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

Hi Henrik,
 It is not a cbdata problem.

An example is in the HttpStateData::sendComplete method which is going
to execute an commSetTimeout(fd ...)

Now there are cases in which this method scheduled for execution
sometime in the future but before it is executed the squid code closes
the fd using comm_close. In this case the fd is not valid any more and
when the HttpStateData::sendComplete executes the commSetTimeout an
assertion will crash squid.
Moreover I believe that it is possible the squid reuse the fd and the
commSetTimeout will be executed on a wrong fd.

Also I had a similar problem in tunnel.cc with the tunnelClientClosed
and tunnelServerClosed comm_close handlers, where the comm_close handler
of server closes the client socket and opposite.

With this patch squid now starts closing the fd , it mark it as
"closing" but actually schedules the real fd closing to a future, after
the comm_close handlers will be really executed.

It is not look the best method to do not release/close immediately a not
needed filedescriptor but I did not found a better way to handle these
problems. Do you see any problem here?

Regards,
   Christos

Henrik Nordstrom wrote:
> On lör, 2008-01-05 at 21:25 +0000, chtsanti wrote:
>
>> When a socket is closed then it is possible that remains AsyncCalls to be
>> executed which will try to perform operation on the closed socket.
>> This patch does not close the socket when comm_close called but instead
>> schedules the socket closing as an AsyncCall operation
>
> Smells like there may be a cbdata barrier missing somewhere...
>
> Regards
> Henrik
Received on Sun Jan 06 2008 - 03:27:42 MST