Giuseppe Aceto

Survey Cloud monitoring: A survey

Nowadays, Cloud Computing is widely used to deliver services over the Internet for both technical and economical reasons. The number of Cloud-based services has increased rapidly and strongly in the last years, and so is increased the complexity of the infrastructures behind these services. To properly operate and manage such complex infrastructures effective and efficient monitoring is constantly needed. Many works in literature have surveyed Cloud properties, features, underlying technologies (e.g. virtualization), security and privacy. However, to the best of our knowledge, these surveys lack a detailed analysis of monitoring for the Cloud. To fill this gap, in this paper we provide a survey on Cloud monitoring. We start analyzing motivations for Cloud monitoring, providing also definitions and background for the following contributions. Then, we carefully analyze and discuss the properties of a monitoring system for the Cloud, the issues arising from such properties and how such issues have been tackled in literature. We also describe current platforms, both commercial and open source, and services for Cloud monitoring, underlining how they relate with the properties and issues identified before. Finally, we identify open issues, main challenges and future directions in the field of Cloud monitoring.

D-ITG: Distributed Internet Traffic Generator

In this paper we present our traffic generation platform, named D-ITG (Distributed Internet Traffic Generator). Its features are first described. We believe that some capabilities are in fact innovative, since no other traffic generator offers them. Then, we describe the original architecture of D-ITG, which allows our traffic generator to achieve high performance. We hint at a comparison with other traffic generators and conclude with the ongoing work to add new features.

Cloud monitoring: Definitions, issues and future directions

Despite its importance for operating Cloud systems, Cloud monitoring has received limited attention from the research community. In this position paper, we provide an analysis of Cloud monitoring. More precisely, we discuss the main motivations, basic concepts and definitions, and point out open research issues and future directions for Cloud monitoring.

Internet Censorship detection

Internet Censorship is a phenomenon that crosses several study fields, from computer networking and computer security to social sciences; together with censorship detection and censorship circumvention it has impact on Internet infrastructure, protocols and user behaviors. Detection of Internet Censorship is the basis for the study of this phenomenon, and recently it has received focus from a technical point of view. Due to the heterogeneity of study fields and approaches, the scientific corpus on these topics is still in need of an overall analysis, based on coherent framework and lexicon to describe the experimented approaches and findings.In this paper we present a survey on Internet Censorship detection. We propose a reference for censoring techniques and a characterization of censoring systems, with definitions of related concepts. Based on the censoring techniques investigated in literature, we propose an analysis and discussion of censorship detection techniques and architectures and we present a chronological synopsis of the literature adopting or introducing them. Then we collect, study, and discuss available tools and platforms for censorship detection, and propose a characterization scheme to analyze and compare them. Finally, we compare and discuss detection architectures, tools and platforms, and we use the results to infer current challenges and for proposing new directions in the field of censorship detection.

Monitoring Internet Censorship with UBICA

Censorship is becoming increasingly pervasive on the Internet, with the Open Net Initiative reporting nearly 50 countries practicing some form of censorship. Previous work has reported the existence of many forms of Internet censorship (e.g., DNS tampering, packet filtering, connection reset, content filtering), each of which may be composed to build a more comprehensive censorship system. Automated monitoring of censorship represents an important and challenging research problem, due to the continually evolving nature of the content that is censored and the means by which censorship is implemented. UBICA, User-based Internet Censorship Analysis, is a platform we implemented to solve this task leveraging crowdsourced data collection. By adopting an integrated and multi-step analysis, UBICA provides simple but effective means of revealing censorship events over time. UBICA has revealed the effect of several censorship techniques including DNS tampering and content filtering. Using UBICA, we demonstrate evidence of censorship in several selected countries (Italy, Pakistan, and South Korea), for which we obtained help from local users and manually validated the automated analysis.

Active techniques for available bandwidth estimation: comparison and application

There are various parameters for analyzing the quality of network communication links and paths, one attracting particular attention is available bandwidth. In this chapter we describe a platform for the available bandwidth estimation, a comparison of different tools for the estimation of this parameter, and an application of such estimation in a real-world application. In details, we describe a novel platform called UANM, capable of properly choosing, configuring, and using different available bandwidth tools and techniques in an autonomic fashion. Moreover, thanks to UANM, we show the results of a comparison of the performance of several tools in terms of accuracy, probing time and intrusiveness. Finally, we show a practical example of the use of the available bandwidth measurement: we describe an approach for server selection and admission control in a content distribution network based on the available bandwidth estimation.

Available bandwidth measurement in software defined networks

Software Defined Networking (SDN) is an emerging paradigm that is expected to revolutionize computer networks. With the decoupling of data and control plane and the introduction of open communication interfaces between layers, SDN enables programmability over the entire network, promising rapid innovation in this area. The SDN concept was already proven to work successfully in cloud and data center environments thus the proper monitoring of such networks is already in the focus of the research community. Methods for measuring Quality of Service (QoS) parameters such as bandwidth utilization, packet loss, and delay have been recently introduced in literature, but they lack a solution for tackling down the question of available bandwidth. In this paper, we attempt to fill this gap and introduce a novel mechanism for measuring available bandwidth in SDN networks. We take advantage of the SDN architecture and build an application over the Network Operating System (NOS). Our application can track the topology of the network and the bandwidth utilization over the network links, and thus it is able to calculate the available bandwidth between any two points in the network. We validate our method using the popular Mininet network emulation environment and the widely used NOS called Floodlight. We present results providing insights into the measurement accuracy and showing its relationship with the delay in the control network and the polling frequency.

Efficient Storage and Processing of High-Volume Network Monitoring Data

Monitoring modern networks involves storing and transferring huge amounts of data. To cope with this problem, in this paper we propose a technique that allows to transform the measurement data in a representation format meeting two main objectives at the same time. Firstly, it allows to perform a number of operations directly on the transformed data with a controlled loss of accuracy, thanks to the mathematical framework it is based on. Secondly, the new representation has a small memory footprint, allowing to reduce the space needed for data storage and the time needed for data transfer. To validate our technique, we perform an analysis of its performance in terms of accuracy and memory footprint. The results show that the transformed data closely approximates the original data (within 5% relative error) while achieving a compression ratio of 20%; storage footprint can also be gradually reduced towards the one of the state-of-the-art compression tools, such as bzip2, if higher approximation is allowed. Finally, a sensibility analysis show that technique allows to trade-off the accuracy on different input fields so to accommodate for specific application needs, while a scalability analysis indicates that the technique scales with input size spanning up to three orders of magnitude.

An efficient storage technique for network monitoring data

Monitoring modern networks involves storing and transferring huge amounts of data. For this reason, compression techniques are typically used in order to reduce the space and time needed for these operations. The main drawback of this approach is that, when data has to be processed, a preliminary decompression is necessary, which increases the time and computational power needed. To cope with this problem, in this paper we propose a technique that allows to transform the measurement data in a representation format meeting two main objectives at the same time. Firstly, it allows to perform a number of operations directly on the transformed data with a controlled loss of accuracy, thanks to the mathematical framework it is based on. Secondly, the new representation has a small memory footprint, allowing to reduce the space needed for data storage and the time needed for data transfer. To validate our technique, we perform an analysis of its performance in terms of accuracy and memory footprint. The results show that the transformed data closely approximates the original data (within 5% relative error) while achieving the compression ratio of 20%; storage footprint can be gradually made close to that of the state-of-the-art compression tools, such as bzip2, if higher approximation is allowed.

UANM: a platform for experimenting with available bandwidth estimation tools

In the field of network monitoring and measurement, the efficiency and accuracy of the adopted tools is strongly dependent on (i) structural and dynamic characteristics of the network scenario under measure and (ii) on manual fine tuning of the involved parameters. This is, for example, the case of the end-to-end available bandwidth estimation, in which the constraints of the measurement stage vary according to the use of the final results. In this work we present UANM (Unified Architecture for Network Measurement), a novel measurement infrastructure for an automatic management of measurement stages, tailored to the end-to-end available bandwidth estimation tools. We describe in details its architecture, illustrating the features we introduced to mitigate the problems affecting available bandwidth estimation in heterogeneous scenarios. Moreover, to provide evidences of UANM benefits, we present an experimental validation in three selected scenarios deployed over a real network testbed: (i) we show how UANM is able to alleviate the interferences among concurrent measures; (ii) we quantify the overhead introduced by the use of UANM; (iii) we illustrate how UANM is capable to provide more accurate results thanks to the knowledge of the network environment.