Resource management for Infrastructure as a Service (IaaS) in cloud computing: A survey

Abstract

The cloud phenomenon is quickly becoming an important service in Internet computing. Infrastructure as a Service (IaaS) in cloud computing is one of the most significant and fastest growing field. In this service model, cloud providers offer resources to users/machines that include computers as virtual machines, raw (block) storage, firewalls, load balancers, and network devices. One of the most pressing issues in cloud computing for IaaS is the resource management. Resource management problems include allocation, provisioning, requirement mapping, adaptation, discovery, brokering, estimation, and modeling. Resource management for IaaS in cloud computing offers following benefits: scalability, quality of service, optimal utility, reduced overheads, improved throughput, reduced latency, specialized environment, cost effectiveness and simplified interface. This paper focuses on some of the important resource management techniques such as resource provisioning, resource allocation, resource mapping and resource adaptation. It brings out an exhaustive survey of such techniques for IaaS in cloud computing, and also put forth the open challenges for further research.

Introduction

A cloud is defined as a place over network infrastructure where information technology (IT) and computing resources such as computer hardware, operating systems, networks, storage, databases, and even entire software applications are available instantly, on-demand as given in Buyya and Ranjan (2011). Cloud computing is the use of cloud resources (hardware and software) that are delivered as a service over a network (typically the Internet). While cloud computing may not involve a lot of new technologies, it certainly represents a new way of managing IT. In many cases, this will not only change the workflow within the IT organization, it will often result in a complete reorganization of the IT department. Cost savings and scalability can be highly achieved from cloud computing.

Cloud computing is often compared with Service Oriented Architectures (SOA), Grid, Utility and Cluster computing as in http://cloudcomputing.sys-con.com. Cloud computing and SOA can be pursued independently or concurrently where cloud computing's platform and storage service offerings can provide a value added underpinning for SOA's efforts as in Dai and Rubin (2012). Cloud computing does not replace SOA or the use of distributed software's components as an integration technology. With grid computing, we can provision computing resources as a utility that can be turned on or off. Cloud computing goes one step further with on-demand resource provisioning. This eliminates over-provisioning when used with utility pricing. It also removes the need to over-provision in order to meet the demands of millions of users. Utility computing is paying for what we use on shared servers like we pay for a public utility (such as electricity, gas) as in http://www.ibm.com.

Clustering is the use of multiple computers, typically PCs or UNIX workstations, multiple storage devices, and redundant interconnections, to form what appears to users as a single highly available system. Cluster computing is a low-cost form of parallel processing for scientific and other applications that lend themselves to parallel operations. The summary of the features of each of the computing techniques is listed in Table 1.

Clouds can be broadly classified as follows:

• Infrastructures as a Service (IaaS).

• Platforms as a Service (PaaS).

• Software as a Service (SaaS).

IaaS refers to a combination of hosting, hardware provisioning and basic services needed to run a cloud. PaaS refers to the provision of a computing platform and the provision and deployment of the associated set of software applications (called a solution stack) to an enterprise by a cloud provider. Software as a Service (SaaS) is a software distribution model in which applications are hosted by a vendor or service provider and made available to customers over a network.

The uses of IaaS are as follows. (1) Provides access to shared resources on need basis, without revealing details like location and hardware to clients, (2) provides details like server images on demand, storage, queuing, and information about other resources, among others, and (3) offers full control of server infrastructure, not limited specifically to applications, instances and containers.

The major issues that are commonly associated with IaaS in cloud systems are resource management, network infrastructure management, virtualization and multi-tenancy, data management, application programming interfaces (APIs), interoperability, etc. These issues are briefly discussed in Section 2. This paper focuses on resource management due to the fact that resource management for IaaS in cloud computing offers following benefits: scalability, Quality of Service (QoS), specialized environment, reduction in overheads and latency, improved throughput, cost effectiveness and simplified interface. This paper focuses on survey of some of the important resource management schemes such as resource mapping, resource provisioning, resource allocation, and resource adaptation. It brings out an exhaustive survey of such schemes for IaaS in cloud computing, and also put forth the open challenges for further research.

Our contributions in the paper are as follows. (1) Classification of resource management schemes into resource provisioning, resource allocation, resource adaptation, resource mapping, resource modeling, resource estimation and resource brokering. (2) Bringing out exhaustive works in resource mapping, resource provisioning, resource allocation, and resource adaptation. Scheme's operation and drawbacks are presented with comparative analysis in terms of performance metrics such as reliability, deployment, QoS, delay and overheads. (3) Providing open challenges in each considered class of resource management, and (4) to facilitate novice researchers to work on the research problems.

The rest of the paper is organized as follows. In Section 2, we discuss different issues in IaaS. Resource management problems in IaaS are presented in Section 3. Tools and technologies for resource management in cloud computing are discussed in Section 4. Some solutions for resource management are given in Section 5. Finally, concluding remarks are presented in Section 6.