Renzo Davoli

VDE: virtual distributed Ethernet

The idea of VDE is very effective but straightforward simple and can be applied in very many configuration to provide several services. It is a sort of Swiss knife of emulated networks. It can be used as a general virtual private network as well as a support technology for mobility, a tool for network testing, a general reconfigurable overlay network, a layer for implementing privacy preserving technologies and many others. A prototype VDE has been implemented and released as free software under the GPL licence.

RELACS: A communications infrastructure for constructing reliable applications in large-scale distributed systems

Distributed systems that span large geographic distances or manage large numbers of objects are already common place. In such systems, programming applications with even modest reliability requirements to run correctly and efficiently is a difficult task due to asynchrony and the possibility of complex failure scenarios. We describe the architecture of the RELACS communication subsystem that constitutes the microkernel of a layered approach to reliable computing in large-scale distributed systems. RELACS is designed to be highly portable and implements a very small number of abstractions and primitives that should be sufficient for building a variety of interesting higher-level paradigms.<<ETX>>

Paralex: an environment for parallel programming in distributed systems

Modern distributed systems consisting of powerful workstations and high-speed interconnection networks are an economical alternative to special-purpose super computers. The technical issues that need to be addressed in exploiting the parallelism inherent in a distributed system include heterogeneity, high-latency communication, fault tolerance and dynamic load balancing. Current software systems for parallel programming provide little or no automatic support towards these issues and require users to be experts in fault-tolerant distributed computing. The Paralex system is aimed at exploring the extent to which the parallel application programmer can be liberated from the complexities of distributed systems. Paralex is a complete programming environment and makes extensive use of graphics to define, edit, execute and debug parallel scientific applications. All of the necessary code for distributing the computation across a network and replicating it to achieve fault tolerance and dynamic load balancing is automatically generated by the system. In this paper we give an overview of Paralex and present our experiences with a prototype implementation.

The Inherent Cost of Strong-Partial View-Synchronous Communication

Process groups and group-based communication have proven to be useful paradigms for structuring reliable applications in distributed systems. The approach is typically realized through view-synchronous communication (VSC) that integrates a reliable multicast facility with a group membership service in the form of view changes. In this paper we examine algorithmic issues associated with VSC group membership in large-scale distributed systems where network partitions may result in multiple views to be active concurrently. We first derive necessary conditions on the partial order of installed views such that VSC is meaningful and solvable in the presence of partitions. We then prove that strong-partial VSC, which guarantees concurrent views to be disjoint, is not easier than atomic commitment. As such, all know lower bound results for atomic commitment are also lower bounds for this problem, including the impossibility of nonblocking solutions in the presence of communication failures. We discuss the practical implications of our results in constructing group communication facilities for large-scale distributed systems.

Learning operating systems structure and implementation through the MPS computer system simulator

Lab activity is fundamental for the real understanding of several computer science topics such as operating systems. We have built our own hardware emulator after using software tools from other Universities for several years. MPS is a general-purpose computer system simulator based on MIPS R3000 processor. Together with the main processor, RAM, ROM, disks, tapes, printer and terminal interfaces are carefully emulated and fully configurable; non-volatile memory units may be retained between simulations.MPS features a full-fledged graphic user interface running under X Window, complete sources and documentation. Along with it we present TINA, an experimental project on operating system development, together with several other project proposals.

Group membership and view synchrony in partitionable asynchronous distributed systems: specifications

Transient failures, unknown scheduling strategies and variable loads on the computing and communication resources give rise to an asynchronous and partitionable characterization for practical distributed systems with large geographic extent. We consider the group membership problem in partitionable asynchronous systems and give a formal specification that guarantees liveness and prevents capricious view splitting. Our work is based on the notion of reachability as an appropriate characterization of failures in partitionable systems in that it subsumes both process crashes and communication failures. The group membership problem is formulated in the context of view synchrony that includes a reliable multicast service for communication within the group. Our specification is modular and includes properties governing group membership separately from those governing reliable multicasts. It can be taken either partially for defining a group membership service alone, or taken as a whole for defining view synchrony.

Mapping parallel computations onto distributed systems in Paralex

Paralex is a programming environment that allows parallel programs to be developed and executed on distributed systems as if the latter were uniform parallel multiprocessor computers. Architectural heterogeneity, remote communication and failures are rendered transparent to the programmer through automatic system support. The authors address the problems of initial mapping and dynamic alteration of the association between parallel computation components and distributed hosts. Results include novel heuristics and mechanisms to resolve these problems despite the complexities introduced by architectural heterogeneity fault tolerance.<<ETX>>

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.

VDE: an emulation environment for supporting computer networking courses

Emulators have long been a valuable tool in teaching. Particularly in the OS course, emulators have allowed students to experiment meaningfully with different machine architectures. Furthermore, many such tools run in user-mode, allowing students to operate as system administrators without the concomitant security risks. Virtual Distributed Ethernet (VDE) is a system which emulates, in user-mode, all aspects of an internet, including switches, routers, communication lines, etc, in a completely realistic manner, consistent with the operation of such artifacts in the real world. VDEs can be implemented on a single computer, spread over several machines on the same LAN or scattered across the Internet. A VDE can interoperate with both real systems (via standard virtual interface/connectivity tools) and several virtual machine environments, support encryption, and actually run fast enough to support real applications. Furthermore, a VDE can interface/interoperate with real networks. VDNs have proven highly effective in supporting both undergraduate and graduate networking courses, and a wide range of student experiments and projects.

The Kaya OS project and the μ MPS hardware emulator

Ideally, the most meaningful learning experience for students in an undergraduate OS course would be to develop fully-functional OSs on their own. This can be accomplished using μmps, a hardware emulator for a pedagogically undergraduate-appropriate hardware architecture, along with Kaya, a specification for a multi-layer OS supporting multiprocessing, VM, thread synchronization, external devices (disks, terminals, tape, printers, and network interfaces) and a file system.Traditional OS projects like Nachos[3] or OS/161[9] provide students with a significant starting code base. Students then modify existing OS modules or add new ones. With μmps/Kaya students undergo an innovative and pedagogically different experience of starting only with a hardware emulator (i.e. no initial OS code base for students to build on/replace) and ending with a completely student written OS capable of running student written C programs.