HERO vs. Zombie: Identifying Zombie Guests in a Virtual Machine Environment

Yael Elinav, Alex Moshinky, Lior Siag, Nezer Jacob Zaidenberg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Virtual servers are important in many data-centers. Multiple guest virtual machines are consolidated on several hosts on-site or on the cloud, and serve the organization’s computational needs. However, virtual machines not cleared from the system, known as zombie machines, waste resources and pose a security risk. We present a novel tool to optimize resource use by tracking down zombie machines: HERO (Host Environment Resource Optimization). HERO leverages multiple testing approaches and machine learning to assist system administrators in locating “zombie” machines.

Original languageEnglish
Title of host publicationMODELSWARD 2021 - Proceedings of the 9th International Conference on Model-Driven Engineering and Software Development
EditorsEdwin Seidewitz, Luís Ferreira Pires, Slimane Hammoudi
PublisherScience and Technology Publications, Lda
Pages240-245
Number of pages6
ISBN (Print)9789897584879
DOIs
StatePublished - 1 Jan 2021
Externally publishedYes
Event9th International Conference on Model-Driven Engineering and Software Development, MODELSWARD 2021 - Virtual, Online
Duration: 8 Feb 202110 Feb 2021

Publication series

NameInternational Conference on Model-Driven Engineering and Software Development
ISSN (Electronic)2184-4348

Conference

Conference9th International Conference on Model-Driven Engineering and Software Development, MODELSWARD 2021
CityVirtual, Online
Period8/02/2110/02/21

Keywords

  • Green Computing
  • Inactive Virtual Machines
  • Remote Management
  • System Administration
  • Virtual Machines
  • Virtualization Sprawling

ASJC Scopus subject areas

  • Software
  • Engineering (miscellaneous)

Fingerprint

Dive into the research topics of 'HERO vs. Zombie: Identifying Zombie Guests in a Virtual Machine Environment'. Together they form a unique fingerprint.

Cite this