# Adaptive Replica Selection and knn load balancing

**URL:** <https://discuss.elastic.co/t/adaptive-replica-selection-and-knn-load-balancing/377991>\
**Category:** Elasticsearch\
**Tags:** vector-search\
**Created:** [May 9, 2025, 1:55pm UTC](https://discuss.elastic.co/t/adaptive-replica-selection-and-knn-load-balancing/377991 "2025-05-09T13:55:54Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![peedeeboy](https://avatars.discourse-cdn.com/v4/letter/p/2acd7d/32.png) [@peedeeboy](https://discuss.elastic.co/u/peedeeboy)\
**Post date:** [May 9, 2025, 1:55pm UTC](https://discuss.elastic.co/t/adaptive-replica-selection-and-knn-load-balancing/377991/1 "2025-05-09T13:55:54Z")

</div>

hey friends 👋

I [posted previously](https://discuss.elastic.co/t/index-pre-load-for-vector-store/375564) about our efforts on optimising our dedicated knn cluster.

The latest thing we've been trying to understand / solve is why when we run load/stress testing, we often see 1 or 2 nodes serving the bulk of requests - and slowing down / queuing search requests due to 80 - 100% CPU usage - whilst other nodes are chilling at 20% CPU usage and less requests.

We disabled Adaptive Replica Selection, which seems to be having the desired affect, load is consistently distributed across all nodes, resulting in a happy cluster 🙂

What we don't understand is WHY we see this skewed load with the default Adaptive Replica Selection switched on? 🤔

We have a very simple setup. ~120k docs in an index consisting of just a keyword (id) and dense vector field, with one shard, one primary and other nodes replica.

We've never seen a problem with load distribution on our main traditional keyword cluster - seems to be an issue specifically with vector / approximate knn searching? 🤔 And we're baffled!

Any ideas what might be going as we're all out of ideas! 🤣