scholarly journals Nudge: Stochastically Improving upon FCFS

2021 ◽  
Vol 5 (2) ◽  
pp. 1-29
Author(s):  
Isaac Grosof ◽  
Kunhe Yang ◽  
Ziv Scully ◽  
Mor Harchol-Balter
Keyword(s):  
Response Time ◽  
Open Problem ◽  
Scheduling Algorithm ◽  
Size Distributions ◽  
Asymptotically Optimal ◽  
Asymptotic Regime ◽  
Scheduling Policy ◽  
Asymptotic Tail

The First-Come First-Served (FCFS) scheduling policy is the most popular scheduling algorithm used in practice. Furthermore, its usage is theoretically validated: for light-tailed job size distributions, FCFS has weakly optimal asymptotic tail of response time. But what if we don't just care about the asymptotic tail? What if we also care about the 99th percentile of response time, or the fraction of jobs that complete in under one second? Is FCFS still best? Outside of the asymptotic regime, only loose bounds on the tail of FCFS are known, and optimality is completely open. In this paper, we introduce a new policy, Nudge, which is the first policy to provably stochastically improve upon FCFS. We prove that Nudge simultaneously improves upon FCFS at every point along the tail, for light-tailed job size distributions. As a result, Nudge outperforms FCFS for every moment and every percentile of response time. Moreover, Nudge provides a multiplicative improvement over FCFS in the asymptotic tail. This resolves a long-standing open problem by showing that, counter to previous conjecture, FCFS is not strongly asymptotically optimal.

PREEMPTIVE JOB SCHEDULING POLICY FOR DISTRIBUTIVELY-OWNED WORKSTATION CLUSTERS

2004 ◽  
Vol 14 (02) ◽  
pp. 255-270 ◽  
Author(s):  
JEMAL H. ABAWAJY
Keyword(s):  
Parallel Processing ◽  
Response Time ◽  
Cluster Computing ◽  
Job Scheduling ◽  
Response Times ◽  
Scheduling Algorithm ◽  
Cost Effective ◽  
Opportunistic Scheduling ◽  
Workstation Clusters ◽  
Scheduling Policy

Cluster computing has come to prominence as a cost-effective parallel processing tool for solving many complex computational problems. In this paper, we propose a new timesharing opportunistic scheduling policy to support remote batch job executions over networked clusters to be used in conjunction with the Condor Up-Down scheduling algorithm. We show that timesharing approaches can be used in an opportunistic setting to improve both mean job slowdowns and mean response times with little or no throughput reduction. We also show that the proposed algorithm achieves significant improvement in job response time and slowdown as compared to exiting approaches and some recently proposed new approaches.

scholarly journals An Efficient Framework to Improve QoS of CSP using Enhanced Minimal Resource Optimization based Scheduling Algorithm

2018 ◽  
Vol 12 (3) ◽  
pp. 1179
Author(s):  
Ravi Mahadevan ◽  
Neelamegam Anbazhagan
Keyword(s):  
Processing Time ◽  
Service Providers ◽  
Scheduling Algorithm ◽  
Cloud Service ◽  
Daily Basis ◽  
Resource Optimization ◽  
Cloud Environment ◽  
Bandwidth Utilization ◽  
Scheduling Policy ◽  
Minimal Resource

<span>Online Nowadays, the enterprises &amp; individuals are contributing their workloads on cloud service providers which are going to increase on daily basis. There are   large amount CSP are available to offer virtualized and dynamic resource on pay and use basis. However, there are almost CSP failed to maintain quality of service (QOS) and minimal resource optimization. Some of the existing approaches are highly dedicated on scheduling policy but, it does not considered reliable services with optimized QOS. To offer best solution of above problem, the framework proposes Enhanced Minimal Resource Optimization based Scheduling Algorithm to minimize the resources and maintain the QOS.  The method avoids delay in Request-Response model in cloud environment. To avoid overload for resource allocation, the proposed design utilized optimized scheduling policy.  Proposed mechanisms utilized optimized service brokering policy to reduce the delay response in cloud environment. The framework also help cloud user to prefer best CSP according to their prior services. The method offers rising trend of resource based structure to reduce the placement churn extensively. Proposed system utilized efficient scheduling policy to transmit data request to CSP with minimal data processing time. The entire utilization is to improve the QOS of cloud service provider in the features of multi-dimensional resource. Based on experimental evaluations, proposed technique improves the CPT (Computation Processing Time) 301.72 milliseconds, BU (Bandwidth Utilization) 20 Mbps, CPUU (CPU Utilization) 5% &amp; MRU (Memory Resource Utilization) 3% on given input parameters compare than existing methodology.</span>

New Optimal Solutions for Real-Time Reconfigurable Periodic Asynchronous Operating System Tasks with Minimizations of Response Time

2012 ◽  
Vol 1 (4) ◽  
pp. 88-131 ◽  
Author(s):  
Hamza Gharsellaoui ◽  
Mohamed Khalgui ◽  
Samir Ben Ahmed
Keyword(s):  
Response Time ◽  
Real Time ◽  
Scheduling Algorithm ◽  
Processing Unit ◽  
Software Faults ◽  
Worst Case ◽  
Agent Based ◽  
Central Processing ◽  
Technical Solutions ◽  
Task Systems

Scheduling tasks is an essential requirement in most real-time and embedded systems, but leads to unwanted central processing unit (CPU) overheads. The authors present a real-time schedulability algorithm for preemptable, asynchronous and periodic reconfigurable task systems with arbitrary relative deadlines, scheduled on a uniprocessor by an optimal scheduling algorithm based on the earliest deadline first (EDF) principles and on the dynamic reconfiguration. A reconfiguration scenario is assumed to be a dynamic automatic operation allowing addition, removal or update of operating system’s (OS) functional asynchronous tasks. When such a scenario is applied to save the system at the occurrence of hardware-software faults, or to improve its performance, some real-time properties can be violated. The authors propose an intelligent agent-based architecture where a software agent is used to satisfy the user requirements and to respect time constraints. The agent dynamically provides precious technical solutions for users when these constraints are not verified, by removing tasks according to predefined heuristic, or by modifying the worst case execution times (WCETs), periods, and deadlines of tasks in order to meet deadlines and to minimize their response time. They implement the agent to support these services which are applied to a Blackberry Bold 9700 and to a Volvo system and present and discuss the results of experiments.

Efficient task scheduling on virtual machine in cloud computing environment

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mahfooz Alam ◽  
Mahak ◽  
Raza Abbas Haidri ◽  
Dileep Kumar Yadav
Keyword(s):  
Cloud Computing ◽  
Load Balancing ◽  
Response Time ◽  
Virtual Machine ◽  
Task Allocation ◽  
Completion Time ◽  
Virtual Machines ◽  
Scheduling Algorithm ◽  
Content Type ◽  
Minimum Completion Time

Purpose Cloud users can access services at anytime from anywhere in the world. On average, Google now processes more than 40,000 searches every second, which is approximately 3.5 billion searches per day. The diverse and vast amounts of data are generated with the development of next-generation information technologies such as cryptocurrency, internet of things and big data. To execute such applications, it is needed to design an efficient scheduling algorithm that considers the quality of service parameters like utilization, makespan and response time. Therefore, this paper aims to propose a novel Efficient Static Task Allocation (ESTA) algorithm, which optimizes average utilization. Design/methodology/approach Cloud computing provides resources such as virtual machine, network, storage, etc. over the internet. Cloud computing follows the pay-per-use billing model. To achieve efficient task allocation, scheduling algorithm problems should be interacted and tackled through efficient task distribution on the resources. The methodology of ESTA algorithm is based on minimum completion time approach. ESTA intelligently maps the batch of independent tasks (cloudlets) on heterogeneous virtual machines and optimizes their utilization in infrastructure as a service cloud computing. Findings To evaluate the performance of ESTA, the simulation study is compared with Min-Min, load balancing strategy with migration cost, Longest job in the fastest resource-shortest job in the fastest resource, sufferage, minimum completion time (MCT), minimum execution time and opportunistic load balancing on account of makespan, utilization and response time. Originality/value The simulation result reveals that the ESTA algorithm consistently superior performs under varying of batch independent of cloudlets and the number of virtual machines’ test conditions.

A Scheduler Designed for the P2P Live Streaming System

2013 ◽  
Vol 756-759 ◽  
pp. 1889-1893
Author(s):  
Lei Kai ◽  
Huang Huai ◽  
Wen Min Wang ◽  
Qiang Ma
Keyword(s):  
Scheduling Algorithm ◽  
Selection Method ◽  
Research Topic ◽  
Live Streaming ◽  
P2p Streaming ◽  
Scheduling Policy ◽  
Streaming Applications ◽  
Dynamic Propagation ◽  
P2p Live Streaming ◽  
Propagation Delays

P2P(peer to peer) live streaming is currently a popular research topic, but for the defective of system architecture and scheduling policy, existing P2P streaming applications have poor user experience, such as long startup delay, long playback delay, and low playback continuity. In this paper, we aim at reducing the playback delay from the source in the environment of heterogeneous upload bandwidth, heterogeneous and dynamic propagation delays. We propose a neighbor selection method in order to utilize the capacity of the peer and consider their scheduler playback deadline. This new peering strategy typically leads to low scheduling delays and improve the playback continuity. Finally we apply a receiver driven chunk selection with a mix scheduling algorithm. Through simulation, we can observe that our scheduler can outperform.

scholarly journals Minimization Response Time Task scheduling Algorithm

2019 ◽  
Vol 705 ◽  
pp. 012008
Author(s):  
Maria Maqsood ◽  
Saima Anwar Lashari ◽  
Murtaja Ali Saare ◽  
Sari Ali Sari ◽  
Yaqdhan Mahmood Hussein ◽  
...  
Keyword(s):  
Response Time ◽  
Task Scheduling ◽  
Scheduling Algorithm ◽  
Time Task ◽  
Task Scheduling Algorithm

Using Value-Based Approach for Managing Cloud-Based Services

2017 ◽  
pp. 33-60
Author(s):  
Salah Eddin Murad ◽  
Salah Dowaji
Keyword(s):  
Response Time ◽  
Virtual Machines ◽  
Scheduling Algorithm ◽  
Software As A Service ◽  
Business Service ◽  
Cloud Infrastructure ◽  
Current Strategy ◽  
Target Value ◽  
Different Types ◽  
And Control

Software-as-a-Service (SaaS) providers are influenced by a variety of characteristics and capabilities of the available cloud infrastructure resources (IaaS). As a result, the decision made by business service owners to lease and use certain resources is an important one in order to achieve the planned outcome. This chapter uses value based approach to manage the SaaS service provided to the customers. Based on our approach, customer satisfaction is modeled not only based on the response time, but also based on the allotted budget. Using our model, the application owner is able to direct and control the decision of renting cloud resources as per the current strategy. This strategy is led by a set of defined key performance indicators. In addition, we present a scheduling algorithm that can bid for different types of virtual machines to achieve the target value. Furthermore, we proposed the required Ontology to semantically discover the needed IaaS resources. We conduct extensive simulations using different types of Amazon EC2 instances with dynamic prices.

A Fluid-Diffusion-Hybrid Limiting Approximation for Priority Systems with Fast and Slow Customers

2021 ◽  
Author(s):  
Lun Yu ◽  
Seyed Iravani ◽  
Ohad Perry
Keyword(s):  
Heavy Traffic ◽  
Priority Queue ◽  
Costs And Benefits ◽  
Fluid Limit ◽  
Asymptotically Optimal ◽  
Asymptotic Regime ◽  
Limit Process ◽  
Priority Systems ◽  
Pool System ◽  
Fluid Diffusion

The paper “Fluid-Diffusion-Hybrid (FDH) Approximation” proposes a new heavy-traffic asymptotic regime for a two-class priority system in which the high-priority customers require substantially larger service times than the low-priority customers. In the FDH limit, the high-priority queue is a diffusion, whereas the low-priority queue operates as a (random) fluid limit, whose dynamics are driven by the former diffusion. A characterizing property of our limit process is that, unlike other asymptotic regimes, a non-negligible proportion of the customers from both classes must wait for service. This property allows us to study the costs and benefits of de-pooling, and prove that a two-pool system is often the asymptotically optimal design of the system.

Sign in / Sign up

Export Citation Format

Share Document