Wave: Offloading Resource Management to SmartNIC Cores
Jack Tigar Humphries, Neel Natu, Kostis Kaffes, Stanko Novakovic, Paul Turner, Henry M. Levy, David E. Culler, Christos Kozyrakis
Abstract
SmartNICs are increasingly deployed in datacenters to offload tasks from server CPUs, improving the efficiency and flexibility of datacenter security, networking and storage. Optimizing cloud server efficiency in this way is critically important to ensure that virtually all server resources are available to paying customers. Userspace system software, specifically, decision-making tasks performed by various operating system subsystems, is particularly well suited for execution on mid-tier SmartNIC ARM cores. To this end, we introduce Wave, a framework for offloading userspace system software to processes/agents running on the SmartNIC. Wave uses Linux userspace systems to better align system functionality with SmartNIC capabilities. It also introduces a new host-SmartNIC communication API that enables offloading of even μs-scale system software. To evaluate Wave, we offloaded preexisting userspace system software including kernel thread scheduling, memory management, and an RPC stack to SmartNIC ARM cores, which showed a performance degradation of 1.1%-7.4% in an apples-to-apples comparison with on-host implementations. Wave recovered host resources consumed by on-host system software for memory management (saving 16 host cores), RPCs (saving 8 host cores), and virtual machines (an 11.2% performance improvement). Wave highlights the potential for rethinking system software placement in modern datacenters, unlocking new opportunities for efficiency and scalability.
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 905f001e-75c2-480b-befc-22414ff1f798Cited by top-tier papers1
Ask how each one uses itBuilds on21
- AIFM: High-Performance, Application-Integrated Far MemoryZhenyuan Ruan, Malte Schwarzkopf, Marcos K. Aguilera, Adam BelayOSDI 2020 · 224 citations
- Caladan: Mitigating Interference at Microsecond TimescalesJoshua Fried, Zhenyuan Ruan, Amy Ousterhout, Adam BelayOSDI 2020 · 213 citations
- RedLeaf: Isolation and Communication in a Safe Operating SystemVikram Narayanan, Tianjiao Huang, David Detweiler, Dan Appel et al.OSDI 2020 · 86 citations
- The Demikernel Datapath OS Architecture for Microsecond-scale Datacenter SystemsIrene Zhang, Amanda Raybuck, Pratyush Patel, Kirk Olynyk et al.SOSP 2021 · 83 citations
- The nanoPU: A Nanosecond Network Stack for DatacentersStephen Ibanez, Alex Mallery, Serhat Arslan, Theo Jepsen et al.OSDI 2021 · 74 citations
Related papers
- STYX: Exploiting SmartNIC Capability to Reduce Datacenter Memory TaxHouxiang Ji, Mark Mansi, Yan Sun, Yifan Yuan et al.USENIX ATC 2023 · 22 citations
- RpcNIC: Enabling Efficient Datacenter RPC Offloading on PCIe-attached SmartNICsJie Zhang, Hongjing Huang, Xuzheng Chen, Xiang Li et al.HPCA 2025 · 6 citations
- TIGA: Towards Efficient Near Data Processing in SmartNICs-based Disaggregated Memory SystemsZhuohui Duan, Zelin Yu, Haikun Liu, Xiaofei Liao et al.DAC 2024
- OSMOSIS: Enabling Multi-Tenancy in Datacenter SmartNICsMikhail Khalilov, Marcin Chrapek, Siyuan Shen, Alessandro Vezzu et al.USENIX ATC 2024 · 14 citations
- HAL: Hardware-assisted Load Balancing for Energy-efficient SNIC-Host Cooperative ComputingJinghan Huang, Jiaqi Lou, Srikar Vanavasam, Xinhao Kong et al.ISCA 2024 · 7 citations
