Conducive Tracking, Monitoring, and Managing of Cloud Resources

Abstract

The development of Infrastructure as a Service structure brings new openings, which additionally goes with new difficulties in auto scaling, resource allocation, and security. A major test supporting these issues is the consistent tracking, monitoring and managing of cloud resources in the framework. In this paper, we propose ATOM, a capable and fruitful system to consequently track, screen, and oversee assets utilized as a part of an Infrastructure as a Service (IaaS) structure that is by and large used as a piece of cloud foundation. We utilize novel tracking technique to persistently track essential framework utilization measurements with low overhead,and build up a Principal Component Analysis (PCA) based way to deal with constantly monitor and consequently discover abnormalities in view of the approximated tracking results. We show how to dynamically set the tracking threshold based on the detection results, and further, how to adjust tracking algorithm to ensure its optimality under dynamic workloads. We exhibit the extensibility of ATOM through virtual machine (VM) clustering. In conclusion, when potential anomalies are recognized, we utilize introspection tools to perform memory forensics on VMs guided by analyzed results from tracking and monitoring to find malevolent behavior inside a VM. We assess the performance of our framework in an open source IaaS framework.