mirror of
https://github.com/papers-we-love/papers-we-love.git
synced 2024-09-28 14:30:47 +00:00
8.0 KiB
8.0 KiB
Unikernels
First-wave: lightweight kernels (microkernels)
- HYDRA: the kernel of a multiprocessor operating system
- Two years of experience with a μ-Kernel based OS
- A persistent system in real use-experiences of the first 13 years
- SPIN: An extensible microkernel for application-specific operating system services
- Extensibility safety and performance in the SPIN operating system
- Policy/mechanism separation in Hydra
- Improving IPC by kernel design
Second-wave: cloud optimization (exokernels, multikernels)
- Exokernel: An operating system architecture for application-level resource management
- Exterminate all operating system abstractions
- The Clive Operating System
- The Multikernel: A new OS architecture for scalable multicore systems
- IX: A Protected Dataplane Operating System for High Throughput and Low Latency
- The IX Operating System: Combining Low Latency, High Throughput, and Efficiency in a Protected Dataplane
- Contiki - a lightweight and flexible operating system for tiny networked sensors
- Arrakis: The Operating System Is the Control Plane
- Embracing diversity in the Barrelfish manycore operating system
- Decoupling Cores, Kernels, and Operating Systems
Unikernels: bespoke, compile-time specialization based on a libOS
Introduction
- Unikernels: Library Operating Systems for the Cloud
- Unikernels: the rise of the virtual library operating system
- Maximizing hypervisor scalability using minimal virtual machines
- Breaking up is hard to do: security and functionality in a commodity hypervisor
- A case for high performance computing with virtual machines
- Comparing the robustness of POSIX operating systems
- Exploring the Design Space of Combining Linux with Lightweight Kernels for Extreme Scale Computing
- Using kernel hypervisors to secure applications
Specific libOS implementations
- IncludeOS: A minimal, resource efficient unikernel for cloud services
- OSv—optimizing the operating system for virtual machines
- ClickOS and the art of network function virtualization
- Enabling fast, dynamic network processing with clickos
- The rump kernel: A tool for driver development and a toolkit for applications
- Flexible operating system internals: the design and implementation of the anykernel and rump kernels
- Rump Kernels: No OS? No Problem!
- HermitCore: A Unikernel for Extreme Scale Computing
- llamaOS: A Solution for Virtualized High-Performance Computing Clusters
- KylinX: A Dynamic Library Operating System for Simplified and Efficient Cloud Virtualization
Performance, comparisons and analysis
- The impact of operating system structure on memory system performance
- Hypervisors vs. Lightweight Virtualization: A Performance Comparison
- A performance evaluation of rump kernels as a multi-server os building block on sel4
- An updated performance comparison of virtual machines and linux containers
- My VM is Lighter (and Safer) than your Container
- Security of OS-level virtualization technologies: Technical report
- Time Provisioning Evaluation of KVM, Docker and Unikernels in a Cloud Platform
Applications of Unikernels
- Tardigrade: Leveraging Lightweight Virtual Machines to Easily and Efficiently Construct Fault-Tolerant Services
- Unikernel-based approach for software-defined security in cloud infrastructures
- FADES: Fine-Grained Edge Offloading with Unikernels
- Enterprise IoT security and scalability: how unikernels can improve the status Quo
- Unikernels Everywhere: The Case for Elastic CDNs
- Towards minimalistic, virtualized content caches with minicache
- Jitsu: Just-in-time summoning of unikernels
- Enabling fast, dynamic network processing with clickOS
- uniprof: A Unikernel Stack Profiler
- On the Fly TCP Acceleration with Miniproxy
- Unikernel monitors: extending minimalism outside of the box
- Unikernels As Processes
- On the Fly Orchestration of Unikernels: Tuning and Performance Evaluation of Virtual Infrastructure Managers
- Live updating in Unikernels
- Android Unikernel: Gearing mobile code offloading towards edge computing