# Hardware - Recommendations

**URL:** <https://discuss.elastic.co/t/hardware-recommendations/103386>\
**Category:** Elasticsearch\
**Created:** [October 10, 2017, 2:09pm UTC](https://discuss.elastic.co/t/hardware-recommendations/103386 "2017-10-10T14:09:43Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![Yann](https://avatars.discourse-cdn.com/v4/letter/y/bc79bd/32.png) [@Yann](https://discuss.elastic.co/u/Yann)\
**Post date:** [October 10, 2017, 2:09pm UTC](https://discuss.elastic.co/t/hardware-recommendations/103386/1 "2017-10-10T14:09:43Z")

</div>

Hello,

I want to migrate ELK on a VM to a more powerful physical machine and I would need recommendations.  
Currently, the VM includes 8 vCPU 2.3 GHz and 32 GB RAM.  
We process about 6 GB of data per day and we wish to upgrade to 40 GB.  
Some requests on the Elastic exceed 30 seconds. We want to greatly improve this performance.

Do you have any recommendations (CPU, RAM, SSD / disk, ...) ?

Best regards,

---

<div class="post-metadata">

**Author:** ![Christian\_Dahlqvist](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/christian_dahlqvist/32/4617_2.png) [@Christian\_Dahlqvist](https://discuss.elastic.co/u/Christian_Dahlqvist)\
**Post date:** [October 10, 2017, 2:17pm UTC](https://discuss.elastic.co/t/hardware-recommendations/103386/2 "2017-10-10T14:17:12Z")

</div>

How much data do you have on the node? How long do you keep data?

---

<div class="post-metadata">

**Author:** ![Yann](https://avatars.discourse-cdn.com/v4/letter/y/bc79bd/32.png) [@Yann](https://discuss.elastic.co/u/Yann)\
**Post date:** [October 12, 2017, 12:33pm UTC](https://discuss.elastic.co/t/hardware-recommendations/103386/3 "2017-10-12T12:33:47Z")

</div>

Currently, we have 10 G documents (5 Go) and we keep 2 weeks of data.

---

<div class="post-metadata">

**Author:** ![Christian\_Dahlqvist](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/christian_dahlqvist/32/4617_2.png) [@Christian\_Dahlqvist](https://discuss.elastic.co/u/Christian_Dahlqvist)\
**Post date:** [October 12, 2017, 12:57pm UTC](https://discuss.elastic.co/t/hardware-recommendations/103386/4 "2017-10-12T12:57:00Z")

</div>

SSDs generally always helps with performance as Elasticsearch is generally I/O intensive. Also make sure that you do not have lots of very small indices and shards as this can be [very inefficient](https://www.elastic.co/blog/how-many-shards-should-i-have-in-my-elasticsearch-cluster), both when indexing and querying.

40GB/day over 14 days is about 600GB of data. I would expect the node you specified should be able to handle that unless it has very slow storage or very heavy dashboards.

---

<div class="post-metadata">

**Author:** ![Yann](https://avatars.discourse-cdn.com/v4/letter/y/bc79bd/32.png) [@Yann](https://discuss.elastic.co/u/Yann)\
**Post date:** [October 12, 2017, 2:12pm UTC](https://discuss.elastic.co/t/hardware-recommendations/103386/5 "2017-10-12T14:12:59Z")

</div>

Ok, thanks for feedback.

---

<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 9, 2017, 2:13pm UTC](https://discuss.elastic.co/t/hardware-recommendations/103386/6 "2017-11-09T14:13:22Z")

</div>

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