I am playing with an idea of using istio for some of the features, however I find it hard to find any reasonable estimates of the latency it adds to every call. 1ms for every service call seems like a lot, especially once there are 10 services involved in a chain, each having request&response passing through istio.
Has anybody measured latency penalty for having sidecar proxy introduced?
Istio provides performance numbers, including latency, here: https://istio.io/docs/concepts/performance-and-scalability/#latency-for-istio-hahahugoshortcode-s2-hbhb
From the page...
The default configuration of Istio 1.1 adds 8ms to the 90th percentile latency of the data plane over the baseline.
This post does a benchmark of Istio and Linkerd to compare both service meshes in different aspects like CPU, memory or latency.