Cisco Performance Routing (PfR)

For most medium-to-large networks, you would usually have more than 1 ISP to connect the enterprise network to all the remote sites. Traditional routing (such as OSPF, BGP etc) could route network traffic through a preferred path or load-balance among different paths. It can also automatically change path when a link is dead.

However, traditional routing alone can't detect and take actions on links that are "half-dead" e.g. congested, flappy link etc. To overcome it, Cisco introduces Performance Routing (PfR) or f.k.s Optimized Edge Routing (OER) and add intelligence bits into the classical IP routing. There are two components to PfR: a Master Controller (MC) and a Border Router (BR). In a typical installation, there is one MC and one or more BRs. In many smaller designs, you can have the MC and BR on the same physical router.

The MC is the brain of PfR. The MC receives performance data from the BRs, compares it against the configured policy, selects the best route for the data and sends commands to the BR to forward traffic to that path.

The BR is the foot soldier of PfR. It collects the performance data and sends it to the MC. The MC compares the data against the configured performance policy. If it is out of policy, the MC sends commands to the BR to change the data path. PfR can monitor link performance based on passive mode (using netflow) and active mode (IP SLA).

There is this good wiki article that explains the fundamental of PfR.