On Wed, Jun 14, 2023 at 12:40 PM John Naylor <john.nay...@enterprisedb.com>
wrote:
>
> On Sat, Nov 5, 2022 at 3:27 PM Andres Freund <and...@anarazel.de> wrote:
> > A real version would have to open /proc/self/maps and do this for at
least
> > postgres' r-xp mapping. We could do it for libraries too, if they're
suitably
> > aligned (both in memory and on-disk).
> For the postmaster, it should be simple to have a function that just
takes the address of itself, then parses /proc/self/maps to find the
boundaries within which it lies. I haven't thought about libraries much.
Though with just the postmaster it seems that would give us the biggest
bang for the buck?
Here's a start at that, trying with postmaster only. Unfortunately, I get
"MADV_COLLAPSE failed: Invalid argument". I tried different addresses with
no luck, and also got the same result with a small standalone program. I'm
on ext4, so I gather I don't need "cp --reflink=never" but tried it anyway.
Configuration looks normal by "grep HUGEPAGE /boot/config-$(uname
-r)". Maybe there's something obvious I'm missing?
--
John Naylor
EDB: http://www.enterprisedb.com
From ca38a370e866d27c8b51c83f8f18bdda1587b3df Mon Sep 17 00:00:00 2001
From: John Naylor <john.nay...@postgresql.org>
Date: Mon, 31 Oct 2022 15:24:29 +0700
Subject: [PATCH v2 2/2] Attmept to remap the .text segment into huge pages at
postmaster start
Use MADV_COLLAPSE advice, available since Linux kernel 6.1.
Andres Freund and John Naylor
---
src/backend/port/huge_page.c | 113 ++++++++++++++++++++++++++++
src/backend/port/meson.build | 4 +
src/backend/postmaster/postmaster.c | 7 ++
src/include/port/huge_page.h | 18 +++++
4 files changed, 142 insertions(+)
create mode 100644 src/backend/port/huge_page.c
create mode 100644 src/include/port/huge_page.h
diff --git a/src/backend/port/huge_page.c b/src/backend/port/huge_page.c
new file mode 100644
index 0000000000..92f87bb3c2
--- /dev/null
+++ b/src/backend/port/huge_page.c
@@ -0,0 +1,113 @@
+/*-------------------------------------------------------------------------
+ *
+ * huge_page.c
+ * Map .text segment of binary to huge pages
+ *
+ * TODO: better rationale for separate file if the huge page handling
+ * in sysv_shmem.c were moved here.
+ *
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/backend/port/huge_page.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include <sys/mman.h>
+
+#include "port/huge_page.h"
+#include "storage/fd.h"
+
+/*
+ * Collapse specified memory range to huge pages.
+ */
+static void
+CollapseRegionToHugePages(void *addr, size_t advlen)
+{
+#ifdef __linux__
+ size_t advlen_up;
+ int r;
+ void *r2;
+ const size_t bound = 1024*1024*2; // FIXME: x86
+
+ fprintf(stderr, "old advlen: %lx\n", advlen);
+ advlen_up = (advlen + bound - 1) & ~(bound - 1);
+
+ /*
+ * Increase size of mapping to cover the tailing padding to the next
+ * segment. Otherwise all the code in that range can't be put into
+ * a huge page (access in the non-mapped range needs to cause a fault,
+ * hence can't be in the huge page).
+ * XXX: Should proably assert that that space is actually zeroes.
+ */
+ r2 = mremap(addr, advlen, advlen_up, 0);
+ if (r2 == MAP_FAILED)
+ fprintf(stderr, "mremap failed: %m\n");
+ else if (r2 != addr)
+ fprintf(stderr, "mremap wrong addr: %m\n");
+ else
+ advlen = advlen_up;
+
+ fprintf(stderr, "new advlen: %lx\n", advlen);
+
+ /*
+ * The docs for MADV_COLLAPSE say there should be at least one page
+ * in the mapped space "for every eligible hugepage-aligned/sized
+ * region to be collapsed". I just forced that. But probably not
+ * necessary.
+ */
+ r = madvise(addr, advlen, MADV_WILLNEED);
+ if (r != 0)
+ fprintf(stderr, "MADV_WILLNEED failed: %m\n");
+
+ r = madvise(addr, advlen, MADV_POPULATE_READ);
+ if (r != 0)
+ fprintf(stderr, "MADV_POPULATE_READ failed: %m\n");
+
+ /*
+ * Make huge pages out of it. Requires at least linux 6.1. We could
+ * fall back to MADV_HUGEPAGE if it fails, but it doesn't do all that
+ * much in older kernels.
+ */
+ r = madvise(addr, advlen, MADV_COLLAPSE);
+ if (r != 0)
+ {
+ fprintf(stderr, "MADV_COLLAPSE failed: %m\n");
+
+ r = madvise(addr, advlen, MADV_HUGEPAGE);
+ if (r != 0)
+ fprintf(stderr, "MADV_HUGEPAGE failed: %m\n");
+ }
+#endif
+}
+
+/* Map the postgres .text segment into huge pages. */
+void
+MapStaticCodeToLargePages(void)
+{
+#ifdef __linux__
+ FILE *fp = AllocateFile("/proc/self/maps", "r");
+ char buf[128]; // got this from code reading /proc/meminfo -- enough?
+ uintptr_t addr;
+ uintptr_t end;
+ void * self = &MapStaticCodeToLargePages;
+
+ if (fp)
+ {
+ while (fgets(buf, sizeof(buf), fp))
+ {
+ if (sscanf(buf, "%lx-%lx", &addr, &end) == 2 &&
+ addr <= (uintptr_t) self && (uintptr_t) self < end)
+ {
+ fprintf(stderr, "self: %p start: %lx end: %lx\n", self, addr, end);
+ CollapseRegionToHugePages((void *) addr, end - addr);
+ break;
+ }
+ }
+ FreeFile(fp);
+ }
+#endif
+}
diff --git a/src/backend/port/meson.build b/src/backend/port/meson.build
index 8fa68a88aa..af4d0c7bb7 100644
--- a/src/backend/port/meson.build
+++ b/src/backend/port/meson.build
@@ -25,6 +25,10 @@ if cdata.has('USE_WIN32_SHARED_MEMORY')
backend_sources += files('win32_shmem.c')
endif
+if host_system == 'linux'
+ backend_sources += files('huge_page.c')
+endif
+
if host_system == 'windows'
subdir('win32')
endif
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 4c49393fc5..216e8c5730 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -106,6 +106,7 @@
#include "pg_getopt.h"
#include "pgstat.h"
#include "port/pg_bswap.h"
+#include "port/huge_page.h"
#include "postmaster/autovacuum.h"
#include "postmaster/auxprocess.h"
#include "postmaster/bgworker_internals.h"
@@ -1007,6 +1008,12 @@ PostmasterMain(int argc, char *argv[])
*/
process_shared_preload_libraries();
+ /*
+ * Try to map the binary code to huge pages. We do this just after
+ * any shared libraries are preloaded for future-proofing.
+ */
+ MapStaticCodeToLargePages();
+
/*
* Initialize SSL library, if specified.
*/
diff --git a/src/include/port/huge_page.h b/src/include/port/huge_page.h
new file mode 100644
index 0000000000..171819dd53
--- /dev/null
+++ b/src/include/port/huge_page.h
@@ -0,0 +1,18 @@
+/*-------------------------------------------------------------------------
+ *
+ * large_page.h
+ * Map .text segment of binary to huge pages
+ *
+ * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/port/large_page.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef LARGE_PAGE_H
+#define LARGE_PAGE_H
+
+extern void MapStaticCodeToLargePages(void);
+
+#endif /* LARGE_PAGE_H */
--
2.40.1
From e8a0c8633e969ad45eef82b40460df6552e6e550 Mon Sep 17 00:00:00 2001
From: John Naylor <john.nay...@postgresql.org>
Date: Fri, 2 Dec 2022 14:58:21 +0700
Subject: [PATCH v2 1/2] Align loadable segments to 2MB boundaries on Linux
Prerequsite for using huge pages for the .text section
on that platform.
TODO: autoconf support
Andres Freund and John Naylor
---
meson.build | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/meson.build b/meson.build
index 16b2e86646..32af8bf5c3 100644
--- a/meson.build
+++ b/meson.build
@@ -248,6 +248,13 @@ elif host_system == 'freebsd'
elif host_system == 'linux'
sema_kind = 'unnamed_posix'
cppflags += '-D_GNU_SOURCE'
+ # Align the loadable segments to 2MB boundaries to support remapping to
+ # huge pages.
+ ldflags += cc.get_supported_link_arguments([
+ '-Wl,-zmax-page-size=0x200000',
+ '-Wl,-zcommon-page-size=0x200000',
+ '-Wl,-zseparate-loadable-segments'
+ ])
elif host_system == 'netbsd'
# We must resolve all dynamic linking in the core server at program start.
--
2.40.1
