Fabio Panzieri

QoS-Aware Clouds

In this paper we discuss the design and experimental evaluation of a middleware architecture that enables Service Level Agreement (SLA)-driven dynamic configuration, management and optimization of cloud resources and services. This architecture has been designed in order to respond effectively to the Quality of Service (QoS) requirements of the cloud customer applications. Typically, an application can be hosted in an execution platform constructed out of (real and virtual) cloud resources. In this context, the application QoS requirements can be specified in a SLA that binds the application to its hosting platform. Our architecture incorporates a load balancer that distributes the computational load across the platform resources, and monitors the QoS the platform delivers. If this deviates from that specified in the SLA, so as to violate it, the platform is reconfigured dynamically in order to incorporate additional resources from the cloud. In contrast, if the SLA is honored and platform resources result unused, platform reconfiguration occurs to release those unused resources.

Server consolidation in Clouds through gossiping

The success of Cloud computing, where computing power is treated as a utility, has resulted in the creation of many large datacenters that are very expensive to build and operate. In particular, the energy bill accounts for a significant fraction of the total operation costs. For this reason a significant attention is being devoted to energy conservation techniques, for example by taking advantage of the built-in power saving features of modern hardware. Cloud computing offers novel opportunities for achieving energy savings: Cloud systems rely on virtualization techniques to allocate computing resources on demand, and modern Virtual Machine (VM) monitors allow live migration of running VMs. Thus, energy conservation can be achieved through server consolidation, moving VM instances away from lightly loaded computing nodes so that they become empty and can be switched to low-power mode. In this paper we present V-MAN, a fully decentralized algorithm for consolidating VMs in large Cloud datacenters. V-MAN can operate on any arbitrary initial allocation of VMs on the Cloud, iteratively producing new allocations that quickly converge towards the one maximizing the number of idle hosts. V-MAN uses a simple gossip protocol to achieve efficiency, scalability and robustness to failures. Simulation experiments indicate that, starting from a random allocation, V-MAN produces an almost-optimal VM placement in just a few rounds; the protocol is intrinsically robust and can cope with computing nodes being added to or removed from the Cloud.

Rajdoot: a remote procedure call mechanism supporting orphan detection and killing

Rajdoot is a remote procedure call (RPC) mechanism with a number of fault tolerance capabilities. A discussion is presented of the reliability-related issues and how these issues have been dealt with in the RPC design. Rajdoot supports exactly-once semantics with call nesting capability, and incorporates effective measures for orphan detection and killing. Performance figures show that the reliability measures of Rajdoot impose little overhead. >

Constructing dependable Web services

The majority of todays millions of Web sites offer read-only access to relatively small amounts of infrequently changing information. The load on these sites is usually small, and services can often be hosted as background tasks on general-purpose workstations. Concern for the quality of service (QoS) presented to users at these sites is generally not primary. Conversely, a much smaller number of sites are very popular; they support heavy loads and must meet user expectations regarding QoS to maintain their popularity. We discuss issues involved in supporting high-volume, high-reliability Web services. We begin by surveying the diverse technical challenges and constraints posed in this environment, followed by currently used hardware and network based approaches to meeting the scalability requirements and software-implemented techniques to addressing fault tolerance. However, these approaches do not scale well, so we discuss possible alternatives.

Seamless Support of Multimedia Distributed Applications Through a Cloud

We describe a cross-layer architecture we are developing in order to offer mobility support to wireless devices executing multimedia applications which require seamless communications. This architecture is based on the use of pairs of proxies, which enable the adaptive and concurrent use of different network interfaces during the communications. A cloud computing environment is used as the infrastructure to set up (and release) dynamically the proxies on the server-side, in accordance with the pay-as-you-go principle of cloud based services.

Real Time Systems: A Tutorial

In this tutorial paper, we introduce a number of issues that arise in the design of distributed real-time systems in general, and hard real-time systems in particular. These issues include time management, process scheduling, and interprocess communications within both local and wide area networks. In addition, we discuss an evaluation, based on a simulation model, of a variety of scheduling policies used in real-time systems. Finally, we examine some relevant examples of existing distributed real-time systems, describe their structuring and implementation, and compare their principal features.

Using P2P techniques for content distribution internetworking: a research proposal

In this paper we discuss the use of algorithms and techniques, currently deployed in peer-to-peer (P2P) systems, in the design of content distribution internetworks (CDIs). Specifically, we propose a CDI design approach that addresses issues of request routing, content delivery, and replication, based on P2P techniques.

On the provision of replicated Internet auction services

The paper presents the design of a software infrastructure that can support negotiation and competition among buyers and sellers of goods (auctioning) over the Internet. The goals of data integrity, responsiveness, and scalability have been achieved by replicating the auction service across a number of auction servers.

Synchronization support and group-membership services for reliable distributed multimedia applications

Abstract.We describe a collection of algorithms designed to support reliable synchronization and group membership services for distributed multimedia applications. In particular, we consider those applications that require interactivity, isochronous rendering of multimedia data, and high reliability. We show that the algorithms we propose (i) provide reliable support for the synchronization of multimedia data streams, despite the occurrence of possible communication failures, (ii) maintain a consistent view of the relative group membership of all the nonfaulty application components, (iii) guarantee time-bounded delay of component failure detection and join, and (iv) meet effectively possible scalability requirements of the applications.

Web Engineering and Peer-to-Peer Computing

In this paper, we capture the main characteristics of WWW traÆc in a stochastic model, which can be used to generate synthetic WWW traces and assess WWW cache designs. To capture temporal and spatial localities, we use a modi ed version of Riedi et al.s multifractal model [18], where we reduce the complexity of the original model from O(N) to O(1); N being the length of the synthetic trace. Our model has the attractiveness of being parsimonious and that it avoids the need to apply a transformation to a self-similar model (as often done in previously proposed models [2]), thus retaining the temporal locality of the tted traÆc. Furthermore, because of the scale-dependent nature of multifractal processes, the proposed model is more exible than monofractal models in describing irregularities in the traÆc. Trace-driven simulations are used to demonstrate the goodness of the proposed model. keywords | WWW modeling, web caching, multifractals, stack distance, self-similarity.