Highly Resilient Systems for Cloud

Traditional methods for implementing highly resilient systems are costly; and their methods using specialized hardware and high-speed interconnects do not extend to cloud.  We demonstrate an architecture that rethinks the traditional approach and uses cloud's agility to provision additional capability as failures occur.  This architecture continues serving requests with the best possible response even as the primary service deteriorates and even fails completely.  It offloads requests according to their need to access the primary service; first redirecting requests with less need to lower-grade secondary capability that is provisioned on-demand on the cloud in order to reserve primary capacity for requests that need it (e.g., first redirect web-browsing requests to a slightly out-of-date cached dataset, and reserve the primary, most-consistent data service for check-out requests).  Our approach 1) triages access to the primary service based on request needs in times when it is overwhelmed, and 2) provisions on-demand cloud capability to offload and continue serving other requests as needed.  The result is a highly resilient system architecture that scales via cloud.