Rosé: Flexible Replication With Strong Semantics For Partitioned Databases
Summary: Rosé fuses snapshot/epoch mechanisms with async replication to provide monotonic-prefix backups and push-based lag tracking with backpressure to bound replication lag. Decoupling replication and apply yields fast recovery and full throughput after failover; implemented in Chablis to keep single-DC latency while adding multi-DC durability. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Ioannis Zarkadas (Columbia University)
- 2. Kelly Kostopoulou (Columbia University)
- 3. Thomas Graham (Columbia University)
- 4. Junfeng Yang (Columbia University)
- 5. Philip A. Bernstein (Microsoft)
- 6. Asaf Cidon (Columbia University)
- 7. Tamer Eldeeb (Columbia University)
BibTeX Citation
@inproceedings{zarkadas_cidr26,
address = {Amsterdam, Netherlands},
series = {{CIDR} '26},
title = {{Rosé: Flexible Replication With Strong Semantics For Partitioned Databases}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Zarkadas, Ioannis and Kostopoulou, Kelly and Graham, Thomas and Yang, Junfeng and Bernstein, Philip A. and Cidon, Asaf and Eldeeb, Tamer},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 73 | Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases | 2017 | SIGMOD | 0.00037333356 |
| 208 | CockroachDB: The Resilient Geo-Distributed SQL Database | 2020 | SIGMOD | 0.00024968157 |
| 604 | Socrates: The New SQL Server in the Cloud | 2019 | SIGMOD | 0.0001584774 |
| 1,213 | MyRocks: LSM-Tree Database Storage Engine Serving Facebook's Social Graph | 2020 | VLDB | 0.00011646797 |
| 1,463 | Amazon Aurora: On Avoiding Distributed Consensus for I/Os, Commits, and Membership Changes | 2018 | SIGMOD | 0.00010700936 |
| 1,999 | On Brewing Fresh Espresso: LinkedIn’s Distributed Data Serving Platform | 2013 | SIGMOD | 9.3349118e-05 |
| 3,088 | Query Fresh: Log Shipping on Steroids | 2018 | VLDB | 7.7694381e-05 |
| 6,402 | C5: Cloned Concurrency Control that Always Keeps Up | 2023 | VLDB | 5.8859793e-05 |
| 11,114 | Chablis: Fast and General Transactions in Geo-Distributed Systems | 2024 | CIDR | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,402 | C5: Cloned Concurrency Control that Always Keeps Up | 2023 | VLDB |
| 2 | 5,331 | ConfluxDB: Multi-Master Replication for Partitioned Snapshot Isolation Databases | 2014 | VLDB |
| 3 | 1,754 | Middleware based Data Replication providing Snapshot Isolation | 2005 | SIGMOD |
| 4 | 13,034 | A Transaction Replication Scheme for a Replicated Database with Node Autonomy | 1994 | VLDB |
| 5 | 3,999 | An Efficient Scheme for Providing High Availability | 1992 | SIGMOD |
| 6 | 7,534 | A Fault-Tolerant Commit Protocol for Replicated Databases | 1992 | PODS |
| 7 | 3,026 | Database Replication: a Tale of Research across Communities | 2010 | VLDB |
| 8 | 9,102 | Asymmetric-Partition Replication for Highly Scalable Distributed Transaction Processing in Practice | 2020 | VLDB |
| 9 | 3,975 | Scalable Replay-Based Replication For Fast Databases | 2017 | VLDB |
| 10 | 2,843 | Rose: Compressed, log-structured replication | 2008 | VLDB |