Aggregate VM: Why Reduce or Evict VM's Resources When You Can Borrow Them From Other Nodes?
Aggregate VM: Why Reduce or Evict VM's Resources When You Can Borrow Them From Other Nodes?
复制标题
DOI：
10.1145/3552326.3587452
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Ho-Ren Chuang;Karim Manaouil;Tong Xing;A. Barbalace;Pierre Olivier;Balvansh Heerekar;B. Ravindran-
中科院分区：
文献类型：
--
作者：
Ho-Ren Chuang;Karim Manaouil;Tong Xing;A. Barbalace;Pierre Olivier;Balvansh Heerekar;B. Ravindran-
硬件资源碎片化是数据中心的常见问题。基于迁移或过度使用的传统解决方案速度慢得令人无法接受，而像 Spot VM 这样的现代商业或研究解决方案可能会随时减少或驱逐 VM 的资源。我们提出了一种不受这些缺点影响的替代解决方案，即聚合虚拟机。我们引入了一种新的分布式虚拟机管理程序设计，即资源借用虚拟机管理程序，它创建聚合虚拟机：临时聚合属于不同主机的碎片资源的分布式虚拟机，这需要虚拟CPU、内存和IO设备的移动性。我们实现了一个原型 FragVisor，它透明地运行客户软件。我们还建议对来宾操作系统进行最少的修改，以实现显着的性能提升。我们通过一组微基准和 IaaS 风格的实际应用程序来评估 FragVisor。尽管聚合虚拟机并不完美适合所有类型的应用程序，但与过度使用的场景相比，某些工作负载可实现显着的加速（使用 4 个分布式 vCPU 时最高可达 3.9 倍）。我们进一步证明 FragVisor 比最先进的竞争对手 GiantVM 更快（高达 2.5 倍）。
Hardware resource fragmentation is a common issue in data centers. Traditional solutions based on migration or overcommitment are unacceptably slow, and modern commercial or research solutions like Spot VM may reduce or evict VM's resources anytime. We propose an alternative solution that does not suffer from these drawbacks, the Aggregate VM. We introduce a new distributed hypervisor design, the resource-borrowing hypervisor, which creates Aggregate VMs: distributed VMs that temporarily aggregate fragmented resources belonging to different host machines, which require mobility of virtual CPUs, memory and IO devices. We implement a prototype, FragVisor, which runs guest software transparently. We also propose minimal modifications to the guest OS that can enable significant performance gains. We evaluate FragVisor over a set of microbenchmarks and IaaS-style real applications. Although Aggregate VMs are not a perfect fit for every type of applications, some workloads enjoy significant speedups compared to overcommitted scenarios (up to 3.9x with 4 distributed vCPUs). We further demonstrate that FragVisor is faster than a state-of-the-art competitor, GiantVM (up to 2.5x).