diff options
Diffstat (limited to 'src')
-rw-r--r-- | src/Makefile.global.in | 6 | ||||
-rw-r--r-- | src/backend/utils/misc/guc_tables.c | 2 | ||||
-rw-r--r-- | src/include/catalog/catversion.h | 2 | ||||
-rw-r--r-- | src/include/catalog/pg_proc.dat | 4 | ||||
-rw-r--r-- | src/include/pg_config.h.in | 3 | ||||
-rw-r--r-- | src/include/port/pg_numa.h | 40 | ||||
-rw-r--r-- | src/include/storage/pg_shmem.h | 1 | ||||
-rw-r--r-- | src/makefiles/meson.build | 3 | ||||
-rw-r--r-- | src/port/Makefile | 1 | ||||
-rw-r--r-- | src/port/meson.build | 1 | ||||
-rw-r--r-- | src/port/pg_numa.c | 120 |
11 files changed, 180 insertions, 3 deletions
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 <unistd.h> + +#ifdef WIN32 +#include <windows.h> +#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 <numa.h> +#include <numaif.h> + +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; +} |