/*
* Author: Marc A. Lehmann <xsthreadpool@schmorp.de>
* License: public domain, or where this is not possible/at your option,
* CC0 (https://creativecommons.org/publicdomain/zero/1.0/)
*/
#ifndef PERL_MULTICORE_H
#define PERL_MULTICORE_H
/*
=head1 NAME
perlmulticore.h - the Perl Multicore Specification and Implementation
=head1 SYNOPSIS
#include "perlmultiore.h"
// in your XS function:
perlinterp_release ();
do_the_C_thing ();
perlinterp_acquire ();
=head1 DESCRIPTION
This header file implements a simple mechanism for XS modules to allow
re-use of the perl interpreter for other threads while doing some lengthy
operation, such as cryptography, SQL queries, disk I/O and so on.
The design goals for this mechanism were to be simple to use, very
efficient when not needed, low code and data size overhead and broad
applicability.
The newest version of this document can be found at
L<http://pod.tst.eu/http://cvs.schmorp.de/Coro-Multicore/perlmulticore.h>.
The newest version of the header file itself, which
includes this documentation, can be downloaded from
L<http://cvs.schmorp.de/Coro-Multicore/perlmulticore.h>.
=head1 HOW DO I USE THIS IN MY MODULES?
The usage is very simple - you include this header file in your XS module. Then, before you
do your lengthy operation, you release the perl interpreter:
perlinterp_release ();
And when you are done with your computation, you acquire it again:
perlinterp_acquire ();
And that's it. This doesn't load any modules and consists of only a few
machine instructions when no module to take advantage of it is loaded.
Here is a simple example, an C<flock> wrapper implemented in XS. Unlike
perl's built-in C<flock>, it allows other threads (for example, those
provided by L<Coro>) to execute, instead of blocking the whole perl
interpreter. For the sake of this example, it requires a file descriptor
instead of a handle.
#include "perlmulticore.h" // this header file
// and in the XS portion
int flock (int fd, int operation)
CODE:
perlinterp_release ();
RETVAL = flock (fd, operation);
perlinterp_acquire ();
OUTPUT:
RETVAL
Another example would be to modify L<DBD::mysql> to allow other
threads to execute while executing SQL queries. One way to do this
is find all C<mysql_st_internal_execute> and similar calls (such as
C<mysql_st_internal_execute41>), and adorn them with release/acquire
calls:
{
perlinterp_release ();
imp_sth->row_num= mysql_st_internal_execute(sth, ...);
perlinterp_acquire ();
}
=head2 HOW ABOUT NOT-SO LONG WORK?
Sometimes you don't know how long your code will take - in a compression
library for example, compressing a few hundred Kilobyte of data can take
a while, while 50 Bytes will compress so fast that even attempting to do
something else could be more costly than just doing it.
This is a very hard problem to solve. The best you can do at the moment is
to release the perl interpreter only when you think the work to be done
justifies the expense.
As a rule of thumb, if you expect to need more than a few thousand cycles,
you should release the interpreter, else you shouldn't. When in doubt,
release.
For example, in a compression library, you might want to do this:
if (bytes_to_be_compressed > 2000) perlinterp_release ();
do_compress (...);
if (bytes_to_be_compressed > 2000) perlinterp_acquire ();
Make sure the if conditions are exactly the same and don't change, so you
always call acquire when you release, and vice versa.
When you don't have a handy indicator, you might still do something
useful. For example, if you do some file locking with C<fcntl> and you
expect the lock to be available immediately in most cases, you could try
with C<F_SETLK> (which doesn't wait), and only release/wait/acquire when
the lock couldn't be set:
int res = fcntl (fd, F_SETLK, &flock);
if (res)
{
// error, assume lock is held by another process and do it the slow way
perlinterp_release ();
res = fcntl (fd, F_SETLKW, &flock);
perlinterp_acquire ();
}
=head1 THE HARD AND FAST RULES
As with everything, there are a number of rules to follow.
=over 4
=item I<Never> touch any perl data structures after calling C<perlinterp_release>.
Possibly the most important rule of them all, anything perl is
completely off-limits after C<perlinterp_release>, until you call
C<perlinterp_acquire>, after which you can access perl stuff again.
That includes anything in the perl interpreter that you didn't prove to be
safe, and didn't prove to be safe in older and future versions of perl:
global variables, local perl scalars, even if you are sure nobody accesses
them and you only try to "read" their value, and so on.
If you need to access perl things, do it before releasing the
interpreter with C<perlinterp_release>, or after acquiring it again with
C<perlinterp_acquire>.
=item I<Always> call C<perlinterp_release> and C<perlinterp_acquire> in pairs.
For each C<perlinterp_release> call there must be a C<perlinterp_acquire>
call. They don't have to be in the same function, and you can have
multiple calls to them, as long as every C<perlinterp_release> call is
followed by exactly one C<perlinterp_acquire> call.
For example., this would be fine:
perlinterp_release ();
if (!function_that_fails_with_0_return_value ())
{
perlinterp_acquire ();
croak ("error");
// croak doesn't return
}
perlinterp_acquire ();
// do other stuff
=item I<Never> nest calls to C<perlinterp_release> and C<perlinterp_acquire>.
That simply means that after calling C<perlinterp_release>, you must
call C<perlinterp_acquire> before calling C<perlinterp_release>
again. Likewise, after C<perlinterp_acquire>, you can call
C<perlinterp_release> but not another C<perlinterp_acquire>.
=item I<Always> call C<perlinterp_release> first.
Also simple: you I<must not> call C<perlinterp_acquire> without having
called C<perlinterp_release> before.
=item I<Never> underestimate threads.
While it's easy to add parallel execution ability to your XS module, it
doesn't mean it is safe. After you release the perl interpreter, it's
perfectly possible that it will call your XS function in another thread,
even while your original function still executes. In other words: your C
code must be thread safe, and if you use any library, that library must be
thread-safe, too.
Always assume that the code between C<perlinterp_release> and
C<perlinterp_acquire> is executed in parallel on multiple CPUs at the same
time. If your code can't cope with that, you could consider using a mutex
to only allow one such execution, which is still better than blocking
everybody else from doing anything:
static pthread_mutex_t my_mutex = PTHREAD_MUTEX_INITIALIZER;
perlinterp_release ();
pthread_mutex_lock (&my_mutex);
do_your_non_thread_safe_thing ();
pthread_mutex_unlock (&my_mutex);
perlinterp_acquire ();
=item I<Don't> get confused by having to release first.
In many real world scenarios, you acquire a resource, do something, then
release it again. Don't let this confuse you, with this, you already own
the resource (the perl interpreter) so you have to I<release> first, and
I<acquire> it again later, not the other way around.
=back
=head1 DESIGN PRINCIPLES
This section discusses how the design goals were reached (you be the
judge), how it is implemented, and what overheads this implies.
=over 4
=item Simple to Use
All you have to do is identify the place in your existing code where you
stop touching perl stuff, do your actual work, and start touching perl
stuff again.
Then slap C<perlinterp_release ()> and C<perlinterp_acquire ()> around the
actual work code.
You have to include F<perlmulticore.h> and distribute it with your XS
code, but all these things border on the trivial.
=item Very Efficient
The definition for C<perlinterp_release> and C<perlinterp_release> is very
short:
#define perlinterp_release() perl_multicore_api->pmapi_release ()
#define perlinterp_acquire() perl_multicore_api->pmapi_acquire ()
Both are macros that read a pointer from memory (perl_multicore_api),
dereference a function pointer stored at that place, and call the
function, which takes no arguments and returns nothing.
The first call to C<perlinterp_release> will check for the presence
of any supporting module, and if none is loaded, will create a dummy
implementation where both C<pmapi_release> and C<pmapi_acquire> execute
this function:
static void perl_multicore_nop (void) { }
So in the case of no magical module being loaded, all calls except the
first are two memory accesses and a predictable function call of an empty
function.
Of course, the overhead is much higher when these functions actually
implement anything useful, but you always get what you pay for.
With L<Coro::Multicore>, every release/acquire involves two pthread
switches, two coro thread switches, a bunch of syscalls, and sometimes
interacting with the event loop.
A dedicated thread pool such as the one L<IO::AIO> uses could reduce
these overheads, and would also reduce the dependencies (L<AnyEvent> is a
smaller and more portable dependency than L<Coro>), but it would require a
lot more work on the side of the module author wanting to support it than
this solution.
=item Low Code and Data Size Overhead
On a 64 bit system, F<perlmulticore.h> uses exactly C<8> octets (one
pointer) of your data segment, to store the C<perl_multicore_api>
pointer. In addition it creates a C<16> octet perl string to store the
function pointers in, and stores it in a hash provided by perl for this
purpose.
This is pretty much the equivalent of executing this code:
$existing_hash{perl_multicore_api} = "123456781234567812345678";
And that's it, which is, as I think, indeed very little.
As for code size, on my amd64 system, every call to C<perlinterp_release>
or C<perlinterp_acquire> results in a variation of the following 9-10
octet sequence:
150> mov 0x200f23(%rip),%rax # <perl_multicore_api>
157> callq *0x8(%rax)
The biggest part if the initialisation code, which consists of 11 lines of
typical XS code. On my system, all the code in F<perlmulticore.h> compiles
to less than 160 octets of read-only data.
=item Broad Applicability
While there are alternative ways to achieve the goal of parallel execution
with threads that might be more efficient, this mechanism was chosen
because it is very simple to retrofit existing modules with it, and it
The design goals for this mechanism were to be simple to use, very
efficient when not needed, low code and data size overhead and broad
applicability.
=back
=head1 DISABLING PERL MULTICORE AT COMPILE TIME
You can disable the complete perl multicore API by defining the
symbol C<PERL_MULTICORE_DISABLE> to C<1> (e.g. by specifying
F<-DPERL_MULTICORE_DISABLE> as compiler argument).
This will leave no traces of the API in the compiled code, suitable
"empty" C<perl_release> and C<perl_acquire> definitions will be provided.
This could be added to perl's C<CPPFLAGS> when configuring perl on
platforms that do not support threading at all for example.
=head1 AUTHOR
Marc A. Lehmann <perlmulticore@schmorp.de>
http://perlmulticore.schmorp.de/
=head1 LICENSE
The F<perlmulticore.h> header file is put into the public
domain. Where this is legally not possible, or at your
option, it can be licensed under creativecommons CC0
license: L<https://creativecommons.org/publicdomain/zero/1.0/>.
=cut
*/
#define PERL_MULTICORE_MAJOR 1 /* bumped on incompatible changes */
#define PERL_MULTICORE_MINOR 0 /* bumped on every change */
#if PERL_MULTICORE_DISABLE
#define perlinterp_release() do { } while (0)
#define perlinterp_acquire() do { } while (0)
#else
/* this struct is shared between all modules, and currently */
/* contain only the two function pointers for release/acquire */
struct perl_multicore_api
{
void (*pmapi_release)(void);
void (*pmapi_acquire)(void);
};
static void perl_multicore_init (void);
const struct perl_multicore_api perl_multicore_api_init = { perl_multicore_init, abort };
static struct perl_multicore_api *perl_multicore_api
= (struct perl_multicore_api *)&perl_multicore_api_init;
#define perlinterp_release() perl_multicore_api->pmapi_release ()
#define perlinterp_acquire() perl_multicore_api->pmapi_acquire ()
/* this is the release/acquire implementation used as fallback */
static void
perl_multicore_nop (void)
{
}
/* this is the initial implementation of "release" - it initialises */
/* the api and then calls the real release function */
static void
perl_multicore_init (void)
{
dTHX;
/* check for existing API struct in PL_modglobal */
SV **api_svp = hv_fetch (PL_modglobal, "perl_multicore_api", sizeof ("perl_multicore_api") - 1, 1);
if (SvPOKp (*api_svp))
perl_multicore_api = (struct perl_multicore_api *)SvPVX (*api_svp); /* we have one, use the existing one */
else
{
/* create a new one with a dummy nop implementation */
SV *api_sv = NEWSV (0, sizeof (*perl_multicore_api));
SvCUR_set (api_sv, sizeof (*perl_multicore_api));
SvPOK_only (api_sv);
perl_multicore_api = (struct perl_multicore_api *)SvPVX (api_sv);
perl_multicore_api->pmapi_release =
perl_multicore_api->pmapi_acquire = perl_multicore_nop;
*api_svp = api_sv;
}
/* call the real (or dummy) implementation now */
perlinterp_release ();
}
#endif
#endif