This is partly right, and partly wrong. Actually, some light-weight
message passing protocols can be cheaper than function calls. A function
call to a kernel function requires two state transitions (user->kernel
and back), and two context switches; since the kernel wants to massage
different data than the user process, it also has an effect on the
cache.
Message passing can make this cheaper, if (and only if) your messages
are handled asynchronously. Put a bunch of messages into your shared
memory message buffer (simple *ptr++ = id; *ptr++ = arg; ...), and when
you are done, do the one state transition and context switch, and let
the kernel handle all the requests at once (also simple: next message is
goto *handlers[*ptr++]; Message code does arg = *ptr++;...). The
communication overhead in a good designed active message system can be
below the state transition overhead in a classical OS.
Counterside: works only if your OS is designed to deliver asynchronous
results, and if your app is programmed to use that. In other words:
forget about blocking read/write calls. Works much better for services
like X Window than for Unix-like OS services. The point is that you must
restructure your app to be message-handling, too. I.e. a web server's
frame would look like
switch(get_next_message(queue)) {
case incoming_connection: accept(connection); break;
case opened_connection: read(request); break;
case request_read: parse(request); send_answer(request); break;
case request_sent: close(connection); free(request); break;
...
}
Note that all the OS-related calls are unblocking and are served (as a
bunch) when the app has no more messages to handle - or the outgoing
message buffer is full. Wraping messages around an OS that is designed
to have services as function calls is a complete waste of time; so in
this respect, Linus is right. Masturbation is only effective if you have
a sperm bank.
-- Bernd Paysan "If you want it done right, you have to do it yourself" http://www.jwdt.com/~paysan/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/