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...     

Handling data skew in join algorithms using MapReduce

One of the major obstacles hindering effective join processing on MapReduce is data skew. Since MapReduce’s basic hash-based partitioning method cannot solve the problem properly, two alternatives have been proposed: range-based and randomized methods. However, they still remain some drawbacks: the range-based method does not handle join product skew, and the randomized method performs worse than the basic hash-based partitioning when input relations are not skewed. In this paper, we present a new skew handling method, called multi-dimensional range partitioning (MDRP). The proposed method overcomes the limitations of traditional algorithms in two ways: 1) the number of output records expected at each machine is considered, which leads to better handling of join product skew, and 2) a small number of input records are sampled before the actual join begins so that an efficient execution plan considering the degree of data skew can be created. As a result, in a scalar skew experiment, the proposed join algorithm is about 6.76 times faster than the range-based algorithm when join product skew exists and about 5.14 times than the randomized algorithm when input relations are not skewed. Moreover, through the worst-case analysis, we show that the input and the output imbalances are less than or equal to 2. The proposed algorithm does not require any modification to the original MapReduce environment and is applicable to complex join operations such as theta-joins and multi-way joins.     

An improved partitioning mechanism for optimizing massive data analysis using MapReduce

In the era of Big Data, huge amounts of structured and unstructured data are being produced daily by a myriad of ubiquitous sources. Big Data is difficult to work with and requires massively parallel software running on a large number of computers. MapReduce is a recent programming model that simplifies writing distributed applications that handle Big Data. In order for MapReduce to work, it has to divide the workload among computers in a network. Consequently, the performance of MapReduce strongly depends on how evenly it distributes this workload. This can be a challenge, especially in the advent of data skew. In MapReduce, workload distribution depends on the algorithm that partitions the data. One way to avoid problems inherent from data skew is to use data sampling. How evenly the partitioner distributes the data depends on how large and representative the sample is and on how well the samples are analyzed by the partitioning mechanism. This paper proposes an improved partitioning algorithm that improves load balancing and memory consumption. This is done via an improved sampling algorithm and partitioner. To evaluate the proposed algorithm, its performance was compared against a state of the art partitioning mechanism employed by TeraSort. Experiments show that the proposed algorithm is faster, more memory efficient, and more accurate than the current implementation.     

基于MapReduce的数据立方体分区优化算法研究

文章利用并行计算框架MapReduce,探索数据立方体的计算问题。数据立方体的计算存在两个关键问题,一个是计算时间的问题,另一个是立方体的体积问题。随着维度的增加,计算时间将呈现指数级的增长,立方体的体积也是如此。尽管MapReduce是一个优秀的并行计算框架,但在处理数据倾斜时,分区算法不够完善,导致一些计算任务时间过长,影响整个作业的完成时间。本文通过数据采样的方式,优化数据分区,实验结果表明,数据立方体的计算的性能明显提升。为解决数据立方体体积过大的问题,在Reduce阶段将最终的结果输出到基于NoSQL的HBase数据库进行存储,HBase方便水平扩展,同时也便于日后对数据立方体的查询。     

Configuration Reusing in On-Line Task Scheduling for Reconfigurable Computing Systems

Reconfigurable computing systems can be reconfigured at runtime and support partial reconfigurability which makes us able to execute tasks in a true multitasking manner.To manage such systems at runtime,a reconfigurable operating system is needed.The main part of this operating system is resource management unit which performs on-line scheduling and placement of hardware tasks at runtime.Reconfiguration overhead is an important obstacle that limits the performance of on-line scheduling algorithms in reconfigurable computing systems and increases the overall execution time.Configuration reusing (task reusing) can decrease reconfiguration overhead considerably,particularly in periodic applications or the applications in which the probability of tasks recurrence is high.In this paper,we present a technique called reusing-based scheduling (RBS),for on-line scheduling and placement in which configuration reusing is considered as a main characteristic in order to reduce reconfiguration overhead and decrease total execution time of the tasks.Several experiments have been conducted on the proposed algorithm.Obtained results show considerable improvement in overall execution time of the tasks.     

Density-based data partitioning strategy to approximate large-scale subgraph mining

Recently, graph mining approaches have become very popular, especially in certain domains such as bioinformatics, chemoinformatics and social networks. One of the most challenging tasks is frequent subgraph discovery. This task has been highly motivated by the tremendously increasing size of existing graph databases. Due to this fact, there is an urgent need of efficient and scaling approaches for frequent subgraph discovery. In this paper, we propose a novel approach for large-scale subgraph mining by means of a density-based partitioning technique, using the MapReduce framework. Our partitioning aims to balance computational load on a collection of machines. We experimentally show that our approach decreases significantly the execution time and scales the subgraph discovery process to large graph databases.     

Co-manipulation with a library of virtual guiding fixtures

Virtual guiding fixtures constrain the movements of a robot to task-relevant trajectories, and have been successfully applied to, for instance, surgical and manufacturing tasks. Whereas previous work has considered guiding fixtures for single tasks, in this paper we propose a library of guiding fixtures for multiple tasks, and propose methods for (1) creating and adding guides based on machine learning; (2) selecting guides on-line based on probabilistic implementation of guiding fixtures; (3) refining existing guides based on an incremental learning method. We demonstrate in an industrial task that a library of guiding fixtures provides an intuitive haptic interface for joint human–robot completion of tasks, and improves performance in terms of task execution time, mental workload and errors.     

Improving MapReduce Performance with Partial Speculative Execution

The MapReduce framework has become the de facto standard for big data processing due to its attractive features and abilities. One is that it automatically parallelizes a job into multiple tasks and transparently handles task execution on a large cluster of commodity machines. The increasing heterogeneity of distributed environments may result in a few straggling tasks, which prolong job completion. Speculative execution is proposed to mitigate stragglers. However, the existing speculative execution mechanism could not work efficiently as many speculative tasks are still slower than their original tasks. In this paper, we explore an approach to increase the efficiency of speculative execution, and further improve MapReduce performance. We propose the Partial Speculative Execution (PSE) strategy to make speculative tasks start from the checkpoint. By leveraging the checkpoint of original tasks, PSE can eliminate the costs of re-reading, re-copying, and re-computing the processed data. We implement PSE in Hadoop, and evaluate its performance in terms of job completion time and the efficiency of speculative execution under several kinds of classical workloads. Experimental results show that, in heterogeneous environments with stragglers, PSE completes jobs 56 % faster than that with no speculation and 12 % faster than that with LATE, an improved speculative execution algorithm. In addition, on average PSE can improve the efficiency of speculative execution by 24 % compared to LATE.     

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.     

SLA-aware energy-efficient scheduling scheme for Hadoop YARN

Apache Hadoop becomes ubiquitous for cloud computing which provides resources as services for multi-tenant applications. YARN (a.k.a. MapReduce 2.0) is one of the key features in the second-generation Hadoop, which provides resource management and scheduling for large-scale MapReduce environments. Two enormous challenges in the YARN scheduler are the abilities to automatically tailor and control resource allocations to different jobs for achieving their Service Level Agreements (SLAs), and minimize energy consumption of the overall cloud computing system. In this work, we propose an SLA-aware energy-efficient scheduling scheme which allocates appropriate amount of resources to MapReduce applications with YARN architecture. In our task scheduling policy, We consider the data locality information to save the MapReduce network traffic. Furthermore, the slack time between the actual execution time of completed tasks and expected completion time of the application is utilized to improve the energy-efficiency of the system. An online userspace governor-based dynamic voltage and frequency scaling (DVFS) scheme is designed in the YARN per-application ApplicationMaster to dynamically change the CPU frequency for upcoming tasks given the slack time from previous completed tasks. Experimental evaluation shows that our proposed scheme outperforms the existing MapReduce scheduling policies in terms of both resource ultization and energy-efficiency.     

基于索引偏移的MapReduce聚类负载均衡策略

MapReduce作为一种分布式编程模型,被广泛应用于大规模和高维度数据集的处理中。其采用原始Hash函数 划分 数据,当数据分布不均匀时,常会出现数据倾斜的问题。基于MapReduce的聚类算法,需要多次迭代且不清楚各阶段Reduce的输入数据分布,因此现有的解决数据倾斜的方法并不适用。为解决数据划分的不均衡问题,提出一种当存在数据倾斜时更改剩余分区索引的策略。该方法在Map运行的过程中统计将要分给各reducer的数据量,由JobTrackcr监控全局的分区信息并根据数据倾斜模型动态修改原分区函数;在接下来的分区过程中,Partitioner把即将导致倾斜的分区索引到其余负载较轻的reducer上,使各节点的负载达到均衡。基于Zipf分布数据集和真实数据集,将所提算法与现有的解决数据倾斜的方法进行对比,结果证明,所提策略解决了MapReduce聚类中的数据倾斜问题,且在稳定性与执行时间上优于Hash和基于采样的动态分区法。     

On the need for attention-aware systems: Measuring effects of interruption on task performance,error rate,and affective state

This paper reports results from a controlled experiment (N = 50) measuring effects of interruption on task completion time, error rate, annoyance, and anxiety. The experiment used a sample of primary and peripheral tasks representative of those often performed by users. Our experiment differs from prior interruption experiments because it measures effects of interrupting a user’s tasks along both performance and affective dimensions and controls for task workload by manipulating only the time at which peripheral tasks were displayed – between vs. during the execution of primary tasks. Results show that when peripheral tasks interrupt the execution of primary tasks, users require from 3% to 27% more time to complete the tasks, commit twice the number of errors across tasks, experience from 31% to 106% more annoyance, and experience twice the increase in anxiety than when those same peripheral tasks are presented at the boundary between primary tasks. An important implication of our work is that attention-aware systems could mitigate effects of interruption by deferring presentation of peripheral information until coarse boundaries are reached during task execution. As our results show, deferring presentation for a short time, i.e. just a few seconds, can lead to a large mitigation of disruption.     

Reducing partition skew on MapReduce: an incremental allocation approach

MapReduce, a parallel computational model, has been widely used in processing big data in a distributed cluster. Consisting of alternate map and reduce phases, MapReduce has to shuffle the intermediate data generated by mappers to reducers. The key challenge of ensuring balanced workload on MapReduce is to reduce partition skew among reducers without detailed distribution information on mapped data. In this paper, we propose an incremental data allocation approach to reduce partition skew among reducers on MapReduce. The proposed approach divides mapped data into many micro-partitions and gradually gathers the statistics on their sizes in the process of mapping. The micropartitions are then incrementally allocated to reducers in multiple rounds. We propose to execute incremental allocation in two steps, micro-partition scheduling and micro-partition allocation. We propose a Markov decision process (MDP) model to optimize the problem of multiple-round micropartition scheduling for allocation commitment. We present an optimal solution with the time complexity of O(K · N²), in which K represents the number of allocation rounds and N represents the number of micro-partitions. Alternatively, we also present a greedy but more efficient algorithm with the time complexity of O(K · N ln N). Then, we propose a minmax programming model to handle the allocation mapping between micro-partitions and reducers, and present an effective heuristic solution due to its NP-completeness. Finally, we have implemented the proposed approach on Hadoop, an open-source MapReduce platform, and empirically evaluated its performance. Our extensive experiments show that compared with the state-of-the-art approaches, the proposed approach achieves considerably better data load balance among reducers as well as overall better parallel performance.     

Handling partitioning skew in MapReduce using LEEN

MapReduce is emerging as a prominent tool for big data processing. Data locality is a key feature in MapReduce that is extensively leveraged in data-intensive cloud systems: it avoids network saturation when processing large amounts of data by co-allocating computation and data storage, particularly for the map phase. However, our studies with Hadoop, a widely used MapReduce implementation, demonstrate that the presence of partitioning skew (Partitioning skew refers to the case when a variation in either the intermediate keys’ frequencies or their distributions or both among different data nodes) causes a huge amount of data transfer during the shuffle phase and leads to significant unfairness on the reduce input among different data nodes. As a result, the applications severe performance degradation due to the long data transfer during the shuffle phase along with the computation skew, particularly in reduce phase. In this paper, we develop a novel algorithm named LEEN for locality-aware and fairness-aware key partitioning in MapReduce. LEEN embraces an asynchronous map and reduce scheme. All buffered intermediate keys are partitioned according to their frequencies and the fairness of the expected data distribution after the shuffle phase. We have integrated LEEN into Hadoop. Our experiments demonstrate that LEEN can efficiently achieve higher locality and reduce the amount of shuffled data. More importantly, LEEN guarantees fair distribution of the reduce inputs. As a result, LEEN achieves a performance improvement of up to 45 % on different workloads.     

Hybrid CPU–GPU execution support in the skeleton programming framework SkePU

In this paper, we present a hybrid execution backend for the skeleton programming framework SkePU. The backend is capable of automatically dividing the workload and simultaneously executing the computation on a multi-core CPU and any number of accelerators, such as GPUs. We show how to efficiently partition the workload of skeletons such as Map, MapReduce, and Scan to allow hybrid execution on heterogeneous computer systems. We also show a unified way of predicting how the workload should be partitioned based on performance modeling. With experiments on typical skeleton instances, we show the speedup for all skeletons when using the new hybrid backend. We also evaluate the performance on some real-world applications. Finally, we show that the new implementation gives higher and more reliable performance compared to an old hybrid execution implementation based on dynamic scheduling.

     

基于两阶分区的MapReduce实验室系统负载均衡研究

在实验室系统处理海量原始数据时,实际应用场景中存在采样率高、偏度（skewness）高的特殊情况,导致在使用两阶分区算法在平衡同构环境下的Reducer节点负载时,无法有效地处理这些问题。为此,引入MapReduce的并行化处理,可以提高实验室系统中采样数据利用率;同时,为了解决数据偏度和采样度高的问题,则采用了ICSC（Improved Cluster Split Combination）分区调度的算法。经过实验证明,基于两阶分区的MapReduce负载均衡算法能够有效减少Mapper和Reducer节点空转的时间。随着数据偏度的增加,算法的执行时长基本不产生变化,即数据偏度对该算法执行时间的影响较小。此外,数据采样度的增加,ICSC分区调度算法也保持着对比模型中最少的时间开销。因此,基于两阶分区的MapReduce负载均衡算法弱化了Reducer节点间的依赖性,并提升MapReduce任务的执行效率和容错率,从而高效地实现MapReduce框架下的实验室系统中数据处理的负载均衡。     

基于MapReduce的数据倾斜连接算法

连接操作是大规模数据集在数据分析应用中最常用的操作,针对MapReduce自身不能有效地处理数据倾斜情况下的连接操作,提出了基于MapReduce的频次分类连接算法。根据数据在连接数据集中出现的频率将整个数据集分为3类,对倾斜数据利用分区算法和广播算法实现数据重分布,以消除数据倾斜的影响;对非倾斜数据采用Hash算法实现数据重分布。重分布后的数据在单节点内即可完成数据连接操作,避免了MapReduce框架下连接操作的跨节点传输代价;同时有效地均衡了MapReduce各节点的任务负载,从而提高了数据倾斜状态下连接操作的效率。通过与传统连接算法的对比,证明了所提算法的有效性和实用性。     

Tails in the cloud: a survey and taxonomy of straggler management within large-scale cloud data centres

Cloud computing systems are splitting compute- and data-intensive jobs into smaller tasks to execute them in a parallel manner using clusters to improve execution time. However, such systems at increasing scale are exposed to stragglers, whereby abnormally slow running tasks executing within a job substantially affect job performance completion. Such stragglers are a direct threat towards attaining fast execution of data-intensive jobs within cloud computing. Researchers have proposed an assortment of different mechanisms, frameworks, and management techniques to detect and mitigate stragglers both proactively and reactively. In this paper, we present a comprehensive review of straggler management techniques within large-scale cloud data centres. We provide a detailed taxonomy of straggler causes, as well as proposed management and mitigation techniques based on straggler characteristics and properties. From this systematic review, we outline several outstanding challenges and potential directions of possible future work for straggler research.

     

Modeling task completion time of in-vehicle information systems while driving with keystroke level modeling

The use of touchscreen-based in-vehicle information systems (IVIS) is increasing. To ensure safe driving, it is important to evaluate IVIS task performance during driving situations. Therefore, we proposed a model to assess the task completion time (TCT) of IVIS tasks while driving using a keystroke-level modeling (KLM) technique. The basic assumptions and heuristic rules of driver behaviors were considered. In addition, based on the characteristics of visual and manual IVIS interactions, we determined the basic unit operators (i.e., visual, manual, and mental operators). User experiments were conducted to determine the individual execution times of unit tasks and to measure the TCT of IVIS tasks while driving. Based on the heuristic rules for model development and individual task execution times, we derive a predictive model for the TCT of IVIS tasks. We used a regression analysis to validate the modeling procedure, showing that the observed TCT was found to have a strong positive correlation with the predicted time from the modeling process. The findings showed that the task completion time needed to perform a secondary task in a driving context can be predicted by KLM. This study provides meaningful insights into the design of touchscreen-based IVIS to enhance driving safety.     

MapReduce:新型的分布式并行计算编程模型

MapReduce是Google提出的分布式并行计算编程模型,用于大规模数据的并行处理。Ma-pReduce模型受函数式编程语言的启发,将大规模数据处理作业拆分成若干个可独立运行的Map任务,分配到不同的机器上去执行,生成某种格式的中间文件,再由若干个Reduce任务合并这些中间文件获得最后的输出文件。用户在使用MapReduce模型进行大规模数据处理时,可以将主要精力放在如何编写Map和Reduce函数上,其它并行计算中的复杂问题诸如分布式文件系统、工作调度、容错、机器间通信等都交给MapReduce系统处理,在很大程度上降低了整个编程难度。MapReduce日益成为云计算平台的主流编程模型。Apache Hadoop项目提供开源的MapReduce系统还有待进一步完善。