March 2026

Conference Paper

DoCeph: DPU-Offloaded Messaging in Ceph for Reduced Host CPU Utilization

By:
Park, Kuri; Yoon, Sungmin; Talibli, Faird; Park, Sungyong; Hyuk kwak, Jae; Jeong, Kimoon; Khan, Awais ; Kim, Youngjae
Page Number:
1658-1666
Book Title:
SC Workshops '25: Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis
Publication Date:
March 2026
Publisher Location:
ACM, St Louis, MO, Missouri, United States of America
Conference Name:
International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'25)
Conference Location:
St Louis, Missouri, United States of America
Conference Sponsor:
IEEE SIGHPC
View DOI Listing:
https://doi.org/10.1145/3731599.3767525

Abstract

Ceph is a widely used distributed object store, but its messenger layer imposes substantial CPU overhead on the host. To address this limitation, we propose DoCeph, a DPU-offloaded storage architecture for Ceph that disaggregates the system by offloading the communication-intensive messaging component to the DPU while retaining the storage backend on the host. The DPU efficiently manages communication, using lightweight RPC for metadata operations and DMA for data transfer. Moreover, DoCeph introduces a pipelining technique that overlaps data transmission with buffer preparation, mitigating hardware-imposed transfer size limitations. We implemented DoCeph on a Ceph cluster with NVIDIA BlueField-3 DPUs. Evaluation results indicate that DoCeph cuts host CPU usage by up to 92% while sustaining stable throughput and providing larger performance benefits for object writes over 1 MB.


Related Researchers