diff --git a/.cirrus.tasks.yml b/.cirrus.tasks.yml index 86a1fa9bbdb..6f4f5c674a1 100644 --- a/.cirrus.tasks.yml +++ b/.cirrus.tasks.yml @@ -471,6 +471,7 @@ task: --enable-cassert --enable-injection-points --enable-debug \ --enable-tap-tests --enable-nls \ --with-segsize-blocks=6 \ + --with-libnuma \ --with-liburing \ \ ${LINUX_CONFIGURE_FEATURES} \ @@ -523,6 +524,7 @@ task: -Dllvm=disabled \ --pkg-config-path /usr/lib/i386-linux-gnu/pkgconfig/ \ -DPERL=perl5.36-i386-linux-gnu \ + -Dlibnuma=disabled \ build-32 EOF diff --git a/configure b/configure index 8f4a5ab28ec..0936010718d 100755 --- a/configure +++ b/configure @@ -708,6 +708,9 @@ XML2_LIBS XML2_CFLAGS XML2_CONFIG with_libxml +LIBNUMA_LIBS +LIBNUMA_CFLAGS +with_libnuma LIBCURL_LIBS LIBCURL_CFLAGS with_libcurl @@ -872,6 +875,7 @@ with_liburing with_uuid with_ossp_uuid with_libcurl +with_libnuma with_libxml with_libxslt with_system_tzdata @@ -906,6 +910,8 @@ LIBURING_CFLAGS LIBURING_LIBS LIBCURL_CFLAGS LIBCURL_LIBS +LIBNUMA_CFLAGS +LIBNUMA_LIBS XML2_CONFIG XML2_CFLAGS XML2_LIBS @@ -1588,6 +1594,7 @@ Optional Packages: --with-uuid=LIB build contrib/uuid-ossp using LIB (bsd,e2fs,ossp) --with-ossp-uuid obsolete spelling of --with-uuid=ossp --with-libcurl build with libcurl support + --with-libnuma build with libnuma support --with-libxml build with XML support --with-libxslt use XSLT support when building contrib/xml2 --with-system-tzdata=DIR @@ -1629,6 +1636,10 @@ Some influential environment variables: C compiler flags for LIBCURL, overriding pkg-config LIBCURL_LIBS linker flags for LIBCURL, overriding pkg-config + LIBNUMA_CFLAGS + C compiler flags for LIBNUMA, overriding pkg-config + LIBNUMA_LIBS + linker flags for LIBNUMA, overriding pkg-config XML2_CONFIG path to xml2-config utility XML2_CFLAGS C compiler flags for XML2, overriding pkg-config XML2_LIBS linker flags for XML2, overriding pkg-config @@ -9063,6 +9074,182 @@ $as_echo "$as_me: WARNING: *** OAuth support tests require --with-python to run" fi +# +# libnuma +# +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to build with libnuma support" >&5 +$as_echo_n "checking whether to build with libnuma support... " >&6; } + + + +# Check whether --with-libnuma was given. +if test "${with_libnuma+set}" = set; then : + withval=$with_libnuma; + case $withval in + yes) + +$as_echo "#define USE_LIBNUMA 1" >>confdefs.h + + ;; + no) + : + ;; + *) + as_fn_error $? "no argument expected for --with-libnuma option" "$LINENO" 5 + ;; + esac + +else + with_libnuma=no + +fi + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_libnuma" >&5 +$as_echo "$with_libnuma" >&6; } + + +if test "$with_libnuma" = yes ; then + { $as_echo "$as_me:${as_lineno-$LINENO}: checking for numa_available in -lnuma" >&5 +$as_echo_n "checking for numa_available in -lnuma... " >&6; } +if ${ac_cv_lib_numa_numa_available+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_check_lib_save_LIBS=$LIBS +LIBS="-lnuma $LIBS" +cat confdefs.h - <<_ACEOF >conftest.$ac_ext +/* end confdefs.h. */ + +/* Override any GCC internal prototype to avoid an error. + Use char because int might match the return type of a GCC + builtin and then its argument prototype would still apply. */ +#ifdef __cplusplus +extern "C" +#endif +char numa_available (); +int +main () +{ +return numa_available (); + ; + return 0; +} +_ACEOF +if ac_fn_c_try_link "$LINENO"; then : + ac_cv_lib_numa_numa_available=yes +else + ac_cv_lib_numa_numa_available=no +fi +rm -f core conftest.err conftest.$ac_objext \ + conftest$ac_exeext conftest.$ac_ext +LIBS=$ac_check_lib_save_LIBS +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_lib_numa_numa_available" >&5 +$as_echo "$ac_cv_lib_numa_numa_available" >&6; } +if test "x$ac_cv_lib_numa_numa_available" = xyes; then : + cat >>confdefs.h <<_ACEOF +#define HAVE_LIBNUMA 1 +_ACEOF + + LIBS="-lnuma $LIBS" + +else + as_fn_error $? "library 'libnuma' is required for NUMA support" "$LINENO" 5 +fi + + +pkg_failed=no +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for numa" >&5 +$as_echo_n "checking for numa... " >&6; } + +if test -n "$LIBNUMA_CFLAGS"; then + pkg_cv_LIBNUMA_CFLAGS="$LIBNUMA_CFLAGS" + elif test -n "$PKG_CONFIG"; then + if test -n "$PKG_CONFIG" && \ + { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"numa\""; } >&5 + ($PKG_CONFIG --exists --print-errors "numa") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + pkg_cv_LIBNUMA_CFLAGS=`$PKG_CONFIG --cflags "numa" 2>/dev/null` + test "x$?" != "x0" && pkg_failed=yes +else + pkg_failed=yes +fi + else + pkg_failed=untried +fi +if test -n "$LIBNUMA_LIBS"; then + pkg_cv_LIBNUMA_LIBS="$LIBNUMA_LIBS" + elif test -n "$PKG_CONFIG"; then + if test -n "$PKG_CONFIG" && \ + { { $as_echo "$as_me:${as_lineno-$LINENO}: \$PKG_CONFIG --exists --print-errors \"numa\""; } >&5 + ($PKG_CONFIG --exists --print-errors "numa") 2>&5 + ac_status=$? + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; }; then + pkg_cv_LIBNUMA_LIBS=`$PKG_CONFIG --libs "numa" 2>/dev/null` + test "x$?" != "x0" && pkg_failed=yes +else + pkg_failed=yes +fi + else + pkg_failed=untried +fi + + + +if test $pkg_failed = yes; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + +if $PKG_CONFIG --atleast-pkgconfig-version 0.20; then + _pkg_short_errors_supported=yes +else + _pkg_short_errors_supported=no +fi + if test $_pkg_short_errors_supported = yes; then + LIBNUMA_PKG_ERRORS=`$PKG_CONFIG --short-errors --print-errors --cflags --libs "numa" 2>&1` + else + LIBNUMA_PKG_ERRORS=`$PKG_CONFIG --print-errors --cflags --libs "numa" 2>&1` + fi + # Put the nasty error message in config.log where it belongs + echo "$LIBNUMA_PKG_ERRORS" >&5 + + as_fn_error $? "Package requirements (numa) were not met: + +$LIBNUMA_PKG_ERRORS + +Consider adjusting the PKG_CONFIG_PATH environment variable if you +installed software in a non-standard prefix. + +Alternatively, you may set the environment variables LIBNUMA_CFLAGS +and LIBNUMA_LIBS to avoid the need to call pkg-config. +See the pkg-config man page for more details." "$LINENO" 5 +elif test $pkg_failed = untried; then + { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 +$as_echo "no" >&6; } + { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5 +$as_echo "$as_me: error: in \`$ac_pwd':" >&2;} +as_fn_error $? "The pkg-config script could not be found or is too old. Make sure it +is in your PATH or set the PKG_CONFIG environment variable to the full +path to pkg-config. + +Alternatively, you may set the environment variables LIBNUMA_CFLAGS +and LIBNUMA_LIBS to avoid the need to call pkg-config. +See the pkg-config man page for more details. + +To get pkg-config, see . +See \`config.log' for more details" "$LINENO" 5; } +else + LIBNUMA_CFLAGS=$pkg_cv_LIBNUMA_CFLAGS + LIBNUMA_LIBS=$pkg_cv_LIBNUMA_LIBS + { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 +$as_echo "yes" >&6; } + +fi +fi + # # XML # diff --git a/configure.ac b/configure.ac index fc5f7475d07..2a78cddd825 100644 --- a/configure.ac +++ b/configure.ac @@ -1053,6 +1053,20 @@ if test "$with_libcurl" = yes ; then fi +# +# libnuma +# +AC_MSG_CHECKING([whether to build with libnuma support]) +PGAC_ARG_BOOL(with, libnuma, no, [build with libnuma support], + [AC_DEFINE([USE_LIBNUMA], 1, [Define to build with NUMA support. (--with-libnuma)])]) +AC_MSG_RESULT([$with_libnuma]) +AC_SUBST(with_libnuma) + +if test "$with_libnuma" = yes ; then + AC_CHECK_LIB(numa, numa_available, [], [AC_MSG_ERROR([library 'libnuma' is required for NUMA support])]) + PKG_CHECK_MODULES(LIBNUMA, numa) +fi + # # XML # diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml index 0224f93733d..9ab070adffb 100644 --- a/doc/src/sgml/func.sgml +++ b/doc/src/sgml/func.sgml @@ -25143,6 +25143,19 @@ SELECT * FROM pg_ls_dir('.') WITH ORDINALITY AS t(ls,n); + + + + pg_numa_available + + pg_numa_available () + boolean + + + Returns true if the server has been compiled with NUMA support. + + + diff --git a/doc/src/sgml/installation.sgml b/doc/src/sgml/installation.sgml index cc28f041330..077bcc20759 100644 --- a/doc/src/sgml/installation.sgml +++ b/doc/src/sgml/installation.sgml @@ -1156,6 +1156,17 @@ build-postgresql: + + + + + Build with libnuma support for basic NUMA support. + Only supported on platforms for which the libnuma + library is implemented. + + + + @@ -2645,6 +2656,17 @@ ninja install + + + + + Build with libnuma support for basic NUMA support. + Only supported on platforms for which the libnuma + library is implemented. The default for this option is auto. + + + + diff --git a/meson.build b/meson.build index 27717ad8976..a1516e54529 100644 --- a/meson.build +++ b/meson.build @@ -943,6 +943,27 @@ else endif +############################################################### +# Library: libnuma +############################################################### + +libnumaopt = get_option('libnuma') +if not libnumaopt.disabled() + # via pkg-config + libnuma = dependency('numa', required: false) + if not libnuma.found() + libnuma = cc.find_library('numa', required: libnumaopt) + endif + if not cc.has_header('numa.h', dependencies: libnuma, required: libnumaopt) + libnuma = not_found_dep + endif + if libnuma.found() + cdata.set('USE_LIBNUMA', 1) + endif +else + libnuma = not_found_dep +endif + ############################################################### # Library: liburing @@ -3279,6 +3300,7 @@ backend_both_deps += [ icu_i18n, ldap, libintl, + libnuma, liburing, libxml, lz4, @@ -3935,6 +3957,7 @@ if meson.version().version_compare('>=0.57') 'icu': icu, 'ldap': ldap, 'libcurl': libcurl, + 'libnuma': libnuma, 'liburing': liburing, 'libxml': libxml, 'libxslt': libxslt, diff --git a/meson_options.txt b/meson_options.txt index dd7126da3a7..06bf5627d3c 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -106,6 +106,9 @@ option('libcurl', type : 'feature', value: 'auto', option('libedit_preferred', type: 'boolean', value: false, description: 'Prefer BSD Libedit over GNU Readline') +option('libnuma', type: 'feature', value: 'auto', + description: 'NUMA support') + option('liburing', type : 'feature', value: 'auto', description: 'io_uring support, for asynchronous I/O') diff --git a/src/Makefile.global.in b/src/Makefile.global.in index 737b2dd1869..6722fbdf365 100644 --- a/src/Makefile.global.in +++ b/src/Makefile.global.in @@ -196,6 +196,7 @@ with_gssapi = @with_gssapi@ with_krb_srvnam = @with_krb_srvnam@ with_ldap = @with_ldap@ with_libcurl = @with_libcurl@ +with_libnuma = @with_libnuma@ with_liburing = @with_liburing@ with_libxml = @with_libxml@ with_libxslt = @with_libxslt@ @@ -223,6 +224,9 @@ krb_srvtab = @krb_srvtab@ ICU_CFLAGS = @ICU_CFLAGS@ ICU_LIBS = @ICU_LIBS@ +LIBNUMA_CFLAGS = @LIBNUMA_CFLAGS@ +LIBNUMA_LIBS = @LIBNUMA_LIBS@ + LIBURING_CFLAGS = @LIBURING_CFLAGS@ LIBURING_LIBS = @LIBURING_LIBS@ @@ -250,7 +254,7 @@ CPP = @CPP@ CPPFLAGS = @CPPFLAGS@ PG_SYSROOT = @PG_SYSROOT@ -override CPPFLAGS := $(ICU_CFLAGS) $(LIBURING_CFLAGS) $(CPPFLAGS) +override CPPFLAGS := $(ICU_CFLAGS) $(LIBNUMA_CFLAGS) $(LIBURING_CFLAGS) $(CPPFLAGS) ifdef PGXS override CPPFLAGS := -I$(includedir_server) -I$(includedir_internal) $(CPPFLAGS) diff --git a/src/backend/utils/misc/guc_tables.c b/src/backend/utils/misc/guc_tables.c index f596fda568c..d54df555fba 100644 --- a/src/backend/utils/misc/guc_tables.c +++ b/src/backend/utils/misc/guc_tables.c @@ -566,7 +566,7 @@ static int ssl_renegotiation_limit; */ int huge_pages = HUGE_PAGES_TRY; int huge_page_size; -static int huge_pages_status = HUGE_PAGES_UNKNOWN; +int huge_pages_status = HUGE_PAGES_UNKNOWN; /* * These variables are all dummies that don't do anything, except in some diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h index 014aefc91a7..2a3d9dc8a7a 100644 --- a/src/include/catalog/catversion.h +++ b/src/include/catalog/catversion.h @@ -57,6 +57,6 @@ */ /* yyyymmddN */ -#define CATALOG_VERSION_NO 202504071 +#define CATALOG_VERSION_NO 202504072 #endif diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat index 5d5be8ba4e1..a9a9afb93c8 100644 --- a/src/include/catalog/pg_proc.dat +++ b/src/include/catalog/pg_proc.dat @@ -8542,6 +8542,10 @@ proargnames => '{name,off,size,allocated_size}', prosrc => 'pg_get_shmem_allocations' }, +{ oid => '4099', descr => 'Is NUMA support available?', + proname => 'pg_numa_available', provolatile => 's', prorettype => 'bool', + proargtypes => '', prosrc => 'pg_numa_available' }, + # memory context of local backend { oid => '2282', descr => 'information about all memory contexts of local backend', diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in index 9891b9b05c3..1af0b6316dd 100644 --- a/src/include/pg_config.h.in +++ b/src/include/pg_config.h.in @@ -689,6 +689,9 @@ /* Define to 1 to build with libcurl support. (--with-libcurl) */ #undef USE_LIBCURL +/* Define to 1 to build with NUMA support. (--with-libnuma) */ +#undef USE_LIBNUMA + /* Define to build with io_uring support. (--with-liburing) */ #undef USE_LIBURING diff --git a/src/include/port/pg_numa.h b/src/include/port/pg_numa.h new file mode 100644 index 00000000000..7e990d9f776 --- /dev/null +++ b/src/include/port/pg_numa.h @@ -0,0 +1,40 @@ +/*------------------------------------------------------------------------- + * + * pg_numa.h + * Basic NUMA portability routines + * + * + * Copyright (c) 2025, PostgreSQL Global Development Group + * + * IDENTIFICATION + * src/include/port/pg_numa.h + * + *------------------------------------------------------------------------- + */ +#ifndef PG_NUMA_H +#define PG_NUMA_H + +#include "fmgr.h" + +extern PGDLLIMPORT int pg_numa_init(void); +extern PGDLLIMPORT int pg_numa_query_pages(int pid, unsigned long count, void **pages, int *status); +extern PGDLLIMPORT int pg_numa_get_max_node(void); +extern PGDLLIMPORT Size pg_numa_get_pagesize(void); + +#ifdef USE_LIBNUMA + +/* + * This is required on Linux, before pg_numa_query_pages() as we + * need to page-fault before move_pages(2) syscall returns valid results. + */ +#define pg_numa_touch_mem_if_required(ro_volatile_var, ptr) \ + ro_volatile_var = *(volatile uint64 *) ptr + +#else + +#define pg_numa_touch_mem_if_required(ro_volatile_var, ptr) \ + do {} while(0) + +#endif + +#endif /* PG_NUMA_H */ diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h index b99ebc9e86f..5f7d4b83a60 100644 --- a/src/include/storage/pg_shmem.h +++ b/src/include/storage/pg_shmem.h @@ -45,6 +45,7 @@ typedef struct PGShmemHeader /* standard header for all Postgres shmem */ extern PGDLLIMPORT int shared_memory_type; extern PGDLLIMPORT int huge_pages; extern PGDLLIMPORT int huge_page_size; +extern PGDLLIMPORT int huge_pages_status; /* Possible values for huge_pages and huge_pages_status */ typedef enum diff --git a/src/makefiles/meson.build b/src/makefiles/meson.build index 46d8da070e8..55da678ec27 100644 --- a/src/makefiles/meson.build +++ b/src/makefiles/meson.build @@ -200,6 +200,8 @@ pgxs_empty = [ 'ICU_LIBS', + 'LIBNUMA_CFLAGS', 'LIBNUMA_LIBS', + 'LIBURING_CFLAGS', 'LIBURING_LIBS', ] @@ -232,6 +234,7 @@ pgxs_deps = { 'icu': icu, 'ldap': ldap, 'libcurl': libcurl, + 'libnuma': libnuma, 'liburing': liburing, 'libxml': libxml, 'libxslt': libxslt, diff --git a/src/port/Makefile b/src/port/Makefile index f11896440d5..4274949dfa4 100644 --- a/src/port/Makefile +++ b/src/port/Makefile @@ -45,6 +45,7 @@ OBJS = \ path.o \ pg_bitutils.o \ pg_localeconv_r.o \ + pg_numa.o \ pg_popcount_aarch64.o \ pg_popcount_avx512.o \ pg_strong_random.o \ diff --git a/src/port/meson.build b/src/port/meson.build index 48d2dfb7cf3..fc7b059fee5 100644 --- a/src/port/meson.build +++ b/src/port/meson.build @@ -8,6 +8,7 @@ pgport_sources = [ 'path.c', 'pg_bitutils.c', 'pg_localeconv_r.c', + 'pg_numa.c', 'pg_popcount_aarch64.c', 'pg_popcount_avx512.c', 'pg_strong_random.c', diff --git a/src/port/pg_numa.c b/src/port/pg_numa.c new file mode 100644 index 00000000000..5e2523cf798 --- /dev/null +++ b/src/port/pg_numa.c @@ -0,0 +1,120 @@ +/*------------------------------------------------------------------------- + * + * pg_numa.c + * Basic NUMA portability routines + * + * + * Copyright (c) 2025, PostgreSQL Global Development Group + * + * + * IDENTIFICATION + * src/port/pg_numa.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" +#include + +#ifdef WIN32 +#include +#endif + +#include "fmgr.h" +#include "miscadmin.h" +#include "port/pg_numa.h" +#include "storage/pg_shmem.h" + +/* + * At this point we provide support only for Linux thanks to libnuma, but in + * future support for other platforms e.g. Win32 or FreeBSD might be possible + * too. For Win32 NUMA APIs see + * https://learn.microsoft.com/en-us/windows/win32/procthread/numa-support + */ +#ifdef USE_LIBNUMA + +#include +#include + +Datum pg_numa_available(PG_FUNCTION_ARGS); + +/* libnuma requires initialization as per numa(3) on Linux */ +int +pg_numa_init(void) +{ + int r = numa_available(); + + return r; +} + +/* + * We use move_pages(2) syscall here - instead of get_mempolicy(2) - as the + * first one allows us to batch and query about many memory pages in one single + * giant system call that is way faster. + */ +int +pg_numa_query_pages(int pid, unsigned long count, void **pages, int *status) +{ + return numa_move_pages(pid, count, pages, NULL, status, 0); +} + +int +pg_numa_get_max_node(void) +{ + return numa_max_node(); +} + +#else + +Datum pg_numa_available(PG_FUNCTION_ARGS); + +/* Empty wrappers */ +int +pg_numa_init(void) +{ + /* We state that NUMA is not available */ + return -1; +} + +int +pg_numa_query_pages(int pid, unsigned long count, void **pages, int *status) +{ + return 0; +} + +int +pg_numa_get_max_node(void) +{ + return 0; +} + +#endif + +Datum +pg_numa_available(PG_FUNCTION_ARGS) +{ + PG_RETURN_BOOL(pg_numa_init() != -1); +} + +/* This should be used only after the server is started */ +Size +pg_numa_get_pagesize(void) +{ + Size os_page_size; +#ifdef WIN32 + SYSTEM_INFO sysinfo; + + GetSystemInfo(&sysinfo); + os_page_size = sysinfo.dwPageSize; +#else + os_page_size = sysconf(_SC_PAGESIZE); +#endif + + Assert(IsUnderPostmaster); + Assert(huge_pages_status != HUGE_PAGES_UNKNOWN); + + if (huge_pages_status == HUGE_PAGES_ON) + GetHugePageSize(&os_page_size, NULL); + + return os_page_size; +}