PROV-TE: A Provenance-Driven Diagnostic Framework for Task Eviction in Data Centers

Cloud Computing allows users to control substantial computing power for complex data processing, generating huge and complex data. However, the virtual resources requested by users are rarely utilized to their full capacities. To mitigate this, providers often perform over-commitment to maximize profit, which can result in node overloading and consequent task eviction. This paper presents a novel framework that mines the huge and growing historical usage data generated by Cloud data centers to identify the causes of overloads. Provenance modelling is applied to add contextual meaning to the data, and the PROV-TE diagnostic framework provides algorithms to efficiently identify the causality of task eviction. Using simulation to reflect real world scenarios, our results demonstrate a precision and recall of the diagnostic algorithms of 83% and 90% respectively. This demonstrates a high level of accuracy of the identification of causes.

[1]  Imad M. Abbadi,et al.  Challenges for Provenance in Cloud Computing , 2011, TaPP.

[2]  Michele Colajanni,et al.  Dynamic Load Management of Virtual Machines in Cloud Architectures , 2009, CloudComp.

[3]  Hakim Weatherspoon,et al.  Overdriver: handling memory overload in an oversubscribed cloud , 2011, VEE '11.

[4]  Bo Li,et al.  Overbooking-Based Resource Allocation in Virtualized Data Center , 2012, 2012 IEEE 15th International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing Workshops.

[5]  Paul T. Groth,et al.  A provenance-aware weighted fault tolerance scheme for service-based applications , 2005, Eighth IEEE International Symposium on Object-Oriented Real-Time Distributed Computing (ISORC'05).

[6]  Paul T. Groth,et al.  Provenance: An Introduction to PROV , 2013, Provenance.

[7]  Mohsen Guizani,et al.  Efficient datacenter resource utilization through cloud resource overcommitment , 2015, 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[8]  Sérgio Manuel Serra da Cruz,et al.  Cirrus: Towards Business Provenance As-a-Service in the Cloud , 2012, 2012 IEEE 19th International Conference on Web Services.

[9]  Nick Taylor,et al.  A Framework for Improving Trust in Dynamic Service-Oriented Systems , 2012, 2012 IEEE 15th International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing Workshops.

[10]  Luc Moreau,et al.  PROV-Overview. An Overview of the PROV Family of Documents , 2013 .

[11]  P. L. Rupasinghe,et al.  Trustworthy provenance framework for document workflow provenance , 2016, 2016 International Conference on Computational Techniques in Information and Communication Technologies (ICCTICT).

[12]  Chita R. Das,et al.  MDCSim: A multi-tier data center simulation, platform , 2009, 2009 IEEE International Conference on Cluster Computing and Workshops.

[13]  Omar Boucelma,et al.  Provenance Monitoring in the Cloud , 2013, 2013 IEEE Sixth International Conference on Cloud Computing.

[14]  Jie Xu,et al.  SEED: A Scalable Approach for Cyber-Physical System Simulation , 2016, IEEE Transactions on Services Computing.

[15]  P. Mell,et al.  The NIST Definition of Cloud Computing , 2011 .

[16]  Bruno Defude,et al.  Document Provenance in the Cloud: Constraints and Challenges , 2010, EUNICE.

[17]  Charles Lim,et al.  Toward cloud computing reference architecture: Cloud service management perspective , 2013, International Conference on ICT for Smart Society.

[18]  Alexander Stage,et al.  Network-aware migration control and scheduling of differentiated virtual machine workloads , 2009, 2009 ICSE Workshop on Software Engineering Challenges of Cloud Computing.

[19]  Ying Liu.  A Consolidation Strategy Supporting Resources Oversubscription in Cloud Computing , 2016, 2016 IEEE 3rd International Conference on Cyber Security and Cloud Computing (CSCloud).

[20]  Omar Boucelma,et al.  Trusting the Cloud: A PROV + RBAC Approach , 2014, 2014 IEEE 7th International Conference on Cloud Computing.

[21]  Rajkumar Buyya,et al.  CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms , 2011, Softw. Pract. Exp..

[22]  Long Wang,et al.  Towards an Understanding of Oversubscription in Cloud , 2012, Hot-ICE.

[23]  Margo I. Seltzer,et al.  Making a Cloud Provenance-Aware , 2009, Workshop on the Theory and Practice of Provenance.

[24]  Marc Chiarini,et al.  Collecting Provenance via the Xen Hypervisor , 2011, TaPP.

[25]  Randy H. Katz,et al.  Heterogeneity and dynamicity of clouds at scale: Google trace analysis , 2012, SoCC '12.

[26]  Dogan Yildiz,et al.  GreenCloud simulation QoSbox in cloud computing , 2016, 2016 24th Signal Processing and Communication Application Conference (SIU).

[27]  Margo I. Seltzer,et al.  Provenance for the Cloud , 2010, FAST.

[28]  Helmut Hlavacs,et al.  Provenance in the Cloud: Why and How? , 2012, CLOUD 2012.

[29]  Jie Xu,et al.  Analysis, Modeling and Simulation of Workload Patterns in a Large-Scale Utility Cloud , 2014, IEEE Transactions on Cloud Computing.

[30]  Evgenia Smirni,et al.  Managing Data Center Tickets: Prediction and Active Sizing , 2016, 2016 46th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).