STYX: Exploiting SmartNIC Capability to Reduce Datacenter Memory Tax
Houxiang Ji, Mark Mansi, Yan Sun, Yifan Yuan, Jinghan Huang, Reese Kuper, Michael M. Swift, Nam Sung Kim
Abstract
Memory optimization kernel features, such as memory deduplication, are designed to improve the overall efficiency of systems like datacenter servers, and they have proven to be effective. However, when invoked, these kernel features notably disrupt the execution of applications, intensively consuming the server CPU's cycles and polluting its caches. To minimize such disruption, we propose STYX, a framework for offloading the intensive operations of these kernel features to SmartNIC (SNIC). STYX first RDMA-copies the server's memory regions, on which these kernel features intend to operate, to an SNIC's memory region, exploiting SNIC's RDMA capability. Subsequently, leveraging SNIC's (underutilized) compute capability, STYX makes the SNIC CPU perform the intensive operations of these kernel features. Lastly, STYX RDMA-copies their results back to a server's memory region, based on which it performs the remaining operations of the kernel features. To demonstrate the efficacy of STYX, we re-implement two memory optimization kernel features in Linux: (1) memory deduplication (ksm) and (2) compressed cache for swap pages (zswap), using the STYX framework. We then show that a system with STYX provides a 55-89% decrease in 99 thpercentile latency of co-running applications, compared to a system without STYX, while preserving the benefits of these kernel features.
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 081045dc-3da1-4f9b-9355-aee9d5517c30Cited by top-tier papers8
- ACCL+: an FPGA-Based Collective Engine for Distributed ApplicationsZhenhao He, Dario Korolija, Yu Zhu, Benjamin Ramhorst et al.OSDI 2024 · 12 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
- Para-ksm: Parallelized Memory Deduplication with Data Streaming AcceleratorHouxiang Ji, Minho Kim, Seonmu Oh, Daehoon Kim et al.USENIX ATC 2025 · 7 citations
- Poby: SmartNIC-accelerated Image Provisioning for Coldstart in CloudsZihao Chang, Jiaqi Zhu, Haifeng Sun, Yunlong Xie et al.USENIX ATC 2025 · 5 citations
- Analyzing Near-Network Hardware Acceleration with Co-Processing on DPUsDimitrios Giouroukis, Dwi P. A. Nugroho, Varun Pandey, Steffen Zeuch et al.VLDB 2025 · 3 citations
Builds on11
- Dedup Est Machina: Memory Deduplication as an Advanced Exploitation VectorErik Bosman, Kaveh Razavi, Herbert Bos, Cristiano GiuffridaS&P 2016 · 252 citations
- When Cloud Storage Meets RDMAYixiao Gao, Qiang Li, Lingbo Tang, Yongqing Xi et al.NSDI 2021 · 228 citations
- TMO: transparent memory offloading in datacentersJohannes Weiner, Niket Agarwal, Dan Schatzberg, Leon Yang et al.ASPLOS 2022 · 103 citations
- LineFS: Efficient SmartNIC Offload of a Distributed File System with Pipeline ParallelismJongyul Kim, Insu Jang, Waleed Reda, Jaeseong Im et al.SOSP 2021 · 83 citations
- Serverless computing on heterogeneous computersDong Du, Qingyuan Liu, Xueqiang Jiang, Yubin Xia et al.ASPLOS 2022 · 68 citations
Related papers
- BASK: Batch And SmartNIC-offloaded KSMChanshin Kwak, Jaehyeon Lee, Minkyu Jung, Changjun Lee et al.EuroSys 2026
- Wave: Offloading Resource Management to SmartNIC CoresJack Tigar Humphries, Neel Natu, Kostis Kaffes, Stanko Novakovic et al.ASPLOS 2025 · 5 citations
- Demystifying a CXL Type-2 Device: A Heterogeneous Cooperative Computing PerspectiveHouxiang Ji, Srikar Vanavasam, Yang Zhou, Qirong Xia et al.MICRO 2024 · 15 citations
- Xenic: SmartNIC-Accelerated Distributed TransactionsHenry N. Schuh, Weihao Liang, Ming Liu, Jacob Nelson et al.SOSP 2021 · 62 citations
- TIGA: Towards Efficient Near Data Processing in SmartNICs-based Disaggregated Memory SystemsZhuohui Duan, Zelin Yu, Haikun Liu, Xiaofei Liao et al.DAC 2024
