High Performance Network I/o in Virtual Machines over Modern Interconnects
نویسنده
چکیده
With the increasing size and complexity of modern computing systems, a balance between performance and manageability is becoming critical to achieve high performance as well as high productivity computing. Virtual Machine (VM) technology provides various features that help management issues on large-scale computing systems; however, performance concerns have largely blocked the deployment of VMbased computing, especially in the High-Performance Computing (HPC) area. This dissertation aims at reducing the virtualization overhead and achieving the co-existence of performance and manageability through VM technologies. We focus on I/O virtualization, designing an experimental VM-based computing framework, and addressing performance issues at different levels of the system software stack. We design VMM-bypass I/O, which achieves native I/O performance in VMs by taking advantage of the OS-bypass interconnects. Also with the OS-bypass interconnects, we propose high performance VM migration with Remote Direct Memory Access (RDMA), which drastically reduces the VM management cost. To further improve the communication efficiency on multi-core systems, we design Inter-VM Communication (IVC), a VM-aware communication library to allow efficient shared memory communication among VMs on the same physical host. Finally, we design MVAPICH2-ivc, an MPI library that is aware of VM-based environments and can transparently benefit HPC applications with our proposed designs.
منابع مشابه
High Performance VMM-Bypass I/O in Virtual Machines
Currently, I/O device virtualization models in virtual machine (VM) environments require involvement of a virtual machine monitor (VMM) and/or a privileged VM for each I/O operation, which may turn out to be a performance bottleneck for systems with high I/O demands, especially those equipped with modern high speed interconnects such as In-
متن کاملMyriXen: Message Passing in Xen Virtual Machines over Myrinet and Ethernet
Data access in HPC infrastructures is realized via user-level networking and OS-bypass techniques through which nodes can communicate with high bandwidth and low-latency. Virtualizing physical components requires hardware-aided software hypervisors to control I/O device access. As a result, line-rate bandwidth or lower latency message exchange over 10GbE interconnects hosted in Cloud Computing ...
متن کاملCommunication-Aware Traffic Stream Optimization for Virtual Machine Placement in Cloud Datacenters with VL2 Topology
By pervasiveness of cloud computing, a colossal amount of applications from gigantic organizations increasingly tend to rely on cloud services. These demands caused a great number of applications in form of couple of virtual machines (VMs) requests to be executed on data centers’ servers. Some of applications are as big as not possible to be processed upon a single VM. Also, there exists severa...
متن کاملSelf-Virtualized I/O: High Performance, Scalable I/O Virtualization in Multi-core Systems
Virtualizing I/O subsystems and peripheral devices is an integral part of system virtualization. This paper advocates the notion of self-virtualized I/O (S-VIO). Specifically, it proposes a hypervisor-level abstraction that permits guest virtual machines to efficiently exploit the multi-core nature of futureion that permits guest virtual machines to efficiently exploit the multi-core nature of ...
متن کاملPerformance Analysis of Virtualised Head Nodes Utilising Cost-Effective Network Attached Storage
In modern systems local disk I/O has significantly lower bandwidth than network I/O. This has lead to the development of Storage Area Networks (SANs) often implemented with expensive, high bandwidth switching fabrics. With the development of Infiniband and 10 Gigabit Ethernet switching fabrics, high bandwidth I/O is becoming commoditised, but as yet is not cost effective as compared to Gigabit ...
متن کامل