Resource addressable network
Balasubramaneyam Maniymaran · eScholarship@McGill (McGill) · 2009
The success of P2P file sharing applications prompted new efforts to explore the applicability of using P2P overlays in other applications, for example, to build computing clusters. These new genres of P2P applications necessitate mechanisms for discovering resources (not contents) in P2P systems. Existing solutions address this issue by converting the resource descriptions into contents and then use content discovery overlays to store and retrieve these descriptions. They use structured P2P overlays that provides the best search efficiency for content discovery. Even though this approach works well, it suffers from a number of drawbacks. For example, structured overlays are designed for discovering specific contents and querying to find a range of content makes the system inefficient. Unfortunately, it is highly likely for resources queries to include range specification like "memory ≥ 3GB." Further, these research efforts discover resources based on their attributes, but neglect connectivity metrics, latency and bandwidth. These issues warrant another look at resource discovery in distributed systems. I introduce a new resource discovery scheme called resource addressable network (RAN) to address these issues. The inability to support range queries in structured overlays is a result from assigning the nodes with random node IDs. The mechanisms introduced in this thesis produce non-random node IDs such that, while they provide a structured search space, they also retain the characteristics of the unstructured metric space where the resources are naturally located, for example, the attribute–value space; the proximity between two resources in terms of their attributes is reflected also in their node IDs. Producing such a mapping from a unstructured metric space to a structured search space and designing supporting architecture is the key contribution of this thesis. RAN is multi-tier discovery substr