Add tower-hedge, a layer that preemptively retries requests which have been
outstanding for longer than a given latency percentile. If either of the original
future or the retry future completes, that value is used. For more information
about hedge requests, see: [The Tail at Scale][1]
[1]: https://cseweb.ucsd.edu/~gmporter/classes/fa17/cse124/post/schedule/p74-dean.pdf
Signed-off-by: Alex Leong <alex@buoyant.io>
Taiki Endo
Jon Gjengset
Alex Leong