# Unbalanced search performance

**URL:** <https://discuss.elastic.co/t/unbalanced-search-performance/102606>\
**Category:** Elasticsearch\
**Created:** [October 3, 2017, 7:45pm UTC](https://discuss.elastic.co/t/unbalanced-search-performance/102606 "2017-10-03T19:45:50Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![avaneeshr](https://avatars.discourse-cdn.com/v4/letter/a/85f322/32.png) [@avaneeshr](https://discuss.elastic.co/u/avaneeshr)\
**Post date:** [October 3, 2017, 7:45pm UTC](https://discuss.elastic.co/t/unbalanced-search-performance/102606/1 "2017-10-03T19:45:51Z")

</div>

Hi!  
I am using ES v2.4.0 on 5 nodes with a very search query (bool queries) workload, in AWS, using compute optimized servers.  
I am querying the cluster via a HAProxy Load Balancer which uses roundrobin policy for each data node.  
The cluster has one dedicated master node.  
When I see the output of cat api / threads

 ![13](https://us1.discourse-cdn.com/elastic/original/3X/c/2/c2ac100891e5fe765b49109182b899569088eefb.png)

All nodes are equal in all aspects, and have equal data. Everything is perfectly uniform across the 5 servers.

Then why does one node have so many active search threads?  
Problem is, this makes the load avg on the 2nd server more than 100!

---

<div class="post-metadata">

**Author:** ![mujtabahussain](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/mujtabahussain/32/17514_2.png) [@mujtabahussain](https://discuss.elastic.co/u/mujtabahussain)\
**Post date:** [October 4, 2017, 12:23am UTC](https://discuss.elastic.co/t/unbalanced-search-performance/102606/2 "2017-10-04T00:23:09Z")

</div>

Any chance the HAProxy policy is not correct? Could you post that here?

---

<div class="post-metadata">

**Author:** ![avaneeshr](https://avatars.discourse-cdn.com/v4/letter/a/85f322/32.png) [@avaneeshr](https://discuss.elastic.co/u/avaneeshr)\
**Post date:** [October 8, 2017, 7:44pm UTC](https://discuss.elastic.co/t/unbalanced-search-performance/102606/3 "2017-10-08T19:44:08Z")

</div>

Okay so there has been a new development in this case.  
I removed the HAProxy and instead directly query one of the data nodes. Still the same result. The load averages appear to be unbalanced.  
I've brought a change in my cluster and since then, I've seen some balance being restored: I marked the data nodes as specifically "data nodes" in the configs and added 3 separate master nodes. Could this be related to the problem?  
Should I add dedicated client nodes? Would that theoretically solve the issue?

Thanks!

---

<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:** [November 5, 2017, 7:44pm UTC](https://discuss.elastic.co/t/unbalanced-search-performance/102606/4 "2017-11-05T19:44:36Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.