Adaptive live VM migration in share-nothing IaaS-clouds with LiveFS

Nick R. Katsipoulakis; Konstantinos Tsakalozos; Alex Delis

doi:10.1109/CloudCom.2013.151

Adaptive live VM migration in share-nothing IaaS-clouds with LiveFS

Nick R. Katsipoulakis, Konstantinos Tsakalozos, Alex Delis

Computer Science

Research output: Contribution to journal › Conference article › peer-review

Abstract

Live migration is a versatile option when it comes to attain load-balancing in IaaS-cloud architectures. Liveness, reliability and conformance to SLAs may all be achieved by moving a VM that creates excessive work from its current physical machine (PM) to a less busy node. Despite its promising features, live migration is an expensive operation in terms of resources. The situation gets further exacerbated when the movement involves PMs working off different file-systems which is often the case in shared-nothing IaaS-cloud infrastructures. In this paper, we suggest an approach that adapts the migration operation based on the I/O activity of the originating-VM. We introduce LiveFS, a FUSE-file system which traps all I/Os and helps determine how to best ship virtual disk segments across PMs in a share-nothing IaaS-cloud. Through prototyping and experimentation, we show that LiveFS can improve the shipment of VMs for diverse types of workloads. In particular, LiveFS succeeds in reducing the Total Migration Time by up to 64% compared to the "pre-copy" live migration technique. Furthermore during migration, we attain up-to 19% less I/O-delay if compared to the "post-copy" live-migration approach.

Original language	English (US)
Article number	6735439
Pages (from-to)	293-298
Number of pages	6
Journal	Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom
Volume	2
DOIs	https://doi.org/10.1109/CloudCom.2013.151
State	Published - 2013
Event	5th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2013 - Bristol, United Kingdom Duration: Dec 2 2013 → Dec 5 2013

Keywords

Cloud Storage
Distributed Systems
Share-Nothing IaaS Cloud
Storage

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Networks and Communications
Software
Theoretical Computer Science

Access to Document

10.1109/CloudCom.2013.151

Cite this

@article{c6f69b570d93432f9fabd4dfc6728ec4,

title = "Adaptive live VM migration in share-nothing IaaS-clouds with LiveFS",

abstract = "Live migration is a versatile option when it comes to attain load-balancing in IaaS-cloud architectures. Liveness, reliability and conformance to SLAs may all be achieved by moving a VM that creates excessive work from its current physical machine (PM) to a less busy node. Despite its promising features, live migration is an expensive operation in terms of resources. The situation gets further exacerbated when the movement involves PMs working off different file-systems which is often the case in shared-nothing IaaS-cloud infrastructures. In this paper, we suggest an approach that adapts the migration operation based on the I/O activity of the originating-VM. We introduce LiveFS, a FUSE-file system which traps all I/Os and helps determine how to best ship virtual disk segments across PMs in a share-nothing IaaS-cloud. Through prototyping and experimentation, we show that LiveFS can improve the shipment of VMs for diverse types of workloads. In particular, LiveFS succeeds in reducing the Total Migration Time by up to 64% compared to the {"}pre-copy{"} live migration technique. Furthermore during migration, we attain up-to 19% less I/O-delay if compared to the {"}post-copy{"} live-migration approach.",

keywords = "Cloud Storage, Distributed Systems, Share-Nothing IaaS Cloud, Storage",

author = "Katsipoulakis, {Nick R.} and Konstantinos Tsakalozos and Alex Delis",

note = "Copyright: Copyright 2014 Elsevier B.V., All rights reserved.; 5th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2013 ; Conference date: 02-12-2013 Through 05-12-2013",

year = "2013",

doi = "10.1109/CloudCom.2013.151",

language = "English (US)",

volume = "2",

pages = "293--298",

journal = "Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom",

issn = "2330-2194",

}

TY - JOUR

T1 - Adaptive live VM migration in share-nothing IaaS-clouds with LiveFS

AU - Katsipoulakis, Nick R.

AU - Tsakalozos, Konstantinos

AU - Delis, Alex

PY - 2013

Y1 - 2013

N2 - Live migration is a versatile option when it comes to attain load-balancing in IaaS-cloud architectures. Liveness, reliability and conformance to SLAs may all be achieved by moving a VM that creates excessive work from its current physical machine (PM) to a less busy node. Despite its promising features, live migration is an expensive operation in terms of resources. The situation gets further exacerbated when the movement involves PMs working off different file-systems which is often the case in shared-nothing IaaS-cloud infrastructures. In this paper, we suggest an approach that adapts the migration operation based on the I/O activity of the originating-VM. We introduce LiveFS, a FUSE-file system which traps all I/Os and helps determine how to best ship virtual disk segments across PMs in a share-nothing IaaS-cloud. Through prototyping and experimentation, we show that LiveFS can improve the shipment of VMs for diverse types of workloads. In particular, LiveFS succeeds in reducing the Total Migration Time by up to 64% compared to the "pre-copy" live migration technique. Furthermore during migration, we attain up-to 19% less I/O-delay if compared to the "post-copy" live-migration approach.

AB - Live migration is a versatile option when it comes to attain load-balancing in IaaS-cloud architectures. Liveness, reliability and conformance to SLAs may all be achieved by moving a VM that creates excessive work from its current physical machine (PM) to a less busy node. Despite its promising features, live migration is an expensive operation in terms of resources. The situation gets further exacerbated when the movement involves PMs working off different file-systems which is often the case in shared-nothing IaaS-cloud infrastructures. In this paper, we suggest an approach that adapts the migration operation based on the I/O activity of the originating-VM. We introduce LiveFS, a FUSE-file system which traps all I/Os and helps determine how to best ship virtual disk segments across PMs in a share-nothing IaaS-cloud. Through prototyping and experimentation, we show that LiveFS can improve the shipment of VMs for diverse types of workloads. In particular, LiveFS succeeds in reducing the Total Migration Time by up to 64% compared to the "pre-copy" live migration technique. Furthermore during migration, we attain up-to 19% less I/O-delay if compared to the "post-copy" live-migration approach.

KW - Cloud Storage

KW - Distributed Systems

KW - Share-Nothing IaaS Cloud

KW - Storage

UR - http://www.scopus.com/inward/record.url?scp=84899712930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899712930&partnerID=8YFLogxK

U2 - 10.1109/CloudCom.2013.151

DO - 10.1109/CloudCom.2013.151

M3 - Conference article

AN - SCOPUS:84899712930

SN - 2330-2194

VL - 2

SP - 293

EP - 298

JO - Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom

JF - Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom

M1 - 6735439

T2 - 5th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2013

Y2 - 2 December 2013 through 5 December 2013

ER -

Adaptive live VM migration in share-nothing IaaS-clouds with LiveFS

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this