Is it just me or is having to modify the Go runtime an indication that maybe Go just isn't performant enough for your use case? There's no way this gets merged into upstream anyways, right?! Maybe look at concurrency models in other languages? E.g., rust :) www.uber.com/in/en/blog/z...
uber.com
Zero-Growth Stack, Real Gains: How Stack Allocation Can Save 10% CPU in Go
With over 2 million cores, 1% efficiency is worth millions. See how Uber tuned Go's runtime stack to boost CPU utilization for a service by 10%.
