CSR: Small: Energy Proportional Storage Systems

美国环境保护署（EPA）估计，到2011年，数据中心的能源消耗将增长到1000亿千瓦时，占美国总电力需求的2.9%。该项目从根本上研究了构建能量比例存储系统的新技术，该系统消耗的能量与I/O工作负载强度成比例。它认为，精心构建的基于数据复制的方法（而不是数据迁移）与为了一致性的后台数据同步相结合，为实现动态存储整合提供了更有效的机制。该项目的贡献包括：(1)虚拟化SAN （VSAN）和复制分布式文件/对象系统（DFS）存储架构的能量比例设计；(2)VSAN和DFS架构的能量比例问题的形式化模型，以及该框架内各种子问题的算法基础的开发；(3)在整合下控制动态工作集移位和意外I/O突发期间I/O性能影响的新技术，后台副本同步的调度策略，以及在特定存储系统上估计给定工作负载或一组整合工作负载性能的新模型。考虑到数据中心内的服务器在远低于峰值水平的情况下运行，以及当今的存储系统由固有的非能量比例磁盘设备组成，该项目开发了一种关键的使能技术，可以更高效地运行数据中心。开源系统软件的创建和分发将有助于技术转让。

The Environmental Protection Agency (EPA) estimates that energy consumption at data centers could grow to 100 billion KWhr, contributing to 2.9% of the total US electricity needs, by the year 2011. This project investigates fundamentally new techniques for building energy proportional storage systems that consume energy in proportion to the I/O workload intensity. It takes the view that a carefully constructed data replication based approach (instead of data migration) combined with background data synchronization for consistency provide more effective mechanisms for enabling dynamic storage consolidation. Contributions of this project include:(1) Energy proportional designs for both virtualized SAN (VSAN) and the replicated distributed file/object system (DFS) storage architectures, (2) Formal models of the energy proportionality problem for VSAN and DFS architectures and the development of algorithmic foundations for various sub-problems within this framework, and (3) Novel techniques to control the I/O performance impact during dynamic working set shifts and unexpected I/O bursts under consolidation, scheduling strategies for background replica synchronization, and new models for estimating the performance of a given workload or a set of consolidated workloads on a specific storage system.Given that servers within data centers operate at well below peak levels and that today's storage systems are composed of inherently non energy proportional disk devices, this project develops a key enabling technology for operating data centers more energy-efficiently. The creation and distribution of open source systems software will aid technology transfer.