Combining batch execution and leasing using virtual machines

Sotomayor, Borja; Keahey, Kate; Foster, Ian

doi:10.1145/1383422.1383434

Cited by 191 publications

(93 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Two extensions of this framework address issues such as energy consumption (the Green Cloud Scheduler [14]) or advance reservation (the Haizea scheduler [15]) in data centers. Haizea is a resource manager used either as a simulator or as a backend VM scheduler for OpenNebula [15,23,24,25,26]. Haizea defines different types of leases implemented as virtual machines [26], uses off-line VMs migration, and considers the VM management time overheads.…”

Section: Related Workmentioning

confidence: 99%

“…This means that by removing the selected VMs, A CPU becomes greater than or equal to zero. Second, the list of selected VMs is scanned backwards and the VMs which are still not causing the host overload are restored (lines [17][18][19][20][21][22][23][24][25][26][27][28]. The VMs suspended from each overloaded host are appended to the SV list (line 30).…”

Section: 32mentioning

confidence: 99%

See 1 more Smart Citation

A Filter-Based Dynamic Resource Management Framework for Virtualized Data Centers

Crăciun

Salomie

2017

Studia UBB Informatica

View full text Add to dashboard Cite

Abstract. Data centers adapt their operation to changing run-time conditions using energy-aware and SLA-compliant resource management techniques. In this context, current paper presents a novel filter-based dynamic resource management framework for virtualized data centers. By choosing and combining properly software filters performing the scheduling and resource management operations, the framework may be used in what-if analysis. The framework is evaluated by simulation for deploying batch best-effort jobs with time-varying CPU requirements.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: 32mentioning

confidence: 99%

A Filter-Based Dynamic Resource Management Framework for Virtualized Data Centers

Crăciun

Salomie

2017

Studia UBB Informatica

View full text Add to dashboard Cite

show abstract

“…In our case, grid resources are modeled by virtual machine requirements like in [7]. A job is composed of a set of virtual machines which will be executed on the infrastructure, it is then called a virtual job or vjob (called lease in other works [16]. Each user belongs to a virtual organization (VO).…”

Section: Specification Of Grid Architecturesmentioning

confidence: 99%

A Reconfiguration Language for Virtualized Grid Infrastructures

Pottier¹,

Léger²,

Menaud³

2010

Distributed Applications and Interoperable Systems

View full text Add to dashboard Cite

Abstract. The growing needs in computational power to answer to the increasing number of on-line services and the complexity of applications makes it mandatory to build corresponding hardware infrastructures and to share several distributed hardware and software resources thanks to grid computing. To help with optimizing resource utilization, system virtualization is a more and more adopted technique in data centers. However, this software layer adds to the administration complexity of servers and it requires specific management tools to deal with hypervisor functionalities like live migration. To address this problem, we propose VMScript, a domain specific language for administration of virtualized grid infrastructures. This language relies on set manipulation and is used to introspect physical and virtual grid architectures thanks to query expressions and notably to modify VM placement on machines.

show abstract

“…One of the schedulers already available for OpenNebula is the Haizea [8,6] scheduler. The VM operations available to the scheduler are shutdown, start, suspend and resume.…”

Section: Vm Management Model and Simulation Frameworkmentioning

confidence: 99%

Multiplexing Low and High QoS Workloads in Virtual Environments

Verboven

Vanmechelen

Broeckhove

2010

Job Scheduling Strategies for Parallel Processing

View full text Add to dashboard Cite

Abstract. Virtualization technology has introduced new ways for managing IT infrastructure. The flexible deployment of applications through self-contained virtual machine images has removed the barriers for multiplexing, suspending and migrating applications with their entire execution environment, allowing for a more efficient use of the infrastructure. These developments have given rise to an important challenge regarding the optimal scheduling of virtual machine workloads. In this paper, we specifically address the VM scheduling problem in which workloads that require guaranteed levels of CPU performance are mixed with workloads that do not require such guarantees. We introduce a framework to analyze this scheduling problem and evaluate to what extent such mixed service delivery is beneficial for a provider of virtualized IT infrastructure. Traditionally providers offer IT resources under a guaranteed and fixed performance profile, which can lead to underutilization. The findings of our simulation study show that through proper tuning of a limited set of parameters, the proposed scheduling algorithm allows for a significant increase in utilization without sacrificing on performance dependability.

show abstract

Combining batch execution and leasing using virtual machines

Cited by 191 publications

References 39 publications

A Filter-Based Dynamic Resource Management Framework for Virtualized Data Centers

A Filter-Based Dynamic Resource Management Framework for Virtualized Data Centers

A Reconfiguration Language for Virtualized Grid Infrastructures

Multiplexing Low and High QoS Workloads in Virtual Environments

Contact Info

Product

Resources

About