Re: client_side and comm_close

On Thu, 2008-04-17 at 20:13 +0300, Tsantilas Christos wrote:
> Alex Rousskov wrote:
> > In reply to comment #8 for bug #2309
> > comm_read assertion failed: "ccb->active == false"
> > http://www.squid-cache.org/bugs/show_bug.cgi?id=2309
> >
> >> Note to the one looking into this bug: The assert happens if a
> >> comm_read() is called while there already is a comm_read() pending.
> >
> > Yes.
> >
> >> I would suspect the half closed client check has been wrongly
> >> adopted to call comm_read where it used commSetSelect periodically
> >> before..
> > d
> > The above may be true, but there are other conditions causing the same
> > assertion in my tests, with and without the pending comm_close patch
> > from Christos.
> >
>
> As I can understand the problem does not exist only in squid3.0 or only
> in squid3-trunk.
>
> The main problem with the client_side code is that the comm_read done by
> the ConnStateData class, the comm_writes by the ClientSocketContext
> class and comm_close (and other comm operations ) by all. This makes
> very difficult to manage the comm related problems in client_side code....

Yes. If we decide to fix this, there will be a single object responsible
for client connection management. Others will simply use its services as
needed. Comm cannot be such an object because it is too low-level.
Currently, the functionality is spread among many classes.

> > We should decide whether to continue patching holes here and there or
> > clean up the client_side*cc connection management mess for good. Should
> > we continue to patch isolated v3.0 problems and cleanup v3.1? Or is this
> > a v3.2 project? Or am I exaggerating the problems since common cases
> > usually work fine?

The question remains.

Thank you,

Alex.
Received on Tue Apr 22 2008 - 15:21:03 MDT