Yuh-Jzer Joung

Asynchronous group mutual exclusion

Abstract. Mutual exclusion and concurrency are two fundamental and essentially opposite features in distributed systems. However, in some applications such as Computer Supported Cooperative Work (CSCW) we have found it necessary to impose mutual exclusion on different groups of processes in accessing a resource, while allowing processes of the same group to share the resource. To our knowledge, no such design issue has been previously raised in the literature. In this paper we address this issue by presenting a new problem, called Congenial Talking Philosophers, to model group mutual exclusion. We also propose several criteria to evaluate solutions of the problem and to measure their performance. Finally, we provide an efficient and highly concurrent distributed algorithm for the problem in a shared-memory model where processes communicate by reading from and writing to shared variables. The distributed algorithm meets the proposed criteria, and has performance similar to some naive but centralized solutions to the problem.

Keyword Search in DHT-Based Peer-to-Peer Networks

Existing techniques for keyword/attribute search in structured P2P overlays suffer from several problems: unbalanced load, hot spots, fault tolerance, storage redundancy, and unable to facilitate ranking. In this paper, we present a general keyword index and search scheme for structured P2P networks that avoids these problems, and in which object insert, delete, and search can be efficiently performed. Some experimental results are also presented to support our claim

Asynchronous group mutual exclusion (extended abstract)

Mutual exclusion and coucurreucy are two fuudameutal and essentially opposite features in distributed systems. However, in some applications such as computer supported cooperative works (CSCW) we have found it necessary to impose mutual exclusion on different groups of processes in accessing a resource, while allowing processes of the same group to share the resource. To our knowledge, no such design issue has been raised in the literature. Our contributions of the paper are to present a new problem, which we refer to as the Congenial Talking Philosophers, to model the design issue for concurrency while mutual exclusion. We also propose several criteria to evaluate solutions of the problem and to measure their performance. Finally, we provide an efficient and highly concurrent distributed algorithm for the problem in a shared-memory model where processes communicate by reading from and writing to shared variables. The distributed algorithm meets the proposed criteria and has a similar performance as some naive but centralized solutions to the problem.

Quorum-based algorithms for group mutual exclusion

We propose a quorum system, which we referred to as the surficial quorum system, for group mutual exclusion. The surficial quorum system is geometrically evident and is easy to construct. It also has a nice structure based on which a truly distributed algorithm for group mutual exclusion can be obtained and processed loads can be minimized. When used with Maekawas algorithm, the surficial quorum system allows up to /spl radic/2n/m(m-l) processes to access a resource simultaneously, where n is the total number of processes and m is the total number of groups. We also present two modifications of Maekawas algorithm so that the number of processes that can access a resource at a time is not limited to the structure of the underlying quorum system, but to the number that the problem definition allows.

The congenial talking philosophers problem in computer networks

Summary. Group mutual exclusion occurs naturally in situations where a resource can be shared by processes of the same group, but not by processes of different groups. For example, suppose data is stored in a CD-jukebox. Then when a disc is loaded for access, users that need data on the disc can concurrently access the disc, while users that need data on a different disc have to wait until the current disc is unloaded.The design issues for group mutual exclusion have been modeled as the Congenial Talking Philosophers problem, and solutions for shared-memory models have been proposed [12,14]. As in ordinary mutual exclusion and many other problems in distributed systems, however, techniques developed for shared memory do not necessary apply to message passing (and vice versa). So in this paper we investigate solutions for Congenial Talking Philosophers in computer networks where processes communicate by asynchronous message passing. We first present a solution that is a straightforward adaptation from Ricart and Agrawalas algorithm for ordinary mutual exclusion. Then we show that the simple modification suffers a severe performance degradation that could cause the system to behave as though only one process of a group can be in the critical section at a time. We then present a more efficient and highly concurrent distributed algorithm for the problem, the first such solution in computer networks.

Strong interaction fairness via randomization

We present MULTI, a symmetric, distributed, randomized algorithm that, with probability one, schedules multiparty interactions in a strongly fair manner. To our knowledge, MULTI is the first algorithm for strong interaction fairness to appear in the literature. Moreover, the expected time taken by MULTI to establish an interaction is a constant not depending on the total number of processes in the system. In this sense, MULTI guarantees real-time response. MULTI makes no assumptions (other than boundedness) about the time it takes processes to communicate. It, thus, offers an appealing tonic to the impossibility results of Tsay and Bagrodia, and Joung concerning strong interaction fairness in an environment, shared-memory, or message-passing, in which processes are deterministic and the communication time is nonnegligible. Because strong interaction fairness is as strong a fairness condition that one might actually want to impose in practice, our results indicate that randomization may also prove fruitful for other notions of fairness lacking deterministic realizations and requiring real-time response.

Tug-of-War: An Adaptive and Cost-Optimal Data Storage and Query Mechanism in Wireless Sensor Networks

We propose Tug-of-War ( ToW ) for data storage and query mechanism in sensor networks. ToW is based on the concept of data-centric storage where events and queries meet on some rendezvous node so that queries for the events can be sent directly to the node without being flooded to the network. However, rather than fixing the rendezvous point, we dynamically replicate the point and float them in between query nodes and event sensor nodes according to the relative frequencies of events and queries. By carefully calculating the optimal setting, we are able to minimize the total communication costs while adapting to the environment.

From P3P to Data Licenses

P3P provides a standard means for Web sites to disclose their privacy policies when they need users’ personal data for processing. A user can then decide whether or not to provide personal data to the sites based on the disclosed policies. The decision process can also be made automatic through an agent or browser via the privacy preferences set by the user. As can be seen, however, this mechanism cannot guarantee that Web sites do act according to their policies once they have obtained user’s personal data. In light of this, we proposed a new technical and legal approach, called Online Personal Data Licensing (OPDL). The idea is that the use of a person’s data must be authorized by the person through the issue of data licenses. Licenses can then be checked to prevent personal data from being misused. This paper focuses on the implementation of OPDL. As P3P provides a standard format for expressing privacy practices about personal data, we use it here to implement data licenses.

On personal data license design and negotiation

Web applications often require users to provide personal information for customization, identification, or completing a transaction. However, the way we disclose our information in current cyberspace does not allow us to control the usage, release and circulation of the information, violating the basic principle of personal information privacy. Online personal data licensing (OPDL) is a framework to bring the control of personal information back to individuals by requiring application and service providers to obtain a license from a person before collecting, processing, and using his personal information. In this paper we present the license design and automation of the license negotiation process.

Wildcard Search in Structured Peer-to-Peer Networks

We address wildcard search in structured peer-to-peer (P2P) networks, which, to our knowledge, has not yet been explored in the literature. We begin by presenting an approach based on some well-known techniques in information retrieval (IR) and discuss why it is not appropriate in a distributed environment. We then present a simple and novel technique to index objects for wildcard search in a fully decentralized manner, along with some search strategies to retrieve objects. Our index scheme, as opposed to a traditional IR approach, can achieve quite balanced loads, avoid hop spots and single point of failure, reduce storage and maintenance costs, and offer some ranking mechanisms for matching objects. We use the compact disc (CD) records collected in FreeDB (http://freedb.org) as the experimental data set to evaluate our scheme. The results confirm that our index scheme is very effective in balancing the load. Moreover, search efficiency depends on the information given in a query: the more the information, the higher the performance.