Recap of the 2023 CLSF (China Linux Storage, Memory Management & File System) Workshop
The 2023 China Linux Storage, Memory Management and File System Workshop, held on October 26‑27 and organized by OPPO, gathered leading Linux kernel developers from firms such as SUSE, Intel, AMD, Huawei and academic institutions to present keynotes and talks on memory reclamation, scalability, storage, BPF, container images, and future kernel innovations, fostering collaborative advancement of Chinese kernel development.
On October 26‑27, 2023, the 2023 CLSF (China Linux Storage, Memory Management & File System) Workshop was successfully held. The event was organized by OPPO and brought together active Linux kernel developers from organizations such as SUSE, OPPO, Intel, AMD, Ant Group, Huawei, Vivo, ByteDance, Tencent, Alibaba Cloud, Kylin Software, Red Hat, Peking University, the Institute of Software of the Chinese Academy of Sciences, and many others. Participants shared research results in their respective fields, discussed technical challenges, and explored the latest developments and future innovations of the Linux kernel.
Day 1 Keynote Sessions
• Huang Jing (Ant Group) presented “Cold Memory Active Reclamation Based on User‑Space Policies”. • Li Peifeng (OPPO) shared “LRU Reclamation Optimization for Page Mapping Frequency and Lock Contention”. • Song Mu‑chun & Zheng Qi (ByteDance) discussed “The Challenges of Scalability in Linux Kernel”, focusing on memory‑reclamation pain points and optimization ideas. • Yin Feng‑wei (Intel) introduced “Large Folio for Anonymous Mapping”.
Additional Day 1 talks included: • Gong Rui‑qi (Huawei) – “Kmalloc Randomization: A New Heap‑Spray Attack Mitigation”. • Alibaba Cloud consultant – “Shared Memory Communication (SMC) Loopback TCP Acceleration”. • Wang Rong‑wei (Alibaba Cloud) – “Page‑Table Sharing”. • Zhu Wei‑xi (Huawei) – “GMEM: General Memory Management for Domain‑Specific Accelerators”. • Li Yong (SUSE) – “badblocks APIs Improvement”. • Zhu Ling‑shan (Intel) – “Virtio Live Migration”.
Day 2 Keynote Sessions
• Yi Shu‑shu (Peking University) – “Next‑Gen RAID”, a technical analysis of high‑performance all‑flash arrays. • He Liang (Institute of Software, Chinese Academy of Sciences) – “One Simple API Can Cause Hundreds of Bugs”. • Tang Ge‑liang (SUSE) – “BPF for MPTCP”. • Lei Ming (Red Hat) – “ublk: AIO Evolution”.
Additional Day 2 talks included: • Xu Jing‑bo (Alibaba Cloud) & Yin Xin (ByteDance) – “Erofs & Container Image”, presenting two container‑image solutions based on new EROFS features. • Zou Ming‑zhe (EasyStack) – “bcache_online_resize”. • Song Kai‑rui (Tencent Cloud) – “MGLRU Application Practice and Algorithm Optimization”, evaluating MGLRU performance under various workloads and its integration in Linux 6.1. • Ye Huai‑sheng (Intel) – “Memory‑Tiering‑CXL‑Damon”.
The workshop concluded with gratitude to OPPO for its strong support and an invitation to continue collaborative efforts to advance Chinese kernel development.
For further reading, the following articles were recommended: Detailed Explanation of Linux Kernel Memory Compaction Introduction to Android logd and Typical Case Analyses OPPO Announces Programmable Kernel Technology at the CLK Conference, Leading Android Smooth Experience Upgrade
OPPO Kernel Craftsman
Sharing Linux kernel-related cutting-edge technology, technical articles, technical news, and curated tutorials
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.