# BalancedShardsAllocator and node computing power

**URL:** <https://discuss.elastic.co/t/balancedshardsallocator-and-node-computing-power/10391>\
**Category:** Elasticsearch\
**Created:** [January 17, 2013, 3:27pm UTC](https://discuss.elastic.co/t/balancedshardsallocator-and-node-computing-power/10391 "2013-01-17T15:27:56Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![otisg](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/otisg/32/492_2.png) [@otisg](https://discuss.elastic.co/u/otisg)\
**Post date:** [January 17, 2013, 3:27pm UTC](https://discuss.elastic.co/t/balancedshardsallocator-and-node-computing-power/10391/1 "2013-01-17T15:27:56Z")

</div>

Hi,

I had a quick look at BalancedShardsAllocator (trivial little patch:

> <https://github.com/elastic/elasticsearch/commit/2eb09e6b1abceb316c789f173988ac733a55dc8b>

  
;)) with an eye towards something that takes into account the computing  
power of the node - the CPU speed, the # of cores, disk speed, etc., but I  
didn't see anything like that.

Isn't something like that (ultimately) needed in order to really do a good  
job balancing, esp. with heterogeneous hardware?  
Is this something that's planned and in the issue tracker? If not, should  
I open?

## Thanks, Otis

ELASTICSEARCH Performance Monitoring - [http://sematext.com/spm/index.html](http://sematext.com/spm/index.html)

--

---

<div class="post-metadata">

**Author:** ![Ivan](https://avatars.discourse-cdn.com/v4/letter/i/df788c/32.png) [@Ivan](https://discuss.elastic.co/u/Ivan)\
**Post date:** [January 17, 2013, 6:28pm UTC](https://discuss.elastic.co/t/balancedshardsallocator-and-node-computing-power/10391/2 "2013-01-17T18:28:17Z")

</div>

It is great seeing another ShardsAllocator being worked on. I have been  
tempted to write my own to balance shards based on its own index and not  
all the indices in general.

--  
Ivan

On Thu, Jan 17, 2013 at 7:27 AM, Otis Gospodnetic \<  
[otis.gospodnetic@gmail.com](mailto:otis.gospodnetic@gmail.com)\> wrote:

> Hi,
> 
> I had a quick look at BalancedShardsAllocator (trivial little patch:  
> [https://github.com/elasticsearch/elasticsearch/commit/2eb09e6b1abceb316c789f173988ac733a55dc8b;](https://github.com/elasticsearch/elasticsearch/commit/2eb09e6b1abceb316c789f173988ac733a55dc8b;))) with an eye towards something that takes into account the computing  
> power of the node - the CPU speed, the # of cores, disk speed, etc., but I  
> didn't see anything like that.
> 
> Isn't something like that (ultimately) needed in order to really do a good  
> job balancing, esp. with heterogeneous hardware?  
> Is this something that's planned and in the issue tracker? If not, should  
> I open?
> 
> ## Thanks, Otis
> 
> ELASTICSEARCH Performance Monitoring - [Sematext Monitoring | Infrastructure Monitoring Service](http://sematext.com/spm/index.html)
> 
> --

--

---

<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 6, 2017, 2:55am UTC](https://discuss.elastic.co/t/balancedshardsallocator-and-node-computing-power/10391/3 "2017-07-06T02:55:53Z")

</div>