Re: Tidying up the deferred reads

On Mon, Oct 17, 2005, Henrik Nordstrom wrote:

> Was also thinking about scheduling a timer event when the bucket was found
> empty, but the problem is that it may quite easily lead to starvation, and
> also degrades fairly badly when there is many clients competing on the
> same bucket.

Hm, not if you checked every time the client side had written some data to the
client - if at this point the bucket has filled up a little then you
immediately delete the timed event and reschedule IO.

> A cleaner alternative would be to have some kind of queue mechanism on the
> delay pool, serving the requests on a first-come-first-serve basis while
> there is space left.. This would also give far better fairness in pool
> usage than today.
>
> The server side is all cbdata handled, so there shouldn't be any issues
> with this callback from the delay pool to the server side.
>
> Series of events:
>
> 1. comm finds the server side fd ready
> 2. delay pools indicates the pool being empty
> 3. server side asks delay pools to get called when there is space
> available
>
> 4. delay pool gets refilled
> 5. server side reactivated by callback in a first-come-first-serve order

I'll have more of a think about it after I've completed removing the
current commDefer stuff and its been tested. What do i have to do to get more
people to test - re-implement kqueue/epoll? :P

Adrian
Received on Sun Oct 16 2005 - 19:02:03 MDT