计算机科学 ›› 2022, Vol. 49 ›› Issue (2): 368-376.doi: 10.11896/jsjkx.210100110
申浩希, 牛保宁
SHEN Hao-xi, NIU Bao-ning
摘要: 响应时间是服务等级目标(Service Level Objective,SLO)的一个重要性能指标,与资源的使用量有关。资源充足可以保证请求的正常执行,响应时间短;资源不足,请求需要等待资源,响应时间长。在云计算虚拟化环境下,控制资源的访问既有对整体资源的控制,也有对CPU、网络带宽等单个资源的控制,但是目前很少有通过对网络I/O请求的直接控制来保证响应时间。为了获得更好的性能,虚拟化技术大多采用半虚拟化框架Virtio。网络I/O请求通过Virtio共享通道进行传输,使得在Virtio设立网络I/O请求的门控机制成为可能。文中利用双端聚合方法(Two-end Aggregation Method,TAM),提出实时网络I/O请求门控机制(Gating Mechanism for Real-time Network I/O Requests,GMRNR),通过控制网络I/O请求经过Virtio的时刻,保证各类请求的响应时间。GMRNR设立在Virtio前端virtio-net模块中,将请求按照其响应时间指标分级,采用计时器和聚合队列长度来控制不同级别请求经过Virtio的时刻和聚合频率,保证请求的响应时间。实验测试表明:GMRNR能够区分网络I/O请求优先级,在资源充足时,使得不同等级的网络I/O请求在各自要求的时间内完成;在资源不充足时,能优先保证高优先级的网络I/O请求的响应时间。同时,GMRNR具有较高的资源利用效率。
中图分类号:
[1]LIN W W,QI D Y.Survey of Resource Scheduling in Cloud Computing[J].Computer Science,2012,39(10):1-6. [2]LI Q,ZHENG X.Research Survey of Cloud Computing[J].Computer Science,2011,38(4):32-37. [3]CHEN Y P,LIU B,LIN W W,et al .Survey of Cloud-edge Collaboration[J].Computer Science,2021,48(3):259-268. [4]ZHANG J.Study on Cloud Computing SLA[J].Telecommunications Network Technology,2012(2):7-10. [5]GUL B,KHAN I A,MUSTAFA S,et al.CPU and RAM Energy-based SLA-aware Workload Consolidation Techniques for Clouds[J].IEEE Access,2020,8:62990-63003. [6]NASTIC S,MORICHETTA A,PUSZTAI T,et al.SLOC:Ser-vice Level Objectives for Next Generation Cloud Computing[J].IEEE Internet Computing,2020,24(3):39-50. [7]LI Q,LI Y,XU B B.QoS-Guaranteed Dynamic Resource Provi-sion in Internet Data Centers[J].Chinese Journal of Computers,2014,37(12):2395-2407. [8]SOPIN E S,GORBUNOVA A V,GAIDAMAKA Y V,et al.Analysis of Cumulative Distribution Function of the Response Time in Cloud Computing Systems with Dynamic Scaling[J].Automatic Control and Computer Sciences,2018,52(1):60-66. [9]ROSENKRANTZ S,LI H,ENGANTI P,et al.JADE:Tail-Latency-SLO-Aware Job Scheduling for Sensing-as-a-Service[C]//2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC).IEEE,2020:366-373. [10]MOSA A,SAKELLARIOU R.Dynamic Virtual Machine Placement Considering CPU and Memory Resource Requirements[C]//2019 IEEE 12th International Conference on Cloud Computing(CLOUD).IEEE,2019:196-198. [11]SUN X,LI Q Z,ZHAO P,et al.An Optimized Replica Distribution Method for Peer-to-Peer Network[J].Chinese Journal of Computers,2014,37(6):1424-1434. [12]HOU S,XU S C.A Resource Utilization Threshold based Vir-tual Machine Allocation Strategy[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2019,31(6):123-130. [13]WANG Y D,YANG J H,XU C,et al.Survey on Access Control Technologies for Cloud Computing[J].Journal of Software,2015(5):1129-1150. [14]NAMASUDRA S.Data access control in the cloud computingenvironment for bioinformatics[J].International Journal of Applied Research in Bioinformatics (IJARB),2021,11(1):40-50. [15]POPA L S,YU M,KO S,et al.CloudPolice:Taking Access Control out of the Network[C]//Proceedings of the 9th ACM SIGCOMM Workshop on Hot Topics in Networks.ACM,2010:1-6. [16]ZHANG W T.Based on I/O Performance of Virtual Machine Resource Scheduling Algorithm Research[D].Wuhan:Huazhong University of Science and Technology,2013. [17]ZHOU J F.A Study of Virtual Machine Network BandwidthDynamic Regulation Mechanism[D].Wuhan:Huazhong University of Science and Technology,2012. [18]MOUZAKITIS A,PINTO C,NIKOLAEV N,et al.Lightweight and Generic RDMA Engine Para-Virtualization for the KVM Hypervisor[C]//International Conference on High Performance Computingand Simulation.IEEE,2017:737-744. [19]KUKREIA G,SINGH S.Virtio based Transcendent Memory[C]//IEEE International Conference on Computer Science and Information Technology.IEEE,2010. [20]ARA G,LAI L,CUCINOTTA T,et al.A Framework for Comparative Evaluation of High-Performance Virtualized Networking Mechanisms[J].Cloud Computing and Services Science,2021,1399:59. [21]LIU Y Y,NIU B N.Optimizing Network Performance Based on Para-virtualization Virtio Framework[J].Journal of Chinese Computer Systems,2018,39(1):105-110. [22]CHENG S X.Research and Optimization of I/O PerformanceBottleneck in Embedded Virtualization Environment[D].Shanghai:Shanghai Jiao Tong University,2015. [23]SU X,LI Y F,ZONG N,et al.Network Real-time SchedulingAlgorithm based on Multi-feature Dynamic Priority[J].Journal on Communications,2020,41(5):159-167. [24]QIU H,BANERJEE S S,JHA S,et al.FIRM:An Intelligent Fine-grained Resource Management Framework for SLO-Oriented Microservices[C]//14th {USENIX} Symposium on Opera-ting Systems Design and Implementation ({OSDI} 20).2020:805-825. [25]LEE J,YU H.I/O Strength-Aware Credit Scheduler for Virtualized Environments[J].Electronics,2020,9(12):2107. [26]ZHANG C,YU M,YAN F.Enabling Cost-Effective,SLO-Aware Machine Learning Inference Serving on Public Cloud[J/OL].IEEE Transactions on Cloud Computing.https://ieeexploreieee.53yu.com/abstract/document/9132666. [27]ZHOU M S,DONG X S,CHEN H,et al.Dynamically Fine-grained Scheduling Method in Cloud Environment[J].Journal of Software,2020,31(12):3981-3999. [28]LIU H.Research and Implementation of Storage Architecturebased on Load Balancing[D].Jinan:Shandong University,2011. [29]RAJAVEL R,MALA T.Achieving Service Level Agreement in Cloud Environment using Job Prioritization in Hierarchical Scheduling[C]//Proceedings of the International Conference on Information Systems Design and Intelligent Applications (INDIA 2012).Springer,2012:547-554. [30]CHAPALA Y,REDDY B E.An Enhancement in Restructured Scatter-Gather for Live Migration of Virtual Machine[C]//2021 6th International Conference on Inventive Computation Technologies (ICICT).IEEE,2021:90-96. [31]KIM J H,JIN H W.Virtio Front-end Network Driver forRTEMS Operating System[J].IEEE Embedded Systems Letters,2019,12(3):91-94. [31]RUSSELL R.Virtio:Towards a De-facto Standard for Virtual I/O Devices[J].ACM SIGOPS Operating Systems Review,2008,42:95-103. |
[1] | 张瑾, 段利国, 李爱萍, 郝晓燕. 基于注意力与门控机制相结合的细粒度情感分析 Fine-grained Sentiment Analysis Based on Combination of Attention and Gated Mechanism 计算机科学, 2021, 48(8): 226-233. https://doi.org/10.11896/jsjkx.200700058 |
[2] | 钱光明, 易超. 一种多节点实时无线连接方案 Real Time Wireless Connection Scheme for Multi-nodes 计算机科学, 2021, 48(11A): 446-451. https://doi.org/10.11896/jsjkx.201200209 |
[3] | 姚泽玮, 林嘉雯, 胡俊钦, 陈星. 基于PSO-GA的多边缘负载均衡方法 PSO-GA Based Approach to Multi-edge Load Balancing 计算机科学, 2021, 48(11A): 456-463. https://doi.org/10.11896/jsjkx.210100191 |
[4] | 张忆文, 林铭炜. 基于动态优先级设备低能耗调度算法 Devices Low Energy Consumption Scheduling Algorithm Based on Dynamic Priority 计算机科学, 2021, 48(11A): 471-475. https://doi.org/10.11896/jsjkx.210100080 |
[5] | 王士浩, 王中卿, 李寿山, 周国栋. 基于门控图卷积与动态依存池化的事件论元抽取 Event Argument Extraction Using Gated Graph Convolution and Dynamic Dependency Pooling 计算机科学, 2021, 48(11A): 52-56. https://doi.org/10.11896/jsjkx.201200259 |
[6] | 夏春艳, 王兴亚, 张岩. 基于多目标优化的测试用例优先级排序方法 Test Case Prioritization Based on Multi-objective Optimization 计算机科学, 2020, 47(6): 38-43. https://doi.org/10.11896/jsjkx.191100113 |
[7] | 陶洋,纪瑞娟,杨理,王进. 异构无线网络中动态优先级接纳控制算法研究 Study on Dynamic Priority Admission Control Algorithm in Heterogeneous Wireless Networks 计算机科学, 2020, 47(3): 242-247. https://doi.org/10.11896/jsjkx.190100089 |
[8] | 刘志, 曹诗鹏, 沈阳, 杨曦. 基于改进深度强化学习方法的单交叉口信号控制 Signal Control of Single Intersection Based on Improved Deep Reinforcement Learning Method 计算机科学, 2020, 47(12): 226-232. https://doi.org/10.11896/jsjkx.200300021 |
[9] | 薛玲玲, 樊秀梅. 基于分簇结构的车联网认知频谱分配机制 Cognitive Spectrum Allocation Mechanism in Internet of Vehicles Based on Clustering Structure 计算机科学, 2019, 46(9): 143-149. https://doi.org/10.11896/j.issn.1002-137X.2019.09.020 |
[10] | 冯沈峰, 高建华. 基于AHP的回归测试用例优先级排序方法 Test Case Prioritization Method Based on AHP for Regression Testing 计算机科学, 2019, 46(8): 233-238. https://doi.org/10.11896/j.issn.1002-137X.2019.08.038 |
[11] | 张浩昱, 熊凯. 改进深度确定性策略梯度算法及其在控制中的应用 Improved Deep Deterministic Policy Gradient Algorithm and Its Application in Control 计算机科学, 2019, 46(6A): 555-557. |
[12] | 张建山, 林兵, 卢宇, 许芙蓉. 基于无线城域网的微云部署及用户任务调度 Cloudlet Placement and User Task Scheduling Based on Wireless Metropolitan Area Networks 计算机科学, 2019, 46(6): 128-134. https://doi.org/10.11896/j.issn.1002-137X.2019.06.019 |
[13] | 张娜, 徐海霞, 包晓安, 徐璐, 吴彪. 一种动态约简的多目标测试用例优先级排序方法 Multi-objective Test Case Prioritization Method Combined with Dynamic Reduction 计算机科学, 2019, 46(12): 208-212. https://doi.org/10.11896/jsjkx.181102106 |
[14] | 杜艳明, 肖建华. 云环境下基于优先级的多QoS约束工作流调度 Workflow Scheduling Strategy with Multi-QoS Constraint Based on Priority in Cloud Environment 计算机科学, 2019, 46(10): 128-134. https://doi.org/10.11896/jsjkx.180801591 |
[15] | 董禹龙,杨连贺,马欣. 主动获取式的分布式网络爬虫集群方法研究 Study on Active Acquisition of Distributed Web Crawler Cluster 计算机科学, 2018, 45(6A): 428-432. |
|