Chain Replication for Supporting High Throughput and Availability

By Robbert van Renesse, Fred B. Schneider. USENIX Symposium on Operating Systems Design and Implementation, 2004

526 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/9a091dacf855c1b6a0cd4361194e238fe6e1ff11

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Windows Azure Storage: a highly available cloud storage service with strong consistency (2011, background): “[20] has shown, via Chain Replication, the feasibility of building largescale storage systems providing both strong consistency and high availability, which was later extended to allow reading from any replica [21].”
NetChain: Scale-Free Sub-RTT Coordination (2018, methodology): “(ii) We design a variant protocol of chain replication [15] to ensure strong consistency of the keyvalue store.”
Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases (2017, background): “While chain replication [8] and its alternatives can reduce network cost, they still suffer from synchronous stalls and additive latencies.”
Ray: A Distributed Framework for Emerging AI Applications (2017, background): “ntrol state of the system, and it is a unique feature of our design. At its core, GCS is a key-value store with pubsub functionality. We use sharding to achieve scale, and per-shard chain replication [61] to provide fault tolerance. The primary reason for the GCS and its design is to maintain fault ”
Fault-scalable Byzantine fault-tolerant services (2005, background): “Various services and data structures that e.ciently tolerate benign failures have been developed (e.g., Paxos [21], Boxwood [25], and Chain Replication [38]).”
Proposal Scaling Distributed Machine Learning with System and Algorithm Co-design (2016, unknown): “4 shows that entries are replicated using chain replication [142] to achieve fault tolerance.”
Efficient Replica Maintenance for Distributed Storage Systems (2006, background): “FAB [33] and Chain Replication [38] both consider how the number of possible replicas sets affects data durability.”
Stronger Semantics for Low-Latency Geo-Replicated Storage (2013, unknown): “, chain replication [50] or Paxos [34]).”
Blockchain Consensus Protocols in the Wild (2017, background): “Chain replication [72, 25] arranges the n nodes linearly and each node normally only receives messages from its predecessor and sends messages to its successor.”
Don't settle for eventual: scalable causal consistency for wide-area storage with COPS (2011, methodology): “We built our system on top of independent clusters of FAWN-KV [5] nodes, which use chain replication [51] within a cluster to mask node failures.”