[zeromq-dev] [Openpgm-dev] Re: Assertion failed

Steven McCoy steven.mccoy at miru.hk
Thu Apr 8 15:26:02 CEST 2010


On 8 April 2010 21:00, Martin Sustrik <sustrik at 250bpm.com> wrote:

>  I notice "holes" in packet sequence number at the moment where according
>> to the graph there is no traffic.
>> Everything looks like some network packet has not been transferred to
>> wireshark. However, these packets has been transmitted on the network
>> otherwise none of my subscribers will have reported a correct transmission.
>> If some packets have not been transmitted to wireshark, I guess the same
>> things happened for my 4 subscribers which has lost messages.
>>
>
> As one of my subscriber has received all my messages, I think the network
> delivered all the messages.
>

Sounds like broken or incorrectly configured hardware.  Try swapping the
application roles between hosts to see if the result changes.  Preferably
try running pgmping from OpenPGM between the hosts.

I had a lot of problems with a SPARC and STP on the switch port recently.


>
> If yes, I guess the solution is to decrease the RATE until the kernel is
>> able to reliably dispatch all the packets received to all the involved
>> subscribers.
>>
> My kernel is linux 2.6.28-18. Do you think that this multicast packet
> dispatching done by the kernel could be the reason of the behavior I am
> observing?
>
> I don't think the rate is problem. By default it's 100kb/sec which is
> extremely low and the system should experience any problems with it.
>
>
At such a minuscule data rate the kernel is not going have any significant
impact.

It is possible the rate is actually so low you keep tripping up the NICs
batching and coalescing features, so I'd also give a go at ramping up to
something more useful.

-- 
Steve-o
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.zeromq.org/pipermail/zeromq-dev/attachments/20100408/b23aa6f6/attachment.html>


More information about the zeromq-dev mailing list