Reestablishing Page Placement Mechanisms for Nested Virtualization
Reestablishing Page Placement Mechanisms for Nested Virtualization
复制标题
DOI：
10.1109/tcc.2023.3276368
复制
发表时间：
2023-07
影响因子：
6.5
通讯作者：
Xiaowei Shang;Weiwei Jia;Jianchen Shan;Xiaoning Ding;C. Borcea
中科院分区：
文献类型：
--
作者：
Xiaowei Shang;Weiwei Jia;Jianchen Shan;Xiaoning Ding;C. Borcea
页面放置机制长期以来一直用于减少缓存冲突未命中。它们在云中变得更加重要，其中新兴的基于方式的缓存分区用于更好的工作负载隔离，但代价是增加缓存冲突。然而，页面放置机制在云等虚拟化环境中变得无效，因为内存页面的真实位置（即它们的主机物理地址）对客户操作系统是隐藏的。该论文提出 xPlace 作为在嵌套虚拟化配置下重建页面放置机制的解决方案。为了保持高可移植性和低开销，xPlace 采用了一种在主机和来宾 VM 之间创建协同作用的方法，使得每个来宾 VM 内的页面放置机制变得有效，即使其页面放置决策是基于内存页面的来宾物理地址做出的。本文解决了在嵌套虚拟化设置中实现此方法的技术问题，特别是如何与位于主机和来宾虚拟机之间的来宾虚拟机管理程序所造成的障碍建立协同作用。基于原型实现和各种实际应用的评估表明，xPlace 可以大大减少嵌套环境中的缓存冲突并提高应用程序性能。
Page placement mechanisms have long been used to reduce cache conflict misses. They become more important in clouds where the emerging way-based cache partitioning is used for better workload isolation but at a cost of increased cache conflicts. However, page placement mechanisms become ineffective in virtualized environments, such as clouds, because the real locations of memory pages (i.e., their host physical addresses) are hidden from guest OSs. The paper proposes xPlace as a solution to reestablish page placement mechanisms under the nested virtualization configuration. To keep high portability and low overhead, xPlace follows an approach that creates a synergy between the host and guest VMs, such that the page placement mechanism inside each guest VM becomes effective even if its page placement decisions are made based on the guest physical addresses of memory pages. The paper addresses the technical issues for implementing this approach in the nested virtualization setting, particularly how to create the synergy with the obstacle created by guest hypervisors sitting between the host and guest VMs. Evaluation based on the prototype implementation and diverse real world applications shows that xPlace can greatly reduce cache conflicts and improve application performance in the nested environment.