VMAR: Optimizing I/O Performance and Resource Utilization in the Cloud - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

VMAR: Optimizing I/O Performance and Resource Utilization in the Cloud

Zhiming Shen
  • Fonction : Auteur
  • PersonId : 1003217
Zhe Zhang
  • Fonction : Auteur
  • PersonId : 1003218
Andrzej Kochut
  • Fonction : Auteur
  • PersonId : 965444
Alexei Karve
  • Fonction : Auteur
  • PersonId : 965445
Han Chen
  • Fonction : Auteur
  • PersonId : 1003219
Minkyong Kim
  • Fonction : Auteur
  • PersonId : 1003220
Hui Lei
  • Fonction : Auteur
  • PersonId : 1003221
Nicholas Fuller
  • Fonction : Auteur
  • PersonId : 1003222

Résumé

A key enabler for standardized cloud services is the encapsulation of software and data into VM images. With the rapid evolution of the cloud ecosystem, the number of VM images is growing at high speed. These images, each containing gigabytes or tens of gigabytes of data, create heavy disk and network I/O workloads in cloud data centers. Because these images contain identical or similar OS, middleware, and applications, there are plenty of data blocks with duplicate content among the VM images. However, current deduplication techniques cannot efficiently capitalize on this content similarity due to their warmup delay, resource overhead and algorithmic complexity.We propose an instant, non-intrusive, and lightweight I/O optimization layer tailored for the cloud: Virtual Machine I/O Access Redirection (VMAR). VMAR generates a block translation map at VM image creation / capture time, and uses it to redirect accesses for identical blocks to the same filesystem address before they reach the OS. This greatly enhances the cache hit ratio of VM I/O requests and leads to up to 55% performance gains in instantiating VM operating systems (48% on average), and up to 45% gain in loading application stacks (38% on average). It also reduces the I/O resource consumption by as much as 70%.
Fichier principal
Vignette du fichier
978-3-642-45065-5_10_Chapter.pdf (851.94 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01480776 , version 1 (01-03-2017)

Licence

Paternité

Identifiants

Citer

Zhiming Shen, Zhe Zhang, Andrzej Kochut, Alexei Karve, Han Chen, et al.. VMAR: Optimizing I/O Performance and Resource Utilization in the Cloud. 14th International Middleware Conference (Middleware), Dec 2013, Beijing, China. pp.183-203, ⟨10.1007/978-3-642-45065-5_10⟩. ⟨hal-01480776⟩
166 Consultations
147 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More