From 5aa29e88e998dc6cb66cd04dd6d8be5d187a0673 Mon Sep 17 00:00:00 2001
From: Tom Lane <tgl@sss.pgh.pa.us>
Date: Sun, 21 Sep 2003 17:57:21 +0000
Subject: [PATCH] Arrange to align shared disk buffers on at least 32-byte
 boundaries, not just MAXALIGN boundaries.  This makes a noticeable difference
 in the speed of transfers to and from kernel space, at least on recent
 Pentiums, and might help other CPUs too.  We should look at making this
 happen for local buffers and buffile.c too.  Patch from Manfred Spraul.

---
 src/backend/storage/ipc/shmem.c | 13 ++++++++++---
 src/include/c.h                 |  7 +++++--
 src/include/pg_config_manual.h  | 10 +++++++++-
 3 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index f2bdc3eb91d..0b80e0585ec 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/storage/ipc/shmem.c,v 1.70 2003/08/04 02:40:03 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/storage/ipc/shmem.c,v 1.71 2003/09/21 17:57:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -131,6 +131,7 @@ InitShmemAllocation(void *seghdr)
 void *
 ShmemAlloc(Size size)
 {
+	uint32		newStart;
 	uint32		newFree;
 	void	   *newSpace;
 
@@ -146,10 +147,16 @@ ShmemAlloc(Size size)
 
 	SpinLockAcquire(ShmemLock);
 
-	newFree = shmemseghdr->freeoffset + size;
+	newStart = shmemseghdr->freeoffset;
+
+	/* extra alignment for large requests, since they are probably buffers */
+	if (size >= BLCKSZ)
+		newStart = BUFFERALIGN(newStart);
+
+	newFree = newStart + size;
 	if (newFree <= shmemseghdr->totalsize)
 	{
-		newSpace = (void *) MAKE_PTR(shmemseghdr->freeoffset);
+		newSpace = (void *) MAKE_PTR(newStart);
 		shmemseghdr->freeoffset = newFree;
 	}
 	else
diff --git a/src/include/c.h b/src/include/c.h
index 02d47bfe461..934e976803c 100644
--- a/src/include/c.h
+++ b/src/include/c.h
@@ -12,7 +12,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: c.h,v 1.152 2003/08/04 02:40:10 momjian Exp $
+ * $Id: c.h,v 1.153 2003/09/21 17:57:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -522,13 +522,16 @@ typedef NameData *Name;
  * ----------------
  */
 
-#define TYPEALIGN(ALIGNVAL,LEN) (((long)(LEN) + (ALIGNVAL-1)) & ~(ALIGNVAL-1))
+#define TYPEALIGN(ALIGNVAL,LEN)  \
+	(((long) (LEN) + (ALIGNVAL-1)) & ~((long) (ALIGNVAL-1)))
 
 #define SHORTALIGN(LEN)			TYPEALIGN(ALIGNOF_SHORT, (LEN))
 #define INTALIGN(LEN)			TYPEALIGN(ALIGNOF_INT, (LEN))
 #define LONGALIGN(LEN)			TYPEALIGN(ALIGNOF_LONG, (LEN))
 #define DOUBLEALIGN(LEN)		TYPEALIGN(ALIGNOF_DOUBLE, (LEN))
 #define MAXALIGN(LEN)			TYPEALIGN(MAXIMUM_ALIGNOF, (LEN))
+/* MAXALIGN covers only built-in types, not buffers */
+#define BUFFERALIGN(LEN)		TYPEALIGN(ALIGNOF_BUFFER, (LEN))
 
 
 /* ----------------------------------------------------------------
diff --git a/src/include/pg_config_manual.h b/src/include/pg_config_manual.h
index 451ef351e65..98d357760dc 100644
--- a/src/include/pg_config_manual.h
+++ b/src/include/pg_config_manual.h
@@ -6,7 +6,7 @@
  * for developers.	If you edit any of these, be sure to do a *full*
  * rebuild (and an initdb if noted).
  *
- * $Id: pg_config_manual.h,v 1.5 2003/08/04 00:43:29 momjian Exp $
+ * $Id: pg_config_manual.h,v 1.6 2003/09/21 17:57:21 tgl Exp $
  *------------------------------------------------------------------------
  */
 
@@ -126,6 +126,14 @@
  */
 #define BITS_PER_BYTE		8
 
+/*
+ * Preferred alignment for disk I/O buffers.  On some CPUs, copies between
+ * user space and kernel space are significantly faster if the user buffer
+ * is aligned on a larger-than-MAXALIGN boundary.  Ideally this should be
+ * a platform-dependent value, but for now we just hard-wire it.
+ */
+#define ALIGNOF_BUFFER	32
+
 /*
  * Disable UNIX sockets for those operating system.
  */