For what it's worth, here's the output from our server just now--with the
exception of one thread (maybe it's the session-sweeper or TaskKit or some
such), we're balancing nicely.  Thanks (Tim Roberts) for "ps axf" -- I
didn't know about that either.

22147 ?        SN     0:00 /bin/sh /home/adc/adc/wwwroot/AppServer
22149 ?        SN     1:52  \_ python Launch.py ThreadedAppServer
22150 ?        SN     0:07      \_ python Launch.py ThreadedAppServer
22151 ?        SN    15:13          \_ python Launch.py ThreadedAppServer
22152 ?        SN     0:00          \_ python Launch.py ThreadedAppServer
22153 ?        SN    31:51          \_ python Launch.py ThreadedAppServer
22154 ?        SN    32:57          \_ python Launch.py ThreadedAppServer
22155 ?        SN    33:03          \_ python Launch.py ThreadedAppServer
22156 ?        SN    30:41          \_ python Launch.py ThreadedAppServer
22157 ?        SN    30:54          \_ python Launch.py ThreadedAppServer
22158 ?        SN    33:10          \_ python Launch.py ThreadedAppServer
22159 ?        SN    31:32          \_ python Launch.py ThreadedAppServer
22160 ?        SN    31:25          \_ python Launch.py ThreadedAppServer
22161 ?        SN    31:11          \_ python Launch.py ThreadedAppServer
22162 ?        SN    31:00          \_ python Launch.py ThreadedAppServer

Cheers!
--
David Hancock | [EMAIL PROTECTED] | 410-266-4384 


-----Original Message-----
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Frank
Barknecht
Sent: Wednesday, July 07, 2004 4:14 PM
To: [EMAIL PROTECTED]
Subject: Re: [Webware-discuss] CPU Usage Pattern


Hallo,
Tim Roberts hat gesagt: // Tim Roberts wrote:

> OK, I admit to knowing almost nothing about the way tasks are allocated 
> between threads in WebWare, but I happened to do a "ps axf" today 

Cool, I didn't know these options.

> on a machine that has been running  for about 8 months, and saw
> this:
> 
> 1622 ?        SN     0:00 /bin/sh ./AppServer 19647 ?        SN
> 49:47  \_ python Launch.py ThreadedAppServer 19648 ?        SN
> 1:48      \_ python Launch.py ThreadedAppServer 19649 ?        SN
> 142:38          \_ python Launch.py ThreadedAppServer 19650 ?
> SN     0:00          \_ python Launch.py ThreadedAppServer 19651 ?
> SN   117:47          \_ python Launch.py ThreadedAppServer 19652 ?
> SN     0:00          \_ python Launch.py ThreadedAppServer 19653 ?
> SN     0:00          \_ python Launch.py ThreadedAppServer 19654 ?
> SN     0:00          \_ python Launch.py ThreadedAppServer 19655 ?
> SN     0:00          \_ python Launch.py ThreadedAppServer 19656 ?
> SN     0:00          \_ python Launch.py ThreadedAppServer
> 
> Notice the uneven distribution of CPU times.  

I get a very similar picture with a slighty more loaded server. There
are 2 out of 10 threads that appear to never be used, one is used a
lot, the others only a little bit. This could be used to tune servers
a bit. In your case it might not be necessary to run all those
threads.

Ciao
-- 
 Frank Barknecht                               _ ______footils.org__


-------------------------------------------------------
This SF.Net email sponsored by Black Hat Briefings & Training.
Attend Black Hat Briefings & Training, Las Vegas July 24-29 - 
digital self defense, top technical experts, no vendor pitches, 
unmatched networking opportunities. Visit www.blackhat.com
_______________________________________________
Webware-discuss mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/webware-discuss


-------------------------------------------------------
This SF.Net email sponsored by Black Hat Briefings & Training.
Attend Black Hat Briefings & Training, Las Vegas July 24-29 - 
digital self defense, top technical experts, no vendor pitches, 
unmatched networking opportunities. Visit www.blackhat.com
_______________________________________________
Webware-discuss mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/webware-discuss

Reply via email to