Why worker process only use cpu0?

I have 4 core CPU’s, cpu0-cpu3, but why NginX worker process only high
on
cpu0 than other cpu’s ?
This is my main configuration http://fpaste.org/VT7I

My hardware spec’s are :
Intel® Xeon® CPU X3220
Memory 4 x 2 GB of RAM

I am using htop to monitor the process’


View this message in context:
http://nginx.2469901.n2.nabble.com/why-worker-process-only-use-cpu0-tp6425023p6425023.html
Sent from the nginx mailing list archive at Nabble.com.

Sorry, for more details, I’m using nginx-0.8.54-1.el5


View this message in context:
http://nginx.2469901.n2.nabble.com/why-worker-process-only-use-cpu0-tp6425023p6425044.html
Sent from the nginx mailing list archive at Nabble.com.

Hello!

On Tue, May 31, 2011 at 04:07:39PM -0700, antituhan wrote:

I have 4 core CPU’s, cpu0-cpu3, but why NginX worker process only high on
cpu0 than other cpu’s ?
This is my main configuration http://fpaste.org/VT7I

Do you mean to ask “why only one nginx process actually uses CPU”
instead? This usually means that nginx isn’t really loaded and
one process is enough to handle all connections/requests.

In some situations you may want to disable accept mutex via

events {
    accept_mutex off;
    ...
}

or tune it with accept_mutex_delay directive. This should result
in more even distribution of load between nginx processes.

Maxim D.

Yup, I mean only one nginx process actually uses CPU :slight_smile:
Ok, I’ll try the directive and monitor them.


View this message in context:
http://nginx.2469901.n2.nabble.com/why-worker-process-only-use-cpu0-tp6425023p6425232.html
Sent from the nginx mailing list archive at Nabble.com.

This forum is not affiliated to the Ruby language, Ruby on Rails framework, nor any Ruby applications discussed here.

| Privacy Policy | Terms of Service | Remote Ruby Jobs