A delay-based dynamic scheduling algorithm for bag-of-task workflows with stochastic task execution times in clouds

Bag-of-Tasks (BoT) workflows are widespread in many big data analysis fields. However, there are very few cloud resource provisioning and scheduling algorithms tailored for BoT workflows. Furthermore, existing algorithms fail to consider the stochastic task execution times of BoT workflows which leads to deadline violations and increased resource renting costs. In this paper, we propose a dynamic cloud resource provisioning and scheduling algorithm which aims to fulfill the workflow deadline by using the sum of task execution time expectation and standard deviation to estimate real task execution times. A bag-based delay scheduling strategy and a single-type based virtual machine interval renting method are presented to decrease the resource renting cost. The proposed algorithm is evaluated using a cloud simulator ElasticSim which is extended from CloudSim. The results show that the dynamic algorithm decreases the resource renting cost while guaranteeing the workflow deadline compared to the existing algorithms.     

Workflow-and-Platform Aware task clustering for scientific workflow execution in Cloud environment

A scientific workflow, usually consists of a good mix of fine and coarse computational granularity tasks displaying varied runtime requirements. It has been observed that fine grained tasks incur more scheduling overhead than their execution time, when executed on widely distributed platforms. Task clustering is extensively used, in such situations, as a runtime optimization method which involves combining multiple short duration tasks into a cluster, to be scheduled on a single resource. This helps in minimizing the scheduling overheads of the fine grained tasks. However, tasks grouping curtails the degree of parallelism and hence needs to be done optimally. Though a number of task clustering techniques have been developed to reduce the impact of system overheads, they fail to identify the appropriate number of clusters at each level of workflow in order to achieve maximum possible parallelism. This work proposes a level based autonomic Workflow-and-Platform Aware (WPA) task clustering technique which takes into consideration both; the workflow structure and the underlying resource set size for task clustering. It aims to achieve maximum possible parallelism among the tasks at a level of a workflow while minimizing the system overheads and resource wastage. A comparative study with current state of the art task clustering approaches on four well-known scientific workflows show that the proposed method significantly reduces the overall workflow execution time and at the same time is able to consolidate the load onto minimum possible resources.     

混合计算环境中截止期约束下的科学工作流调度策略

整合云和网格基础设施,增强科研机构现有网格系统的计算能力并向应用提供截止时间保障的服务是科学研究领域的热点。在这种"网格-云"混合计算环境中,对何时租借云虚拟资源以及如何租借做出有效决策是一个难题。现有的一些调度策略主要在网格资源静态能力特征的基础上,以作业等待时间作为决策依据,缺乏对资源动态服务能力的有效评估,无法保证科学应用的截止时间需求。本文提出了一种混合环境下的科学工作流执行系统架构并对其核心组件进行了阐述。针对其中的工作流调度问题,利用随机服务模型建模已有网格系统中的资源的动态服务能力,以任务违约风险作为是否租借外部虚拟资源的判断指标,提出了一个科学工作流调度算法HCA_SASWD。实验结果表明,HCA_SASWD相对于其他算法,能有效保证用户的截止时间要求,为需要提供截止时间保障的系统架构提供了参考。     

适用于实例密集型云工作流的调度算法

工作流调度算法仅适用于单个复杂工作流实例,而不适用于实例密集型云工作流实例,为此,提出了基于实例密集型的云工作流调度算法(MCUD)。MCUD算法先对待处理的一组工作流实例进行分类,再对分类后的同类工作流实例采用一种新的分配方法将用户指定的总最后期限分配到各任务;同时,在调度的过程中动态地调整后续任务的子最后期限。MCUD算法对同类工作流实例中的任务分配不同子最后期限,减小了资源竞争,提高了资源的利用率。仿真实验表明,MCUD相比于其他算法,在满足总的最后期限的前提下更进一步地降低了执行成本和执行时间。     

Real-time workflows oriented online scheduling in uncertain cloud environment

Workflow scheduling has become one of the hottest topics in cloud environments, and efficient scheduling approaches show promising ways to maximize the profit of cloud providers via minimizing their cost, while guaranteeing the QoS for users’ applications. However, existing scheduling approaches are inadequate for dynamic workflows with uncertain task execution times running in cloud environments, because those approaches assume that cloud computing environments are deterministic and pre-computed schedule decisions will be statically followed during schedule execution. To cover the above issue, we introduce an uncertainty-aware scheduling architecture to mitigate the impact of uncertain factors on the workflow scheduling quality. Based on this architecture, we present a scheduling algorithm, incorporating both event-driven and periodic rolling strategies (EDPRS), for scheduling dynamic workflows. Lastly, we conduct extensive experiments to compare EDPRS with two typical baseline algorithms using real-world workflow traces. The experimental results show that EDPRS performs better than those algorithms.     

并行任务图的优化调度算法

科学与工程计算中的很多复杂应用问题需要使用科学工作流技术,超算领域中的科学工作流常以并行任务图建模,并行任务图的有效调度对应用的高效执行有重要意义。给出了资源限制条件下并行任务图的调度模型;针对Fork-Join类并行任务图给出了若干最优化调度结论;针对一般并行任务图提出了一种新的调度算法,该算法考虑了数据通信开销对资源分配和调度性能的影响,并对已有的CPA算法在特定情况下进行了改进。通过实验与常用的CPR和CPA算法做比较,验证了提出的新算法能够获得很好的调度效果。本文提出的调度算法和得到的最优调度结论对工作流应用系统的高性能调度功能开发具有借鉴意义。     

FGFS: Feature Guided Frontier Scheduling for SIMT DAGs

In the past decade, heterogeneous multicore architectures with support for Single Instruction Multiple Thread (SIMT) style computing have become the standard platform of choice for scheduling HPC applications. Here, applications are typically modelled as a set of data-parallel tasks with dependencies represented in the form of a directed acyclic graph (DAG). The relevant execution time information for each constituent task in the DAG is known beforehand and is leveraged by scheduling algorithms (List or Cluster based) to ascertain near-optimal schedules at runtime. However, given an online setting, where applications are submitted by multiple users and the types of applications are not restrictive, the chances of knowing execution time information for every program are highly unlikely. In this context, we propose a class of intelligent algorithms for heterogeneous CPU-GPU platforms that leverage static analysis-assisted machine learning techniques for deciding how device assignments should be made at runtime, thus bypassing the requirement for expensive offline profiling passes. We formalize relevant task-level ranking metrics and discuss how existing scheduling techniques can be adapted for our proposed class of algorithms. We also devise an online cluster scheduling algorithm that supports dynamic task arrival by determining in any given scheduling epoch, mapping decisions for a subset of tasks in a DAG. We perform a detailed comparative analysis between our proposed cluster and list scheduling heuristics via extensive simulation experiments using a variety of heterogeneous multicore platform configurations and observe performance speedups in the range of 1.1–1.5× for cluster scheduling over that of list scheduling.

     

Using imbalance metrics to optimize task clustering in scientific workflow executions

Scientific workflows can be composed of many fine computational granularity tasks. The runtime of these tasks may be shorter than the duration of system overheads, for example, when using multiple resources of a cloud infrastructure. Task clustering is a runtime optimization technique that merges multiple short running tasks into a single job such that the scheduling overhead is reduced and the overall runtime performance is improved. However, existing task clustering strategies only provide a coarse-grained approach that relies on an over-simplified workflow model. In this work, we examine the reasons that cause Runtime Imbalance and Dependency Imbalance in task clustering. Then, we propose quantitative metrics to evaluate the severity of the two imbalance problems. Furthermore, we propose a series of task balancing methods (horizontal and vertical) to address the load balance problem when performing task clustering for five widely used scientific workflows. Finally, we analyze the relationship between these metric values and the performance of proposed task balancing methods. A trace-based simulation shows that our methods can significantly decrease the runtime of workflow applications when compared to a baseline execution. We also compare the performance of our methods with two algorithms described in the literature.     

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.     

Stochastic DAG scheduling using a Monte Carlo approach

In heterogeneous computing systems, there is a need for solutions that can cope with the unavoidable uncertainty in individual task execution times, when scheduling DAGs. When such uncertainties occur, static DAG scheduling approaches may suffer, and some rescheduling may be necessary. Assuming that the uncertainty in task execution times is modelled in a stochastic manner, we may be able to use this information to improve static DAG scheduling considerably. In this paper, a novel DAG scheduling approach is proposed to solve this stochastic scheduling problem, based on a Monte Carlo method. The approach is built on the top of a classic static DAG scheduling heuristic and evaluated through extensive simulation. Empirical results show that a significant improvement of average application performance can be achieved by the proposed approach at a reasonable execution time cost.     

Cost optimal scheduling in IaaS for dependent workload with particle swarm optimization

Optimizing cloud provisioning for scientific workflow applications is a challenging problem, since the workflows generally contain dependency between tasks and require specific deadlines. Usually, cloud providers offer many options to the consumers. These options include the number of virtual machines, the type of each virtual machine and the purchasing method for each machine. Currently, cloud provisioning cost optimization is an active research topic. Most of this literature is concerned with task scheduling, cloud option selection, and cloud option selection for scientific workflow applications. However, research that attempts to find solutions which cover both cloud option selection and workflow task scheduling is very limited. In this paper, we focus on optimizing the cost of purchasing infrastructure-as-a-service cloud capabilities to achieve scientific work flow execution within the specific deadlines. The proposed system considers the number of purchased instances, instance types, purchasing options, and task scheduling as constraints in an optimization process. Particle swarm optimization augmented with a variable neighborhood search technique is used to find the optimal solution. Our approach finds the configurations of purchasing options with the optimum budget for a specified workflow application based on the required performance. The solutions from the proposed system show promising performance from the perspectives of the total cost and fitness convergence when compared with other state-of-the-art algorithms.     

Cloud workflow scheduling with hybrid resource provisioning

Resource provisioning strategies are crucial for workflow scheduling problems which are widespread in cloud computing. The main challenge lies in determining the amounts of reserved and on-demand resources to meet users’ requirements. In this paper, we consider the cloud workflow scheduling problem with hybrid resource provisioning to minimize the total renting cost, which is NP-hard and has not been studied yet. An iterative population-based meta-heuristic is developed. According to the shift vectors obtained during the search procedure, timetables are computed quickly. The appropriate amounts of reserved and on-demand resources are determined by an incremental optimization method. The utilization of each resource is balanced in a swaying way, in terms of which the probabilistic matrix is updated for the next iteration. The proposed algorithm is compared with modified existing algorithms for similar problems. Experimental results demonstrate effectiveness and efficiency of the proposed algorithm.     

DAG分割模型下的云工作流调度策略

为了优化云工作流调度的经济代价和执行效率,提出一种基于有向无循环图（DAG）分割的工作流调度算法PBWS。以工作流调度效率与代价同步优化为目标,算法将调度求解过程划分为三个阶段进行：工作流DAG结构分割、分割结构调整及资源分配。工作流DAG结构分割阶段在确保任务间执行顺序依赖的同时求解初始的任务分割图;分割结构调整阶段以降低执行跨度为目标,在不同分割间对任务进行重分配;资源分配阶段旨在选择代价最高效的任务与资源映射关系,确保资源的总空闲时间最小。利用五种科学工作流DAG模型对算法进行了仿真实验。结果表明。PBWS算法仅以较小的执行跨度为开销,极大降低了工作流执行代价,实现了调度效率与调度代价的同步优化,其综合性能是优于同类型算法的。     

A hybrid instance-intensive workflow scheduling method in private cloud environment

Aiming to solve the problem of instance-intensive workflow scheduling in private cloud environment, this paper first formulates a scheduling optimization model considering the communication time between tasks. The objective of this model is to minimize the execution time of all workflow instances. Then, a hybrid scheduling method based on the batch strategy and an improved genetic algorithm termed fragmentation based genetic algorithm is proposed according to the characters of instance-intensive cloud workflow, where task priority dispatching rules are also taken into account. Simulations are conducted to compare the proposed method with the canonical genetic algorithm and two heuristic algorithms. Our simulation results demonstrate that the proposed method can considerably enhance the search efficiency of the genetic algorithm and is able to considerably outperform the compared algorithms, in particular when the number of workflow instances is high and the computational resource available for optimization is limited.

     

一种多重约束下确保成功率的云工作流调度方法

为提高多重约束下的调度成功率,提出一种满足期限和预算双重约束的云工作流调度算法.将可行工作流调度方案求解分解为工作流结构分层、预算分配、期限分配、任务选择和实例选择.工作流结构分层将所有工作流任务划分层次形成包任务,以提高并行执行程度;预算分配对整体预算在层次间进行分割;期限分配将全局期限在不同层次间分割;任务选择基于...     

基于改进DPSO的网格资源调度算法

基于市场经济模型的网格资源调度问题是一个典型的离散问题及NP-Hard问题,考虑到离散粒子群优化算法在解决离散问题上的有效性,本文在现有算法的研究基础上,提出一种基于改进的离散粒子群优化算法的网格资源分配和任务调度算法,并采用GridSim模拟器对相关算法进行仿真模拟实验和比较。实验结果表明,本文提出的调度算法在作业完成时间、综合性能以及资源的负载平衡方面均具有较大的优势。     

An Effective Cloud Workflow Scheduling Approach Combining PSO and Idle Time Slot-Aware Rules

Workflow scheduling is a key issue and remains a challenging problem in cloud computing.Faced with the large number of virtual machine(VM)types offered by cloud providers,cloud users need to choose the most appropriate VM type for each task.Multiple task scheduling sequences exist in a workflow application.Different task scheduling sequences have a significant impact on the scheduling performance.It is not easy to determine the most appropriate set of VM types for tasks and the best task scheduling sequence.Besides,the idle time slots on VM instances should be used fully to increase resources'utilization and save the execution cost of a workflow.This paper considers these three aspects simultaneously and proposes a cloud workflow scheduling approach which combines particle swarm optimization(PSO)and idle time slot-aware rules,to minimize the execution cost of a workflow application under a deadline constraint.A new particle encoding is devised to represent the VM type required by each task and the scheduling sequence of tasks.An idle time slot-aware decoding procedure is proposed to decode a particle into a scheduling solution.To handle tasks'invalid priorities caused by the randomness of PSO,a repair method is used to repair those priorities to produce valid task scheduling sequences.The proposed approach is compared with state-of-the-art cloud workflow scheduling algorithms.Experiments show that the proposed approach outperforms the comparative algorithms in terms of both of the execution cost and the success rate in meeting the deadline.     

DAGMap: efficient and dependable scheduling of DAG workflow job in Grid

DAG has been extensively used in Grid workflow modeling. Since Grid resources tend to be heterogeneous and dynamic, efficient and dependable workflow job scheduling becomes essential. It poses great challenges to achieve minimum job accomplishing time and high resource utilization efficiency, while providing fault tolerance. Based on list scheduling and group scheduling, in this paper, we propose a novel scheduling heuristic called DAGMap. DAGMap consists of two phases, namely Static Mapping and Dependable Execution. Four salient features of DAGMap are: (1) Task grouping is based on dependency relationships and task upward priority; (2) Critical tasks are scheduled first; (3) Min-Min and Max-Min selective scheduling are used for independent tasks; and (4) Checkpoint server with cooperative checkpointing is designed for dependable execution. The experimental results show that DAGMap can achieve better performance than other previous algorithms in terms of speedup, efficiency, and dependability.     

Comparison of selected algorithms for scheduling workflow applications with dynamically changing service availability

This paper compares the quality and execution times of several algorithms for scheduling service based workflow applications with changeable service availability and parameters. A workflow is defined as an acyclic directed graph with nodes corresponding to tasks and edges to dependencies between tasks. For each task, one out of several available services needs to be chosen and scheduled to minimize the workflow execution time and keep the cost of service within the budget. During the execution ofa workflow, some services may become unavailable, new ones may appear, and costs and execution times may change with a certain probability. Rescheduling is needed to obtain a better schedule. A solution is proposed on how integer linear pro- gramming can be used to solve this problem to obtain optimal solutions for smaller problems or suboptimal solutions for larger ones. It is compared side-by-side with GAIN, divide-and-conquer, and genetic algorithms for various probabilities of service unavailability or change in service parameters. The algorithms are implemented and subsequently tested in a real BeesyCluster environment.     

Static scheduling of multiple workflows with soft deadlines in non-dedicated heterogeneous environments

Typical patterns of using scientific workflows include their periodical executions using a fixed set of computational resources. Using the statistics from multiple runs, one can accurately estimate task execution and communication times to apply static scheduling algorithms. Several workflows with known estimates could be combined into a set to improve the resulting schedule. In this paper, we consider the mapping of multiple workflows to partially available heterogeneous resources. The problem is how to fill free time windows with tasks from different workflows, taking into account users’ requirements of the urgency of the results of calculations. To estimate quality of schedules for several workflows with various soft deadlines, we introduce the unified metric incorporating levels of meeting constraints and fairness of resource distribution.The main goal of the work was to develop a set of algorithms implementing different scheduling strategies for multiple workflows with soft deadlines in a non-dedicated environment, and to perform a comparative analysis of these strategies. We study how time restrictions (given by resource providers and users) influence the quality of schedules, and which scheme of grouping and ordering the tasks is the most effective for the batched scheduling of non-urgent workflows. Experiments with several types of synthetic and domain-specific sets of multiple workflows show that: (i) the use of information about time windows and deadlines leads to the significant increase of the quality of static schedules, (ii) the clustering-based scheduling scheme outperforms task-based and workflow-based schemes. This was confirmed by an evaluation of studied algorithms on a basis of the CLAVIRE workflow management platform.