Hybrid CPU Management for Adapting to the Diversity of Virtual Machines

As an important cornerstone for clouds, virtualization plays a vital role in building this emerging infrastructure. Virtual machines (VMs) with a variety of workloads may run simultaneously on a physical machine in the cloud platform. The scheduling algorithm used in Xen schedules virtual CPUs (VCPU...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on computers 2013-07, Vol.62 (7), p.1332-1344
Main Authors: Chuliang Weng, Minyi Guo, Yuan Luo, Minglu Li
Format: Article
Language:English
Subjects:
Central Processing Unit
cloud computing
cloud platform
Computers
concurrency control
concurrent application performance
CPU management
CPU time
emerging infrastructure
high-throughput application
hybrid CPU management method
hybrid scheduling framework
multi-threading
multithreaded program
near-native performance
Processor scheduling
proportional sharing method
Schedules
Scheduling
scheduling algorithm
synchronisation
Synchronization
synchronization operation
VCPU
virtual CPU scheduling
Virtual machine
virtual machine diversity
virtual machine monitor
Virtual machine monitors
virtual machines
virtualization
virtualized system
VMM
Xen
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As an important cornerstone for clouds, virtualization plays a vital role in building this emerging infrastructure. Virtual machines (VMs) with a variety of workloads may run simultaneously on a physical machine in the cloud platform. The scheduling algorithm used in Xen schedules virtual CPUs (VCPUs) of a VM asynchronously and guarantees the proportion of the CPU time allocated to the VM. This proportional sharing (PS) method is beneficial as it simplifies the implementation of CPU scheduling in the virtual machine monitor (VMM), and can deliver near-native performance for some workloads. However, when workloads in VMs are concurrent applications such as multithreaded programs with the synchronization operation, it has been demonstrated that this method in the VMM can reduce the performance, due to the negative impact of virtualization on synchronization. To address this issue, we present a hybrid scheduling framework for CPU management in the VMM to adapt to the diversity of VMs running simultaneously on a physical machine. We implement a hybrid scheduler based on Xen, and experimental results indicate that the hybrid CPU management method is feasible to mitigate the negative influence of virtualization on synchronization, and improve the performance of concurrent applications in the virtualized system, while maintaining the performance of high-throughput applications.
ISSN:0018-9340
1557-9956
DOI:10.1109/TC.2012.80