DocumentCode
244087
Title
CloudVMI: Virtual Machine Introspection as a Cloud Service
Author
Hyun Wook Baek ; Srivastava, Anurag ; van der Merwe, J.
Author_Institution
Univ. of Utah, Salt Lake City, UT, USA
fYear
2014
fDate
11-14 March 2014
Firstpage
153
Lastpage
158
Abstract
Virtual machine introspection (VMI) is a mechanism that allows indirect inspection and manipulation of the state of virtual machines. The indirection of this approach offers attractive isolation properties that has resulted in a variety of VMI-based applications dealing with security, performance, and debugging in virtual machine environments. Because it requires privileged access to the virtual machine monitor, VMI functionality is unfortunately not available to cloud users on public cloud platforms. In this paper, we present our work on the CloudVMI architecture to address this concern. CloudVMI virtualizes the VMI interface and makes it available as-a-service in a cloud environment. Because it allows introspection of users´ VMs running on arbitrary physical machines in a cloud environment, our VMI-as-a-service abstraction allows a new class of cloud-centric VMI applications to be developed. We present the design and implementation of CloudVMI in the Xen hypervisor environment. We evaluate our implementation using a number of VMI applications, including a simple application that illustrates the cross-physical machine capabilities of CloudVMI.
Keywords
cloud computing; virtual machines; CloudVMI architecture; VMI functionality; VMI-as-a-service abstraction; VMI-based applications; Xen hypervisor environment; cloud environment; cloud service; cloud-centric VMI applications; public cloud platforms; virtual machine environment; virtual machine introspection; virtual machine monitor; Cloud computing; Computer architecture; Libraries; Monitoring; Servers; Virtual machine monitors; Virtual machining;
fLanguage
English
Publisher
ieee
Conference_Titel
Cloud Engineering (IC2E), 2014 IEEE International Conference on
Conference_Location
Boston, MA
Type
conf
DOI
10.1109/IC2E.2014.82
Filename
6903469
Link To Document