DDS: DPU-optimized Disaggregated Storage

Summary: DDS uses DPUs, DMA, zero-copy, userspace I/O, and DPU-resident request execution to optimize disaggregated storage with minimal DBMS changes. It delivers higher throughput, order-of-magnitude lower latency, and saves tens of host CPU cores per server. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 13731
Venue: VLDB
Year: 2024
Pagerank: 5.3996947e-05
Overall Rank: 8,619 | 40.87%
DOI: 10.14778/3681954.3682002

Incoming Non-self Citations Over Time

Authors

1. Qizhen Zhang (University of Toronto)
2. Philip A. Bernstein (Microsoft)
3. Badrish Chandramouli (Microsoft)
4. Jiasheng Hu (University of Toronto)
5. Yiming Zheng (University of Toronto)

BibTeX Citation

@article{zhang_vldb24,
        title = {{DDS: DPU-optimized Disaggregated Storage}},
        author = {Zhang, Qizhen and Bernstein, Philip A. and Chandramouli, Badrish and Hu, Jiasheng and Zheng, Yiming},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {11},
        pages = {3304--3317},
        doi = {10.14778/3681954.3682002},
        url = {https://doi.org/10.14778/3681954.3682002},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
9,511	DPDPU: Data Processing with DPUs	2025	CIDR	5.25736e-05
10,073	DFlush: DPU-Offloaded Flush for Disaggregated LSM-based Key-Value Stores	2025	SIGMOD	5.1624218e-05
11,080	Analyzing Near-Network Hardware Acceleration with Co-Processing on DPUs	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 13 of 13 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
604	Socrates: The New SQL Server in the Cloud	2019	SIGMOD	0.0001584774
614	Faster: A Concurrent Key-Value Store with In-Place Updates	2018	SIGMOD	0.00015720975
1,283	PolarFS: An Ultra-low Latency and Failure Resilient Distributed File System for Shared Storage Cloud Database	2018	VLDB	0.00011337934
2,828	Exploiting Directly-Attached NVMe Arrays in DBMS	2020	CIDR	8.0803679e-05
3,196	Farview: Disaggregated Memory with Operator Off-loading for Database Engines	2022	CIDR	7.6467469e-05
3,632	FlexPushdownDB: Hybrid Pushdown and Caching in a Cloud DBMS	2021	VLDB	7.2368817e-05
4,557	Not your Grandpa's SSD: The Era of Co-Designed Storage Devices	2021	SIGMOD	6.6333658e-05
4,677	Redy: Remote Dynamic Memory Cache	2022	VLDB	6.5698961e-05
4,726	Computational Storage: Where Are We Today?	2021	CIDR	6.5364137e-05
5,196	Optimizing Data-intensive Systems in Disaggregated Data Centers with TELEPORT	2022	SIGMOD	6.3230009e-05
6,198	Database Kernels: Seamless Integration of Database Systems and Fast Storage via CXL	2024	CIDR	5.945932e-05
6,776	X-SSD: A Storage System with Native Support for Database Logging and Replication	2022	SIGMOD	5.777467e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	5,196	Optimizing Data-intensive Systems in Disaggregated Data Centers with TELEPORT	2022	SIGMOD
2	9,609	Lachesis: Robust Database Storage Management Based on Device-specific Performance Characteristics	2003	VLDB
3	7,341	Understanding the Performance Implications of the Design Principles in Storage-Disaggregated Databases	2024	SIGMOD
4	9,668	D-RDMA: Bringing Zero-Copy RDMA to Database Systems	2022	CIDR
5	10,073	DFlush: DPU-Offloaded Flush for Disaggregated LSM-based Key-Value Stores	2025	SIGMOD
6	11,080	Analyzing Near-Network Hardware Acceleration with Co-Processing on DPUs	2025	VLDB
7	976	The End of Slow Networks: It's Time for a Redesign	2016	VLDB
8	5,109	The Case for Distributed Shared-Memory Databases with RDMA-Enabled Memory Disaggregation	2023	VLDB
9	3,100	Rethinking Data Management Systems for Disaggregated Data Centers	2020	CIDR
10	9,511	DPDPU: Data Processing with DPUs	2025	CIDR