Questions about stub status numbers

Server NGINX
1

Below is a snapshot of what the stub status returns:

Active connections: 2617 server accepts handled requests 15883769
15883769 52195337 Reading: 96 Writing: 56 Waiting: 2465

Is the fact that we have 2K+ processes waiting a problem, meaning, on a
high
traffic, optimized server, should the number of waiting connections be
much
less?

Let me ask different, is having 2K+ connections waiting considered a
problem? Should that number ideally be as close to “0” as possible?

Thanks

–

Ilan B.
Chief Technology Officer

6300 NE 1st Ave., Suite 203
Ft. Lauderdale, FL 33334
(954) 771-0914

http://www.twitter.com/time4learning
http://www.facebook.com/Time4Learning

Time4Learning.com - Online interactive curriculum for home use, PreK-8th
Grade.
Time4Writing.com - Online writing tutorials for high, middle, and
elementary
school students.
Time4Learning.net - A forum to chat with parents online about kids,
education, parenting and more.
spellingcity.com - Online vocabulary and spelling activities for
teachers,
parents and students.

2

Is the fact that we have 2K+ processes waiting a problem, meaning, on a
high traffic, optimized server, should the number of waiting connections
be much less?
Let me ask different, is having 2K+ connections waiting considered a
problem? Should that number ideally be as close to “0” as possible?

No and no. In fact on high traffic server there could be even more.
Waiting are just keepalive connections. It is also mentioned in
documentation: Module ngx_http_stub_status_module

rr

3

On 10/27/11 23:57, Ilan B. wrote:

Is the fact that we have 2K+ processes waiting a problem, meaning, on a high
traffic, optimized server, should the number of waiting connections be much
less?

It is normal if keep-alive enabled. 2k+ is a small number for big site.
And in most cases you should not disable keep-alive.

Let me ask different, is having 2K+ connections waiting considered a problem?
Should that number ideally be as close to “0” as possible?

No.

But don’t forget to tune server - rise maxfiles, maxsockets and
worker_connections if this number will be close to current limits.

About stab_status numbers - graph them (e. g. by rrdtool) and see trends
on
graph. Is some number stable for a long time, and then grow rapidly -
this can
be problem indicator.

–
Anton Y.