Threading model

By default, there is no coordination between worker threads. This means that all worker threads independently attempt to accept connections on each listener and rely on the kernel to perform adequate balancing between threads. For most workloads, the kernel does a very good job of balancing incoming connections. However, for some workloads, particularly those that have a small number of very long lived connections (e.g., service mesh HTTP2/gRPC egress), it may be desirable to have Envoy forcibly balance connections between worker threads. To support this behavior, Envoy allows for different types of connection balancing to be configured on each .