基于利益相关视角的多维QoS云资源调度方法
|
摘要
基于云用户和云服务提供商的利益相关视角,以低计算成本(如能耗、经济成本和系统可用性等)满足云用户高QoS需求(如任务执行时间和任务最终完成时间),设计多维Qo S云计算体系结构,构建多维QoS云资源调度模型,面向二级云资源调度,提出采用多重Greedy算法思想的MQo S云资源调度算法。实验结果表明,在具有无后效性的4种云计算应用场景下,MQo S云资源调度算法相比FIFO云资源调度算法、M2EC多维能耗虚拟机调度算法,其多维QoS度总体提升206.42%～228.99%、34.26%～56.93%,其云数据中心负载均衡差平均总体降低0.48～0.49、0.20～0.27。
A multidimensional cloud computing architecture is designed and a multidimensional cloud resource scheduling model is constructed based on the stakeholder perspective of cloud users and cloud service providers to meet the high QoS requirements of cloud users(such as task execution time and task completion time) with low computing costs(such as energy consumption, economic costs and system availability). For the second-level cloud resource scheduling, an MQoS cloud resource scheduling algorithm based on multiple Greedy algorithm is proposed. The experimental results show that under the four cloud computing application scenarios with no aftereffects, the MQoS cloud resource scheduling algorithm has an overall increase of 206.42%～228.99% and 34.26%～56.93 in terms of multidimensional QoS degree compared with FIFO and M2 EC algorithms. It has an average overall reduction of 0.48～0.49 and 0.20～0.27 in terms of cloud data center load balance difference.
A multidimensional cloud computing architecture is designed and a multidimensional cloud resource scheduling model is constructed based on the stakeholder perspective of cloud users and cloud service providers to meet the high QoS requirements of cloud users(such as task execution time and task completion time) with low computing costs(such as energy consumption, economic costs and system availability). For the second-level cloud resource scheduling, an MQoS cloud resource scheduling algorithm based on multiple Greedy algorithm is proposed. The experimental results show that under the four cloud computing application scenarios with no aftereffects, the MQoS cloud resource scheduling algorithm has an overall increase of 206.42%～228.99% and 34.26%～56.93 in terms of multidimensional QoS degree compared with FIFO and M2 EC algorithms. It has an average overall reduction of 0.48～0.49 and 0.20～0.27 in terms of cloud data center load balance difference.
引文
[1]TOPCUOGLU H,HARIRI S,WU M Y. Performance-effective and low-complexity task scheduling for heterogeneous computing[J]. IEEE TransactionsonParallelandDistributedSystems,2002,13(3):260-274.
[2]MACE J, BODIK P, MUSUVATHI M, et al. 2DFQ:two-dimensional fairqueuingformulti-tenantcloudservices[C]//TheACMSpecial Interest Group on Data Communication. ACM, 2016:144-159.
[3]GRANDL R, CHOWDHURY M, AKELLA A, et al. Altruistic scheduling inmulti-resourceclusters[C]//TheUSENIXSymposiumonOperating Systems Design and Implementation. USENIX, 2016:65-80.
[4]WANGZ,HAYATM,GHANIN,etal.Optimizingcloud-service performance:efficient resource provisioning via optimal workload allocation[J].IEEETransactionsonParallelandDistributedSystems,2017, 28(6):1689-1702.
[5]DALVANDI A, GURUSAMY M, CHUA K. Application scheduling,placement, and routing for power efficiency in cloud data centers[J].IEEE Transactions on Parallel and Distributed Systems, 2017, 28(4):947-960.
[6]陈黄科,祝江汉,朱晓敏,等.云计算中资源延迟感知的实时任务调度方法[J].计算机研究与发展, 2017, 54(2):446-456.CHEN H K, ZHU J H, ZHU X M, et al. Resource-delay-aware scheduling for real-time tasks in clouds[J]. Journal of Computer Research and Development, 2017, 54(2):446-456.
[7]ZHANG H, CHEN L, YI B, et al. CODA:toward automatically identifying and scheduling coflows in the dark[C]//The Conference of the ACMSpecialInterestGrouponDataCommunication.ACM,2016:160-173.
[8]GHADERIJ.Randomizedalgorithmsforschedulingvmsinthe cloud[C]//TheAnnualIEEEInternationalConferenceonComputer Communications. IEEE, 2016:1-9.
[9]KULKARNI S G, ZHANG W, HWANG J, et al. NFVnice:dynamic backpressure and scheduling for NFV service chains[C]//The ConferenceoftheACMSpecialInterestGrouponDataCommunication.ACM, 2017:71-84.
[10]GONG Y, HE B, LI D. Network performance aware optimizations on IaaSclouds[J].IEEETransactionsonComputers,2017,66(4):672-687.
[11]刘维杰,王丽娜,王丹磊,等.面向云计算平台的虚拟机同驻方法[J].通信学报, 2018, 39(11):116-128.LIUWJ,WANGLN,WANGDL,etal.Virtualmachine co-residencymethodoncloudcomputingplatform[J].Journalon Communications, 2018, 39(11):116-128.
[12]CHOWDHURYM,STOICAI.Efficientcoflowschedulingwithout priorknowledge[C]//TheConferenceoftheACMSpecialInterest Group on Data Communication. ACM, 2015:393-406.
[13]DALVANDI A, GURUSAMY M, CHUA K C. Application scheduling,placement, and routing for power efficiency in cloud data centers[J].IEEE Transactions on Parallel and Distributed Systems, 2017, 28(4):947-960.
[14]李智勇,陈少淼,杨波,等.异构云环境多目标memetic优化任务调度方法[J].计算机学报, 2016, 39(2):377-390.LI Z Y, CHEN S M, YANG B, et al. Multi-objective memetic algorithm for task scheduling on heterogeneous cloud[J]. Chinese Journal of Computers, 2016, 39(2):377-390.
[15]沈尧,秦小麟,鲍芝峰.一种云环境中数据流的高效多目标调度方法[J].软件学报, 2017, 28(3):579-597.SHENY,QINXL,BAOZF.Effectivemulti-objectivescheduling strategyofdataflowincloud[J].JournalofSoftware,2017,28(3):579-597.
[16]徐久强,郭雪静,王进法,等.CPS资源服务模型和资源调度研究[J].计算机学报, 2018, 41(10):2330-2343.XU J Q, GUO X J, WANG J F, et al. Research on CPS resource service model and resource scheduling[J]. Chinese Journal of Computers,2018, 41(10):2330-2343.
[17]REN X, ANANTHANARAYANAN G, WIERMAN A, et al. Hopper:decentralized speculation-aware cluster scheduling at scale[C]//The ACMSpecialInterestGrouponDataCommunication.ACM,2015:379-392.
[18]CUI L, HAO Z, PENG Y, et al. Piccolo:a fast and efficient rollback system for virtual machine clusters[J]. IEEE Transactions on Parallel and Distributed Systems, 2017, 28(8):2328-2341.
[19]HOMSIS,LIUS,CHAPARRO-BAQUEROGA,etal.Workload consolidation for cloud data centers with guaranteed qos using request reneging[J].IEEETransactionson ParallelandDistributedSystems,2017, 28(7):2103-2116.
[20]CHENG D Z H, ZHOU X B, LAMA P, et al. Energy efficiency aware taskassignmentwithDVFSinheterogeneoushadoopclusters[J].IEEETransactionsonParallelandDistributedSystems,2018,29(1):70-82.
[21]HUZ,LIB,LUOJ,etal.Time-andcost-efficienttaskscheduling across geo-distributed data centers[J].IEEE Transactions on Parallel and Distributed Systems, 2018, 29(3):705-718.
[22]DUY,VECIANAGD.Scheduling forcloud-basedcomputing systems to support soft real-time applications[C]//The Conference of the ACMSpecialInterestGrouponDataCommunication.ACM,2016:1-9.
[23]CUI L, CZIVA R, TSO F P, et al. Synergistic policy and virtual machine consolidation in cloud data centers[C]//The Annual IEEE International Conference on Computer Communications. IEEE, 2016:1-9.
[24]YANGS,WIEDERP,YAHYAPOURR,etal.Reliablevirtualmachine placement and routing in clouds[J]. IEEE Transactions on Parallel and Distributed Systems, 2017, 28(10):2965-2978.
[25]ADAM O, LEE Y C, ZOMAYA A Y. Stochastic resource provisioning for containerized multi-tier Web services in clouds[J]. IEEE Transactions on Parallel and Distributed Systems, 2017, 28(7):2060-2073.
[26]RAMPERSAUD S, GROSU D. Sharing-aware online virtual machine packinginheterogeneousresourceclouds[J].IEEETransactionson Parallel and Distributed Systems, 2017, 28(7):2046-2059.
[27]孙大为,常桂然,陈东,等.云计算环境中绿色服务级目标的分析、量化、建模及评价[J].计算机学报, 2013, 36(7):1509-1525.SUN D W, CHANG G R, CHEN D, et al. Profiling, quantifying, modeling and evaluating green service level objectives in cloud computing enviroments[J].ChineseJournalofComputers,2013,36(7):1509-1525.
[28]ADDYA S K, TURUK A K, SAHOO B, et al. A game theoretic approach to estimate fair cost of VM Placement in cloud data center[J].IEEE System Journal, 2018, 12(4):3509-3518.
[29]ALHARBI F, TIAN Y C, TANG M L, et al. An ant colony system for energy-efficient dynamic virtual machine placement in data centers[J].Expert System witch Applications, 2019(120):228-239.
[30]LEBRE A, PASTOR J, SIMONET A, et al. Putting the next 500 VM placementalgorithmstotheacidtest:theinfrastructureprovider viewpoint[J]. IEEE Transactions on Parallel and Distributed Systems,2019, 30(1):204-217.
[2]MACE J, BODIK P, MUSUVATHI M, et al. 2DFQ:two-dimensional fairqueuingformulti-tenantcloudservices[C]//TheACMSpecial Interest Group on Data Communication. ACM, 2016:144-159.
[3]GRANDL R, CHOWDHURY M, AKELLA A, et al. Altruistic scheduling inmulti-resourceclusters[C]//TheUSENIXSymposiumonOperating Systems Design and Implementation. USENIX, 2016:65-80.
[4]WANGZ,HAYATM,GHANIN,etal.Optimizingcloud-service performance:efficient resource provisioning via optimal workload allocation[J].IEEETransactionsonParallelandDistributedSystems,2017, 28(6):1689-1702.
[5]DALVANDI A, GURUSAMY M, CHUA K. Application scheduling,placement, and routing for power efficiency in cloud data centers[J].IEEE Transactions on Parallel and Distributed Systems, 2017, 28(4):947-960.
[6]陈黄科,祝江汉,朱晓敏,等.云计算中资源延迟感知的实时任务调度方法[J].计算机研究与发展, 2017, 54(2):446-456.CHEN H K, ZHU J H, ZHU X M, et al. Resource-delay-aware scheduling for real-time tasks in clouds[J]. Journal of Computer Research and Development, 2017, 54(2):446-456.
[7]ZHANG H, CHEN L, YI B, et al. CODA:toward automatically identifying and scheduling coflows in the dark[C]//The Conference of the ACMSpecialInterestGrouponDataCommunication.ACM,2016:160-173.
[8]GHADERIJ.Randomizedalgorithmsforschedulingvmsinthe cloud[C]//TheAnnualIEEEInternationalConferenceonComputer Communications. IEEE, 2016:1-9.
[9]KULKARNI S G, ZHANG W, HWANG J, et al. NFVnice:dynamic backpressure and scheduling for NFV service chains[C]//The ConferenceoftheACMSpecialInterestGrouponDataCommunication.ACM, 2017:71-84.
[10]GONG Y, HE B, LI D. Network performance aware optimizations on IaaSclouds[J].IEEETransactionsonComputers,2017,66(4):672-687.
[11]刘维杰,王丽娜,王丹磊,等.面向云计算平台的虚拟机同驻方法[J].通信学报, 2018, 39(11):116-128.LIUWJ,WANGLN,WANGDL,etal.Virtualmachine co-residencymethodoncloudcomputingplatform[J].Journalon Communications, 2018, 39(11):116-128.
[12]CHOWDHURYM,STOICAI.Efficientcoflowschedulingwithout priorknowledge[C]//TheConferenceoftheACMSpecialInterest Group on Data Communication. ACM, 2015:393-406.
[13]DALVANDI A, GURUSAMY M, CHUA K C. Application scheduling,placement, and routing for power efficiency in cloud data centers[J].IEEE Transactions on Parallel and Distributed Systems, 2017, 28(4):947-960.
[14]李智勇,陈少淼,杨波,等.异构云环境多目标memetic优化任务调度方法[J].计算机学报, 2016, 39(2):377-390.LI Z Y, CHEN S M, YANG B, et al. Multi-objective memetic algorithm for task scheduling on heterogeneous cloud[J]. Chinese Journal of Computers, 2016, 39(2):377-390.
[15]沈尧,秦小麟,鲍芝峰.一种云环境中数据流的高效多目标调度方法[J].软件学报, 2017, 28(3):579-597.SHENY,QINXL,BAOZF.Effectivemulti-objectivescheduling strategyofdataflowincloud[J].JournalofSoftware,2017,28(3):579-597.
[16]徐久强,郭雪静,王进法,等.CPS资源服务模型和资源调度研究[J].计算机学报, 2018, 41(10):2330-2343.XU J Q, GUO X J, WANG J F, et al. Research on CPS resource service model and resource scheduling[J]. Chinese Journal of Computers,2018, 41(10):2330-2343.
[17]REN X, ANANTHANARAYANAN G, WIERMAN A, et al. Hopper:decentralized speculation-aware cluster scheduling at scale[C]//The ACMSpecialInterestGrouponDataCommunication.ACM,2015:379-392.
[18]CUI L, HAO Z, PENG Y, et al. Piccolo:a fast and efficient rollback system for virtual machine clusters[J]. IEEE Transactions on Parallel and Distributed Systems, 2017, 28(8):2328-2341.
[19]HOMSIS,LIUS,CHAPARRO-BAQUEROGA,etal.Workload consolidation for cloud data centers with guaranteed qos using request reneging[J].IEEETransactionson ParallelandDistributedSystems,2017, 28(7):2103-2116.
[20]CHENG D Z H, ZHOU X B, LAMA P, et al. Energy efficiency aware taskassignmentwithDVFSinheterogeneoushadoopclusters[J].IEEETransactionsonParallelandDistributedSystems,2018,29(1):70-82.
[21]HUZ,LIB,LUOJ,etal.Time-andcost-efficienttaskscheduling across geo-distributed data centers[J].IEEE Transactions on Parallel and Distributed Systems, 2018, 29(3):705-718.
[22]DUY,VECIANAGD.Scheduling forcloud-basedcomputing systems to support soft real-time applications[C]//The Conference of the ACMSpecialInterestGrouponDataCommunication.ACM,2016:1-9.
[23]CUI L, CZIVA R, TSO F P, et al. Synergistic policy and virtual machine consolidation in cloud data centers[C]//The Annual IEEE International Conference on Computer Communications. IEEE, 2016:1-9.
[24]YANGS,WIEDERP,YAHYAPOURR,etal.Reliablevirtualmachine placement and routing in clouds[J]. IEEE Transactions on Parallel and Distributed Systems, 2017, 28(10):2965-2978.
[25]ADAM O, LEE Y C, ZOMAYA A Y. Stochastic resource provisioning for containerized multi-tier Web services in clouds[J]. IEEE Transactions on Parallel and Distributed Systems, 2017, 28(7):2060-2073.
[26]RAMPERSAUD S, GROSU D. Sharing-aware online virtual machine packinginheterogeneousresourceclouds[J].IEEETransactionson Parallel and Distributed Systems, 2017, 28(7):2046-2059.
[27]孙大为,常桂然,陈东,等.云计算环境中绿色服务级目标的分析、量化、建模及评价[J].计算机学报, 2013, 36(7):1509-1525.SUN D W, CHANG G R, CHEN D, et al. Profiling, quantifying, modeling and evaluating green service level objectives in cloud computing enviroments[J].ChineseJournalofComputers,2013,36(7):1509-1525.
[28]ADDYA S K, TURUK A K, SAHOO B, et al. A game theoretic approach to estimate fair cost of VM Placement in cloud data center[J].IEEE System Journal, 2018, 12(4):3509-3518.
[29]ALHARBI F, TIAN Y C, TANG M L, et al. An ant colony system for energy-efficient dynamic virtual machine placement in data centers[J].Expert System witch Applications, 2019(120):228-239.
[30]LEBRE A, PASTOR J, SIMONET A, et al. Putting the next 500 VM placementalgorithmstotheacidtest:theinfrastructureprovider viewpoint[J]. IEEE Transactions on Parallel and Distributed Systems,2019, 30(1):204-217.