# Performance difference 1 node vs 3 nodes
**URL:** https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994
**Category:** Elasticsearch
**Tags:** rally
**Created:** [February 8, 2018, 8:19am UTC](https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994 "2018-02-08T08:19:30Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@arcaya](https://discuss.elastic.co/u/arcaya)
#### Post date: [February 8, 2018, 8:19am UTC](https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994/1 "2018-02-08T08:19:30Z")
Hi,
I am trying to know which would be the performance improvement of running a 3 node cluster over a 1 node cluster.
In order to do this, I have installed esrally and run this way
- esrally --distribution-version=6.0.0 // running locally on 1 node
- esrally --distribution-version=6.0.0 --target-hosts=172.16.8.117:9200,172.16.8.118:9200,172.16.8.119:9200
To my surprise the results are pretty much the same, it looks as rally has run the same workload 3 times instead of 1 workload shared amongst the 3 nodes.
Is there any way to achive what I want?
Thanks!
---
### Author:  [@arcaya](https://discuss.elastic.co/u/arcaya)
#### Post date: [February 8, 2018, 10:31am UTC](https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994/2 "2018-02-08T10:31:05Z")
I can close this topic as I run erally differently, when running it correctly it displays a significant improvement
---
### Author:  [@Christian\_Dahlqvist](https://discuss.elastic.co/u/Christian_Dahlqvist)
#### Post date: [February 8, 2018, 10:32am UTC](https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994/3 "2018-02-08T10:32:03Z")
What change did you make?
---
### Author:  [@arcaya](https://discuss.elastic.co/u/arcaya)
#### Post date: [February 8, 2018, 10:47am UTC](https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994/4 "2018-02-08T10:47:13Z")
I think I was a bit confused about the results. Since there are some that improve like index append median that goes from 5500 docs/s to 12000 docs/s, wile others stay pretty much the same like index-stats that is around 100 ops/s in both
---
### Author:  [@danielmitterdorfer](https://discuss.elastic.co/u/danielmitterdorfer)
#### Post date: [February 8, 2018, 12:24pm UTC](https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994/5 "2018-02-08T12:24:15Z")
> [@arcaya](#):
>
> others stay pretty much the same like index-stats that is around 100 ops/s in both
The reason for this is that [we intentionally throttle the throughput](https://github.com/elastic/rally-tracks/blob/master/geonames/challenges/default.json#L33) so this is expected. Here is some further reading why we do this:
- [Rally FAQ](http://esrally.readthedocs.io/en/stable/faq.html#what-does-latency-and-service-time-mean-and-how-do-they-related-to-the-took-field-that-elasticsearch-returns)
- [track reference](http://esrally.readthedocs.io/en/stable/track.html#schedule) (see docs on target-throughput).
---
### Author:  [@system](https://discuss.elastic.co/u/system)
#### Post date: [March 8, 2018, 12:24pm UTC](https://discuss.elastic.co/t/performance-difference-1-node-vs-3-nodes/118994/6 "2018-03-08T12:24:23Z")
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.