paperbot · PL 论文追踪

全部论文 待读 收藏

P2 CPU-Oblivious Offloading of Failure-Atomic Transactions for Disaggregated Memory

面向解聚内存的 CPU 无感失败原子事务卸载
ASPLOS Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 22026匹配度 1/10 · 该论文属于分布式系统与内存解聚方向,研究故障原子事务的日志持久化卸载与交换机内处理单元的设计,与静态分析、程序分析、LLM/Agent 及浮点/贝叶斯程序分析等研究方向没有交集。引用 1 inbox
Cheng Chen, Chencheng Ye, Yuanchao Xu, Xipeng Shen, Xiaofei Liao, Hai Jin, Wenbin Jiang, Yan Solihin
crossref: 2026-09-12dblp: 2026-09-12

AI 速览

一句话:Fanmem 将失败原子事务的日志持久化卸载到交换机处理单元,在解聚内存中保证故障一致性并降低计算服务器开销。

内存解聚在提升资源利用率的同时带来新的可靠性挑战:计算服务器或互连网络故障可能中断执行,导致内存服务器中的数据不一致。本文提出 Fanmem,一个专为解聚内存架构设计的失败原子事务系统。Fanmem 借鉴持久内存事务的思想,但针对解聚场景进行定制,其核心创新包括异步事务模型,以及将处理单元集成到交换机中,从而把耗时的日志持久化操作卸载到交换机处理单元,显著减少计算服务器上的开销。作者在两种代表性的内存解聚架构上评估 Fanmem,并与最先进的持久内存事务系统对比。结果显示,Fanmem 在两种架构上分别取得平均 1.2 倍和 1.7 倍的性能提升,验证了其有效性。

问题
内存解聚架构中,计算服务器或互连故障可能中断执行并导致内存服务器数据不一致,现有持久内存事务难以直接适用。
方法
提出 Fanmem 失败原子事务系统,采用异步事务模型,并在交换机中集成处理单元,将日志持久化操作从计算服务器卸载到交换机处理单元。
评估
在两种代表性内存解聚架构上与最先进的持久内存事务系统进行性能对比,平均性能分别提升 1.2 倍和 1.7 倍。
原文摘要(Abstract)

Memory disaggregation introduces new challenges for application reliability, as compute server or interconnection failures can interrupt execution and lead to data inconsistency in the memory server. This paper presents Fanmem, a novel failure-atomic transaction system designed specifically for disaggregated memory architectures. Fanmem ensures data consistency in the presence of failures, drawing inspiration from persistent memory transactions while tailored for memory disaggregation. The key innovations of Fanmem include an asynchronous transaction model and the integration of a processing unit within the switch, enabling the offloading of time-consuming log persistency operations to the switch processing unit and significantly reducing the overhead on the compute servers. Evaluation confirms the effectiveness of Fanmem on two representative memory-disaggregated architectures. Compared to the state-of-the-art persistent memory transaction system, Fanmem achieves an average performance improvement of 1.2X and 1.7X on the respective architectures.

链接与引用

DOI 原文 · PDF(开放获取) · DBLP

BibTeX
@inproceedings{Chen00SL00S26,
  title = {CPU-Oblivious Offloading of Failure-Atomic Transactions for Disaggregated Memory},
  author = {Cheng Chen and Chencheng Ye and Yuanchao Xu and Xipeng Shen and Xiaofei Liao and Hai Jin and Wenbin Jiang and Yan Solihin},
  booktitle = {ASPLOS},
  year = {2026},
  doi = {10.1145/3779212.3790146}
}