The Convergence of Container and Traditional Virtualization: Strengths and Limitations

The Convergence of Container and Traditional Virtualization: Strengths and Limitations
复制标题

容器与传统虚拟化的融合:优点和局限性

DOI:
10.1007/s42979-023-01827-9
复制
发表时间:
2023
期刊:
SN Computer Science
影响因子:
--
通讯作者:
Passakorn Phannachitta
Passakorn Phannachitta
中科院分区:
--
文献类型:
--
作者:
Guoqing Li;Keichi Takahashi;Kohei Ichikawa;Hajimu Iida;Chawanat Nakasan;Pattara Leelaprute;Pree Thiengburanathum;Passakorn Phannachitta

文献摘要

参考文献

被引文献

相似文献

虚拟机(vm)在云中被广泛使用。底层管理程序允许将硬件资源拆分为多个虚拟单元,从而支持服务器整合、故障控制和资源管理。但是,传统架构的虚拟机开销较大,降低了应用程序的性能。容器正在成为运行应用程序的流行选择,但是这种解决方案由于比vm更弱的隔离性而引起了安全问题。我们正处于容器和传统虚拟化的融合点,实现了轻量级管理程序并将其集成到容器生态系统中,以最大限度地发挥VM隔离和容器性能的优势。然而,目前还没有对不同的收敛架构进行全面的比较。为了确定限制和最适合的用例,我们通过测量磁盘存储、主内存、CPU、网络、系统调用和启动时间的性能来研究Docker、Kata、gVisor、鞭炮和QEMU/KVM的特性。此外,我们还评估了它们运行Nginx web服务器和MySQL数据库管理系统的性能。我们使用QEMU/KVM作为运行传统虚拟机的示例,Docker作为标准运行容器,其余的作为轻量级管理程序的代表。我们比较和分析基准测试结果,讨论可能的含义,解释每个组织所做的权衡,并详细说明每个体系结构的优缺点。
Virtual machines (VMs) are used extensively in the cloud. The underlying hypervisors allow hardware resources to be split into multiple virtual units which enables server consolidation, fault containment, and resource management. However, VMs with traditional architecture introduce heavy overhead and reduce application performance. Containers are becoming popular options for running applications, yet such a solution raises security concerns due to weaker isolation than VMs. We are at the point of container and traditional virtualization convergence where lightweight hypervisors are implemented and integrated into the container ecosystem to maximize the benefits of VM isolation and container performance. However, there has been no comprehensive comparison among different convergence architectures. To identify limitations and best-fit use cases, we investigate the characteristics of Docker, Kata, gVisor, Firecracker, and QEMU/KVM by measuring the performance of disk storage, main memory, CPU, network, system call, and startup time. In addition, we evaluate their performance of running the Nginx web server and the MySQL database management system. We use QEMU/KVM as an example of running traditional VMs, Docker as the standard runc container, and the rest as the representatives of lightweight hypervisors. We compare and analyze the benchmark results, discuss the possible implications, explain the trade-off each organization made, and elaborate on the pros and cons of each architecture.
DOI: 10.1145/361011.361073
发表时间: 1974
期刊: --
影响因子: --
作者:
G. Popek;R. Goldberg
通讯作者: G. Popek;R. Goldberg
DOI: --
发表时间: 2007
期刊: --
影响因子: --
作者:
Avi Kivity;Anthony Liguori
通讯作者: Avi Kivity;Anthony Liguori
DOI: --
发表时间: 2004
期刊: 第22回日本ロボット学会学術講演会予稿集
影响因子: --
作者:
M.Higashimori;東森 充;東森 充
通讯作者: 東森 充
混合容器和虚拟机:Firecracker 和 gVisor 的研究
DOI: 10.1145/3381052.3381315
发表时间: 2020
期刊: 16th ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments
影响因子: --
作者:
Anjali, FNU;Caraza-Harter, Tyler;Swift, Michael M.
通讯作者: Swift, Michael M.
RunC、gVisor 和 Kata Containers 运行时的性能和隔离分析
DOI: --
发表时间: 2022
期刊: Cluster Computing
影响因子: --
作者:
Xing Wang;Junzhao Du;Hui Liu
通讯作者: Hui Liu