A Lightweight Cloud Computing Service Method Based On Unikernel

Serverless computing,also known as “Function as a Service(Faa S)”,is emerging as an event-driven paradigm of cloud computing.In this Faa S model,applications are programmed in the form of functions that are executed and managed separately.The event-driven functions are triggered by requests of cloud users,and cloud providers dynamically provision containers or virtual machines(VMs)to execute the functions.The startup delays of containers or VMs usually lead to rather high latency of response to client users.Moreover,the communication between different functions generally relies on virtual net devices or shared memory,and may lead to extremely high performance overhead.In this paper,we propose Unikernel as a Function(Uaa F),a much more lightweight approach to serverless computing.Applications can be abstracted as a combination of different functions,and we program each function with an unikernel in which a function is linked with a specified minimum-sized library operating system(Lib OS).Uaa F offers extremely low startup latency to execute functions,and a more efficient communication model to speed up the interactions between functions within a single server.We exploit an existing hardware technique(namely VMFUNC)to invoke functions or access data in other unikernel-based VMs seamlessly(mostly like inter-process communica-tions),without suffering performance penalty of VM Exits.We implement our proof-of-concept prototype based on KVM and deploy Uaa F in four unikernels(Mirage OS,Include OS,Solo5 and OSv).The experimental results show that Uaa F can significantly reduce the startup latency and memory consumption of serverless cloud applications.Moreover,our VMFUNC-based communica-tion model can also significantly improve the performance of function invocations between different unikernels.