One example of what I'm trying to say.<div><br></div><div>In part of the packet handling there is a condition where the server needs to respond to the client, but does not yet know the identity of the client. So the server responds to the client and then spawns a thread which loops and sleeps until it can identify the client.( I don't really understand what's going on here,)</div>
<div><br></div><div>Nevertheless in this case you could do without the new thread if you queued a lambda function which would check to see if the client can be identified. A second event loop could periodically poll this function until it completes.</div>
<div><br></div><div>You could also queue other contexts which would complete the handling of <span></span>other types of packets.</div><div><br></div><div>Matt</div><div><br>On Friday, April 25, 2014, Dahlia Trimble <<a href="mailto:dahliatrimble@gmail.com">dahliatrimble@gmail.com</a>> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div><div><div><div><div>From my experience there are some things that need to happen as soon as possible and others which can be delayed. What needs to happen ASAP:<br>
</div>1). reading the socket and keeping it emptied.<br>
</div>2) acknowledge any received packets which may require such<br></div>3) process any acknowledgements sent by the viewer<br></div>4) handle AgentUpdate packets. (these can probably be filtered for uniqueness and mostly discarded if not unique).<br>
<br></div>This list is off the top of my head and may not be complete. Most, if not all, other packets could be put into queues and process as resources permit without negatively affecting the quality of the shared state of the simulation.<br>
<br></div>Please be aware that viewers running on high-end machines can constantly send several hundred packets per second, and that under extreme conditions there can be several hundred viewers connected to a single simulator. Any improvements in the UDP processing portions of the code base should probably take these constraints into consideration.<br>
</div><div class="gmail_extra"><br><br><div class="gmail_quote">On Fri, Apr 25, 2014 at 8:17 PM, Matt Lehmann <span dir="ltr"><<a href="javascript:_e(%7B%7D,'cvml','mattlehma@gmail.com');" target="_blank">mattlehma@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">That makes sense to me. <div><br></div><div>If I recall, the packet handlers will create more threads if they expect delays, such as when waiting for a client to finish movement into the sim.</div>
<div><br></div><div>Considering that I have 65 threads running on my standalone instance, with 4 cores that leaves about 15 threads competing. You have to do the work at some point. <span><font color="#888888"><br>
<br>Matt</font></span></div><div><div><div><span></span><br>On Friday, April 25, 2014, Dahlia Trimble <<a href="javascript:_e(%7B%7D,'cvml','dahliatrimble@gmail.com');" target="_blank">dahliatrimble@gmail.com</a>> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div dir="ltr"><div>Depends on what you mean by "services the packets". Decoding and ACKing could probably work well in a socket read loop but dispatching the packet to the proper part of the simulation could incur many delays which can cause a lot of packet loss in the lower level operating system routines as the buffers are only so large and any excessive data is discarded. Putting them in a queue for another thread to service is a good compromise which tends to keep things working under most load conditions.</div>
<div><br></div>However, if your design seems to improve things under a wide range of operating conditions, feel free to submit a patch! But please don't expect it to be accepted as it may need a *lot* of testing to show it's benefit over the current implementation.<br>
<div><br><br></div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Fri, Apr 25, 2014 at 7:45 PM, Matt Lehmann <span dir="ltr"><<a>mattlehma@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><p dir="ltr">As of the last release, the algorithm for handling udp packets from clients is as so... </p>
<p dir="ltr"> Start an async read cycle on the socket, adding packets to a blocking queue.<br>
Also start a smart thread which waits on the queue and services the packets. </p>
<p dir="ltr">Wouldn't it be more efficient to use a single thread that waits on the socket by looping on a socket.poll call, immediately servicing packets? </p>
<p dir="ltr">I have tried this locally and I really think it would improve efficiency. If you want I can submit a patch. </p>
<p dir="ltr">Thanks</p><span><font color="#888888">
<p dir="ltr">Matt</p>
</font></span><br>_______________________________________________<br>
Opensim-dev mailing list<br>
<a>Opensim-dev@opensimulator.org</a><br>
<a href="http://opensimulator.org/cgi-bin/mailman/listinfo/opensim-dev" target="_blank">http://opensimulator.org/cgi-bin/mailman/listinfo/opensim-dev</a><br>
<br></blockquote></div><br></div>
</blockquote></div>
</div></div><br>_______________________________________________<br>
Opensim-dev mailing list<br>
<a href="javascript:_e(%7B%7D,'cvml','Opensim-dev@opensimulator.org');" target="_blank">Opensim-dev@opensimulator.org</a><br>
<a href="http://opensimulator.org/cgi-bin/mailman/listinfo/opensim-dev" target="_blank">http://opensimulator.org/cgi-bin/mailman/listinfo/opensim-dev</a><br>
<br></blockquote></div><br></div>
</blockquote></div>