This paper introduces the FAWN—Fast Array of Wimpy Nodes—cluster architecture for providing fast, scalable, and power-efficient key-value storage. A FAWN links together a large number of tiny nodes built using embedded processors and small amounts (2–16GB) of flash memory into an ensemble capable of handling 700 queries per second per node, while consuming fewer than 6 watts of power per node. We have designed and implemented a clustered key-value storage system, FAWN-DHT, that runs atop these node. Nodes in FAWN-DHT use a specialized log-like back-end hash-based database to ensure that the system can absorb the large write workload imposed by frequent node arrivals and departures. FAWN uses a two-level cache hierarchy to ensure that imbalanced workloads cannot create hot-spots on one or a few wimpy nodes that impair the system’s ability to service queries at its guaranteed rate. Our evaluation of a small-scale FAWN cluster and several candidate FAWN node systems suggest that FAWN can be a practical approach to building large-scale storage for seek-intensive workloads. Our further analysis indicates that a FAWN cluster is cost-competitive with other approaches (e.g., DRAM, multitudes of magnetic disks, solid-state disk) to providing high query rates, while consuming 3-10x less power. Acknowledgements: We thank the members and companies of the CyLab Corporate Partners and the PDL

Energy expenses are becoming an increasingly important fraction of data center operating costs. At the same time, the energy expense per unit of computation can vary significantly between two different locations. In this paper, we characterize the variation due to fluctuating electricity prices and argue that existing distributed systems should be able to exploit this variation for significant economic gains. Electricity prices exhibit both temporal and geographic variation, due to regional demand differences, transmission inefficiencies, and generation diversity. Starting with historical electricity prices, for twenty nine locations in the US, and network traffic data collected on Akamai’s CDN, we use simulation to quantify the possible economic gains for a realistic workload. Our results imply that existing systems may be able to save millions of dollars a year in electricity costs, by being cognizant of locational computation cost differences. Categories andSubject Descriptors

Recent years have seen a flurry of energy-efficient networking research. But does decreasing the energy used by the Internet actually save society much energy? To answer this question, we estimate the Internet’s energy consumption. We include embodied energy (emergy)—the energy required to construct the Internet—a quantity that has often been ignored in previous work. We find that while in absolute terms the Internet uses significant energy, this quantity is negligible when compared with society’s colossal energy use.

This paper presents the architecture and motivation for a clusterbased, many-core computing architecture for energy-efficient, dataintensive computing. FAWN, a Fast Array of Wimpy Nodes, consists of a large number of slower but efficient nodes coupled with low-power storage. We present the computing trends that motivate a FAWN-like approach, for CPU, memory, and storage. We follow with a set of microbenchmarks to explore under what workloads these “wimpy nodes ” perform well (or perform poorly). We conclude with an outline of the longer-term implications of FAWN that lead us to select a tightly integrated stacked chip-and-memory architecture for future FAWN development.

Technological and economic trends in data centers push toward facilities operated at higher ambient temperatures and at higher power densities to meet ever-increasing computational demands. Conventionally, data centers are cooled with vapor-compressor equipment which requires extra power to be driven. This paper proposes an alternative and sustainable data center cooling architecture that is heat driven. The thermal source is the heat produced by the data center room's equipment. A major challenge is providing both enough cooling to the data center and enough exergy to drive the cooling process, regardless of the thermal output of the data center equipment. This challenge is addressed by the use of organic heat storage and a sustainably powered (i.e. solarpowered) heat source, leading potentially to a PUE (Power Usage Effectiveness) value of less than one.

sustainable development.

Data center networks encode locality and topology information into their server and switch addresses for performance and routing purposes. For this reason, the traditional address configuration protocols such as DHCP require huge amount of manual input, leaving them error-prone. In this paper, we present DAC, a generic and automatic Data center Address Configuration system. With an automatically generated blueprint which defines the connections of servers and switches labeled by logical IDs, e.g., IP addresses, DAC first learns the physical topology labeled by device IDs, e.g., MAC addresses. Then at the core of DAC is its device-to-logical ID mapping and malfunction detection. DAC makes an innovation in abstracting the device-to-logical ID mapping to the graph isomorphism problem, and solves it with low time-complexity by leveraging the attributes of data center network

Abstract. In this paper we analyze energy usage in divisible load processing. Divisible load theory (DLT) applies to computations which can be divided into parts of arbitrary sizes, and the parts can be independently processed in parallel. The shortest schedule for divisible load processing is determined by the speed of computation and communication. Energy usage for such a time-optimum schedule is analyzed in this paper. We propose a simple model of energy consumption. Two states of the computing system are taken into account: an active state and an idle state with reduced energy consumption. Energy consumption is examined as a function of system parameters. We point out possible ways of energy conservation. It is demonstrated that energy can be saved by use of parallel processing. Keywords: Energy-efficient computing, performance evaluation, divisible loads. 1

This paper presents the architecture and motivation for a clusterbased, many-core computing architecture for energy-efficient, dataintensive computing. FAWN, a Fast Array of Wimpy Nodes, consists of a large number of slower but efficient nodes coupled with low-power storage. We present the computing trends that motivate a FAWN-like approach, for CPU, memory, and storage. We follow with a set of microbenchmarks to explore under what workloads these FAWN nodes perform well (or perform poorly), and briefly examine scenarios in which both code and algorithms may need to be re-designed or optimized to perform well on an efficient platform. We conclude with an outline of the longer-term implications of FAWN that lead us to select a tightly integrated stacked chipand-memory architecture for future FAWN development.

0716287, and CCF-0964474, Intel, by gi�s from Network Appliance and Google, and through fellowships