作者: Fred B. Schneider , Robbert van Renesse
DOI:
关键词:
摘要: Chain replication is a new approach to coordinating clusters of fail-stop storage servers. The intended for supporting large-scale services that exhibit high throughput and availability without sacrificing strong consistency guarantees. Besides outlining the chain protocols themselves, simulation experiments explore performance characteristics prototype implementation. Throughput, availability, several object-placement strategies (including schemes based on distributed hash table routing) are discussed.