Michał Karpowicz

Energy-efficient CPU frequency control for the Linux system

Efficiency of energy usage in computing systems improves, however, still not at the rate matching the climbing demand for computing capacity. To address this urging problem, computing elements of the latest generation, that is, CPUs/graphics processing units, memory units, and network interface cards, have been designed to operate in multiple modes with differentiated energy consumption levels. Mode switching and high‐frequency performance monitoring functions have also been exposed by co‐designed abstract programming interfaces. The challenge of energy‐efficient computing is to develop hardware control mechanisms taking advantage of the new capabilities. This paper aims at giving an insight into the structure of optimal energy‐aware CPU frequency scaling rules. It gives a characterization of solutions to the optimal control problem of energy‐efficient real‐time packet inspection performed by a Linux server. A class of CPU frequency switching rules, exploiting dynamic voltage and frequency scaling mechanisms, is constructed based on experimentally identified model of server operations. The control rules are demonstrated to outperform the default CPU frequency scaling governor for the Linux kernel, both in terms of achievable power savings and service quality. Copyright

Nash equilibrium design and price-based coordination in hierarchical systems

This paper deals with the problem of designing Nash equilibrium points in noncooperative games in which agents anticipate values of Lagrange multipliers coordinating their payoff functions. The addressed model of agents’ interactions, referred to as the price-anticipation game, is studied within the framework of coordination and mechanism design theory for hierarchical systems. Sufficient conditions are formulated for Nash implementation of a regular and isolated solution to a coordination problem. An equilibrium design procedure is proposed and applied as an analytic tool in a study of mechanism design games. In the setting considered the well-known fact is demonstrated that gains from reaching a desired solution to a coordination problem in a Nash equilibrium point need not balance the overall costs of its implementation. However, it is also demonstrated how these costs can be distributed among the agents and related to the particular organization of interactions in the system. Finally, application of the developed framework in the field of Internet traffic engineering is presented.

Characterization of scalar strategy mechanisms for efficient resource allocation: Supply side case

We give a characterization of scalar strategy mechanisms that efficiently allocate production among strategically interdependent agents. We establish necessary and sufficient conditions for the mechanisms to yield allocations that maximize aggregate surplus of the market under constraints given by the market-clearing equation setting a price at which the total output supplied equals demand. Efficient Nash equilibria of games induced by the proposed class of mechanisms are proved to be asymptotically stable and reachable in a dynamical bidding process. A distributed bidding algorithm is given as well.

On Efficient Resource Allocation in Communication Networks

We study the problem of allocating a single divisible resource to strategic agents in communication networks. For the setting of inelastic supply we formulate conditions for the efficiency of Nash equilibria in a resulting resource allocation game. Then we answer the question how to design a mechanism which yields efficient allocations and analyze revenues generated by the proposed class of mechanisms. Finally, we propose a distributed resource allocation algorithm and prove its convergence.

Preliminary results on the Linux libpcap model identification

The article presents the results of studies in which models of the Linux system packet capture operations were identified. Performance of the kernel-level packet filters was recorded in a series of adequately designed experiments. Based on the collected data linear models of CPU workload were estimated and analyzed in time and frequency domain. Models of low orders were obtained that provide satisfactory fit to estimation data with normally distributed residuals.

Energy-Aware Multilevel Control System for a Network of Linux Software Routers: Design and Implementation

The Linux operating system provides many well-developed tools that support the concept of energy-efficient networking. This paper outlines the results of research focused on the design and implementation of a control system reducing power consumption of IP-traffic processing in a network of Linux-based software routers. It is demonstrated how the standard ACPI-compliant system components can be adjusted to meet the requirements of adaptive energy-aware network control and what performance tradeoffs may there be expected. In particular, it is demonstrated how the abstraction layers provided by the Linux kernel can be used to exploit energy-saving mechanisms of packet processing servers. Formulations of the routing optimization and service rate control problems are presented and discussed. The results of the extensive experimental studies are presented as well.

Design and implementation of energy-aware application-specific CPU frequency governors for the heterogeneous distributed computing systems☆

Abstract This paper deals with the design of application-specific energy-aware CPU frequency scaling mechanisms. The proposed customized CPU controllers may optimize performance of data centers in which diverse tasks are allocated to servers with different characteristics. First, it is demonstrated that server power usage can be accurately estimated based on the measurements of CPU power consumption read from the model specific registers (MSRs). Next, a benchmarking methodology derived from the RFC2544 specification is proposed that allows to identify models of CPU workload dynamics. Finally, it is demonstrated how the identified models can be applied in the design of customized energy-aware controllers that dynamically adjust CPU frequency to the application-specific workload patterns. According to the results of experimental studies the customized controllers may outperform standard general-purpose governors of the Linux kernel both in terms of reachable server performance and power saving capabilities.

Energy and Power Efficiency in Cloud

Reduction of energy consumption is clearly one of the major technological challenges arising with development of cloud computing infrastructures. To meet the ever increasing demand for computing power, recent research efforts have been taking holistic view to energy-aware design of hardware, middleware, and data processing applications. Indeed, advances in hardware layer development require immediate improvements in the design of system control software. For this to be possible, new power management capabilities of hardware layer need to be exposed in the form of flexible Application Program Interfaces (APIs). Consequently, novel APIs and cluster management tools allow for system-wide regulation of energy consumption, capable of collecting and processing detailed cluster performance measurements, and taking real-time coordinated actions across the cloud infrastructure. This chapter presents an overview of techniques developed to improve energy efficiency of cloud computing. Power consumption models and energy usage profiles are presented together with energy efficiency measuring methods. Modeling of computing and network dynamics is discussed from the viewpoint of system identification theory, indicating basic experiment design problems and challenges. Novel approaches to cluster and network-wide energy usage optimisation are surveyed, including multi-level power and software control systems, energy-aware task scheduling, resource allocation algorithms and frameworks for backbone networks management. Software-development techniques and tools are also presented as a new promising way to reduce power consumption at the computing node level. Finally, energy-aware server-level and network-level control mechanisms are presented, including ACPI-compliant low power idle and service rate scaling solutions.

Server Power Consumption: Measurements and Modeling with MSRs

Precise model of power consumption is crucial for the design of controllers improving energy effectiveness of servers. This paper shows how the power usage statistics available via processor registers may be correlated to the total power consumption measurements of servers performing different types of operations. Identification of such relations may support development of power consumption models and application specific energy-aware server controllers.

CHARACTERIZATION OF SCALAR-STRATEGY MECHANISMS FOR EFFICIENT RESOURCE ALLOCATION: DEMAND SIDE CASE

Abstract We give a characterization of scalar strategy mechanisms that efficiently allocate a single divisible resource among strategically interdependent agents. We establish necessary and sufficient conditions for the mechanisms to yield allocations that maximize aggregate surplus of the system under constraints given by the market-clearing equation setting a price at which the total output supplied equals demand.