多虚拟机机架间热迁移

Umesh Deshpande, Unmesh Kulkarni, Kartik Gopalan
{"title":"多虚拟机机架间热迁移","authors":"Umesh Deshpande, Unmesh Kulkarni, Kartik Gopalan","doi":"10.1145/2287056.2287062","DOIUrl":null,"url":null,"abstract":"Within datacenters, often multiple virtual machines (VMs) need to be live migrated simultaneously for various reasons such as maintenance, power savings, and load balancing. Such mass simultaneous live migration of multiple VMs can trigger large data transfers across the core network links and switches, and negatively affect the cluster-wide performance of network-bound applications. In this paper, we present a distributed system for inter-rack live migration (IRLM), i.e., parallel live migration of multiple VMs across racks. The key performance objective of IRLM is to reduce the traffic load on the core network links during mass VM migration through distributed deduplication of VMs' memory images. We present an initial prototype of IRLM that migrates multiple QEMU/KVM VMs within a Gigabit Ethernet cluster with 10GigE core links. We also present preliminary evaluation on a small testbed having 6 hosts per rack and 4 VMs per host. Our evaluations show that, compared to the default live migration technique in QEMU/KVM, IRLM reduces the network traffic on core links by up to 44% and the total migration time by up to 26%. We also demonstrate that network-bound applications experience a smaller degradation during migration using IRLM.","PeriodicalId":176127,"journal":{"name":"Virtualization Technologies in Distributed Computing","volume":"34 4","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"53","resultStr":"{\"title\":\"Inter-rack live migration of multiple virtual machines\",\"authors\":\"Umesh Deshpande, Unmesh Kulkarni, Kartik Gopalan\",\"doi\":\"10.1145/2287056.2287062\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Within datacenters, often multiple virtual machines (VMs) need to be live migrated simultaneously for various reasons such as maintenance, power savings, and load balancing. Such mass simultaneous live migration of multiple VMs can trigger large data transfers across the core network links and switches, and negatively affect the cluster-wide performance of network-bound applications. In this paper, we present a distributed system for inter-rack live migration (IRLM), i.e., parallel live migration of multiple VMs across racks. The key performance objective of IRLM is to reduce the traffic load on the core network links during mass VM migration through distributed deduplication of VMs' memory images. We present an initial prototype of IRLM that migrates multiple QEMU/KVM VMs within a Gigabit Ethernet cluster with 10GigE core links. We also present preliminary evaluation on a small testbed having 6 hosts per rack and 4 VMs per host. Our evaluations show that, compared to the default live migration technique in QEMU/KVM, IRLM reduces the network traffic on core links by up to 44% and the total migration time by up to 26%. We also demonstrate that network-bound applications experience a smaller degradation during migration using IRLM.\",\"PeriodicalId\":176127,\"journal\":{\"name\":\"Virtualization Technologies in Distributed Computing\",\"volume\":\"34 4\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2012-06-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"53\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Virtualization Technologies in Distributed Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2287056.2287062\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Virtualization Technologies in Distributed Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2287056.2287062","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 53

摘要

在数据中心内,由于维护、节能和负载平衡等各种原因,通常需要同时对多个虚拟机(vm)进行实时迁移。多台虚拟机同时进行大规模的热迁移,可能会引发核心网络链路和交换机之间的大量数据传输,对网络绑定应用在集群范围内的性能产生负面影响。在本文中,我们提出了一个分布式机架间热迁移系统(IRLM),即多个虚拟机跨机架并行热迁移。IRLM的主要性能目标是通过对虚拟机内存映像进行分布式重复数据删除,降低虚拟机大规模迁移过程中核心网络链路的流量负荷。我们提出了一个IRLM的初始原型,该原型可以在具有10GigE核心链路的千兆以太网集群中迁移多个QEMU/KVM虚拟机。我们还对一个小型测试平台进行了初步评估,每个机架有6个主机,每个主机有4个虚拟机。我们的评估表明,与QEMU/KVM中的默认实时迁移技术相比,IRLM将核心链路上的网络流量减少了44%,总迁移时间减少了26%。我们还证明,在使用IRLM迁移期间,网络绑定应用程序的降级较小。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Inter-rack live migration of multiple virtual machines
Within datacenters, often multiple virtual machines (VMs) need to be live migrated simultaneously for various reasons such as maintenance, power savings, and load balancing. Such mass simultaneous live migration of multiple VMs can trigger large data transfers across the core network links and switches, and negatively affect the cluster-wide performance of network-bound applications. In this paper, we present a distributed system for inter-rack live migration (IRLM), i.e., parallel live migration of multiple VMs across racks. The key performance objective of IRLM is to reduce the traffic load on the core network links during mass VM migration through distributed deduplication of VMs' memory images. We present an initial prototype of IRLM that migrates multiple QEMU/KVM VMs within a Gigabit Ethernet cluster with 10GigE core links. We also present preliminary evaluation on a small testbed having 6 hosts per rack and 4 VMs per host. Our evaluations show that, compared to the default live migration technique in QEMU/KVM, IRLM reduces the network traffic on core links by up to 44% and the total migration time by up to 26%. We also demonstrate that network-bound applications experience a smaller degradation during migration using IRLM.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信