Spelling suggestions: "subject:"longrunning applicatications"" "subject:"longrunning applicationoptions""
1 |
Dynamic Software Update for Production and Live Programming Environments / Mise à jour Dynamique pour Environnemts de Production et Programmation InteractiveTesone, Pablo 17 December 2018 (has links)
Mettre à jour des applications durant leur exécution est utilisé aussi bien en production pour réduire les temps d’arrêt des applications que dans des environnements de développement interactifs (IDE pour live programming). Toutefois, ces deux scénarios présentent des défis différents qui font que les solutions de mise à jour dynamique (DSU pour Dynamic Software Updating) existantes sont souvent spécifiques à l’un des deux. Par exemple, les DSUs pour la programmation interactives ne supportent généralement pas la détection automatique de points sûrs de mise à jour ni la migration d’instances, alors que les DSUs pour la production nécessitent une génération manuelle de l’ensemble des modifications et manquent d’intégration avec l’IDE. Les solutions existantes ont également une capacité limitées à se mettre à jour elles-mêmes ou à mettre à jour les bibliothèques de base du langage ; et certaines d’entre elles introduisent mêmle une dégradation des performances d’exécution en dehors du processus de mise à jour.Dans cette thèse, nous proposons un DSU (nommé gDSU) unifié qui fonctionne à la fois pour la programmation interactive et les environnements de production. gDSU permet la détection automatique des points sûrs de mise à jour en analysant et manipulant la pile d’exécution, et offre un mécanisme réutilisable de migration d’instances afin de minimiser les interventions manuelles lors de l’application d’une migration. gDSU supporte également la mise à jour des bibliothèques du noyau du langage et du mécanisme de mise à jour lui-même. Ceci est réalisé par une copie incrémentale des objets à modifier et une application atomique de ces modifications.gDSU n’affecte pas les performances globales de l’application et ne présente qu’une pénalité d’exécution lors processus de mise à jour. Par exemple, gDSU est capable d’appliquer une mise à jour sur 100 000 instances en 1 seconde. Durant cette seconde, l’application ne répond pas pendant 250 milli-secondes seulement. Le reste du temps, l’application s’exécute normalement pendant que gDSU recherche un point sûr de mise à jour qui consiste alors uniquement à copier les éléments modifiés.Nous présentons également deux extensions de gDSU permettant un meilleur support du développement interactif dans les IDEs : la programmation interactive transactionnelle et l’application atomique de reusinages (refactorings). / Updating applications during their execution is used both in production to minimize application downtine and in integrated development environments to provide live programming support. Nevertheless, these two scenarios present different challenges making Dynamic Software Update (DSU) solutions to be specifically designed for only one of these use cases. For example, DSUs for live programming typically do not implement safe point detection or insistance migration, while production DSUs require manual generation of patches and lack IDE integration. These sollutions also have a limited ability to update themselves or the language core libraries and some of them present execution penalties outside the update window.In this PhD, we propose a unified DSU named gDSU for both live programming and production environments. gDSU provides safe update point detection using call stack manipulation and a reusable instance migration mechanism to minimize manual intervention in patch generation. It also supports updating the core language libraries as well as the update mechanism itself thanks to its incremental copy of the modified objects and its atomic commit operation.gDSU does not affect the global performance of the application and it presents only a run-time penalty during the window. For example, gDSU is able to apply an update impacting 100,000 instances in 1 second making the application not responsive for only 250 milliseconds. The rest of the time the applications runs normally while gDSU is looking for a safe update point during which modified elements will be copied.We also present extensions of gDSU to support transactional live programming and atomic automactic refactorings which increase the usability of live programming environments.
|
2 |
Long-Running Multi-Component Climate Applications On GridsSundari, Sivagama M 10 1900 (has links) (PDF)
Climate science or climatology is the scientific study of the earth’s climate, where climate is the term representing weather conditions averaged over a period of time. Climate models are mathematical models used to quantitatively describe, simulate and study the interactions among the components of the climate system -atmosphere, ocean, land and sea-ice. CCSM (Community Climate System Model) is a state-of-the-art climate model, and a long-running coupled multicomponent parallel application involving component models for simulating the components of the climate system. Each of the component models is a large-scale parallel application, and the parallel components exchange climate data through a specialized component called coupler. Typical multi-century climate simulations using CCSM take several weeks or months to execute on most parallel systems.
In this thesis, we study the applicability of a computational grid for effective execution of long-running coupled multi-component climate applications like CCSM. Initial studies of the application characteristics led us to develop a dynamic component extension strategy for temporal inter-component load-balancing. By means of experiments on different parallel platforms with different number of processors, we showed that using our strategy can lead to about 15% reduction and savings of several days in execution times of CCSM for 1000-year simulation runs. Our initial studies also indicated that unlike typical grid applications, CCSM has limits on scalability to very large number of processors and hence cannot directly benefit from the large number of processors on a computational grid. However, its long-running nature and the limits of execution imposed on jobs on most multi-user batch queueing systems, led us to investigate the benefits of its execution on a grid of batch systems. The idea is that multiple batch queues can improve the processor availability rate with respect to the application thereby possibly improving its effective throughput. We explored this idea in detail with simulation studies involving various system and application characteristics, and execution models. By conducting large number of simulations with different workload characteristics and queuing policies of the systems, processor allocations to components of the application, distributions of the components to the batch systems and inter-cluster bandwidths, we showed that multiple batch executions lead to upto 55% average increase in throughput over single batch executions for long-running CCSM. Having convinced ourselves of possible advantages in performance, we then ventured to construct an application-level middleware framework.
Our framework supports long duration execution of multi-component applications spanning multiple submissions to queues on multiple batch systems. It coordinates the distribution, execution, rescheduling, migration and restart of the application components across resources on different sites. It also addresses challenges including execution time limits for jobs, and differences in job-startup times corresponding to different components. Further, within the framework, we developed robust rescheduling policies that decide when and where to reschedule the components to the available resources based on the application execution characteristics and queue dynamics. Our grid middleware framework resulted in multi-site executions that provided larger application throughput than single-site executions, typically performed by climate scientists, and also removed the bottlenecks associated with a single system execution.
We used this framework for long-running executions of CCSM to study the effect of increased black carbon aerosols and dust aerosols on the Indian monsoons. Black Carbon aerosols are essentially of anthropogenic origin and occur due to improper burning of fossil fuels, and dust is a naturally occurring aerosol. The concentrations of both these aerosols is high over the Indian region. We study the impact of these aerosols on precipitation and sea surface temperature (SST) through multi-decadal simulations conducted with our grid-enabled climate system model. Our observations indicated that increasing the concentrations of aerosols leads to an increase in precipitation in the central and eastern parts of India, and a decrease in SST over most of Indian ocean.
|
Page generated in 0.1366 seconds