Keyang Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Keyang Hu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Kang Chen
Tsinghua University, Beijing, China
3 shared publications - Yu Chen
Tsinghua University, Beijing, China
2 shared publications - Anqi Shen
Ant Group, Hangzhou, China
1 shared publication - Bo Jiang
Anhui University
1 shared publication - Ce Mo
School of Computer Science and Engineering, Beihang University, Beihang University, Beijing, China
1 shared publication - Dawei Shen
Ant Group, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 499-515
Turning Linux into a High-Performance Library OS with Flux
Modern high-performance applications increasingly bypass the host kernel for I/O and scheduling and rely on library OSes for operating-system services. High-performance library OSes are often built from scratch, but supporting unmodified applications requires reimplementing mature Linux semantics. Running Linux itself as a library OS avoids this cost, yet existing Linux-based designs remain slow. Our analysis of LKL shows that the main bottlenecks lie in the surrounding user-space runtime rather than Linux subsystems. We present Flux, a Linux-based library OS that reduces the runtime bottlenecks while keeping Linux subsystems largely intact. Flux redesigns scheduling, user-space interrupt delivery, and syscall paths, and introduces a new process abstraction that supports Linux fork semantics without giving up direct-call syscalls. Flux improves Nginx throughput by up to 18.5× over Linux, and approaches Junction's Memcached throughput under a 100μs p99 latency target, showing that Linux can provide a high-performance library OS without rebuilding Linux functionality from scratch.
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 499-515
Open AccessTurning Linux into a High-Performance Library OS with Flux
Modern high-performance applications increasingly bypass the host kernel for I/O and scheduling and rely on library OSes for operating-system services. High-performance library OSes are often built from scratch, but supporting unmodified applications requires reimplementing mature Linux semantics. Running Linux itself as a library OS avoids this cost, yet existing Linux-based designs remain slow. Our analysis of LKL shows that the main bottlenecks lie in the surrounding user-space runtime rather than Linux subsystems. We present Flux, a Linux-based library OS that reduces the runtime bottlenecks while keeping Linux subsystems largely intact. Flux redesigns scheduling, user-space interrupt delivery, and syscall paths, and introduces a new process abstraction that supports Linux fork semantics without giving up direct-call syscalls. Flux improves Nginx throughput by up to 18.5× over Linux, and approaches Junction's Memcached throughput under a 100μs p99 latency target, showing that Linux can provide a high-performance library OS without rebuilding Linux functionality from scratch.
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 605-623
SKernel: An Elastic and Efficient Secure Container System at Scale with a Split-Kernel Architecture
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 605-623
Open AccessSKernel: An Elastic and Efficient Secure Container System at Scale with a Split-Kernel Architecture
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 921-937
AlloyStack: A Library Operating System for Serverless Workflow Applications
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 921-937
Open AccessAlloyStack: A Library Operating System for Serverless Workflow Applications
- Open Access
- 17 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 13-14
Work-in-Progress: Unishyper, A Reliable Rust-based Unikernel for Embedded Scenarios
Unishyper is a reliable Rust-based unikernel with good performance for embedded scenarios. It relies on Rust Features to enable customization at fine granularity. To achieve high reliability, Unishyper makes full use of the Rust language features to reduce memory safety bugs, ensure safe resource management, and achieve fault handling and recovery. Finally, Unishyper achieves high performance through safe multi-threading model as well as the single-privilege-level and single-address-space design.
- 17 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 13-14
Open AccessWork-in-Progress: Unishyper, A Reliable Rust-based Unikernel for Embedded Scenarios
Unishyper is a reliable Rust-based unikernel with good performance for embedded scenarios. It relies on Rust Features to enable customization at fine granularity. To achieve high reliability, Unishyper makes full use of the Rust language features to reduce memory safety bugs, ensure safe resource management, and achieve fault handling and recovery. Finally, Unishyper achieves high performance through safe multi-threading model as well as the single-privilege-level and single-address-space design.