Granular Computing and Network Intensive Applications: Friends or Foes?

摘要: Computing/infrastructure as a service continues to evolve with bare metal, virtual machines, containers and now serverless granular computing offerings. Granular enables developers decompose their applications into smaller logical units or functions, run them on small, low cost short lived computation without having worry about setting up servers - hence the term computing. While environments can be used very effectively for large scale parallel processing data analytics applications, it is less clear if network intensive packet also benefit from these new services they do not share same characteristics. This paper examines architectural constraints well current implementations develop position this topic influence next generation of services. We support our through measurement experimentation Amazon's AWS Lambda few popular functions.