[zeromq-dev] ooc bindings for ØMQ

Peter Alexander vel.accel at gmail.com
Mon Jun 21 13:09:31 CEST 2010


Hi Martin,

On Sat, Jun 19, 2010 at 3:11 AM, Martin Sustrik <sustrik at 250bpm.com> wrote:
> Peter Alexander wrote:
>
>> The first is a very flexible, even autonomous load
>> distribution/balancing scheme(s) that take into consideration various
>> aspects of distributed pipeline processing like the distribution of
>> components (local, lan, wan, etc) as well as the various individual
>> machine characteristics like cpu, memory, etc. Currently I believe,
>> only a round-robin scheme is available.
>
> What's currently done is that size of the queue leading to a downstream
> component can be limited (ZMQ_HWM socket option). Thus, if the component
> is not catching up, its queue gets full and the scheduler stops sending
> more requests to the component. Instead it dispatches requests to the
> components that are working OK.
>
> What's your idea with the resource-monitoring approach?
>
> Btw, one thing that would be worth implementing in the scheduler IMO are
> priorities. That way you would be able to say: load balance the work
> among components A, B and C and only if none of those is available use
> component D (which may be off-site or too expensive etc.)
>

In the next few days I'm going to be putting focused thought towards
this. I'll start a new thread after studying the sources a bit more.

>> The second is a transparent standard-socket adapter, which I believe
>> is what you have in mind and are currently planning. I think atm only
>> zmq_poll() is available for adapting a standard-socket into the zmq
>> system.
>
> Yes. That's what I am working on although it's technically impossible in
> POSIX-y environment :)

So are you saying that, in the future, the only way we're going to be
able adapt a standard-socket into the zmq system, at the user level,
is going to be via the zmq_poll(). So, I think what you are suggesting
is a portable approach to transparency is what the difficulty is.

thanks..  ~Peter.

>
> Martin
> _______________________________________________
> zeromq-dev mailing list
> zeromq-dev at lists.zeromq.org
> http://lists.zeromq.org/mailman/listinfo/zeromq-dev
>



More information about the zeromq-dev mailing list