The Immediate Dependency Relation: An Optimal Way to Ensure Causal Group Communication

Abstract

In this paper we present a study on the subject of the Immediate Dependency Relation (IDR), and we show how by extending the IDR relation, one can ensure a global causal delivery in group communication, including in the overlapping group case. The main objective of this paper is to show that the use of the Immediate Dependency Relation (IDR) obliterates the notion that causality is expensive to set up in distributed systems. The IDR minimizes considerably the amount of control information sent per message to ensure causal ordering, without imposing restrictions in interaction (e.g. network topology, redifussion servers, executions models etc.). In order to demonstrate the feasibility of its implementation, we present an optimal broadcast causal protocol inspired by the IDR relation. We show the optimality of the protocol in terms of the amount of control information timestamped per message.

A Graph Transformation-Based Approach for the Validation of Checkpointing Algorithms in Distributed Systems

“…For this, the MCSR uses the Immediate Dependency Relation (IDR) [5]. The IDR graph greatly reduces the state-space of a system.…”

Synchronization Protocol for Real Time Multimedia in Mobile Distributed Systems

“…This protocol is also based on the Immediate Dependency Relation protocol presented in [21], in our implementation the size of the control information (overhead) for each message that is sent through communication channels derives according to the number of parallel messages that immediately precede a causal message m. This means a fifo type message does not content overhead. Since the structure H(m) in the wired channels only uses recent messages that immediately precede a message m, the cardinality for the overhead generated is given by the cardinality of the number of concurrent messages in the communication group, which vary between 0 and n-1 (0 ≤| H(m) |≤ n-1), where n is the number of mobile hosts in the communication group.…”

An Asynchronous Control Method For Reducing Inconsistency In DVE

“…In [6], the authors propose a lock-step synchronization technique, which avoids the occurrence of inconsistency by forcing the clocks of the blocking nodes to advance until all of the nodes finish the calculation in the last cycle, and they then enter into the next cycle. This method can ensure the correctness of the system function, but the performance cannot meet the requirements of the interaction of the user.…”