Blade server

Abstract: Network architecture, computer system and/or server, circuit, device, apparatus, method, and computer program and control mechanism for managing power consumption and workload in computer system and data and information servers. Further provides power and energy consumption and workload management and control systems and architectures for high-density and modular multi-server computer systems that maintain performance while conserving energy and method for power management and workload management. Dynamic server power management and optional dynamic workload management for multi-server environments is provided by aspects of the invention. Modular network devices and integrated server system, including modular servers, management units, switches and switching fabrics, modular power supplies and modular fans and a special backplane architecture are provided as well as dynamically reconfigurable multi-purpose modules and servers. Backplane architecture, structure, and method that has no active components and separate power supply lines and protection to provide high reliability in server environment.

Abstract: The increasing costs of power delivery and cooling, as well as the trend toward higher-density computer systems, have created a growing demand for better power management in server environments. Despite the increasing interest in this issue, little work has been done in quantitatively understanding power consumption trends and developing simple yet accurate models to predict full-system power. We study the component-level power breakdown and variation, as well as temporal workload-specific power consumption of an instrumented power-optimized blade server. Using this analysis, we examine the validity of prior adhoc approaches to understanding power breakdown and quantify several interesting trends important for power modeling and management in the future. We also introduce Mantis, a nonintrusive method for modeling full-system power consumption and providing real-time power prediction. Mantis uses a onetime calibration phase to generate a model by correlating AC power measurements with user-level system utilization metrics. We experimentally validate the model on two server systems with drastically different power footprints and characteristics (a low-end blade and high-end compute-optimized server) using a variety of workloads. Mantis provides power estimates with high accuracy for both overall and temporal power consumption, making it a valuable tool for power-aware scheduling and analysis.

Abstract: Network architecture, computer system and/or server, circuit, device, apparatus, method, and computer program and control mechanism for managing power consumption and workload in computer system and data and information servers Further provides power and energy consumption and workload management and control systems and architectures for high-density and modular multi-server computer systems that maintain performance while conserving energy and method for power management and workload management Dynamic server power management and optional dynamic workload management for multi-server environments is provided by aspects of the invention Modular network devices and integrated server system, including modular servers, management units, switches and switching fabrics, modular power supplies and modular fans and a special backplane architecture are provided as well as dynamically reconfigurable multi-purpose modules and servers Backplane architecture, structure, and method that has no active components and separate power supply lines and protection to provide high reliability in server environment

Abstract: Distributed data processing framework MapReduce is increasingly deployed in Clouds to leverage the pay-per-usage cloud computing model. Popular Hadoop MapReduce environment expects that end users determine the type and amount of Cloud resources for reservation as well as the configuration of Hadoop parameters. However, such resource reservation and job provisioning decisions require in-depth knowledge of system internals and laborious but often ineffective parameter tuning. We propose and develop AROMA, a system that automates the allocation of heterogeneous Cloud resources and configuration of Hadoop parameters for achieving quality of service goals while minimizing the incurred cost. It addresses the significant challenge of provisioning ad-hoc jobs that have performance deadlines in Clouds through a novel two-phase machine learning and optimization framework. Its technical core is a support vector machine based performance model that enables the integration of various aspects of resource provisioning and auto-configuration of Hadoop jobs. It adapts to ad-hoc jobs by robustly matching their resource utilization signature with previously executed jobs and making provisioning decisions accordingly. We implement AROMA as an automated job provisioning system for Hadoop MapReduce hosted in virtualized HP ProLiant blade servers. Experimental results show AROMA's effectiveness in providing performance guarantee of diverse Hadoop benchmark jobs while minimizing the cost of Cloud resource usage.