Abstract
Transactional memory is a rather novel approach to concurrency control in parallel computing, that has just recently found its way into distributed systems research. However, the research concentrates mainly on single processor solutions or cluster environment. In this paper we argue, that peer-to-peer systems would require a different design of transactional memory because of the increased failure-rate of nodes, slower network and possibility of network splits. We also present a few of our design ideas, namely increased performance and fault tolerance through the use of higher-level conflict detection and resolution via abstract data types and eventually consistency, that as we think could be important to a successful implementation of a scalable and resilient transactional memory.