Re: POST procedure (squid 2.7 stable9)

sön 2012-03-18 klockan 21:19 +0800 skrev Schulz Xu:
> Thanks for the tips. I trace back from the
> ProcessRequest->clientAccessCheck->ClientFinishRewrite->ClientStoreURLRewrite->clientRedirect->clientAccCheckDone
> On the other hand, I follow from tryParse to
> clientCheckFollowXForwardFor. But other problem occur.
> 1. in clientCheckFollowXForwardFor, what is FOLLOW_X_FORWARDED_FOR???

It's a define set by configure, enabled by the
--enable-follow-x-forwarded-for configure options. If enabled then
FOLLOW_X_FORWARDED_FOR is true and the related code gets compiled. If
not enabled then it's false/undefined and the related code do not get
compiled.

> 2. no matter how, the procedure will finally lead to the
> clientAccessCheck-->aclNBCheck-->aclCheck--> then I am kinda lost in
> the codes couldn't find the way from function aclCheck to function
> clientAccessCheckDone (which I think is the process.)

aclNBCheck calls the given callback on completion, i.e.
clientAccessCheckDone in case of clientAccessCheck().

    aclNBCheck(http->acl_checklist, clientAccessCheckDone, http);

processes the given checklist, then calls clientAccessCheckDone with the
result and http as argument.

> 3. If I am about to INTERCEPT the POST request and manage to store the
> body-content in the file system(I'll start with ufs but I hope that I
> can utilize the COSS),

ufs and coss uses the same interface, only implementation differ.

> what procedure you think I should follow. At the moment, I'd like
> examine the code in processReq. Cuz usually when tagged as MISS, the
> squid will be asked to forward the POST. However,can you tell me a
> simple procedure to store the content in the squid?

I am not entirely sure what you want to do with stored POST data.

What is it from an HTTP layer point of view that you want to accomplish?
Please describe your goal in terms of HTTP requests and their responses.

Regards
Henrik

>
>
> Thank you( and your time)
>
> Schulz
>
>
> 在 2012年3月16日 下午9:33，Henrik Nordström
> <henrik_at_henriknordstrom.net>写道：
> tor 2012-03-15 klockan 18:40 -0700 skrev Schulz:
>
>
> > Simply speaking, when dealing with the POST request, squid
> mainly use
> > the readRequest-->tryParseHttp-->parseHttpReq(in which using
> the
> > urlParse to find the method )
>
>
> That's the general request parsing path, parsing the request
> into
>
> Request line
> Request headers
> Body pipe (not parsed, only transferred)
>
> this is the same for all requests with POST no different from
> a
> GET/HEAD/OPTIONS/PUT/DELETE/whatever. Even CONNECT gets parsed
> the same
> way.
>
>
> > When parseHttpReq retrieve all the useful info, then the
> tryParse
> > would react according to the http. But tryParse only return
> the bytes
> > it used to the readRequest. Where is the following
> procedure?
>
>
> When the request is parsed it's added to the list of pending
> requests on
> the connection and handed off to the chain of access controls.
>
> In Squid-2 the access control chain starts with
> clientCheckFollowXForwardedFor() and ends in
> clientProcessRequest(),
> where it checks it it's a cache etc.
>
> then if the request needs to be forwarded (which is always the
> case for
> POST) it calls fwdStart(), which does a bit of a dance to
> figure the
> right path for forwarding the request, opens a connection and
> hands off
> to the respective protocol handler, i.e. http.
>
> Up to this point the body of the POST request is not touched
> at all.
> Only the protocol handler accesses the body of the POST
> request.
>
> Regards
> Henrik
>
>
>
>
Received on Sun Mar 18 2012 - 13:59:48 MDT