Slashing the disaggregation tax in heterogeneous data centers with FractOS
Lluís Vilanova, Lina Maudlej, Shai Bergman, Till Miemietz, Matthias Hille, Nils Asmussen, Michael Roitzsch, Hermann Härtig, Mark Silberstein
Abstract
Disaggregated heterogeneous data centers promise higher efficiency, lower total costs of ownership, and more flexibility for data-center operators. However, current software stacks can levy a high tax on application performance. Applications and OSes are designed for systems where local PCIe-connected devices are centrally managed by CPUs, but this centralization introduces unnecessary messages through the shared data-center network in a disaggregated system.
We present FractOS, a distributed OS that is designed to minimize the network overheads of disaggregation in heterogeneous data centers. FractOS elevates devices to be firstclass citizens, enabling direct peer-to-peer data transfers and task invocations among them, without centralized application and OS control. FractOS achieves this through: (1) new abstractions to express distributed applications across services and disaggregated devices, (2) new mechanisms that enable devices to securely interact with each other and other data-center services, (3) a distributed and isolated OS layer that implements these abstractions and mechanisms, and can run on host CPUs and SmartNICs.
Our prototype shows that FractOS accelerates real-world heterogeneous applications by 47%, while reducing their network traffic by 3×.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 9136ed20-e14f-4e8b-9f53-efc72a14b059Cited by top-tier papers8
- A Tale of Two Paths: Toward a Hybrid Data Plane for Efficient Far-Memory ApplicationsLei Chen, Shi Liu, Chenxi Wang, Haoran Ma et al.OSDI 2024 · 16 citations
- CHIME: A Cache-Efficient and High-Performance Hybrid Index on Disaggregated MemoryXuchuan Luo, Jiacheng Shen, Pengfei Zuo, Xin Wang et al.SOSP 2024 · 10 citations
- RL-Watchdog: A Fast and Predictable SSD Liveness Watchdog on Storage SystemsJinyong Ha, Sangjin Lee, Heon Young Yeom, Yongseok SonUSENIX ATC 2024 · 10 citations
- ScalaCache: Scalable User-Space Page Cache Management with Software-Hardware CoordinationLi Peng, Yuda An, You Zhou, Chenxi Wang et al.USENIX ATC 2024 · 6 citations
- Harvesting Idle Memory for Application-managed Soft State with MidasYifan Qiao, Zhenyuan Ruan, Haoran Ma, Adam Belay et al.NSDI 2024 · 5 citations
Builds on2
Related papers
- R2d2: Robotized Reconfigurable Network for Disaggregated DatacentersLinus Y. Wong, Zhiyao Tang, Justin R. Yu, Zhilei Zheng et al.ISCA 2026
- DiLOS: Do Not Trade Compatibility for Performance in Memory DisaggregationWonsup Yoon, Jisu Ok, Jinyoung Oh, Sue Moon et al.EuroSys 2023 · 21 citations
- Understanding the Effect of Data Center Resource Disaggregation on Production DBMSsQizhen Zhang, Yifan Cai, Xinyi Chen, Sebastian Angel et al.VLDB 2020 · 64 citations
- MIND: In-Network Memory Management for Disaggregated Data CentersSeung-Seob Lee, Yanpeng Yu, Yupeng Tang, Anurag Khandelwal et al.SOSP 2021 · 51 citations
- DHAP: Towards Efficient OLAP in a Disaggregated and Heterogeneous EnvironmentGuangda Liu, Chenqi Zhang, Yizhou Shan, Hao Feng et al.SC 2025 · 1 citation
