<html><head><meta http-equiv="Content-Type" content="text/html charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class=""><div class="">Diva</div><div class=""><br class=""></div><div class="">Thank you for the testing workflow, it is always helpful to see how others have had success in testing.</div><div class=""><br class=""></div><div class="">However, this particular endeavor is not a poorly performing grid. We would like to contribute to the scalability of the OpenSim project. </div><div class=""><br class=""></div><div class="">Michael Heilmann</div><div class=""><br class=""></div><blockquote type="cite" class="">Date: Fri, 14 Nov 2014 13:56:24 -0800<br class="">From: Diva Canto <<a href="mailto:diva@metaverseink.com" class="">diva@metaverseink.com</a>><br class="">To: <a href="mailto:opensim-dev@opensimulator.org" class="">opensim-dev@opensimulator.org</a><br class="">Subject: Re: [Opensim-dev] Modifying the networking stack<br class="">Message-ID: <<a href="mailto:54667A88.4040300@metaverseink.com" class="">54667A88.4040300@metaverseink.com</a>><br class="">Content-Type: text/plain; charset="iso-8859-1"; Format="flowed"<br class=""><br class="">Michael,<br class=""><br class="">If I understand it correctly, the problem you are dealing with is a<br class="">poorly performing grid. With proper configuration, 1 simulator running<br class="">on a reasonable server should be able to handle 50 real people hanging<br class="">around without showing signs of distress. That's the kind of performance<br class="">we have been seeing recently at OSCC and other simulators. These days,<br class="">an OpenSim simulator can easily handle 100 people removed from the<br class="">physics scene (sitting). When a simulator performs poorly with 2 users,<br class="">something is very wrong. My guess would be mono, but that can have other<br class="">causes too (i.e. a bad kernel, inappropriate machine, etc.).<br class=""><br class="">Independent of configuration issues, which I can't really help with, if<br class="">you want to get a systematic grasp of the performance of OpenSim,<br class="">especially the network-related aspects, here's my suggestion: (this is<br class="">what I did last year)<br class=""><br class="">1 - Use WinGridProxy between your viewer and your grid, so to understand<br class="">what the traffic really is. WireShark is the wrong tool; WinGridProxy<br class="">shows you everything. Pay particular attention to AgentUpdate messages<br class="">because those are, by far, the largest portion of UDP traffic from<br class="">viewers to the server once the initial login phase is over.<br class=""><br class="">2 - Reconfigure your bot framework to send AgentUpdates at a constant<br class="">rate of at least 10/sec, or whatever you observe in step 1. Note that<br class="">libomv bots may or may not send AgentUpdates at a constant rate,<br class="">depending on how they are configured. That setting is<br class="">Settings.SEND_AGENT_UPDATES in libomv. By default, libomv bots send<br class="">2/sec, and that is given by a timer that runs at<br class="">Settings.DEFAULT_AGENT_UPDATE_INTERVAL (500ms). 2/sec is insignificant<br class="">compared to what I've seen real viewers do, so if your bot framework<br class="">doesn't change that setting, the results will not correlate to<br class="">performance with real viewers.<br class=""><br class="">3 - Measure load at the server when the bots are sitting down doing<br class="">nothing (except sending the AgentUpdate messages). If the CPU increases<br class="">much more than linearly with the number of bots, and you're running a<br class="">version of OpenSim as of the last 12 months, then there's something<br class="">wrong with the configuration of your simulator server -- kernel, mono,<br class="">or opensim -- because that is not what we observe in properly configured<br class="">OpenSim servers these days. It was, however, what we observed when our<br class="">server had the wrong kernel that was making mono behave badly.<br class=""><br class="">Good luck!<br class=""><blockquote type="cite" class=""></blockquote></blockquote></body></html>