Congestion avoidance and control
SIGCOMM '88 Symposium proceedings on Communications architectures and protocols
Lightweight causal and atomic group multicast
ACM Transactions on Computer Systems (TOCS)
Totem: a fault-tolerant multicast group communication system
Communications of the ACM
Time, clocks, and the ordering of events in a distributed system
Communications of the ACM
Proceedings of the 2000 ACM/IEEE conference on Supercomputing
Peer-to-Peer: Harnessing the Power of Disruptive Technologies
Peer-to-Peer: Harnessing the Power of Disruptive Technologies
Reliable Distributed Computing with the ISIS Toolkit
Reliable Distributed Computing with the ISIS Toolkit
Data management and transfer in high-performance computational grid environments
Parallel Computing - Parallel data-intensive algorithms and applications
Causally Ordering Group Communication Protocol
Proceedings of the 1994 International Conference on Parallel and Distributed Systems
An evaluation of the Amoeba group communication system
ICDCS '96 Proceedings of the 16th International Conference on Distributed Computing Systems (ICDCS '96)
Two-Layered Protocol for a Large-Scale Group of Processes
ICPADS '02 Proceedings of the 9th International Conference on Parallel and Distributed Systems
Group Communication Protocol for Realtime Applications
ICDCS '98 Proceedings of the The 18th International Conference on Distributed Computing Systems
Detecting Abandoned Packages in a Multi-Camera Video Surveillance System
AVSS '03 Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance
SplitStream: high-bandwidth multicast in cooperative environments
SOSP '03 Proceedings of the nineteenth ACM symposium on Operating systems principles
NIST Net: a Linux-based network emulation tool
ACM SIGCOMM Computer Communication Review
Heterogeneous Groups to Causally Ordered Delivery
ICDCSW '04 Proceedings of the 24th International Conference on Distributed Computing Systems Workshops - W7: EC (ICDCSW'04) - Volume 7
The Grid 2: Blueprint for a New Computing Infrastructure
The Grid 2: Blueprint for a New Computing Infrastructure
Causally Ordered Delivery for a Hierarchical Group
ICPADS '04 Proceedings of the Parallel and Distributed Systems, Tenth International Conference
Design of a Hierarchical Group to Realize a Scalable Group
AINA '05 Proceedings of the 19th International Conference on Advanced Information Networking and Applications - Volume 1
Hi-index | 0.00 |
According to the advance of computer and network technologies, information systems are getting scalable. Especially, peer-to-peer (P2P) overlay networks and Grid computing system are now taking a central position in information systems. In these systems, a large number of peer processes are cooperating. In group communication, each peer process sends a message to multiple processes while receiving messages from multiple processes. Here, messages transmitted are required to be causally/totally delivered to every common destination of the messages. The computation and communication complexity is O(n) to O(n2) for the number n of peer processes. In order to reduce the overheads, a group is divided into smaller subgroups where processes exchange messages with other subgroups only through gateway processes while processes directly exchange messages in each subgroup. In this paper, we discuss a hierarchical group protocol aiming at reducing communication and computation overheads for supporting a scalable group of cooperating peer processes. In traditional hierarchical group protocols, each subgroup communicates with another subgroup through a single gateway communication link. A gateway communication link among subgroups implies performance bottleneck and a single point of failure. In order to increase the throughput and reliability of inter-subgroup communication, messages are in parallel transmitted in a network striping way through multiple channels between multiple processes in the subgroups. We discuss a striping multi-channel inter-subgroup communication protocol (SMIP). We evaluate SMIP in terms of stability of bandwidth and message loss ratio and show how SMIP can support more stable bandwidth and message loss ratio.