Xavier Molero

Polytechnical University of Valencia, Valenza, Valencia, Spain

Are you Xavier Molero?

Claim your profile

Publications (20)0 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Cache memories are widely used to improve computer performance, but their inherent unpredictability presents new problems when cached systems must be analysed. In preemptive, multitask real-time systems, the cache memories have been analysed from two complementary points of view. First, calculating the Worst Case Execution Time #WCET# of each task considering no preemptions. Second, making the schedulability analysis considering the e#ect of cache when tasks are preempted.
    08/2003;
  • Xavier Molero, Vicente Santonja
    Proceedings of the 16th European Simulation Multiconference on Modelling and Simulation 2002; 01/2002
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Parallel simulation methods can be used to reduce the execution time of the simulations of complex systems. In this context, we apply the method of the replications in parallel in order to reduce the execution time of the models. The particular technique consists of starting a fixed number of replications that are maintained in execution until a stop criterion is achieved. Different stopping criteria can be used in order to finish the simulation. These criteria must be robust in order to provide results according the applied statistical theory. The results obtained with two habitual criteria applied to a simple simulation model show that it is necessary to provide more elaborated stopping criteria of the simulation in order to obtain the adequate coverage. In order to reduce the detected problems we propose a new stopping criterion that increments the coverage of the true mean. The analysis of performance shows that, obviously, this better coverage has the cost of more simulation time, but it is important to get results statistically correct.
    01/2002;
  • [Show abstract] [Hide abstract]
    ABSTRACT: The fast growth of data intensive applications has caused a change in the traditional storage model. The server-to-disk approach is being replaced by storage area networks (SANs), which enable storage to be externalized from servers, thus allowing storage devices to be shared among multiple servers. Nowadays, the majority of SANs use fibre channel. The standard for fibre channel defines several issues related to the switch interface, but does not make any suggestion about the internal switch architecture to be implemented by manufacturers. We analyze the key architectural switch characteristics for building fibre channel storage area networks. To do so, our starting point is the performance analysis of two different switch architectures, identifying their strongest and weakest points, and thus taking advantage of the best features from both of them. After this first analysis, we introduce several other features in the switch, concluding with a proposed architecture that doubles network throughput while reducing response delay
    Parallel and Distributed Systems, 2001. ICPADS 2001. Proceedings. Eighth International Conference on; 02/2001
  • [Show abstract] [Hide abstract]
    ABSTRACT: Traffic in a Storage Area Networks is bimodal, composed of long messages carrying several KBytes of data, and short messages containing control information (I/O commands). From the network point of view, latency of control messages is highly affected by the transmission of data messages, due to their length. As a consequence, it is necessary to establish management policies that benefit the transmission of short control messages, thus reducing the overall response time for I/O operations and increasing network throughput. In this paper we propose several strategies for dealing with short control messages and analyze their impact on the performance of storage area networks. This analysis is carried out for a fully adaptive routing algorithm in the context of two different network topology environments: buildings and departments. Simulation results show that both I/O response time and network throughput may be improved when efficiently managing control messages.
    Euro-Par 2001: Parallel Processing, 7th International Euro-Par Conference Manchester, UK August 28-31, 2001, Proceedings; 01/2001
  • [Show abstract] [Hide abstract]
    ABSTRACT: Nowadays, the fast growth of data intensive applications is changing the way storage is devised. The traditional server-to-disk approach is being replaced by storage area networks (SANs), which are a separate network for storage, isolated from the messaging network and optimized for the movement of data between servers and storage devices (usually disks). We analyze the performance and cost scalability of a family of network topologies devised to be used in building environments. Performance simulation results combined with cost estimations have revealed that slight modifications in network topology can affect the overall scalability. In particular wraparound links connecting the lowest and highest floors in the building significantly affect the scalability of the network. Anyway, the use of this kind of links by itself does not provide the best solution. It is also necessary to have a good interconnection pattern in the backbone
    IEEE International Symposium on Network Computing and Applications (NCA 2001), October 8-10, 2001, Cambridge, MA, USA; 01/2001
  • [Show abstract] [Hide abstract]
    ABSTRACT: Networks of workstations (NOWs) are becoming an increasingly popular alternative to parallel computers for those applications with high needs of resources such as memory capacity and input/output storage space, and also for small scale parallel computing. Usually, the software messaging layers in these systems become a bottleneck due to the overhead they introduce. Some proposals like FM and BIP considerably reduce this overhead by splitting long messages into several packets. These proposals have been shown to improve communication performance. However, the effect of message packetization on the network interconnects has not been analyzed yet. In this paper we examine the effect of message packetization from the point of view of the interconnection network in the context of bimodal traffic. Two different routing algorithms have been considered: up*/down* and minimal adaptive routing. Our study shows that when the up */down* routing algorithm is used, message packetization dramatically increases latency and reduces throughput for both long and short messages. On the other hand, if minimal adaptive routing is used, short messages could benefit from message packetization, but at the cost of increasing latency for long messages. In any case, network throughput is considerably reduced
    Ninth Euromicro Workshop on Parallel and Distributed Processing, PDP 2001, 7-9 February 2001, Mantova, Italy; 01/2001
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Parallel simulation methods can be used to reduce the execution time of simulations of complex systems. This approach is being used to improve the execution time of a storage area network (SAN) simulator designed in our department. From our experience in planning simulation experiments, we have realized that, in most cases, a simulation experiment (group of simulations) is executed while varying only one input variable, which usually corresponds to the input, workload or a configuration model parameter. We propose two methods to reduce the overall execution time of a simulation experiment using a cluster of workstations. The first method uses the first simulation in order to tune the rest of the remaining work to be done in the experiment. The second method, based in the first one, tries to minimize the negative influence of the initial transient period by chaining the simulations in the experiment. We show that these two methods noticeably decrease the overall execution time needed to run the simulations that compose the experiment
    Proceedings 34th Annual Simulation Symposium (SS 2001), Seattle, WA, USA, 22-26 April 2001; 01/2001
  • [Show abstract] [Hide abstract]
    ABSTRACT: Clusters of workstations are becoming an interesting alternative to parallel computers for those applications with high needs of resources such as memory, processing powe< and input/output storage capacity. Also, the fast growth of data intensive applications has caused a change in the traditional storage model. The server-to-disk approach is being replaced by storage area networks (SANS). SANS are a separate network for storage, isolated from the messaging network and optimized for the movement of data between servers and storage devices. Depending on the required network size and the environment targeted for the SAN, different interconnection topologies may be advisable, affecting both performance and cost. Moreove~ for a given topology, the routing algorithm used by messages also influences network performance. In this paper we analyze the impact of network topology on both performance and cost of storage area networks. This analysi,s is pe~ormedfor up */down* and minimal adaptive routin,g in the context of two different environments: buildings and departments. We show that depending on the network topology and the routing scheme, differences in the pe~ormance/cost ratio may increase by a factor of up to 6. Moreove~ we demonstrate that slightly modifiing the network topology, such as adding a few new links, we can noticeably improve the overall performance without significantly affecting the total cost.
    Proceedings of the 15th International Parallel & Distributed Processing Symposium (IPDPS-01), San Francisco, CA, April 23-27, 2001; 01/2001
  • [Show abstract] [Hide abstract]
    ABSTRACT: The fast growth of data intensive applications has caused a change in the traditional storage model. The server-to-disk approach, usually implemented with SCSI buses, is being replaced by storage area networks (SAN), which enable storage to be externalized from servers, thus allowing storage devices to be shared among multiple servers. A SAN is a separate network for storage, isolated from the messaging network and optimized for the movement of data between servers and storage devices. Nowadays, most current SAN use Fibre Channel as the technology to move data between servers and storage devices. In order to design and evaluate the performance of these systems it is necessary to have adequate tools. Usually, performance evaluation may be based on analytical modeling or simulation. Each of them differs in their scope and applicability or simulation modeling technique offers more freedom, flexibility, and accuracy than analytical methods. Thus, when evaluating the performance of SAN, simulation modeling should be used. We present the main capabilities of a simulator for Fibre Channel SAN, focusing on its input parameters and output variables. We also show several simple examples of performance measurements that can be obtained using this tool
    Proceedings 34th Annual Simulation Symposium (SS 2001), Seattle, WA, USA, 22-26 April 2001; 01/2001
  • [Show abstract] [Hide abstract]
    ABSTRACT: Storage Area Networks (SANs) are an emerging data communications platform, which interconnects servers and storage devices (such as disks, disk arrays, and tape drives) to create a pool of storage that users can access directly. This networking approach reports benefits such as computer clustering, topological flexibility, fault tolerance, high availability, and remote management.In order to evaluate the performance of these systems it is necessary to have the adequate tools. Usually, performance evaluation may be based on analytical modeling or simulation. Each of them differs in their scope and applicability. However, the simulation modeling technique offers more freedom, flexibility, and accuracy than the analytical methods. Thus, when evaluating the performance of SANs, simulation modeling should be used.In this paper, the issues involved in the modeling and design of a very flexible and easy to use SAN simulator are presented. This tool is able to consider, among others, both real-world I/O traces and synthetic I/O traffic, message paquetization, faults in links and switches, virtual channels, different routing algorithms, etc. We describe its main internal organization, the basic modeling mechanisms the simulator is based on, and the main input parameters and output performance variables. In addition, the analysis of preliminary results using I/O traces is presented, showing that the storage network increases self-similarity of the traffic received by servers, latency variations are more important for control messages than for data messages, and links have a low utilization.
    2012 IEEE 20th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems. 02/2000;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract The fast growth of data intensive applications has caused a change in the traditional storage model. The server- to-disk approach is being replaced by storage area net- works (SANS), which enable storage to be externalizedfrom servers, thus allowing storage devices to be shared among multiple servers. The prominent technology for implement- ing SANs is Fibre Channel, due to its suitability for storage networking. Although the probability of a link failure for individual links in a SAN is very low, this probability dramatically in- creases as the network size becomes larger. Moreover, there are external factors, such as accidental link disconnections, that also can affect the overall SAN reliability, Until the faulty element is replaced, the SAN is functioning in a de- graded mode. In this paper we analyze by simulation the performance degradation of Fibre Channel storage area networks when failures in links occur, quantifying how much the global SAN performance is reduced during the time the system re- mains in the degraded state. We perform this analysis by using both synthetic and real It0 trafslc. Simulation results show that performance degradation mainly depends on the routing algorithm and the switch architecture used.
    5th International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN 2000), 7-10 December 2000, Dallas / Richardson, TX, USA; 01/2000
  • [Show abstract] [Hide abstract]
    ABSTRACT: Networks of workstations (NOWs) are becoming an increasingly popular alternative to parallel computers for those applications with high needs of resources such as memory capacity and input/output storage space, and also for small scale parallel computing. Although the mean time between failures (MTBF) for individual links and switches in a NOW isvery high, the probability of a failure occurrence dramatically increases as the network size becomes larger. Moreover, there are external factors, such as accidental link disconnections, that also can aÿect the overall NOW reliability. Until the faulty element is replaced, the NOW is functioning in a degraded mode. Thus, it becomes necessary to quantify how much the global NOW performance is reduced during the time the system remains in this state. In this paper we analyze the performance degradation of networks of workstations when failures in links or switches occur. Because the routing algorithm is a key issue in the design of a NOW, we quantify the sensitivity to failures of two routing algorithms: up*/down* and minimal adaptive routing algorithms. Simulation results show that, in general, up*/down* routing is highly robust to failures. On the other hand, the minimal adaptive routing algorithm presents a better performance, even in the presence of failures, but at the expense of a larger sensitivity.
    High Performance Computing, Third International Symposium, ISHPC 2000, Tokyo, Japan, October 16-18, 2000. Proceedings; 01/2000
  • [Show abstract] [Hide abstract]
    ABSTRACT: Storage Area Networks (SANs) are an emerging data communications platform, which interconnects servers an storage devices (such as disks, disk arrays, and tape drives) to create a pool of storage that users can access directly. SANs eliminate the bandwidth bottlenecks and scalability limitations imposed by previous SCSI bus-based architectures and LAN connections between servers and the stored data. This networking approach reports benefits such as computer clustering, topological flexibility, fault tolerance, high availability, and remote management. The prominent technology for implementing SANs is Fibre Channel, due to the suitability of this technology for storage networking. Recently, other technologies for high performance interconnects have been developed. These interconnects provide switch-based networks with links transferring data at more than 1 Gigabit per second, being mainly used in the LAN environments. In this paper we analyze whether these high-speed LAN technologies could also be an interesting alternative to storage networking. We perform this analysis using real-world I/O traces. The main conclusion from our study is that most of the messages present the base network latency, meaning that the network is not heavily loaded. Moreover, response time is, in general, acceptable, being dominated by the time disks need to process the requests.
    Networks, IEEE International Conference on. 01/2000;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cache memories are widely used to improve computer performance, buttheir inherent unpredictability presents new problems when cached systems must beanalysed. In preemptive, multitask real-time systems, the cache memories have beenanalysed from two complementary points of view. First, calculating the Worst CaseExecution Time #WCET# of each task considering no preemptions. Second, makingthe schedulability analysis considering the e#ect of cache when tasks are preempted.
    01/2000;
  • X. Molero, F. Silla, V. Santonja
    [Show abstract] [Hide abstract]
    ABSTRACT: Networks of workstations (NOW) are becoming a very popular alternative to parallel computers for those applications with high needs of resources such as memory capacity, processing power, and input/output storage space. Typically, these networks connect workstations using irregular topologies, providing the wiring flexibility, scalability, and incremental expansion capability required in this environment.In order to analyze and design these kinds of systems it is necessary to have adequate tools. To address this problem, we have implemented a very flexible and easy to use NOW simulator. It supports a technique for message fragmentation in packets, generates self-similar traffic, and it can model networks with permanent faulted links or switches.In this paper we present this NOW simulator, the basic queuing models it is based on, its main internal organization, input parameters, output performance variables, and finally, we show several simple examples of performance measures obtained for, among others, message fragmentation, failures in links and switches, and self-similar traffic.
    Simulation Symposium, Annual. 01/2000;
  • Dependable Computing - EDCC-2, Second European Dependable Computing Conference, Taormina, Italy, October 2-4, 1996, Proceedings; 01/1996
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Resumen La planificación de actividades prácticas a fin de consolidar el aprendizaje de los conceptos clave relacionados con la memoria cache no es una tarea fácil. En esta ponencia destacamos los conceptos que hemos considerado fundamentales sobre el sistema de memoria cache. A continuación plan-teamos un conjunto de actividades prácticas ba-sándonos en el refuerzo de dichos conceptos y establecemos la metodología para su enseñanza. Finalmente, presentamos una herramienta de ayuda, accesible mediante un navegador web, que apoyará el proceso de aprendizaje. 1. Introducción y motivación El concepto de jerarquía de memoria, y dentro de él, el sistema de memoria cache, es un elemento fundamental en cualquier curso introductorio sobre estructura o arquitectura de computadores [4,5,7]. En el caso que nos ocupa, la docencia de este tema tiene lugar en la asignatura Estructura de Computadores II. Esta asignatura es obligatoria y se sitúa en el tercer cuatrimestre de los planes de estudio de las titulaciones de ingeniería informáti-ca, tanto superior como técnicas, que se imparte en la Escuela Universitaria y en la Facultad de Informática de la Universitat Politècnica de Va-lència. Dada la relevancia que actualmente tiene el sistema de memoria cache dentro de los computa-dores actuales, la localización de los conceptos teóricos clave es una tarea fundamental, así como su refuerzo mediante una buena planificación de las actividades prácticas. En esta línea, los autores se han propuesto una doble tarea: aislar aquellos aspectos relevantes en la organización del sistema de memoria cache, y proponer una serie de expe-riencias prácticas que ayuden al alumno a una óptima comprensión de los conceptos clave. Por último, hemos creído necesario apoyar este apren-dizaje práctico sobre una herramienta diseñada con una finalidad exclusivamente didáctica, y al mismo tiempo que sea fácil de usar para la conse-cución de las actividades prácticas. El resto de esta ponencia se ha organizado de la siguiente manera: la Sección 2 presenta los conceptos más destacables relacionados con el sistema de memoria cache. En la Sección 3 se presenta un conjunto de actividades prácticas diseñadas en torno a los conceptos fundamentales. La metodología que proponemos de aprendizaje se describe en la Sección 4, mientras que la he-rramienta que proponemos para utilizarse en las actividades prácticas se describe brevemente en la Sección 5, así como un ejemplo de utilización. Por último, las conclusiones se detallan en la última sección.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: modeling of storage systems based on magnetic disks" projects. ABSTRACT A Storage Area Network is a high-speed subnet that establishes a direct connection between heterogeneous storage resources and servers. Up to now, the work done in our department on the performance evaluation of these systems has been carried out using traditional simulation techniques. However, the SAN simulator designed by our researchers needed a lot of computational time to obtain statistically correct results. In this work we show how we have improved the execution time of our SAN simulator using a concurrent simulation approach. This approximation basically consists of executing in parallel variable-sized independent replications of the simulation model. The obtained results encourage us to continue working on concurrent simulation development.
  • Source