Cloud computing: evolution or redefinition

  • Published on

  • View

  • Download


Campo do conhecimento: Enfoque na Modelagem Complexa ou Orientada a Objetos; Campo da comunicao humana:Diretrizes conceituais na modelagem complexa da comunicao humana , Canais Representacionais Mentais, Estilos de Aprender e Ensinar; Teste verificador dos canais representacionais; Teste verificador dos estilos pessoais; Exemplos prticos de utilizao do conhecimento complexo na comunicao humana ; Trabalhando com a diversidade e suas potencialidades na comunicao interpessoal afetando positivamente o ambiente de trabalho; Concluses e Orientaes Prticas para o Desenvolvimento de Competncias para o Profissional do sculo XXI.


  • 1. 11/10/2012 This talk addresses fundamental concepts of cloud computing which are related to parallel and distributed environments.Cloud Computing:This is followed by a discussion of challenges faced by this computational paradigm in order to meet the requirements ofEvolution or Redefinition applications from different domains. Additionally, limitations of the cloud computing paradigm will be highlightedand finally commercial and academic study cases will be presented. Prof. Mario Dantas Federal University of Santa Catarina (UFSC) Informatics and Statistics Department (INE)Florianpolis - Brazil E-mail: mario.dantas@ufsc.brMotivation for this talk Motivation for this talka) Internet x Webb) Downsizing x Rightsizing (90s)Number of computers connected to the internet From centralised environments to distributed computingDate ComputersWeb Server1979, Dec188 01989,July130,000 01999, July 56,218,000 5,560,866Motivation for this talk Motivation for this talkc) Unix x Linuxd) wired x wireless networks (90s and early 00s)Standards (BSD and AT&T) against standardReliable, high speed links against unsecure and slow networks1

2. 11/10/2012Motivation for this talkMotivation for this talke) HPC x Cloud Environments f) Academic x Commercial ApproachAre these environments excludents Several challenges in the computer industryor complementaries paradigms?were studied in the past with an initial collaborationfrom the academic community.BUT, without this approach we can have figures like these: Motivation for this talk Agenda > Conceptsg) A special user view > Challenges Ive never seen something more powerful than this computation combined with> Requirements this network that we now have... In the last seven years, do you know how many times Ive lost any personal data? Zero. Do you know how many times Ive backed up> Limitations my computer? Zero. Steve Jobs, 1997. > Study Cases > Conclusions and Recommendations ConceptsAgenda l Architecture evolution> Concepts Von Neumann Architecture> Challenges l> Requirements> Limitations CPU Memoryl Main bus> Study Cases> Conclusions and Recommendationsl I/O bus Output Input Device Device 2 3. 11/10/2012Concepts Conceptsl Architecture evolutionl Architecture evolutionlFermi Architecturel Old fashion clustersl Source: []Concepts Concepts l Architecture evolution l Cloud computing buzzwords l PaaS l PaaS l SaaS Remote Viz. Groupware Virtualization Web Portal Collaboration l EC2l Google l APPs l PrivatelPublic l Cloud l Cloud [Dominic Lam, IBM]Concepts Concepts Cloud computing is a model But, how can we understand these> for enabling ubiquitous, convenient, on-demand network cloud buzzwords?access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services) > that can be rapidly provisioned and released with minimal management effort or service provider interaction.3 4. 11/10/2012ConceptsConcepts Essential Characteristics: This cloud model is composed of: 1) On-demand self-service;> five essential characteristics; > three service models; and 2) Broad network access;> four deployment models. 3) Resource pooling; 4) Rapid elasticity; 5) Measured service.ConceptsConcepts Service Model: 1) SaaS (Software as a Service); 2) PaaS (Plataform as a Service); 3) IaaS (Infrastructure as a Service).l [Zhang, Cheng, Boutaba, 2010]ConceptsConceptsService Model4 5. 11/10/2012 ConceptsConcepts Deployment Models: 1) Private cloud. The cloud infrastructure is provisioned for But, is this idea of cloud effort new?exclusive use by a single organization 2) Community cloud. The cloud infrastructure is provisioned Wewill probably see the spread of computer utilities, wfor exclusive use by a specific community of consumers like present electric and telephone utilities, will service Individual homes and offices across the country. 3) Public cloud. The cloud infrastructure is provisioned for [1969, Len Kleinrock]open use by the general public 4) Hybrid cloud. The cloud infrastructure is a composition of two or more distinct cloud infrastructures ConceptsAgenda > ConceptsA computational grid is a hardware and software > Challengesinfrastructure that provides dependable, consistent,pervasive, and inexpensive access to high-end computational> Requirementscapabilities. > Limitations > Study Cases [1998, Ian Foster and Carl Kesselman] > Conclusions and RecommendationsChallengesChallenges But, does the cloud approach have any challenge? Essential characteristics Examples to rememberBut, does the cloud approach have any challenge? 1) On-demand self-service;Self-service restaurant queues; 2) Broad network access; Different roads from differentstates/provinces/countries; 3) Resource pooling;Shared or distributed memory; 4) Rapid elasticity;EURO monetary elasticity; 5) Measured service.bills never delay.5 6. 11/10/2012ChallengesAgenda> Interoperability: Lack of (or to many) standards; > Concepts> Challenges> Human Resources: Small number of people with real good knowledge of distributed systems; > Requirements> Limitations> Security : . Byzantines attacks;> Study Cases. not yet known......(e.g. Cyber attacks such as Stuxnet and flame)> Conclusions and RecommendationsRequirementsRequirements Deployment Models: But, which are the requirements 1) Private cloud. It may be owned, managed,to have a cloud environment? and operated by the organization, a third party, or some combination of them, and it may exist on or off premises. 2) Community cloud. It may be owned, managed, and operated by one or more of the organizations in the community, a third party, or some combination of them, and it may exist on or off premises.RequirementsAgenda> Concepts Deployment Models:> Challenges> Requirements 3) Public cloud. It may be owned, managed, and operated by a business, academic, or government> Limitations organization, or some combination of them. It exists on the premises of the cloud provider.> Study Cases 4) Hybrid cloud. cloud infrastructures (private, > Conclusions and Recommendations community, or public) that remain unique entities, but are bound together by standardized or proprietary technology that enables data and application portability (e.g., cloud bursting for load balancing between clouds). 6 7. 11/10/2012Limitations Limitations > Heterogeneity: cloud providers facilities; But, does the cloud computing approach> Elasticity: this number is not known yet; have any limitation?> (full) Interoperability: between low level applications (e.g. virtual machine tools);> Human resources: developers for this Hybrid environment (shared, distributed memory and GPU environments)Agenda > Concepts Study Cases > ChallengesPublic Clouds > Requirements > Limitations > Study Cases > Conclusions and RecommendationsStudy Casesl Public Clouds l [Zhang, Cheng, Boutaba, 2010] 7 8. 11/10/2012Study Cases l AZURE (PaaS)Study Cases Study Casesl S3 (PaaS) l S3 (PaaS)l Source: [] l Source: []Study Casesl [Zhang, Cheng, Boutaba, 2010] Study CasesPrivate Clouds(UFSC/CTC/INE/LaPeSD)8 9. 11/10/2012Study Cases Study Cases Private Clouds(UFSC/CTC/INE/LaPeSD) lSysteml Interface l Managementl ProvisioninglToolsl MonitoringlServiceslPrivate CloudlCatalog l [Dantas et al., 2009] Study CasesStudy Cases l A) Context oriented approach Resource ReservationStudy Cases Study Cases User Centric AuthenticationSpatio-Temporal Model ll 9 10. 11/10/2012Study Cases Study CaseslExperimental Results l Experimental Resultsl Experimento 1 Comparao das abordagens del Experimento 2 Comparao da eficinciadasautenticao adotando o consumo energtico como abordagens de autenticao em termos percentuaismtricaStudy Cases Study Casesl B) Ontology Approachl Ontology Approachl Reference Brazil CanadalVO-Cl # processors l VO-Bl # processorslCluster_01l7 l Cluster_1l 4lCluster_02l5 l Cluster_2l 4lCluster_03l3l - l - lMulti-cluster (cloud) configurationl [Dantas et al., 2009] l [Dantas et al., 2009]Study Cases Study CasesExperimental ResultsExperimental Results Interactive Interface Interactive Interface Test without dynamic information Test with dynamic informationl [Dantas et al., 2009] l [Dantas et al., 2009] 10 11. 11/10/2012Study CasesStudy Cases Experimental ResultsExperimental Results Interactive Interface Interactive Interface No dynamic information consideredDynamic Information l [Dantas et al., 2009]l [Dantas et al., 2009]Study Cases AgendaC) Advance reservation of resources through augmented reality> Concepts > Challenges > Requirements > Limitations > Study Cases > Conclusions and Recommendationsa.b. This centralized environment adopts several approaches from:a. > computer architecture;a. The cloud approach can be considered now as redefinition on how to use several existinga. > computer networks: paradigms, such as:a.> distributed and parallel computingGrid computing; b. paradigms;l Utility computing;l Virtualization;l Autonomic computing. 11 12. 11/10/2012a.c. The cloud approach has some news d. The cloud approach in the future could be challenges to be considered in large scale:a. considered as an Evolution. if the used paradigms form a new approacha.> heterogemeity (hw & sw);a.> security; anda.> mobile computing interaction. Recomendations Recomendations Consider multi- disciplinary subjects, such as: When developing to cloud environments, dont forget: DB; > The context aware, ontology and fault tolerance approaches;> How a better computing performance can help Distributed systems (e.g. Mosix, Condor); (e.g. speed up web paradigm); Mobile computing (e.g. sensors);> Mobility facilities; Programming languages (e.g. CUDA, PGAS);> Security issues.Computer newtorks (e.g. Infiniband, Quadrics); Computer architectures (e.g.multi-computers, multi-procesores); Cloud Computing: Evolution or RedefinitionQUESTIONS?Prof. Mario DantasFederal University of Santa Catarina (UFSC)Informatics and Statistics Department (INE) Florianpolis - BrazilE-mail: 12


View more >