Hardware virtualization | EPFL Graph Search

Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?

Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur GraphSearch.

Découvrez-en plus sur les applications Graph.

Hardware virtualization is the virtualization of computers as complete hardware platforms, certain logical abstractions of their componentry, or only the functionality required to run various operating systems. Virtualization hides the physical characteristics of a computing platform from the users, presenting instead an abstract computing platform. At its origins, the software that controlled virtualization was called a "control program", but the terms "hypervisor" or "virtual machine monitor" became preferred over time. The term "virtualization" was coined in the 1960s to refer to a virtual machine (sometimes called "pseudo machine"), a term which itself dates from the experimental IBM M44/44X system. The creation and management of virtual machines has also been called "platform virtualization", or "server virtualization", more recently. Platform virtualization is performed on a given hardware platform by host software (a control program), which creates a simulated computer environment, a virtual machine (VM), for its guest software. The guest software is not limited to user applications; many hosts allow the execution of complete operating systems. The guest software executes as if it were running directly on the physical hardware, with several notable caveats. Access to physical system resources (such as the network access, display, keyboard, and disk storage) is generally managed at a more restrictive level than the host processor and system-memory. Guests are often restricted from accessing specific peripheral devices, or may be limited to a subset of the device's native capabilities, depending on the hardware access policy implemented by the virtualization host. Virtualization often exacts performance penalties, both in resources required to run the hypervisor, and as well as in reduced performance on the virtual machine compared to running native on the physical machine. In the case of server consolidation, many small physical servers can be replaced by one larger physical server to decrease the need for more (costly) hardware resources such as CPUs, and hard drives.

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (2)

Concepts associés (20)

Cours associés (7)

Séances de cours associées (76)

The IX Operating System: Combining Low Latency, High Throughput, and Efficiency in a Protected Dataplan

Edouard Bugnion, Christos Kozyrakis, Georgios Prekas, Mia Primorac, Ana Klimovic

The conventional wisdom is that aggressive networking requirements, such as high packet rates for small messages and μs-scale tail latency, are best addressed outside the kernel, in a user-level networking stack. We present ix, a dataplane operating system that provides high I/O performance and high resource efficiency while maintaining the protection and isolation benefits of existing kernels. ix uses hardware virtualization to separate management and scheduling functions of the kernel (control plane) from network processing (dataplane). The dataplane architecture builds upon a native, zero-copy API and optimizes for both bandwidth and latency by dedicating hardware threads and networking queues to dataplane instances, processing bounded batches of packets to completion, and eliminating coherence traffic and multicore synchronization. The control plane dynamically adjusts core allocations and voltage/frequency settings to meet service-level objectives. We demonstrate that ix outperforms Linux and a user-space network stack significantly in both throughput and end-to-end latency. Moreover, ix improves the throughput of a widely deployed, key-value store by up to 6.4× and reduces tail latency by more than 2× . With three varying load patterns, the control plane saves 46%--54% of processor energy, and it allows background jobs to run at 35%--47% of their standalone throughput.

Association for Computing Machinery2016

IX: A Protected Dataplane Operating System for High Throughput and Low Latency

Edouard Bugnion, Christos Kozyrakis, Georgios Prekas, Ana Klimovic

The conventional wisdom is that aggressive networking requirements, such as high packet rates for small messages and microsecond-scale tail latency, are best addressed outside the kernel, in a user-level networking stack. We present IX, a dataplane operating system that provides high I/O performance, while maintaining the key advantage of strong protection offered by existing kernels. IX uses hardware virtualization to separate management and scheduling functions of the kernel (control plane) from network processing (dataplane). The dataplane architecture builds upon a native, zero-copy API and optimizes for both bandwidth and latency by dedicating hardware threads and networking queues to dataplane instances, processing bounded batches of packets to completion, and by eliminating coherence traffic and multi-core synchronization. We demonstrate that IX outperforms Linux and state-of-the-art, user-space network stacks significantly in both throughput and end-to-end latency. Moreover, IX improves the throughput of a widely deployed, key-value store by up to 3.6x and reduces tail latency by more than 2x.

USENIX2014

CS-728: Topics on Datacenter Design

Modern datacenters with thousands of servers and multi-megawatt power budgets form the backbone of our digital universe. ln this course, we will survey a broad and comprehensive spectrum of datacenter

CS-522: Principles of computer systems

This advanced graduate course teaches the key design principles underlying successful computer and communication systems, and shows how to solve real problems with ideas, techniques, and algorithms fr

CS-470: Advanced computer architecture

The course studies techniques to exploit Instruction-Level Parallelism (ILP) statically and dynamically. It also addresses some aspects of the design of domain-specific accelerators. Finally, it explo

Discute des moteurs JIT, HTAP, virtualisation des données et défis pour les femmes dans les systèmes informatiques.

Explore les défis dans le volume de code, la complexité et la métaprogrammation des requêtes par rapport au code.

Plongez dans l'impact sociétal et l'innovation spatiale d'Internet, en explorant ses virtualités transformatrices et ses implications sociétales.

Virtual Iron Software, was located in Lowell, Massachusetts, sold proprietary software for virtualization and management of a virtual infrastructure. Co-founded by Alex Vasilevsky, Virtual Iron figured among the first companies to offer virtualization software to fully support Intel VT-x and AMD-V hardware-assisted virtualization. Oracle Corporation agreed to acquire Virtual Iron Software, Inc., subject to customary closing conditions. Oracle now declines to offer any updates or patches for current customers, even updates and patches developed before the purchase.

Un noyau de système d’exploitation, ou simplement noyau, ou kernel en anglais, est une des parties fondamentales de certains systèmes d’exploitation. Il gère les ressources de l’ordinateur et permet aux différents composants — matériels et logiciels — de communiquer entre eux. En tant que partie du système d’exploitation, le noyau fournit des mécanismes d’abstraction du matériel, notamment de la mémoire, du (ou des) processeur(s), et des échanges d’informations entre logiciels et périphériques matériels.