On the impact of process replication on executions of large-scale parallel applications with coordinated checkpointing

A return on investment analysis of applying health monitoring to LED lighting systems

Dynamic loop scheduling (DLS) algorithms provide application-level load balancing of loop iterates, with the goal of maximizing application performance on the underlying system. These methods use run-time information regarding the performance of the application's execution (for which irregularities change over time). Many DLS methods are based on probabilistic analyses, and therefore account for unpredictable variations of application and system related parameters. Scheduling scientific and engineering applications in large-scale distributed systems (possibly shared with other users) makes the problem of DLS even more challenging. Moreover, the chances of failure, such as processor or link failure, are high in such large-scale systems. In this paper, we employ the hierarchical approach for three DLS methods, and propose metrics for quantifying their robustness with respect to variations of two parameters (load and processor failures), for scheduling irregular applications in large-scale heterogeneous distributed systems.

Speedup models are powerful analytical tools for evaluating and predicting the performance of parallel applications. Unfortunately, the well-known speedup models like Amdahl’s law and Gustafson’s law do not take reliability into consideration and therefore cannot accurately account for application performance in the presence of failures. In this study, we enhance Amdahl’s law and Gustafson’s law by considering the impact of failures and the effect of coordinated checkpointing/restart. Unlike existing analytical studies relying on Exponential failure distribution alone, in this work we consider both Exponential and Weibull failure distributions in the construction of our reliability-aware speedup models. The derived reliability-aware models are validated through trace-based simulations under a variety of parameter settings. Our trace-based simulations demonstrate these models can effectively quantify failure impact on application speedup. Moreover, we present two case studies to illustrate the use of these reliability-aware speedup models.

Many mathematical models for the disease transmission dynamics of Ebola have been developed and studied, particularly during and after the 2014 outbreak in West Africa. Most of these models are systems of ordinary differential equations (ODEs). One of the common assumptions made in these ODE models is that the duration of disease stages, such as latent and infectious periods, follows an exponential distribution. Gamma distributions have also been used in some of these models. It has been demonstrated that, when the models are used to evaluate disease control strategies such as quarantine or isolation, the models with exponential and Gamma distribution assumptions may generate contradictory results (Feng et al. in Bull Math Biol 69(5):1511-1536, 2007). Several Ebola models are considered in this paper with various stage distributions, including exponential, Gamma and arbitrary distributions. These models are used to evaluate control strategies such as isolation (or hospitalization) and timely burial and to identify potential discrepancies between the results from models with exponential and Gamma distributions.

Exploring cosmology applications on distributed environments

Due to the demands on the engineering profession, all products and systems are expected to satisfy certain availability requirements. The availability is a measure of the readiness of a product or system for use at any specified time. In this work, the availability of single-component systems is addressed. Monte Carlo simulation is used to estimate the availability of the system, assuming that the failure and repair times follow exponential, normal (Gaussian), and uniform probability distributions. The results are compared. Although the availability functions look very different, the steady-state availability is the same for all. Also, the availability of a component whose hazard function follows the bathtub curve is estimated, and it is found that the exponential distribution is not a good approximation, especially at the earliest stages of operation.

This article revisits the optimization problems of age-based replacement models for exponential failure distributions. First, we show the steps how an age replacement time goes to an infinite value when the lifetime of a unit has an exponential distribution, and then, we give two discussions of possible replacement times, by introducing a new concept of cost named as deviation cost per unit of time between replacement and failure. Second, similar discussion is given for a random replacement model when the age replacement time is a random variable with a uniform distribution. Third, the models of age-based replacement first and last with deviation costs are discussed when a random replacement is taken into account for an age replacement model. Numerical examples are illustrated to show the results of the analytical discussions. Finally, necessary proofs are provided in the Appendixes.

This study mainly concerned with the K-capacity queueing system with recurrent input and two heterogeneous servers. Interarrival times are independent and have an arbitrary distribution. There are two servers and server k has an exponential distribution with parameter \(\mu _k\). Arriving customers choose server from the empty servers with equal probability. At an arrival time the customer joins the queue when both servers are busy. In addition an arrival leaves without having service when the system capacity is achieved. The defined system is represented by semi-Markov process and embedded Markov chain is obtained. Steady-state probabilities are found and loss probability is calculated by analyzing stream of overflows. Moreover loss probabilities are computed numerically for the queueing systems where the interarrival times are assumed as exponential, Erlang and deterministic distribution.

Monitoring and management of large scale applications is already a complex task because of syntactic and unstructured nature of execution data. Traditional application monitoring and management solutions focused on employing analysis techniques on unstructured and syntactic log information become limited as unstructured information cannot be well utilized to find out related events information or correlate such information with other related information from applications. Our proposed solution of semantically formalized logging fills this gap by bringing formal semantics and combining it in a meaningful way to enable automated monitoring and management of applications. Such formalized and well-structured log information helps analytical solution to maximally automate the process of monitoring and management of applications. However, while formalizing and structuring the log information, we came across several missing and incomplete data which causes hindrance in this process. In this paper, we tackle this problem and propose a social network analysis based solution to handle incomplete and missing data from application execution, possibly compute it and use it by our proposed solution of semantically formalizing and structured logs with adapted data mining techniques to enable automated and effective application monitoring and management. We demonstrate from an industrial use-case application that how historical data from application execution is stored using semantic logging and utilized with standard social-network analysis techniques to find out missing values in incomplete data and perform application monitoring and management.

This research paper deals with analysis on reliability of some complex systems using various distributions. The structural designs and configuration of different complex systems with various failure laws are analyzed. In this article, it is observed that reliability of a system can be improved by providing better configuration to components thereof. There are different types of configurations such as series, parallel, series- parallel, parallel- series, k-out-of-n and mixed configurations for a complex system, however, in this paper only two types of systems namely series system and parallel system are discussed with various failure distributions i.e. Weibull, Rayleigh and Exponential distribution. The results of the reliability for arbitrary values of parameters such as number of components, failure rates in three distributions have been obtained which may be very helpful in using various complex systems.

Operational reliability calculations for critical systems

Exploiting the computing power of the diversity of resources available on heterogeneous systems is mandatory but a very challenging task. The diversity of architectures, execution models and programming tools, together with disjoint address spaces and different computing capabilities, raise a number of challenges that severely impact on application performance and programming productivity. This problem is further compounded in the presence of data parallel irregular applications. This paper presents a framework that addresses development and execution of data parallel irregular applications in heterogeneous systems. A unified task-based programming and execution model is proposed, together with inter and intra-device scheduling, which, coupled with a data management system, aim to achieve performance scalability across multiple devices, while maintaining high programming productivity. Intra-device scheduling on wide SIMD/SIMT architectures resorts to consumer-producer kernels, which, by allowing dynamic generation and rescheduling of new work units, enable balancing irregular workloads and increase resource utilization. Results show that regular and irregular applications scale well with the number of devices, while requiring minimal programming effort. Consumer-producer kernels are able to sustain significant performance gains as long as the workload per basic work unit is enough to compensate overheads associated with intra-device scheduling. This not being the case, consumer kernels can still be used for the irregular application. Comparisons with an alternative framework, StarPU, which targets regular workloads, consistently demonstrate significant speedups. This is, to the best of our knowledge, the first published integrated approach that successfully handles irregular workloads over heterogeneous systems.

A major method of constructing applications to run on a computational Grid is to assemble them from components - separately deployable units of computation of well-defined functionality. Performance steering is an adaptive process involving run-time adjustment of factors affecting the performance of an application. This paper presents a design for a system capable of steering, towards a minimum run-time, the performance of a component-based application executing in a distributed fashion on a computational Grid. The proposed performance steering system controls the performance of single applications, and the basic design seeks to separate application-level and component-level concerns. The existence of a middleware resource scheduler external to the performance steering system is assumed, and potential problems are discussed. A possible model of operation is given in terms of application and component execution phases. The need for performance prediction capability, and for repositories of application-specific and component-specific performance information, is discussed. An initial implementation is briefly described.

The paper begins with an arbitrary single-output, discrete-signal, irredundant system consisting of interconnected computing units each of which has the same exponential distribution for failure time. Then it presents several corresponding redundant designs that compute the same function, derives their distributions for failure time, and illustrates them with quantitative examples. None of the straight replicative designs very much improves the original distribution for failure time; nor do the releasing designs do better. The standby designs do best, even after the standby management-system failure distribution is factored into the system failure distribution. Replicate releasing designs, as a group, are better than straight replicate designs; and standby designs are best. >

The pay-per-use business model is one of the key factors for the success of the cloud computing paradigm: resources are acquired only when needed and charged on the basis of their actual usage. The execution of applications in the cloud implies costs that depend on the usage of the leased resources and on the resource pricing model adopted by the providers. This paper presents a technique to evaluate the trade-off between costs and performance of cloud applications through the use of benchmarks and simulation. Given a mOSAIC cloud application, it is possible to predict performance indexes and resource consumption under generic workloads. This makes it possible to choose the deployment on the resources of the provider that guarantees the desired performance levels and minimizes the costs for executing the application.