Performance Analysis of Preemption-aware Scheduling in Multi-Cluster Grid Environments Mohsen Amini Salehi, Bahman Javadi, Rajkumar Buyya Cloud Computing.

Slides:

Advertisements

Similar presentations

Pricing for Utility-driven Resource Management and Allocation in Clusters Chee Shin Yeo and Rajkumar Buyya Grid Computing and Distributed Systems (GRIDS)

Advertisements

Enabling Cost-Effective Resource Leases with Virtual Machines Borja Sotomayor University of Chicago Ian Foster Argonne National Laboratory/

Evaluating the Cost-Benefit of Using Cloud Computing to Extend the Capacity of Clusters Presenter: Xiaoyu Sun.

Hadi Goudarzi and Massoud Pedram

CS 149: Operating Systems February 3 Class Meeting

SLA-Oriented Resource Provisioning for Cloud Computing

1 GridSim 2.0 Adv. Grid Modelling & Simulation Toolkit Rajkumar Buyya, Manzur Murshed (Monash), Anthony Sulistio, Chee Shin Yeo Grid Computing and Distributed.

CSE 522 Real-Time Scheduling (4)

Anthony Sulistio 1, Kyong Hoon Kim 2, and Rajkumar Buyya 1 Managing Cancellations and No-shows of Reservations with Overbooking to Increase Resource Revenue.

LOAD BALANCING IN A CENTRALIZED DISTRIBUTED SYSTEM BY ANILA JAGANNATHAM ELENA HARRIS.

Contention-aware Resource Provisioning in Federated Computational Grids Mohsen Amini Salehi Supervisors: Professor Rajkumar Buyya A/Professor Jemal Abawajy.

Energy-efficient Virtual Machine Provision Algorithms for Cloud System Ching-Chi Lin Institute of Information Science, Academia Sinica Department of Computer.

Green Cloud Computing Hadi Salimi Distributed Systems Lab, School of Computer Engineering, Iran University of Science and Technology,

Towards Virtual Routers as a Service 6th GI/ITG KuVS Workshop on “Future Internet” November 22, 2010 Hannover Zdravko Bozakov.

Managing Risk of Inaccurate Runtime Estimates for Deadline Constrained Job Admission Control in Clusters Chee Shin Yeo and Rajkumar Buyya Grid Computing.

COMMA: Coordinating the Migration of Multi-tier applications 1 Jie Zheng* T.S Eugene Ng* Kunwadee Sripanidkulchai† Zhaolei Liu* *Rice University, USA †NECTEC,

GridFlow: Workflow Management for Grid Computing Kavita Shinde.

QoS-constrained List Scheduling Heuristics for Parallel Applications on Grids 16-th Euromicro PDP Toulose, February 2008 QoS-CONSTRAINED LIST SCHEDULING.

Resource Manager for Grid with global job queue and with planning based on local schedules V.N.Kovalenko, E.I.Kovalenko, D.A.Koryagin, E.Z.Ljubimskii,

Present By : Bahar Fatholapour M.Sc. Student in Information Technology Mazandaran University of Science and Technology Supervisor:

Integrated Risk Analysis for a Commercial Computing Service Chee Shin Yeo and Rajkumar Buyya Grid Computing and Distributed Systems (GRIDS) Lab. Dept.

Dynamic and Decentralized Approaches for Optimal Allocation of Multiple Resources in Virtualized Data Centers Wei Chen, Samuel Hargrove, Heh Miao, Liang.

Virtual Machine Hosting for Networked Clusters: Building the Foundations for “Autonomic” Orchestration Based on paper by Laura Grit, David Irwin, Aydan.

CS 712 | Fall 2007 Using Mobile Relays to Prolong the Lifetime of Wireless Sensor Networks Wei Wang, Vikram Srinivasan, Kee-Chaing Chua. National University.

Bargaining Towards Maximized Resource Utilization in Video Streaming Datacenters Yuan Feng 1, Baochun Li 1, and Bo Li 2 1 Department of Electrical and.

A Budget Constrained Scheduling of Workflow Applications on Utility Grids using Genetic Algorithms Jia Yu and Rajkumar Buyya Grid Computing and Distributed.

Computer Architecture and Operating Systems CS 3230: Operating System Section Lecture OS-3 CPU Scheduling Department of Computer Science and Software Engineering.

OPERATING SYSTEMS CPU SCHEDULING.  Introduction to CPU scheduling Introduction to CPU scheduling  Dispatcher Dispatcher  Terms used in CPU scheduling.

Network Aware Resource Allocation in Distributed Clouds.

Ruppa K. Thulasiram Slide 1/24 Resource Provisioning Policies to Increase IaaS Provider’s Profit in a Federated Cloud Environment Adel Nadjaran Toosi *,

Scheduling of Parallel Jobs In a Heterogeneous Multi-Site Environment By Gerald Sabin from Ohio State Reviewed by Shengchao Yu 02/2005.

Marcos Dias de Assunção 1,2, Alexandre di Costanzo 1 and Rajkumar Buyya 1 1 Department of Computer Science and Software Engineering 2 National ICT Australia.

Cloud Computing Energy efficient cloud computing Keke Chen.

INFORMATION AND COMMUNICATION SYSTEMS MERIT 2008 Research Symposium Melbourne Engineering Graduates Look to the Future System Architecture An internetworking.

Resource Provisioning based on Lease Preemption in InterGrid Mohsen Amini Salehi, Bahman Javadi, Rajkumar Buyya Cloud Computing and Distributed Systems.

SLA-based Resource Allocation for Software as a Service Provider (SaaS) in Cloud Computing Environments Author Linlin Wu, Saurabh Kumar Garg and Rajkumar.

Policy-based CPU-scheduling in VOs Catalin Dumitrescu, Mike Wilde, Ian Foster.

Computer Science and Engineering Parallel and Distributed Processing CSE 8380 March 01, 2005 Session 14.

Challenges towards Elastic Power Management in Internet Data Center.

An Energy-Efficient Hypervisor Scheduler for Asymmetric Multi- core 1 Ching-Chi Lin Institute of Information Science, Academia Sinica Department of Computer.

The Owner Share scheduler for a distributed system 2009 International Conference on Parallel Processing Workshops Reporter: 李長霖.

BOF: Megajobs Gracie: Grid Resource Virtualization and Customization Infrastructure How to execute hundreds of thousands tasks concurrently on distributed.

1 Our focus  scheduling a single CPU among all the processes in the system  Key Criteria: Maximize CPU utilization Maximize throughput Minimize waiting.

Power-Aware Scheduling of Virtual Machines in DVFS-enabled Clusters

Job scheduling algorithm based on Berger model in cloud environment Advances in Engineering Software (2011) Baomin Xu,Chunyan Zhao,Enzhao Hua,Bin Hu 2013/1/251.

Parallelizing Video Transcoding Using Map-Reduce-Based Cloud Computing Speaker : 童耀民 MA1G0222 Feng Lao, Xinggong Zhang and Zongming Guo Institute of Computer.

Scheduling MPI Workflow Applications on Computing Grids Juemin Zhang, Waleed Meleis, and David Kaeli Electrical and Computer Engineering Department, Northeastern.

Efficient Resource Allocation for Wireless Multicast De-Nian Yang, Member, IEEE Ming-Syan Chen, Fellow, IEEE IEEE Transactions on Mobile Computing, April.

Author Utility-Based Scheduling for Bulk Data Transfers between Distributed Computing Facilities Xin Wang, Wei Tang, Raj Kettimuthu,

Data Consolidation: A Task Scheduling and Data Migration Technique for Grid Networks Author: P. Kokkinos, K. Christodoulopoulos, A. Kretsis, and E. Varvarigos.

Courtesy Piggybacking: Supporting Differentiated Services in Multihop Mobile Ad Hoc Networks Wei LiuXiang Chen Yuguang Fang WING Dept. of ECE University.

Cloudsim: simulator for cloud computing infrastructure and modeling Presented By: SHILPA V PIUS 1.

Developing resource consolidation frameworks for moldable virtual machines in clouds Author: Liang He, Deqing Zou, Zhang Zhang, etc Presenter: Weida Zhong.

Lecture 4 CPU scheduling. Basic Concepts Single Process  one process at a time Maximum CPU utilization obtained with multiprogramming CPU idle :waiting.

CPU Scheduling G.Anuradha Reference : Galvin. CPU Scheduling Basic Concepts Scheduling Criteria Scheduling Algorithms Multiple-Processor Scheduling Real-Time.

CPU scheduling.  Single Process  one process at a time  Maximum CPU utilization obtained with multiprogramming  CPU idle :waiting time is wasted 2.

IIS Progress Report 2016/01/11. Goal Propose an energy-efficient scheduler that minimize the power consumption while providing sufficient computing resources.

Simulation and Exploration of

LIGHTWEIGHT CLOUD COMPUTING FOR FAULT-TOLERANT DATA STORAGE MANAGEMENT

Cloud-Assisted VR.

CS 425 / ECE 428 Distributed Systems Fall 2016 Nov 10, 2016

CS 425 / ECE 428 Distributed Systems Fall 2017 Nov 16, 2017

Cloud-Assisted VR.

Chapter 6: CPU Scheduling

CPU Scheduling G.Anuradha

Uniprocessor scheduling

Process Scheduling B.Ramamurthy 4/19/2019.

Process Scheduling B.Ramamurthy 5/7/2019.

IIS Progress Report 2016/01/18.

Presentation transcript:

Performance Analysis of Preemption-aware Scheduling in Multi-Cluster Grid Environments Mohsen Amini Salehi, Bahman Javadi, Rajkumar Buyya Cloud Computing and Distributed Systems (CLOUDS) Laboratory, Department of Computer Science and Software Engineering, The University of Melbourne, Australia 1

Introduction: InterGrid 2 provides an architecture and policies for inter-connecting different Grids. Computational resources in each RP are shared between grid users and local users. Provisioning rights of the resources in a Grid are delegated to the InterGrid Gateway (IGG). Local users vs External users. Local users have priority!

Contention between Local and External users 3 When contention happens? Lack of resource Solution for Contention: Preemption of Ext. requests in favor of local requests Drawbacks of Preemption: overhead to the underlying system (degrades utilization) increases the response time of the grid requests

Contention Scenario in InterGrid 4

Lease based Resource Provisioning in InterGrid 5 A lease is an agreement between resource provider and resource consumer whereby the provider agrees to allocate resources to the consumer according to the lease terms presented. Virtual Machine (VM) technology is a way to implement lease- based resource provisioning. VMs are able to get suspended, resumed, stopped, or even migrated. InterGrid makes one lease for each user request. Best-Eort (BE) Cancelable Suspendable Deadline-Constraint (DC) Migratable Non-preemptive

Problem Statement 6 How to decrease the number of preemptions that take place in a multi-cluster Grid? Analytical modeling of preemption in a multi-cluster Grid environment based on routing in parallel queues

Analysis: Correlation of Response time and Number of preemption 7 Therefore, if we decrease response time the number of preemption also decreased!

Analysis: Minimize Response Time 8 Where the constrain is:

Analysis: Optimal arrival Rate to each Cluster 9 Response time of Ext. requests for each cluster j (M/G/1 queue with preemption): The input arrival rate to each cluster by using Lagrange multiplier:

Analysis: Finding out Lagrange multiplier (z) 10 Since we have: Z can be worked out from the below equation:

Analysis: Using bisection algorithm for finding z 11 Since: Then: upper bound also can be worked out as follows:

12

Preemption-aware Scheduling Policy 13 The analysis provided is based on the following assumption: each cluster was an M/G/1 queue. However, in InterGrid we are investigating each cluster as a G/G/M j j queue. all requests needed one VM. InterGrid requests need several VMs for a certain amount of time. each queue is run in FCFS fashion while we consider conservative backfilling.

Implementation details 14 To support several VMs, the service time of ext. and local requests on cluster j is calculated: CV is used to obtain second moment:

Experiment Set up 15 GridSim Simulator 3 clusters with 32, 64, and 128 nodes Conservative backfilling scheduler as LRM 100 Mbps network bandwidth Different ext. request types: BE-Suspendable:40% and BE-Cancelable:10% DC-Nonpreemptable:40% and DC-Migratable:10%.

Baseline Policies 16 Round Robin Policy (RRP) Least Rate Policy (LRP) DAS-2 workload model

Experimental Results: Number of VM Preemptions 17

Experimental Results: Resource Utilization 18

Experimental Results: Average Response Time 19

Conclusions and Future Work 20 we explored how we can minimize the number of preemptions in InterGrid. We proposed a preemption-aware scheduling policy (PAP) Experiments show that PAP resulted in up to 1000 less VM preemptions (22.5% improvement) comparing with other policies.

21 Questions?