Cluster security with NVisionCC: process monitoring by leveraging emergent properties

  • Authors:

  • G. A. Koenig;Xin Meng;A. J. Lee;M. Treaster;N. Kiyanclar;W. Yurcik

  • Affiliations:

  • Nat. Center for Supercomput. Applications, Illinois Univ., Urbana-Champaign, IL, USA;Nat. Center for Supercomput. Applications, Illinois Univ., Urbana-Champaign, IL, USA;Nat. Center for Supercomput. Applications, Illinois Univ., Urbana-Champaign, IL, USA;Nat. Center for Supercomput. Applications, Illinois Univ., Urbana-Champaign, IL, USA;Nat. Center for Supercomput. Applications, Illinois Univ., Urbana-Champaign, IL, USA;Nat. Center for Supercomput. Applications, Illinois Univ., Urbana-Champaign, IL, USA

  • Venue:
  • CCGRID '05 Proceedings of the Fifth IEEE International Symposium on Cluster Computing and the Grid - Volume 01
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

We have observed that supercomputing clusters made up of commodity off-the-shelf computers possess emergent properties that are apparent when these systems are considered as an indivisible entity rather than as a collection of independent nodes. By exploiting predicatable characteristics inherent to supercomputing clusters coupled with these emergent properties, we propose several mechanisms by which cluster security may be enhanced. In this paper, we describe NVisionCC, a cluster security tool that monitors processes across cluster nodes and raises alerts when deviations from a predefined profile of expected processes are noted. Additionally, we demonstrate that the monitoring infrastructure used by NVisionCC incurs a negligible performance penalty on the computational and network resources of the cluster.