[OpenSIPS-Users] Degrades the performance of opensips after 100k calls

Dipteshkumar Patel diptesh.patel at ecosmob.com
Wed Nov 22 00:56:31 EST 2017


hello Razvan

Sorry for addressing you as Bogdan.

We found following statistics after making lots of calls

opensipsctl fifo get_statistics shmem:
shmem:total_size:: 12582912000
shmem:used_size:: 7009825993193851937
shmem:real_used_size:: 7009825993216059273
shmem:max_used_size:: 18446711925787847093
shmem:free_size:: 11436918093076404343
shmem:fragments:: 497092

After restarting opensips

opensipsctl fifo get_statistics shmem:
shmem:total_size:: 12582912000
shmem:used_size:: 3369296
shmem:real_used_size:: 3428304
shmem:max_used_size:: 3435928
shmem:free_size:: 12579483696
shmem:fragments:: 1043


Thanks






*Diptesh Patel*
Jr. Software Developer
Ecosmob Technologies Ltd
Ahmedabad
Mo:*+919898962659*

On Tue, Nov 21, 2017 at 10:46 PM, Răzvan Crainea <razvan at opensips.org>
wrote:

> So you are not seeing any memory reports, are you?
> You should also check what opensips is doing when the CPU usage goes up.
> For example, when the issue occurs, write down the PIDs involved and then
> do a full gdb snapshot using the 'opensipsctl trap' command. Get this
> information and send the resulted info here.
>
> Best regards,
>
> Răzvan Crainea
> OpenSIPS Developerwww.opensips-solutions.com
>
> On 11/21/2017 06:06 PM, Dipteshkumar Patel wrote:
>
> hello Bogdan
>
> I am using -m 12000 -M 24 at startup.
>
> thanks
>
>
>
> *Diptesh Patel*
> Jr. Software Developer
> Ecosmob Technologies Ltd
> Ahmedabad
> Mo:*+919898962659*
>
>
> _______________________________________________
> Users mailing list
> Users at lists.opensips.org
> http://lists.opensips.org/cgi-bin/mailman/listinfo/users
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.opensips.org/pipermail/users/attachments/20171122/aba3fe56/attachment.html>


More information about the Users mailing list