The pinwheel asynchronous atomic broadcast protocols

Author

Cristian, Flaviu ; Mishra, Shivakant

Author_Institution

Dept. of Comput. Sci. & Eng., California Univ., San Diego, La Jolla, CA, USA

fYear

1995

fDate

25-27 Apr 1995

Firstpage

215

Lastpage

221

Abstract

We discuss two asynchronous atomic broadcast protocols that provide fast delivery and stability times, use a small number of messages to accomplish a broadcast, distribute evenly the processing load, use efficient flow control techniques, and provide gracefully degraded performance in the presence of communication failures. In a prototype implementation on top of UDP and Ethernet, for a group of three broadcast servers, these protocols achieve a throughput of up to a thousand independent broadcasts per second and measure average delivery and stability times of 2.9 and 4.7 msec

Keywords

fault tolerant computing; message passing; multiprocessor interconnection networks; protocols; stability; system recovery; Ethernet; UDP; broadcast servers; communication failures; efficient flow control techniques; evenly distributed processing load; fast delivery times; fast stability times; gracefully degraded performance; messages; pinwheel asynchronous atomic broadcast protocols; prototype implementation; Broadcasting; Communication system control; Computer science; Degradation; Delay; Ethernet networks; Fault tolerance; Protocols; Prototypes; Stability; Throughput;

fLanguage

English

Publisher

ieee

Conference_Titel

Autonomous Decentralized Systems, 1995. Proceedings. ISADS 95., Second International Symposium on

Conference_Location

Phoenix, AZ

Print_ISBN

0-8186-7087-8

Type

conf

DOI

10.1109/ISADS.1995.398975

Filename

398975