Opensim Devs
I have been working on an external process that I hope to link to an
opensim plugin I am authoring. As a sanity check, I ran a simple socket
test against the components to test for obvious problems before I get to
the heavy lifting. This test was not meant to reveal anything,
The first step is to benchmark with iperf or something similar. 160K packets
per second is a fairly stiff load. It’s often not so much
the bandwidth in these cases as the time necessary for the OS to process the
packet. If a new packet comes in before
the OS has finished processing the old one
Sounds great Sean, however I must say that submitting monolithic patches
into OpenSimulator is not something we tend to accept or encourage, it
would be considerably better if development was actively done in smaller
pieces so it could be tested on a very wide audience as development is
occurring
Good point. I will explore that more.
From: opensim-dev-boun...@opensimulator.org
[mailto:opensim-dev-boun...@opensimulator.org] On Behalf Of Michael Emory
Cerquoni
Sent: Monday, March 16, 2015 10:13 AM
To: opensim-dev@opensimulator.org
Subject: Re: [Opensim-dev] UDP async performance
I
I'm not sure where the loss occurs but I've seen similar behavior in other
network layer implementations based on UDP. You can only send so much
before the receiving end sees packet loss and this makes sense as there is
no (or very little) buffering at the receiving end to store unprocessed
I am not sure the HTTP server handles UDP, I want to say it does not handle
that.
On Mon, Mar 16, 2015 at 11:50 AM, Myron Curtis
myro...@virtualworldsgrid.com wrote:
Could this be a case of the Http server in opensim just being too slow to
respond to this traffic quickly enough?
I'm pleased to announce that OpenSimulator 0.8.1 is now available [1]. Release
notes are at [2].
There are only minor changes compared with 0.8.1-rc2, the most significant being a fix for a regression where script
state was being lost for Hypergrid transfers.
As always, thanks to all the
Some information which may be useful for those implementing protocols over
UDP: https://tools.ietf.org/html/rfc5405
On Mon, Mar 16, 2015 at 10:46 AM, Dahlia Trimble dahliatrim...@gmail.com
wrote:
I'm not sure where the loss occurs but I've seen similar behavior in other
network layer
Thanks for the response Michael. Our PhysX-OpenSim development is now
underway. We wanted to make the announcement and let the dev community know
of our plans to share the fruit of our labor.
On Mon, Mar 16, 2015 at 11:56 AM, Michael Emory Cerquoni
nebadon2...@gmail.com wrote:
Sounds great
