No description available.

Conventional parallel computer architectures do not provide support for non-uniformly distributed objects. In this thesis, I introduce sparsely faceted arrays (SFAs), a new low-level mechanism for naming regions of memory, or facets, on different processors in a distributed, shared memory parallel processing system. Sparsely faceted arrays address the disconnect between the global distributed arrays provided by conventional architectures (e.g. the Cray T3 series), and the requirements of high-level parallel programming methods that wish to use objects that are distributed over only a subset of processing elements. A sparsely faceted array names a virtual globally-distributed array, but actual facets are lazily allocated. By providing simple semantics and making efficient use of memory, SFAs enable efficient implementation of a variety of non-uniformly distributed data structures and related algorithms. I present example applications which use SFAs, and describe and evaluate simple hardware mechanisms for implementing SFAs. Keeping track of which nodes have allocated facets for a particular SFA is an important task that suggests the need for automatic memory management, including garbage collection. To address this need, I first argue that conventional tracing techniques such as mark/sweep and copying GC are inherently unscalable in parallel systems. I then present a parallel memory-management strategy, based on reference-counting, that is capable of garbage collecting sparsely faceted arrays. I also discuss opportunities for hardware support of this garbage collection strategy. I have implemented a high-level hardware/OS simulator featuring hardware support for sparsely faceted arrays and automatic garbage collection. I describe the simulator and outline a few of the numerous details associated with a "real" implementation of SFAs and SFA-aware garbage collection. Simulation results are used throughout this thesis in the evaluation of hardware support mechanisms.

A memory leak is a common software vulnerability that will lead to performance degradation of the software or crash or both. A Memory leak is one typical cause of software aging. The phenomenon of memory leaks usually occurs in C/C++ because programmers need to manage memory by themselves when programs run. However, many think that Java does not suffer from memory leaks since Java provides automatic garbage collection. Actually, Java programs will run out of memory unexpectedly after executing for a long time. The reason for Java memory leaks is that reachable objects are no longer needed. These objects should be reclaimed but they can¡¦t because they are still referenced. This thesis introduces a method for filtering the leaked objects in Java memory leak programs. First, we monitor the heap growth after each full garbage collection and the numbers of full garbage collection to identify programs that might have potential memory management problems. Second, we periodically keep track of growth trend of each object of problematic programs and filter out the suspected one by time series analysis. Finally, we execute the program blocks that include objects that we find out to see if the program will run out of memory eventually. The method has been implemented and has been verified successful by four Java memory leak programs.

Thesis (M. Sc.)--York University, 2001. Graduate Programme in Computer Science. / Typescript. Includes bibliographical references (leaves 87-92). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://wwwlib.umi.com/cr/yorku/fullcit?pMQ67749.

This thesis concentrates on the derivation of a modularised version of the DMOS distributed garbage collection algorithm and the implementation of this algorithm in a distributed computational environment. DMOS appears to exhibit a unique combination of attractive characteristics for a distributed garbage collector but the original algorithm is known to contain a bug and, previous to this work, lacks a satisfactory, understandable implementation. The relationship between distributed termination detection algorithms and distributed garbage collectors is central to this thesis. A modularised DMOS algorithm is developed using a previously published distributed garbage collector derivation methodology that centres on mapping centralised collection schemes to distributed termination detection algorithms. In examining the utility and suitability of the derivation methodology, a family of six distributed collectors is developed and an extension to the methodology is presented. The research work described in this thesis incorporates the definition and implementation of a distributed computational environment based on the ProcessBase language and a generic definition of a previously unimplemented distributed termination detection algorithm called Task Balancing. The role of distributed termination detection in the DMOS collection mechanisms is defined through a process of step-wise refinement. The implementation of the collector is achieved in two stages; the first stage defines the implementation of two distributed termination mappings with the Task Balancing algorithm; the second stage defines the DMOS collection mechanisms.

No description available.

Utility Accrual (UA) scheduling is a method of dynamic real-time scheduling that is designed to respond to overload conditions by producing a feasible schedule that heuristically maximizes a pre-defined metric of utility. Whereas utility accrual schedulers have traditionally focused on CPU overload, this dissertation explores memory overload conditions during which the aggregate memory demand exceeds a system's available memory bandwidth. Real-time systems are typically implemented in C or other languages that use explicit dynamic memory management. Taking advantage of modern type-safe languages, such as Java, necessitates the use of garbage collection (GC). The timeliness requirements of real-time systems, however, impose specific demands on the garbage collector. Garbage collection introduces a significant source of unpredictability in the execution timeline of a task because it unexpectedly interjects pauses of arbitrary length, at arbitrary points in time, with an arbitrary frequency. To construct a feasible schedule, a real-time scheduler must have the ability to predict the collector's activities and plan for them accordingly. We have devised CADUS (Collector-Aware Dynamic Utility Scheduler), a utility accrual algorithm that tightly links CPU scheduling with the memory requirements -and the corresponding garbage collection activities - of real-time tasks. By constructing and storing memory time allocation profiles, we address the problem of GC activation strategy. We estimate GC latency by using a real-time collector and modeling its behavior. We project GC frequency by planning, at schedule construction time, the memory bandwidth available to the collector. CADUS can point the collector's activities to any specific task in the system. The runtime system provides this ability by maintaining separate logical heaps for all tasks. We demonstrate the viability of CADUS through extensive simulation studies. We evaluated the behavior of CADUS under a wide range of CPU and memory load conditions and utility distributions. We compared its performance against an existing GC-unaware UA scheduler and found that CADUS consistently outperformed its GC-unaware counterpart. We investigated and identified the reasons for the superior performance of CADUS and quantified our results. Most significantly, we found that in an overloaded dynamic soft real-time system, a scheduler's preemption decisions have a highly significant impact on GC latency. A dynamic real-time scheduler therefore must predict the impact of its preemption decisions on GC latency in order to construct time-feasible schedules. / Ph. D.

Implementing a Prolog Runtime System in a language like Java which provides its own automatic memory management and safety features such as built--in index checking and array initialization requires a consistent approach to memory management based on a simple ultimate goal: minimizing total memory management time and extra space involved. The total memory management time for Jinni is made up of garbage collection time both for Java and Jinni itself. Extra space is usually requested at Jinni's garbage collection. This goal motivates us to find a simple and practical garbage collection algorithm and implementation for our Prolog engine. In this thesis we survey various algorithms already proposed and offer our own contribution to the study of garbage collection by improvements and optimizations for some classic algorithms. We implemented these algorithms based on the dynamic array algorithm for an all--dynamic Prolog engine (JINNI 2000). The comparisons of our implementations versus the originally proposed algorithm allow us to draw informative conclusions on their theoretical complexity model and their empirical effectiveness.

Moderne, objektorientierte Sprachen spielen bei der Entwicklung von Software für eingebettete Systeme bislang kaum eine Rolle. Die Gründe hierfür sind vielfältig, meist wird jedoch die mangelnde Effizienz und der größere Speicherbedarf hervorgehoben. Obwohl Java viele Eigenschaften hat, die sehr für einen Einsatz in eingebetteten Systemen sprechen, so hängt doch gerade Java vielfach immer noch das Vorurteil an, in Systemen mit beschränkter Rechenleistung und Speicher zu viele Ressourcen zu benötigen. Diese Arbeit soll dazu beitragen, diese Vorurteile abzutragen. Sie stellt insbesondere Techniken vor, die den Speicherbedarf einer JVM so gering wie möglich halten und diese effizient mit der zur Verfügung stehenden Rechenleistung umgehen lassen. Viele der dargestellten Verfahren und Algorithmen wurden in der Kertasarie VM implementiert, einer virtuellen Maschine, die speziell für den Einsatz in eingebetteten Systemen konzipiert wurde. Durch die weit verbreitete Vernetzung eingebetteter Systeme über das Internet stellt sich in vielen Fällen zudem das Problem einer modernen, abstrakten und effizienten Form der Kommunikation. Aus diesem Grund liegt der zweite Schwerpunkt dieser Arbeit auf dem Vergleich von objektorientierten Middleware-Architekturen, insbesondere von Java-RMI. Auch auf diesem Gebiet wird eine eigene, speziell an eingebettete Systeme angepasste RMI-Variante vorgestellt. / Modern, object oriented languages do not play an important role when developing software for embedded systems. There are many reasons for it, most often an inadequate performance and a greater memory demand are mentioned. In spite of the fact that Java has many features suitable for embedded systems, Java often faces the prejudice to consume too much resources in systems with limited processing power and memory. This work is a contribution to diminish this prejudices. It presents techniques to limit the memory demands of a Java Virtual Machine and to effectively cope with limited computing power. Many of the presented methods and algorithms are implemented in the Kertasarie VM, a JVM designed to run in embedded systems.Due to the fact of increasing network capabilities embedded systems often face the problem of a modern, abstract and efficient communication. Therefore the second emphasis of this work is put on the comparison of object oriented middleware architectures, especially Java-RMI. An own implementation for embedded systems is also presented.

Moderne, objektorientierte Sprachen spielen bei der Entwicklung von Software für eingebettete Systeme bislang kaum eine Rolle. Die Gründe hierfür sind vielfältig, meist wird jedoch die mangelnde Effizienz und der größere Speicherbedarf hervorgehoben. Obwohl Java viele Eigenschaften hat, die sehr für einen Einsatz in eingebetteten Systemen sprechen, so hängt doch gerade Java vielfach immer noch das Vorurteil an, in Systemen mit beschränkter Rechenleistung und Speicher zu viele Ressourcen zu benötigen. Diese Arbeit soll dazu beitragen, diese Vorurteile abzutragen. Sie stellt insbesondere Techniken vor, die den Speicherbedarf einer JVM so gering wie möglich halten und diese effizient mit der zur Verfügung stehenden Rechenleistung umgehen lassen. Viele der dargestellten Verfahren und Algorithmen wurden in der Kertasarie VM implementiert, einer virtuellen Maschine, die speziell für den Einsatz in eingebetteten Systemen konzipiert wurde. Durch die weit verbreitete Vernetzung eingebetteter Systeme über das Internet stellt sich in vielen Fällen zudem das Problem einer modernen, abstrakten und effizienten Form der Kommunikation. Aus diesem Grund liegt der zweite Schwerpunkt dieser Arbeit auf dem Vergleich von objektorientierten Middleware-Architekturen, insbesondere von Java-RMI. Auch auf diesem Gebiet wird eine eigene, speziell an eingebettete Systeme angepasste RMI-Variante vorgestellt. / Modern, object oriented languages do not play an important role when developing software for embedded systems. There are many reasons for it, most often an inadequate performance and a greater memory demand are mentioned. In spite of the fact that Java has many features suitable for embedded systems, Java often faces the prejudice to consume too much resources in systems with limited processing power and memory. This work is a contribution to diminish this prejudices. It presents techniques to limit the memory demands of a Java Virtual Machine and to effectively cope with limited computing power. Many of the presented methods and algorithms are implemented in the Kertasarie VM, a JVM designed to run in embedded systems.Due to the fact of increasing network capabilities embedded systems often face the problem of a modern, abstract and efficient communication. Therefore the second emphasis of this work is put on the comparison of object oriented middleware architectures, especially Java-RMI. An own implementation for embedded systems is also presented.