arXiv (Cornell University) · 2017 · 34 citations · 1 references
ComputingComputer ScienceComputer SystemsDistributed SystemsFault ToleranceFault-tolerant SystemsDistributed ComputingDistributed Systems PerformanceHigh AvailabilityQueueing SystemsQueueing TheoryReliable Distributed SystemsCommunication Protocol DesignDistributed Communication TopologyDistributed QueueingDistributed Systems CommunicationFault Tolerance MechanismsMessage QueuesMessage Queuing
This paper surveys the message brokers that are in vogue today for distributed communication. Their primary goal is to facilitate the construction of decentralized topologies without single points of failure, enabling fault tolerance and high availability. These characteristics make them optimal for usage within distributed architectures. However, there are multiple protocols built to achieve this, and it would be beneficial to have a empirical comparison between their features and performance to determine their real-world applicability. This paper focuses on two popular protocols (Kafka and AMQP) and explores the divergence in their features as well as their performance under varied testing workloads.
1
Advanced Message Queuing Protocol
Steve Vinoski · IEEE Internet Computing · 2006 · 445 citations · Full text