mirror of https://github.com/postgres/postgres
Add basic NUMA awareness routines, using a minimal src/port/pg_numa.c portability wrapper and an optional build dependency, enabled by --with-libnuma configure option. For now this is Linux-only, other platforms may be supported later. A built-in SQL function pg_numa_available() allows checking NUMA support, i.e. that the server was built/linked with the NUMA library. The main function introduced is pg_numa_query_pages(), which allows determining the NUMA node for individual memory pages. Internally the function uses move_pages(2) syscall, as it allows batching, and is more efficient than get_mempolicy(2). Author: Jakub Wartak <jakub.wartak@enterprisedb.com> Co-authored-by: Bertrand Drouvot <bertranddrouvot.pg@gmail.com> Reviewed-by: Andres Freund <andres@anarazel.de> Reviewed-by: Álvaro Herrera <alvherre@alvh.no-ip.org> Reviewed-by: Tomas Vondra <tomas@vondra.me> Discussion: https://postgr.es/m/CAKZiRmxh6KWo0aqRqvmcoaX2jUxZYb4kGp3N%3Dq1w%2BDiH-696Xw%40mail.gmail.compull/210/head
Tomas Vondra
5 months ago
parent
17bcf4f545
commit
65c298f61f
@ -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 */ |
||||||
@ -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; |
||||||
|
} |
||||||
Loading…
Reference in new issue