How Milvus Balances Query Load across Nodes?

What this post added

This post details the implementation of query load balancing in Milvus 2.0. It explains how the query coordinator monitors query node RAM usage and triggers balancing when thresholds are exceeded or significant differences exist between nodes. The mechanism involves transferring segments between query nodes and communicating these changes via sealedSegmentChangeInfo messages to ensure consistent data availability and balanced resource utilization.