Subject: Re: [Fwd: [saga-rg] monitoring, again...]
Raül Sirvent
rsirvent at ac.upc.edu
Wed Nov 9 09:35:38 CST 2005
Andre Merzky wrote:
> Quoting [Raul Sirvent] (Nov 09 2005):
>
>>>Ah, I am having a Deja Vu here :-) I found in one of our
>>>earlier discussions:
>>
>>You mean we are always talking about the same thing? That's not good... :)
>
>
> Right you are! How is wether in Barcelona :-P?
>
> (Hehe, now that I am in Louisiana for a while, and don't
> have to suffer from the rainy Dutch Fall I actually dare to
> ask :-P)
>
>
>
>>Yes. It is clear now. You support a threaded model with asynchronous
>>notifications, and you don't support a non-threaded model with
>>synchronous notifications. I'm just a bit worried about the CPU wasted
>>with active waits (to receive callbacks) in the main thread, or even
>>having to insert sleeps (as you do) in the code. Do you think it is
>>really so difficult to support both? (as Globus does, for instance).
>
>
> difficult not:
>
> void event_poll
> {
> while ( ! event_counter )
> {
> // that noeeds virtually NO CPU
> nanosleep (10);
> }
> }
>
> The internal callback mechanism would then increase
> event_counter before any callback is issued.
>
> The question with that really is:
>
> - do you want to wait for specific types of events
> -> how are types specified?
> - do you want to wait for events from any task?
> -> what object has the event_poll method?
In our particular case we wait for any events from any task. Where the
event_poll should be located? It's difficult to say. In a generic place
that represents all the things that can be monitorable? (almost
everything? :D).
Raul.
>
> Cheers, Andre.
>
>
More information about the saga-rg
mailing list