Newsgroups: php.internals
Path: news.php.net
Xref: news.php.net php.internals:21753
Mailing-List: contact internals-help@lists.php.net; run by ezmlm
Message-ID: <200602011939.OAA10156@alexander.concentric.com>
Errors-To: <jluedke@concentric.com>
To: <internals@lists.php.net>
Reply-To: jluedke@concentric.com
Date: Wed, 01 Feb 2006 14:39:14 -0500 (EST)
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
Subject: reducing open calls in php
From: jluedke@concentric.com (James M Luedke)

Hello:
    We have a very high-volume site that runs across a cluster of several
machines which needs to have access to our back end storage platform, which
needless to say is very busy. I have been given the task of reducing load t=
o
the filer. Due to the fact that our application is rather large and include=
s
lots of files which reside on our filer, php would be a good place to cut d=
own load.

    We currently have a rather unique setup. We are running php with
fast-cgi support via sapi/cgi/cgi_main.c as well as APC for opcode/user
caching**. This allows us to run php as a daemon which reduces system calls
and retains persistence with APC. Our setup has been working quite well.
However, there is one behavior that is less than optimal.
=20
    Whenever one of our pages is accessed, it appears*** that the requested
file and all included files are opened, which results in several open calls=
 to our filer. As I mentioned, we are running APC which seems to be doing a
nice job of op-code caching. It would be ideal if somehow I could modify ph=
p
to first check APC cache for the pre-compiled opcode before attempting to
open the file. This would be a huge win on our cluster, since each hit
currently generates 5-10 open calls.

    Now please bear with me because I am new to the Zend / main tree of=20
the php source. If my understanding is correct, the basic flow of=20
cgi/php goes something like this:                   =20

   request
   some variable init.
   module_init <-apc overide compile_file w/my_compile_file
   php_fopen_primary_script(&file_handle TSRMLS_CC);
   php_execute_script(&file_handle TSRMLS_CC);
       VCWD_CHDIR_FILE(primary_file->filename);
       # i think included_files gets opened here someplace
       # i do not understand that magic yet.
       zend_execute_scripts()
           zend_compile_file()
               compile_file || my_compile_file() <-- apc
               # it looks like the std compile_file
               # may do some zend_open cmds here via
               # open_file_for_scaning()
           zend_destroy_file_handle() <-- destroy before execute?
           zend_execute()
       php_request_shutdown()
    FCGX_Finish_r;

I have a few questions:
1. When exactly do the files get opened/read? And is this a necessary=20
step if you already have the op-code.
2. Is it possible to check apc_cache before opening files? If it=20
is possible, how/where do you think it could be best implemented?=20
Is there some similar interface to the my_compile_file trick used=20
to override zend_compile_file by apc? Perhaps something like=20
my_open_file, which I could then add support for into the apc module?
3. would changing utility_functions->fopen_function; to point to=20
my_fopen_function in place of zend_open work.

Any input would be greatly appreciated.

-James

** ( mod_php and the likes are not an option for us as we have our own
custom web server which we cannot do without  :)  )

*** when i truss one of the php daemon process i can clearly see that
it opens and reads the requested file. It also opens all the=20
included/required files but does not seem read them.