C. Ruz - PONTIFICIA UNIVERSIDAD CATÓLICA DE CHILE (original) (raw)
Papers by C. Ruz
Lecture Notes in Computer Science, 2005
This work presents a study regarding the search for an optimal value of the history size for the ... more This work presents a study regarding the search for an optimal value of the history size for the prediction/prefetching technique history-based prefetching, which collects the recent history of accesses to individual shared memory pages and uses that information to predict the next access to a page. On correct predictions, this technique allows to hide the latency generated by page faults on the remote node when the access is effectively done. Some parameters as the size of the page history structure that is stored and transmitted among nodes can be fine-tuned to improve the prediction efficency. Our experiments show that small values of history size provide a better performance in the tested applications, while bigger values tend to generate more latency when the page history is transmitted, without improving the prediction efficiency.
Component-based generic approach for reconfigurable management of component-based SOA applications
Proceedings of the 3rd International Workshop on Monitoring, Adaptation and Beyond - MONA '10, 2010
ABSTRACT Service Oriented Architecture (SOA) applications can be composed by sets of loosely coup... more ABSTRACT Service Oriented Architecture (SOA) applications can be composed by sets of loosely coupled interacting heterogenous services from different providers. The Service Component Architecture (SCA) specification allows to build hierarchical applications, applying the principles of SOA and Component Based Software Engineering (CBSE). However, concerns like dynamic management, including reconfiguration and distribution handling for composite services are left as platform specific matters. In this context, monitoring and management tasks are not trivial, since compositions and required QoS levels can change depending on the effective location that services and components are deployed onto. Service Level Agreements (SLA) can also evolve during the lifecycle of the deployed application. Several solutions for monitoring and adaptation of QoS-aware service compositions have been proposed so far, but they have rarely been designed in an integrated way and with evolution capabilities in mind. In this work we advocate that a component based approach is an adequate one in order to implement a reconfigurable framework to handle tasks of monitoring and management of hierarchical component-based SOA applications. Our approach allows to address concerns like monitoring, SLA management and adaptation strategies, possibly autonomous ones, as a component-based distributed application. The main advantage is the capability to reconfigure this management architecture at runtime whenever needed, allowing to dynamically adapt it to the possibly evolving non functional requirements of the managed application. The framework is illustrated through a scenario of a composite SOA application that is dynamically augmented with components to tackle non-functional concerns as it is needed. We describe an implementation over an SCA compliant platform that allows distribution and architectural reconfiguration of components.
Lecture Notes in Computer Science, 2007
In this paper we present the thread migration mechanism of DSM-PEPE, a multithreaded distributed ... more In this paper we present the thread migration mechanism of DSM-PEPE, a multithreaded distributed shared memory system. DSM systems like DSM-PEPE provide a parallel environment to harness the available computing power of computer networks. DSM systems offer a virtual shared memory space on top of a distributed-memory multicomputer, featuring the scalability and low cost of a multicomputer, and the ease of programming of a shared-memory multiprocessor. DSM systems rely on data migration to make data available to running threads. The thread migration mechanism of DSM-PEPE was designed as an alternative to this data migration paradigm. Threads are allowed to migrate from one node to another, as needed by the computation. We show by experimentation the feasibility of the thread migration mechanism of DSM-PEPE as an alternative to improve application perfomance by enhancing spatial locality.
2011 IEEE 15th International Enterprise Distributed Object Computing Conference Workshops, 2011
We present an integrated approach to design, monitor and manage the lifecycle of applications bas... more We present an integrated approach to design, monitor and manage the lifecycle of applications based on the Service Oriented Architecture (SOA) principles and capable of taking advantage of cloud computing environments. The integrated framework takes profit of publicly available open source tools and standards in an effective and coherent way, and covers the steps from business and architectural design of the application, to deployment and runtime support. We exemplify our approach with a walkthrough in a simple yet illustrative scenario.
Lecture Notes in Computer Science, 2003
Lecture Notes in Computer Science, 2006
This article introduces a self-stabilizing deadlock-detection algorithm for the OR model. The alg... more This article introduces a self-stabilizing deadlock-detection algorithm for the OR model. The algorithm is complete, because it detects all deadlocks, and it is correct, because it does not detect false deadlocks. Because of the self-stabilization property, the algorithm supports dynamic changes in the wait-for graph on which it works, and transient faults; also, it can be started in an arbitrary state. Previous deadlock-detection algorithms for the OR model are not guaranteed to recover from transient faults, nor can they be started in an arbitrary state. Once the algorithm terminates, each process knows if it is or not deadlocked; moreover, deadlocked processes know whether they cause or only suffer from deadlock.
Software: Practice and Experience, 2014
Component oriented software has become a useful tool to build larger and more complex systems by ... more Component oriented software has become a useful tool to build larger and more complex systems by describing the application in terms of encapsulated, loosely-coupled entities called components. At the same time, asynchronous programming patterns allow for the development of efficient distributed applications. While several component models and frameworks have been proposed, most of them tightly integrate the component model with the middleware they run upon. This intertwining is generally implicit and not discussed, leading to entangled, hard to maintain code. This article describes our efforts in the development of the GCM/ProActive framework for providing distributed and adaptable autonomous components. GCM/ProActive integrates a component model designed for execution on large scale environments, with a programming model based on active objects allowing a high degree of distribution and concurrency. This new integrated model provides a more powerful development, composition, and execution environment than other distributed component frameworks. We illustrate that GCM/ProActive is particularly adapted to the programming of autonomic component systems, and to the integration into a service oriented environment. component model in a common structured programming environment: our components are active objects, they communicate by asynchronous requests, and each of them can be placed on a different location. We think that implementing the component model using this programming model provides a good abstraction for distribution and concurrency, and we claim here that this new integrated model provides a more powerful development, composition, and execution environment than other distributed component frameworks.
Autonomic Monitoring and Management of Component-based Services
... Cristian Ruz (INRIA Oasis Team) Autonomic M&M of Comp-based Services 23/06/2011 5 / 52 Pa... more ... Cristian Ruz (INRIA Oasis Team) Autonomic M&M of Comp-based Services 23/06/2011 5 / 52 Page 19. 1. Introduction Motivation ... Hotel Reservation Car Reservation Credit Card Billing Room Management Vacation Planner ... Service Registry Service Consumer Service Provider ...
The Service Oriented Architecture (SOA) model fosters dynamic interactions of heteregeneous and l... more The Service Oriented Architecture (SOA) model fosters dynamic interactions of heteregeneous and looselycoupled service providers and consumers. Specifications like the Service Component Architecture (SCA) have been used to tackle the complexity of developing such dynamic applications; however, concerns like runtime management and adaptation are often left as platform specific matters. At the same time, runtime QoS requirements stated in Service Level Agreements (SLA) may also evolve at runtime, and not only the application needs to adapt to them, but also the monitoring and management tasks. This work presents a component based framework that provides flexible monitoring and management tasks and allows to introduce adaptivity to component-based SOA applications. The framework implements each phase of the autonomic control loop as a separate component, and allows multiple implementations on each phase, giving enough runtime flexibility to support evolving non functional requirements on the application. We present an illustrative scenario that is dynamically augmented with components to tackle nonfunctional concerns and support adaptation as it is needed. We use an SCA compliant platform that allows distribution and architectural reconfiguration of components.
Visual Recognition to Access and Analyze People Density and Flow Patterns in Indoor Environments
2015 IEEE Winter Conference on Applications of Computer Vision, 2015
Open Journal of Modern Hydrology, 2014
The storage, longitudinal distribution and recruitment processes of in-stream large wood (LW) wer... more The storage, longitudinal distribution and recruitment processes of in-stream large wood (LW) were studied comparing channel segments draining four Chilean mountain catchments with different land use. The segments were divided into relatively uniform reaches of different lengths and surveyed for LW (piece dimensions, position in the channel, orientation to flow and aggregation) and stream morphology (slope and bank full channel width and depth) characterizations. LW volume stored in the Pichun, El Toro and Vuelta de Zorra study channels are within the range informed in international researches from streams draining catchments with similar forest covers. However, the 1057 m 3 /ha of LW stored in Tres Arroyos is extremely high and in the same order of magnitude than the reports from old-growth forests in the Pacific Northwest of USA. The size of the area that can potentially provide wood to streams depends on the wood supply mechanisms within any catchment, and the LW stored in the study segments increases as the size of this area increases. This study aims to contribute to the knowledge on the effects of LW in mountain channels, gathering new information and expanding investigations developed in Chile since 2008. This research was carried out within the framework of Project FONDECYT 11106209.
D2. 3.1. Studio Analysis Platform Design
Migraci on de Ì Ö× en un Sistema de Memoria Compartida Distribuida sobre un Multicomputador Homog eneo
... A diferencia de un sistema en que los computadores tienen iguales caracteréisticas de hardwar... more ... A diferencia de un sistema en que los computadores tienen iguales caracteréisticas de hardware y software, en los sistemas heterogéeneos es necesario tomar en cuenta que la manera en que se representan internamente los datos e ... [16] Hai Jiang and Vipin Chaudhary. ...
Aplicando orientación a aspectos para mejorar el diseño de un sistema de memoria compartida distribuida
Using Components to Provide a Flexible Adaptation Loop to Component-based SOA Applications
D1. 4.1 B SOA4All Runtime
Lecture Notes in Computer Science, 2005
This work presents a study regarding the search for an optimal value of the history size for the ... more This work presents a study regarding the search for an optimal value of the history size for the prediction/prefetching technique history-based prefetching, which collects the recent history of accesses to individual shared memory pages and uses that information to predict the next access to a page. On correct predictions, this technique allows to hide the latency generated by page faults on the remote node when the access is effectively done. Some parameters as the size of the page history structure that is stored and transmitted among nodes can be fine-tuned to improve the prediction efficency. Our experiments show that small values of history size provide a better performance in the tested applications, while bigger values tend to generate more latency when the page history is transmitted, without improving the prediction efficiency.
Component-based generic approach for reconfigurable management of component-based SOA applications
Proceedings of the 3rd International Workshop on Monitoring, Adaptation and Beyond - MONA '10, 2010
ABSTRACT Service Oriented Architecture (SOA) applications can be composed by sets of loosely coup... more ABSTRACT Service Oriented Architecture (SOA) applications can be composed by sets of loosely coupled interacting heterogenous services from different providers. The Service Component Architecture (SCA) specification allows to build hierarchical applications, applying the principles of SOA and Component Based Software Engineering (CBSE). However, concerns like dynamic management, including reconfiguration and distribution handling for composite services are left as platform specific matters. In this context, monitoring and management tasks are not trivial, since compositions and required QoS levels can change depending on the effective location that services and components are deployed onto. Service Level Agreements (SLA) can also evolve during the lifecycle of the deployed application. Several solutions for monitoring and adaptation of QoS-aware service compositions have been proposed so far, but they have rarely been designed in an integrated way and with evolution capabilities in mind. In this work we advocate that a component based approach is an adequate one in order to implement a reconfigurable framework to handle tasks of monitoring and management of hierarchical component-based SOA applications. Our approach allows to address concerns like monitoring, SLA management and adaptation strategies, possibly autonomous ones, as a component-based distributed application. The main advantage is the capability to reconfigure this management architecture at runtime whenever needed, allowing to dynamically adapt it to the possibly evolving non functional requirements of the managed application. The framework is illustrated through a scenario of a composite SOA application that is dynamically augmented with components to tackle non-functional concerns as it is needed. We describe an implementation over an SCA compliant platform that allows distribution and architectural reconfiguration of components.
Lecture Notes in Computer Science, 2007
In this paper we present the thread migration mechanism of DSM-PEPE, a multithreaded distributed ... more In this paper we present the thread migration mechanism of DSM-PEPE, a multithreaded distributed shared memory system. DSM systems like DSM-PEPE provide a parallel environment to harness the available computing power of computer networks. DSM systems offer a virtual shared memory space on top of a distributed-memory multicomputer, featuring the scalability and low cost of a multicomputer, and the ease of programming of a shared-memory multiprocessor. DSM systems rely on data migration to make data available to running threads. The thread migration mechanism of DSM-PEPE was designed as an alternative to this data migration paradigm. Threads are allowed to migrate from one node to another, as needed by the computation. We show by experimentation the feasibility of the thread migration mechanism of DSM-PEPE as an alternative to improve application perfomance by enhancing spatial locality.
2011 IEEE 15th International Enterprise Distributed Object Computing Conference Workshops, 2011
We present an integrated approach to design, monitor and manage the lifecycle of applications bas... more We present an integrated approach to design, monitor and manage the lifecycle of applications based on the Service Oriented Architecture (SOA) principles and capable of taking advantage of cloud computing environments. The integrated framework takes profit of publicly available open source tools and standards in an effective and coherent way, and covers the steps from business and architectural design of the application, to deployment and runtime support. We exemplify our approach with a walkthrough in a simple yet illustrative scenario.
Lecture Notes in Computer Science, 2003
Lecture Notes in Computer Science, 2006
This article introduces a self-stabilizing deadlock-detection algorithm for the OR model. The alg... more This article introduces a self-stabilizing deadlock-detection algorithm for the OR model. The algorithm is complete, because it detects all deadlocks, and it is correct, because it does not detect false deadlocks. Because of the self-stabilization property, the algorithm supports dynamic changes in the wait-for graph on which it works, and transient faults; also, it can be started in an arbitrary state. Previous deadlock-detection algorithms for the OR model are not guaranteed to recover from transient faults, nor can they be started in an arbitrary state. Once the algorithm terminates, each process knows if it is or not deadlocked; moreover, deadlocked processes know whether they cause or only suffer from deadlock.
Software: Practice and Experience, 2014
Component oriented software has become a useful tool to build larger and more complex systems by ... more Component oriented software has become a useful tool to build larger and more complex systems by describing the application in terms of encapsulated, loosely-coupled entities called components. At the same time, asynchronous programming patterns allow for the development of efficient distributed applications. While several component models and frameworks have been proposed, most of them tightly integrate the component model with the middleware they run upon. This intertwining is generally implicit and not discussed, leading to entangled, hard to maintain code. This article describes our efforts in the development of the GCM/ProActive framework for providing distributed and adaptable autonomous components. GCM/ProActive integrates a component model designed for execution on large scale environments, with a programming model based on active objects allowing a high degree of distribution and concurrency. This new integrated model provides a more powerful development, composition, and execution environment than other distributed component frameworks. We illustrate that GCM/ProActive is particularly adapted to the programming of autonomic component systems, and to the integration into a service oriented environment. component model in a common structured programming environment: our components are active objects, they communicate by asynchronous requests, and each of them can be placed on a different location. We think that implementing the component model using this programming model provides a good abstraction for distribution and concurrency, and we claim here that this new integrated model provides a more powerful development, composition, and execution environment than other distributed component frameworks.
Autonomic Monitoring and Management of Component-based Services
... Cristian Ruz (INRIA Oasis Team) Autonomic M&M of Comp-based Services 23/06/2011 5 / 52 Pa... more ... Cristian Ruz (INRIA Oasis Team) Autonomic M&M of Comp-based Services 23/06/2011 5 / 52 Page 19. 1. Introduction Motivation ... Hotel Reservation Car Reservation Credit Card Billing Room Management Vacation Planner ... Service Registry Service Consumer Service Provider ...
The Service Oriented Architecture (SOA) model fosters dynamic interactions of heteregeneous and l... more The Service Oriented Architecture (SOA) model fosters dynamic interactions of heteregeneous and looselycoupled service providers and consumers. Specifications like the Service Component Architecture (SCA) have been used to tackle the complexity of developing such dynamic applications; however, concerns like runtime management and adaptation are often left as platform specific matters. At the same time, runtime QoS requirements stated in Service Level Agreements (SLA) may also evolve at runtime, and not only the application needs to adapt to them, but also the monitoring and management tasks. This work presents a component based framework that provides flexible monitoring and management tasks and allows to introduce adaptivity to component-based SOA applications. The framework implements each phase of the autonomic control loop as a separate component, and allows multiple implementations on each phase, giving enough runtime flexibility to support evolving non functional requirements on the application. We present an illustrative scenario that is dynamically augmented with components to tackle nonfunctional concerns and support adaptation as it is needed. We use an SCA compliant platform that allows distribution and architectural reconfiguration of components.
Visual Recognition to Access and Analyze People Density and Flow Patterns in Indoor Environments
2015 IEEE Winter Conference on Applications of Computer Vision, 2015
Open Journal of Modern Hydrology, 2014
The storage, longitudinal distribution and recruitment processes of in-stream large wood (LW) wer... more The storage, longitudinal distribution and recruitment processes of in-stream large wood (LW) were studied comparing channel segments draining four Chilean mountain catchments with different land use. The segments were divided into relatively uniform reaches of different lengths and surveyed for LW (piece dimensions, position in the channel, orientation to flow and aggregation) and stream morphology (slope and bank full channel width and depth) characterizations. LW volume stored in the Pichun, El Toro and Vuelta de Zorra study channels are within the range informed in international researches from streams draining catchments with similar forest covers. However, the 1057 m 3 /ha of LW stored in Tres Arroyos is extremely high and in the same order of magnitude than the reports from old-growth forests in the Pacific Northwest of USA. The size of the area that can potentially provide wood to streams depends on the wood supply mechanisms within any catchment, and the LW stored in the study segments increases as the size of this area increases. This study aims to contribute to the knowledge on the effects of LW in mountain channels, gathering new information and expanding investigations developed in Chile since 2008. This research was carried out within the framework of Project FONDECYT 11106209.
D2. 3.1. Studio Analysis Platform Design
Migraci on de Ì Ö× en un Sistema de Memoria Compartida Distribuida sobre un Multicomputador Homog eneo
... A diferencia de un sistema en que los computadores tienen iguales caracteréisticas de hardwar... more ... A diferencia de un sistema en que los computadores tienen iguales caracteréisticas de hardware y software, en los sistemas heterogéeneos es necesario tomar en cuenta que la manera en que se representan internamente los datos e ... [16] Hai Jiang and Vipin Chaudhary. ...
Aplicando orientación a aspectos para mejorar el diseño de un sistema de memoria compartida distribuida
Using Components to Provide a Flexible Adaptation Loop to Component-based SOA Applications
D1. 4.1 B SOA4All Runtime