Sponsor: VoiceMeUp - Corporate & Wholesale VoIP Services

VoIP Mailing List Archives
Mailing list archives for the VoIP community
 SearchSearch 

[Freeswitch-users] Freeswitch performance as a redirecting server

Goto page Previous  1, 2
 
Post new topic   Reply to topic    VoIP Mailing List Archives Forum Index -> freeSWITCH Users
View previous topic :: View next topic  
Author Message
tculjaga at gmail.com
Guest





PostPosted: Tue Aug 25, 2009 1:00 pm    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

nice, this is one way to go...

btw: when do you exactly bring up a new thread ?

T.

On Tue, Aug 25, 2009 at 7:40 PM, Michael Collins <msc@freeswitch.org (msc@freeswitch.org)> wrote:
Quote:


On Tue, Aug 25, 2009 at 10:31 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Of course i removed everytihng from teh dialplan except my extension Smile

when exactly do you react and bring up a new thread ? ... is it on INVITE or on 1st 1xx response ?

i beleive i can have several lets call it SIP interfaces ... on different ports 5060, 5070, 5080 ... every interface will have it's own sip profile.

does it mean i will have one thread per profile?

Yes.




_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org

Back to top
mike at jerris.com
Guest





PostPosted: Tue Aug 25, 2009 1:03 pm    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

On Aug 25, 2009, at 1:40 PM, Michael Collins wrote:
Quote:


On Tue, Aug 25, 2009 at 10:31 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Of course i removed everytihng from teh dialplan except my extension Smile

when exactly do you react and bring up a new thread ? ... is it on INVITE or on 1st 1xx response ?



Before it hits the dialplan.

Quote:
Quote:

i beleive i can have several lets call it SIP interfaces ... on different ports 5060, 5070, 5080 ... every interface will have it's own sip profile.

does it mean i will have one thread per profile?
Yes.




And no. There are still parts of the stack that are in one thread.


Mike
Back to top
mrene_lists at avgs.ca
Guest





PostPosted: Tue Aug 25, 2009 1:09 pm    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

mod_sofia will take care of spawning the session thread once it authenticated the call and loaded all the variables related to the call such as the caller profile (callerid, destination number, etc).

If you want to check the source, this is done in sofia_handle_sip_i_invite() (sofia.c:5261) with switch_core_session_thread_launch().

Mathieu Rene
Avant-Garde Solutions Inc
Office: + 1 (514) 664-1044 x100
Cell: +1 (514) 664-1044 x200
mrene@avgs.ca (mrene@avgs.ca)








On 25-Aug-09, at 1:53 PM, Tihomir Culjaga wrote:
Quote:
nice, this is one way to go...

btw: when do you exactly bring up a new thread ?

T.

On Tue, Aug 25, 2009 at 7:40 PM, Michael Collins <msc@freeswitch.org (msc@freeswitch.org)> wrote:
Quote:


On Tue, Aug 25, 2009 at 10:31 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Of course i removed everytihng from teh dialplan except my extension Smile

when exactly do you react and bring up a new thread ? ... is it on INVITE or on 1st 1xx response ?

i beleive i can have several lets call it SIP interfaces ... on different ports 5060, 5070, 5080 ... every interface will have it's own sip profile.

does it mean i will have one thread per profile?

Yes.




_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org
Back to top
tculjaga at gmail.com
Guest





PostPosted: Tue Aug 25, 2009 1:12 pm    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

clear... thanks!

On Tue, Aug 25, 2009 at 7:55 PM, Michael Jerris <mike@jerris.com (mike@jerris.com)> wrote:
Quote:

On Aug 25, 2009, at 1:40 PM, Michael Collins wrote:

Quote:


On Tue, Aug 25, 2009 at 10:31 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Of course i removed everytihng from teh dialplan except my extension Smile

when exactly do you react and bring up a new thread ? ... is it on INVITE or on 1st 1xx response ?




Before it hits the dialplan.

Quote:
Quote:

i beleive i can have several lets call it SIP interfaces ... on different ports 5060, 5070, 5080 ... every interface will have it's own sip profile.

does it mean i will have one thread per profile?
Yes.





And no. There are still parts of the stack that are in one thread.


Mike


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org

Back to top
tculjaga at gmail.com
Guest





PostPosted: Wed Aug 26, 2009 3:12 am    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

Hi Giovanny,

regarding ubuntu, did you mean 8.04 server or desktop ?


On Tue, Aug 25, 2009 at 3:41 PM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)> wrote:
Quote:
Definitely go for 64 bit OS.

If you want to be safe and sure,  go for CentOS 5.2 64bit. Is the one
used both for development and for heavy duty production.

Also Ubuntu 8.04 is good.

Other versions/distros are less used by the community.

Adding RAM and CPUs helps to scale up.

-gm



Sincerely,

Giovanni Maruzzelli
Cell : +39-347-2665618





On Tue, Aug 25, 2009 at 3:19 PM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Hey Giovanni,

thanks for the tip... indeed the db files were heavily used regardless if i
started freeswitch with nosql option (freeswitch -nosql)... FS was not
writing anything into that files ... instead it was just accessing it....
This behaviour leads to a waste of 40% CPU time... waiting for other
processes (mainly disk access) to finish!!!

I moved freeswitch/db/ to a ramdisk and the performance got a boost to 140
CPS with a CPU load of 80%. I was keeping the machine for a while (20 - 30
minutes) on that rate when i sow CPU suddenly went to 100% and FS becoming
irresponsive Smile.


What can be wrong?
What are the limits in CPU usage (50%, 60%, 70%, 80%...) we should not
cross?
What fine tuning do we need in order to asure a long high load run?



Also, I'm running 32-bit OS (debian 5) on a 64 bit CPU... does it have sense
to move my OS to 64 bit? ... will FS gain more preformance ?... I mean will
FS perofomr drastically better 20%+ ?


Tihomir.


On Tue, Aug 25, 2009 at 11:00 AM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Maybe your load comes from disk access?

Try putting the sql and log directories on a ramdisk.

OTH,

-giovanni

On Tue, Aug 25, 2009 at 10:54 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hello,

i'm trying to use freeswitch as a redirecting server meaning FS has to
receive an INVITE and according to some rules it will redirect calls to
other destinations.


CALLING_USER                FREESWITCH                        SOMEWHERE

INVITE ------------------------------->
           <------------------------------ 100 Trying
           <------------------------------ 302 Moved Temporary
ACK    ------------------------------->

INVITE--------------------------------------------------------------------------------->



Well, wverything works well except i have perfromance issues .... on my
HW
FS cannot do more than 40 CPS (INVITE answered by 302 Moved Temporary).
When
i increase the rate, FS starts delaying 302 response. Right at 50 CPS i
see
"calls" being build up in FS and the delay begining to grow.

When i observe the machine, load average is almost nothing (load
average:
1.41, 0.61, 0.60) CPU never goes to 100%, and i see only one thread
taking
most load... all others are just sitting there with 1-5 % CPU time.
This looks to me as FS handles 302 messages in a single thread?!?!


tculjaga@FS:/usr/local/freeswitch/conf/dialplan$ top -H

top - 10:41:37 up 167 days, 20:42,  3 users,  load average: 1.41, 0.61,
0.60
Tasks:  83 total,   2 running,  81 sleeping,   0 stopped,   0 zombie
Cpu(s): 25.3%us,  1.5%sy,  0.0%ni, 30.3%id, 42.7%wa,  0.0%hi,  0.2%si,
0.0%st
Mem:   2074520k total,   571244k used,  1503276k free,   259604k buffers
Swap:  2650684k total,     3020k used,  2647664k free,   153868k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
COMMAND
 4814 root      20   0 34188  20m 3780 S   38  1.0   3:10.29
freeswitch
 4800 root      20   0 34188  20m 3780 S    6  1.0   0:08.26
freeswitch
 4798 root      20   0 34188  20m 3780 R    5  1.0   0:24.46
freeswitch
 4787 root      20   0 34188  20m 3780 S    2  1.0   0:11.24
freeswitch
 4794 root      20   0 34188  20m 3780 S    1  1.0   0:11.42
freeswitch
 4803 root      20   0 34188  20m 3780 S    1  1.0   0:11.74
freeswitch
 4788 root      20   0 34188  20m 3780 S    1  1.0   0:02.96
freeswitch
 4804 root      20   0 34188  20m 3780 S    1  1.0   0:01.64
freeswitch
 4807 root      20   0 34188  20m 3780 S    1  1.0   0:01.68
freeswitch
 4811 root      20   0 34188  20m 3780 S    1  1.0   0:02.50 freeswitch



cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
apicid          : 0
initial apicid  : 0
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2 ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4670.78
clflush size    : 64
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2 ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4666.82
clflush size    : 64
power management:



uname -a
Linux l01sipindir1 2.6.26-1-686 #1 SMP Sat Jan 10 18:29:31 UTC 2009 i686
GNU/Linux



Of course, i've tuned the machine up

ulimit -c unlimited
ulimit -d unlimited
ulimit -f unlimited
ulimit -i unlimited
ulimit -n 999999
ulimit -q unlimited
ulimit -u unlimited
ulimit -v unlimited
ulimit -x unlimited
ulimit -s 240
ulimit -l unlimited
ulimit -a


Started FS with minimum modules but still 40 CPS seems to be the limit.


So, is there any way to improve performance?


Tihomir.







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


Back to top
gmaruzz at celliax.org
Guest





PostPosted: Wed Aug 26, 2009 3:34 am    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

netbook remix


joking! Server 64bit Smile

-gm



On Wed, Aug 26, 2009 at 10:08 AM, Tihomir Culjaga<tculjaga@gmail.com> wrote:
Quote:
Hi Giovanny,

regarding ubuntu, did you mean 8.04 server or desktop ?


On Tue, Aug 25, 2009 at 3:41 PM, Giovanni Maruzzelli <gmaruzz@celliax.org>
wrote:
Quote:

Definitely go for 64 bit OS.

If you want to be safe and sure,  go for CentOS 5.2 64bit. Is the one
used both for development and for heavy duty production.

Also Ubuntu 8.04 is good.

Other versions/distros are less used by the community.

Adding RAM and CPUs helps to scale up.

-gm



Sincerely,

Giovanni Maruzzelli
Cell : +39-347-2665618




On Tue, Aug 25, 2009 at 3:19 PM, Tihomir Culjaga<tculjaga@gmail.com>
wrote:
Quote:
Hey Giovanni,

thanks for the tip... indeed the db files were heavily used regardless
if i
started freeswitch with nosql option (freeswitch -nosql)... FS was not
writing anything into that files ... instead it was just accessing
it....
This behaviour leads to a waste of 40% CPU time... waiting for other
processes (mainly disk access) to finish!!!

I moved freeswitch/db/ to a ramdisk and the performance got a boost to
140
CPS with a CPU load of 80%. I was keeping the machine for a while (20 -
30
minutes) on that rate when i sow CPU suddenly went to 100% and FS
becoming
irresponsive Smile.


What can be wrong?
What are the limits in CPU usage (50%, 60%, 70%, 80%...) we should not
cross?
What fine tuning do we need in order to asure a long high load run?



Also, I'm running 32-bit OS (debian 5) on a 64 bit CPU... does it have
sense
to move my OS to 64 bit? ... will FS gain more preformance ?... I mean
will
FS perofomr drastically better 20%+ ?


Tihomir.


On Tue, Aug 25, 2009 at 11:00 AM, Giovanni Maruzzelli
<gmaruzz@celliax.org>
wrote:
Quote:

Maybe your load comes from disk access?

Try putting the sql and log directories on a ramdisk.

OTH,

-giovanni

On Tue, Aug 25, 2009 at 10:54 AM, Tihomir Culjaga<tculjaga@gmail.com>
wrote:
Quote:
Hello,

i'm trying to use freeswitch as a redirecting server meaning FS has
to
receive an INVITE and according to some rules it will redirect calls
to
other destinations.


CALLING_USER                FREESWITCH
SOMEWHERE

INVITE ------------------------------->
           <------------------------------ 100 Trying
           <------------------------------ 302 Moved Temporary
ACK    ------------------------------->


INVITE--------------------------------------------------------------------------------->



Well, wverything works well except i have perfromance issues .... on
my
HW
FS cannot do more than 40 CPS (INVITE answered by 302 Moved
Temporary).
When
i increase the rate, FS starts delaying 302 response. Right at 50 CPS
i
see
"calls" being build up in FS and the delay begining to grow.

When i observe the machine, load average is almost nothing (load
average:
1.41, 0.61, 0.60) CPU never goes to 100%, and i see only one thread
taking
most load... all others are just sitting there with 1-5 % CPU time.
This looks to me as FS handles 302 messages in a single thread?!?!


tculjaga@FS:/usr/local/freeswitch/conf/dialplan$ top -H

top - 10:41:37 up 167 days, 20:42,  3 users,  load average: 1.41,
0.61,
0.60
Tasks:  83 total,   2 running,  81 sleeping,   0 stopped,   0 zombie
Cpu(s): 25.3%us,  1.5%sy,  0.0%ni, 30.3%id, 42.7%wa,  0.0%hi,
0.2%si,
0.0%st
Mem:   2074520k total,   571244k used,  1503276k free,   259604k
buffers
Swap:  2650684k total,     3020k used,  2647664k free,   153868k
cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
COMMAND
 4814 root      20   0 34188  20m 3780 S   38  1.0   3:10.29
freeswitch
 4800 root      20   0 34188  20m 3780 S    6  1.0   0:08.26
freeswitch
 4798 root      20   0 34188  20m 3780 R    5  1.0   0:24.46
freeswitch
 4787 root      20   0 34188  20m 3780 S    2  1.0   0:11.24
freeswitch
 4794 root      20   0 34188  20m 3780 S    1  1.0   0:11.42
freeswitch
 4803 root      20   0 34188  20m 3780 S    1  1.0   0:11.74
freeswitch
 4788 root      20   0 34188  20m 3780 S    1  1.0   0:02.96
freeswitch
 4804 root      20   0 34188  20m 3780 S    1  1.0   0:01.64
freeswitch
 4807 root      20   0 34188  20m 3780 S    1  1.0   0:01.68
freeswitch
 4811 root      20   0 34188  20m 3780 S    1  1.0   0:02.50
freeswitch



cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
apicid          : 0
initial apicid  : 0
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4670.78
clflush size    : 64
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4666.82
clflush size    : 64
power management:



uname -a
Linux l01sipindir1 2.6.26-1-686 #1 SMP Sat Jan 10 18:29:31 UTC 2009
i686
GNU/Linux



Of course, i've tuned the machine up

ulimit -c unlimited
ulimit -d unlimited
ulimit -f unlimited
ulimit -i unlimited
ulimit -n 999999
ulimit -q unlimited
ulimit -u unlimited
ulimit -v unlimited
ulimit -x unlimited
ulimit -s 240
ulimit -l unlimited
ulimit -a


Started FS with minimum modules but still 40 CPS seems to be the
limit.


So, is there any way to improve performance?


Tihomir.







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org
Back to top
tculjaga at gmail.com
Guest





PostPosted: Wed Aug 26, 2009 3:37 am    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

intanto e il centos che si sta installando Smile

grazie.

T.

On Wed, Aug 26, 2009 at 10:25 AM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)> wrote:
Quote:
netbook remix


joking! Server 64bit Smile

-gm




On Wed, Aug 26, 2009 at 10:08 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Hi Giovanny,

regarding ubuntu, did you mean 8.04 server or desktop ?


On Tue, Aug 25, 2009 at 3:41 PM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Definitely go for 64 bit OS.

If you want to be safe and sure,  go for CentOS 5.2 64bit. Is the one
used both for development and for heavy duty production.

Also Ubuntu 8.04 is good.

Other versions/distros are less used by the community.

Adding RAM and CPUs helps to scale up.

-gm



Sincerely,

Giovanni Maruzzelli
Cell : +39-347-2665618




On Tue, Aug 25, 2009 at 3:19 PM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hey Giovanni,

thanks for the tip... indeed the db files were heavily used regardless
if i
started freeswitch with nosql option (freeswitch -nosql)... FS was not
writing anything into that files ... instead it was just accessing
it....
This behaviour leads to a waste of 40% CPU time... waiting for other
processes (mainly disk access) to finish!!!

I moved freeswitch/db/ to a ramdisk and the performance got a boost to
140
CPS with a CPU load of 80%. I was keeping the machine for a while (20 -
30
minutes) on that rate when i sow CPU suddenly went to 100% and FS
becoming
irresponsive Smile.


What can be wrong?
What are the limits in CPU usage (50%, 60%, 70%, 80%...) we should not
cross?
What fine tuning do we need in order to asure a long high load run?



Also, I'm running 32-bit OS (debian 5) on a 64 bit CPU... does it have
sense
to move my OS to 64 bit? ... will FS gain more preformance ?... I mean
will
FS perofomr drastically better 20%+ ?


Tihomir.


On Tue, Aug 25, 2009 at 11:00 AM, Giovanni Maruzzelli
<gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Maybe your load comes from disk access?

Try putting the sql and log directories on a ramdisk.

OTH,

-giovanni

On Tue, Aug 25, 2009 at 10:54 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hello,

i'm trying to use freeswitch as a redirecting server meaning FS has
to
receive an INVITE and according to some rules it will redirect calls
to
other destinations.


CALLING_USER                FREESWITCH
SOMEWHERE

INVITE ------------------------------->
           <------------------------------ 100 Trying
           <------------------------------ 302 Moved Temporary
ACK    ------------------------------->


INVITE--------------------------------------------------------------------------------->



Well, wverything works well except i have perfromance issues .... on
my
HW
FS cannot do more than 40 CPS (INVITE answered by 302 Moved
Temporary).
When
i increase the rate, FS starts delaying 302 response. Right at 50 CPS
i
see
"calls" being build up in FS and the delay begining to grow.

When i observe the machine, load average is almost nothing (load
average:
1.41, 0.61, 0.60) CPU never goes to 100%, and i see only one thread
taking
most load... all others are just sitting there with 1-5 % CPU time.
This looks to me as FS handles 302 messages in a single thread?!?!


tculjaga@FS:/usr/local/freeswitch/conf/dialplan$ top -H

top - 10:41:37 up 167 days, 20:42,  3 users,  load average: 1.41,
0.61,
0.60
Tasks:  83 total,   2 running,  81 sleeping,   0 stopped,   0 zombie
Cpu(s): 25.3%us,  1.5%sy,  0.0%ni, 30.3%id, 42.7%wa,  0.0%hi,
0.2%si,
0.0%st
Mem:   2074520k total,   571244k used,  1503276k free,   259604k
buffers
Swap:  2650684k total,     3020k used,  2647664k free,   153868k
cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
COMMAND
 4814 root      20   0 34188  20m 3780 S   38  1.0   3:10.29
freeswitch
 4800 root      20   0 34188  20m 3780 S    6  1.0   0:08.26
freeswitch
 4798 root      20   0 34188  20m 3780 R    5  1.0   0:24.46
freeswitch
 4787 root      20   0 34188  20m 3780 S    2  1.0   0:11.24
freeswitch
 4794 root      20   0 34188  20m 3780 S    1  1.0   0:11.42
freeswitch
 4803 root      20   0 34188  20m 3780 S    1  1.0   0:11.74
freeswitch
 4788 root      20   0 34188  20m 3780 S    1  1.0   0:02.96
freeswitch
 4804 root      20   0 34188  20m 3780 S    1  1.0   0:01.64
freeswitch
 4807 root      20   0 34188  20m 3780 S    1  1.0   0:01.68
freeswitch
 4811 root      20   0 34188  20m 3780 S    1  1.0   0:02.50
freeswitch



cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
apicid          : 0
initial apicid  : 0
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4670.78
clflush size    : 64
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4666.82
clflush size    : 64
power management:



uname -a
Linux l01sipindir1 2.6.26-1-686 #1 SMP Sat Jan 10 18:29:31 UTC 2009
i686
GNU/Linux



Of course, i've tuned the machine up

ulimit -c unlimited
ulimit -d unlimited
ulimit -f unlimited
ulimit -i unlimited
ulimit -n 999999
ulimit -q unlimited
ulimit -u unlimited
ulimit -v unlimited
ulimit -x unlimited
ulimit -s 240
ulimit -l unlimited
ulimit -a


Started FS with minimum modules but still 40 CPS seems to be the
limit.


So, is there any way to improve performance?


Tihomir.







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


Back to top
kadantsev.d at gmail.com
Guest





PostPosted: Wed Aug 26, 2009 9:05 am    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

Hi all,

is there same situation with FS for Windows? I mean 64bit is more preferable than 32bit, isn't it?

Any performance test on Win 32/64 were done?
--
Best regards,
Dmitry Kadantsev


On Wed, Aug 26, 2009 at 10:29 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
intanto e il centos che si sta installando Smile

grazie.

T.


On Wed, Aug 26, 2009 at 10:25 AM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)> wrote:
Quote:
netbook remix


joking! Server 64bit Smile

-gm




On Wed, Aug 26, 2009 at 10:08 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Hi Giovanny,

regarding ubuntu, did you mean 8.04 server or desktop ?


On Tue, Aug 25, 2009 at 3:41 PM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Definitely go for 64 bit OS.

If you want to be safe and sure,  go for CentOS 5.2 64bit. Is the one
used both for development and for heavy duty production.

Also Ubuntu 8.04 is good.

Other versions/distros are less used by the community.

Adding RAM and CPUs helps to scale up.

-gm



Sincerely,

Giovanni Maruzzelli
Cell : +39-347-2665618




On Tue, Aug 25, 2009 at 3:19 PM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hey Giovanni,

thanks for the tip... indeed the db files were heavily used regardless
if i
started freeswitch with nosql option (freeswitch -nosql)... FS was not
writing anything into that files ... instead it was just accessing
it....
This behaviour leads to a waste of 40% CPU time... waiting for other
processes (mainly disk access) to finish!!!

I moved freeswitch/db/ to a ramdisk and the performance got a boost to
140
CPS with a CPU load of 80%. I was keeping the machine for a while (20 -
30
minutes) on that rate when i sow CPU suddenly went to 100% and FS
becoming
irresponsive Smile.


What can be wrong?
What are the limits in CPU usage (50%, 60%, 70%, 80%...) we should not
cross?
What fine tuning do we need in order to asure a long high load run?



Also, I'm running 32-bit OS (debian 5) on a 64 bit CPU... does it have
sense
to move my OS to 64 bit? ... will FS gain more preformance ?... I mean
will
FS perofomr drastically better 20%+ ?


Tihomir.


On Tue, Aug 25, 2009 at 11:00 AM, Giovanni Maruzzelli
<gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Maybe your load comes from disk access?

Try putting the sql and log directories on a ramdisk.

OTH,

-giovanni

On Tue, Aug 25, 2009 at 10:54 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hello,

i'm trying to use freeswitch as a redirecting server meaning FS has
to
receive an INVITE and according to some rules it will redirect calls
to
other destinations.


CALLING_USER                FREESWITCH
SOMEWHERE

INVITE ------------------------------->
           <------------------------------ 100 Trying
           <------------------------------ 302 Moved Temporary
ACK    ------------------------------->


INVITE--------------------------------------------------------------------------------->



Well, wverything works well except i have perfromance issues .... on
my
HW
FS cannot do more than 40 CPS (INVITE answered by 302 Moved
Temporary).
When
i increase the rate, FS starts delaying 302 response. Right at 50 CPS
i
see
"calls" being build up in FS and the delay begining to grow.

When i observe the machine, load average is almost nothing (load
average:
1.41, 0.61, 0.60) CPU never goes to 100%, and i see only one thread
taking
most load... all others are just sitting there with 1-5 % CPU time.
This looks to me as FS handles 302 messages in a single thread?!?!


tculjaga@FS:/usr/local/freeswitch/conf/dialplan$ top -H

top - 10:41:37 up 167 days, 20:42,  3 users,  load average: 1.41,
0.61,
0.60
Tasks:  83 total,   2 running,  81 sleeping,   0 stopped,   0 zombie
Cpu(s): 25.3%us,  1.5%sy,  0.0%ni, 30.3%id, 42.7%wa,  0.0%hi,
0.2%si,
0.0%st
Mem:   2074520k total,   571244k used,  1503276k free,   259604k
buffers
Swap:  2650684k total,     3020k used,  2647664k free,   153868k
cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
COMMAND
 4814 root      20   0 34188  20m 3780 S   38  1.0   3:10.29
freeswitch
 4800 root      20   0 34188  20m 3780 S    6  1.0   0:08.26
freeswitch
 4798 root      20   0 34188  20m 3780 R    5  1.0   0:24.46
freeswitch
 4787 root      20   0 34188  20m 3780 S    2  1.0   0:11.24
freeswitch
 4794 root      20   0 34188  20m 3780 S    1  1.0   0:11.42
freeswitch
 4803 root      20   0 34188  20m 3780 S    1  1.0   0:11.74
freeswitch
 4788 root      20   0 34188  20m 3780 S    1  1.0   0:02.96
freeswitch
 4804 root      20   0 34188  20m 3780 S    1  1.0   0:01.64
freeswitch
 4807 root      20   0 34188  20m 3780 S    1  1.0   0:01.68
freeswitch
 4811 root      20   0 34188  20m 3780 S    1  1.0   0:02.50
freeswitch



cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
apicid          : 0
initial apicid  : 0
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4670.78
clflush size    : 64
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4666.82
clflush size    : 64
power management:



uname -a
Linux l01sipindir1 2.6.26-1-686 #1 SMP Sat Jan 10 18:29:31 UTC 2009
i686
GNU/Linux



Of course, i've tuned the machine up

ulimit -c unlimited
ulimit -d unlimited
ulimit -f unlimited
ulimit -i unlimited
ulimit -n 999999
ulimit -q unlimited
ulimit -u unlimited
ulimit -v unlimited
ulimit -x unlimited
ulimit -s 240
ulimit -l unlimited
ulimit -a


Started FS with minimum modules but still 40 CPS seems to be the
limit.


So, is there any way to improve performance?


Tihomir.







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org

Back to top
tculjaga at gmail.com
Guest





PostPosted: Wed Aug 26, 2009 12:51 pm    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

Guys you made a monster!!


so, i moved the machine to 64bit CentOS 5.3... recompiled the latest trunk and did my tests again.

The old tests on 32bit debian 5 on the same hardware shown a CPS rate of 120 as 75 - 80% CPU.... and after some time on that 120 CPS rate the CPU goes to 100% without any chance FS recovers at all.
New tests on 64bit CentOS shown a monster.... 400 CPS rate at 75% CPU.... during the tests FS was really stable and responsive... i placed few calls that went through as a charm Smile.


Also, i didn't optimize the machine at all ... as it is after CentOS install!.... not even db files are on ramdisk.

What did it really happen? .. did you guys change something in the trunk overnight or it is just moving to CentOS 64bit that boosted drastically?




Here are some details:

ÚnmonÄ12aÄÄÄÄÄÄ[H for help]ÄÄÄHostname=l01sipindir2ÄRefresh= 2secs ÄÄÄ19:17.48ÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄ¿ ³ CPU +-------------------------------------------------------------------------+                                                  ³ ³100%-|  |                                                                                                                         ³ ³ 95%-|  |                                                                                                                         ³ ³ 90%-|  |                                                                                                                         ³ ³ 85%-|  |                                                                                                                         ³ ³ 80%-|  | w              s  w      www  w        s   sw    s    s           s                                                     ³ ³ 75%-|  |ssssssssssssssssssssswssssssssssssssssssssssssssssssssssssssssssssss                                                     ³ ³ 70%-|  +sssssssssssssssssssssssssssssssUssssssssUsssUssssssssssUssssssssssss                                                     ³ ³ 65%-|  |UUUUUsUsUUUUUUUUUUUUUsUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUsUUU                                                     ³ ³ 60%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 55%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 50%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 45%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 40%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUw                                                    ³ ³ 35%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUs                                                    ³ ³ 30%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 25%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 20%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 15%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 10%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³  5%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³     +-------------------------------------------------------------------------+                                                  ³ ³ CPU Utilisation ÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄij ³                           +-------------------------------------------------+                                                    ³ ³CPU  User%  Sys% Wait% Idle|0          |25         |50          |75       100|                                                    ³ ³ 1   1.0   0.5   0.0   98.5|                                      >          |                                                    ³ ³ 2   1.5   1.0   0.0   97.5|                                              >  |                                                    ³ ³                           +-------------------------------------------------+                                                    ³ ³Avg  1.2   0.5   0.0   98.3|                                       >         |                                                    ³ ³                           +-------------------------------------------------+                                                    ³ ³ Disk I/O ÄÄÄÄÄ(/proc/diskstats)ÄÄÄÄÄÄÄÄall data is Kbytes per secondÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄij ³DiskName Busy  Read WriteKB|0          |25         |50          |75       100|                                                    ³ ³iss/c0d0   0%    0.0    0.0|                                             >   |                                                    ³ ³s/c0d0p1   0%    0.0    0.0|>                                                |                                                    ³ ³s/c0d0p2   0%    0.0    0.0|                                              >  |                                                    ³ ³dm-0       0%    0.0    0.0|                                              >  |                                                    ³ ³dm-1       0%    0.0    0.0|>                                                |                                                    ³ ³ÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄij






------------------------------ Scenario Screen -------- [1-9]: Change Screen --   Call-rate(length)   Port   Total-time  Total-calls  Remote-host  40.0(0 ms)/0.100s   5060     488.20 s       193555  10.4.4.252:5060(UDP)   402 new calls during 1.002 s period    0 ms scheduler resolution  3 calls (limit 4000)                   Peak was 53 calls, after 351 s   0 Running, 13216 Paused, 670 Woken up  0 dead call msg (discarded)            0 out-of-call msg (discarded)          3 open sockets                                                         Messages  Retrans   Timeout   Unexpected-Msg       INVITE ---------->  B-RTD1 193553    0         0                           100 <----------  E-RTD1 193553    0         0         0                 302 <----------  E-RTD2 193552    0         0         0                 ACK ---------->         193552    0                            ------ [+|-|*|/]: Adjust rate ---- [q]: Soft exit ---- [p]: Pause traffic ----- ------------------------------ Scenario Screen -------- [1-9]: Change Screen --  Call-rate(length)   Port   Total-time  Total-calls  Remote-host   40.0(0 ms)/0.100s   5060     489.10 s       193917  10.4.4.252:5060(UDP)   362 new calls during 0.906 s period    1 ms scheduler resolution  2 calls (limit 4000)                   Peak was 53 calls, after 351 s   0 Running, 13215 Paused, 623 Woken up  0 dead call msg (discarded)            0 out-of-call msg (discarded)          3 open sockets                                                         Messages  Retrans   Timeout   Unexpected-Msg       INVITE ---------->  B-RTD1 193917    0         0                           100 <----------  E-RTD1 193917    0         0         0                 302 <----------  E-RTD2 193915    0         0         0                 ACK ---------->         193915    0                            ------------------------------ Test Terminated -------------------------------- ----------------------------- Statistics Screen ------- [1-9]: Change Screen --   Start Time             | 2009-08-26   19:09:34:575    1251306574.575684              Last Reset Time        | 2009-08-26   19:17:42:779    1251307062.779468              Current Time           | 2009-08-26   19:17:43:685    1251307063.685281            -------------------------+---------------------------+--------------------------   Counter Name           | Periodic value            | Cumulative value-------------------------+---------------------------+--------------------------   Elapsed Time           | 00:00:00:905              | 00:08:09:109               Call Rate              |  400.000 cps              |  396.470 cps             -------------------------+---------------------------+--------------------------  Incoming call created  |        0                  |        0                   OutGoing call created  |      362                  |   193917                   Total Call created     |                           |   193917                   Current Call           |        2                  |                          -------------------------+---------------------------+--------------------------   Successful call        |      363                  |   193915                   Failed call            |        0                  |        0                 -------------------------+---------------------------+--------------------------  Response Time 1        | 00:00:00:001              | 00:00:00:000               Response Time 2        | 00:00:00:010              | 00:00:00:008               Call Length            | 00:00:00:010              | 00:00:00:008             ------------------------------ Test Terminated --------------------------------



...i didn't beleive to SIPp and i went to FS console issuing status command to conferm the results.


freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 13 seconds, 703 milliseconds, 971 microseconds
183382 session(s) since startup
1 session(s) 410/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 15 seconds, 109 milliseconds, 891 microseconds
183944 session(s) since startup
1 session(s) 401/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 16 seconds, 139 milliseconds, 412 microseconds
184356 session(s) since startup
2 session(s) 389/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 17 seconds, 62 milliseconds, 16 microseconds
184717 session(s) since startup
6 session(s) 410/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 35 seconds, 150 milliseconds, 253 microseconds
191959 session(s) since startup
1 session(s) 400/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 36 seconds, 892 milliseconds, 672 microseconds
192657 session(s) since startup
1 session(s) 393/800
8000 session(s) max



On Wed, Aug 26, 2009 at 1:53 PM, Dmitry Kadantsev <kadantsev.d@gmail.com (kadantsev.d@gmail.com)> wrote:
Quote:
Hi all,

is there same situation with FS for Windows? I mean 64bit is more preferable than 32bit, isn't it?

Any performance test on Win 32/64 were done?
--
Best regards,
Dmitry Kadantsev



On Wed, Aug 26, 2009 at 10:29 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
intanto e il centos che si sta installando Smile

grazie.

T.


On Wed, Aug 26, 2009 at 10:25 AM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)> wrote:
Quote:
netbook remix


joking! Server 64bit Smile

-gm




On Wed, Aug 26, 2009 at 10:08 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Hi Giovanny,

regarding ubuntu, did you mean 8.04 server or desktop ?


On Tue, Aug 25, 2009 at 3:41 PM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Definitely go for 64 bit OS.

If you want to be safe and sure,  go for CentOS 5.2 64bit. Is the one
used both for development and for heavy duty production.

Also Ubuntu 8.04 is good.

Other versions/distros are less used by the community.

Adding RAM and CPUs helps to scale up.

-gm



Sincerely,

Giovanni Maruzzelli
Cell : +39-347-2665618




On Tue, Aug 25, 2009 at 3:19 PM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hey Giovanni,

thanks for the tip... indeed the db files were heavily used regardless
if i
started freeswitch with nosql option (freeswitch -nosql)... FS was not
writing anything into that files ... instead it was just accessing
it....
This behaviour leads to a waste of 40% CPU time... waiting for other
processes (mainly disk access) to finish!!!

I moved freeswitch/db/ to a ramdisk and the performance got a boost to
140
CPS with a CPU load of 80%. I was keeping the machine for a while (20 -
30
minutes) on that rate when i sow CPU suddenly went to 100% and FS
becoming
irresponsive Smile.


What can be wrong?
What are the limits in CPU usage (50%, 60%, 70%, 80%...) we should not
cross?
What fine tuning do we need in order to asure a long high load run?



Also, I'm running 32-bit OS (debian 5) on a 64 bit CPU... does it have
sense
to move my OS to 64 bit? ... will FS gain more preformance ?... I mean
will
FS perofomr drastically better 20%+ ?


Tihomir.


On Tue, Aug 25, 2009 at 11:00 AM, Giovanni Maruzzelli
<gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Maybe your load comes from disk access?

Try putting the sql and log directories on a ramdisk.

OTH,

-giovanni

On Tue, Aug 25, 2009 at 10:54 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hello,

i'm trying to use freeswitch as a redirecting server meaning FS has
to
receive an INVITE and according to some rules it will redirect calls
to
other destinations.


CALLING_USER                FREESWITCH
SOMEWHERE

INVITE ------------------------------->
           <------------------------------ 100 Trying
           <------------------------------ 302 Moved Temporary
ACK    ------------------------------->


INVITE--------------------------------------------------------------------------------->



Well, wverything works well except i have perfromance issues .... on
my
HW
FS cannot do more than 40 CPS (INVITE answered by 302 Moved
Temporary).
When
i increase the rate, FS starts delaying 302 response. Right at 50 CPS
i
see
"calls" being build up in FS and the delay begining to grow.

When i observe the machine, load average is almost nothing (load
average:
1.41, 0.61, 0.60) CPU never goes to 100%, and i see only one thread
taking
most load... all others are just sitting there with 1-5 % CPU time.
This looks to me as FS handles 302 messages in a single thread?!?!


tculjaga@FS:/usr/local/freeswitch/conf/dialplan$ top -H

top - 10:41:37 up 167 days, 20:42,  3 users,  load average: 1.41,
0.61,
0.60
Tasks:  83 total,   2 running,  81 sleeping,   0 stopped,   0 zombie
Cpu(s): 25.3%us,  1.5%sy,  0.0%ni, 30.3%id, 42.7%wa,  0.0%hi,
0.2%si,
0.0%st
Mem:   2074520k total,   571244k used,  1503276k free,   259604k
buffers
Swap:  2650684k total,     3020k used,  2647664k free,   153868k
cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
COMMAND
 4814 root      20   0 34188  20m 3780 S   38  1.0   3:10.29
freeswitch
 4800 root      20   0 34188  20m 3780 S    6  1.0   0:08.26
freeswitch
 4798 root      20   0 34188  20m 3780 R    5  1.0   0:24.46
freeswitch
 4787 root      20   0 34188  20m 3780 S    2  1.0   0:11.24
freeswitch
 4794 root      20   0 34188  20m 3780 S    1  1.0   0:11.42
freeswitch
 4803 root      20   0 34188  20m 3780 S    1  1.0   0:11.74
freeswitch
 4788 root      20   0 34188  20m 3780 S    1  1.0   0:02.96
freeswitch
 4804 root      20   0 34188  20m 3780 S    1  1.0   0:01.64
freeswitch
 4807 root      20   0 34188  20m 3780 S    1  1.0   0:01.68
freeswitch
 4811 root      20   0 34188  20m 3780 S    1  1.0   0:02.50
freeswitch



cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
apicid          : 0
initial apicid  : 0
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4670.78
clflush size    : 64
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4666.82
clflush size    : 64
power management:



uname -a
Linux l01sipindir1 2.6.26-1-686 #1 SMP Sat Jan 10 18:29:31 UTC 2009
i686
GNU/Linux



Of course, i've tuned the machine up

ulimit -c unlimited
ulimit -d unlimited
ulimit -f unlimited
ulimit -i unlimited
ulimit -n 999999
ulimit -q unlimited
ulimit -u unlimited
ulimit -v unlimited
ulimit -x unlimited
ulimit -s 240
ulimit -l unlimited
ulimit -a


Started FS with minimum modules but still 40 CPS seems to be the
limit.


So, is there any way to improve performance?


Tihomir.







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org






_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org

Back to top
jaybinks at gmail.com
Guest





PostPosted: Wed Aug 26, 2009 5:56 pm    Post subject: [Freeswitch-users] Freeswitch performance as a redirecting s Reply with quote

Just for fun...
Im personally interested how this holds up on Debian 5 - 64 bit..

Im more of a debian person... not a huge centos fan and it seems you had a pref for debian at first also
so if you have the time to play, let us know how that goes Smile
surly its just the change to a 64 bit OS....

Jay



On Thu, Aug 27, 2009 at 3:42 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Guys you made a monster!!


so, i moved the machine to 64bit CentOS 5.3... recompiled the latest trunk and did my tests again.

The old tests on 32bit debian 5 on the same hardware shown a CPS rate of 120 as 75 - 80% CPU.... and after some time on that 120 CPS rate the CPU goes to 100% without any chance FS recovers at all.
New tests on 64bit CentOS shown a monster.... 400 CPS rate at 75% CPU.... during the tests FS was really stable and responsive... i placed few calls that went through as a charm Smile.


Also, i didn't optimize the machine at all ... as it is after CentOS install!.... not even db files are on ramdisk.

What did it really happen? .. did you guys change something in the trunk overnight or it is just moving to CentOS 64bit that boosted drastically?




Here are some details:

ÚnmonÄ12aÄÄÄÄÄÄ[H for help]ÄÄÄHostname=l01sipindir2ÄRefresh= 2secs ÄÄÄ19:17.48ÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄ¿ ³ CPU +-------------------------------------------------------------------------+                                                  ³ ³100%-|  |                                                                                                                         ³ ³ 95%-|  |                                                                                                                         ³ ³ 90%-|  |                                                                                                                         ³ ³ 85%-|  |                                                                                                                         ³ ³ 80%-|  | w              s  w      www  w        s   sw    s    s           s                                                     ³ ³ 75%-|  |ssssssssssssssssssssswssssssssssssssssssssssssssssssssssssssssssssss                                                     ³ ³ 70%-|  +sssssssssssssssssssssssssssssssUssssssssUsssUssssssssssUssssssssssss                                                     ³ ³ 65%-|  |UUUUUsUsUUUUUUUUUUUUUsUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUsUUU                                                     ³ ³ 60%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 55%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 50%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 45%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                     ³ ³ 40%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUw                                                    ³ ³ 35%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUs                                                    ³ ³ 30%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 25%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 20%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 15%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³ 10%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³  5%-|  |UUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUUU                                                    ³ ³     +-------------------------------------------------------------------------+                                                  ³ ³ CPU Utilisation ÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄij ³                           +-------------------------------------------------+                                                    ³ ³CPU  User%  Sys% Wait% Idle|0          |25         |50          |75       100|                                                    ³ ³ 1   1.0   0.5   0.0   98.5|                                      >          |                                                    ³ ³ 2   1.5   1.0   0.0   97.5|                                              >  |                                                    ³ ³                           +-------------------------------------------------+                                                    ³ ³Avg  1.2   0.5   0.0   98.3|                                       >         |                                                    ³ ³                           +-------------------------------------------------+                                                    ³ ³ Disk I/O ÄÄÄÄÄ(/proc/diskstats)ÄÄÄÄÄÄÄÄall data is Kbytes per secondÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄij ³DiskName Busy  Read WriteKB|0          |25         |50          |75       100|                                                    ³ ³iss/c0d0   0%    0.0    0.0|                                             >   |                                                    ³ ³s/c0d0p1   0%    0.0    0.0|>                                                |                                                    ³ ³s/c0d0p2   0%    0.0    0.0|                                              >  |                                                    ³ ³dm-0       0%    0.0    0.0|                                              >  |                                                    ³ ³dm-1       0%    0.0    0.0|>                                                |                                                    ³ ³ÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄÄij






------------------------------ Scenario Screen -------- [1-9]: Change Screen --   Call-rate(length)   Port   Total-time  Total-calls  Remote-host  40.0(0 ms)/0.100s   5060     488.20 s       193555  10.4.4.252:5060(UDP)   402 new calls during 1.002 s period    0 ms scheduler resolution  3 calls (limit 4000)                   Peak was 53 calls, after 351 s   0 Running, 13216 Paused, 670 Woken up  0 dead call msg (discarded)            0 out-of-call msg (discarded)          3 open sockets                                                         Messages  Retrans   Timeout   Unexpected-Msg       INVITE ---------->  B-RTD1 193553    0         0                           100 <----------  E-RTD1 193553    0         0         0                 302 <----------  E-RTD2 193552    0         0         0                 ACK ---------->         193552    0                            ------ [+|-|*|/]: Adjust rate ---- [q]: Soft exit ---- [p]: Pause traffic ----- ------------------------------ Scenario Screen -------- [1-9]: Change Screen --  Call-rate(length)   Port   Total-time  Total-calls  Remote-host   40.0(0 ms)/0.100s   5060     489.10 s       193917  10.4.4.252:5060(UDP)   362 new calls during 0.906 s period    1 ms scheduler resolution  2 calls (limit 4000)                   Peak was 53 calls, after 351 s   0 Running, 13215 Paused, 623 Woken up  0 dead call msg (discarded)            0 out-of-call msg (discarded)          3 open sockets                                                         Messages  Retrans   Timeout   Unexpected-Msg       INVITE ---------->  B-RTD1 193917    0         0                           100 <----------  E-RTD1 193917    0         0         0                 302 <----------  E-RTD2 193915    0         0         0                 ACK ---------->         193915    0                            ------------------------------ Test Terminated -------------------------------- ----------------------------- Statistics Screen ------- [1-9]: Change Screen --   Start Time             | 2009-08-26   19:09:34:575    1251306574.575684              Last Reset Time        | 2009-08-26   19:17:42:779    1251307062.779468              Current Time           | 2009-08-26   19:17:43:685    1251307063.685281            -------------------------+---------------------------+--------------------------   Counter Name           | Periodic value            | Cumulative value-------------------------+---------------------------+--------------------------   Elapsed Time           | 00:00:00:905              | 00:08:09:109               Call Rate              |  400.000 cps              |  396.470 cps             -------------------------+---------------------------+--------------------------  Incoming call created  |        0                  |        0                   OutGoing call created  |      362                  |   193917                   Total Call created     |                           |   193917                   Current Call           |        2                  |                          -------------------------+---------------------------+--------------------------   Successful call        |      363                  |   193915                   Failed call            |        0                  |        0                 -------------------------+---------------------------+--------------------------  Response Time 1        | 00:00:00:001              | 00:00:00:000               Response Time 2        | 00:00:00:010              | 00:00:00:008               Call Length            | 00:00:00:010              | 00:00:00:008             ------------------------------ Test Terminated --------------------------------



...i didn't beleive to SIPp and i went to FS console issuing status command to conferm the results.


freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 13 seconds, 703 milliseconds, 971 microseconds
183382 session(s) since startup
1 session(s) 410/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 15 seconds, 109 milliseconds, 891 microseconds
183944 session(s) since startup
1 session(s) 401/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 16 seconds, 139 milliseconds, 412 microseconds
184356 session(s) since startup
2 session(s) 389/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 17 seconds, 62 milliseconds, 16 microseconds
184717 session(s) since startup
6 session(s) 410/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 35 seconds, 150 milliseconds, 253 microseconds
191959 session(s) since startup
1 session(s) 400/800
8000 session(s) max

freeswitch@l01sipindir2.ot.hr (freeswitch@l01sipindir2.ot.hr)> status
API CALL [status()] output:
UP 0 years, 0 days, 0 hours, 8 minutes, 36 seconds, 892 milliseconds, 672 microseconds
192657 session(s) since startup
1 session(s) 393/800
8000 session(s) max




On Wed, Aug 26, 2009 at 1:53 PM, Dmitry Kadantsev <kadantsev.d@gmail.com (kadantsev.d@gmail.com)> wrote:
Quote:
Hi all,

is there same situation with FS for Windows? I mean 64bit is more preferable than 32bit, isn't it?

Any performance test on Win 32/64 were done?
--
Best regards,
Dmitry Kadantsev



On Wed, Aug 26, 2009 at 10:29 AM, Tihomir Culjaga <tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
intanto e il centos che si sta installando Smile

grazie.

T.


On Wed, Aug 26, 2009 at 10:25 AM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)> wrote:
Quote:
netbook remix


joking! Server 64bit Smile

-gm




On Wed, Aug 26, 2009 at 10:08 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)> wrote:
Quote:
Hi Giovanny,

regarding ubuntu, did you mean 8.04 server or desktop ?


On Tue, Aug 25, 2009 at 3:41 PM, Giovanni Maruzzelli <gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Definitely go for 64 bit OS.

If you want to be safe and sure,  go for CentOS 5.2 64bit. Is the one
used both for development and for heavy duty production.

Also Ubuntu 8.04 is good.

Other versions/distros are less used by the community.

Adding RAM and CPUs helps to scale up.

-gm



Sincerely,

Giovanni Maruzzelli
Cell : +39-347-2665618




On Tue, Aug 25, 2009 at 3:19 PM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hey Giovanni,

thanks for the tip... indeed the db files were heavily used regardless
if i
started freeswitch with nosql option (freeswitch -nosql)... FS was not
writing anything into that files ... instead it was just accessing
it....
This behaviour leads to a waste of 40% CPU time... waiting for other
processes (mainly disk access) to finish!!!

I moved freeswitch/db/ to a ramdisk and the performance got a boost to
140
CPS with a CPU load of 80%. I was keeping the machine for a while (20 -
30
minutes) on that rate when i sow CPU suddenly went to 100% and FS
becoming
irresponsive Smile.


What can be wrong?
What are the limits in CPU usage (50%, 60%, 70%, 80%...) we should not
cross?
What fine tuning do we need in order to asure a long high load run?



Also, I'm running 32-bit OS (debian 5) on a 64 bit CPU... does it have
sense
to move my OS to 64 bit? ... will FS gain more preformance ?... I mean
will
FS perofomr drastically better 20%+ ?


Tihomir.


On Tue, Aug 25, 2009 at 11:00 AM, Giovanni Maruzzelli
<gmaruzz@celliax.org (gmaruzz@celliax.org)>
wrote:
Quote:

Maybe your load comes from disk access?

Try putting the sql and log directories on a ramdisk.

OTH,

-giovanni

On Tue, Aug 25, 2009 at 10:54 AM, Tihomir Culjaga<tculjaga@gmail.com (tculjaga@gmail.com)>
wrote:
Quote:
Hello,

i'm trying to use freeswitch as a redirecting server meaning FS has
to
receive an INVITE and according to some rules it will redirect calls
to
other destinations.


CALLING_USER                FREESWITCH
SOMEWHERE

INVITE ------------------------------->
           <------------------------------ 100 Trying
           <------------------------------ 302 Moved Temporary
ACK    ------------------------------->


INVITE--------------------------------------------------------------------------------->



Well, wverything works well except i have perfromance issues .... on
my
HW
FS cannot do more than 40 CPS (INVITE answered by 302 Moved
Temporary).
When
i increase the rate, FS starts delaying 302 response. Right at 50 CPS
i
see
"calls" being build up in FS and the delay begining to grow.

When i observe the machine, load average is almost nothing (load
average:
1.41, 0.61, 0.60) CPU never goes to 100%, and i see only one thread
taking
most load... all others are just sitting there with 1-5 % CPU time.
This looks to me as FS handles 302 messages in a single thread?!?!


tculjaga@FS:/usr/local/freeswitch/conf/dialplan$ top -H

top - 10:41:37 up 167 days, 20:42,  3 users,  load average: 1.41,
0.61,
0.60
Tasks:  83 total,   2 running,  81 sleeping,   0 stopped,   0 zombie
Cpu(s): 25.3%us,  1.5%sy,  0.0%ni, 30.3%id, 42.7%wa,  0.0%hi,
0.2%si,
0.0%st
Mem:   2074520k total,   571244k used,  1503276k free,   259604k
buffers
Swap:  2650684k total,     3020k used,  2647664k free,   153868k
cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
COMMAND
 4814 root      20   0 34188  20m 3780 S   38  1.0   3:10.29
freeswitch
 4800 root      20   0 34188  20m 3780 S    6  1.0   0:08.26
freeswitch
 4798 root      20   0 34188  20m 3780 R    5  1.0   0:24.46
freeswitch
 4787 root      20   0 34188  20m 3780 S    2  1.0   0:11.24
freeswitch
 4794 root      20   0 34188  20m 3780 S    1  1.0   0:11.42
freeswitch
 4803 root      20   0 34188  20m 3780 S    1  1.0   0:11.74
freeswitch
 4788 root      20   0 34188  20m 3780 S    1  1.0   0:02.96
freeswitch
 4804 root      20   0 34188  20m 3780 S    1  1.0   0:01.64
freeswitch
 4807 root      20   0 34188  20m 3780 S    1  1.0   0:01.68
freeswitch
 4811 root      20   0 34188  20m 3780 S    1  1.0   0:02.50
freeswitch



cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
apicid          : 0
initial apicid  : 0
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4670.78
clflush size    : 64
power management:

processor       : 1
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Xeon(R) CPU            5140  @ 2.33GHz
stepping        : 6
cpu MHz         : 2333.560
cache size      : 4096 KB
physical id     : 0
siblings        : 2
core id         : 1
cpu cores       : 2
apicid          : 1
initial apicid  : 1
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge
mca
cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe lm
constant_tsc arch_perfmon pebs bts pni monitor ds_cpl vmx est tm2
ssse3
cx16
xtpr dca lahf_lm
bogomips        : 4666.82
clflush size    : 64
power management:



uname -a
Linux l01sipindir1 2.6.26-1-686 #1 SMP Sat Jan 10 18:29:31 UTC 2009
i686
GNU/Linux



Of course, i've tuned the machine up

ulimit -c unlimited
ulimit -d unlimited
ulimit -f unlimited
ulimit -i unlimited
ulimit -n 999999
ulimit -q unlimited
ulimit -u unlimited
ulimit -v unlimited
ulimit -x unlimited
ulimit -s 240
ulimit -l unlimited
ulimit -a


Started FS with minimum modules but still 40 CPS seems to be the
limit.


So, is there any way to improve performance?


Tihomir.







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users

UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org


_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org



_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org







_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org






_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org






_______________________________________________
FreeSWITCH-users mailing list
FreeSWITCH-users@lists.freeswitch.org (FreeSWITCH-users@lists.freeswitch.org)
http://lists.freeswitch.org/mailman/listinfo/freeswitch-users
UNSUBSCRIBE:http://lists.freeswitch.org/mailman/options/freeswitch-users
http://www.freeswitch.org




--
Sincerely

Jay
Back to top
Display posts from previous:   
Post new topic   Reply to topic    VoIP Mailing List Archives Forum Index -> freeSWITCH Users All times are GMT - 5 Hours
Goto page Previous  1, 2
Page 2 of 2

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by phpBB © 2001, 2005 phpBB Group

VoiceMeUp - Corporate & Wholesale VoIP Services