The problem of cache sharing for supporting data access in mobile ad hoc networks is studied in this paper. The key to this problem is to discover a requested data item in an efficient manner. In the paper, we propose two caching protocols, IXP and DPIP, which distinguish themselves from the existing ones in that they fully exploit in-zone broadcasts to facilitate cache sharing operation. In particular, the DPIP protocol offers an implicit index push property, which is highly useful for enhancing cache hit ratio in the neighborhood of a data requester node. Moreover, our protocols also exploit the broadcasts to facilitate the design of a simple but efficient count-based cache replacement scheme. Performance study shows that the proposed protocols can significantly improve the performance of data access in a mobile ad hoc network.

In this paper, we present a novel protocol for disseminating data in broadcast environments such that view consistency, a useful correctness criterion for broadcast environments, is guaranteed. Our protocol is based on concurrency control information that is constructed by the server and is broadcasted at the beginning of each broadcast cycle. The concurrency control information mainly captures read-from relations among update transactions. A salient feature of the protocol is that the concurrency control information is small in size, but precise enough for reducing unnecessary abortion of mobile transactions. The small-sized concurrency control information implies low communication overhead on broadcasting system. In addition, the computation overheads imposed by the algorithm on the server and the clients are low. We also address the reliability issue of wireless communication and the incorporation of a prefetching mechanism into our protocol. Simulation results demonstrate the superiority of our protocol in comparison with existing methods. Furthermore, we have extended our protocol to deal with local view consistency which requires that all mobile transactions submitted by the same client observe the same serial order of update transactions

We propose an approach for implementing rollback recovery in a distributed computing system. A concept of logical ring is introduced for the maintenance of information required for consistent recovery from a system crash. Message processing order of a process is kept by all other processes on its logical ring. Transmission of data messages are accompanied by the circulation of the associated order messages on the ring. The sizes of the order messages are small. In addition, redundant transmission of order information is avoided, thereby reducing the communication overhead incurred during failure free operation. Furthermore, updating of the order information and garbage collection task are simplified in the proposed mechanism. Our approach does not require information about message processing order be written to stable storage; in fact, the time consuming operations of saving information in stable storage are confined to the checkpointing activities. When failures occur, a surviving process need roll back only if some preceding order information is totally lost, which is relatively unlikely considering the ever growing speed of communication networks. It is shown that a system can recover correctly as long as there exists at least one surviving process.

In this paper we propose a new mechanism for implementing checkpoint/rollback-recovery in a distributed computing system. A logical-ring structure is introduced for the maintenance of recovery-related information. Message processing order of a process is maintained by all other processes on its associated ring. It requires no time-consuming operations of writing order information into stable storage. As a result, fail-free overhead is small. When failures occur, only failed processes have to roll back to their latest checkpoints. Surviving processes continue execution without being blocked. Output commit is fast as it needs no synchronization before a message is sent to the outside world.>