一种优化MapReduce系统能耗的数据布局算法

在云计算技术和大数据技术的推动下,IT资源的规模不断扩大,其能耗问题日益显著.研究表明:节点资源利用率不高、资源空闲导致的能源浪费,是目前大规模分布式系统的主要问题之一.研究了MapReduce系统的能耗优化.传统的基于软件技术的能耗优化方法多采用负载集中和节点开关算法,但由于MapReduce任务的特点,集群节点不仅要完成运算,还需要存储数据,因此,传统方法难以应用到MapReduce集群.提出了良好的数据布局可以优化集群能耗.基于此,首先定义了数据布局的能耗优化目标,并提出相应的数据布局算法;接着,从理论上证明该算法能够实现数据布局的能耗优化目标;最后,在异构集群中部署3种数据布局不同的MapReduce系统,通过对比三者在执行CPU密集型、I/O密集型和交互型这3种典型运算时的集群能耗,验证了所提出的数据布局算法的能耗优化效果.理论和实验结果均表明,所提出的布局算法能够有效地降低MapReduce集群的能耗.上述工作都将促进高能耗计算和大数据分析的应用.     

MapReduce集群环境下的数据放置策略

MapReduce是一种适用于大规模数据密集型应用的有效编程模型,具有编程简单、易于扩展、容错性好等特点,已在并行和分布式计算领域得到了广泛且成功的应用.由于MapReduce将计算扩展到大规模的机器集群上,处理数据的合理放置成为影响MapReduce集群系统性能(包括能耗、资源利用率、通信和I/O代价、响应时间、系统的可靠性和吞吐率等)的关键因素之一.首先,对MapReduce编程模型的典型实现——Hadoop缺省的数据放置策略进行分析,并进一步讨论了MapReduce框架下,设计数据放置策略时需考虑的关键问题和衡量数据放置策略的标准;其次,对目前MapReduce集群环境下的数据放置策略优化方法的研究与进展进行了综述和分析;最后,分析和归纳了MapReduce集群环境下数据放置策略的下一步研究工作.     

Governing energy consumption in Hadoop through CPU frequency scaling: An analysis

With increasingly inexpensive storage and growing processing power, the cloud has rapidly become the environment of choice to store and analyze data for a variety of applications. Most large-scale data computations in the cloud heavily rely on the MapReduce paradigm and on its Hadoop implementation. Nevertheless, this exponential growth in popularity has significantly impacted power consumption in cloud infrastructures. In this paper, we focus on MapReduce processing and we investigate the impact of dynamically scaling the frequency of compute nodes on the performance and energy consumption of a Hadoop cluster. To this end, a series of experiments are conducted to explore the implications of Dynamic Voltage and Frequency Scaling (DVFS) settings on power consumption in Hadoop clusters. By enabling various existing DVFS governors (i.e., performance, powersave, ondemand, conservative and userspace) in a Hadoop cluster, we observe significant variation in performance and power consumption across different applications: the different DVFS settings are only sub-optimal for several representative MapReduce applications. Furthermore, our results reveal that the current CPU governors do not exactly reflect their design goal and may even become ineffective to manage the power consumption in Hadoop clusters. This study aims at providing a clearer understanding of the interplay between performance and power management in Hadoop clusters and therefore offers useful insight into designing power-aware techniques for Hadoop systems.     

Optimizing and Tuning MapReduce Jobs to Improve the Large‐Scale Data Analysis Process

Data‐intensive applications process large volumes of data using a parallel processing method. MapReduce is a programming model designed for data‐intensive applications for massive data sets and an execution framework for large‐scale data processing on clusters of commodity servers. While fault tolerance, easy programming structure, and high scalability are considered strong points of MapReduce; however its configuration parameters must be fine‐tuned to the specific deployment, which makes it more complex in configuration and performance. This paper explains tuning of the Hadoop configuration parameters, which directly affect MapReduce's job workflow performance under various conditions to achieve maximum performance. On the basis of the empirical data we collected, it became apparent that three main methodologies can affect the execution time of MapReduce running on cluster systems. Therefore, in this paper, we present a model that consists of three main modules: (1) Extending a data redistribution technique in order to find the high‐performance nodes, (2) Utilizing the number of map/reduce slots in order to make it more efficient in terms of execution time, and (3) Developing a new hybrid routing schedule shuffle phase in order to define the scheduler task while memory management level is reduced.     

最小化多MapReduce任务总完工时间的分析模型及其应用

随着大规模的MapReduce集群广泛地用于大数据处理,特别是当有多个任务需要使用同一个Hadoop集群时,一个关键问题是如何最大限度地减少集群的工作时间,提高MapReduce作业的服务效率。可将多个MapReduce作业当做一个调度任务建模,观察发现多个任务的总完工时间和任务的执行顺序有密切关系。 研究目标是设计作业调度系统分析模型,最小化一批MapReduce作业的总完工时间。提出一个更好的调度策略和实现方法, 使整个调度系统符合经典Johnson算法的条件, 从而可使用经典Johnson算法在线性时间内获取总完工时间的最优解。同时,针对需要使用两个或多个资源池进行平衡的问题, 提出了一种线性时间解决方案, 优于已知的近似模拟方案。该理论模型可应用于提高系统响应速度、节能和负载均衡等方面, 对应的应用实例提供了证实。     

Improving the energy efficiency of data-intensive applications running on clusters

Abstract

As an alternative to traditional computing architecture, cloud computing now is rapidly growing. However, it is based on models like cluster computing in general. Now supercomputers are getting more and more powerful, helping scientists have more indepth understanding of the world. At the same time, clusters of commodity servers have been mainstream in the IT industry, powering not only large Internet services but also a growing number of data-intensive scientific applications, such as MPI based deep learning applications. In order to reduce the energy cost, more and more efforts are made to improve the energy consumption of HPC systems. Because I/O accesses account for a large portion of the execution time for data intensive applications, it is critical to design energy-aware parallel I/O functions for addressing challenges related to HPC energy efficiency. As the de facto standard for designing parallel applications in cluster environment, the Message Passing Interface has been widely used in high performance computing, therefore, getting the energy consumption information of MPI applications is critical for improving the energy efficiency of HPC systems. In this work we first present our energy measurement tool, a software framework that eases the energy collection in cluster environment. And then we present an approach which can optimise the parallel I/O operation’s energy efficiency. The energy scheduling algorithm is evaluated in a cluster.     

Parallel meta-blocking for scaling entity resolution over big heterogeneous data

Entity resolution constitutes a crucial task for many applications, but has an inherently quadratic complexity. In order to enable entity resolution to scale to large volumes of data, blocking is typically employed: it clusters similar entities into (overlapping) blocks so that it suffices to perform comparisons only within each block. To further increase efficiency, Meta-blocking is being used to clean the overlapping blocks from unnecessary comparisons, increasing precision by orders of magnitude at a small cost in recall. Despite its high time efficiency though, using Meta-blocking in practice to solve entity resolution problem on very large datasets is still challenging: applying it to 7.4 million entities takes (almost) 8 full days on a modern high-end server.In this paper, we introduce scalable algorithms for Meta-blocking, exploiting the MapReduce framework. Specifically, we describe a strategy for parallel execution that explicitly targets the core concept of Meta-blocking, the blocking graph. Furthermore, we propose two more advanced strategies, aiming to reduce the overhead of data exchange. The comparison-based strategy creates the blocking graph implicitly, while the entity-based strategy is independent of the blocking graph, employing fewer MapReduce jobs with a more elaborate processing. We also introduce a load balancing algorithm that distributes the computationally intensive workload evenly among the available compute nodes. Our experimental analysis verifies the feasibility and superiority of our advanced strategies, and demonstrates their scalability to very large datasets.     

用于Hadoop2.x的MapReduce性能评估模型

基于MapReduce的程序被越来越多地应用于大型数据分析的应用中.Apache Hadoop是最常用的开源MapReduce模型之一.程序运行时间的缩短对于MapReduce程序以及所有数据处理应用而言至关重要,而能够准确估算MapReduce程序的执行时间是优化程序的重要环节.本文定义了一个在Hadoop2.x版本...     

基于Spark的MapReduce相似度计算效率优化

随着互联网的用户及内容呈指数级增长,大规模数据场景下的相似度计算对算法的效率提出了更高的要求。为提高算法的执行效率,对MapReduce架构下的算法执行缺陷进行了分析,结合Spark适于迭代型及交互型任务的特点,基于二维划分算法将算法从MapReduce平台移植到Spark平台;同时,通过参数调整、内存优化等方法进一步提高算法的执行效率。通过2组数据集分别在3组不同规模的集群上的实验表明,与MapReduce相比,在Spark平台下算法的执行效率平均提高了4.715倍,平均能耗效率只有Hadoop能耗的24.86%,能耗效率提升了4倍左右。     

Evaluating ARM HPC clusters for scientific workloads

The power consumption of modern high‐performance computing (HPC) systems that are built using power hungry commodity servers is one of the major hurdles for achieving Exascale computation. Several efforts have been made by the HPC community to encourage the use of low‐powered system‐on‐chip (SoC) embedded processors in large‐scale HPC systems. These initiatives have successfully demonstrated the use of ARM SoCs in HPC systems, but there is still a need to analyze the viability of these systems for HPC platforms before a case can be made for Exascale computation. The major shortcomings of current ARM‐HPC evaluations include a lack of detailed insights about performance levels on distributed multicore systems and performance levels for benchmarking in large‐scale applications running on HPC. In this paper, we present a comprehensive evaluation of results that covers major aspects of server and HPC benchmarking for ARM‐based SoCs. For the experiments, we built an unconventional cluster of ARM Cortex‐A9s that is referred to as Weiser and ran single‐node benchmarks (STREAM, Sysbench, and PARSEC) and multi‐node scientific benchmarks (High‐performance Linpack (HPL), NASA Advanced Supercomputing (NAS) Parallel Benchmark, and Gadget‐2) in order to provide a baseline for performance limitations of the system. Based on the experimental results, we claim that the performance of ARM SoCs depends heavily on the memory bandwidth, network latency, application class, workload type, and support for compiler optimizations. During server‐based benchmarking, we observed that when performing memory intensive benchmarks for database transactions, x86 performed 12% better for multithreaded query processing. However, ARM performed four times better for performance to power ratios for a single core and 2.6 times better on four cores. We noticed that emulated double precision floating point in Java resulted in three to four times slower performance as compared with the performance in C for CPU‐bound benchmarks. Even though Intel x86 performed slightly better in computation‐oriented applications, ARM showed better scalability in I/O bound applications for shared memory benchmarks. We incorporated the support for ARM in the MPJ‐Express runtime and performed comparative analysis of two widely used message passing libraries. We obtained similar results for network bandwidth, large‐scale application scaling, floating‐point performance, and energy‐efficiency for clusters in message passing evaluations (NBP and Gadget 2 with MPJ‐Express and MPICH). Our findings can be used to evaluate the energy efficiency of ARM‐based clusters for server workloads and scientific workloads and to provide a guideline for building energy‐efficient HPC clusters. Copyright © 2015 John Wiley & Sons, Ltd.     

Adapting scientific computing problems to clouds using MapReduce

Cloud computing, with its promise of virtually infinite resources, seems to suit well in solving resource greedy scientific computing problems. To study this, we established a scientific computing cloud (SciCloud) project and environment on our internal clusters. The main goal of the project is to study the scope of establishing private clouds at the universities. With these clouds, students and researchers can efficiently use the already existing resources of university computer networks, in solving computationally intensive scientific, mathematical, and academic problems. However, to be able to run the scientific computing applications on the cloud infrastructure, the applications must be reduced to frameworks that can successfully exploit the cloud resources, like the MapReduce framework. This paper summarizes the challenges associated with reducing iterative algorithms to the MapReduce model. Algorithms used by scientific computing are divided into different classes by how they can be adapted to the MapReduce model; examples from each such class are reduced to the MapReduce model and their performance is measured and analyzed. The study mainly focuses on the Hadoop MapReduce framework but also compares it to an alternative MapReduce framework called Twister, which is specifically designed for iterative algorithms. The analysis shows that Hadoop MapReduce has significant trouble with iterative problems while it suits well for embarrassingly parallel problems, and that Twister can handle iterative problems much more efficiently. This work shows how to adapt algorithms from each class into the MapReduce model, what affects the efficiency and scalability of algorithms in each class and allows us to judge which framework is more efficient for each of them, by mapping the advantages and disadvantages of the two frameworks. This study is of significant importance for scientific computing as it often uses complex iterative methods to solve critical problems and adapting such methods to cloud computing frameworks is not a trivial task.     

Accelerating big data analytics on HPC clusters using two-level storage

Data-intensive applications that are inherently I/O bound have become a major workload on traditional high-performance computing (HPC) clusters. Simply employing data-intensive computing storage such as HDFS or using parallel file systems available on HPC clusters to serve such applications incurs performance and scalability issues. In this paper, we present a novel two-level storage system that integrates an upper-level in-memory file system with a lower-level parallel file system. The former renders memory-speed high I/O performance and the latter renders consistent storage with large capacity. We build a two-level storage system prototype with Tachyon and OrangeFS, and analyze the resulting I/O throughput for typical MapReduce operations. Theoretical modeling and experiments show that the proposed two-level storage delivers higher aggregate I/O throughput than HDFS and OrangeFS and achieves scalable performance for both read and write. We expect this two-level storage approach to provide insights on system design for big data analytics on HPC clusters.     

能耗感知的绿色数据库研究综述

随着全球的低碳化趋势以及以数据为中心的计算趋势,研究节能的绿色数据库系统已成为政府、企业和学术界共同关注的问题。然而,已有的数据库系统与算法大都针对性能目标而设计,缺乏对能耗的感知与处理,包括能耗有效性以及能耗同比性等问题的考虑。围绕绿色数据库系统的发展需求,对绿色数据库技术中的关键问题进行了讨论,重点阐述了数据库系统能耗有效性,以及面向数据库节点集群的能耗同比性等问题。在此基础上,给出了能耗感知的绿色数据库技术的未来发展方向,为该方向的进一步深入研究提供新的参考。     

DBCURE-MR: An efficient density-based clustering algorithm for large data using MapReduce

Clustering is a useful data mining technique which groups data points such that the points within a single group have similar characteristics, while the points in different groups are dissimilar. Density-based clustering algorithms such as DBSCAN and OPTICS are one kind of widely used clustering algorithms. As there is an increasing trend of applications to deal with vast amounts of data, clustering such big data is a challenging problem. Recently, parallelizing clustering algorithms on a large cluster of commodity machines using the MapReduce framework have received a lot of attention.In this paper, we first propose the new density-based clustering algorithm, called DBCURE, which is robust to find clusters with varying densities and suitable for parallelizing the algorithm with MapReduce. We next develop DBCURE-MR, which is a parallelized DBCURE using MapReduce. While traditional density-based algorithms find each cluster one by one, our DBCURE-MR finds several clusters together in parallel. We prove that both DBCURE and DBCURE-MR find the clusters correctly based on the definition of density-based clusters. Our experimental results with various data sets confirm that DBCURE-MR finds clusters efficiently without being sensitive to the clusters with varying densities and scales up well with the MapReduce framework.     

Dynamic energy efficient data placement and cluster reconfiguration algorithm for MapReduce framework

With the recent emergence of cloud computing based services on the Internet, MapReduce and distributed file systems like HDFS have emerged as the paradigm of choice for developing large scale data intensive applications. Given the scale at which these applications are deployed, minimizing power consumption of these clusters can significantly cut down operational costs and reduce their carbon footprint—thereby increasing the utility from a provider’s point of view. This paper addresses energy conservation for clusters of nodes that run MapReduce jobs. The algorithm dynamically reconfigures the cluster based on the current workload and turns cluster nodes on or off when the average cluster utilization rises above or falls below administrator specified thresholds, respectively. We evaluate our algorithm using the GridSim toolkit and our results show that the proposed algorithm achieves an energy reduction of 33% under average workloads and up to 54% under low workloads.     

Context‐aware scheduling in MapReduce: a compact review

It is a fact that the attention of research community in computer science, business executives, and decision makers is drastically drawn by big data. As the volume of data becomes bigger, it needs performance‐oriented data‐intensive processing frameworks such as MapReduce, which can scale computation on large commodity clusters. Hadoop MapReduce processes data in Hadoop Distributed File System as jobs scheduled according to YARN fair scheduler and capacity scheduler. However, with advancement and dynamic changes in hardware and operating environments, the performance of clusters is greatly affected. Various efforts in literature have been made to address the issues of heterogeneity (i.e., clusters consisting of virtual machines and machines with different hardware), network communication, data locality, better resource utilization, and run‐time scheduling. In this paper, we present a survey to discuss various research efforts made so far to improve Hadoop MapReduce scheduling. We classify scheduling algorithms and techniques proposed in the literature so far based on their addressing areas and present a taxonomy. Furthermore, we also discuss various aspects of open issues and challenges in the scheduling of MapReduce to improve its performance. Copyright © 2015 John Wiley & Sons, Ltd.     

CloudFlow: A data-aware programming model for cloud workflow applications on modern HPC systems

Traditional High-Performance Computing (HPC) based big-data applications are usually constrained by having to move large amount of data to compute facilities for real-time processing purpose. Modern HPC systems, represented by High-Throughput Computing (HTC) and Many-Task Computing (MTC) platforms, on the other hand, intend to achieve the long-held dream of moving compute to data instead. This kind of data-aware scheduling, typically represented by Hadoop MapReduce, has been successfully implemented in its Map Phase, whereby each Map Task is sent out to the compute node where the corresponding input data chunk is located. However, Hadoop MapReduce limits itself to a one-map-to-one-reduce framework, leading to difficulties for handling complex logics, such as pipelines or workflows. Meanwhile, it lacks built-in support and optimization when the input datasets are shared among multiple applications and/or jobs. The performance can be improved significantly when the knowledge of the shared and frequently accessed data is taken into scheduling decisions.To enhance the capability of managing workflow in modern HPC system, this paper presents CloudFlow, a Hadoop MapReduce based programming model for cloud workflow applications. CloudFlow is built on top of MapReduce, which is proposed not only being data aware, but also shared-data aware. It identifies the most frequently shared data, from both task-level and job-level, replicates them to each compute node for data locality purposes. It also supports user-defined multiple Map- and Reduce functions, allowing users to orchestrate the required data-flow logic. Mathematically, we prove the correctness of the whole scheduling framework by performing theoretical analysis. Further more, experimental evaluation also shows that the execution runtime speedup exceeds 4X compared to traditional MapReduce implementation with a manageable time overhead.     

Scheduling algorithm based on prefetching in MapReduce clusters

Due to cluster resource competition and task scheduling policy, some map tasks are assigned to nodes without input data, which causes significant data access delay. Data locality is becoming one of the most critical factors to affect performance of MapReduce clusters. As machines in MapReduce clusters have large memory capacities, which are often underutilized, in-memory prefetching input data is an effective way to improve data locality. However, it is still posing serious challenges to cluster designers on what and when to prefetch. To effectively use prefetching, we have built HPSO (High Performance Scheduling Optimizer), a prefetching service based task scheduler to improve data locality for MapReduce jobs. The basic idea is to predict the most appropriate nodes for future map tasks based on current pending tasks and then preload the needed data to memory without any delaying on launching new tasks. To this end, we have implemented HPSO in Hadoop-1.1.2. The experiment results have shown that the method can reduce the map tasks causing remote data delay, and improves the performance of Hadoop clusters.     

SHadoop: Improving MapReduce performance by optimizing job execution mechanism in Hadoop clusters

As a widely-used parallel computing framework for big data processing today, the Hadoop MapReduce framework puts more emphasis on high-throughput of data than on low-latency of job execution. However, today more and more big data applications developed with MapReduce require quick response time. As a result, improving the performance of MapReduce jobs, especially for short jobs, is of great significance in practice and has attracted more and more attentions from both academia and industry. A lot of efforts have been made to improve the performance of Hadoop from job scheduling or job parameter optimization level. In this paper, we explore an approach to improve the performance of the Hadoop MapReduce framework by optimizing the job and task execution mechanism. First of all, by analyzing the job and task execution mechanism in MapReduce framework we reveal two critical limitations to job execution performance. Then we propose two major optimizations to the MapReduce job and task execution mechanisms: first, we optimize the setup and cleanup tasks of a MapReduce job to reduce the time cost during the initialization and termination stages of the job; second, instead of adopting the loose heartbeat-based communication mechanism to transmit all messages between the JobTracker and TaskTrackers, we introduce an instant messaging communication mechanism for accelerating performance-sensitive task scheduling and execution. Finally, we implement SHadoop, an optimized and fully compatible version of Hadoop that aims at shortening the execution time cost of MapReduce jobs, especially for short jobs. Experimental results show that compared to the standard Hadoop, SHadoop can achieve stable performance improvement by around 25% on average for comprehensive benchmarks without losing scalability and speedup. Our optimization work has passed a production-level test in Intel and has been integrated into the Intel Distributed Hadoop (IDH). To the best of our knowledge, this work is the first effort that explores on optimizing the execution mechanism inside map/reduce tasks of a job. The advantage is that it can complement job scheduling optimizations to further improve the job execution performance.     

Effectiveness Analysis of DVFS and DPM in Mobile Devices

The demand for high-performance embedded processors in multimedia mobile electronics is growing and their power consumption thus increasingly threatens battery lifetime.It is usually believed that the dynamic voltage and frequency scaling (DVFS) feature saves significant energy by changing the performance levels of processors to match the performance demands of applications on the fly.However,because the energy efficiency of embedded processors is rapidly improving,the effectiveness of DVFS is expected to change.In this paper,we analyze the benefit of DVFS in state-of-the-art mobile embedded platforms in comparison to those in servers or PCs.To obtain a clearer view of the relationship between power and performance,we develop a measurement methodology that can synchronize time series for power consumption with those for processor utilization.The results show that DVFS hardly improves the energy efficiency of mobile multimedia electronics,and can even significantly worsen energy efficiency and performance in some cases.According to this observation,we suggest that power management for mobile electronics should concentrate on adaptive and intelligent power management for peripheral devices.As a preliminary design,we implement an adaptive network interface card (NIC) speed control that reduces power consumption by 10% when NIC is not heavily used.Our results provide valuable insights into the design of power management schemes for future mobile embedded systems.