Byte-addressable persistent memories (PM) has finally made their way into production. An important and pressing problem that follows is how to deploy them in existing datacenters. One viable approach is to attach PM as self-contained devices to the network as disaggregated persistent memory, or DPM. DPM requires no changes to existing servers in datacenters; without the need to include a processor, DPM devices are cheap to build; and by sharing DPM across compute servers, they offer great elasticity and efficient resource packing.
This paper explores different ways to organize DPM and to build data stores with DPM. Specifically, we propose three architectures of DPM: 1) compute nodes directly access DPM (DPM-Direct); 2) compute nodes send requests to a coordinator server, which then accesses DPM to complete a request (DPM-Central); and 3) compute nodes directly access DPM for data operations and communicate with a global metadata server for the control plane (DPM-Sep). Based on these architectures, we built three atomic, crash-consistent data stores. We evaluated their performance, scalability, and CPU cost with micro-benchmarks and YCSB. Our evaluation results show that DPM-Direct has great small-size read but poor write performance; DPM-Central has the best write performance when the scale of the cluster is small but performs poorly when the scale increases; and DPM-Sep performs well overall.
CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization
College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；National Key Laboratory of Parallel and Distributed Computing（并行与分布式计算国家重点实验室）；Duke Kunshan University（杜克昆山大学）
Assise: Performance and Availability via NVM Colocation in a Distributed File System
极低延迟持久内存模块（PMM）的采用颠覆了长期建立的分散式文件系统访问模型。相反，通过将计算和PMM存储放在同一位置，我们可以为应用程序提供更高的I/O性能、亚秒级的应用程序故障转移和强一致性。为了证明这一点，我们构建了基于持久性、复制一致性协议的Assise分布式文件系统，用于管理一组服务器托管的PMM，作为应用程序和较慢的分散存储（如SSD）之间的快速、崩溃可恢复的缓存。与分散式文件系统不同，Assise通过尽可能在共置的PMM上执行IO来最大限度地提高所有文件IO的局部性，并通过在IO操作粒度（而不是固定的块大小）上保持一致性来最大限度地减少一致性开销。我们将Assise与Ceph/Bluestore、NFS和Octopus在具有英特尔Optane DC PMM和SSD的群集上进行了比较，用于常见的云应用程序和基准测试，例如LevelDB、Postfix和FileBench。我们发现，Assise将写入延迟提高了22倍，吞吐量提高了56倍，故障转移时间提高了103倍，并且比同类产品的扩展能力提高了6倍，同时提供了更强的一致性语义。Assise承诺将以1.5倍的速度打破MinuteSort世界纪录。
BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure
Southern University of Science and Technology（南方科技大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；State Key Lab of IOTSC, Faculty of Science and Technology, University of Macau（澳门科技大学物联网与感知系统国家重点实验室、理学院）；AIOS Team, Alibaba Group Inc（阿里巴巴集团 AIOS 团队）
BatchWeave: A Consistent Object-Store-Native Data Plane for Large Foundation Model Training
Lionrock AI Lab, China Merchants Group, Hong Kong, China（狮岩人工智能实验室，中国商人集团，香港，中国）；Wuhan University, Wuhan, China（武汉大学，武汉，中国）；The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳））
