nbo Chu

Predicate Detection Modality and Semantics in Three Partially Synchronous Models

Predicate detection addresses the challenge of monitoring the state of a distributed system. This research is the first step to explore predicate detection with partial synchrony assumptions. We study the observability of computation and focus on predicate detection semantics in three partially synchronous models. A framework of the behavior of predicate detection is established in terms of partial synchrony, modalities permitted and the best detection semantics. This work forms a conceptualization of the problem space and leads to disciplined approaches to predicate detection in realistic systems by identifying the strongest possible semantics for each modality and partial synchrony assumption.

Towards Partially Synchronous Overlays: Issues and Challenges

The main advantage of synchronous systems over asynchronous systems is that timing and reliability guarantees can be established ensuring a strong programming model for many applications. These strong guarantees are not provided by the current model of the Internet. However the Internet possesses some synchronous properties which can be exploited to observe partial synchrony, leading to a stronger programming model. In this paper, we argue the importance of synchrony and describe mechanisms which can be used for the construction of partially synchronous overlays on the Internet

PSON: predictable service overlay networks

We describe the design of PSON, an overlay network, which improves the predictability of end-to-end communication latency on the Internet. Predictable Service Overlay Networks (PSON) monitor the paths between overlay nodes and continuously estimates an upper bound on communication latency to provide a soft synchrony guarantee to application. Through network measurements on PlanetLab nodes we observe that the upper bound estimation provides long durations of synchrony and rapidly adjusts the bound in response to an asynchronous event. Upper bound estimation is enhanced by the use of routing and overlay configuration to provide stable routes while reducing overhead. We describe the architecture, design and interface for the PSON and discuss various issues related to its performance.

Online Teaching and Learning Strategies for Programming-intensive Courses

Using the general guidelines for online teaching and learning as a backdrop, we have investigated best practices that are effective specifically in the context of computer science courses that involve extensive programming and hands-on laboratory explorations. In this paper, we describe our preliminary effort in this direction. More specifically, we describe the strategy we have used in planning, designing, developing, delivering, and assessing the best practices for a course in programming languages.

Eventually perfect predicate detection in crash-affected finite average response time systems

Monitoring and predicate detection is a fundamental challenge of evaluating whether or not a predicate has held on the state of a distributed system in an execution. We solve eventually perfect predicate detection in a failure-prone system assuming that only the average response time is finite. The solution is based on an eventually accurate failure detection sequencer ( ) which we propose and implement in the finite average response time system. We prove that can solve eventually perfect detection of predicates involving process operational status. This research contributes to identifying realistic detection semantics in a weak partially synchronous model. Our approach has a layered model with which applications have the flexibility to choose appropriate predicate detection algorithms with the possibility to solve different predicate modalities.

Brief announcement: the design of an internet-scale monitoring and assertion-checking infrastructure

In this paper, we describe the design of a global infrastructure for monitoring and assertion-checking which is scalable and resilient to network and node failures, leveraging the benefits of distributed hash tables. Our mechanism distributes the event notification, predicate evaluation, and predicate reporting tasks across the Internet and is orthogonal to the specific monitoring techniques deployed. Our approach creates a hierarchy of event reporting and monitoring relationships, decoupling the event notification task from the monitored node and facilitating decomposition of the predicate evaluation and monitoring task if the semantics of the monitoring approach permits. The proposed infrastructure is designed for a best effort monitoring service, but may be strengthened to support stronger guarantees. The proposed has many desirable properties, including scalability, efficient routing, load balancing and good behavior under flash crowds, resiliency to node failure, including failure of monitored hosts and monitoring end-hosts, loose coupling of the monitored hosts and the monitoring task, and self-organizing behavior.

Mobile Agents and Eventually Perfect Predicate Detection: An Intelligent General Approach to Monitoring Distributed Systems

This chapter presents an application of mobile agents to solve distributed predicate detection by distributing and delegating monitoring tasks, result collection, and aggregation to overcome the scalability and flexibility limitations (as compared to most traditional centralized predicate detection approaches). Mobile agents are very useful for monitoring purposes because mobility gives the agents the autonomy needed to monitor the computation effectively. By restructuring the implementation of an eventually accurate failure detection sequencer into mobile agents, the functionalities of predicate detection in a failure-prone partially synchronous system are clearly separated from the monitored computation. The separation leads to additional benefits of enhanced flexibility, performance, and robustness. It provides a solution to create a general-purpose predicate detection infrastructure that provides the basic functionalities to achieve reasonable predicate detection semantics in a realistic distributed system.