Scientists today have the ability to generate data at an unprecedented scale and rate and, as a result, they must increasingly turn to parallel data processing engines to perform their analyses. However, the simple execution model of these engines can make it difficult to implement efficient algorithms for scientific analytics. In particular, many scientific analytics require the extraction of features from data represented as either a multidimensional array or points in a multidimensional space. These applications exhibit significant computational skew, where the runtime of different partitions depends on more than just input size and can therefore vary dramatically and unpredictably. In this paper, we present SkewReduce, a new system implemented on top of Hadoop that enables users to easily express feature extraction analyses and execute them efficiently. At the heart of the SkewReduce system is an optimizer, parameterized by user-defined cost functions, that determines how best to partition the input data to minimize computational skew. Experiments on real data from two different science domains demonstrate that our approach can improve execution times by a factor of up to 8 compared to a naive implementation.

Abstract — The effectiveness and scalability of MapReducebased implementations of complex data-intensive tasks depend on an even redistribution of data between map and reduce tasks. In the presence of skewed data, sophisticated redistribution approaches thus become necessary to achieve load balancing among all reduce tasks to be executed in parallel. For the complex problem of entity resolution, we propose and evaluate two approaches for such skew handling and load balancing. The approaches support blocking techniques to reduce the search space of entity resolution, utilize a preprocessing MapReduce job to analyze the data distribution, and distribute the entities of large blocks among multiple reduce tasks. The evaluation on a real cloud infrastructure shows the value and effectiveness of the proposed load balancing approaches. I.

Abstract—This paper presents a study of skew — highly variable task runtimes — in MapReduce applications. We describe various causes and manifestations of skew as observed in real world Hadoop applications. Runtime task distributions from these applications demonstrate the presence and negative impact of skew on performance behavior. We discuss best practices recommended for avoiding such behavior and their limitations. I.

In this paper, we study efficient ways to construct, represent and analyze large-scale archival web graphs. We first discuss details of the distributed graph construction algorithm implemented in MapReduce and the design of a space-efficient layered graph representation. While designing this representation, we consider both offline and online algorithms for the graph analysis. The offline algorithms, such as PageRank, can use MapReduce and similar largescale, distributed frameworks for computation. On the other side, online algorithms can be implemented by tapping into a scalable repository (similar to DEC’s Connectivity Server or Scalable Hyperlink Store by Najork), in order to perform the computations. Moreover, we also consider updating the graph representation with the most recent information available and propose an efficient way to perform updates using MapReduce. We survey various storage options and outline essential API calls for the archival web graph specific real-time access repository. Finally, we conclude with a discussion of ideas for interesting archival web graph analysis that can lead us to discover novel patterns for designing state-of-art compression techniques.

We present an automatic skew mitigation approach for userdefined MapReduce programs and present SkewTune, a system that implements this approach as a drop-in replacement for an existing MapReduce implementation. There are three key challenges: (a) require no extra input from the user yet work for all MapReduce applications, (b) be completely transparent, and (c) impose minimal overhead if there is no skew. The SkewTune approach addresses these challenges and works as follows: When a node in the cluster becomes idle, SkewTune identifies the task with the greatest expected remaining processing time. The unprocessed input data of this straggling task is then proactively repartitioned in a way that fully utilizes the nodes in the cluster and preserves the ordering of the input data so that the original output can be reconstructed by concatenation. We implement SkewTune as an extension to Hadoop and evaluate its effectiveness using several real applications. The results show that Skew-Tune can significantly reduce job runtime in the presence of skew and adds little to no overhead in the absence of skew.

We demonstrate SkewTune, a system that automatically mitigates skew in user-defined MapReduce programs and is a drop-in replacement for Hadoop. The demonstration has two parts. First, we demonstrate how SkewTune mitigates skew in real MapReduce applications at runtime by running a real application in a public cloud. Second, through an interactive graphical interface, we demonstrate the details of the skew mitigation process using both real and synthetic workloads that represent various skew configurations.

(will be inserted by the editor)