[SR-Users] Question about CPU

Daniel-Constantin Mierla miconda at gmail.com
Wed Sep 26 17:52:25 CEST 2012


Hello,

it might be due to dialog timeout checking. Do you get many calls 
terminated via dialog BYEs? You have some log messages that are printed 
for each BYE, that could be slowing the processing -- are these messages 
printed by that pid?

Cheers,
Daniel

On 9/26/12 3:12 PM, Ricardo Martinez wrote:
>
> Hi Daniel.
>
> This is the output for TOP
>
> top - 09:08:50 up 16:19,  3 users,  load average: 0.23, 0.12, 0.06
>
> Tasks: 160 total,   1 running, 159 sleeping,   0 stopped,   0 zombie
>
> Cpu0 : 45.1%us,  1.0%sy,  0.0%ni, 53.9%id,  0.0%wa,  0.0%hi, 0.0%si,  
> 0.0%st
>
> Cpu1 :  8.9%us,  4.6%sy,  0.0%ni, 83.8%id,  0.0%wa,  0.7%hi, 2.0%si,  
> 0.0%st
>
> Cpu2 :  1.9%us,  1.9%sy,  0.0%ni, 96.1%id,  0.0%wa,  0.0%hi, 0.0%si,  
> 0.0%st
>
> Cpu3 :  1.3%us,  1.3%sy,  0.0%ni, 97.4%id,  0.0%wa,  0.0%hi, 0.0%si,  
> 0.0%st
>
> Mem: 3924912k total,   706492k used,  3218420k free,    59448k buffers
>
> Swap: 6291448k total,        0k used,  6291448k free,   348716k cached
>
>   PID USER      PR NI  VIRT  RES  SHR S %CPU %MEM    TIME+ COMMAND
>
> *3804 root      20   0 1163m  25m  20m S 44.2  0.7   0:40.66 kamailio *
>
>  1103 root      20   0  249m 1704  968 S  5.9  0.0   5:27.39 rsyslogd
>
>  3789 root      20 0 1163m  26m  21m S  2.3  0.7   0:04.59 kamailio
>
>  3796 root      20   0 1163m  26m  21m S  2.3  0.7   0:04.38 kamailio
>
>  3802 root      20   0 1163m  26m  21m S  2.3  0.7   0:04.31 kamailio
>
>  3794 root      20 0 1163m  26m  21m S  2.0  0.7   0:04.45 kamailio
>
>  3803 root      20   0 1163m  26m  21m S  2.0  0.7   0:04.60 kamailio
>
>  3790 root      20   0 1163m  26m  21m S  1.6  0.7   0:04.48 kamailio
>
>  3792 root      20 0 1163m  26m  21m S  1.6  0.7   0:04.50 kamailio
>
>  3799 root      20   0 1163m  26m  21m S  1.6  0.7   0:04.68 kamailio
>
>  3649 root      20   0 15088 1232  900 R  1.3  0.0   0:07.83 top
>
>  3805 root      20 0 1163m  24m  20m S  0.3  0.6   0:00.61 kamailio
>
> And this is the output for “kamctl ps”
>
> [root at vLCR kamailio]# kamctl ps
>
> Process:: ID=0 PID=3781 Type=attendant
>
> Process:: ID=1 PID=3789 Type=udp receiver child=0 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> Process:: ID=2 PID=3790 Type=udp receiver child=1 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> Process:: ID=3 PID=3792 Type=udp receiver child=2 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> Process:: ID=4 PID=3794 Type=udp receiver child=3 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> Process:: ID=5 PID=3796 Type=udp receiver child=4 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> Process:: ID=6 PID=3799 Type=udp receiver child=5 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> Process:: ID=7 PID=3802 Type=udp receiver child=6 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> Process:: ID=8 PID=3803 Type=udp receiver child=7 
> sock=64.76.154.210:5060 <http://64.76.154.210:5060>
>
> *Process:: ID=9 PID=3804 Type=slow timer*
>
> Process:: ID=10 PID=3805 Type=timer
>
> Process:: ID=11 PID=3807 Type=MI FIFO
>
> Process:: ID=12 PID=3810 Type=TIMER RT
>
> Process:: ID=13 PID=3811 Type=MI DATAGRAM
>
> Process:: ID=14 PID=3812 Type=ctl handler
>
> Seems that the “Slow timer” is taking too much CPU.  Is this normal?.  
> I’m managing all the calls coming through the server with the dialog 
> module (dlg_manage ), as I mention I have a rate of 30cps and 
> sometimes I have 4500 active calls….
>
> Could be some way to release some of the CPU use by this process?
>
> Thanks again.
>
> Regards,
>
> Ricardo.-
>
> *De:*Daniel-Constantin Mierla [mailto:miconda at gmail.com 
> <mailto:miconda at gmail.com>]
> *Enviado el:* martes, 25 de septiembre de 2012 19:21
> *Para:* SIP Router - Kamailio (OpenSER) and SIP Express Router (SER) - 
> Users Mailing List
> *CC:* Ricardo Martinez
> *Asunto:* Re: [SR-Users] Question about CPU
>
> Hello,
>
> what is the type of the process? Run 'kamctl ps' and see the 
> description for that pid.
>
> Cheers,
> Daniel
>
> On 9/25/12 11:49 PM, Ricardo Martinez wrote:
>
>     Hello.
>
>     Is normal this output from the “top” command?!
>
>     I have a kamailio with 16 children receiving calls at rate of
>     30cps and using the dialog module to timeout the calls :
>
>     This is the top command :
>
>     Tasks: 168 total,   2 running, 166 sleeping,   0 stopped,   0 zombie
>
>     Cpu0  : 56.0%us, 0.7%sy,  0.0%ni, 43.4%id,  0.0%wa,  0.0%hi, 
>     0.0%si, 0.0%st
>
>     Cpu1  :  6.3%us, 3.0%sy,  0.0%ni, 87.8%id,  0.0%wa,  0.7%hi, 
>     2.3%si, 0.0%st
>
>     Cpu2  :  0.3%us, 0.3%sy,  0.0%ni, 99.3%id,  0.0%wa,  0.0%hi, 
>     0.0%si, 0.0%st
>
>     Cpu3  :  0.7%us, 0.3%sy,  0.0%ni, 99.0%id,  0.0%wa,  0.0%hi, 
>     0.0%si, 0.0%st
>
>     Mem:   3924912k total,   535700k used,  3389212k free,    20236k
>     buffers
>
>     Swap:  6291448k total,        0k used,  6291448k free,   226120k
>     cached
>
>       PID USER      PR NI  VIRT  RES  SHR S %CPU %MEM    TIME+ COMMAND
>
>     *2566 root 20   0 1163m  27m  23m R 56.2  0.7   2:08.32 kamailio *
>
>      1103 root      20 0  249m 1656  924 S  2.7  0.0   1:32.89 rsyslogd
>
>      2525 root      20   0 1163m  27m  23m S  0.7  0.7   0:02.93 kamailio
>
>      2527 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.11 kamailio
>
>      2528 root      20   0 1163m  27m  23m S  0.7  0.7   0:02.89 kamailio
>
>      2529 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.13 kamailio
>
>      2535 root      20   0 1163m  27m  23m S  0.7  0.7   0:02.86 kamailio
>
>      2537 root      20   0 1163m  27m  23m S  0.7  0.7   0:02.85 kamailio
>
>      2538 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.17 kamailio
>
>      2541 root      20   0 1163m  27m  23m S  0.7  0.7   0:02.91 kamailio
>
>      2542 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.07 kamailio
>
>      2543 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.12 kamailio
>
>      2544 root      20   0 1163m  27m  23m S  0.7  0.7   0:02.64 kamailio
>
>      2549 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.10 kamailio
>
>      2551 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.14 kamailio
>
>      2552 root      20   0 1163m  27m  23m S  0.7  0.7   0:03.00 kamailio
>
>      2495 root      20   0 15088 1240  900 R  0.3  0.0   0:04.10 top
>
>      2526 root      20   0 1163m  27m  23m S  0.3  0.7   0:02.83 kamailio
>
>      2532 root      20   0 1163m  27m  23m S  0.3  0.7   0:02.87 kamailio
>
>         1 root      20   0 19396 1500 1192 S  0.0  0.0   0:02.86 init
>
>         2 root      20 0     0    0    0 S  0.0  0.0   0:00.01 kthreadd
>
>         3 root      RT 0     0    0    0 S  0.0  0.0   0:00.00
>     migration/0
>
>         4 root      20 0     0    0    0 S  0.0  0.0   0:00.00
>     ksoftirqd/0
>
>         5 root      RT 0     0    0    0 S  0.0  0.0   0:00.00
>     migration/0
>
>         6 root      RT   0     0    0    0 S  0.0  0.0   0:00.00
>     watchdog/0
>
>     The question is : I always see the process PID : 2566 using more
>     CPU than the rest of the childrens.
>
>     Is this normal?
>
>     Regards,
>
>     Ricardo Martinez-.
>
>
>
>
>     _______________________________________________
>
>     SIP Express Router (SER) and Kamailio (OpenSER) - sr-users mailing list
>
>     sr-users at lists.sip-router.org  <mailto:sr-users at lists.sip-router.org>
>
>     http://lists.sip-router.org/cgi-bin/mailman/listinfo/sr-users
>
>
>
> -- 
> Daniel-Constantin Mierla -http://www.asipto.com
> http://twitter.com/#!/miconda  <http://twitter.com/#%21/miconda>  -http://www.linkedin.com/in/miconda
> Kamailio Advanced Training, Berlin, Nov 5-8, 2012 -http://asipto.com/u/kat
> Kamailio Advanced Training, Miami, USA, Nov 12-14, 2012 -http://asipto.com/u/katu

-- 
Daniel-Constantin Mierla - http://www.asipto.com
http://twitter.com/#!/miconda - http://www.linkedin.com/in/miconda
Kamailio Advanced Training, Berlin, Nov 5-8, 2012 - http://asipto.com/u/kat
Kamailio Advanced Training, Miami, USA, Nov 12-14, 2012 - http://asipto.com/u/katu

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.sip-router.org/pipermail/sr-users/attachments/20120926/12bfc0ef/attachment-0001.htm>


More information about the sr-users mailing list