On Mon, Dec 16, 2024 at 6:00 PM Alexander Lakhin <exclus...@gmail.com> wrote:
> It turned out that OpenBSD has semmns as low as 60 (see [4])
Whenever I run into this, or my Mac requires manual ipcrm to clean up
leaked SysV kernel junk, I rebase my patch for sema_kind = 'futex'.
Here it goes. It could be updated to support NetBSD I believe, but I
didn't try as its futex stuff came out later.
Then I remember why I didn't go anywhere with it. It triggers a
thought loop about flipping it all around: use futexes to implement
lwlocks directly in place, and get rid of semaphores completely, but
that involves a few rabbit holes and sub-projects. From memory:
classic r/w lock implementation on futexes is tricky but doable in the
portability constraints, futex fallback implementation even works
surprisingly well but has fun memory map sub-problems, actually lwlock
is not really a classic r/w lock as it has sprouted extra funky APIs
that lead the intrepid rabbit-holer to design an entirely different
new concurrency primitive that is really wanted for those users, a
couple of other places use raw semaphores directly namely procarray.c
and clog.c and if you stare at those for long you will be overwhelmed
with a desire to rewrite them, EOVERFLOW.
From 42054d64062da58e44a383d0ed0c1c6bb2ba88e1 Mon Sep 17 00:00:00 2001
From: Thomas Munro <thomas.munro@gmail.com>
Date: Sun, 24 Oct 2021 21:48:26 +1300
Subject: [PATCH 1/3] A basic API for futexes.
A thin wrapper for basic 32 bit futex wait and wake. Currently, it maps
to native support on Linux, DragonFlyBSD, FreeBSD, OpenBSD and macOS,
with detection via configure/meson.
NetBSD could probably be added, no investigated. Windows'
WaitOnAddress() can't because it only works between threads. A
latch-based backend-only fallback implementation is plausible.
---
configure | 4 +-
configure.ac | 5 +
meson.build | 5 +
src/backend/port/meson.build | 2 +-
src/include/pg_config.h.in | 15 +++
src/include/port/pg_futex.h | 171 +++++++++++++++++++++++++++++++++++
6 files changed, 199 insertions(+), 3 deletions(-)
create mode 100644 src/include/port/pg_futex.h
diff --git a/configure b/configure
index 518c33b73a9..6eb25178dab 100755
--- a/configure
+++ b/configure
@@ -13227,7 +13227,7 @@ fi
## Header files
##
-for ac_header in atomic.h copyfile.h execinfo.h getopt.h ifaddrs.h mbarrier.h sys/epoll.h sys/event.h sys/personality.h sys/prctl.h sys/procctl.h sys/signalfd.h sys/ucred.h termios.h ucred.h xlocale.h
+for ac_header in atomic.h copyfile.h execinfo.h getopt.h ifaddrs.h linux/futex.h mbarrier.h sys/epoll.h sys/event.h sys/futex.h sys/personality.h sys/prctl.h sys/procctl.h sys/signalfd.h sys/ucred.h sys/umtx.h termios.h ucred.h xlocale.h
do :
as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
ac_fn_c_check_header_mongrel "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default"
@@ -15044,7 +15044,7 @@ fi
LIBS_including_readline="$LIBS"
LIBS=`echo "$LIBS" | sed -e 's/-ledit//g' -e 's/-lreadline//g'`
-for ac_func in backtrace_symbols copyfile copy_file_range elf_aux_info getauxval getifaddrs getpeerucred inet_pton kqueue mbstowcs_l memset_s posix_fallocate ppoll pthread_is_threaded_np setproctitle setproctitle_fast strchrnul strsignal syncfs sync_file_range uselocale wcstombs_l
+for ac_func in __ulock_wait backtrace_symbols copyfile copy_file_range elf_aux_info getauxval getifaddrs getpeerucred inet_pton kqueue mbstowcs_l memset_s posix_fallocate ppoll pthread_is_threaded_np setproctitle setproctitle_fast strchrnul strsignal syncfs sync_file_range umtx_sleep uselocale wcstombs_l
do :
as_ac_var=`$as_echo "ac_cv_func_$ac_func" | $as_tr_sh`
ac_fn_c_check_func "$LINENO" "$ac_func" "$as_ac_var"
diff --git a/configure.ac b/configure.ac
index 247ae97fa4c..6b4f3e0f2e5 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1438,14 +1438,17 @@ AC_CHECK_HEADERS(m4_normalize([
execinfo.h
getopt.h
ifaddrs.h
+ linux/futex.h
mbarrier.h
sys/epoll.h
sys/event.h
+ sys/futex.h
sys/personality.h
sys/prctl.h
sys/procctl.h
sys/signalfd.h
sys/ucred.h
+ sys/umtx.h
termios.h
ucred.h
xlocale.h
@@ -1707,6 +1710,7 @@ LIBS_including_readline="$LIBS"
LIBS=`echo "$LIBS" | sed -e 's/-ledit//g' -e 's/-lreadline//g'`
AC_CHECK_FUNCS(m4_normalize([
+ __ulock_wait
backtrace_symbols
copyfile
copy_file_range
@@ -1727,6 +1731,7 @@ AC_CHECK_FUNCS(m4_normalize([
strsignal
syncfs
sync_file_range
+ umtx_sleep
uselocale
wcstombs_l
]))
diff --git a/meson.build b/meson.build
index e5ce437a5c7..5c9775f1a6e 100644
--- a/meson.build
+++ b/meson.build
@@ -2380,15 +2380,18 @@ header_checks = [
'execinfo.h',
'getopt.h',
'ifaddrs.h',
+ 'linux/futex.h',
'mbarrier.h',
'strings.h',
'sys/epoll.h',
'sys/event.h',
+ 'sys/futex.h',
'sys/personality.h',
'sys/prctl.h',
'sys/procctl.h',
'sys/signalfd.h',
'sys/ucred.h',
+ 'sys/umtx.h',
'termios.h',
'ucred.h',
'xlocale.h',
@@ -2611,6 +2614,7 @@ endif
# XXX: Might be worth conditioning some checks on the OS, to avoid doing
# unnecessary checks over and over, particularly on windows.
func_checks = [
+ ['__ulock_wait'],
['backtrace_symbols', {'dependencies': [execinfo_dep]}],
['clock_gettime', {'dependencies': [rt_dep], 'define': false}],
['copyfile'],
@@ -2654,6 +2658,7 @@ func_checks = [
['strsignal'],
['sync_file_range'],
['syncfs'],
+ ['umtx_sleep'],
['uselocale'],
['wcstombs_l'],
]
diff --git a/src/backend/port/meson.build b/src/backend/port/meson.build
index 7820e86016d..e34499bafb3 100644
--- a/src/backend/port/meson.build
+++ b/src/backend/port/meson.build
@@ -5,7 +5,7 @@ backend_sources += files(
)
-if cdata.has('USE_UNNAMED_POSIX_SEMAPHORES') or cdata.has('USE_NAMED_POSIX_SEMAPHORES')
+if cdata.has('USE_UNNAMED_POSIX_SEMAPHORES') or cdata.has('USE_NAMED_POSIX_SEMAPHORES') or cdata.has('USE_FUTEX_SEMAPHORES')
backend_sources += files('posix_sema.c')
endif
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 07b2f798abd..19cbf6e74ee 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -265,6 +265,9 @@
/* Define to 1 if you have the `zstd' library (-lzstd). */
#undef HAVE_LIBZSTD
+/* Define to 1 if you have the <linux/futex.h> header file. */
+#undef HAVE_LINUX_FUTEX_H
+
/* Define to 1 if you have the <mbarrier.h> header file. */
#undef HAVE_MBARRIER_H
@@ -418,6 +421,9 @@
/* Define to 1 if you have the <sys/event.h> header file. */
#undef HAVE_SYS_EVENT_H
+/* Define to 1 if you have the <sys/futex.h> header file. */
+#undef HAVE_SYS_FUTEX_H
+
/* Define to 1 if you have the <sys/personality.h> header file. */
#undef HAVE_SYS_PERSONALITY_H
@@ -439,6 +445,9 @@
/* Define to 1 if you have the <sys/ucred.h> header file. */
#undef HAVE_SYS_UCRED_H
+/* Define to 1 if you have the <sys/umtx.h> header file. */
+#undef HAVE_SYS_UMTX_H
+
/* Define to 1 if you have the <termios.h> header file. */
#undef HAVE_TERMIOS_H
@@ -448,6 +457,9 @@
/* Define to 1 if you have the <ucred.h> header file. */
#undef HAVE_UCRED_H
+/* Define to 1 if you have the `umtx_sleep' function. */
+#undef HAVE_UMTX_SLEEP
+
/* Define to 1 if the system has the type `union semun'. */
#undef HAVE_UNION_SEMUN
@@ -538,6 +550,9 @@
/* Define to 1 if your compiler understands _Static_assert. */
#undef HAVE__STATIC_ASSERT
+/* Define to 1 if you have the `__ulock_wait' function. */
+#undef HAVE___ULOCK_WAIT
+
/* Define as the maximum alignment requirement of any C data type. */
#undef MAXIMUM_ALIGNOF
diff --git a/src/include/port/pg_futex.h b/src/include/port/pg_futex.h
new file mode 100644
index 00000000000..e5ae05d1d5a
--- /dev/null
+++ b/src/include/port/pg_futex.h
@@ -0,0 +1,171 @@
+/*
+ * Minimal wrapper over futex APIs.
+ */
+
+#ifndef PG_FUTEX_H
+#define PG_FUTEX_H
+
+#if defined(HAVE_LINUX_FUTEX_H)
+
+/* https://man7.org/linux/man-pages/man2/futex.2.html */
+
+#include <linux/futex.h>
+#include <sys/syscall.h>
+
+#elif defined(HAVE_SYS_FUTEX_H)
+
+/* https://man.openbsd.org/futex, since OpenBSD 6.2. */
+
+#include <sys/time.h>
+#include <sys/futex.h>
+
+#elif defined(HAVE_SYS_UMTX_H)
+
+/* https://www.freebsd.org/cgi/man.cgi?query=_umtx_op */
+
+#include <sys/types.h>
+#include <sys/umtx.h>
+
+#elif defined(HAVE_UMTX_SLEEP)
+
+/* https://man.dragonflybsd.org/?command=umtx§ion=2 */
+
+#include <unistd.h>
+
+#elif defined(HAVE___ULOCK_WAIT)
+
+/*
+ * This interface is undocumented, but provided by libSystem.dylib since
+ * xnu-3789.1.32 (macOS 10.12, 2016) and is used by eg libc++.
+ *
+ * https://github.com/apple/darwin-xnu/blob/main/bsd/kern/sys_ulock.c
+ * https://github.com/apple/darwin-xnu/blob/main/bsd/sys/ulock.h
+ */
+
+#include <stdint.h>
+
+#define UL_COMPARE_AND_WAIT_SHARED 3
+#define ULF_WAKE_ALL 0x00000100
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+extern int __ulock_wait(uint32_t operation,
+ void *addr,
+ uint64_t value,
+ uint32_t timeout);
+extern int __ulock_wake(uint32_t operation,
+ void *addr,
+ uint64_t wake_value);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+/*
+ * Wait for someone to call pg_futex_wake() for the same address, with an
+ * initial check that the value pointed to by 'fut' matches 'value' and an
+ * optional timeout. Returns 0 when woken, and otherwise -1, with errno set to
+ * EAGAIN if the initial value check fails, and otherwise errors including
+ * EINTR, ETIMEDOUT and EFAULT.
+ */
+static int
+pg_futex_wait_u32(volatile void *fut,
+ uint32 value,
+ struct timespec *timeout)
+{
+#if defined(HAVE_LINUX_FUTEX_H)
+ if (syscall(SYS_futex, fut, FUTEX_WAIT, value, timeout, 0, 0) == 0)
+ return 0;
+#elif defined(HAVE_SYS_FUTEX_H)
+ if ((errno = futex((void *) fut, FUTEX_WAIT, (int) value, timeout, NULL)) == 0)
+ return 0;
+ if (errno == ECANCELED)
+ errno = EINTR;
+#elif defined(HAVE_SYS_UMTX_H)
+ if (_umtx_op((void *) fut, UMTX_OP_WAIT_UINT, value, 0, timeout) == 0)
+ return 0;
+#elif defined(HAVE_UMTX_SLEEP)
+ if (umtx_sleep((volatile const int *) fut,
+ (int) value,
+ timeout ? timeout->tv_sec * 1000000 + timeout->tv_nsec / 1000 : 0) == 0)
+ return 0;
+ if (errno == EBUSY)
+ errno = EAGAIN;
+#elif defined (HAVE___ULOCK_WAIT)
+ if (__ulock_wait(UL_COMPARE_AND_WAIT_SHARED,
+ (void *) fut,
+ value,
+ timeout ? timeout->tv_sec * 1000000 + timeout->tv_nsec / 1000 : 0) >= 0)
+ return 0;
+#else
+ /*
+ * If we wanted to simulate futexes on systems that don't have them, here
+ * we could add a link from our PGPROC struct to a shared memory hash
+ * table using "fut" (ie address) as the key, then compare *fut == value.
+ * If false, remove link and fail with EAGAIN. If true, sleep on proc
+ * latch. This wouldn't work for DSM segments; for those, we could search
+ * for matching DSM segment mappings in this process, and convert the key
+ * to { segment ID, offset }, just like kernels do internally to make
+ * inter-process futexes work on shared memory, but... ugh.
+ */
+ errno = ENOSYS;
+#endif
+
+ Assert(errno != 0);
+
+ return -1;
+}
+
+/*
+ * Wake up to nwaiters waiters that currently wait on the same address as
+ * 'fut'. Returns 0 on success, and -1 on failure, with errno set. Though
+ * some of these interfaces can tell us how many were woken, they can't all do
+ * that, so we'll hide that information.
+ */
+static int
+pg_futex_wake(volatile void *fut, int nwaiters)
+{
+#if defined(HAVE_LINUX_FUTEX_H)
+ if (syscall(SYS_futex, fut, FUTEX_WAKE, nwaiters, NULL, 0, 0) >= 0)
+ return 0;
+#elif defined(HAVE_SYS_FUTEX_H)
+ if (futex(fut, FUTEX_WAKE, nwaiters, NULL, NULL) >= 0)
+ return 0;
+#elif defined(HAVE_SYS_UMTX_H)
+ if (_umtx_op((void *) fut, UMTX_OP_WAKE, nwaiters, 0, 0) == 0)
+ return 0;
+#elif defined(HAVE_UMTX_SLEEP)
+ if (umtx_wakeup((volatile const int *) fut, nwaiters) == 0)
+ return 0;
+#elif defined (HAVE___ULOCK_WAIT)
+ if (__ulock_wake(UL_COMPARE_AND_WAIT_SHARED | (nwaiters > 1 ? ULF_WAKE_ALL : 0),
+ (void *) fut,
+ 0) >= 0)
+ return 0;
+ if (errno == ENOENT)
+ return 0;
+#else
+ /* No implementation available. */
+ errno = ENOSYS;
+#endif
+
+ Assert(errno != 0);
+
+ return -1;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* PG_FUTEX_H */
--
2.47.1
From 4614b62e6006f202a3a739175b73684e51c58914 Mon Sep 17 00:00:00 2001
From: Thomas Munro <thomas.munro@gmail.com>
Date: Sun, 24 Oct 2021 21:48:26 +1300
Subject: [PATCH 2/3] Add futex-based semaphore replacement.
Provide a drop-in replacement for POSIX unnamed semaphores using
futexes. This is useful for systems that don't have unnamed semaphores
at all, or don't have unnamed semaphores that work inter-process. This
should be more convenient because the alternatives require kernel
resources and configuration and can also leak in various scenarios.
---
configure | 16 +++++-
configure.ac | 16 +++++-
src/backend/port/posix_sema.c | 100 +++++++++++++++++++++++++++++++++-
src/include/pg_config.h.in | 3 +
4 files changed, 128 insertions(+), 7 deletions(-)
diff --git a/configure b/configure
index 6eb25178dab..acbd7cecaac 100755
--- a/configure
+++ b/configure
@@ -17632,6 +17632,10 @@ if test "$ac_res" != no; then :
fi
fi
+ if test x"$PREFERRED_SEMAPHORES" = x"FUTEX" ; then
+ # Need futex implementation for this
+ USE_FUTEX_SEMAPHORES=1
+ fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking which semaphore API to use" >&5
$as_echo_n "checking which semaphore API to use... " >&6; }
if test x"$USE_NAMED_POSIX_SEMAPHORES" = x"1" ; then
@@ -17648,11 +17652,19 @@ $as_echo "#define USE_UNNAMED_POSIX_SEMAPHORES 1" >>confdefs.h
SEMA_IMPLEMENTATION="src/backend/port/posix_sema.c"
sematype="unnamed POSIX"
else
+ if test x"$USE_FUTEX_SEMAPHORES" = x"1" ; then
+
+$as_echo "#define USE_FUTEX_SEMAPHORES 1" >>confdefs.h
+
+ SEMA_IMPLEMENTATION="src/backend/port/posix_sema.c"
+ sematype="futex"
+ else
$as_echo "#define USE_SYSV_SEMAPHORES 1" >>confdefs.h
- SEMA_IMPLEMENTATION="src/backend/port/sysv_sema.c"
- sematype="System V"
+ SEMA_IMPLEMENTATION="src/backend/port/sysv_sema.c"
+ sematype="System V"
+ fi
fi
fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $sematype" >&5
diff --git a/configure.ac b/configure.ac
index 6b4f3e0f2e5..9001c85a74e 100644
--- a/configure.ac
+++ b/configure.ac
@@ -2164,6 +2164,10 @@ if test "$PORTNAME" != "win32"; then
# Need sem_init for this
AC_SEARCH_LIBS(sem_init, [rt pthread], [USE_UNNAMED_POSIX_SEMAPHORES=1])
fi
+ if test x"$PREFERRED_SEMAPHORES" = x"FUTEX" ; then
+ # Need futex implementation for this
+ USE_FUTEX_SEMAPHORES=1
+ fi
AC_MSG_CHECKING([which semaphore API to use])
if test x"$USE_NAMED_POSIX_SEMAPHORES" = x"1" ; then
AC_DEFINE(USE_NAMED_POSIX_SEMAPHORES, 1, [Define to select named POSIX semaphores.])
@@ -2175,9 +2179,15 @@ if test "$PORTNAME" != "win32"; then
SEMA_IMPLEMENTATION="src/backend/port/posix_sema.c"
sematype="unnamed POSIX"
else
- AC_DEFINE(USE_SYSV_SEMAPHORES, 1, [Define to select SysV-style semaphores.])
- SEMA_IMPLEMENTATION="src/backend/port/sysv_sema.c"
- sematype="System V"
+ if test x"$USE_FUTEX_SEMAPHORES" = x"1" ; then
+ AC_DEFINE(USE_FUTEX_SEMAPHORES, 1, [Define to select futex semaphores.])
+ SEMA_IMPLEMENTATION="src/backend/port/posix_sema.c"
+ sematype="futex"
+ else
+ AC_DEFINE(USE_SYSV_SEMAPHORES, 1, [Define to select SysV-style semaphores.])
+ SEMA_IMPLEMENTATION="src/backend/port/sysv_sema.c"
+ sematype="System V"
+ fi
fi
fi
AC_MSG_RESULT([$sematype])
diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7e..88feec98d40 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -36,6 +36,10 @@
#include "storage/pg_sema.h"
#include "storage/shmem.h"
+#if defined(USE_FUTEX_SEMAPHORES)
+#include "port/atomics.h"
+#include "port/pg_futex.h"
+#endif
/* see file header comment */
#if defined(USE_NAMED_POSIX_SEMAPHORES) && defined(EXEC_BACKEND)
@@ -45,6 +49,9 @@
typedef union SemTPadded
{
sem_t pgsem;
+#if defined(USE_FUTEX_SEMAPHORES)
+ pg_atomic_uint32 futexsem;
+#endif
char pad[PG_CACHE_LINE_SIZE];
} SemTPadded;
@@ -70,6 +77,72 @@ static int nextSemKey; /* next name to try */
static void ReleaseSemaphores(int status, Datum arg);
+#ifdef USE_FUTEX_SEMAPHORES
+
+/*
+ * An implementation of POSIX unnamed semaphores in shared memory, for OSes
+ * that lack them but have futexes.
+ */
+
+/*
+ * Like standard sem_init() with pshared set to 1, meaning that it can work in
+ * shared memory.
+ */
+static void
+pg_futex_sem_init(pg_atomic_uint32 *fut, uint32 value)
+{
+ pg_atomic_init_u32(fut, value);
+}
+
+/*
+ * Like standard sem_post().
+ */
+static int
+pg_futex_sem_post(pg_atomic_uint32 *fut)
+{
+ pg_atomic_fetch_add_u32(fut, 1);
+
+ /*
+ * XXX If some bits held a waiter count, then the result of the above could
+ * be checked to see if we can skip this call. Currently we use semaphores
+ * as the slow path for lwlocks, so there is always expected to be a
+ * waiter.
+ */
+ return pg_futex_wake(fut, INT_MAX);
+}
+
+/*
+ * Like standard sem_wait().
+ */
+static int
+pg_futex_sem_wait(pg_atomic_uint32 *fut)
+{
+ uint32 value = 1;
+
+ /*
+ * The futex API takes void *, so there is no type checking or casting.
+ * Assert that pg_atomic_uint32 is really just a wrapped uint32_t as
+ * required by the kernel for 32 bit futex pre-check.
+ */
+ StaticAssertStmt(sizeof(*fut) == sizeof(uint32), "unexpected size");
+
+ while (!pg_atomic_compare_exchange_u32(fut, &value, value - 1))
+ {
+ if (value == 0)
+ {
+ /* Wait for someone else to move it above 0. */
+ if (pg_futex_wait_u32(fut, 0, NULL) < 0)
+ {
+ if (errno != EAGAIN)
+ return -1;
+ /* The value changed under our feet. Try again. */
+ }
+ }
+ }
+ return 0;
+}
+
+#endif
#ifdef USE_NAMED_POSIX_SEMAPHORES
@@ -124,7 +197,7 @@ PosixSemaphoreCreate(void)
return mySem;
}
-#else /* !USE_NAMED_POSIX_SEMAPHORES */
+#elif defined(USE_UNNAMED_POSIX_SEMAPHORES)
/*
* PosixSemaphoreCreate
@@ -139,6 +212,7 @@ PosixSemaphoreCreate(sem_t *sem)
}
#endif /* USE_NAMED_POSIX_SEMAPHORES */
+#ifndef USE_FUTEX_SEMAPHORES
/*
* PosixSemaphoreKill - removes a semaphore
@@ -156,6 +230,7 @@ PosixSemaphoreKill(sem_t *sem)
elog(LOG, "sem_destroy failed: %m");
#endif
}
+#endif
/*
@@ -238,18 +313,22 @@ PGReserveSemaphores(int maxSemas)
static void
ReleaseSemaphores(int status, Datum arg)
{
+#ifdef USE_NAMED_POSIX_SEMAPHORES
int i;
-#ifdef USE_NAMED_POSIX_SEMAPHORES
for (i = 0; i < numSems; i++)
PosixSemaphoreKill(mySemPointers[i]);
free(mySemPointers);
#endif
#ifdef USE_UNNAMED_POSIX_SEMAPHORES
+ int i;
+
for (i = 0; i < numSems; i++)
PosixSemaphoreKill(PG_SEM_REF(sharedSemas + i));
#endif
+
+ /* Futex-based semaphores have no kernel resource to clean up. */
}
/*
@@ -261,7 +340,9 @@ PGSemaphore
PGSemaphoreCreate(void)
{
PGSemaphore sema;
+#ifndef USE_FUTEX_SEMAPHORES
sem_t *newsem;
+#endif
/* Can't do this in a backend, because static state is postmaster's */
Assert(!IsUnderPostmaster);
@@ -274,6 +355,9 @@ PGSemaphoreCreate(void)
/* Remember new sema for ReleaseSemaphores */
mySemPointers[numSems] = newsem;
sema = (PGSemaphore) newsem;
+#elif defined(USE_FUTEX_SEMAPHORES)
+ sema = &sharedSemas[numSems];
+ pg_futex_sem_init(&sema->sem_padded.futexsem, 1);
#else
sema = &sharedSemas[numSems];
newsem = PG_SEM_REF(sema);
@@ -293,6 +377,9 @@ PGSemaphoreCreate(void)
void
PGSemaphoreReset(PGSemaphore sema)
{
+#ifdef USE_FUTEX_SEMAPHORES
+ pg_atomic_write_u32(&sema->sem_padded.futexsem, 0);
+#else
/*
* There's no direct API for this in POSIX, so we have to ratchet the
* semaphore down to 0 with repeated trywait's.
@@ -308,6 +395,7 @@ PGSemaphoreReset(PGSemaphore sema)
elog(FATAL, "sem_trywait failed: %m");
}
}
+#endif
}
/*
@@ -323,7 +411,11 @@ PGSemaphoreLock(PGSemaphore sema)
/* See notes in sysv_sema.c's implementation of PGSemaphoreLock. */
do
{
+#if defined(USE_FUTEX_SEMAPHORES)
+ errStatus = pg_futex_sem_wait(&sema->sem_padded.futexsem);
+#else
errStatus = sem_wait(PG_SEM_REF(sema));
+#endif
} while (errStatus < 0 && errno == EINTR);
if (errStatus < 0)
@@ -348,7 +440,11 @@ PGSemaphoreUnlock(PGSemaphore sema)
*/
do
{
+#if defined(USE_FUTEX_SEMAPHORES)
+ errStatus = pg_futex_sem_post(&sema->sem_padded.futexsem);
+#else
errStatus = sem_post(PG_SEM_REF(sema));
+#endif
} while (errStatus < 0 && errno == EINTR);
if (errStatus < 0)
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 19cbf6e74ee..3fe34e91e1b 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -669,6 +669,9 @@
/* Define to 1 to build with BSD Authentication support. (--with-bsd-auth) */
#undef USE_BSD_AUTH
+/* Define to select futex semaphores. */
+#undef USE_FUTEX_SEMAPHORES
+
/* Define to build with ICU support. (--with-icu) */
#undef USE_ICU
--
2.47.1
From aca7b842282f2f180ff497072079a9c40556f6fc Mon Sep 17 00:00:00 2001
From: Thomas Munro <thomas.munro@gmail.com>
Date: Thu, 26 Oct 2023 18:43:26 +1300
Subject: [PATCH 3/3] Use futex-based semaphores on macOS.
---
meson.build | 2 ++
src/template/darwin | 13 +------------
2 files changed, 3 insertions(+), 12 deletions(-)
diff --git a/meson.build b/meson.build
index 5c9775f1a6e..0e713f65a66 100644
--- a/meson.build
+++ b/meson.build
@@ -205,6 +205,8 @@ if host_system == 'cygwin'
mod_link_with_dir = 'libdir'
elif host_system == 'darwin'
+ sema_kind = 'futex'
+
dlsuffix = '.dylib'
library_path_var = 'DYLD_LIBRARY_PATH'
diff --git a/src/template/darwin b/src/template/darwin
index e8eb9390687..d3c78805401 100644
--- a/src/template/darwin
+++ b/src/template/darwin
@@ -14,17 +14,6 @@ fi
# Extra CFLAGS for code that will go into a shared library
CFLAGS_SL=""
-# Select appropriate semaphore support. Darwin 6.0 (macOS 10.2) and up
-# support System V semaphores; before that we have to use named POSIX
-# semaphores, which are less good for our purposes because they eat a
-# file descriptor per backend per max_connection slot.
-case $host_os in
- darwin[015].*)
- USE_NAMED_POSIX_SEMAPHORES=1
- ;;
- *)
- USE_SYSV_SEMAPHORES=1
- ;;
-esac
+USE_FUTEX_SEMAPHORES=1
DLSUFFIX=".dylib"
--
2.47.1
