TechPrufer
Sign inGet started

Blogs›Milvus›In-Memory Replicas

In-Memory Replicas

In-Memory Replicas

1
posts
2022

Milvus 2.1 introduces in-memory replicas to enhance read throughput and system availability. This feature allows data segments to be loaded onto multiple query nodes, enabling parallel search requests and improving resilience to query node failures. Configuration involves specifying the replica number during collection loading, with limitations based on available memory.

2022

Increase Your Vector Database Read Throughput with In-Memory Replicas

8/22/2022

Introduces the concept and implementation of in-memory replicas in Milvus 2.1. Explains replica groups, shard replicas, streaming replicas, historical replicas, and shard leaders. Details how enabling in-memory replicas boosts QPS and throughput by allowing multiple query nodes to serve search requests for the same data segment. Provides a Python code example for loading a collection with multiple replicas and a method to retrieve replica information.