Using a binary serialized format is actually pretty good that way. For a high throughput API that I built, shifting to protobuf from json, and using binary formats made a lot of difference. The packet size is lower, you can use JVM based platforms to do analysis and analytics (esp when storing logs as proto) - those benefits outweigh the slowness of the object creation (which isn't THAT slow on cpython). Atleast on the proto 2.3.x versions that I use.
That said, to my point of keep alives - lets say you've got process A talking to process B on localhost, which is making web service calls to the internet. Every 5ms delay is hurting your total response time, especially when your connection pool is waiting on a dropped connection to be reinstated.
What I am more worried about with microservices is the data serialization overhead. Transforming data to some encoding that is robust against version changes (say using protobuf) can be quite costly on both sender and receiver, especially in languages with relatively slow object creation (e.g. python). This is highly application specific, but I'd love to hear others' thoughts on this trade-off.