Infusing Cognition into Distributed Computing: A New Approach to Distributed Datacenters with Self-Managing Services on Commodity Hardware (Virtualized or Not)

摘要

The advent of virtualization technologies and cloud computing has improved application provisioning speed, resource utilization, fault-management, availability using auto-failover and performance optimization using auto-scaling in distributed computing environments. However, heterogeneous virtualization technologies offered by different service providers with disparate infrastructure and their orchestration and management systems have also increased the complexity of managing distributed applications and vendor lock-in. In this paper we utilize new computing, management and programming models introduced using the DIME network architecture to provide end to end service visibility and control across distributed physical or virtual infrastructure. Resulting decoupling of application and service transaction management from myriad distributed infrastructure management systems at run-time enables policy based, secure, service mobility across physical servers or virtual machines deployed in data enters or public clouds. Using the new architecture we have implemented service self-repair, auto-scaling, live-migration and end-to-end service transaction security independent of server and network security mechanisms.