The assessment of benchmarks executed on bare-metal and using para-virtualization

A full assessment of para-­virtualization is important, because without knowledge about the various overheads, users can not understand whether using virtualization is a good idea or not. In this paper we are very interested in assessing the overheads of running various benchmarks on bare-­‐metal, as well as on para-­‐virtualization. The idea is to see what the overheads of para-­‐ virtualization are, as well as looking at the overheads of turning on monitoring and logging. The knowledge from assessing various benchmarks on these different systems will help a range of users understand the use of virtualization systems. In this paper we assess the overheads of using Xen, VMware, KVM and Citrix, see Table 1. These different virtualization systems are used extensively by cloud-­‐users. We are using various Netlib1 benchmarks, which have been developed by the University of Tennessee at Knoxville (UTK), and Oak Ridge National Laboratory (ORNL). In order to assess these virtualization systems, we run the benchmarks on bare-­‐metal, then on the para-­‐virtualization, and finally we turn on monitoring and logging. The later is important as users are interested in Service Level Agreements (SLAs) used by the Cloud providers, and the use of logging is a means of assessing the services bought and used from commercial providers. In this paper we assess the virtualization systems on three different systems. We use the Thamesblue supercomputer, the Hactar cluster and IBM JS20 blade server (see Table 2), which are all servers available at the University of Reading. A functional virtualization system is multi-­‐layered and is driven by the privileged components. Virtualization systems can host multiple guest operating systems, which run on its own domain, and the system schedules virtual CPUs and memory within each Virtual Machines (VM) to make the best use of the available resources. The guest-­‐operating system schedules each application accordingly. You can deploy virtualization as full virtualization or para-­‐virtualization. Full virtualization provides a total abstraction of the underlying physical system and creates a new virtual system, where the guest operating systems can run. No modifications are needed in the guest OS or application, e.g. the guest OS or application is not aware of the virtualized environment and runs normally. Para-­‐virualization requires user modification of the guest operating systems, which runs on the virtual machines, e.g. these guest operating systems are aware that they are running on a virtual machine, and provide near-­‐native performance. You can deploy both para-­‐virtualization and full virtualization across various virtualized systems. Para-­‐virtualization is an OS-­‐assisted virtualization; where some modifications are made in the guest operating system to enable better performance. In this kind of virtualization, the guest operating system is aware of the fact that it is running on the virtualized hardware and not on the bare hardware. In para-­‐virtualization, the device drivers in the guest operating system coordinate the device drivers of host operating system and reduce the performance overheads. The use of para-­‐virtualization [0] is intended to avoid the bottleneck associated with slow hardware interrupts that exist when full virtualization is employed. It has revealed [0] that para-­‐ virtualization does not impose significant performance overhead in high performance computing, and this in turn this has implications for the use of cloud computing for hosting HPC applications. The “apparent” improvement in virtualization has led us to formulate the hypothesis that certain classes of HPC applications should be able to execute in a cloud environment, with minimal performance degradation. In order to support this hypothesis, first it is necessary to define exactly what is meant by a “class” of application, and secondly it will be necessary to observe application performance, both within a virtual machine and when executing on bare hardware. A further potential complication is associated with the need for Cloud service providers to support Service Level Agreements (SLA), so that system utilisation can be audited.

Maximizing revenue in Grid markets using an economically enhanced resource manager

Traditional resource management has had as its main objective the optimization of throughput, based on parameters such as CPU, memory, and network bandwidth. With the appearance of Grid markets, new variables that determine economic expenditure, benefit and opportunity must be taken into account. The Self-organizing ICT Resource Management (SORMA) project aims at allowing resource owners and consumers to exploit market mechanisms to sell and buy resources across the Grid. SORMA's motivation is to achieve efficient resource utilization by maximizing revenue for resource providers and minimizing the cost of resource consumption within a market environment. An overriding factor in Grid markets is the need to ensure that the desired quality of service levels meet the expectations of market participants. This paper explains the proposed use of an economically enhanced resource manager (EERM) for resource provisioning based on economic models. In particular, this paper describes techniques used by the EERM to support revenue maximization across multiple service level agreements and provides an application scenario to demonstrate its usefulness and effectiveness. Copyright © 2008 John Wiley & Sons, Ltd.

On the Use of Agents in a Bioinformatics Grid

MyGrid is an e-Science Grid project that aims to help biologists and bioinformaticians to perform workflow-based in silico experiments, and help them to automate the management of such workflows through personalisation, notification of change and publication of experiments. In this paper, we describe the architecture of myGrid and how it will be used by the scientist. We then show how myGrid can benefit from agents technologies. We have identified three key uses of agent technologies in myGrid: user agents, able to customize and personalise data, agent communication languages offering a generic and portable communication medium, and negotiation allowing multiple distributed entities to reach service level agreements.

Análise de contratos de tecnologia da informação (TI)

Organizações de TI deparam-se com problemas em contratos de TI (produtos e serviços) tais como: definição inadequada ou insuficiente dos produtos/serviços contratados; indefinição de responsabilidades; SLAs (Service Level Agreements) inadequados ou inexistentes; ausência ou inadequação de cláusulas de penalidades e métodos claros e objetivos de mensuração dos produtos/serviços entregues; sobreposição ou lacunas entre contratos de diferentes fornecedores

Un sistema di monitoring SLA a livello applicativo

In questo lavoro si vuole studiare il problema del monitoring di quei parametri del SLA che riguardano aspetti definiti a livello applicativo, nei contesti dell’erogazione di servizi business-to-business.

Dynamic SLA management with forecasting using multi-objective optimization

Cost-efficient operation while satisfying performance and availability guarantees in Service Level Agreements (SLAs) is a challenge for Cloud Computing, as these are potentially conflicting objectives. We present a framework for SLA management based on multi-objective optimization. The framework features a forecasting model for determining the best virtual machine-to-host allocation given the need to minimize SLA violations, energy consumption and resource wasting. A comprehensive SLA management solution is proposed that uses event processing for monitoring and enables dynamic provisioning of virtual machines onto the physical infrastructure. We validated our implementation against serveral standard heuristics and were able to show that our approach is significantly better.

Cloud-based Orchestration of Multimedia Services and Applications

The Mobile Cloud Networking project develops among others, several virtualized services and applications, in particular: (1) IP Multimedia Subsystem as a Service that gives the possibility to deploy a virtualized and on-demand instance of the IP Multimedia Subsystem platform, (2) Digital Signage Service as a Service that is based on a re-designed Digital Signage Service architecture, adopting the cloud computing principles, and (3) Information Centric Networking/Content Delivery Network as a Service that is used for distributing, caching and migrating content from other services. Possible designs for these virtualized services and applications have been identified and are being implemented. In particular, the architectures of the mentioned services were specified, adopting cloud computing principles, such as infrastructure sharing, elasticity, on-demand and pay-as-you-go. The benefits of Reactive Programming paradigm are presented in the context of Interactive Cloudified Digital Signage services in a Mobile Cloud Platform, as well as the benefit of interworking between different Mobile Cloud Networking Services as Digital Signage Service and Content Delivery Network Service for better performance of Video on Demand content deliver. Finally, the management of Service Level Agreements and the support of rating, charging and billing has also been considered and defined.

Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications

Cloud Computing has evolved to become an enabler for delivering access to large scale distributed applications running on managed network-connected computing systems. This makes possible hosting Distributed Enterprise Information Systems (dEISs) in cloud environments, while enforcing strict performance and quality of service requirements, defined using Service Level Agreements (SLAs). {SLAs} define the performance boundaries of distributed applications, and are enforced by a cloud management system (CMS) dynamically allocating the available computing resources to the cloud services. We present two novel VM-scaling algorithms focused on dEIS systems, which optimally detect most appropriate scaling conditions using performance-models of distributed applications derived from constant-workload benchmarks, together with SLA-specified performance constraints. We simulate the VM-scaling algorithms in a cloud simulator and compare against trace-based performance models of dEISs. We compare a total of three SLA-based VM-scaling algorithms (one using prediction mechanisms) based on a real-world application scenario involving a large variable number of users. Our results show that it is beneficial to use autoregressive predictive SLA-driven scaling algorithms in cloud management systems for guaranteeing performance invariants of distributed cloud applications, as opposed to using only reactive SLA-based VM-scaling algorithms.

Methodology for developing and application outsourcing in the cloud using SOA

New technologies such as, the new Information and Communication Technology ICT, break new paths and redefines the way we understand business, the Cloud Computing is one of them. The on demand resource gathering and the per usage payment scheme are now commonplace, and allows companies to save on their ICT investments. Despite the importance of this issue, we still lack methodologies that help companies, to develop applications oriented for its exploitation in the Cloud. In this study we aim to fill this gap and propose a methodology for the development of ICT applications, which are directed towards a business model, and further outsourcing in the Cloud. In the former the Development of SOA applications, we take, as a baseline scenario, a business model from which to obtain a business process model. To this end, we use software engineering tools; and in the latter The Outsourcing we propose a guide that would facilitate uploading business models into the Cloud; to this end we describe a SOA governance model, which controls the SOA. Additionally we propose a Cloud government that integrates Service Level Agreements SLAs, plus SOA governance, and Cloud architecture. Finally we apply our methodology in an example illustrating our proposal. We believe that our proposal can be used as a guide/pattern for the development of business applications.

Cloud adoption:prioritizing obstacles and obstacles resolution tactics using AHP

The enormous potential of cloud computing for improved and cost-effective service has generated unprecedented interest in its adoption. However, a potential cloud user faces numerous risks regarding service requirements, cost implications of failure and uncertainty about cloud providers' ability to meet service level agreements. These risks hinder the adoption of cloud. We extend the work on goal-oriented requirements engineering (GORE) and obstacles for informing the adoption process. We argue that obstacles prioritisation and their resolution is core to mitigating risks in the adoption process. We propose a novel systematic method for prioritising obstacles and their resolution tactics using Analytical Hierarchy Process (AHP). We provide an example to demonstrate the applicability and effectiveness of the approach. To assess the AHP choice of the resolution tactics we support the method by stability and sensitivity analysis. Copyright 2014 ACM.

Improving resource management in virtualized data centers using application performance models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity.^ We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. ^ This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.^

Extensões na arquitetura SDN para o provisionamento de QoS através do monitoramento e uso de múltiplos caminhos

The substantial increase in the number of applications offered through the computer networks, as well as in the volume of traffic forwarded through the network, have hampered to assure adequate service level to users. The Quality of Service (QoS) offer, honoring specified parameters in Service Level Agreements (SLA), established between the service providers and their clients, composes a traditional and extensive computer networks’ research area. Several schemes proposals for the provision of QoS were presented in the last three decades, but the acting scope of these proposals is always limited due to some factors, including the limited development of the network hardware and software, generally belonging to a single manufacturer. The advent of Software Defined Networking (SDN), along with the maturation of its main materialization, the OpenFlow protocol, allowed the decoupling between network hardware and software, through an architecture which provides a control plane and a data plane. This eases the computer networks scenario, allowing that new abstractions are applied in the hardware composing the data plane, through the development of new software pieces which are executed in the control plane. This dissertation investigates the QoS offer through the use and extension of the SDN architecture. Based on the proposal of two new modules, one to perform the data plane monitoring, SDNMon, and the second, MP-ROUTING, developed to determine the use of multiple paths in the forwarding of data referring to a flow, we demonstrated in this work that some QoS metrics specified in the SLAs, such as bandwidth, can be honored. Both modules were implemented and evaluated through a prototype. The evaluation results referring to several aspects of both proposed modules are presented in this dissertation, showing the obtained accuracy of the monitoring module SDNMon and the QoS gains due to the utilization of multiple paths defined by the MP-Routing, when forwarding data flow through the SDN.

The Importance of Proper Measurement for a Cloud Security Assurance Model

Winner of a best paper award.

Information Security in the Cloud: Should We be Using a Different Approach?

Postprint

Improving Resource Management in Virtualized Data Centers using Application Performance Models

The rapid growth of virtualized data centers and cloud hosting services is making the management of physical resources such as CPU, memory, and I/O bandwidth in data center servers increasingly important. Server management now involves dealing with multiple dissimilar applications with varying Service-Level-Agreements (SLAs) and multiple resource dimensions. The multiplicity and diversity of resources and applications are rendering administrative tasks more complex and challenging. This thesis aimed to develop a framework and techniques that would help substantially reduce data center management complexity. We specifically addressed two crucial data center operations. First, we precisely estimated capacity requirements of client virtual machines (VMs) while renting server space in cloud environment. Second, we proposed a systematic process to efficiently allocate physical resources to hosted VMs in a data center. To realize these dual objectives, accurately capturing the effects of resource allocations on application performance is vital. The benefits of accurate application performance modeling are multifold. Cloud users can size their VMs appropriately and pay only for the resources that they need; service providers can also offer a new charging model based on the VMs performance instead of their configured sizes. As a result, clients will pay exactly for the performance they are actually experiencing; on the other hand, administrators will be able to maximize their total revenue by utilizing application performance models and SLAs. This thesis made the following contributions. First, we identified resource control parameters crucial for distributing physical resources and characterizing contention for virtualized applications in a shared hosting environment. Second, we explored several modeling techniques and confirmed the suitability of two machine learning tools, Artificial Neural Network and Support Vector Machine, to accurately model the performance of virtualized applications. Moreover, we suggested and evaluated modeling optimizations necessary to improve prediction accuracy when using these modeling tools. Third, we presented an approach to optimal VM sizing by employing the performance models we created. Finally, we proposed a revenue-driven resource allocation algorithm which maximizes the SLA-generated revenue for a data center.