Robert Collins wrote:
>
> Right. The proxy_auth dlink is obsolete -
> I thought I'd #ifdef GLOBALPROXYHEADERCACHE but obviosuly I haven't.
The same structure is used in auth_ntlm.c.
> The point was to allow multiple references back to a single
> structure that need to be cleaned all at the same time.
Like what you do in ntlm_auth.c.
> Aliases: a single scheme's auth_user->scheme structure can
> potentially have aliases - multiple auth_user structures pointing
> at it (and return different usernames). It's not supported by any
> of the current modules, and may need a little more API tweaking to
> work fully. As far as memory usage goes - I was going off the fact
> that 10,000 users, will only use ~2M of memory.
I don't se how that belongs in the username hash for auth_user. Feels
more like the job of a list inside the scheme specific data to keep
track of which user_auth that references this scheme structure.
If you were talking about username aliases where one auth_user could
have many names then it makes sense, but as long as "one username ==
one auth_user" (per scheme) then the indirection above auth_user is only
confusing.
One more thing I dislike: Today, if you have the same username in more
than one scheme then you have duplicate entries in the username hash. I
like to see this unified to one auth_user with multiple scheme specific
structures attached.
/Henrik
Received on Sat Jan 13 2001 - 17:24:18 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:13:18 MST