paperbot · PL 论文追踪

全部论文 待读 收藏

P2 Dagger: efficient and fast RPCs in cloud microservices with near-memory reconfigurable NICs

Dagger:在云微服务中利用近内存可重构NIC实现高效快速RPC
ASPLOS Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems2021匹配度 0/10 · 该论文聚焦于云微服务中基于FPGA近内存可重构NIC的RPC硬件加速,属于体系结构与数据中心网络方向,完全不涉及静态分析、程序分析、浮点分析、贝叶斯程序分析或LLM/Agent相关主题。引用 54 inbox
Nikita Lazarev, Shaojie Xiang, Neil Adit, Zhiru Zhang, Christina Delimitrou
crossref: 2026-09-12

AI 速览

一句话:提出基于FPGA近内存可重构NIC的RPC加速架构Dagger,将RPC栈卸载到NIC并显著提升云微服务吞吐与延迟。

云服务从单体转向微服务后,细粒度小消息RPC在传统软件栈和外设NIC上开销高。Dagger提出一种基于FPGA的RPC硬件加速结构:将整个RPC栈卸载到FPGA NIC,用可配置内存互连而非PCIe与主机CPU紧耦合,并使加速结构可重构以适配不同微服务。评估显示,相比高度优化的软件栈和专用RDMA适配器,Dagger的每核RPC吞吐提升1.3-3.8倍,在4个CPU核、8线程下达到84 Mrps并保持µs级尾延迟;memcached和MICA KVS仅需最小代码改动即可移植,其中位和尾访问延迟分别降至2.8-3.5µs与5.4-7.8µs;8层航班值机微服务也验证了其端到端收益。

问题
云微服务中细粒度小消息RPC在商品软件栈和外设NIC上开销高,需要高效高性能的数据中心网络栈。
方法
Dagger基于FPGA构建RPC硬件加速结构,将整个RPC栈卸载到FPGA NIC,使用可配置内存互连而非PCIe与主机CPU紧耦合,并支持加速结构可重构以适应不同微服务。
评估
与高度优化软件栈和专用RDMA适配器相比,Dagger每核RPC吞吐提升1.3-3.8倍,4 CPU核8线程达84 Mrps并保持µs级尾延迟;memcached和MICA KVS最小改动移植后中位/尾访问延迟降至2.8-3.5µs和5.4-7.8µs,并在8层航班值机微服务上验证收益。
原文摘要(Abstract)

The ongoing shift of cloud services from monolithic designs to mi- croservices creates high demand for efficient and high performance datacenter networking stacks, optimized for fine-grained work- loads. Commodity networking systems based on software stacks and peripheral NICs introduce high overheads when it comes to delivering small messages. We present Dagger, a hardware acceleration fabric for cloud RPCs based on FPGAs, where the accelerator is closely-coupled with the host processor over a configurable memory interconnect. The three key design principle of Dagger are: (1) offloading the entire RPC stack to an FPGA-based NIC, (2) leveraging memory interconnects instead of PCIe buses as the interface with the host CPU, and (3) making the acceleration fabric reconfigurable, so it can accommodate the diverse needs of microservices. We show that the combination of these principles significantly improves the efficiency and performance of cloud RPC systems while preserving their generality. Dagger achieves 1.3 − 3.8× higher per-core RPC throughput compared to both highly-optimized software stacks, and systems using specialized RDMA adapters. It also scales up to 84 Mrps with 8 threads on 4 CPU cores, while maintaining state-of- the-art µs-scale tail latency. We also demonstrate that large third- party applications, like memcached and MICA KVS, can be easily ported on Dagger with minimal changes to their codebase, bringing their median and tail KVS access latency down to 2.8 − 3.5 us and 5.4 − 7.8 us, respectively. Finally, we show that Dagger is beneficial for multi-tier end-to-end microservices with different threading models by evaluating it using an 8-tier application implementing a flight check-in service.

链接与引用

DOI 原文 ·

BibTeX
@inproceedings{paperbot6146,
  title = {Dagger: efficient and fast RPCs in cloud microservices with near-memory reconfigurable NICs},
  author = {Nikita Lazarev and Shaojie Xiang and Neil Adit and Zhiru Zhang and Christina Delimitrou},
  booktitle = {ASPLOS},
  year = {2021},
  doi = {10.1145/3445814.3446696}
}