Deployment and usage of cloud based applications and services that use
an underlying MPLS network are expanding and an increasing number of
applications are extremely sensitive to delay and packet loss.
Furthermore, in cloud computing an additional decision problem arises of
simultaneously choosing the data center to host applications along with
MPLS network connectivity such that the overall performance of the
application is met. Mechanisms exist to measure and monitor MPLS path
performance parameters for packet loss and delay, but the mechanisms
work only after the path has been setup. The cloud-based and performance
sensitive applications would benefit from measurement of MPLS network
and potential path information that would be provided for use in the
computation before LSP setup and then the selection of LSPs.
This document provides a framework and architecture to solve operator
problems and requirements using current/proposed approaches, documents
scalability assessment and recommendations, and identifies any needed