-
摘要: 隨著互聯網服務、大數據、云計算的興起，云服務器漸成需求主流。相對于傳統基于虛擬機的解決方案，基于硬件虛擬化的云服務器因減少了軟件的花銷能更好地實現高效能、按需簡約，能更好地滿足云計算的需求。與傳統云服務器相比，該服務器的特點是高密度、高效能成本比、高效能功耗比和高可擴展性。本文介紹了云服務器按需配置的設計理念、分布式硬件資源共享的系統結構和硬件資源虛擬化的方法。設計并實現了一個基于硬件虛擬化的16個處理器的云服務器原型系統。在該系統中，基于現場可編程門陣列（Field programmable gate array，FPGA）設計實現云服務器的互聯架構控制器（IFC）。IFC集成網絡、存儲和通用I/O資源，為高密度的云服務器提供多處理器間的互聯。借助于IFC，所有CPU能夠共享網絡、存儲和通用I/O資源，實現硬件資源的虛擬化。對原型系統的網絡和存儲性能進行了測試，結果表明該系統不但具有傳統云服務器的架構優點而且還提供更好的擴展性和更高的性能。Abstract: Traditional cloud computing is developed from a high-performance cluster. Every server in the high-performance cluster has its own resources, including a CPU, memory, a network, I/O (Input/Output), a power system, and a heat dissipation system. Using software virtualization technologies such as the kernel-based virtual machine (KVM), Xen, VMware, and Hyper-V, these exclusive resources can be shared among these servers to improve the utilization rate. Although these technologies provide a great improvement in the resource utilization rate, some overhead in the process of software virtualization is inevitable. Server architecture and virtualization technology are the two factors that mainly affect cloud computing efficiency. With the rapid development of internet services, big data, and cloud computing, the cloud server has become mainstream instead of the traditional server. On the other hand, hardware virtualization technology has gradually developed. Compared with the traditional cloud computing solutions based on virtual machines, the cloud server based on hardware virtualization can achieve much higher efficiency to better meet cloud computing requirements by removing the software overhead. The cloud server’s design concept of configuration on demand, distributed sharing of hardware resource architecture, and construction method of hardware resource virtualization are presented. A three-level interconnection architecture of the cloud server is designed. In Level-1, the computing pool and the memory pool are built, while Level-2 is for the network pool, and Level-3 is for all resource pools. Different applications in these levels can be realized in the cloud server: Level-1 for computing-intensive applications, Level-2 for transactional applications, and Level-3 for virtual applications. A prototype system of a 16-processor cloud server using hardware virtualization architecture is designed and implemented. In this system, there are sixteen physical nodes. Every physical node is composed of a CPU and two DIMMs (dual inline memory modules). Different types of CPUs may be used in these physical nodes. Every four physical nodes form a computing module. In every computing module, a field-programmable gate array (FPGA)-based interconnection fabric controller (IFC) integrated network, storage, and general I/O resources is designed to interconnect these processors. All IFCs are interlinked. All the processors in this prototype system can share the network, storage, and general I/O resources to realize hardware resource virtualization through these IFCs. For the prototyping system, evaluation experiments on network performance tests by the Netperf program and storage performance tests by the FIO program are performed. The test results show that the prototyping system not only keeps the traditional cloud server’s advantages but also provides better scalability and performance. The advantages of this cloud server are in providing a high-density, high performance-to-cost ratio, a high performance-to-Watt ratio, and high scalability compared with the existing traditional cloud server.
-
Key words:
- cloud computing /
- cloud server /
- shared storage /
- shared network /
- shared I/O
-
圖 3 基于高性能互聯網絡的硬件資源池化方法
Figure 3. Hardware resource pooling approach based on a high-performance interconnection network
圖 5 一種分級硬件資源共享云服務器系統
Figure 5. Cloud server based on a classified pooling hardware resource structure
圖 6 16顆處理器云服務器原型系統架構
Figure 6. Architecture of the 16-processor cloud server prototyping system
久色视频
圖 7 16顆處理器的云服務器原型系統樣品
Figure 7. Sample of the 16-processor cloud server prototyping system
-
參考文獻
[1] Gupta R. Above the clouds: a view of cloud computing. Asian J Res Social Sci Humanities, 2012, 2(6): 84 [2] Russinovich M, Costa M, Fournet C, et al. Toward confidential cloud computing. Commun ACM, 2021, 64(6): 54 doi: 10.1145/3453930 [3] Fellah H, Mezioud C, Batouche M C. Mobile cloud computing: Architecture, advantages and security issues // Proceedings of the 3rd International Conference on Networking, Information Systems & Security. Marrakech, 2020: 1 [4] Duan W X, Hu M, Zhou Q, et al. Reliability in cloud computing system: A review. J Comput Res Dev, 2020, 57(1): 102 doi: 10.7544/issn1000-1239.2020.20180675段文雪, 胡銘, 周瓊, 等. 云計算系統可靠性研究綜述. 計算機研究與發展, 2020, 57(1):102 doi: 10.7544/issn1000-1239.2020.20180675 [5] Hu X D, Ke X M, Yin F, et al. Shenwei-26010: A high-performance many-core processor. J Comput Res Dev, 2021, 58(6): 1155 doi: 10.7544/issn1000-1239.2021.20201041胡向東, 柯希明, 尹飛, 等. 高性能眾核處理器申威26010. 計算機研究與發展, 2021, 58(6):1155 doi: 10.7544/issn1000-1239.2021.20201041 [6] Muda J, Tumsa S, Tuni A M, et al. Cloud-enabled E-governance framework for citizen centric services. J Comput Commun, 2020, 8(7): 63 doi: 10.4236/jcc.2020.87006 [7] Sargunam S S. Cloud computing-system implementation for business applications. Circuits Syst, 2016, 7(6): 891 doi: 10.4236/cs.2016.76076 [8] Beloglazov A, Abawajy J, Buyya R. Energy-aware resource allocation heuristics for efficient management of data centers for Cloud computing. Future Gener Comput Syst, 2012, 28(5): 755 doi: 10.1016/j.future.2011.04.017 [9] Rupra S S, Omamo A. A cloud computing security assessment framework for small and medium enterprises. J Inf Secur, 2020, 11(4): 201 [10] Hua Z, Wang X. Cloud computing and the essentials of security management. OALib, 2016, 3(5): 1 [11] Chen X M, Jha N K. A 3-D CPU-FPGA-DRAM hybrid architecture for low-power computation. IEEE Trans Very Large Scale Integr (VLSI)Syst, 2016, 24(5): 1649 doi: 10.1109/TVLSI.2015.2483525 [12] Rusek M, Dwornicki G. Swarm-like distributed algorithm for scheduling a microservice-based application to the cloud servers. Electronics, 2021, 10(13): 1553 doi: 10.3390/electronics10131553 [13] Hu F, Che S J. Establishment of the docker-based laboratory environment. OALib, 2019, 6(6): 1 [14] Wood T, Ramakrishnan K K, Hwang J, et al. Toward a software-based network: Integrating software defined networking and network function virtualization. IEEE Netw, 2015, 29(3): 36 doi: 10.1109/MNET.2015.7113223 [15] Mijumbi R, Serrat J, Gorricho J L, et al. Network function virtualization: State-of-the-art and research challenges. IEEE Commun Surv Tutor, 2016, 18(1): 236 doi: 10.1109/COMST.2015.2477041 [16] Alam I, Sharif K, Li F, et al. A survey of network virtualization techniques for internet of things using SDN and NFV. ACM Comput Surv, 2021, 53(2): 35 [17] Minhas U I, Russell M, Kaloutsakis S, et al. NanoStreams: A microserver architecture for real-time analytics on fast data streams. IEEE Trans Multi Scale Comput Syst, 2018, 4(3): 396 doi: 10.1109/TMSCS.2017.2764087 [18] Dutta H, Kissler D, Hannig F, et al. A holistic approach for tightly coupled reconfigurable parallel processors. Microprocess Microsyst, 2009, 33(1): 53 doi: 10.1016/j.micpro.2008.08.007 [19] Hu W W, Yang L, Fan B X, et al. An 8-core MIPS-compatible processor in 32/28 nm bulk CMOS. IEEE J Solid State Circuits, 2014, 49(1): 41 doi: 10.1109/JSSC.2013.2284649 [20] Cheng K, Doddamani S, Chiueh T C, et al. Directvisor: Virtualization for bare-metal cloud // Proceedings of the 16th ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments. Lausanne, 2020: 45 [21] Venkateswaran S, Sarkar S. Time-sensitive provisioning of bare metal compute as a cloud service // 2019 IEEE 12th International Conference on Cloud Computing. Milan, 2019: 447 [22] Zhang X T, Zheng X, Wang Z, et al. High-density multi-tenant bare-metal cloud // Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems. Lausanne, 2020: 483 [23] Zhou S J, Prasanna V K. Accelerating graph analytics on CPU-FPGA heterogeneous platform // 2017 29th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). Campinas, 2017: 137 [24] Zheng C M, Yao X X, Zhou F, et al. Adaption and implementation of server chipsets for the Loongson CPU. Chin J Eng, 2022, 44(7): 1244鄭臣明, 姚宣霞, 周芳, 等. 龍芯處理器服務器芯片組的適配與實現. 工程科學學報, 2022, 44(7):1244 [25] Zhang W L, Chen M Y, Fan J P. Emulation and forecast of HPL test performance. J Comput Res Dev, 2006, 43(3): 557 doi: 10.1360/crad20060328張文力, 陳明宇, 樊建平. HPL測試性能仿真與預測. 計算機研究與發展, 2006, 43(3):557 doi: 10.1360/crad20060328 [26] Wang S, Qi F B, Gu H F, et al. Linpack parallel performance model and its prediction. Comput Eng, 2012, 38(16): 81 doi: 10.3969/j.issn.1000-3428.2012.16.020王申, 漆鋒濱, 谷洪峰, 等. Linpack并行性能模型及其預測. 計算機工程, 2012, 38(16):81 doi: 10.3969/j.issn.1000-3428.2012.16.020 -
下載:
點擊查看大圖
圖(10)
計量
- 文章訪問數: 483
- HTML全文瀏覽量: 173
- PDF下載量: 56
- 被引次數: 0
