D-RDMA: Bringing Zero-Copy RDMA to Database Systems
Summary: Shows that canonical RDMA in DB engines produces many small, noncontiguous DMAs forcing costly copies into large buffers and forfeiting zero-copy benefits. D-RDMA: a declarative RDMA API that offloads fragment aggregation to a smartNIC to emit large DMAs, restoring zero-copy and driving up to 98 Gbps with near-zero CPU. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. André Ryser (University of Freiburg)
- 2. Alberto Lerner (University of Freiburg)
- 3. Alex Forencich (University of California San Diego)
- 4. Philippe Cudré-Mauroux (University of Freiburg)
BibTeX Citation
@inproceedings{ryser_cidr22,
address = {Amsterdam, Netherlands},
series = {{CIDR} '22},
title = {{D-RDMA: Bringing Zero-Copy RDMA to Database Systems}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Ryser, André and Lerner, Alberto and Forencich, Alex and Cudré-Mauroux, Philippe},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,911 | Databases on Modern Networks: A Decade of Research That Now Comes into Practice | 2023 | VLDB | 5.4284007e-05 |
| 7,939 | GraphINC: Graph Pattern Mining at Network Speed | 2023 | SIGMOD | 5.4223464e-05 |
| 9,827 | AMNES: Accelerating the computation of data correlation using FPGAs | 2023 | VLDB | 5.1249969e-05 |
| 11,909 | DBMS Annihilator: A High-Performance Database Workload Generator in Action | 2022 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 27 | Database Architecture Optimized for the New Bottleneck: Memory Access | 1999 | VLDB | 0.0005158963 |
| 48 | Weaving Relations for Cache Performance | 2001 | VLDB | 0.00043805923 |
| 889 | Rack-Scale In-Memory Join Processing using RDMA | 2015 | SIGMOD | 0.00013247362 |
| 945 | The End of Slow Networks: It's Time for a Redesign | 2016 | VLDB | 0.00012939225 |
| 1,028 | High-Speed Query Processing over High-Speed Networks | 2016 | VLDB | 0.00012422084 |
| 1,366 | Designing Distributed Tree-based Index Structures for Fast RDMA-capable Networks | 2019 | SIGMOD | 0.00010912114 |
| 3,608 | DFI: The Data Flow Interface for High-Speed Networks | 2021 | SIGMOD | 7.1650501e-05 |
| 6,534 | DPI: The Data Processing Interface for Modern Networks | 2019 | CIDR | 5.7541988e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 7,175 | CoRM: Compactable Remote Memory over RDMA | 2021 | SIGMOD |
| 2 | 11,867 | KafkaDirect: Zero-copy Data Access for Apache Kafka over RDMA Networks | 2022 | SIGMOD |
| 3 | 7,976 | Rethinking Stateful Stream Processing with RDMA | 2022 | SIGMOD |
| 4 | 8,758 | DDS: DPU-optimized Disaggregated Storage | 2024 | VLDB |
| 5 | 1,059 | Accelerating Relational Databases by Leveraging Remote Memory and RDMA | 2016 | SIGMOD |
| 6 | 13,763 | Scalable Distributed Transaction Processing on Modern RDMA-enabled Networks | 2021 | SIGMOD |
| 7 | 4,201 | The Case for Distributed Shared-Memory Databases with RDMA-Enabled Memory Disaggregation | 2023 | VLDB |
| 8 | 945 | The End of Slow Networks: It's Time for a Redesign | 2016 | VLDB |
| 9 | 8,752 | Zero-sided RDMA: Network-driven Data Shuffling for Disaggregated Heterogeneous Cloud DBMSs | 2024 | SIGMOD |
| 10 | 3,270 | Rethinking Database High Availability with RDMA Networks | 2019 | VLDB |