wired connections or tethers (e.g. from ROVs to the surface) which presents severe operational constraints that makes acoustic links together with AUVs and sensor networks strongly appealing. Using new polymer-based acoustic transducers, which in very recent works have shown to have bandwidth and power efficiency much higher than the usual ceramics, this article proposes the development of a reprogrammable acoustic modem for operating in underwater communications with video streaming capabilities. The results have shown a maximum data-rate of 1Mbps with a simple modulation scheme such as OOK, at a distance of 20 m.

Implementation of a unified userspace time handling library under the Linux OS

An appropriate assessment of end-to-end network performance presumes highly efficient time tracking and measurement with precise time control of the stopping and resuming of program operation. In this paper, a novel approach to solving the problems of highly efficient and precise time measurements on PC-platforms and on ARM-architectures is proposed. A new unified High Performance Timer and a corresponding software library offer a unified interface to the known time counters and automatically identify the fastest and most reliable time source, available in the user space of a computing system. The research is focused on developing an approach of unified time acquisition from the PC hardware and accordingly substituting the common way of getting the time value through Linux system calls. The presented approach provides a much faster means of obtaining the time values with a nanosecond precision than by using conventional means. Moreover, it is capable of handling the sequential time value, precise sleep functions and process resuming. This ability means the reduction of wasting computer resources during the execution of a sleeping process from 100% (busy-wait) to 1-1.5%, whereas the benefits of very accurate process resuming times on long waits are maintained.

Improving TCP Performance on CSMA/CA Connections

In IP networks, most of packets, that have been dropped, are recovered after the expiration of retransmission timeouts. These can result in unnecessary retransmissions and needless reduction of congestion window. An inappropriate retransmission timeout has a huge impact on TCP performance. In this paper we have proved that CSMA/CA mechanism can cause TCP retransmissions due to CSMA/CA effects. For this we have observed three wireless connections that use CSMA/CA: with good link quality, poor link quality and in presence of cross traffic. The measurements have been performed using real devices. Through tracking of each transmitted packet it is possible to analyze the relation between one-way delay and packet loss probability and the cumulative distribution of distances between peaks of OWDs. The distribution of OWDs and the distances between peaks of OWDs are the most important parameters of tuning TCP retransmission timeout on CSMA/CA networks. A new perspective through investigating the dynamical relation between one-way delay and packet loss ratio depending on the link quality to enhance the TCP performance has been provided.

ParallelKnoppix - Rapid deployment of a linux cluster for MPI parallel processing using non-dedicated computers

This note describes ParallelKnoppix, a bootable CD that allows creation of a Linux cluster in very little time. An experienced user can create a cluster ready to execute MPI programs in less than 10 minutes. The computers used may be heterogeneous machines, of the IA-32 architecture. When the cluster is shut down, all machines except one are in their original state, and the last can be returned to its original state by deleting a directory. The system thus provides a means of using non-dedicated computers to create a cluster. An example session is documented.

Automatización de la gestión del ciclo de vida de entornos Linux y Solaris

Los requisitos del Negocio que requieren un gran crecimiento generan mayor complejidad en los Centros de Cómputo.Son los administradores quienes necesitan gestionar el creciente volumen de datos, aplicaciones, y usuarios, así como la rápida proliferación de los servidores y los diferentes sistemas operativos. En este proyecto se pretende reducir la complejidad en la gestión de los Centros de Cómputo, combinando la automatización de la gestión del ciclo de vida y todas las medidas de contingencia necesarias para mantener la integridad de los mismos.

Derivation of soil-specific streaming potential electrical parameters from hydrodynamic characteristics of partially saturated soils

Water movement in unsaturated soils gives rise to measurable electrical potential differences that are related to the flow direction and volumetric fluxes, as well as to the soil properties themselves. Laboratory and field data suggest that these so-called streaming potentials may be several orders of magnitudes larger than theoretical predictions that only consider the influence of the relative permeability and electrical conductivity on the self potential (SP) data. Recent work has improved predictions somewhat by considering how the volumetric excess charge in the pore space scales with the inverse of water saturation. We present a new theoretical approach that uses the flux-averaged excess charge, not the volumetric excess charge, to predict streaming potentials. We present relationships for how this effective excess charge varies with water saturation for typical soil properties using either the water retention or the relative permeability function. We find large differences between soil types and the predictions based on the relative permeability function display the best agreement with field data. The new relationships better explain laboratory data than previous work and allow us to predict the recorded magnitudes of the streaming potentials following a rainfall event in sandy loam, whereas previous models predict values that are three orders of magnitude too small. We suggest that the strong signals in unsaturated media can be used to gain information about fluxes (including very small ones related to film flow), but also to constrain the relative permeability function, the water retention curve, and the relative electrical conductivity function.

Could cell membranes produce acoustic streaming? Making the case for synechococcus self-propulsion

Sir James Lighthill proposed in 1992 that acoustic streaming occurs in the inner ear, as part of the cochlear amplifier mechanism. Here we hypothesize that some of the most ancient organisms use acoustic streaming not only for self-propulsion but also to enhance their nutrient uptake. We focus on a motile strain of Synechococcus, a yanobacteria whose mechanism for self-propulsion is not known. Molecular motors could work like piezoelectric transducers acting on the crystalline structure surrounding the outer cell membrane. Our calculations show that a traveling surface acoustic wave (SAW)could account for the observed velocities. These SAW waves will also produce a non-negligible Stokes layer surrounding the cell: motion within this region being essentially chaotic. Therefore, an AS mechanism would be biologically advantageous, enhancing localized diffusion processes and consequently, chemical reactions. We believe that acoustic streaming, produced by nanometer scale membrane vibrations could be widespread in cell biology. Other possible instances are yeast cells and erythrocytes. Flows generated by acoustic streaming may also be produced by silica coated diatoms along their raphe. We note that microelectromechanical (MEMS) acoustic streaming devices were first introduced in the 1990’s. Nature may have preceded this invention by 2.7 Gyr.

Comment on "Streaming potential dependence on water-content in Fontainebleau sand" by V. Allegre, L. Jouniaux, F. Lehmann and P. Sailhac

Allegre et al. recently presented new experimental data regarding the dependence of the streaming potential coupling coefficient with the saturation of the water phase. Such experiments are important to model the self-potential response associated with the flow of water in the vadose zone and the electroseismic/seismoelectric conversions in unsaturated porous media. However, the approach used to interpret the data is questionable and the conclusions reached by Allegre et al. likely incorrect