AIDA-Based Real-Time Fault-Tolerant Broadcast Disks

The proliferation of mobile computers and wireless networks requires the design of future distributed real-time applications to recognize and deal with the significant asymmetry between downstream and upstream communication capacities, and the significant disparity between server and client storage capacities. Recent research work proposed the use of Broadcast Disks as a scalable mechanism to deal with this problem. In this paper, we propose a new broadcast disks protocol, based on our Adaptive Information Dispersal Algorithm (AIDA). Our protocol is different from previous broadcast disks protocols in that it improves communication timeliness, fault-tolerance, and security, while allowing for a finer control of multiplexing of prioritized data (broadcast frequencies). We start with a general introduction of broadcast disks. Next, we propose broadcast disk organizations that are suitable for real-time applications. Next, we present AIDA and show its fault-tolerance and security properties. We conclude the paper with the description and analysis of AIDA-based broadcast disks organizations that achieve both timeliness and fault-tolerance, while preserving downstream communication capacity.

An Admission Control Paradigm for Real-time Databases

We propose and evaluate an admission control paradigm for RTDBS, in which a transaction is submitted to the system as a pair of processes: a primary task, and a recovery block. The execution requirements of the primary task are not known a priori, whereas those of the recovery block are known a priori. Upon the submission of a transaction, an Admission Control Mechanism is employed to decide whether to admit or reject that transaction. Once admitted, a transaction is guaranteed to finish executing before its deadline. A transaction is considered to have finished executing if exactly one of two things occur: Either its primary task is completed (successful commitment), or its recovery block is completed (safe termination). Committed transactions bring a profit to the system, whereas a terminated transaction brings no profit. The goal of the admission control and scheduling protocols (e.g., concurrency control, I/O scheduling, memory management) employed in the system is to maximize system profit. We describe a number of admission control strategies and contrast (through simulations) their relative performance.

Distributed Parallel Computing in Mermera: Mixing Noncoherent Shared Memories

Programmers of parallel processes that communicate through shared globally distributed data structures (DDS) face a difficult choice. Either they must explicitly program DDS management, by partitioning or replicating it over multiple distributed memory modules, or be content with a high latency coherent (sequentially consistent) memory abstraction that hides the DDS' distribution. We present Mermera, a new formalism and system that enable a smooth spectrum of noncoherent shared memory behaviors to coexist between the above two extremes. Our approach allows us to define known noncoherent memories in a new simple way, to identify new memory behaviors, and to characterize generic mixed-behavior computations. The latter are useful for programming using multiple behaviors that complement each others' advantages. On the practical side, we show that the large class of programs that use asynchronous iterative methods (AIM) can run correctly on slow memory, one of the weakest, and hence most efficient and fault-tolerant, noncoherence conditions. An example AIM program to solve linear equations, is developed to illustrate: (1) the need for concurrently mixing memory behaviors, and, (2) the performance gains attainable via noncoherence. Other program classes tolerate weak memory consistency by synchronizing in such a way as to yield executions indistinguishable from coherent ones. AIM computations on noncoherent memory yield noncoherent, yet correct, computations. We report performance data that exemplifies the potential benefits of noncoherence, in terms of raw memory performance, as well as application speed.

Characterizing Reference Locality in the WWW

As the World Wide Web (Web) is increasingly adopted as the infrastructure for large-scale distributed information systems, issues of performance modeling become ever more critical. In particular, locality of reference is an important property in the performance modeling of distributed information systems. In the case of the Web, understanding the nature of reference locality will help improve the design of middleware, such as caching, prefetching, and document dissemination systems. For example, good measurements of reference locality would allow us to generate synthetic reference streams with accurate performance characteristics, would allow us to compare empirically measured streams to explain differences, and would allow us to predict expected performance for system design and capacity planning. In this paper we propose models for both temporal and spatial locality of reference in streams of requests arriving at Web servers. We show that simple models based only on document popularity (likelihood of reference) are insufficient for capturing either temporal or spatial locality. Instead, we rely on an equivalent, but numerical, representation of a reference stream: a stack distance trace. We show that temporal locality can be characterized by the marginal distribution of the stack distance trace, and we propose models for typical distributions and compare their cache performance to our traces. We also show that spatial locality in a reference stream can be characterized using the notion of self-similarity. Self-similarity describes long-range correlations in the dataset, which is a property that previous researchers have found hard to incorporate into synthetic reference strings. We show that stack distance strings appear to be strongly self-similar, and we provide measurements of the degree of self-similarity in our traces. Finally, we discuss methods for generating synthetic Web traces that exhibit the properties of temporal and spatial locality that we measured in our data.

Communicable Memory and Lazy Barriers for Bulk Synchronous Parallelism in BSPk

Communication and synchronization stand as the dual bottlenecks in the performance of parallel systems, and especially those that attempt to alleviate the programming burden by incurring overhead in these two domains. We formulate the notions of communicable memory and lazy barriers to help achieve efficient communication and synchronization. These concepts are developed in the context of BSPk, a toolkit library for programming networks of workstations|and other distributed memory architectures in general|based on the Bulk Synchronous Parallel (BSP) model. BSPk emphasizes efficiency in communication by minimizing local memory-to-memory copying, and in barrier synchronization by not forcing a process to wait unless it needs remote data. Both the message passing (MP) and distributed shared memory (DSM) programming styles are supported in BSPk. MP helps processes efficiently exchange short-lived unnamed data values, when the identity of either the sender or receiver is known to the other party. By contrast, DSM supports communication between processes that may be mutually anonymous, so long as they can agree on variable names in which to store shared temporary or long-lived data.

TCP Boston: A Fragmentation-tolerant TCP Protocol for ATM Networks

The popularity of TCP/IP coupled with the premise of high speed communication using Asynchronous Transfer Mode (ATM) technology have prompted the network research community to propose a number of techniques to adapt TCP/IP to ATM network environments. ATM offers Available Bit Rate (ABR) and Unspecified Bit Rate (UBR) services for best-effort traffic, such as conventional file transfer. However, recent studies have shown that TCP/IP, when implemented using ABR or UBR, leads to serious performance degradations, especially when the utilization of network resources (such as switch buffers) is high. Proposed techniques-switch-level enhancements, for example-that attempt to patch up TCP/IP over ATMs have had limited success in alleviating this problem. The major reason for TCP/IP's poor performance over ATMs has been consistently attributed to packet fragmentation, which is the result of ATM's 53-byte cell-oriented switching architecture. In this paper, we present a new transport protocol, TCP Boston, that turns ATM's 53-byte cell-oriented switching architecture into an advantage for TCP/IP. At the core of TCP Boston is the Adaptive Information Dispersal Algorithm (AIDA), an efficient encoding technique that allows for dynamic redundancy control. AIDA makes TCP/IP's performance less sensitive to cell losses, thus ensuring a graceful degradation of TCP/IP's performance when faced with congested resources. In this paper, we introduce AIDA and overview the main features of TCP Boston. We present detailed simulation results that show the superiority of our protocol when compared to other adaptations of TCP/IP over ATMs. In particular, we show that TCP Boston improves TCP/IP's performance over ATMs for both network-centric metrics (e.g., effective throughput) and application-centric metrics (e.g., response time).

On the Relationship Between File Sizes, Transport Protocols, and Self-Similar Network Traffic

Recent measurements of local-area and wide-area traffic have shown that network traffic exhibits variability at a wide range of scales self-similarity. In this paper, we examine a mechanism that gives rise to self-similar network traffic and present some of its performance implications. The mechanism we study is the transfer of files or messages whose size is drawn from a heavy-tailed distribution. We examine its effects through detailed transport-level simulations of multiple TCP streams in an internetwork. First, we show that in a "realistic" client/server network environment i.e., one with bounded resources and coupling among traffic sources competing for resources the degree to which file sizes are heavy-tailed can directly determine the degree of traffic self-similarity at the link level. We show that this causal relationship is not significantly affected by changes in network resources (bottleneck bandwidth and buffer capacity), network topology, the influence of cross-traffic, or the distribution of interarrival times. Second, we show that properties of the transport layer play an important role in preserving and modulating this relationship. In particular, the reliable transmission and flow control mechanisms of TCP (Reno, Tahoe, or Vegas) serve to maintain the long-range dependency structure induced by heavy-tailed file size distributions. In contrast, if a non-flow-controlled and unreliable (UDP-based) transport protocol is used, the resulting traffic shows little self-similar characteristics: although still bursty at short time scales, it has little long-range dependence. If flow-controlled, unreliable transport is employed, the degree of traffic self-similarity is positively correlated with the degree of throttling at the source. Third, in exploring the relationship between file sizes, transport protocols, and self-similarity, we are also able to show some of the performance implications of self-similarity. We present data on the relationship between traffic self-similarity and network performance as captured by performance measures including packet loss rate, retransmission rate, and queueing delay. Increased self-similarity, as expected, results in degradation of performance. Queueing delay, in particular, exhibits a drastic increase with increasing self-similarity. Throughput-related measures such as packet loss and retransmission rate, however, increase only gradually with increasing traffic self-similarity as long as reliable, flow-controlled transport protocol is used.

Load Profiling in Distributed Real-Time Systems

Load balancing is often used to ensure that nodes in a distributed systems are equally loaded. In this paper, we show that for real-time systems, load balancing is not desirable. In particular, we propose a new load-profiling strategy that allows the nodes of a distributed system to be unequally loaded. Using load profiling, the system attempts to distribute the load amongst its nodes so as to maximize the chances of finding a node that would satisfy the computational needs of incoming real-time tasks. To that end, we describe and evaluate a distributed load-profiling protocol for dynamically scheduling time-constrained tasks in a loosely-coupled distributed environment. When a task is submitted to a node, the scheduling software tries to schedule the task locally so as to meet its deadline. If that is not feasible, it tries to locate another node where this could be done with a high probability of success, while attempting to maintain an overall load profile for the system. Nodes in the system inform each other about their state using a combination of multicasting and gossiping. The performance of the proposed protocol is evaluated via simulation, and is contrasted to other dynamic scheduling protocols for real-time distributed systems. Based on our findings, we argue that keeping a diverse availability profile and using passive bidding (through gossiping) are both advantageous to distributed scheduling for real-time systems.

Beta-Reduction As Unification

We define a unification problem ^UP with the property that, given a pure lambda-term M, we can derive an instance Gamma(M) of ^UP from M such that Gamma(M) has a solution if and only if M is beta-strongly normalizable. There is a type discipline for pure lambda-terms that characterizes beta-strong normalization; this is the system of intersection types (without a "top" type that can be assigned to every lambda-term). In this report, we use a lean version LAMBDA of the usual system of intersection types. Hence, ^UP is also an appropriate unification problem to characterize typability of lambda-terms in LAMBDA. It also follows that ^UP is an undecidable problem, which can in turn be related to semi-unification and second-order unification (both known to be undecidable).

An Infinite Pebble Game and Applications

We generalize the well-known pebble game to infinite dag's, and we use this generalization to give new and shorter proofs of results in different areas of computer science (as diverse as "logic of programs" and "formal language theory"). Our applications here include a proof of a theorem due to Salomaa, asserting the existence of a context-free language with infinite index, and a proof of a theorem due to Tiuryn and Erimbetov, asserting that unbounded memory increases the power of logics of programs. The original proofs by Salomaa, Tiuryn, and Erimbetov, are fairly technical. The proofs by Tiuryn and Erimbetov also involve advanced techniques of model theory, namely, back-and-forth constructions based on a variant of Ehrenfeucht-Fraisse games. By contrast, our proofs are not only shorter, but also elementary. All we need is essentially finite induction and, in the case of the Tiuryn-Erimbetov result, the compactness and completeness of first-order logic.

A Linearization of the Lambda-Calculus and Consequences

If every lambda-abstraction in a lambda-term M binds at most one variable occurrence, then M is said to be "linear". Many questions about linear lambda-terms are relatively easy to answer, e.g. they all are beta-strongly normalizing and all are simply-typable. We extend the syntax of the standard lambda-calculus L to a non-standard lambda-calculus L^ satisfying a linearity condition generalizing the notion in the standard case. Specifically, in L^ a subterm Q of a term M can be applied to several subterms R1,...,Rk in parallel, which we write as (Q. R1 \wedge ... \wedge Rk). The appropriate notion of beta-reduction beta^ for the calculus L^ is such that, if Q is the lambda-abstraction (\lambda x.P) with m\geq 0 bound occurrences of x, the reduction can be carried out provided k = max(m,1). Every M in L^ is thus beta^-SN. We relate standard beta-reduction and non-standard beta^-reduction in several different ways, and draw several consequences, e.g. a new simple proof for the fact that a standard term M is beta-SN iff M can be assigned a so-called "intersection" type ("top" type disallowed).

Typability is Undecidable for F+Eta

System F is the well-known polymorphically-typed λ-calculus with universal quantifiers ("∀"). F+η is System F extended with the eta rule, which says that if term M can be given type τ and M η-reduces to N, then N can also be given the type τ. Adding the eta rule to System F is equivalent to adding the subsumption rule using the subtyping ("containment") relation that Mitchell defined and axiomatized [Mit88]. The subsumption rule says that if M can be given type τ and τ is a subtype of type σ, then M can be given type σ. Mitchell's subtyping relation involves no extensions to the syntax of types, i.e., no bounded polymorphism and no supertype of all types, and is thus unrelated to the system F≤("F-sub"). Typability for F+η is the problem of determining for any term M whether there is any type τ that can be given to it using the type inference rules of F+η. Typability has been proven undecidable for System F [Wel94] (without the eta rule), but the decidability of typability has been an open problem for F+η. Mitchell's subtyping relation has recently been proven undecidable [TU95, Wel95b], implying the undecidability of "type checking" for F+η. This paper reduces the problem of subtyping to the problem of typability for F+η, thus proving the undecidability of typability. The proof methods are similar in outline to those used to prove the undecidability of typability for System F, but the fine details differ greatly.

Pinwheel Scheduling for Fault-tolerant Broadcast Disks in Real-time Database Systems

The design of programs for broadcast disks which incorporate real-time and fault-tolerance requirements is considered. A generalized model for real-time fault-tolerant broadcast disks is defined. It is shown that designing programs for broadcast disks specified in this model is closely related to the scheduling of pinwheel task systems. Some new results in pinwheel scheduling theory are derived, which facilitate the efficient generation of real-time fault-tolerant broadcast disk programs.

ImageRover: A Content-Based Image Browser for the World Wide Web

ImageRover is a search by image content navigation tool for the world wide web. To gather images expediently, the image collection subsystem utilizes a distributed fleet of WWW robots running on different computers. The image robots gather information about the images they find, computing the appropriate image decompositions and indices, and store this extracted information in vector form for searches based on image content. At search time, users can iteratively guide the search through the selection of relevant examples. Search performance is made efficient through the use of an approximate, optimized k-d tree algorithm. The system employs a novel relevance feedback algorithm that selects the distance metrics appropriate for a particular query.

Generating Representative Web Workloads for Network and Server Performance Evaluation

One role for workload generation is as a means for understanding how servers and networks respond to variation in load. This enables management and capacity planning based on current and projected usage. This paper applies a number of observations of Web server usage to create a realistic Web workload generation tool which mimics a set of real users accessing a server. The tool, called Surge (Scalable URL Reference Generator) generates references matching empirical measurements of 1) server file size distribution; 2) request size distribution; 3) relative file popularity; 4) embedded file references; 5) temporal locality of reference; and 6) idle periods of individual users. This paper reviews the essential elements required in the generation of a representative Web workload. It also addresses the technical challenges to satisfying this large set of simultaneous constraints on the properties of the reference stream, the solutions we adopted, and their associated accuracy. Finally, we present evidence that Surge exercises servers in a manner significantly different from other Web server benchmarks.