基于网格存储系统的自适应数据分配策略

在网格存储系统中通常包含各种异构的存储设备节点.基于同构系统的传统数据分配和放置策略并不能针对网格存储系统中异构存储设备的性能差异来进行数据分配,降低了网格存储系统的性能.提出一种自适应的数据分配策略(AD).通过运用基于虚拟磁盘性能的自适应分配策略和自适应的数据副本创建策略,AD能够根据存储设备节点的性能差异有效的进行数据分配.实验证明,自适应的数据分配策略能够充分发挥异构存储设备的性能,有效解决网格存储系统的数据放置不平衡问题,提高网格存储系统的利用率.     

虚拟网络存储系统自适应数据分配策略

在虚拟网络存储系统中通常包含各种异构的存储设备节点。基于同构系统的传统数据分配和放置策略并不能针对异构存储设备的性能差异来进行数据分配,降低了虚拟网络存储系统的性能。该文提出一种自适应的数据分配策略,能够根据存储设备节点的性能差异有效地进行数据分配。实验证明,该策略能够充分发挥异构存储设备的性能,有效解决虚拟网络存储系统的数据放置不平衡问题,提高虚拟网络存储系统的利用率。     

进化存储系统中的物理进化

系统整体结构不能很好地适应系统磁盘的动态变化,这是现有存储系统中普遍存在的一个问题。而我们提出的进化存储系统ERAID（Evolving RAID system）是一个动态存储系统,能够在不停止系统I／O服务的前提下,采用DAA、HDAA、e-HDAA算法分别实现存储系统中同构磁盘的添加、异构磁盘的添加以及异构磁盘的替换,即实现存储系统的物理进化。仿真实验结果表明：在较小的系统开销下,DAA、HDAA、e-HDAA算法能逐渐吸收添加或替换到ERAID系统的（同构或异构）磁盘,使ERAID系统获得优化的存储客量和存储性能。     

基于竞争概率的片上网络带宽分配方法

在面向特定应用的片上系统中,不同模块之间的通信量和延迟需求差异很大,均等位宽的链路不能充分利用带宽资源。为此,提出一种非均匀的带宽分配方案,根据流量特征和竞争状况设定各链路的数据宽度,采用异构的互联结构合理分配连线资源并优化吞吐量。实验结果表明,在均匀流量模式下,非均匀位宽的异构网络和同构架构的吞吐量相近,而连线资源节省16%。在热点流量模式下,异构网络能够有效缓解局部拥塞状况,提高网络吞吐量。     

异构磁盘阵列DSUraid5数据分布方法

通过分析以往的异构磁盘阵列数据算法，提出了DSUraid5数据分布方法。根据磁盘性能参数，给磁盘设定不同的条带单元，提出虚拟同构磁阵的概念，解决校验块的计算及分布问题。通过结合动态条带单元和左对称校验单元布局方法，使磁阵中各磁盘达到负载均衡或基本均衡。模拟实验结果表明，与raid5相比，DSUraid5数据分布方法的性能可提升40％，适应于不同场合。     

异构Hadoop集群下的比例数据分配策略

针对异构Hadoop环境下仍采用均等的数据分配方法将严重降低MapReduce的性能,提出比例数据分配策略。通过计算异构集群中各节点的计算比率,将已经分割好的数据块重新进行组合,形成数个按比例划分的数据块。每个节点根据自身性能来选择所分配和存储的数据块,从而使异构Hadoop集群中各节点处理数据的时间大致相同,降低节点之间数据的移动量。实验验证了提出的比例数据分配方法可以有效地提高MapReduce的性能,并使数据负载均衡。     

并行I/O中大型多维数据集合分配策略研究

在大型多维数据集合处理中,对多维数据集合的拆分及其在磁盘上的存储分配是重要的研究课题。由于磁盘的机械运动已形成了数据I/O时的速度瓶颈,因此通过采用并行I/O技术,将多维数据进行有效的拆分,并在多个磁盘间进行分布存储是克服瓶颈的有效办法。基于此,论文中提出了一种多维数据的循环拆分方法,它是对二维数据集合循环拆分分配方法的扩展,性能比较与分析表明了新算法的有 效性。     

基于离散控制器合成的异构多核系统资源管理方法

近年来，随着半导体技术的发展以及应用多样化的需求，异构多核处理器已被广泛应用于高性能嵌入式系统中。这类系统面临的一个主要挑战就是如何在运行时对系统的可用资源（包括处理核等）进行管理分配从而满足系统及其所运行应用在性能和功耗等方面的需求。然而，虽然目前一些主流的资源管理技术在性能和/或功耗优化等方面取得了良好表现，但却经常对所设计的资源管理部件缺乏严格的可靠性保证，因此提出了一种基于离散控制器合成（DCS）的方法来对异构多核系统的在线资源管理策略进行自动、可靠的设计，即将形式化的、能够自动构造管理控制部件的DCS应用到异构多核系统的在线资源管理部件设计中。该方法通过采用形式化模型来描述异构系统的运行行为（例如如何为应用分配处理核），并将在线资源管理问题转换为一个面向某个系统管理目标（例如最大化应用性能）的DCS问题。在此基础上，通过现有的DCS工具对提出的方法进行了示例演示和验证，并对所使用DCS方法的可扩展性进行了评估。     

磁盘子系统striping技术的性能研究

本文对N 台磁盘存贮器组成一体,共同传输同一数据集的striping技术,应用软件模拟和理论分析的方法进行了性能研究,得出了传输块长与传输率间的关系,给出了为获得较高传输率加速比所需的最小块长,提出了能提高传输率的命令重迭控制方法。     

面向申威异构架构的并行代码自动生成

异构架构逐渐成为高性能计算领域的主流架构,但相较于同构多核架构,其硬件结构及存储层次更为复杂,程序编写更为困难.先进的优化编译器可以协助程序开发人员实现更为高效的代码,降低程序开发复杂度.多面体编译模型通过抽象分析将程序抽象成空间多面体表示形式,能够将多种循环变换与硬件映射相结合,并面向特定体系结构生成相应的代码.设计实现了一个面向国产申威异构架构的并行代码自动生成系统,采用“源-源”编译模式,基于多面体编译模型实现.系统针对申威异构架构特点将程序计算过程进行硬件部署,同时实现数据传输与内存空间的自动管理.实验基于Polybench测试集中线性代数相关用例进行测试.结果表明,利用代码自动生成系统生成的异构并行代码能够在申威异构平台上正确运行,并能够有效发挥申威异构平台的性能,基于申威异构平台利用64线程加速计算的平均加速比达到了539.16倍.     

Continuous retrieval of multimedia data using parallelism

Most implementations of workstation-based multimedia information systems cannot support a continuous display of high resolution audio and video data and suffer from frequent disruptions and delays termed hiccups. This is due to the low I/O bandwidth of the current disk technology, the high bandwidth requirement of multimedia objects, and the large size of these objects, which requires them to be almost always disk resident. A parallel multimedia information system and the key technical ideas that enable it to support a real-time display of multimedia objects are described. In this system, a multimedia object across several disk drives is declustered, enabling the system to utilize the aggregate bandwidth of multiple disks to retrieve an object in real-time. Then, the workload of an application is distributed evenly across the disk drives to maximize the processing capability of the system. To support simultaneous display of several multimedia objects for different users, two alternative approaches are described. The first approach multitasks a disk drive among several requests while the second replicates the data and dedicates resources to each individual request. The trade-offs associated with each approach are investigated using a simulation model     

Data‐aware task scheduling on heterogeneous hybrid memory multiprocessor systems

In this paper, we propose a method about task scheduling and data assignment on heterogeneous hybrid memory multiprocessor systems for real‐time applications. In a heterogeneous hybrid memory multiprocessor system, an important problem is how to schedule real‐time application tasks to processors and assign data to hybrid memories. The hybrid memory consists of dynamic random access memory and solid state drives when considering the performance of solid state drives into the scheduling policy. To solve this problem, we propose two heuristic algorithms called improvement greedy algorithm and the data assignment according to the task scheduling algorithm, which generate a near‐optimal solution for real‐time applications in polynomial time. We evaluate the performance of our algorithms by comparing them with a greedy algorithm, which is commonly used to solve heterogeneous task scheduling problem. Based on our extensive simulation study, we observe that our algorithms exhibit excellent performance and demonstrate that considering data allocation in task scheduling is significant for saving energy. We conduct experiments on two heterogeneous multiprocessor systems. Copyright © 2016 John Wiley & Sons, Ltd.     

Staggered striping: A flexible technique to display continuous media

During the past decade, information technology has evolved to where it is economically viable to store and retrieve continuous media data types, e.g., audio and video objects. Systems that support this data type are expected to play a major role in many applications including library information systems, entertainment technology, and educational applications. The objects of this new data type should be retrieved at a pre-specified bandwidth. If an object is retrieved at a rate lower than its pre-specified bandwidth then its display will suffer from frequent disruptions and delays termed hiccups.This paper describes staggered striping as a novel technique to support a hiccup-free retrieval of continuous media data types. Its design is based on a multidisk architecture. It is a flexible technique that can support media types whose bandwidth requirements are either lower or higher than the bandwidth of a single disk. Its design allows a system to scale to thousands of disk drives as its incurred overhead is fixed and does not increase as a function of additional disk drives.This research was supported in part by grants from AT&T/NCR/Teradata, Hewlett-Packard, IBM grant SJ92488, NSF grants IRI-9110522, IRI-9203389, and CDA-9216321 and DARPA contract DABT63-91-C-0001. An earlier version of this paper appeared in Proceedings of SIGMOD '94.     

Dual-stage servo systems and vibration compensation in computer hard disk drives

This paper discusses two mechatronic innovations in magnetic hard disk drive servo systems, which may have to be deployed in the near future, in order to sustain the continuing 60% annual increase in storage density of these devices. The first is the use of high bandwidth dual-stage actuator servo systems to improve the precision and track-following capability of the read/write head positioning control system. The second is the instrumentation of disk drive suspensions with vibration sensing strain gages, in order to enhance airflow-induced suspension vibration suppression in hard disk drives.     

A video caching policy for providing differentiated service grades and maximizing system revenue in hierarchical video servers

A video server normally targets at providing abundant bandwidth access and massive storage in supporting large-scale video archival applications. Its performance is sensitive to the deployment of the stored contents. In this paper, we propose a video caching policy for a video server, based on the knowledge of video profiles, namely: access rate, video size and bandwidth, tolerable rejection probability, and rental price. We consider the video server as having a hierarchical architecture which consists of a set of high-speed disk drives located in the front end for caching a subset of videos, and another set of high-capacity tertiary devices located in the back end for archiving the entire video collection. The front-end disks particularly, are organized together by employing a proposed data striping scheme, termed the adaptive striping (AS), which is flexible on heterogeneous disk integration. The proposed policy determines what video set should be cached, and how to arrange them in the front-end disks with two objectives in mind: (1) offering differentiated service grades conforming to the video profiles as well as (2) maximizing the overall system revenue. We simulate the system with various configurations, and the results affirm our effective approach.     

Highly available and heterogeneous continuous media storage systems

A number of recent technological trends have made data intensive applications such as continuous media (audio and video) servers a reality. These servers store and retrieve large volumes of data using magnetic disks. Servers consisting of multiple nodes and large arrays of heterogeneous disk drives have become a fact of life for several reasons. First, magnetic disks might fail. Failed disks are almost always replaced with newer disk models because the current technological trend for these devices is one of annual increase in both performance and storage capacity. Second, storage requirements are ever increasing, forcing servers to be scaled up progressively. In this study, we present a framework to enable parity-based data protection for heterogeneous storage systems and to compute their mean lifetime. We describe the tradeoffs associated with three alternative techniques: independent subservers, dependent subservers, and disk merging. The disk merging approach provides a solution for systems that require highly available secondary storage in environments that also necessitate maximum flexibility.     

Towards minimizing disk I/O contention: A partitioned file assignment approach

One problem with data-intensive computing facilitating is how to effectively manage massive amounts of data stored in a parallel I/O system. The file assignment method plays a significant role in data management. However, in the context of a parallel I/O system, most existing file assignment approaches share the following two limitations. First, most existing methods are designed for a non-partitioned file, while the file in a parallel I/O system is generally partitioned to provide aggregated bandwidth. Second, the file allocation metric, e.g. service time, of most existing methods is difficult to determine in practice, and also these metrics only reflect the static property of the file. In this paper, a new metric, namely file access density is proposed to capture the dynamic property of file access, i.e. disk contention property. Based on file access density definition, this paper introduces a new static file assignment algorithm named MinCPP and its dynamic version DMinCPP, both of which aim at minimizing the disk contention property. Furthermore MinCPP and DMinCPP take the file partition property into consideration by trying to allocate the partitions belonging to the same file onto different disks. By assuming file request arrival follows the Poisson process, we prove the effectiveness of the proposed schemes both analytically and experimentally. The MinCPP presented in this study can be applied to reorganize the files stored in a large-scale parallel I/O system and the DMinCPP can be integrated into file systems which dynamically allocate files in a batch.     

Servo design for high-TPI computer disk drives using a delay-accommodating state estimator

A servo design method is presented for high track-density computer disk drives, in which the plant time delay, mainly due to the processor computation time, is taken into account. The key idea is to incorporate the delay model into the output equation of the state-space representation of the plant model. The application results confirm that the proposed method is very effective in enabling a higher servo bandwidth and, thereby, in realizing nano-level control accuracy required in high track-density computer disk drives.