Riccardo Lancellotti

Performance Evolution of Mobile Web-Based Services

The mobile Webs widespread diffusion opens many interesting design and management issues about server infrastructures that must satisfy present and future client demand. Future mobile Web-based services will have growing computational costs. Even requests for the same Web resource will require services to dynamically generate content that takes into account specific devices, user profiles, and contexts. The authors consider the evolution of the mobile Web workload and trends in server and client devices with the goal of anticipating future bottlenecks and developing management strategies.

Adaptive Computing-plus-Communication Optimization Framework for Multimedia Processing in Cloud Systems

A clear trend in the evolution of network-based services is the ever-increasing amount of multimedia data involved. This trend towards big-data multimedia processing finds its natural placement together with the adoption of the cloud computing paradigm, that seems the best solution to cope with the demands of a highly fluctuating workload that characterizes this type of services. However, as cloud data centers become more and more powerful, energy consumption becomes a major challenge both for environmental concerns and for economic reasons. An effective approach to improve energy efficiency in cloud data centers is to rely on traffic engineering techniques to dynamically adapt the number of active servers to the current workload. Towards this aim, we propose a joint computing-plus-communication optimization framework exploiting virtualization technologies, called MMGreen. Our proposal specifically addresses the typical scenario of multimedia data processing with computationally intensive tasks and exchange of a big volume of data. The proposed framework not only ensures users the Quality of Service (through Service Level Agreements), but also achieves maximum energy saving and attains green cloud computing goals in a fully distributed fashion by utilizing the DVFS-based CPU frequencies. To evaluate the actual effectiveness of the proposed framework, we conduct experiments with MMGreen under real-world and synthetic workload traces. The results of the experiments show that MMGreen may significantly reduce the energy cost for computing, communication and reconfiguration with respect to the previous resource provisioning strategies, respecting the SLA constraints.

Cooperative architectures and algorithms for discovery and transcoding of multi-version content

A clear trend of the Web is that a variety of new consumer devices with diverse processing powers, display capabilities, and network connections is gaining access to the Internet. Tailoring Web content to match the device characteristics requires functionalities for content transformation, namely transcoding, that are typically carried out by the content provider or by some proxy server at the edge. In this paper, we propose an alternative solution consisting of an intermediate infrastructure of distributed servers which collaborate in discovering, transcoding, and delivering multiple versions of Web resources to the clients. We investigate different algorithms for cooperative discovery and transcoding in the context of this intermediate infrastructure where the servers are organized in hierarchical and flat peer-to-peer topologies. We compare the performance of the proposed schemes through a flexible prototype that implements all proposed mechanisms.

Automatic virtual machine clustering based on bhattacharyya distance for multi-cloud systems

Size and complexity of modern data centers pose scalability issues for the resource monitoring system supporting management operations, such as server consolidation. When we pass from cloud to multi-cloud systems, scalability issues are exacerbated by the need to manage geographically distributed data centers and exchange monitored data across them. While existing solutions typically consider every Virtual Machine (VM) as a black box with independent characteristics, we claim that scalability issues in multi-cloud systems could be addressed by clustering together VMs that show similar behaviors in terms of resource usage. In this paper, we propose an automated methodology to cluster VMs starting from the usage of multiple resources, assuming no knowledge of the services executed on them. This innovative methodology exploits the Bhattacharyya distance to measure the similarity of the probability distributions of VM resources usage, and automatically selects the most relevant resources to consider for the clustering process. The methodology is evaluated through a set of experiments with data from a cloud provider. We show that our proposal achieves high and stable performance in terms of automatic VM clustering. Moreover, we estimate the reduction in the amount of data collected to support system management in the considered scenario, thus showing how the proposed methodology may reduce the monitoring requirements in multi-cloud systems.

Analysis of peer-to-peer systems: workload characterization and effects on traffic cacheability

Peer-to-peer file sharing networks have emerged as a new popular application in the Internet scenario. We provide an analytical model of the resource size and of the contents shared at a given node. We also study the composition of the content workload hosted in the Gnutella network over time. Finally, we investigate the negative impact of oversimplified hypotheses (e.g., the use of filenames as resource identifiers) on the potentially achievable hit rate of a file-sharing cache. It is clear from our findings that file sharing traffic can be reduced by using a cache to minimize download time and network usage. The design and tuning of the cache server should take into account the presence of different resources sharing the same name and should consider push-based downloads. Failing to do so can result in reduced effectiveness of the caching mechanism.

Improving Scalability of Cloud Monitoring Through PCA-Based Clustering of Virtual Machines

Cloud computing has recently emerged as a leading paradigm to allow customers to run their applications in virtualized large-scale data centers. Existing solutions for monitoring and management of these infrastructures consider virtual machines (VMs) as independent entities with their own characteristics. However, these approaches suffer from scalability issues due to the increasing number of VMs in modern cloud data centers. We claim that scalability issues can be addressed by leveraging the similarity among VMs behavior in terms of resource usage patterns. In this paper we propose an automated methodology to cluster VMs starting from the usage of multiple resources, assuming no knowledge of the services executed on them. The innovative contribution of the proposed methodology is the use of the statistical technique known as principal component analysis (PCA) to automatically select the most relevant information to cluster similar VMs. We apply the methodology to two case studies, a virtualized testbed and a real enterprise data center. In both case studies, the automatic data selection based on PCA allows us to achieve high performance, with a percentage of correctly clustered VMs between 80% and 100% even for short time series (1 day) of monitored data. Furthermore, we estimate the potential reduction in the amount of collected data to demonstrate how our proposal may address the scalability issues related to monitoring and management in cloud computing data centers.

Content Adaptation Architectures Based on Squid Proxy Server

The overwhelming popularity of Internet and the technology advancements have determined the diffusion of many different Web-enabled devices. In such an heterogeneous client environment, efficient content adaptation and delivery services are becoming a major requirement for the new Internet service infrastructure. In this paper we describe intermediary-based architectures that provide adaptation and delivery of Web content to different user terminals. We present the design of a Squid-based prototype that carries out the adaptation of Web images and combines such a functionality with the caching of multiple versions of the same resource. We also investigate how to provide some form of cooperation among the nodes of the intermediary infrastructure, with the goal to evaluate to what extent the cooperation in discovering, adapting, and delivering Web resources can improve the user-perceived performance.

Characteristics and evolution of content popularity and user relations in social networks

Social networks have changed the characteristics of the traditional Web and these changes are still ongoing. Nowadays, it is impossible to design valid strategies for content management, information dissemination and marketing in the context of a social network system without considering the popularity of its content and the characteristics of the relations among its users. By analyzing two popular social networks and comparing current results with studies dating back to 2007, we confirm some previous results and we identify novel trends that can be utilized as a basis for designing appropriate content and system management strategies. Our analyses confirm the growth of the two social networks in terms of quantity of contents and numbers of social links among the users. The social navigation is having an increasing influence on the content popularity because the social links are representing a primary method through which the users search and find contents. An interesting novel trend emerging from our study is that subsets of users have major impact on the content popularity with respect to previous analyses, with evident consequences on the possibility of implementing content dissemination strategies, such as viral marketing1.

A distributed architecture of edge proxy servers for cooperative transcoding

The large variety of devices that are gaining access to the Internet requires novel server functionalities to tailor Web content at run-time, namely transcoding. Traditional schemes assign transcoding operations to the Web server or single edge proxies. We propose an alternative architecture consisting of cooperative proxy servers which collaborate in discovering and transcoding multiple versions of Web objects. The transcoding functionality opens an entirely new space of investigation in the research area of cache cooperation, because it transforms the proxy servers from content repositories into pro-active network elements providing computation and adaptive delivery. We investigate and evaluate experimentally different schemes for cooperative discovery of multiversion content and transcoding in the context of a flat topology of edge servers.

Exploiting ensemble techniques for automatic virtual machine clustering in cloud systems

Cloud computing has recently emerged as a new paradigm to provide computing services through large-size data centers where customers may run their applications in a virtualized environment. The advantages of cloud in terms of flexibility and economy encourage many enterprises to migrate from local data centers to cloud platforms, thus contributing to the success of such infrastructures. However, as size and complexity of cloud infrastructures grow, scalability issues arise in monitoring and management processes. Scalability issues are exacerbated because available solutions typically consider each virtual machine (VM) as a black box with independent characteristics, which is monitored at a fine-grained granularity level for management purposes, thus generating huge amounts of data to handle. We claim that scalability issues can be addressed by leveraging the similarity between VMs in terms of resource usage patterns. In this paper, we propose an automated methodology to cluster similar VMs starting from their resource usage information, assuming no knowledge of the software executed on them. This is an innovative methodology that combines the Bhattacharyya distance and ensemble techniques to provide a stable evaluation of similarity between probability distributions of multiple VM resource usage, considering both system- and network-related data. We evaluate the methodology through a set of experiments on data coming from an enterprise data center. We show that our proposal achieves high and stable performance in automatic VMs clustering, with a significant reduction in the amount of data collected which allows to lighten the monitoring requirements of a cloud data center.