Re: async-calls squid3/src comm.cc,1.81.4.16,1.81.4.17

On Sun, Jan 06, 2008, Tsantilas Christos wrote:

> Adrian Chadd wrote:
> > .. I read that as "the code is broken and needs to be fixed."
>
> I think not so broken because there are solutions or workarounds off the
> problems.
> I think the last changes fix the problem (however I want to look more on
> this to be sure there are not any other problems....).

I like async-calls, and it solves this problem, but I think we need
to be sure to fix bugs that creep up rather than relying on this to
try and sort it out for us Bad code is going to be crap to follow
regardless of whether we get the stack unwound or not.

> The problem was that when the HttpStateData::SendComplete scheduled the
> descriptor was valid. But a comm_close on this file descriptor could
> make it invalid before the HttpStateData::SendComplete really executed.

Ah, so SendComplete is being called via an async call gate after
the fd has been thrown?

Adrian
Received on Sun Jan 06 2008 - 05:15:01 MST