一句话：提出 CPS 半虚拟化调度框架，把 hypervisor 内部运行时状态暴露给 guest，消除由此引发的可扩展性瓶颈。
当前云平台在众核机器上提供含大量 vCPU 的大规格虚拟机实例，这类机器具有较深的存储层次以加速核心间通信。以往针对虚拟化中「双重调度」可扩展性问题的研究，多集中于同步原语的抢占问题以及传统 NUMA 架构。本文指出一个此前被忽视的可扩展性来源：guest 无法获知 hypervisor 内部维护的运行时状态（RHS）。作者给出两类典型的 RHS 问题——不可见的 pCPU 负载与动态 cache group 映射。由于 guest VM 看不到最新的 pCPU 负载与 vCPU-pCPU 映射等信息，其调度决策变得低效，进而导致 VM 性能崩塌与 CPU 利用率偏低。为此论文提出 CPS，一个协同式半虚拟化调度框架，使 guest 能够感知这些运行时内部状态并据此改善调度。摘要未给出具体的评估方法与实验数据。
Today's cloud platforms offer large virtual machine (VM) instances with multiple virtual CPUs (vCPU) on manycore machines. These machines typically have a deep memory hierarchy to enhance communication between cores. Although previous researches have primarily focused on addressing the performance scalability issues caused by the double scheduling problem in virtualized environments, they mainly concentrated on solving the preemption problem of synchronization primitives and the traditional NUMA architecture. This paper specifically targets a new aspect of scalability issues caused by the absence of runtime hypervisor-internal states (RHS). We demonstrate two typical RHS problems, namely the invisible pCPU (physical CPU) load and dynamic cache group mapping. These RHS problems result in a collapse in VM performance and low CPU utilization because the guest VM lacks visibility into the latest runtime internal states maintained by the hypervisor, such as pCPU load and vCPU-pCPU mappings. Consequently, the guest VM makes inefficient scheduling decisions.
@inproceedings{paperbot10123,
title = {CPS: A Cooperative Para-virtualized Scheduling Framework for Manycore Machines},
author = {Yuxuan Liu and Tianqiang Xu and Zeyu Mi and Zhichao Hua and Binyu Zang and Haibo Chen},
booktitle = {ASPLOS},
year = {2023},
doi = {10.1145/3623278.3624762}
}