VoIP Mailing List Archives

[egghunt at gmail.com]

Jon, why don't you let the number of calls increase and see how
FreeSWITCH behave? If it starts dropping the calls, then you might
want to review the process or get some more help, otherwise you're
done.

On Mon, Sep 29, 2008 at 6:06 PM, Anthony Minessale
<anthony.minessale@gmail.com> wrote:

[jbr at consiglia.dk]

OK, you can access it directly now, and yes it would be fine if we can
find out what's wrong once for all. Phone is: +45 45 16 1001. I'm on
CET.
Regarding the calling application: It is Asterisk, setting up one leg to
MOH and the other to FS, so audio is certainly going through.
Regarding the responsiveness of FS when the load is high: it does
respond, but the is a delay of around 1 second.
The load measurement is done by "top". /Jon


_______________________________________________
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

[anthony.minessale at g...]

hopefully on 2 different servers?

please send a private email with the box login credentials to consulting@freeswitch.org (consulting@freeswitch.org)
and we will contact you.



On Tue, Sep 30, 2008 at 4:06 AM, Jon Bruel <jbr@consiglia.dk (jbr@consiglia.dk)> wrote:

[jbr at consiglia.dk]

I have made some further studies of the performance, and after I have
removed and old PC running 10 Mb/s on the Ethernet, the performance has
been drastically improved. So I tentatively think that there has been a
bottleneck somehow in the combination of Ethernet switch and slow
Ethernet cards.
I'll test further and report back. At this stage, Anthony, I need more
testing before you look at my system. If any others have had similar
experiences, please report back. /Jon


_______________________________________________
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

[mike at jerris.com]

On Oct 2, 2008, at 3:00 PM, Jon Bruel wrote:

[cstomi.levlist at gmai...]

Hello,

Could you please check this out:
http://jira.freeswitch.org/browse/FSCORE-197
and test the performance with the attached patch?
It would be nice to make sure that it doesn't change the performance
negatively.
Just if you have time and are you interested in

Thank you,
Tamas

Jon Bruel írta:

[jbr at consiglia.dk]

Hi all
An update on the performance measurements:
The measurements I have referred to earlier all involved an Asterisk as
the call generator. Somehow this setup leads to extensive rtp bandwidth
usage. Each channel used around 500 kbps. If a phone is entered into the
loop, this is reduced to the expected 64 kbps. I have not found any
reason for this, but it certainly fouls up the test, and I have changed
the test setup.
Further, and since the earlier tests, the network has been updated to a
Gbits network.
I have now made two new test:
1) Using WinSIP from Touchstone as a call generator.
2) Using the Asterisk as one component, and setting up a chain of calls
which goes forth and back from the Asterisk and the FS. All call are
started from a real phone, and after 100 loops, where the calls are
answered and sent on by the dial plan, the calls are terminated by an
tone (<action application="gentones" data="%(500000,0,400)"/>) in the
FS.
The two test show similar top-figures at similar loads.
The first test would be my preferable, but it is limited to 50 calls due
to the trial licence limitations. Using an external non-FS and
non-Asterisk device will eliminate some uncertainties, that's why it
would be preferred.
The other test has been done with 600, 400 and 200 channels (300, 200
and 100 calls), and the results of the top command are:
cpu sy ni id wa hi si total
* 600 10 30 0 33 0 2 25 100
FS600 22 33 0 30 0 0 15 100
0
* 400 7 18 0 67 0 1 7 100
FS400 14 17 0 62 0 0 7 100
0
* 200 3 10 0 84 1 0 2 100
FS200 7 8 0 82 1 0 2 100
The results do not show significant differences between the capacity
behaviour of the Asterisk (*) and the FS. The also show an expected
interrupt load (si) proportional to the square of the call load.
Still the FS does not really outperform the Asterisk - which I find
disappointing. Any comments are welcome.


_______________________________________________
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

[krice at suspicious.org]

Try using something like SIPP for load testing you can load test to much
higher numbers
http://www.freeswitch.org/eg/load_test.tgz is what we use for testing so
you can duplicate the results...

Also, look at the configuration you are doing and determine if you really
need all the features that are there... Things like presence tracking,
certain CDR loggers, and a few other things under high CPS loads can cause
more problems then you think...

Hint... Mount freeswitch/db as a ram drive in linux this is a big
performance booster (since it takes the load of sqlite of the hdd), also
turn off presence tracking on all sip profiles that don't need it...

Something doesn't sound right on the 500k of rtp... Also remember that
asterisk RTP stack doesn't handle async rtp.. It depends on receiving a
packet to transmit a packet

[anthony.minessale at g...]

Like I told the other guy we are pretty much done supporting people doing load testing.
I know for a fact that on my dual core wood crest that is now 4 years old that I can bring up 3000 channels
playing a file out RTP at 20ms ptime, 5000 if i switch to 60 and 10000 if i use 120ms ptime.

Ken can also attest to these numbers as well as provide you with his numbers from his own testing I'm sure.


This is a fact. If you cannot reproduce it then it's not my problem. I know for a fact that you are clearly
trying to develop a commercial application and I have subtly pointed out that you need to seek commercial support.
Now I am making it crystal clear, Stop asking for help about load testing unless you are going to pay for our
time to teach you how to set it up properly.


On Sat, Oct 4, 2008 at 4:11 AM, Ken Rice <krice@suspicious.org (krice@suspicious.org)> wrote:

[jbr at consiglia.dk]

Anthony, your last response is surprising me. I appreciate the work you
have done in supporting people doing load testing. But the information
about this is rather unorganized and difficult to access for newbies.
Further, many threads on this and other topics are written in telegram
style language, which increases the learning time. As an example, the
first time I heard about the testing tool sipp was yesterday - through
the users list - thanks. What a great tool! The documentation though, is
not aimed at making the learning curve easy. A "these are the 20 steps
to do test" manual does not exist to my knowledge. Bear in mind that I'm
not a programmer but a generalist with all-round knowledge about
telecoms and virtual PBXs.
I hope you can use this feedback in a productive way in order to improve
the overall level of documentation. And it also pinpoints the need for
the userlist and repetitive questions.
Setting up commercial relations also makes sense when we have reached
the proof of concept and a business plan can be made. The proof of
concept includes a decision about which switch to use, Asterisk is still
an alternative to FS. Asterisk may have some architectural drawbacks,
but it has been tested for a longer time and in more setups than FS.
Further, Asterisk has a bad reputation.
As you have mentioned before, it may be worth while visiting your team
soon, and I'm preparing for that. /Jon


_______________________________________________
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

[anthony.minessale at g...]

Sorry,

We are all very busy. We take time out of our day to answer as many
questions as we can in the little spare time we have.
I personally do not have the time to educate everyone on sipp. There
is a community here working together on all the docs and I am afraid
you may have just insulted them with your comments.
My point is I do not have time to stop what I am doing and support
people trying to do load testing when they clearly have a lot to learn
about the whole concept.
I have already added 2 features for you for free and answered all of
your questions. What elese do you want from us?

sent from my phone -stop-

On 10/4/08, Jon Bruel <jbr@consiglia.dk> wrote:

[mctch at yahoo.com]

"your last response is surprising me. I appreciate the work you have done in supporting people doing load testing. "

Countless hours at no cost to you or me have been put in by Anthony, Brian, Mike and many others in building documenting and supporting FreeSWITCH. If you truly do appreciate the work then join the community and do things that help make it better. These include helping with documentation as you learn it, helping to support it or contributing to it with money.

Load testing has not been done by many in the community. So it is logical that the road less used will have less documentation. As you learn the load testing you should document it on the wiki.

There has been enormous man hours put into this documentation already. Hundreds of pages worth of documentation and examples are already available to anyone.

A suggestion if you choose to be a part of the FreeSWITCH community. Recognize that some things should help Keep out comments that portray a feeling of entitlement and word your questions and comments with a little gratitude. Then as people voluntarily answer your questions give back to the community in some way.


Mark


--- On Sat, 10/4/08, Jon Bruel <jbr@consiglia.dk> wrote:

[jbr at consiglia.dk]

Resolved: I have made further tests, and my final conclusion is that the
previous stated test results were screwed by the application 'gentones'.
This application does in some cases send more rtp than expected. If I
used:
<action application="gentones" data="%(5,0,300)"/>
<action application="gentones" data="%(5,0,300)"/>
<action application="gentones" data="%(60000,0,300)"/>
the expected rtp of 8600 kB/s was transmitted. If I used
<action application="gentones" data="%(60000,0,300)"/>
<action application="gentones" data="%(5,0,300)"/>
<action application="gentones" data="%(5,0,300)"/>.
the rtp was 34600 kB/s, and the memory is heavily consumed. The only
difference being the sequence of the gentones commands. I don't know if
this is the expected behaviour of 'gentones' or not, but it certainly
screwed up the results previously posted. /Jon


_______________________________________________
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

[anthony.minessale at g...]

%(60000,0,300) means to generate a 60 second long 300hz tone
%(5,0,300) means a 5 ms long 300hz tone

if you are just trying to send a tone you are better off with
<action application="gentones" data="%(1000,0,300)|60"/>

which only generates 1 second of audio then buffers and loops it via the application
rather than allocating enough room for 60 seconds of signed linear audio and generating
the whole 60 seconds into memory for no reason vs 1 second sample looped 60 times.

No matter what you do it will not effect the bandwidth used, it's a factor of what codec you are using.


On Mon, Oct 6, 2008 at 4:15 AM, Jon Bruel <jbr@consiglia.dk (jbr@consiglia.dk)> wrote:

[kjoseph.us at gmail.com]

Jon,

We would appreciate it if you post all your testing scripts ,with results. And maybe you can even give us 5 minutes of your time and create a wiki page: "Load testing"


This way the next person who's trying to reproduce the results and for all the unbelievers, will have an easy answer.


Best Regards,
Joseph