[zeromq-dev] ZMQ_MCAST_LOOP with PGM

Pierre Ynard linkfanel at yahoo.fr
Tue Aug 7 15:01:24 CEST 2012

> Redundancy on the same host is retarded you are wasting resources to
> catch less 0.01% error scenarios that don't bring down the entire host
> or network;scaling sounds like a bad design: split the channel up into
> many separate PGM sessions with rate limited senders and your data
> stream load balanced across them. It is becoming popular to automate
> this load-balancing but 0MQ does not yet implement such a feature:
> TIBCO Rendezvous 8 does.

I'm not talking about redundancy and scalability of the transport
channel, but of my business stuff.

> The UDP loopback network stack is broken for anything above minimal
> transfer rates.

For information, my personal transfer rate should be minimal enough, so
I'm inclined to spare myself extra TCP or IPC sockets for the loopback
case; that wouldn't fix the multiple sender issue anyway.

> It has been this way a long time and can be easily reproduced with
> multicast testing tools. Windows fairs better as sockets are handled
> outside of the kernel but performance is significantly worse.

> On Solaris and other UNIX flavours this is true, however as noted
> before on Linux it is broken.

That's interesting. Do you have any pointers to discussions about the
roots of this? All I could find was stuff related to the basics I
mentioned earlier.

Pierre Ynard
"Une âme dans un corps, c'est comme un dessin sur une feuille de papier."

More information about the zeromq-dev mailing list