Introduce PG_IO_ALIGN_SIZE and align all I/O buffers.

In order to have the option to use O_DIRECT/FILE_FLAG_NO_BUFFERING in a
later commit, we need the addresses of user space buffers to be well
aligned.  The exact requirements vary by OS and file system (typically
sectors and/or memory pages).  The address alignment size is set to
4096, which is enough for currently known systems: it matches modern
sectors and common memory page size.  There is no standard governing
O_DIRECT's requirements so we might eventually have to reconsider this
with more information from the field or future systems.

Aligning I/O buffers on memory pages is also known to improve regular
buffered I/O performance.

Three classes of I/O buffers for regular data pages are adjusted:
(1) Heap buffers are now allocated with the new palloc_aligned() or
MemoryContextAllocAligned() functions introduced by commit 439f617.
(2) Stack buffers now use a new struct PGIOAlignedBlock to respect
PG_IO_ALIGN_SIZE, if possible with this compiler.  (3) The buffer
pool is also aligned in shared memory.

WAL buffers were already aligned on XLOG_BLCKSZ.  It's possible for
XLOG_BLCKSZ to be configured smaller than PG_IO_ALIGNED_SIZE and thus
for O_DIRECT WAL writes to fail to be well aligned, but that's a
pre-existing condition and will be addressed by a later commit.

BufFiles are not yet addressed (there's no current plan to use O_DIRECT
for those, but they could potentially get some incidental speedup even
in plain buffered I/O operations through better alignment).

If we can't align stack objects suitably using the compiler extensions
we know about, we disable the use of O_DIRECT by setting PG_O_DIRECT to
0.  This avoids the need to consider systems that have O_DIRECT but
can't align stack objects the way we want; such systems could in theory
be supported with more work but we don't currently know of any such
machines, so it's easier to pretend there is no O_DIRECT support
instead.  That's an existing and tested class of system.

Add assertions that all buffers passed into smgrread(), smgrwrite() and
smgrextend() are correctly aligned, unless PG_O_DIRECT is 0 (= stack
alignment tricks may be unavailable) or the block size has been set too
small to allow arrays of buffers to be all aligned.

Author: Thomas Munro <thomas.munro@gmail.com>
Author: Andres Freund <andres@anarazel.de>
Reviewed-by: Justin Pryzby <pryzby@telsasoft.com>
Discussion: https://postgr.es/m/CA+hUKGK1X532hYqJ_MzFWt0n1zt8trz980D79WbjwnT-yYLZpg@mail.gmail.com

Author: macdice

contrib/bloom/blinsert.c

@@ -166,7 +166,7 @@ blbuildempty(Relation index)
 	Page		metapage;
 
 	/* Construct metapage. */
-	metapage = (Page) palloc(BLCKSZ);
+	metapage = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 	BloomFillMetapage(index, metapage);
 
 	/*

contrib/pg_prewarm/pg_prewarm.c

@@ -36,7 +36,7 @@ typedef enum
 	PREWARM_BUFFER
 } PrewarmType;
 
-static PGAlignedBlock blockbuffer;
+static PGIOAlignedBlock blockbuffer;
 
 /*
  * pg_prewarm(regclass, mode text, fork text,

src/backend/access/gist/gistbuild.c

@@ -415,7 +415,7 @@ gist_indexsortbuild(GISTBuildState *state)
 	 * Write an empty page as a placeholder for the root page. It will be
 	 * replaced with the real root page at the end.
 	 */
-	page = palloc0(BLCKSZ);
+	page = palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, MCXT_ALLOC_ZERO);
 	smgrextend(RelationGetSmgr(state->indexrel), MAIN_FORKNUM, GIST_ROOT_BLKNO,
 			   page, true);
 	state->pages_allocated++;
@@ -509,7 +509,8 @@ gist_indexsortbuild_levelstate_add(GISTBuildState *state,
 			levelstate->current_page++;
 
 		if (levelstate->pages[levelstate->current_page] == NULL)
-			levelstate->pages[levelstate->current_page] = palloc(BLCKSZ);
+			levelstate->pages[levelstate->current_page] =
+				palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 
 		newPage = levelstate->pages[levelstate->current_page];
 		gistinitpage(newPage, old_page_flags);
@@ -579,7 +580,7 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
 
 		/* Create page and copy data */
 		data = (char *) (dist->list);
-		target = palloc0(BLCKSZ);
+		target = palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, MCXT_ALLOC_ZERO);
 		gistinitpage(target, isleaf ? F_LEAF : 0);
 		for (int i = 0; i < dist->block.num; i++)
 		{
@@ -630,7 +631,7 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state,
 		if (parent == NULL)
 		{
 			parent = palloc0(sizeof(GistSortedBuildLevelState));
-			parent->pages[0] = (Page) palloc(BLCKSZ);
+			parent->pages[0] = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 			parent->parent = NULL;
 			gistinitpage(parent->pages[0], 0);
 

src/backend/access/hash/hashpage.c

@@ -992,7 +992,7 @@ static bool
 _hash_alloc_buckets(Relation rel, BlockNumber firstblock, uint32 nblocks)
 {
 	BlockNumber lastblock;
-	PGAlignedBlock zerobuf;
+	PGIOAlignedBlock zerobuf;
 	Page		page;
 	HashPageOpaque ovflopaque;
 

src/backend/access/heap/rewriteheap.c

@@ -255,7 +255,7 @@ begin_heap_rewrite(Relation old_heap, Relation new_heap, TransactionId oldest_xm
 
 	state->rs_old_rel = old_heap;
 	state->rs_new_rel = new_heap;
-	state->rs_buffer = (Page) palloc(BLCKSZ);
+	state->rs_buffer = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 	/* new_heap needn't be empty, just locked */
 	state->rs_blockno = RelationGetNumberOfBlocks(new_heap);
 	state->rs_buffer_valid = false;

src/backend/access/nbtree/nbtree.c

@@ -154,7 +154,7 @@ btbuildempty(Relation index)
 	Page		metapage;
 
 	/* Construct metapage. */
-	metapage = (Page) palloc(BLCKSZ);
+	metapage = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 	_bt_initmetapage(metapage, P_NONE, 0, _bt_allequalimage(index, false));
 
 	/*

src/backend/access/nbtree/nbtsort.c

@@ -619,7 +619,7 @@ _bt_blnewpage(uint32 level)
 	Page		page;
 	BTPageOpaque opaque;
 
-	page = (Page) palloc(BLCKSZ);
+	page = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 
 	/* Zero the page and set up standard page header info */
 	_bt_pageinit(page, BLCKSZ);
@@ -660,7 +660,9 @@ _bt_blwritepage(BTWriteState *wstate, Page page, BlockNumber blkno)
 	while (blkno > wstate->btws_pages_written)
 	{
 		if (!wstate->btws_zeropage)
-			wstate->btws_zeropage = (Page) palloc0(BLCKSZ);
+			wstate->btws_zeropage = (Page) palloc_aligned(BLCKSZ,
+														  PG_IO_ALIGN_SIZE,
+														  MCXT_ALLOC_ZERO);
 		/* don't set checksum for all-zero page */
 		smgrextend(RelationGetSmgr(wstate->index), MAIN_FORKNUM,
 				   wstate->btws_pages_written++,
@@ -1170,7 +1172,7 @@ _bt_uppershutdown(BTWriteState *wstate, BTPageState *state)
 	 * set to point to "P_NONE").  This changes the index to the "valid" state
 	 * by filling in a valid magic number in the metapage.
 	 */
-	metapage = (Page) palloc(BLCKSZ);
+	metapage = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 	_bt_initmetapage(metapage, rootblkno, rootlevel,
 					 wstate->inskey->allequalimage);
 	_bt_blwritepage(wstate, metapage, BTREE_METAPAGE);

src/backend/access/spgist/spginsert.c

@@ -158,7 +158,7 @@ spgbuildempty(Relation index)
 	Page		page;
 
 	/* Construct metapage. */
-	page = (Page) palloc(BLCKSZ);
+	page = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0);
 	SpGistInitMetapage(page);
 
 	/*

src/backend/access/transam/generic_xlog.c

@@ -58,14 +58,17 @@ typedef struct
 	char		delta[MAX_DELTA_SIZE];	/* delta between page images */
 } PageData;
 
-/* State of generic xlog record construction */
+/*
+ * State of generic xlog record construction.  Must be allocated at an I/O
+ * aligned address.
+ */
 struct GenericXLogState
 {
+	/* Page images (properly aligned, must be first) */
+	PGIOAlignedBlock images[MAX_GENERIC_XLOG_PAGES];
 	/* Info about each page, see above */
 	PageData	pages[MAX_GENERIC_XLOG_PAGES];
 	bool		isLogged;
-	/* Page images (properly aligned) */
-	PGAlignedBlock images[MAX_GENERIC_XLOG_PAGES];
 };
 
 static void writeFragment(PageData *pageData, OffsetNumber offset,
@@ -269,7 +272,9 @@ GenericXLogStart(Relation relation)
 	GenericXLogState *state;
 	int			i;
 
-	state = (GenericXLogState *) palloc(sizeof(GenericXLogState));
+	state = (GenericXLogState *) palloc_aligned(sizeof(GenericXLogState),
+												PG_IO_ALIGN_SIZE,
+												0);
 	state->isLogged = RelationNeedsWAL(relation);
 
 	for (i = 0; i < MAX_GENERIC_XLOG_PAGES; i++)

src/backend/access/transam/xlog.c

@@ -4506,7 +4506,7 @@ XLOGShmemSize(void)
 	/* xlblocks array */
 	size = add_size(size, mul_size(sizeof(XLogRecPtr), XLOGbuffers));
 	/* extra alignment padding for XLOG I/O buffers */
-	size = add_size(size, XLOG_BLCKSZ);
+	size = add_size(size, Max(XLOG_BLCKSZ, PG_IO_ALIGN_SIZE));
 	/* and the buffers themselves */
 	size = add_size(size, mul_size(XLOG_BLCKSZ, XLOGbuffers));
 

src/backend/catalog/storage.c

@@ -451,7 +451,7 @@ void
 RelationCopyStorage(SMgrRelation src, SMgrRelation dst,
 					ForkNumber forkNum, char relpersistence)
 {
-	PGAlignedBlock buf;
+	PGIOAlignedBlock buf;
 	Page		page;
 	bool		use_wal;
 	bool		copying_initfork;

src/backend/storage/buffer/buf_init.c

@@ -78,9 +78,12 @@ InitBufferPool(void)
 						NBuffers * sizeof(BufferDescPadded),
 						&foundDescs);
 
+	/* Align buffer pool on IO page size boundary. */
 	BufferBlocks = (char *)
-		ShmemInitStruct("Buffer Blocks",
-						NBuffers * (Size) BLCKSZ, &foundBufs);
+		TYPEALIGN(PG_IO_ALIGN_SIZE,
+				  ShmemInitStruct("Buffer Blocks",
+								  NBuffers * (Size) BLCKSZ + PG_IO_ALIGN_SIZE,
+								  &foundBufs));
 
 	/* Align condition variables to cacheline boundary. */
 	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
@@ -163,7 +166,8 @@ BufferShmemSize(void)
 	/* to allow aligning buffer descriptors */
 	size = add_size(size, PG_CACHE_LINE_SIZE);
 
-	/* size of data pages */
+	/* size of data pages, plus alignment padding */
+	size = add_size(size, PG_IO_ALIGN_SIZE);
 	size = add_size(size, mul_size(NBuffers, BLCKSZ));
 
 	/* size of stuff controlled by freelist.c */

src/backend/storage/buffer/bufmgr.c

@@ -4250,7 +4250,7 @@ RelationCopyStorageUsingBuffer(RelFileLocator srclocator,
 	bool		use_wal;
 	BlockNumber nblocks;
 	BlockNumber blkno;
-	PGAlignedBlock buf;
+	PGIOAlignedBlock buf;
 	BufferAccessStrategy bstrategy_src;
 	BufferAccessStrategy bstrategy_dst;
 

src/backend/storage/buffer/localbuf.c

@@ -744,8 +744,11 @@ GetLocalBufferStorage(void)
 		/* And don't overflow MaxAllocSize, either */
 		num_bufs = Min(num_bufs, MaxAllocSize / BLCKSZ);
 
-		cur_block = (char *) MemoryContextAlloc(LocalBufferContext,
-												num_bufs * BLCKSZ);
+		/* Buffers should be I/O aligned. */
+		cur_block = (char *)
+			TYPEALIGN(PG_IO_ALIGN_SIZE,
+					  MemoryContextAlloc(LocalBufferContext,
+										 num_bufs * BLCKSZ + PG_IO_ALIGN_SIZE));
 		next_buf_in_block = 0;
 		num_bufs_in_block = num_bufs;
 	}

src/backend/storage/file/buffile.c

@@ -95,6 +95,12 @@ struct BufFile
 	off_t		curOffset;		/* offset part of current pos */
 	int			pos;			/* next read/write position in buffer */
 	int			nbytes;			/* total # of valid bytes in buffer */
+
+	/*
+	 * XXX Should ideally us PGIOAlignedBlock, but might need a way to avoid
+	 * wasting per-file alignment padding when some users create many
+	 * files.
+	 */
 	PGAlignedBlock buffer;
 };
 

src/backend/storage/page/bufpage.c

@@ -1522,7 +1522,10 @@ PageSetChecksumCopy(Page page, BlockNumber blkno)
 	 * and second to avoid wasting space in processes that never call this.
 	 */
 	if (pageCopy == NULL)
-		pageCopy = MemoryContextAlloc(TopMemoryContext, BLCKSZ);
+		pageCopy = MemoryContextAllocAligned(TopMemoryContext,
+											 BLCKSZ,
+											 PG_IO_ALIGN_SIZE,
+											 0);
 
 	memcpy(pageCopy, (char *) page, BLCKSZ);
 	((PageHeader) pageCopy)->pd_checksum = pg_checksum_page(pageCopy, blkno);

src/backend/storage/smgr/md.c

@@ -453,6 +453,10 @@ mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	int			nbytes;
 	MdfdVec    *v;
 
+	/* If this build supports direct I/O, the buffer must be I/O aligned. */
+	if (PG_O_DIRECT != 0 && PG_IO_ALIGN_SIZE <= BLCKSZ)
+		Assert((uintptr_t) buffer == TYPEALIGN(PG_IO_ALIGN_SIZE, buffer));
+
 	/* This assert is too expensive to have on normally ... */
 #ifdef CHECK_WRITE_VS_EXTEND
 	Assert(blocknum >= mdnblocks(reln, forknum));
@@ -783,6 +787,10 @@ mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	int			nbytes;
 	MdfdVec    *v;
 
+	/* If this build supports direct I/O, the buffer must be I/O aligned. */
+	if (PG_O_DIRECT != 0 && PG_IO_ALIGN_SIZE <= BLCKSZ)
+		Assert((uintptr_t) buffer == TYPEALIGN(PG_IO_ALIGN_SIZE, buffer));
+
 	TRACE_POSTGRESQL_SMGR_MD_READ_START(forknum, blocknum,
 										reln->smgr_rlocator.locator.spcOid,
 										reln->smgr_rlocator.locator.dbOid,
@@ -848,6 +856,10 @@ mdwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	int			nbytes;
 	MdfdVec    *v;
 
+	/* If this build supports direct I/O, the buffer must be I/O aligned. */
+	if (PG_O_DIRECT != 0 && PG_IO_ALIGN_SIZE <= BLCKSZ)
+		Assert((uintptr_t) buffer == TYPEALIGN(PG_IO_ALIGN_SIZE, buffer));
+
 	/* This assert is too expensive to have on normally ... */
 #ifdef CHECK_WRITE_VS_EXTEND
 	Assert(blocknum < mdnblocks(reln, forknum));
@@ -1429,7 +1441,8 @@ _mdfd_getseg(SMgrRelation reln, ForkNumber forknum, BlockNumber blkno,
 			 */
 			if (nblocks < ((BlockNumber) RELSEG_SIZE))
 			{
-				char	   *zerobuf = palloc0(BLCKSZ);
+				char	   *zerobuf = palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE,
+													 MCXT_ALLOC_ZERO);
 
 				mdextend(reln, forknum,
 						 nextsegno * ((BlockNumber) RELSEG_SIZE) - 1,

src/backend/utils/sort/logtape.c

@@ -252,7 +252,7 @@ ltsWriteBlock(LogicalTapeSet *lts, long blocknum, const void *buffer)
 	 */
 	while (blocknum > lts->nBlocksWritten)
 	{
-		PGAlignedBlock zerobuf;
+		PGIOAlignedBlock zerobuf;
 
 		MemSet(zerobuf.data, 0, sizeof(zerobuf));
 

src/bin/pg_checksums/pg_checksums.c

@@ -183,7 +183,7 @@ skipfile(const char *fn)
 static void
 scan_file(const char *fn, int segmentno)
 {
-	PGAlignedBlock buf;
+	PGIOAlignedBlock buf;
 	PageHeader	header = (PageHeader) buf.data;
 	int			f;
 	BlockNumber blockno;

src/bin/pg_rewind/local_source.c

@@ -77,7 +77,7 @@ static void
 local_queue_fetch_file(rewind_source *source, const char *path, size_t len)
 {
 	const char *datadir = ((local_source *) source)->datadir;
-	PGAlignedBlock buf;
+	PGIOAlignedBlock buf;
 	char		srcpath[MAXPGPATH];
 	int			srcfd;
 	size_t		written_len;
@@ -129,7 +129,7 @@ local_queue_fetch_range(rewind_source *source, const char *path, off_t off,
 						size_t len)
 {
 	const char *datadir = ((local_source *) source)->datadir;
-	PGAlignedBlock buf;
+	PGIOAlignedBlock buf;
 	char		srcpath[MAXPGPATH];
 	int			srcfd;
 	off_t		begin = off;

src/bin/pg_upgrade/file.c

@@ -178,8 +178,8 @@ rewriteVisibilityMap(const char *fromfile, const char *tofile,
 {
 	int			src_fd;
 	int			dst_fd;
-	PGAlignedBlock buffer;
-	PGAlignedBlock new_vmbuf;
+	PGIOAlignedBlock buffer;
+	PGIOAlignedBlock new_vmbuf;
 	ssize_t		totalBytesRead = 0;
 	ssize_t		src_filesize;
 	int			rewriteVmBytesPerPage;

src/common/file_utils.c

@@ -540,8 +540,8 @@ pg_pwritev_with_retry(int fd, const struct iovec *iov, int iovcnt, off_t offset)
 ssize_t
 pg_pwrite_zeros(int fd, size_t size, off_t offset)
 {
-	static const PGAlignedBlock zbuffer = {{0}};	/* worth BLCKSZ */
-	void	   *zerobuf_addr = unconstify(PGAlignedBlock *, &zbuffer)->data;
+	static const PGIOAlignedBlock zbuffer = {{0}};	/* worth BLCKSZ */
+	void	   *zerobuf_addr = unconstify(PGIOAlignedBlock *, &zbuffer)->data;
 	struct iovec iov[PG_IOV_MAX];
 	size_t		remaining_size = size;
 	ssize_t		total_written = 0;

src/include/c.h

@@ -1119,14 +1119,11 @@ extern void ExceptionalCondition(const char *conditionName,
 
 /*
  * Use this, not "char buf[BLCKSZ]", to declare a field or local variable
- * holding a page buffer, if that page might be accessed as a page and not
- * just a string of bytes.  Otherwise the variable might be under-aligned,
- * causing problems on alignment-picky hardware.  (In some places, we use
- * this to declare buffers even though we only pass them to read() and
- * write(), because copying to/from aligned buffers is usually faster than
- * using unaligned buffers.)  We include both "double" and "int64" in the
- * union to ensure that the compiler knows the value must be MAXALIGN'ed
- * (cf. configure's computation of MAXIMUM_ALIGNOF).
+ * holding a page buffer, if that page might be accessed as a page.  Otherwise
+ * the variable might be under-aligned, causing problems on alignment-picky
+ * hardware.  We include both "double" and "int64" in the union to ensure that
+ * the compiler knows the value must be MAXALIGN'ed (cf. configure's
+ * computation of MAXIMUM_ALIGNOF).
  */
 typedef union PGAlignedBlock
 {
@@ -1135,9 +1132,30 @@ typedef union PGAlignedBlock
 	int64		force_align_i64;
 } PGAlignedBlock;
 
+/*
+ * Use this to declare a field or local variable holding a page buffer, if that
+ * page might be accessed as a page or passed to an SMgr I/O function.  If
+ * allocating using the MemoryContext API, the aligned allocation functions
+ * should be used with PG_IO_ALIGN_SIZE.  This alignment may be more efficient
+ * for I/O in general, but may be strictly required on some platforms when
+ * using direct I/O.
+ */
+typedef union PGIOAlignedBlock
+{
+#ifdef pg_attribute_aligned
+	pg_attribute_aligned(PG_IO_ALIGN_SIZE)
+#endif
+	char		data[BLCKSZ];
+	double		force_align_d;
+	int64		force_align_i64;
+} PGIOAlignedBlock;
+
 /* Same, but for an XLOG_BLCKSZ-sized buffer */
 typedef union PGAlignedXLogBlock
 {
+#ifdef pg_attribute_aligned
+	pg_attribute_aligned(PG_IO_ALIGN_SIZE)
+#endif
 	char		data[XLOG_BLCKSZ];
 	double		force_align_d;
 	int64		force_align_i64;