# Usage CPU during search query

**URL:** <https://discuss.elastic.co/t/usage-cpu-during-search-query/357059>\
**Category:** Elasticsearch\
**Created:** [April 9, 2024, 11:41am UTC](https://discuss.elastic.co/t/usage-cpu-during-search-query/357059 "2024-04-09T11:41:38Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![INS](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/ins/32/92827_2.png) [@INS](https://discuss.elastic.co/u/INS)\
**Post date:** [April 9, 2024, 11:41am UTC](https://discuss.elastic.co/t/usage-cpu-during-search-query/357059/1 "2024-04-09T11:41:39Z")

</div>

Hi  
I'm wondering why during search query, only one are overloading CPU, while we have index divided on 3 shards each on nodes.

 ![Screenshot 2024-04-09 at 13.39.10](https://us1.discourse-cdn.com/elastic/original/3X/5/7/5789255228e33dcc1f49df495ac37e59349c98f6.png)  
 ![Screenshot 2024-04-09 at 13.38.58](https://us1.discourse-cdn.com/elastic/original/3X/1/9/19fa313d758683cd4f637587e466e51c40a6c13d.png)  
 ![Screenshot 2024-04-09 at 13.38.50](https://us1.discourse-cdn.com/elastic/original/3X/8/5/8567347aa9f715b389897296b065db70376ba9be.png)

---

<div class="post-metadata">

**Author:** ![INS](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/ins/32/92827_2.png) [@INS](https://discuss.elastic.co/u/INS)\
**Post date:** [April 10, 2024, 12:41pm UTC](https://discuss.elastic.co/t/usage-cpu-during-search-query/357059/2 "2024-04-10T12:41:05Z")

</div>

cluster was build over operator on ECK