Host Physical Machines Research Articles

AVDR: A Framework for Migration Policy to Handle DDoS Attacked VM in Cloud

The recent trends of Distributed Denial of Service (DDoS) attacks in cloud computing have revealed a new menace of DDoS attacks called collateral damages on non-target stakeholders. These stakeholders are victim Virtual Machine (VM), sibling VMs, host physical machine, other host physical machines, VMs on other host machine, users of attacked and co-hosted VMs, cloud providers and cloud customer. The main reason behind these collateral damages are the features of cloud like virtualization, auto-scaling, resource sharing, and migrations. During the DDoS attacks due to the massive number of requests, it will result in host overload situation. In cloud, this overload situation is handled by various existing migration policies. These simple migration policies are not efficient if the attacked VMs are present in the cloud network. Therefore a supporting framework, Attacked VM Detection and Recovery (AVDR) is proposed in this work. Proposed AVDR framework improves the performance of existing migration policies and reduces the collateral damages. The AVDR framework is based on attack strength ‘ $$Y_{as}$$ ’, thus a linear model to evaluate ‘ $$Y_{as}$$ ’ is also proposed. The dataset used for the modeling of ‘ $$Y_{as}$$ ’ is generated over the VM instances created on AWS. It consists of both the attack as well as benign request traces. The results prove the effectiveness of the proposed work.

Energy-aware virtual machine allocation for cloud with resource reservation

To reduce the price of pay-as-you-go style cloud applications, an increasing number of cloud service providers offer resource reservation-based services that allow tenants to customize their virtual machines (VMs) with specific time windows and physical resources. However, due to the lack of efficient management of reserved services, the energy efficiency of host physical machines cannot be guaranteed. In today’s highly competitive cloud computing market, such low energy efficiency will significantly reduce the profit margin of cloud service providers. Therefore, how to explore energy efficient VM allocation solutions for reserved services to achieve maximum profit is becoming a key issue for the operation and maintenance of cloud computing. To address this problem, this paper proposes a novel and effective evolutionary approach for VM allocation that can maximize the energy efficiency of a cloud data center while incorporating more reserved VMs. Aiming at accurate energy consumption estimation, our approach needs to simulate all the VM allocation updates, which is time-consuming using traditional cloud simulators. To overcome this, we have designed a simplified simulation engine for CloudSim that can accelerate the process of our evolutionary approach. Comprehensive experimental results obtained from both simulation on CloudSim and real cloud environments show that our approach not only can quickly achieve an optimized allocation solution for a batch of reserved VMs, but also can consolidate more VMs with fewer physical machines to achieve better energy efficiency than existing methods. To be specific, the overall profit improvement and energy savings achieved by our approach can be up to 24% and 41% as compared to state-of-the-art methods, respectively. Moreover, our approach could enable the cloud data center to serve more tenant requests.

Shadow-Routing Based Dynamic Algorithms for Virtual Machine Placement in a Network Cloud

We consider a shadow routing based approach to the problem of real-time adaptive placement of virtual machines (VM) in large data centers (DC) within a network cloud. Such placement in particular has to respect vector packing constraints on the allocation of VMs to host physical machines (PM) within a DC, because each PM can potentially serve multiple VMs simultaneously. Shadow routing is attractive in that it allows a large variety of system objectives and/or constraints to be treated within a common framework (as long as the underlying optimization problem is convex). Perhaps even more attractive feature is that the corresponding algorithm is very simple to implement, it runs continuously, and adapts automatically to changes in the VM demand rates, changes in system parameters, etc., without the need to re-solve the underlying optimization problem “from scratch”. In this paper we focus on the min-max-DC-load problem. Namely, we propose a combined VM-to-DC routing and VM-to-PM assignment algorithm, referred to as Shadow scheme, which minimizes the maximum of appropriately defined DC utilizations. We prove that the Shadow scheme is asymptotically optimal (as one of its parameters goes to 0). Simulation confirms good performance and high adaptivity of the algorithm. Favorable performance is also demonstrated in comparison with a baseline algorithm based on VMware implementation [7], [8]. We also propose a simplified - “more distributed” - version of the Shadow scheme, which performs almost as well in simulations.

Performance Analysis for Pareto-Optimal Green Consolidation Based on Virtual Machines Live Migration

Huge energy requirement of cloud data centers is prime concern. Dynamic Virtual Machine (VM) consolidation based on VM live migration to switched-off or put some of the under-loaded host Physical Machines (PMs) into a low power consumption mode can significantly save energy in data centers and achieve green cloud computing. Performance overheads imposed on source and destination hosts during and after VM live migration is the main focus of research. Existing VM consolidation approaches are inefficient regarding VM live migration time, application downtime, VM pre and post-migration overheads which results in Quality of Service (QoS) degradation. So, near-optimal solution which optimizes these overheads is main challenge. This paper discusses the causes of VM live migration performance overheads and comparison of different overhead optimization techniques on the basis of parameters like accuracy and migration cost. Pareto-Optimal solution is proposed to eliminate the VM performance overheads.

Handling Boot Storms in Virtualized Data Centers—A Survey

Large-scale virtual machine (VM) deployment in virtualized data centers is a very slow process. This is primarily due to the resource bottlenecks that are created at the storage, network, and host physical machines when a large number of VMs are requested simultaneously. For companies that provide virtual desktops to their employees, it is common to encounter such requests each day, when their employees turn up for work. In addition, a large number of VMs are often required to be deployed instantly, in order to absorb a spike in the workload, at online e-commerce websites. In such scenarios, long deployment times are unacceptable, and reducing them is of paramount importance. In this article, we first abstract out the key techniques suggested in the literature to speed up this deployment process. We follow this with a classification of these techniques into a taxonomy and propose a framework that can be used to compare them. Finally, we identify problem areas that warrant further research and bring out the shortcomings of the current state-of-the-art solutions.

Replica allocation policy of cloudy services based on social network properties

To improve the running efficiency of business workflow in cloud environment,a policy of replica allocation of cloudy services was proposed.Taking the advantage of social network analysis,the policy specified the central service nodes in a service network based on mining the social network properties such as connectivity and centralization for a service community.The host physical machine of the replica of the central service was specified according to the analysis of logical sequence between the central service and its pre-service,and the usage of other physical machines.The analysis and simulation show that the policy can improve the running efficiency of data intensive business workflow in a cloud environment by averaging the overload of physical machine and reducing the time wasted by long-distance service interaction.