Christopher Peery

PlanetP: using gossiping to build content addressable peer-to-peer information sharing communities

We introduce PlanetP, content addressable publish/subscribe service for unstructured peer-to-peer (P2P) communities. PlanetP supports content addressing by providing: (1) a gossiping layer used to globally replicate a membership directory and an extremely compact content index; and (2) a completely distributed content search and ranking algorithm that help users find the most relevant information. PlanetP is a simple, yet powerful system for sharing information. PlanetP is simple because each peer must only perform a periodic, randomized, point-to-point message exchange with other peers. PlanetP is powerful because it maintains a globally content-ranked view of the shared data. Using simulation and a prototype implementation, we show that PlanetP achieves ranking accuracy that is comparable to a centralized solution and scales easily to several thousand peers while remaining resilient to rapid membership changes.

Wayfinder: navigating and sharing information in a decentralized world

Social networks offering unprecedented content sharing are rapidly developing over the Internet. Unfortunately, it is often difficult to both locate and manage content in these networks, particularly when they are implemented on current peer-to-peer technologies. In this paper, we describe Wayfinder, a peer-to-peer file system that targets the needs of medium-sized content sharing communities. Wayfinder seeks to advance the state-of-the-art by providing three synergistic abstractions: a global namespace that is uniformly accessible across connected and disconnected operation, content-based queries that can be persistently embedded into the global namespace, and automatic availability management. Interestingly, Wayfinder achieves much of its functionality through the use of a peer-to-peer indexed data storage system called PlanetP: essentially, Wayfinder constructs the global namespace, locates specific files, and performs content searches by posing appropriate queries to PlanetP. We describe this query-based design and present preliminary performance measurements of a prototype implementation.

Multi-dimensional search for personal information management systems

With the explosion in the amount of semi-structured data users access and store in personal information management systems, there is a need for complex search tools to retrieve often very heterogeneous data in a simple and efficient way. Existing tools usually index text content, allowing for some IR-style ranking on the textual part of the query, but only consider structure (e.g., file directory) and metadata (e.g., date, file type) as filtering conditions. We propose a novel multi-dimensional approach to semi-structured data searches in personal information management systems by allowing users to provide fuzzy structure and metadata conditions in addition to keyword conditions. Our techniques provide a complex query interface that is more comprehensive than content-only searches as it considers three query dimensions (content, structure, metadata) in the search. We propose techniques to individually score each dimension, as well as a framework to integrate the three dimension scores into a meaningful unified score. Our work is integrated in Wayfinder, an existing fully-functioning file system. We perform a thorough experimental evaluation of our techniques to show the effect of approximating individual dimensions on the overall scores and ranks of files, as well as on query performance. Our experiments show that our scoring strategy adequately takes into account the approximation in each dimension to efficiently evaluate fuzzy multi-dimensional queries. In addition, fuzzy query conditions in non-content dimensions can significantly improve scoring (and thus ranking) accuracy.

DDDDRRaW: A prototype toolkit for distributed real-time rendering on commodity clusters

We describe DDDDRRaW, a prototype toolkit for distributed real-time rendering on commodity clusters. In constrast to most work on cluster computing, DDDDRRaW supports a repeated, low-latency computation, the drawing of frames which must take place on a time scale of 30-100 ms. DDDDRRaW employs image layer decomposition, a rendering-specific work partitioning algorithm described and evaluated using simulation. In this paper we address implementation issues. In particular, one important issue we explore is how to exploit the potential parallelism afforded by the multiple hardware resources of each node: the CPU, the network adapter and the video card. We evaluate DDDDRRaWs live performance on two small workstation clusters representing different points in the technology spectrum. Our results show that DDDDRRaW effectively exploits cluster resources to improve real-time rendering performance and should scale well to moderately sized clusters.

Efficient Multidimensional Fuzzy Search for Personal Information Management Systems

With the explosion in the amount of semistructured data users access and store in personal information management systems, there is a critical need for powerful search tools to retrieve often very heterogeneous data in a simple and efficient way. Existing tools typically support some IR-style ranking on the textual part of the query, but only consider structure (e.g., file directory) and metadata (e.g., date, file type) as filtering conditions. We propose a novel multidimensional search approach that allows users to perform fuzzy searches for structure and metadata conditions in addition to keyword conditions. Our techniques individually score each dimension and integrate the three dimension scores into a meaningful unified score. We also design indexes and algorithms to efficiently identify the most relevant files that match multidimensional queries. We perform a thorough experimental evaluation of our approach and show that our relaxation and scoring framework for fuzzy query conditions in noncontent dimensions can significantly improve ranking accuracy. We also show that our query processing strategies perform and scale well, making our fuzzy search approach practical for every day usage.

Fuzzy Multi-Dimensional Search in the Wayfinder File System

With the explosion in the amount of semi-structured data users access and store, there is a need for complex search tools to retrieve often very heterogeneous data in a simple and efficient way. Existing tools usually index text content, allowing for some IR-style ranking on the textual part of the query, but only consider structure (e.g., file directory) and metadata (e.g., date, file type) as filtering conditions. We propose a novel multidimensional querying approach to semi-structured data searches in personal information systems by allowing users to provide fuzzy structure and metadata conditions in addition to traditional keyword conditions. The provided query interface is more comprehensive than content-only searches as it considers three query dimensions (content, structure, metadata) in the search. We have implemented our proposed approach in the Wayfinder file system. In this demo, we will use this implementation to both present an overview of the unified scoring framework underlying the fuzzy multi-dimensional querying approach and demonstrate its potential in improving search results.

Wayfinder: a federated information sharing and management system

The decreasing costs of computing devices, increases in connectivity, and improved performance are altering the computing environments of users in fundamental ways. Users are no longer restricted to operating single devices in isolation but rather distribute and access information across many devices and develop complex sharing patterns among groups of users. Unfortunately, while these trends are significantly enriching the user’s computing experience, they are also increasing the data management overhead as users must explicitly reason about data placement and replication across multiple devices and logical sharing groups. In this thesis, we present the Wayfinder file system, which was designed to simplify the management of information in federate systems. Wayfinder focuses on three critical management deficiencies present in most current federated environments: (1) the lack of a consistent view for stored information across devices, (2) the required manual management of replicated information, and (3) the limited search/ranking capability for finding relevant information. The Wayfinder file system addresses these deficiencies by providing three synergistic abstractions: (1) a global namespace that is uniformly accessible across connected and disconnected operation, (2) a user-centric automatic availability management to ensure continuous access to information based on data-centric availability policies, and (3) a multi-dimensional fuzzy search framework that significantly improves relevance ranking. We will show that these abstractions simplify the management burden by requiring users to reason only about the data and its properties while ignoring the underlying physical complexities of the system. Underlying all three abstractions is a common implementation layer that adheres to three principles. First, any subset of nodes in a Wayfinder community can interact normally when they are interconnected, regardless of the membership of the subset. Second, all protocols and interactions are tolerant of a weakly consistent model allowing them to suffer unexpected devices departures. Finally, devices are assumed to be owned by specific users and so should prioritize the needs of their owners in the presence of resource constraints, while using excess resources to benefit the community as a whole.