I have a quick question on the LEAST_CONN load balancing method.
The documentation
describes LEAST_CONN as
The least request load balancer uses an O(1) algorithm which selects two random healthy hosts and picks the host which has fewer active requests.
My question:
How does istio ingress controller know the number of active requests in a pod? Are these constantly programmed by “pilot” based on stats received by the “mixer” from the “istio proxy” in the pod ?
What happens if the ingress controller has scaled and has 5 pods? Does the mixer update all the ingress controllers? Doesn’t this become too performance intensive?
Or am I completely wrong? And the ingress controller knows about the number of active requests in a pod in a different manner?
thanks,
Farhad.