A High-Speed Stateful Packet Processing Approach for Tbps Programmable Switches
Mariano Scazzariello, Tommaso Caiazzi, Hamid Ghasemirahni, Tom Barbette, Dejan Kostic, Marco Chiesa
摘要
High-speed ASIC switches hold great promise for offloading complex packet processing pipelines directly in the highspeed data-plane. Yet, a large variety of today's packet processing pipelines, including stateful network functions and packet schedulers, require storing some (or all the) packets for short amount of times in a programmatic manner. Such a programmable buffer feature is missing on today's high-speed ASIC switches.
In this work, we present RIBOSOME, a system that extends programmable switches with external memory (to store packets) and external general-purpose packet processing devices such as CPUs or FPGAs (to perform stateful operations). As today's packet processing devices are bottlenecked by their network interface speeds, RIBOSOME carefully transmits only the relevant bits to these devices. RIBOSOME leverages spare bandwidth from any directly connected servers to store the incoming payloads through RDMA. Our evaluation shows that RIBOSOME can process 300G of traffic through a stateful packet processing pipeline (e.g., firewall, load balancer, packet scheduler) by running the pipeline logic on a single server equipped with one 100G interface.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper16
- Direct Telemetry AccessJonatan Langlet, Ran Ben Basat, Gabriele Oliaro, Michael Mitzenmacher 等SIGCOMM 2023 · 被引用 31 次
- Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba CloudXing Li, Xiaochong Jiang, Ye Yang, Lilong Chen 等SIGCOMM 2024 · 被引用 18 次
- ShRing: Networking with Shared Receive RingsBoris Pismenny, Adam Morrison, Dan TsafrirOSDI 2023 · 被引用 13 次
- FENIX: Enabling In-Network DNN Inference with FPGA-Enhanced Programmable SwitchesXiangyu Gao, Tong Li, Yinchao Zhang, Ziqiang Wang 等NSDI 2026 · 被引用 12 次
- High-throughput and Flexible Host Networking for Accelerated ComputingAthinagoras Skiadopoulos, Zhiqiang Xie, Mark Zhao, Qizhe Cai 等OSDI 2024 · 被引用 11 次
它引用的顶会 Paper11
- Jaqen: A High-Performance Switch-Native Approach for Detecting and Mitigating Volumetric DDoS Attacks with Programmable SwitchesZaoxing Liu, Hun Namkung, Georgios Nikolaidis, Jeongkeun Lee 等USENIX Security 2021 · 被引用 221 次
- TEA: Enabling State-Intensive Network Functions on Programmable SwitchesDaehyeok Kim, Zaoxing Liu, Yibo Zhu, Changhoon Kim 等SIGCOMM 2020 · 被引用 121 次
- Tiara: A Scalable and Efficient Hardware Acceleration Architecture for Stateful Layer-4 Load BalancingChaoliang Zeng, Layong Luo, Teng Zhang, Zilong Wang 等NSDI 2022 · 被引用 97 次
- RDMA is Turing complete, we just did not know it yet!Waleed Reda, Marco Canini, Dejan Kostic, Simon PeterNSDI 2022 · 被引用 56 次
- PacketMill: toward per-Core 100-Gbps networkingAlireza Farshin, Tom Barbette, Amir Roozbeh, Gerald Q. Maguire Jr. 等ASPLOS 2021 · 被引用 46 次
相关 Paper
- Queue-Mem: Energy-Efficient Hardware Storage for Advanced Network Function AccelerationMariano Scazzariello, Tommaso Caiazzi, Hamid Ghasemirahni, Dejan Kostic 等NSDI 2026
- Empower Programmable Pipeline for Advanced Stateful Packet ProcessingYong Feng, Zhikang Chen, Haoyu Song, Yinchao Zhang 等NSDI 2024 · 被引用 8 次
- Norma: Towards Practical Network Load TestingYanqing Chen, Bingchuan Tian, Chen Tian, Li Dai 等NSDI 2023 · 被引用 9 次
- Network Load Balancing with In-network Reordering Support for RDMACha Hwan Song, Xin Zhe Khooi, Raj Joshi, Inho Choi 等SIGCOMM 2023 · 被引用 110 次
- Stateful multi-pipelined programmable switchesVishal ShrivastavSIGCOMM 2022 · 被引用 24 次
