[JDEV] Stress testing and connection limits

[Thomas Charron]

Quoting Chuck Bohling <chuck at ultris.com>:
> I've been stress testing Jabber to get a feel for how many concurrent users
> it can handle. I've hit some limit on the number of connections that Jabber
> will accept. Hopefully, it's a soft limit in Linux or Jabber, or maybe a
> mistake in my test. (Could it be a problem with Windows 2000?) Here's what
> I've done. The test is in C++ on Windows 2000. The program spawns some
> number of threads, emulating Jabber clients. Each "client" starts a stream,
> registers, authenticates, does an online presence, and then, in a somewhat
> random fashion, sends messages to other "clients". The receiving client
> prints the message. This works great up to about 1000 (1024?) clients
> (threads). Above that number, I start seeing all kinds of failures. I think
> it may be caused by pth_accept rejecting the connection, but I'm not sure.
> Anyone have any ideas? I did disable the connection rate check in
> tlisten.c.
> Hopefully, it's something like a 1024 limit on the number of connections
> from the same IP.

  What OS is the server running on?  If your answer is Linux, then there's your 
answer.  The default Linux kernel setup cannot have more then 1024 open 
sockets.  In order to solve this issue, you need to configure your kernel to 
accept more sockets.  I believe temas provided a quickie on how to do this 
somewhere..

--- 
Thomas Charron
<< Wanted: One decent sig >>
<< Preferably litle used  >>
<< and stored in garage.  ?>>