# "buffers" RAM use under Linux while running nginx

**URL:** <https://www.ruby-forum.com/t/buffers-ram-use-under-linux-while-running-nginx/208787>\
**Category:** NGINX\
**Created:** [June 27, 2011, 7:47am UTC](https://www.ruby-forum.com/t/buffers-ram-use-under-linux-while-running-nginx/208787 "2011-06-27T07:47:12Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![luislavena](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/l/0ea827/32.png) [@luislavena](https://www.ruby-forum.com/u/luislavena)\
**Post date:** [June 27, 2011, 7:47am UTC](https://www.ruby-forum.com/t/buffers-ram-use-under-linux-while-running-nginx/208787/1 "2011-06-27T07:47:12Z")

</div>

Hi all,

I have a couple of web servers running nginx 1.0.4 on Ubuntu 10.04  
AMD64, serving several hundred GB of static images. Each machine has 4GB  
of RAM, but less than 1GB is used by the Linux page cache, because  
there’s more than 2GB assigned to “buffers”. Here’s the output from the  
“free” on one of them:

```
        total used free shared buffers cached

```

Mem: 4057484 4024404 33080 0 2421352 947772  
-/+ buffers/cache: 655280 3402204  
Swap: 3998712 0 3998712

From what I understand, “buffers” includes the TCP send buffers for  
each outgoing connection, and might include read buffers for each file  
that’s in transit, but I’m surprised that it’s adding up to 2.4GB.

Is this expected behaviour? Is there any way I can reduce those buffers  
to get more cache RAM, or should I just throw more RAM in these  
machines?

Thanks  
Leigh