journal article
LitStream Collection
Home
Yu, Li; Moretti, Christopher; Thrasher, Andrew; Emrich, Scott; Judd, Kenneth; Thain, Douglas
doi: 10.1007/s10586-010-0134-7pmid: N/A
Both distributed systems and multicore systems are difficult programming environments. Although the expert programmer may be able to carefully tune these systems to achieve high performance, the non-expert may struggle. We argue that high level abstractions are an effective way of making parallel computing accessible to the non-expert. An abstraction is a regularly structured framework into which a user may plug in simple sequential programs to create very large parallel programs. By virtue of a regular structure and declarative specification, abstractions may be materialized on distributed, multicore, and distributed multicore systems with robust performance across a wide range of problem sizes. In previous work, we presented the All-Pairs abstraction for computing on distributed systems of single CPUs. In this paper, we extend All-Pairs to multicore systems, and introduce the Wavefront and Makeflow abstractions, which represent a number of problems in economics and bioinformatics. We demonstrate good scaling of both abstractions up to 32 cores on one machine and hundreds of cores in a distributed system.
Asiki, Athanasia; Tsoumakos, Dimitrios; Koziris, Nectarios
doi: 10.1007/s10586-010-0136-5pmid: N/A
Concept hierarchies greatly help in the organization and reuse of information and are widely used in a variety of information systems applications. In this paper, we describe a method for efficiently storing and querying data organized into concept hierarchies and dispersed over a DHT. In our method, peers individually decide on the level of indexing according to the granularity of the incoming queries. Roll-up and drill-down operations are performed on a per-node basis in order to minimize the required bandwidth for answering queries on variable aggregation levels. We motivate our approach by applying it on a large-scale Grid system: Specifically, we apply our fully decentralized scheme that creates, queries and updates large volumes of hierarchical data on-line and replace the traditional centralized and strictly indexed information systems. Our extensive experimental results support this argument on many diverse configurations: Our system proves very efficient in skewed workloads, both over single and multiple hierarchy levels at the same time. It adapts to sudden changes in popularity and effectively stores and updates large amounts of data at very low cost.
Abbasi, Hasan; Wolf, Matthew; Eisenhauer, Greg; Klasky, Scott; Schwan, Karsten; Zheng, Fang
doi: 10.1007/s10586-010-0135-6pmid: N/A
Known challenges for petascale machines are that (1) the costs of I/O for high performance applications can be substantial, especially for output tasks like checkpointing, and (2) noise from I/O actions can inject undesirable delays into the runtimes of such codes on individual compute nodes. This paper introduces the flexible ‘DataStager’ framework for data staging and alternative services within that jointly address (1) and (2). Data staging services moving output data from compute nodes to staging or I/O nodes prior to storage are used to reduce I/O overheads on applications’ total processing times, and explicit management of data staging offers reduced perturbation when extracting output data from a petascale machine’s compute partition. Experimental evaluations of DataStager on the Cray XT machine at Oak Ridge National Laboratory establish both the necessity of intelligent data staging and the high performance of our approach, using the GTC fusion modeling code and benchmarks running on 1000+ processors.
Assunção, Marcos; Costanzo, Alexandre; Buyya, Rajkumar
doi: 10.1007/s10586-010-0131-xpmid: N/A
In this paper, we investigate the benefits that organisations can reap by using “Cloud Computing” providers to augment the computing capacity of their local infrastructure. We evaluate the cost of seven scheduling strategies used by an organisation that operates a cluster managed by virtual machine technology and seeks to utilise resources from a remote Infrastructure as a Service (IaaS) provider to reduce the response time of its user requests. Requests for virtual machines are submitted to the organisation’s cluster, but additional virtual machines are instantiated in the remote provider and added to the local cluster when there are insufficient resources to serve the users’ requests. Naïve scheduling strategies can have a great impact on the amount paid by the organisation for using the remote resources, potentially increasing the overall cost with the use of IaaS. Therefore, in this work we investigate seven scheduling strategies that consider the use of resources from the “Cloud”, to understand how these strategies achieve a balance between performance and usage cost, and how much they improve the requests’ response times.
Showing 1 to 7 of 7 Articles
Many-task computing aims to bridge the gap between two computing paradigms, high throughput computing and high performance computing. Many-task computing denotes high-performance computations comprising multiple distinct activities, coupled via file system operations. The aggregate number of tasks, quantity of computing, and volumes of data may be extremely large. Traditional techniques found in production systems in the scientific community to support many-task computing do not scale to today’s largest systems, due to issues in local resource manager scalability and granularity, efficient utilization of the raw hardware, long wait queue times, and shared/parallel file system contention and scalability. To address these limitations, we adopted a “top-down” approach to building a middleware called Falkon, to support the most demanding many-task computing applications at the largest scales. Falkon (Fast and Light-weight tasK executiON framework) integrates (1) multi-level scheduling to enable dynamic resource provisioning and minimize wait queue times, (2) a streamlined task dispatcher able to achieve orders-of-magnitude higher task dispatch rates than conventional schedulers, and (3) data diffusion which performs data caching and uses a data-aware scheduler to co-locate computational and storage resources. Micro-benchmarks have shown Falkon to achieve over 15K+ tasks/s throughputs, scale to hundreds of thousands of processors and to millions of queued tasks, and execute billions of tasks per day. Data diffusion has also shown to improve applications scalability and performance, with its ability to achieve hundreds of Gb/s I/O rates on modest sized clusters, with Tb/s I/O rates on the horizon. Falkon has shown orders of magnitude improvements in performance and scalability than traditional approaches to resource management across many diverse workloads and applications at scales of billions of tasks on hundreds of thousands of processors across clusters, specialized systems, Grids, and supercomputers. Falkon’s performance and scalability have enabled a new class of applications called Many-Task Computing to operate at previously so-believed impossible scales with high efficiency.
Data analysis processes in scientific applications can be expressed as coarse-grain workflows of complex data processing operations with data flow dependencies between them. Performance optimization of these workflows can be viewed as a search for a set of optimal values in a multidimensional parameter space consisting of input performance parameters to the applications that are known to affect their execution times. While some performance parameters such as grouping of workflow components and their mapping to machines do not affect the accuracy of the analysis, others may dictate trading the output quality of individual components (and of the whole workflow) for performance. This paper describes an integrated framework which is capable of supporting performance optimizations along multiple such parameters. Using two real-world applications in the spatial, multidimensional data analysis domain, we present an experimental evaluation of the proposed framework.