I haven't been able to follow this thread very closely, but I do have
one question:

You can already do non-copying sends of non-contiguous memory using
0MQ, you just have to send multiple messages.  What additional benefit
would message groups give beyond that?

Cheers,

Brian


On Sun, Mar 7, 2010 at 1:41 PM, Jon Dyte <[email protected]> wrote:
> Martin Sustrik wrote:
>>
>> Michael,
>>
>>
>>>>
>>>> It's less trivial to implement (at very least it would require tweaking
>>>> the wire protocol), however, the added value is much greater than in the
>>>> simple iovec case.
>>>>
>>>
>>> Agreed, it certainly seems non-trivial, especially over some of the
>>> socket
>>> types.  What did you have in mind for the API on the receiving side?
>>>  Would
>>> the receiver have to know that it is receiving a message group, or would
>>> all
>>> of the messages be delivered as one large message?  Or do you have
>>> another
>>> idea?
>>>
>>
>> I thought of leaving the receiving API as is:
>>
>> zmq_recv (&msg1);
>> zmq_recv (&msg2);
>> zmq_recv (&msg3);
>>
>> Note that as the messages are guaranteed to be delivered atomically in one
>> go, second and third recv won't ever block.
>> Additionally, it's possible to check for 'end of the group' flag:
>>
>> bool end = zmq_is_end_of_group (msg);
>>
>> However, my feeling is that such a functionality just makes the API more
>> complex without providing much added value. If needed, the same thing can be
>> done on application level.
>>
>>
>
> by which you mean a continuation_indicator would have to be in the app
> message and the
> api thread could loop creating zmq_msg and then calling zmq_recv?
>
>
> jon
>
>
>> Martin
>> _______________________________________________
>> zeromq-dev mailing list
>> [email protected]
>> http://lists.zeromq.org/mailman/listinfo/zeromq-dev
>>
>>
>
>



-- 
Brian E. Granger, Ph.D.
Assistant Professor of Physics
Cal Poly State University, San Luis Obispo
[email protected]
[email protected]
_______________________________________________
zeromq-dev mailing list
[email protected]
http://lists.zeromq.org/mailman/listinfo/zeromq-dev

Reply via email to