Power management has become increasingly necessary in large-scale datacenters to address costs and limitations in cooling or power delivery. This paper explores how to integrate power management mechanisms and policies with the virtualization technologies being actively deployed in these environments. The goals of the proposed VirtualPower approach to online power management are (i) to support the isolated and independent operation assumed by guest virtual machines (VMs) running on virtualized platforms and (ii) to make it possible to control and globally coordinate the effects of the diverse power management policies applied by these VMs to virtualized resources. To attain these goals, VirtualPower extends to guest VMs ‘soft ’ versions of the hardware power states for which their policies are designed. The resulting technical challenge is to appropriately map VM-level updates made to soft power states to actual changes in the states or in the allocation of underlying virtualized hardware. An implementation of VirtualPower Management (VPM) for the Xen hypervisor addresses this challenge by provision of multiple system-level abstractions including VPM states, channels, mechanisms, and rules. Experimental evaluations on modern multicore platforms highlight resulting improvements in online power management capabilities, including minimization of power consumption with little or no performance penalties and the ability to throttle power consumption while still meeting application requirements. Finally, coordination of online methods for server consolidation with VPM management techniques in heterogeneous server systems is shown to provide up to 34% improvements in power consumption.

Service placement deals with the problem of selecting which node in a network is most suitable for hosting a service that responds to queries from other nodes. Optimally placing services reduces network traffic and improves connectivity between clients and servers. Service placement algorithms may thus be regarded as an interesting building block for research into service-oriented middleware. Recently, new approaches to address the service placement problem in the field of ad-hoc networking have been proposed. This paper surveys, classifies and evaluates ten representative approaches, thereby providing a summary of the state of the art in service placement. 1

Power has become the first class design constraint in modern processor design. To reduce the power density caused by aggressive, speculative execution seen in previous processor generations, computer architects have turned to a multicore design strategy with each core substantially simplified. Additionally, different power-saving features have been proposed and integrated into each core to adapt dynamic execution scenarios. Due in part to the independent nature of these cores, the power management has also become more flexible to further reduce the overall power consumption. With careful adaptation schemes, the system can save power by entering different idle states dynamically with minimal performance impact. Given the simultaneous emergence of virtualization technologies, the question, then, is how to effectively leverage these idle states in the context of multiple virtual machines (VMs) executing on multicore parts. Towards this end, we develop the IdlePower approach to managing idle states in virtualized systems. Our approach combines a novel batching algorithm that creates improved opportunities to enter deep idle states by removing unnecessary system wakeups depending upon monitored behavior of workloads. IdlePower also provides application awareness in another fashion by not only entering deep idle states based upon transition latencies, but also factoring in the performance degradation that can occur due to secondary effects such as data loss in cache structures. We extend the use of Bloom filters with IdlePower to detect application characteristics for dynamically predicting whether deep idle states are worthwhile based upon possible performance implications. Overall, IdlePower is shown to improve residencies in the deepest C3 idle state by up to 10%, and to avoid performance degradations in workloads of up to 26%. 1.

approaches have gained remarkable ground from academia and industry. CMA is the state-of-the-art mobile augmentation model that employs resource-rich clouds to increase, enhance, and optimize computing capabilities of mobile devices aiming at execution of resource-intensive mobile applications. Augmented mobile devices envision to perform extensive computations and to store big data beyond their intrinsic capabilities with least footprint and vulnerability. Researchers utilize varied cloudbased computing resources (e.g., distant clouds and nearby mobile nodes) to meet various computing requirements of mobile users. However, employing cloud-based computing resources is not a straightforward panacea. Comprehending critical factors (e.g., current state of mobile client and remote resources) that impact on augmentation process and optimum selection of cloudbased resource types are some challenges that hinder CMA