[Spce-user] SEMS SBC CPU question

Schaefer, Larry Larry.Schaefer at pgi.com
Thu Feb 13 12:06:25 EST 2014


Andreas,

Thanks for the response... I have been modifying media_processor_threads in sems.conf, but so far it does not seem to make a difference.  I am still wondering if running in Amazon EC2 is part of the issue.  

Wondering if anyone has experience with running SEMS in EC2 and if they are seeing any similar problems with CPU.  

Any additional advice or suggestions would be appreciated...

Thanks,
Larry 

-----Original Message-----
From: spce-user-bounces at lists.sipwise.com [mailto:spce-user-bounces at lists.sipwise.com] On Behalf Of Andreas Granig
Sent: Saturday, February 08, 2014 1:19 PM
To: spce-user at lists.sipwise.com
Subject: Re: [Spce-user] SEMS SBC CPU question

Hi,

I think there is a setting called media_processor_threads in sems.conf, which you could try to increase to see if it makes a difference.

Andreas

On 02/08/2014 12:12 AM, Schaefer, Larry wrote:
> I am trying to run SPCE with the SEMS SBC module (running with symmetric rtp configuration) in Amazon EC2 and having performance issues.  After about 700 callers, CPU on SEMS process is maxed and RTP starts to drop.  While watching top, it appears that sems is only running on one core.  Below is the output that I see while under load:
> 
> top - 23:08:06 up  7:31,  2 users,  load average: 0.43, 0.12, 0.08
> Tasks: 144 total,   1 running, 143 sleeping,   0 stopped,   0 zombie
> %Cpu0  :  9.2 us, 66.7 sy,  0.0 ni,  0.7 id,  0.0 wa,  0.0 hi, 23.4 
> si,  0.0 st
> %Cpu1  :  1.3 us,  0.0 sy,  0.0 ni, 98.3 id,  0.0 wa,  0.0 hi,  0.0 
> si,  0.3 st
> %Cpu2  :  0.0 us,  0.0 sy,  0.0 ni,100.0 id,  0.0 wa,  0.0 hi,  0.0 
> si,  0.0 st
> %Cpu3  :  0.0 us,  0.0 sy,  0.0 ni,100.0 id,  0.0 wa,  0.0 hi,  0.0 
> si,  0.0 st
> %Cpu4  :  0.3 us,  0.3 sy,  0.0 ni, 99.3 id,  0.0 wa,  0.0 hi,  0.0 
> si,  0.0 st
> %Cpu5  :  0.0 us,  0.0 sy,  0.0 ni,100.0 id,  0.0 wa,  0.0 hi,  0.0 
> si,  0.0 st
> %Cpu6  :  0.0 us,  0.0 sy,  0.0 ni,100.0 id,  0.0 wa,  0.0 hi,  0.0 
> si,  0.0 st
> %Cpu7  :  0.7 us,  1.0 sy,  0.0 ni, 98.3 id,  0.0 wa,  0.0 hi,  0.0 si,  0.0 st
> KiB Mem:   7134848 total,  2906892 used,  4227956 free,    46916 buffers
> KiB Swap:        0 total,        0 used,        0 free,  2022252 cached
> 
>   PID USER      PR  NI  VIRT  RES  SHR S  %CPU %MEM    TIME+  COMMAND
> 32702 sems      20   0  329m 186m 2088 S 103.0  2.7   4:26.85 sems
> 29108 root      20   0  128m 1636  424 S   3.0  0.0   1:17.43 mediaproxy-ng
> 1638 root      20   0  255m 1584 1128 S   1.3  0.0   0:21.14 rsyslogd
> 2985 mysql     20   0  657m 110m 7576 S   0.3  1.6   0:18.12 mysqld
> 29755 kamailio  20   0 1061m  24m 6500 S   0.3  0.4   0:02.16 kamailio
> 29756 kamailio  20   0 1061m  24m 6500 S   0.3  0.4   0:02.16 kamailio
> 29757 kamailio  20   0 1061m  24m 6500 S   0.3  0.4   0:02.11 kamailio
> 29759 kamailio  20   0 1061m  24m 6496 S   0.3  0.4   0:02.13 kamailio
> 29760 kamailio  20   0 1061m  24m 6500 S   0.3  0.4   0:02.10 kamailio
> 29762 kamailio  20   0 1060m  23m 4852 S   0.3  0.3   0:04.63 kamailio
>     1 root      20   0 10644  820  688 S   0.0  0.0   0:03.01 init
> 
> Is there any way to configure sems to use multiple cores for processing calls?  From the display looks like Cpu1-Cpu7 are idle, but Cpu0 is getting hit at 100%.
> 
> Thanks,
> Larry
> 
> 
> 
> 
> _______________________________________________
> Spce-user mailing list
> Spce-user at lists.sipwise.com
> http://lists.sipwise.com/listinfo/spce-user
> 

_______________________________________________
Spce-user mailing list
Spce-user at lists.sipwise.com
http://lists.sipwise.com/listinfo/spce-user




More information about the Spce-user mailing list