Towards certifiable adaptive reservations for hypervisor-based virtualization

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2014

Autores

Stefan Groesbrink (Autor) Outra; Luis Almeida (Autor) FEUP; Mário de Sousa (Autor) FEUP; Stefan M. Petters (Autor) Outra

Ata de Conferência Internacional

Título: Proceedings of the 20th IEEE Real-Time and Embedded Technology and Applications Symposium

Páginas: 13-24

RTAS 2014 20th IEEE Real-Time and Embedded Technology and Applications Symposium

Berlin, Germany, April 15-17, 2014

Indexação

ISI Web of Knowledge - 6 Citações

Scopus - 15 Citações

INSPEC

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Engenharia electrotécnica, electrónica e informática

CORDIS: Ciências Tecnológicas > Engenharia > Engenharia de computadores

Outras Informações

ID Authenticus: P-00G-EQN

DOI: 10.1109/RTAS.2014.6925987

Abstract (EN): Hypervisor-based virtualization provides a natural way to integrate formerly distinct systems into a single mixed-criticality multicore system by consolidating in separated virtual machines. We propose an adaptive computation bandwidth management for such architectures, which is compatible with a potential certification based on the guarantee of specified bandwidth minimums and the isolation of overruns of virtual machines. This management uses periodic servers and an elastic task model to combine analyzability at design time with adaptability at runtime. Mode changes or early termination of VMs trigger a resource redistribution that reassigns spare capacity. In this paper we focus on the integration of an adaptive reservation policy into a virtualization software stack and the co-design of hypervisor and paravirtualized guest operating system. In a concrete implementation on a PowerPC 405, the bandwidth distribution policy incurred in a memory footprint below 2.7KB and a worst-case execution time for the redistribution function below 4 microseconds for realistic low numbers of VMs. Simulations over synthetically generated sets of VMs with random mode changes showed a gain of 13% of computation bandwidth when compared to an approach with fixed partitions and provided a relative error of allocated bandwidth to desired bandwidth 4 times lower.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 12