A system and method for handling network overload includes receiving one or more requests, wherein an originating client originates the one or more requests. It is determined if a network element processing the one or more requests is overloaded. If the network element is overloaded, a pushback message is generated. The pushback message is sent with request gapping information to a previous hop in a network, wherein the previous hop is one or more network elements operable to route the one or more network requests to the network element processing the one or more requests.