Scalability and Resilience of Multi-Tenant Distributed Clouds in the Big Services Era

Scalability and Resilience of Multi-Tenant Distributed Clouds in the Big Services Era

• 1.
  Scalability and Resilienceof Multi-Tenant Distributed Clouds in the Big Services Era Pradeeban Kathiravelu1,2 ,Tihana Galina Grbac3 , Peter Van Roy2 , Luís Veiga1 1 INESC-ID Lisboa / Instituto Superior Técnico, Portugal. 2 Université catholique de Louvain, Belgium. 3 University of Rijeka, Croatia. Introduction  Data-centric big services with complex workloads.  Geographically distributed big data to be processed.  Resource availabilities at remote locations; for example,  Distributed clouds with resources in multiple regions.  Volunteer computing leverages idle client resources.  Edge computing with execution close to the end users.  Critical flows - End-to-end delivery guarantees. Challenges  Differentiated Quality of Service (QoS) in cloud networks!  Discriminate flows with redundancy in data and execution paths? Motivation  Network level performance based on service level inputs.  Scalability and Resilience for big services in distributed clouds. SDN for Distributed Clouds  Cross-layer optimization of multi-tenant cloud networks  Leveraging Software-Defined Networking (SDN) and middleboxes. Our Approach 1. SMART (SDN Middlebox Architecture for Reliable Transfers)  SMART: Network Resilience with Differentiated SLAs.  Policies and tenant preferences: ● Service Level / Application Layer → Network (Figure 1).  Timely delivery of priority flows:  Dynamically diverting them to a less congested path.  Cloning subflows of higher priority flows.  An adaptive approach in cloning and diverting of the flows.  An approach motivated by FlowTags Middlebox  Tag the network flows with service level inputs. Solution Architecture  A cross-layer architecture and communication.  Ensuring differentiated QoS.  A context-aware approach in load balancing the network.  servers supporting multihoming, connected topologies, …  Extend beyond data centers: network nodes → virtual executions.  Blurring the borders between the networks and the applications. Contributions * These results have been partly discussed in our recent publications: ICWS (2016), CoopIS (2015, 2016), NCA (2016), IM (2017), IC2E (2016), and SDS (2015, 2016, 2017). Questions and Comments? [email protected] 2. Mayan (Componentizing Data-Centric Big Services In the Internet)  An Inter-cloud framework to componentize big services.  Execute them as a network-aware distributed service composition.  Modelling, Scalability, and Orchestration.  Use the best-fit execution path among available alternatives.  Web services and microservices as the building blocks of the big services. Solution Architecture  A scalable resilient framework for big service execution.  Services as building blocks of the composition of big services (Figure 2).  Message-Oriented Middleware (MOM) for inter-domain communications. Contributions  Synergy of network and service levels in decision making.  A federated controller deployment for inter-cloud networks.  Componentizing big services as service compositions.  Scalability and resilience for multi-tenant distributed clouds. Conclusion  Increased QoS and Speedup with network-aware scalability.  Performance growth = f(problem size, workflow as services).  Federated deployment of SDN controller clusters.