Scalable and leaderless Byzantine consensus in cloud computing environments

Traditional Byzantine consensus in distributed systems requires n ≥ 3f + 1, where n is the number of nodes. In this paper, we present a scalable and leaderless Byzantine consensus implementation based on gossip, requiring only n ≥ 2f + 1 nodes. Unlike conventional distributed systems, the network topology of cloud computing systems is often not fully connected, but loosely coupled and layered. Hence, we revisit the Byzantine consensus problem in cloud computing environments, in which each node maintains some number of neighbors, called local view. The message complexity of our Byzantine consensus scheme is O(n), instead of O(n ²). Experimental results and correctness proof show that our Byzantine consensus scheme can solve the Byzantine consensus problem safely in a scalable way without a bottleneck and a leader in cloud computing environments.     

Efficient Garbage Collection Schemes for Causal Message Logging with Independent Checkpointing

This paper presents three garbage collection schemes for causal message logging with independent checkpointing. The first scheme allows each process to autonomously remove useless log information in its volatile storage by piggybacking only some additional information without requiring any extra message and forced checkpoint. Additionally, it supports faster output commit than traditional schemes. The second scheme enables each process to remove a part of log information in the storage if more empty space is required. It reduces the number of processes participating in the garbage collection by using the size of the log information of each process. The third scheme is a hybrid scheme having the advantages of the two proposed schemes. Simulation results show that the third scheme significantly reduces the garbage collection overhead compared with the traditional schemes regardless of specific communication patterns of distributed applications.     

Revisiting Transaction Management in Multidatabase Systems

A lot of research efforts have focused on global serializability, global atomicity, and global deadlocks in multidatabase systems. Surprisingly, however, very few transaction processing model exists that ensures global serializability, global atomicity, and freedom from global deadlocks in a uniform manner. In this paper, we examine previous transaction processing models and propose a new transaction processing model that generates globally serializable and deadlock-free schedules in failure-prone multidatabase systems. A new transaction processing model adopts rigid conflict serializability as a correctness criterion on global serializability, and follows an emulated 2PC, criteria for global commitment, and an abort-based multidatabase recovery scheme for global serializability in failure-prone multidatabase systems. In addition, a deadlock-free policy is suggested where rigid conflict serializability is enforced when each subtransaction, including redo transactions, begins its execution. To practically support a new transaction processing model, Rigid Ticket Ordering (RTO) methods are designed. The proposed transaction processing model has the following improvements: (a) it resolves abnormal direct conflicts identified in this paper, (b) it imposes no restrictions on the execution of local transactions, and (c) it relaxes the restrictions on the execution of global transactions.