<p dir="ltr">You should compare that to bare metal on the same box. And look at the stats of the host during the test to make sure its not maxed out.</p>
<div class="gmail_quote">On Sep 4, 2013 4:52 AM, &quot;Grant Bagdasarian&quot; &lt;<a href="mailto:GB@cm.nl">GB@cm.nl</a>&gt; wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div lang="EN-US" link="blue" vlink="purple"><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I’ll look for those options, thanks.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I did some random tests with Sipp 3.2. (more detailed results will follow a future post)<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">The flow is as following:<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">Sipp ----&gt; FreeSWITCH SBC 1 ----&gt; FreeSWITCH SBC 2 ----&gt; FreeSWITCH App Server<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">The SBC’s just bridge the incoming call with an outgoing one.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">The App Server plays a file which is about 2 minutes in length. G711 Alaw codec.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">The host has a 6 Core Intel Xeon(12 Threads) CPU and 8 GB of RAM. Running ESXi 5.1<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">Each virtual has 4 Virtual cores and 2 GB of memory.<u></u><u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I tweaked the ulimit settings on all machines according to the information in :</span> <a href="http://wiki.freeswitch.org/wiki/Performance_testing_and_configurations" target="_blank">http://wiki.freeswitch.org/wiki/Performance_testing_and_configurations</a><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I generated about 2000 calls using Sipp. <u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">The audio quality was good until it hit 800+ concurrent calls.<u></u><u></u></span></p><p class="MsoNormal">
<span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I let the test run and called in myself using X-Lite. <u></u><u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">SBC 1 and SBC 2 had each about ~1600 channels active (incoming and outgoing leg) and the App Server had 800.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">At 1000 concurrent calls the audio was still fair, but did have some audio drops. At around 1400 the audio was completely dropped, no sound from that point on.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">SBC 1 and SBC 2 were at 100% CPU usage, on all 4 cores. The App Server was at a constant 50% on all 4 cores.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I’m still wondering the following, the audio file which was played is stored on the App Server in /freeswitch/sounds/. Does FreeSWITCH read the file for every new call? Or is the file cached in memory and accessed from there? <u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">If it does read it for every new call, maybe I can get even more performance out of this if we can cache it somehow.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"><u></u> <u></u></span></p><p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:&quot;Tahoma&quot;,&quot;sans-serif&quot;">From:</span></b><span style="font-size:10.0pt;font-family:&quot;Tahoma&quot;,&quot;sans-serif&quot;"> <a href="mailto:freeswitch-users-bounces@lists.freeswitch.org" target="_blank">freeswitch-users-bounces@lists.freeswitch.org</a> [mailto:<a href="mailto:freeswitch-users-bounces@lists.freeswitch.org" target="_blank">freeswitch-users-bounces@lists.freeswitch.org</a>] <b>On Behalf Of </b>Anthony Minessale<br>
<b>Sent:</b> Tuesday, September 3, 2013 10:13 PM<br><b>To:</b> FreeSWITCH Users Help<br><b>Subject:</b> Re: [Freeswitch-users] Running FS on a heavy loaded VMWare host<u></u><u></u></span></p><p class="MsoNormal"><u></u> <u></u></p>
<div><p class="MsoNormal">The key setting in vmware is one regarding passing the timer reqs down to the real hardware.<u></u><u></u></p><div><p class="MsoNormal">I don&#39;t remember the name but if its set to emulate the timer source rather than share the real one, it will break for sure.<u></u><u></u></p>
</div><div><p class="MsoNormal">The other thing was the mode the network is in, there is on that is like a hub with the host box and that one duplicates the RTP traffic over a bridge vs the virtual interface mode that is more performant.<u></u><u></u></p>
</div><div><p class="MsoNormal"><u></u> <u></u></p></div><div><p class="MsoNormal">That said we don&#39;t officially guarantee any results with virtual hosts but the community is encouraged to document their experiences here and on the wiki.<u></u><u></u></p>
</div><div><p class="MsoNormal"><u></u> <u></u></p></div><div><p class="MsoNormal"><u></u> <u></u></p></div></div><div><p class="MsoNormal" style="margin-bottom:12.0pt"><u></u> <u></u></p><div><p class="MsoNormal">On Tue, Sep 3, 2013 at 7:40 AM, Grant Bagdasarian &lt;<a href="mailto:GB@cm.nl" target="_blank">GB@cm.nl</a>&gt; wrote:<u></u><u></u></p>
<div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">Hello,</span><u></u><u></u></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">Thank you all for your comments.</span><u></u><u></u></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I’ve decided to use a separate VM host dedicated to Voice services. Our current physical box running FreeSWITCH will be re-installed with ESXi and will host 3 virtuals where FreeSWITCH will be installed on. Each having dedicated cores.</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I’m planning to do exactly what Michael Jerris suggested, but with SIPp generating load on the virtuals and calling in using X-Lite to measure the audio quality.</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">This way I can simulate a (heavy) loaded host.</span><u></u><u></u></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">I’ll post the results once I have completed the tests.</span><u></u><u></u></p><p class="MsoNormal">
<span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"> </span><u></u><u></u></p><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d">Grant</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;;color:#1f497d"> </span><u></u><u></u></p><div><div style="border:none;border-top:solid #b5c4df 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:&quot;Tahoma&quot;,&quot;sans-serif&quot;">From:</span></b><span style="font-size:10.0pt;font-family:&quot;Tahoma&quot;,&quot;sans-serif&quot;"> <a href="mailto:freeswitch-users-bounces@lists.freeswitch.org" target="_blank">freeswitch-users-bounces@lists.freeswitch.org</a> [mailto:<a href="mailto:freeswitch-users-bounces@lists.freeswitch.org" target="_blank">freeswitch-users-bounces@lists.freeswitch.org</a>] <b>On Behalf Of </b>Michael Jerris<br>
<b>Sent:</b> Tuesday, September 3, 2013 2:15 PM<br><b>To:</b> FreeSWITCH Users Help<br><b>Subject:</b> Re: [Freeswitch-users] Running FS on a heavy loaded VMWare host</span><u></u><u></u></p></div></div><div><div><p class="MsoNormal">
 <u></u><u></u></p><p class="MsoNormal">Any voip running on a very heavily loaded VM host runs the risk of having audio issues.  The question is, is it so heavily loaded that freeswitch will be starved of clock cycles or not.  Testing it is the only way to see.  Even if it is to some extent, things that don&#39;t need timing like regular bridged calls will be much more tolerant of some load than things that require more timing like playing sound files or conferences.  I would test spinning up a bunch of channels and calling in and listening to a milliwatt tone to see if its clean or not.<u></u><u></u></p>
<div><p class="MsoNormal"> <u></u><u></u></p></div><div><p class="MsoNormal">Mike<u></u><u></u></p></div><div><p class="MsoNormal"> <u></u><u></u></p><div><div><p class="MsoNormal">On Sep 2, 2013, at 2:34 AM, Grant Bagdasarian &lt;<a href="mailto:GB@cm.nl" target="_blank">GB@cm.nl</a>&gt; wrote:<u></u><u></u></p>
</div><p class="MsoNormal" style="margin-bottom:12.0pt"><u></u> <u></u></p><div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;">Hello,</span><u></u><u></u></p>
</div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;"> </span><u></u><u></u></p></div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;">I’ve been going through some threads about virtualization, some say it works for them, others say it doesn’t. Multiple platforms are used like MS Hyper-V, VM Ware, etc.</span><u></u><u></u></p>
</div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;">We currently run FS on a physical box, which works great.</span><u></u><u></u></p></div><div><p class="MsoNormal">
<span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;"> </span><u></u><u></u></p></div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;">We have our own virtual environment, VMWare vSphere 5.0. Our 5.0 environment is running under heavy load and I was wondering would FS (configured properly for correct timing) still function properly and able to handle hundreds of concurrent calls on a heavy loaded VMWare host? The FS virtual will also process RTP in default mode. I was hoping if someone had any experience using this setup and could give me some insights on this matter. The FS virtuals will function only as SBC’s, so no complex dial plans, no call recording, no conferencing. Just bridging the incoming call leg with an outgoing one.</span><u></u><u></u></p>
</div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;"> </span><u></u><u></u></p></div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;">VMWare has a tech paper about running VoIP on their virtual machine, and they claim it works. (<a href="http://www.vmware.com/files/pdf/techpaper/voip-perf-vsphere5.pdf" target="_blank"><span style="color:purple">http://www.vmware.com/files/pdf/techpaper/voip-perf-vsphere5.pdf</span></a>). In the paper they used Mitel vMCD, but I’m not sure if the software has been optimized to run on VMWare so the tests would come out better than running any other telephony software like FreeSwitch or Asterisk.</span><u></u><u></u></p>
</div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;"> </span><u></u><u></u></p></div><div><p class="MsoNormal"><span style="font-size:11.0pt;font-family:&quot;Calibri&quot;,&quot;sans-serif&quot;">Grant</span><u></u><u></u></p>
</div><p class="MsoNormal"><span style="font-size:13.5pt;font-family:&quot;Helvetica&quot;,&quot;sans-serif&quot;">_________________________________________________________________________<br>Professional FreeSWITCH Consulting Services:<br>
<a href="mailto:consulting@freeswitch.org" target="_blank"><span style="color:purple">consulting@freeswitch.org</span></a><br><a href="http://www.freeswitchsolutions.com" target="_blank"><span style="color:purple">http://www.freeswitchsolutions.com</span></a><br>
<br>FreeSWITCH-powered IP PBX: The CudaTel Communication Server<br><a href="http://www.cudatel.com" target="_blank"><span style="color:purple">http://www.cudatel.com</span></a><br><br>Official FreeSWITCH Sites<br><a href="http://www.freeswitch.org" target="_blank"><span style="color:purple">http://www.freeswitch.org</span></a><br>
<a href="http://wiki.freeswitch.org" target="_blank"><span style="color:purple">http://wiki.freeswitch.org</span></a><br><a href="http://www.cluecon.com" target="_blank"><span style="color:purple">http://www.cluecon.com</span></a><br>
<br>FreeSWITCH-users mailing list<br><a href="mailto:FreeSWITCH-users@lists.freeswitch.org" target="_blank"><span style="color:purple">FreeSWITCH-users@lists.freeswitch.org</span></a><br><a href="http://lists.freeswitch.org/mailman/listinfo/freeswitch-users" target="_blank"><span style="color:purple">http://lists.freeswitch.org/mailman/listinfo/freeswitch-users</span></a><br>
UNSUBSCRIBE:http://<a href="http://lists.freeswitch.org/mailman/options/freeswitch-users" target="_blank"><span style="color:purple">lists.freeswitch.org/mailman/options/freeswitch-users</span></a><br><a href="http://www.freeswitch.org" target="_blank"><span style="color:purple">http://www.freeswitch.org</span></a></span><u></u><u></u></p>
</div></div><p class="MsoNormal"> <u></u><u></u></p></div></div></div></div></div><p class="MsoNormal" style="margin-bottom:12.0pt"><br>_________________________________________________________________________<br>Professional FreeSWITCH Consulting Services:<br>
<a href="mailto:consulting@freeswitch.org" target="_blank">consulting@freeswitch.org</a><br><a href="http://www.freeswitchsolutions.com" target="_blank">http://www.freeswitchsolutions.com</a><br><br>FreeSWITCH-powered IP PBX: The CudaTel Communication Server<br>
<a href="http://www.cudatel.com" target="_blank">http://www.cudatel.com</a><br><br>Official FreeSWITCH Sites<br><a href="http://www.freeswitch.org" target="_blank">http://www.freeswitch.org</a><br><a href="http://wiki.freeswitch.org" target="_blank">http://wiki.freeswitch.org</a><br>
<a href="http://www.cluecon.com" target="_blank">http://www.cluecon.com</a><br><br>FreeSWITCH-users mailing list<br><a href="mailto:FreeSWITCH-users@lists.freeswitch.org" target="_blank">FreeSWITCH-users@lists.freeswitch.org</a><br>
<a href="http://lists.freeswitch.org/mailman/listinfo/freeswitch-users" target="_blank">http://lists.freeswitch.org/mailman/listinfo/freeswitch-users</a><br>UNSUBSCRIBE:<a href="http://lists.freeswitch.org/mailman/options/freeswitch-users" target="_blank">http://lists.freeswitch.org/mailman/options/freeswitch-users</a><br>
<a href="http://www.freeswitch.org" target="_blank">http://www.freeswitch.org</a><u></u><u></u></p></div><p class="MsoNormal"><br><br clear="all"><u></u><u></u></p><div><p class="MsoNormal"><u></u> <u></u></p></div><p class="MsoNormal">
-- <br>Anthony Minessale II<br><br>FreeSWITCH <a href="http://www.freeswitch.org/" target="_blank">http://www.freeswitch.org/</a><br>ClueCon <a href="http://www.cluecon.com/" target="_blank">http://www.cluecon.com/</a><br>
Twitter: <a href="http://twitter.com/FreeSWITCH_wire" target="_blank">http://twitter.com/FreeSWITCH_wire</a><br><br>AIM: anthm<br><a href="mailto:MSN%3Aanthony_minessale@hotmail.com" target="_blank">MSN:anthony_minessale@hotmail.com</a><br>
GTALK/JABBER/<a href="mailto:PAYPAL%3Aanthony.minessale@gmail.com" target="_blank">PAYPAL:anthony.minessale@gmail.com</a><br>IRC: <a href="http://irc.freenode.net" target="_blank">irc.freenode.net</a> #freeswitch<br><br>FreeSWITCH Developer Conference<br>
<a href="mailto:sip%3A888@conference.freeswitch.org" target="_blank">sip:888@conference.freeswitch.org</a><br><a href="mailto:googletalk%3Aconf%2B888@conference.freeswitch.org" target="_blank">googletalk:conf+888@conference.freeswitch.org</a><br>
pstn:<a href="tel:%2B19193869900" value="+19193869900" target="_blank">+19193869900</a> <u></u><u></u></p></div></div></div><br>_________________________________________________________________________<br>
Professional FreeSWITCH Consulting Services:<br>
<a href="mailto:consulting@freeswitch.org">consulting@freeswitch.org</a><br>
<a href="http://www.freeswitchsolutions.com" target="_blank">http://www.freeswitchsolutions.com</a><br>
<br>
FreeSWITCH-powered IP PBX: The CudaTel Communication Server<br>
<a href="http://www.cudatel.com" target="_blank">http://www.cudatel.com</a><br>
<br>
Official FreeSWITCH Sites<br>
<a href="http://www.freeswitch.org" target="_blank">http://www.freeswitch.org</a><br>
<a href="http://wiki.freeswitch.org" target="_blank">http://wiki.freeswitch.org</a><br>
<a href="http://www.cluecon.com" target="_blank">http://www.cluecon.com</a><br>
<br>
FreeSWITCH-users mailing list<br>
<a href="mailto:FreeSWITCH-users@lists.freeswitch.org">FreeSWITCH-users@lists.freeswitch.org</a><br>
<a href="http://lists.freeswitch.org/mailman/listinfo/freeswitch-users" target="_blank">http://lists.freeswitch.org/mailman/listinfo/freeswitch-users</a><br>
UNSUBSCRIBE:<a href="http://lists.freeswitch.org/mailman/options/freeswitch-users" target="_blank">http://lists.freeswitch.org/mailman/options/freeswitch-users</a><br>
<a href="http://www.freeswitch.org" target="_blank">http://www.freeswitch.org</a><br>
<br></blockquote></div>