Section: New Results

Energy efficiency of large scale distributed systems

Participants : Laurent Lefèvre, Daniel Balouek Thomert, Eddy Caron, Radu Carpa, Ghislain Landry Tsafack Chetsa, Marcos Dias de Assunçao, Jean-Patrick Gelas, Olivier Glück, Jean-Christophe Mignot, François Rossigneux, Violaine Villebonnet.

Improving Energy Efficiency of Large Scale Systems without a priori Knowledge of Applications and Services

Unlike their hardware counterpart, software solutions to the energy reduction problem in large scale and distributed infrastructures hardly result in real deployments. At the one hand, this can be justified by the fact that they are application oriented. At the other hand, their failure can be attributed to their complex nature which often requires vast technical knowledge behind proposed solutions and/or thorough understanding of applications at hand. This restricts their use to a limited number of experts, because users usually lack adequate skills. In addition, although subsystems including the memory and the storage are becoming more and more power hungry, current software energy reduction techniques fail to take them into account. We propose a methodology for reducing the energy consumption of large scale and distributed infrastructures. Broken into three steps known as (i) phase identification, (ii) phase characterization, and (iii) phase identification and system reconfiguration; our methodology abstracts away from any individual applications as it focuses on the infrastructure, which it analyses the runtime behaviour and takes reconfiguration decisions accordingly.

The proposed methodology is implemented and evaluated in high performance computing (HPC) clusters of varied sizes through a Multi-Resource Energy Efficient Framework (MREEF). MREEF implements the proposed energy reduction methodology so as to leave users with the choice of implementing their own system reconfiguration decisions depending on their needs. Experimental results show that our methodology reduces the energy consumption of the overall infrastructure of up to 24% with less than 7% performance degradation. By taking into account all subsystems, our experiments demonstrate that the energy reduction problem in large scale and distributed infrastructures can benefit from more than “the traditional” processor frequency scaling. Experiments in clusters of varied sizes demonstrate that MREEF and therefore our methodology can easily be extended to a large number of energy aware clusters. The extension of MREEF to virtualized environments like cloud shows that the proposed methodology goes beyond HPC systems and can be used in many other computing environments.

Reservation based Usage for Energy Efficient Clouds: the Climate/Blazar Architecture

The FSN XLcloud project (cf Section  8.1 ) strives to establish the demonstration of a High Performance Cloud Computing (HPCC) platform based on OpenStask, that is designed to run a representative set of compute intensive workloads, including more specifically interactive games, interactive simulations and 3D graphics. XLcloud is based on OpenStack, and Avalon is contributing to the energy efficiency part of this project. We have proposed and brought our contribution to Climate, a new resource reservation framework for OpenStack, developed in collaboration with Bull, Mirantis and other OpenStack contributors. Climate allows the reservation of both physical and virtual resources, in order to provide a mono-tenancy environment suitable for HPC applications. Climate chooses the most efficient hosts (flop/W). This metric is computed from the CPU / GPU informations, mixed with real power consumption measurements provided by the Kwapi framework. The user requirements may be loose, allowing Climate to choose the best time slot to place the reservation. Climate has been improved with standby mode features, to shut down automatically the unused hosts. The first release of Climate was done in January 2014. Through the OpenStack process, Climate is now named Blazar.

Clustered Virtual Home Gateway (vHGW)

This result is a joint work between Avalon team (J.P. Gelas, L. Lefevre) and Addis Abeba University (M. Tsibie and T. Assefa). The customer premises equipment (CPE), which provides the interworking functions between the access network and the home network, consumes more than 80% of the total power in a wireline access network. In the GreenTouch initiative (cf Section  8.3 ), we aim at a drastic reduction of the power consumption by means of a passive or quasi-passive CPE. Such approach requires that typical home gateway functions, such as routing, security, and home network management, are moved to a virtual home gateway (vHGW) server in the network. In our first prototype virtual home gateways of the subscribers were put in LXC containers on a unique GNU/Linux server. The container approach is more scalable than separating subscribers by virtual machines. We demonstrated a sharing factor of 500 to 1000 virtual home gateways on one server, which consumes about 150 W, or 150 to 300 mW per subscriber. Comparing this power consumption with the power of about 2 W for the processor in a thick client home gateway, we achieved an efficiency gain of 5-10x. The prototype was integrated and demonstrated at TIA 2012 in Dallas. In our current work, we propose the Clustered vHGWs Data center architecture to yield optimal energy conservation through virtual machine’s migration among physical nodes based on the current subscriber’s service access state, while ensuring SLA respective subscribers. Thus, optimized energy utilization of the data center is assured without compromising the availability of service connectivity and QoS preferences of respective subscribers. The last prototype including those new features was integrated and demonstrated recently to the GreenTouch consortium members at Melbourne University.

Energy proportionality with heterogeneous computing resources

This work [16] focuses on improving energy proportionality of large scale virtualized environments. The main problem of such infrastructures is their high static costs due to high idle power consumption of idle servers. Our goal is to reach an infrastructure able to adapt its energy consumption to the current working load. Therefore we propose an original infrastructure composed of heterogeneous computing resources. We consider the heterogeneity at the level of the architecture, and we gather in our platform low power ARM processors together with powerful x86 servers. Around this infrastructure, we are developing a decisional framework to schedule applications on the architecture, or combination of architectures, most suitable to their current needs. The framework reacts dynamically to the resource needs evolutions by migrating the applications to the chosen destinations, and switching off unused nodes to save energy. We validate our scheduling policies by building a simulator based on a set of experimental inputs about power and performance hardware profiles and applications load profiles. This work is jointly done with IRIT Lab. (Toulouse) under the support of Inria Large Scale Initiative Hemera.

Energy efficient Core Networks

This work [11] seeks to improve the energy efficiency of backbone networks by providing an intra-domain Software Defined Network (SDN) approach to selectively turn off a subset of links. To do this, we change the status of router ports and transponders on the two extremities of a link. The status of these components is set to sleep mode whenever a link is not required to transfer data, and brought back to operational state when needed. We have analyzed the implementation issues of an energy-efficient SDN-based traffic engineering in core networks. We propose the STREETE framework (SegmenT Routing based Energy Efficient Traffic Engineering) that represents an online method to switch some links off/on dynamically according to the network load. We have implemented our proposed algorithms in the OMNET++ packet-based discrete event simulator. Experiments considering real network topologies (Germany50 and Géant) and real dynamic traffic matrices allowed us to quantify the trade-off between energy saving and impact of our solution on network performance. As mean to reroute the traffic we use a promising new protocol, SPRING. This comes in contrast with other works, which use classical IP link weights changes or MPLS+RSVP-TE for this purpose. SPRING proved itself well suited for dynamic reconfiguration of the network. Experimental results show that the consumption of 44% of links can be reduced while preserving good quality of service.

Energy aware scheduling for multi data centers clouds

Our work tackles the challenge of improving the energy efficiency of server provisioning and workload management [17] . It introduces a metric allowing infrastructure administrators to specify their preferences between performance and energy savings. We describe a framework for resource management which provides control for informed and automated provisioning at the scheduler level while providing developers (administrator or end-user) with an abstract layer to implement aggregation and resource ranking based on contextual information such as infrastructure status, users’ preferences and energy- related external events occurring over time. We integrate our solution in DIET which allows for managing heterogeneous nodes at the middleware layer. The evaluation is performed by means of simulations and real-life experiments on the GRID’5000 testbed. Results show improvements in energy efficiency with minimal impact on application and system performance. Implementation has been used within the industrial project Nu@ge in the context of a federation of modular datacenters.