Re: cbdataFree

----- Original Message -----
From: "Henrik Nordstrom" <hno@hem.passagen.se>
To: "Robert Collins" <robert.collins@itdomain.com.au>
Cc: <squid-dev@squid-cache.org>
Sent: Tuesday, May 08, 2001 8:55 AM
Subject: Re: cbdataFree

> cbdata types are meant to be used in two ways:
>
> 1. A "original" pointer, as returned from cbdataAlloc.
>
> 2. Reference pointers, all locked with cbdataLock.
>
> When the "original" pointer is cbdataFree()d then all reference
pointers
> are marked as invalid (cbdataValid() returns false).
>
> If you look in the cbdata branch all this is a lot clearer. There the
> cbdataLock/Unlock calls has been replaced by
cbdataReference/Unreference
> using slightly different syntax glue to empasis the intended use and
> lessen the risk for errors, and the programmers guide extended to
better
> explain the cbdata use.
>
> Note: Many parts of Squid uses cbdata in bad ways and there is needs
for
> a quite big cleanup there.. most of the errors is in how data is freed
> (members should be freed by the callback, not by the function calling
> cbdataFree(). This because there might be references using these
members
> without verifying the reference validity...)
>
>
> If you only wish to use them as "reference counted allocations" then
you
> can theoretically do this by only saving a reference pointer..
>
> foo = cbdataAlloc()
> saved_foo = foo; cbdataLock(foo);
> cbdataFree(foo);
> ...
> cbdataUnlock(saved_foo);

Well thats what I tried, but all through the code cbdataValid() will
spit the dummy as well.

> but I would not encourage such use of cbdata, even if I have done so
> myself in the eventio branch (but only temporarily until some better
> mechanism for reference counted allocations can be found).
>
> cbdata is a quite nice thing, but reference counting is only a
sideffect
> of what is needed to implement cbdata, not the main feature of cbdata
> as. If you need reference couting but not cbdata then a pure reference
> couting should be used.

Right. Well I've probably done what you've done in eventio :-[. However
it works and I've abstracted the called to it so it will easy to fix
later.

Rob

> --
> Henrik
>
> Robert Collins wrote:
> >
> > This macro:
> >
> > #define cbdataFree(var) (var = (var != NULL ?
cbdataInternalFree(var):
> > NULL))
> >
> > is a problem for me:
> > I'm build a refcounted structure.
> > the cbdata code has provision to allow the following sequence:
> >
> > CBDATA_INIT_TYPE_FREECB(footype, freefoo)
> >
> > foo=cbdataAlloc(footype);
> > cbdataLock(foo);
> > cbdataFree(foo);
> >
> > access, lock and unlock foo until a matching
> > cbdataUnlock(foo);
> > occurs and then freefoo(foo) is automatically called.
> >
> > However the above macro is setting foo to NULL !? (because
> > cbdataInternalFree is returning NULL).
> >
> > Is this by design or oversite?
> >
> > Rob
>
Received on Mon May 07 2001 - 17:29:19 MDT