# Select replica to query by load average

**URL:** <https://discuss.elastic.co/t/select-replica-to-query-by-load-average/62237>\
**Category:** Elasticsearch\
**Created:** [October 5, 2016, 7:17am UTC](https://discuss.elastic.co/t/select-replica-to-query-by-load-average/62237 "2016-10-05T07:17:33Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Alexandr\_Dorosh](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/alexandr_dorosh/32/416_2.png) [@Alexandr\_Dorosh](https://discuss.elastic.co/u/Alexandr_Dorosh)\
**Post date:** [October 5, 2016, 7:17am UTC](https://discuss.elastic.co/t/select-replica-to-query-by-load-average/62237/1 "2016-10-05T07:17:33Z")

</div>

Is there a way to send queries to replica with lower load average?

Sometimes we have a problems with whole elasticsearch cluster (25 nodes) only because of one node with high load averege. Elasticsearch continues to send queries to this node which executes very slow and slow down whole cluster.

Elasticsearch version: 2.3.4

---

<div class="post-metadata">

**Author:** ![warkolm](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/warkolm/32/39224_2.png) [@warkolm](https://discuss.elastic.co/u/warkolm)\
**Post date:** [October 6, 2016, 12:00am UTC](https://discuss.elastic.co/t/select-replica-to-query-by-load-average/62237/2 "2016-10-06T00:00:44Z")

</div>

Not natively within ES.

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [July 5, 2017, 10:14pm UTC](https://discuss.elastic.co/t/select-replica-to-query-by-load-average/62237/3 "2017-07-05T22:14:33Z")

</div>

Closed on July 5, 2017, 10:14pm UTC