[zeromq-dev] openpgm

Jim Hague jim.hague at acm.org
Tue Apr 18 14:22:37 CEST 2017


On 17/04/2017 15:44, Marlborough, Rick wrote:
> 	I set the environment variables and reran my test. Seeing something very curious. My publisher is running on 10.0.0.5.  My subscriber is on 10.0.0.4. On my publisher side I see the following output from pgm...
> 
> Minor: OpenPGM 5.2.122 (1487) 2017-03-27 13:04:29 Linux x86_64
> Minor: Detected 8 available 8 online 8 configured CPUs.
> Minor: Using gettimeofday() timer.
> Trace: Opening UDP encapsulated sockets.
> Trace: Set socket sharing.
> Trace: Request socket packet-info.
> IP: 224.15.15.5, PORT: 5008                                                                    <-- my test log statement. This is the ip and port we are using
> Trace: Assuming IP header size of 20 bytes
> Trace: Assuming UDP header size of 8 bytes
> Trace: Create transmit window.
> Trace: Binding receive socket to INADDR_ANY
> Trace: Binding send socket to interface index 0
> Trace: Setting ODATA rate regulation to 125000000 bytes per second.
> Trace: Join multicast group 224.15.15.5 on interface index 0
> Trace: Multicast send interface set to 127.0.0.1 index 0                <-- sending multicast on loopback ??

Yes, it looks like you're suffering from the same problem I had. This
was, unfortunately, in a previous job a couple of years ago, so I don't
have access to the documentation.

>From memory, your only option as things stand is to specify the
interface to use in the connection spec, either by using the interface
name or its IP.  http://api.zeromq.org/master:zmq-pgm.

This wasn't good enough for me; I was deploying to a RHEL 6 fleet where
the interface name wasn't predictable, the IP address (obviously) varied
from host to host, and I wanted to avoid host-specific configuration.
The current OpenPGM trunk fixes these issues. I think I ended up
preparing a custom openpgm RPM with an updated OpenPGM. I may have had
to update the 0MQ RPM as well to use it, I can't remember.
-- 
Jim Hague - jim.hague at acm.org          Never trust a computer you can't
lift.



More information about the zeromq-dev mailing list