a survey on resource allocation & monitoring in cloud computing
DESCRIPTION
Existing research works on Resource Allocation & Monitoring In Cloud ComputingTRANSCRIPT
A SURVEY ON RESOURCE A SURVEY ON RESOURCE ALLOCATION & MONITORING IN ALLOCATION & MONITORING IN
CLOUD COMPUTINGCLOUD COMPUTING
By:
Mohd Hairy Mohamaddiah, Azizol Abdullah, Shamala Subramaniam & Masnida Hussin
Department of Communication Technology and Network
Faculty Of Computer Science & Information Technology
Universiti Putra Malaysia (UPM)
OutlinesOutlines
i.i. Cloud Computing : OverviewCloud Computing : Overview
ii.ii. Resource Management Resource Management
iii.iii. Research ProblemResearch Problem
iv.iv. Research ObjectivesResearch Objectives
v.v. Research MethodologiesResearch Methodologies
vi.vi. Resource Allocation & Monitoring : Existing Resource Allocation & Monitoring : Existing MechanismsMechanisms
vii.vii. Research Gap Research Gap
viii.viii.ConclusionConclusion
ix.ix. ReferencesReferences
Cloud Computing : OverviewCloud Computing : Overview
Model enabling ubiquitous, convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services) that can be rapidly provisioned and released with minimal management effort or service provider interaction (NIST,2009)
Cloud Computing : OverviewCloud Computing : Overview
Deployment Deployment ModelModel
CharacteristicsCharacteristics Service ModelService Model
Public Public PrivatePrivate HybridHybrid CommunityCommunity
Infrastructure as a ServiceInfrastructure as a Service Platform as a ServicePlatform as a Service Software as a ServiceSoftware as a Service Network as a ServiceNetwork as a Service X as a ServiceX as a Service
ProviderProvider Service ProviderService Provider Infrastructure ProviderInfrastructure Provider
On Demand Self ServiceOn Demand Self Service Resource PoolingResource Pooling Broad Network AccessBroad Network Access Rapid elasticityRapid elasticity Measured ServiceMeasured Service
Cloud Computing : OverviewCloud Computing : Overview
Cloud Reference ArchitectureCloud Reference Architecture
Resource ManagementResource Management
Process that manage physical resources such as Process that manage physical resources such as CPU cores, disk space, and network bandwidth. CPU cores, disk space, and network bandwidth. This resources must be sliced and shared This resources must be sliced and shared between virtual machines running potentially between virtual machines running potentially heterogeneous workloads. heterogeneous workloads.
Resource ManagementResource Management
DISCOVERY
Discovery & Provision of
Resources
DISCOVERY
Discovery & Provision of
Resources
ALLOCATION
Allocate the Resources
MONITORING
Monitoring the client / cloud subscriber & availability of
resources
RESOURCE MANAGEMENT
Elements in Resource ManagementElements in Resource Management
Resource ManagementResource ManagementResource Provisioning ProcessResource Provisioning Process
Resource ManagementResource ManagementResource Monitoring ProcessResource Monitoring Process
Research ProblemResearch Problem
RESOURCE MANAGEMENT
Exhausted Resources/Contention/Scasrcity
(Calatrava A et al, 2011; Vinothina, V et al ,2012)
Providing Guaranteed resources On Time
(Dechminko et al,2011)
Limited Usage, Resource Contention (Calatrava A et al, 2011; Iyer R et al
2009)
Energy efficiency becoming low in Resource Management (Wang et al, 2012)
Objectives Objectives
To conduct a study in resource allocation and monitoring
in the cloud computing environment.
To describe cloud computing and its properties, research
issues in resource management mainly in resource
allocation and monitoring
To study current solutions approach for resource
allocation and monitoring
Methodologies Methodologies
Provide a cloud computing taxonomy covers the cloud
definitions, characteristics and deployment models.
Analyze the literatures and discuss about resource
management, the process and the elements.
Concentrate literatures on resource allocation and
monitoring.
Derived the problems, challenge and the approach solution
for resource allocation and monitoring in the cloud.
Resource Allocation : Existing MechanismResource Allocation : Existing Mechanism(Selected Review)(Selected Review)
Researchers Mechanism Contribution
Maurer, M., Brandic, I., & Sakellariou, R (2013)
Knowledge management (case-based & rule-based)
Decreased the most costly SLA violations, and improve performance and low energy consumption for autonomic allocation workload.
Espadas, J. et al (2013)
Tenant Isolation concept (algorithm) tenant isolation, VM Instance allocation and load balancing
Establish measurement model for underutilized resources (CPU & Memory)
Li, J. et al (2012) Optimization, Scheduling present a resource optimization mechanism in heteroge- neous IaaS federated multi-cloud systems, which enables pre-emptable task scheduling
Javadi, B. et al (2012) Scheduling Proposed a preemption policies to improve the QoS for the user request by facilitating lease preemption to resolve resource contention
Resource Allocation : Existing MechanismResource Allocation : Existing Mechanism(Selected Review)(Selected Review)
Researchers Mechanism Contribution
Young C.L , & Zomaya, A. Y (2011)
Scheduling Algorithm for Energy
Present energy conscious algorithms to reduce power consumption
Dechminko et al. (2011)
Service Oriented Architecture
Proposed Infrastructure Services Modelling Framework to support service provisioning
Calatrava, A. et al (2011)
Model Integration & Meta Scheduling analysis
Integrates cloud and grid resources to allocate resources for scientific applications
Urgaonkar, R. et al (2010)
Optimization Proposed Online admission control, routing and resource allocation for virtualized data center
Hu, Y. et al (2009) Scheduling (First Come First Server (FCFS))
Provide an allocation method to meet the SLAs for shared and dedicated allocation by using FCFS algorithms
Resource Allocation : Existing MechanismResource Allocation : Existing Mechanism(Selected Review)(Selected Review)
Researchers Mechanism Contribution
Hu, Y. et al (2009) Scheduling (First Come First Server (FCFS))
Provide an allocation method to meet the SLAs for shared and dedicated allocation by using FCFS algorithms
Resource Allocation : Existing MechanismResource Allocation : Existing MechanismTaxanomyTaxanomy
Resource Monitoring : Existing MechanismResource Monitoring : Existing Mechanism(Selected Review )(Selected Review )
Researchers Mechanism Contribution
Dabrowski, C & Hunt, F. (2011)
Fault Detection Mechanism via Discrete Time Markov Chain
Detecting & Fixing problem on time in cloud facilities
Zhy, Y. & Xu, W.(2010)
Event triggering / High availability
Monitor current state of resources
Emeakaroha, V.C. et al (2010)
Fault Detection (SLA Threats)
Introduce a framework for mappings of the Low-level resource Metrics to High-level SLAs
Sun, Y., et al (2010) IT Service Management process
Assist to achieve visualization, controllability and automation of theservice availability and performance management, to ensure QoS and reduce operation cost of deployment of cloud.
Iyer, R. , et al. (2009)
State estimation via monitoring scheme of cache space and memory bandwidth.
The estimation helps to reduce the overhead of VPA and works well with data center consolidation scenario in data center.
Resource Monitoring: Solution MechanismResource Monitoring: Solution MechanismTaxanomyTaxanomy
Gap AnalysisGap Analysis
Resource Management Process
Features Limitations
Resource Allocation
Agility, Elastic
No Infrastructure and Service Agility to adapt and formulate changes
Reliability No reliability checking mechanism for actual task executions in allocation of resources
Predictive, Scalable
Prediction model used to lower the power consumption only can be adapted in private cloud
Gap AnalysisGap Analysis
Resource Management Process
Features Limitations
Resource Monitoring
Availability, Security,
No monitoring & triggering automatically the resources state (at storage level) and resource provider availability
Not much significant study on failure detection in a dynamic and cluster environment
Both
Single Framework, Scalability
There is also no single framework for the whole autonomous resource management process being carried out in order to provide services to cloud subscriber.
Conclusion Conclusion
• Previous studies have shown the importance of resource management in cloud computing comprising discovery, monitoring and allocation resources.
• Currently and in the future there will be / are multiple heterogeneous workload will be outsourced to cloud resources. The importance of an efficient framework for the process is a high demand especially to fulfill the agile of user requests.
• We had summarized different methods (algorithms technique) and
theory which being used to formulate framework and model, derived
to provide a better resource allocation and monitoring process in
terms of a better performance, competitive and efficiency to meet the
required SLA, improved the resource performance and lowered the
power consumption
ReferencesReferences(Selected) (Selected)
1. Espadas, J., Molina, A., Jiménez, G., Molina, M., Ramírez, R., & Concha, D. : A tenant-based resource allocation model for scaling software-as-a-service applications over cloud computing infrastructures. Future Generation Computer Systems, 29(1), 273-286. doi: 10.1016/j.future.2011.10.013.(2013).
2. Maurer, M., Brandic, I., & Sakellariou, R. : Adaptive resource configuration for Cloud infrastructure management. Future Generation Computer Systems, 29(2), 472–487. doi:10.1016/j.future.2012.07.004. (2013).
3. Li, J., Qiu, M., Ming, Z., Quan, G., Qin, X., & Gu, Z.: Online optimization for scheduling preemptable tasks on IaaS cloud systems. Journal of Parallel and Distributed Computing, 72(5), 666–677. doi:10.1016/j.jpdc.2012.02.002.(2012).
4. Javadi, B., Abawajy, J., & Buyya, R. : Failure-aware resource provisioning for hybrid Cloud infrastructure. Journal of Parallel and Distributed Computing, 72(10), 1318–1331. doi:10.1016/j.jpdc.2012.06.012.(2012).
5. Wang, X., Du, Z., & Chen, Y. : An adaptive model-free resource and power management approach for multi-tier cloud environments. Journal of Systems and Software, 85(5), 1135-1146. doi: 10.1016/j.jss.2011.12.043.(2012).
6. Vinothina, V. , Sridaran R. & Ganapathi, P. : A Survey on Resource Allocation Strategies in Cloud Computing. International Journal Of Advanced Computer Science and Applications, 3(6), 97–104. (2012).
ReferencesReferences(Selected) (Selected)
6. Demchenko, Y.; Van der Ham, J.; Yakovenko, V.; De Laat, C.; Ghijsen, M.; Cristea, M., On-demand provisioning of Cloud and Grid based infrastructure services for collaborative projects and groups,. Collaboration Technologies and Systems (CTS), 2011 International Conference on , vol., no., pp.134,142, 23-27 May 2011.doi: 10.1109/CTS.2011.5928675.
7. Calatrava, A.; Molto, G.; Hernandez, V. : Combining Grid and Cloud Resources for Hybrid Scientific Computing Executions," Cloud Computing Technology and Science (CloudCom), 2011 IEEE Third International Conference on , vol., no., pp.494-501. (2011).
8. Young Choon Lee, & Zomaya, A. Y. : Energy conscious scheduling for distributed computing systems under different operating conditions. Parallel and Distributed Systems, IEEE Transactions on, 22(8), 1374-1381. (2011).
9. Dabrowski, C., & Hunt, F. : Identifying Failure Scenarios in Complex System by Perturbing Markov Chain Analysis Models. In : Proceedings of the 2011 Pressure Vessels & Piping Division (PVPD) Conference . PVP2011-57683, 1–24. (2011).
10.Urgaonkar, R., Kozat, U. C., Igarashi, K., & Neely, M. J. : Dynamic Resource Allocation and Power Management in Virtualized Data Centers (pp. 479–486). (2010).
11.Sun, Y., Xiao, Z., & Bao, D. : An architecture model of management and monitoring on Cloud services resources. 2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE), V3–207–V3–211. doi:10.1109/ICACTE.2010.5579654.(2010).
ReferencesReferences(Selected) (Selected)
12.Hu, Y., Wong, J., Iszlai, G., & Litoiu, M. : Resource provisioning for cloud computing. CASCON '09 Proceedings of the 2009 Conference of the Center for Advanced Studies on Collaborative Research, 101–111. (2009).
13. Iyer, R., Illikkal, R., Tickoo, O., Zhao, L., Apparao, P., & Newell, D. : VM3: Measuring, modeling and managing VM shared resources. Computer Networks, 53(17), 2873-2887. doi: 10.1016/j.comnet.2009.04.015.(2009).
Thank you