Re: Apache + mod_php performance

On Sun, 29 Sep 2024 19:16:48 -0400, Arne Vajhøj wrote:

On 9/29/2024 6:57 PM, Lawrence D'Oliveiro wrote:

>
On Sun, 29 Sep 2024 10:46:12 -0400, Arne Vajhøj wrote:

>
That is not how Apache prefork MPM works.

 
If that’s not how it works, then how can you serve a client from more
than one member of the worker pool?

 
A new request on a new connection goes to another worker. No problem.

But with keepalive, the request will come in on the existing connection.
So you have to dedicate a worker process to each connection? That’s
inefficient.

And I don't understand the "put all the client context into shared
memory" either. Are you saying that if socket descriptors are put in
shared memory then any process that map that memory can use those
sockets????

 
No, but the shared-memory context can contain an index into a table of
socket descriptors in private per-process memory. If the process trying
to server a client context does not actually have a socket descriptor
in the slot for that context, it can ask for one.

 
I still can't follow the idea.
 
Client X has a connection to server worker A. That means that A has
index 77 in shared memory that points to the socket descriptor for the
connection from X.
 
Worker B wants to serve X as well and it get index 77 from shared
memory. And then it does what?

Looks up its entry in its process-private copy of the array that contains
the socket descriptors, to see if it has its own valid fd for that socket.

You would also want to associate a generation number with that socket
entry, so you can detect that the client connection associated with the
previous socket has been closed, so that client entry is in fact for a
different client connection.