Lightweight causal and atomic group multicast
ACM Transactions on Computer Systems (TOCS)
Understanding the limitations of causally and totally ordered communication
SOSP '93 Proceedings of the fourteenth ACM symposium on Operating systems principles
Impossibility of distributed consensus with one faulty process
Journal of the ACM (JACM)
Fault-tolerant broadcasts and related problems
Distributed systems (2nd Ed.)
Broadcast Protocols for Distributed Systems
IEEE Transactions on Parallel and Distributed Systems
A High Performance Totally Ordered Multicast Protocol
Selected Papers from the International Workshop on Theory and Practice in Distributed Systems
Totally ordered multicast in large-scale systems
ICDCS '96 Proceedings of the 16th International Conference on Distributed Computing Systems (ICDCS '96)
Newtop: a fault-tolerant group communication protocol
ICDCS '95 Proceedings of the 15th International Conference on Distributed Computing Systems
A Hierarchy of Totally Ordered Multicasts
A Hierarchy of Totally Ordered Multicasts
Multicast transport protocols: a survey and taxonomy
IEEE Communications Magazine
Multipoint communication: a survey of protocols, functions, and mechanisms
IEEE Journal on Selected Areas in Communications
Anonymous agreed order multicast: performance and free riding
ICDCIT'06 Proceedings of the Third international conference on Distributed Computing and Internet Technology
| Hi-index | 0.00 |
Membership-insensitive group transport protocols are particularly desirable for large groups of fast-varying membership where the distributed application being served insists on collective output and survivability rather than producing a consistent record of successive group views. An overview of such a protocol, able to maintain agreed delivery order of multicast messages across the group except for scenarios that can be made arbitrarily improbable, is presented along with a proposed specification of the so-called '1C network service with ContiguityDetector' it is built upon. Key properties of the protocol are expressed through some graph-theoretic observations. LAN implementation experience and performance measurements are described to conclude that the group throughput remains high under constant group membership and, there being virtually no group reconfiguration overhead, varies gracefully in step with the number of active group members.