THEME 3 SMART CONVERGED EDGE
|“On Satisfying Green SLAs in Distributed Clouds” Ahmed Amokrane, Mohamed Faten Zhani, Qi Zhang, Rami Langar, Raouf Boutaba, University of Waterloo|
|“CQNCR: Optimal VM Migration Planning in Cloud Data Centers” Md. Faizul Bari, Mohamed Faten Zhani, Qi Zhang, Reaz Ahmed, Raouf Boutaba, University of Waterloo|
|“Design and Management of DOT: A Distributed OpenFlow Testbed” Arup Raton Roy, Md. Faizul Bari, Mohamed Faten Zhani, Reaz Ahmed, Raouf Boutaba, University of Waterloo|
|“A Simple Programming Model for Scalable SDN Control Applications” Soheil Hassas Yeganeh and Yashar Ganjali, University of Toronto|
|“FleXam: Flexible Sampling Extension for Monitoring and Security Applications in OpenFlow” Sajad Shirali-Shahreza and Yashar Ganjali, University of Toronto|
|“Dynamic Virtual Infrastructure Provisioning in Geographically Distributed Clouds” Qi Zhang and Alberto Leon-Garcia, University of Toronto|
|“Online Algorithms for Energy Cost Minimization in Cellular Networks” Ali Abbasi and Majid Ghaderi, University of Calgary|
|“Greenhead: Virtual Data Center Embedding Across Distributed Infrastructures” Aimal Khan, Ahmed Amokrane, Arup Raton Roy, Mohamed Faten Zhani, Maissa Jabri, Qi Zhang, Rami Langar, Raouf Boutaba, University of Waterloo|
|“DOT in Action” Arup Raton Roy, Md. Faizul Bari, Reaz Ahmed, Raouf Boutaba, University of Waterloo|
Ahmed Amokrane, Mohamed Faten Zhani, Qi Zhang, Rami Langar, Raouf Boutaba, University of Waterloo
With the massive adoption of cloud-based services, high energy consumption and carbon footprint of cloud infrastructures have become a major concern in IT industry. Consequently, many governments and IT advisory organizations have urged IT stakeholders (i.e., cloud provider and cloud customers) to embrace green IT and regularly monitor and report their carbon emissions and put in place efficient strategies and techniques to control the environmental impact of their infrastructures and/or applications.
Motivated by this growing trend, we investigate how cloud providers can meet Service Level Agreements (SLAs) with green requirements. In such SLAs, a cloud customer requires from cloud providers that carbon emissions generated by the leased resources should not exceed a fixed bound. We hence propose a resource management framework allowing cloud providers to provision resources in the form of Virtual Data Centers (VDCs) (i.e., a set of virtual machines and virtual links with guaranteed bandwidth) across a geo-distributed infrastructure with the aim of reducing operational costs and green SLA violation penalties. Extensive simulations show that the proposed solution maximizes the cloud provider’s profit and minimizes the violation of green SLAs.
Md. Faizul Bari, Mohamed Faten Zhani, Qi Zhang, Reaz Ahmed, Raouf Boutaba, University of Waterloo
With the proliferation of cloud computing, virtualization has become the cornerstone of modern data centers and an effective solution to reduce operational costs, maximize utilization and improve performance and reliability. One of the powerful features provided by virtualization is Virtual Machine (VM) migration, which facilitates moving workloads within the infrastructure to reach various performance objectives. As recent virtual resource management schemes are more reliant on this feature, a large number of VM migrations may be triggered simultaneously to optimize resource allocations. In this context, a challenging problem is to find an efficient migration plan, i.e., an optimal sequence in which migrations should be triggered in order to minimize the total migration time and impact on services.
In this work, we propose CQNCR (read as sequencer), an effective technique for determining the execution order of massive VM migrations within data centers. Specifically, given an initial and a target resource configuration, CQNCR sequences VM migrations so as to efficiently reach the final configuration with minimal time and impact on performance. Experiments show that CQNCR can significantly reduce total migration time by up to 35% and service downtime by up to 60%.
Arup Raton Roy, Md. Faizul Bari, Mohamed Faten Zhani, Reaz Ahmed, Raouf Boutaba, University of Waterloo
With the growing adoption of Software Defined Networking (SDN), there is a compelling need for SDN emulators that facilitate experimenting with new SDN-based technologies. Unfortunately, Mininet , the de facto standard emulator for software defined networks, fails to scale with network size and traffic volume. The aim of this work is to fill the void in this space by presenting a low cost and scalable network emulator called Distributed OpenFlow Testbed (DOT). It can emulate large SDN deployments by distributing the workload over a cluster of compute nodes. Through extensive experiments, we show that DOT can overcome the limitations of Mininet and emulate larger networks. We also demonstrate the effectiveness of DOT on four Rocketfuel topologies. DOT is available for public use and community-driven development at dothub.org.
Soheil Hassas Yeganeh and Yashar Ganjali, University of Toronto
Simplicity is a prominent advantage of Software-Defined Networking (SDN), and is often exemplified by implementing a complicated control logic as a simple control application deployed on a centralized controller. When it comes to practice, however, such simple control applications transform into complex logics on distributed control platforms, since they need to tolerate eventual consistency (as existing control platforms favor availability) and implement complex coordination and partitioning mechanisms (as existing control platforms envision such functions belonging to control applications with the excuse of generality). As a result, distributed control applications are polluted with boilerplates of distributed programming that are usually more complicated than the control logic itself.
Here, we present programming model that simplifies the development process of distributed applications. It familiar and intuitive, yet generic enough to implement different communication patterns (such as Request/Response and Pub/Sub) and existing distributed controllers (such as ONIX and Kandoo). Moreover, we have implemented a highly efficient control platform and our evaluations indicate that the proposed programming model does not impose an inherent scalability bottleneck.
Sajad Shirali-Shahreza and Yashar Ganjali, University of Toronto
Current OpenFlow specifications provide limited access to packet-level information such as packet content, making it very inefficient, if not impossible, to deploy security and monitoring applications as controller applications. In this poster, we present FleXam, a flexible sampling extension for OpenFlow designed to provide access to packet level information at the controller. Simplicity of FleXam makes it possible to implement it easily in OpenFlow switches and operate at line rate without requiring any additional memory. At the same time, its flexibility allows implementation of various monitoring and security applications in the controller, while maintaining balance between overhead and collected information details. FleXam realizes the advantages of both proactive and reactive routing schemes by providing a tunable trade-off between the visibility of individual flows, and the controller load. As an example, we show how FleXam can be used to implement a port scan detection application with an extremely low overhead.
Qi Zhang and Alberto Leon-Garcia, University of Toronto
Large-scale online services today often span multiple geographically distributed domains and require significant storage, compute and networking resources. Furthermore, these services often need to be scaled up and down dynamically according to service demand fluctuation. To facilitate efficient resource allocation while allowing multiple online services to share to physical hosting infrastructure (e.g. data centers), there is a emerging trend towards allocating resources to service applications in the form of virtual infrastructures (VI) that consist of virtual machines, virtual routers and switches interconnected by virtual links. However, despite extensive study of virtual infrastructure scheduling algorithms, existing work has not studied the problem of provisioning VIs dynamically according to demand fluctuations. To address limitation, in this work we present a framework for virtual infrastructure provisioning that adjusts virtual infrastructure resource allocation according to demand fluctuations, while satisfying performance requirements. We demonstrate the effectiveness of our framework through simulations in realistic application scenarios.
Ali Abbasi and Majid Ghaderi, University of Calgary
Dynamic base station activation and transmission power control are the key mechanisms to reduce energy consumption in cellular networks. In this work, we consider employing these methods for the purpose of minimizing long-term energy cost in cellular networks. Based on the two-timescale Lyapunov optimization technique, we formulate an online control problem to ensure achieving minimal energy cost while stabilizing use queues. While the control problem can be solved in a centralized manner, we limit our attention to distributed solutions which are highly attractive in the design of next generation mobile networks. Due to the combinatorial nature of the problem and the complex relation of achievable rates to interfering signals, the problem is non-convex. Consequently, conventional duality methods cannot be employed to achieve the distributed solution.
Thus, we design a distributed solution for the problem based on Gibbs sampling method. The proposed algorithm can be implemented in a fully distributed manner, does not depend on the convexity or continuity of the energy cost functions, and guarantees solution optimality. Numerical results are provided to demonstrate the behavior of the solution in some example network scenarios.
Aimal Khan, Ahmed Amokrane, Arup Raton Roy, Mohamed Faten Zhani, Maissa Jabri, Qi Zhang, Rami Langar, Raouf Boutaba, University of Waterloo
In our recent work, we proposed Greenhead, a holistic resource management framework for embedding Virtual Data Centers (VDCs) across distributed infrastructure. Greenhead is able to achieve multiple goals including revenue maximization, operational costs reduction, energy efficiency, and green IT, or to simply satisfy geographic location constraints of the VDCs. In this demo, we show how SAVI users can define their VDC specifications and how Greenhead allocates the required resources across the smart edges. In particular, we implemented Greenhead as a testbed-wide management module that communicates with local smart edge managers (VDCPlanner) to efficiently allocate computing and networking resources while satisfying geographic location constraints (i.e., proximity of some VMs to end users).
Arup Raton Roy, Md. Faizul Bari, Reaz Ahmed, Raouf Boutaba, University of Waterloo
With the growing adoption of Software Defined Networking (SDN), there is a compelling need for SDN emulators that facilitate experimenting with new SDN-based technologies. Unfortunately, Mininet , the de facto standard emulator for software defined networks, fails to scale with network size and traffic volume. DOT (Distributed OpenFlow Testbed) fills the void in this space by providing a low cost and scalable network emulator capable to emulate large SDN deployments by distributing the workload over a cluster of compute nodes. DOT is available for public use and community-driven development at dothub.org. The goal of this demo is to show how DOT can be easily used to effectively emulate large scale SDN networks.