diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml
index 2ef21fb..356aed4 100644
--- a/doc/src/sgml/config.sgml
+++ b/doc/src/sgml/config.sgml
@@ -2500,6 +2500,24 @@ include_dir 'conf.d'
       </listitem>
      </varlistentry>

+     <varlistentry id="guc-checkpoint-flush-to-disk" xreflabel="checkpoint_flush_to_disk">
+      <term><varname>checkpoint_flush_to_disk</varname> (<type>bool</type>)
+      <indexterm>
+       <primary><varname>checkpoint_flush_to_disk</> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        When writing data for a checkpoint, hint the underlying OS that the
+        data must be sent to disk as soon as possible.  This may help smoothing
+        disk I/O writes and avoid a stall when fsync is issued at the end of
+        the checkpoint, but it may also reduce average performance.
+        This setting may have no effect on some platforms.
+        The default is <literal>on</> on Linux, <literal>off</> otherwise.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-min-wal-size" xreflabel="min_wal_size">
       <term><varname>min_wal_size</varname> (<type>integer</type>)
       <indexterm>
diff --git a/doc/src/sgml/wal.sgml b/doc/src/sgml/wal.sgml
index f538698..1b658f2 100644
--- a/doc/src/sgml/wal.sgml
+++ b/doc/src/sgml/wal.sgml
@@ -558,6 +558,18 @@
   </para>

   <para>
+   On Linux and POSIX platforms, <xref linkend="guc-checkpoint-flush-to-disk">
+   allows to hint the OS that pages written on checkpoints must be flushed
+   to disk quickly.  Otherwise, these pages may be kept in cache for some time,
+   inducing a stall later when <literal>fsync</> is called to actually
+   complete the checkpoint.  This setting helps to reduce transaction latency,
+   but it may also have a small adverse effect on the average transaction rate
+   at maximum throughput on some OS.  It should be beneficial for high write
+   loads on HDD.  This feature probably brings no benefit on SSD, as the I/O
+   write latency is small on such hardware, thus it may be disabled.
+  </para>
+
+  <para>
    The number of WAL segment files in <filename>pg_xlog</> directory depends on
    <varname>min_wal_size</>, <varname>max_wal_size</> and
    the amount of WAL generated in previous checkpoint cycles. When old log
diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index 6a6fc3b..2a8f645 100644
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -918,7 +918,7 @@ logical_heap_rewrite_flush_mappings(RewriteState state)
 		 * Note that we deviate from the usual WAL coding practices here,
 		 * check the above "Logical rewrite support" comment for reasoning.
 		 */
-		written = FileWrite(src->vfd, waldata_start, len);
+		written = FileWrite(src->vfd, waldata_start, len, false, NULL);
 		if (written != len)
 			ereport(ERROR,
 					(errcode_for_file_access(),
diff --git a/src/backend/access/nbtree/nbtree.c b/src/backend/access/nbtree/nbtree.c
index cf4a6dc..4b5e9cd 100644
--- a/src/backend/access/nbtree/nbtree.c
+++ b/src/backend/access/nbtree/nbtree.c
@@ -203,7 +203,7 @@ btbuildempty(PG_FUNCTION_ARGS)
 	/* Write the page.  If archiving/streaming, XLOG it. */
 	PageSetChecksumInplace(metapage, BTREE_METAPAGE);
 	smgrwrite(index->rd_smgr, INIT_FORKNUM, BTREE_METAPAGE,
-			  (char *) metapage, true);
+			  (char *) metapage, true, false, NULL);
 	if (XLogIsNeeded())
 		log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
 					BTREE_METAPAGE, metapage, false);
diff --git a/src/backend/access/nbtree/nbtsort.c b/src/backend/access/nbtree/nbtsort.c
index f95f67a..ea7a45d 100644
--- a/src/backend/access/nbtree/nbtsort.c
+++ b/src/backend/access/nbtree/nbtsort.c
@@ -315,7 +315,7 @@ _bt_blwritepage(BTWriteState *wstate, Page page, BlockNumber blkno)
 	{
 		/* overwriting a block we zero-filled before */
 		smgrwrite(wstate->index->rd_smgr, MAIN_FORKNUM, blkno,
-				  (char *) page, true);
+				  (char *) page, true, false, NULL);
 	}

 	pfree(page);
diff --git a/src/backend/access/spgist/spginsert.c b/src/backend/access/spgist/spginsert.c
index bceee8d..b700efb 100644
--- a/src/backend/access/spgist/spginsert.c
+++ b/src/backend/access/spgist/spginsert.c
@@ -170,7 +170,7 @@ spgbuildempty(PG_FUNCTION_ARGS)
 	/* Write the page.  If archiving/streaming, XLOG it. */
 	PageSetChecksumInplace(page, SPGIST_METAPAGE_BLKNO);
 	smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_METAPAGE_BLKNO,
-			  (char *) page, true);
+			  (char *) page, true, false, NULL);
 	if (XLogIsNeeded())
 		log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
 					SPGIST_METAPAGE_BLKNO, page, false);
@@ -180,7 +180,7 @@ spgbuildempty(PG_FUNCTION_ARGS)

 	PageSetChecksumInplace(page, SPGIST_ROOT_BLKNO);
 	smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_ROOT_BLKNO,
-			  (char *) page, true);
+			  (char *) page, true, false, NULL);
 	if (XLogIsNeeded())
 		log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
 					SPGIST_ROOT_BLKNO, page, true);
@@ -190,7 +190,7 @@ spgbuildempty(PG_FUNCTION_ARGS)

 	PageSetChecksumInplace(page, SPGIST_NULL_BLKNO);
 	smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_NULL_BLKNO,
-			  (char *) page, true);
+			  (char *) page, true, false, NULL);
 	if (XLogIsNeeded())
 		log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
 					SPGIST_NULL_BLKNO, page, true);
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index 3b3a09e..e361907 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -665,7 +665,8 @@ ImmediateCheckpointRequested(void)
  * fraction between 0.0 meaning none, and 1.0 meaning all done.
  */
 void
-CheckpointWriteDelay(int flags, double progress)
+CheckpointWriteDelay(int flags, double progress,
+					 FileFlushContext * context, int ctx_size)
 {
 	static int	absorb_counter = WRITES_PER_ABSORB;

@@ -700,6 +701,26 @@ CheckpointWriteDelay(int flags, double progress)
 		 */
 		pgstat_send_bgwriter();

+#if defined(HAVE_SYNC_FILE_RANGE) || defined(HAVE_POSIX_FADVISE)
+
+		/*
+		 * Before sleeping, flush written blocks for each tablespace.
+		 */
+		if (checkpoint_flush_to_disk)
+		{
+			int i;
+
+			for (i = 0; i < ctx_size; i++)
+			{
+				if (context[i].ncalls != 0)
+				{
+					PerformFileFlush(&context[i]);
+					ResetFileFlushContext(&context[i]);
+				}
+			}
+		}
+#endif /* HAVE_SYNC_FILE_RANGE || HAVE_POSIX_FADVISE */
+
 		/*
 		 * This sleep used to be connected to bgwriter_delay, typically 200ms.
 		 * That resulted in more frequent wakeups if not much work to do.
diff --git a/src/backend/storage/buffer/bufmgr.c b/src/backend/storage/buffer/bufmgr.c
index 09af13b..deacec1 100644
--- a/src/backend/storage/buffer/bufmgr.c
+++ b/src/backend/storage/buffer/bufmgr.c
@@ -105,6 +105,8 @@ int			bgwriter_lru_maxpages = 100;
 double		bgwriter_lru_multiplier = 2.0;
 bool		track_io_timing = false;
 int			effective_io_concurrency = 0;
+/* hint to move writes to high priority */
+bool		checkpoint_flush_to_disk = DEFAULT_CHECKPOINT_FLUSH_TO_DISK;
 bool		checkpoint_sort = true;

 /*
@@ -427,7 +429,8 @@ static bool PinBuffer(volatile BufferDesc *buf, BufferAccessStrategy strategy);
 static void PinBuffer_Locked(volatile BufferDesc *buf);
 static void UnpinBuffer(volatile BufferDesc *buf, bool fixOwner);
 static void BufferSync(int flags);
-static int	SyncOneBuffer(int buf_id, bool skip_recently_used);
+static int	SyncOneBuffer(int buf_id, bool skip_recently_used,
+						  bool flush_to_disk, FileFlushContext *context);
 static void WaitIO(volatile BufferDesc *buf);
 static bool StartBufferIO(volatile BufferDesc *buf, bool forInput);
 static void TerminateBufferIO(volatile BufferDesc *buf, bool clear_dirty,
@@ -440,7 +443,8 @@ static volatile BufferDesc *BufferAlloc(SMgrRelation smgr,
 			BlockNumber blockNum,
 			BufferAccessStrategy strategy,
 			bool *foundPtr);
-static void FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln);
+static void FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln,
+						bool flush_to_disk, FileFlushContext *context);
 static void AtProcExit_Buffers(int code, Datum arg);
 static void CheckForBufferLeaks(void);
 static int	rnode_comparator(const void *p1, const void *p2);
@@ -1107,7 +1111,7 @@ BufferAlloc(SMgrRelation smgr, char relpersistence, ForkNumber forkNum,
 												smgr->smgr_rnode.node.dbNode,
 											  smgr->smgr_rnode.node.relNode);

-				FlushBuffer(buf, NULL);
+				FlushBuffer(buf, NULL, false, NULL);
 				LWLockRelease(buf->content_lock);

 				TRACE_POSTGRESQL_BUFFER_WRITE_DIRTY_DONE(forkNum, blockNum,
@@ -1770,6 +1774,7 @@ BufferSync(int flags)
 	HTAB		*spcBuffers;
 	TableSpaceCheckpointStatus *spcStatus = NULL;
 	int         nb_spaces, space;
+	FileFlushContext * spcContext = NULL;

 	/* Make sure we can handle the pin inside SyncOneBuffer */
 	ResourceOwnerEnlargeBuffers(CurrentResourceOwner);
@@ -1857,10 +1862,12 @@ BufferSync(int flags)

 	TRACE_POSTGRESQL_BUFFER_SYNC_START(NBuffers, num_to_write);

-	/* Build checkpoint tablespace buffer status */
+	/* Build checkpoint tablespace buffer status & flush context arrays */
 	nb_spaces = hash_get_num_entries(spcBuffers);
 	spcStatus = (TableSpaceCheckpointStatus *)
 		palloc(sizeof(TableSpaceCheckpointStatus) * nb_spaces);
+	spcContext = (FileFlushContext *)
+		palloc(sizeof(FileFlushContext) * nb_spaces);

 	{
 		int index = 0;
@@ -1877,6 +1884,12 @@ BufferSync(int flags)
 			/* should it be randomized? chosen with some criterion? */
 			spcStatus[index].index = 0;

+#if defined(HAVE_SYNC_FILE_RANGE) || defined(HAVE_POSIX_FADVISE)
+
+			ResetFileFlushContext(&spcContext[index]);
+
+#endif /* HAVE_SYNC_FILE_RANGE || HAVE_POSIX_FADVISE */
+
 			index ++;
 		}
 	}
@@ -1932,7 +1945,8 @@ BufferSync(int flags)
 		 */
 		if (bufHdr != NULL && bufHdr->flags & BM_CHECKPOINT_NEEDED)
 		{
-			if (SyncOneBuffer(buf_id, false) & BUF_WRITTEN)
+			if (SyncOneBuffer(buf_id, false, checkpoint_flush_to_disk,
+							  &spcContext[space]) & BUF_WRITTEN)
 			{
 				TRACE_POSTGRESQL_BUFFER_SYNC_WRITTEN(buf_id);
 				BgWriterStats.m_buf_written_checkpoints++;
@@ -1942,7 +1956,8 @@ BufferSync(int flags)
 				/*
 				 * Sleep to throttle our I/O rate.
 				 */
-				CheckpointWriteDelay(flags, (double) num_written / num_to_write);
+				CheckpointWriteDelay(flags, (double) num_written / num_to_write,
+									 spcContext, nb_spaces);
 			}
 		}

@@ -1959,6 +1974,13 @@ BufferSync(int flags)
 		if (spcStatus[space].index >= num_to_write ||
 			spcStatus[space].num_written >= spcStatus[space].num_to_write)
 		{
+#if defined(HAVE_SYNC_FILE_RANGE) || defined(HAVE_POSIX_FADVISE)
+
+			PerformFileFlush(&spcContext[space]);
+			ResetFileFlushContext(&spcContext[space]);
+
+#endif /* HAVE_SYNC_FILE_RANGE || HAVE_POSIX_FADVISE */
+
 			nb_spaces--;
 			if (space != nb_spaces)
 				spcStatus[space] = spcStatus[nb_spaces];
@@ -1969,6 +1991,8 @@ BufferSync(int flags)

 	pfree(spcStatus);
 	spcStatus = NULL;
+	pfree(spcContext);
+	spcContext = NULL;

 	/*
 	 * Update checkpoint statistics. As noted above, this doesn't include
@@ -2216,7 +2240,7 @@ BgBufferSync(void)
 	/* Execute the LRU scan */
 	while (num_to_scan > 0 && reusable_buffers < upcoming_alloc_est)
 	{
-		int			buffer_state = SyncOneBuffer(next_to_clean, true);
+		int	buffer_state = SyncOneBuffer(next_to_clean, true, false, NULL);

 		if (++next_to_clean >= NBuffers)
 		{
@@ -2293,7 +2317,8 @@ BgBufferSync(void)
  * Note: caller must have done ResourceOwnerEnlargeBuffers.
  */
 static int
-SyncOneBuffer(int buf_id, bool skip_recently_used)
+SyncOneBuffer(int buf_id, bool skip_recently_used, bool flush_to_disk,
+	FileFlushContext * context)
 {
 	volatile BufferDesc *bufHdr = GetBufferDescriptor(buf_id);
 	int			result = 0;
@@ -2334,7 +2359,7 @@ SyncOneBuffer(int buf_id, bool skip_recently_used)
 	PinBuffer_Locked(bufHdr);
 	LWLockAcquire(bufHdr->content_lock, LW_SHARED);

-	FlushBuffer(bufHdr, NULL);
+	FlushBuffer(bufHdr, NULL, flush_to_disk, context);

 	LWLockRelease(bufHdr->content_lock);
 	UnpinBuffer(bufHdr, true);
@@ -2596,9 +2621,16 @@ BufferGetTag(Buffer buffer, RelFileNode *rnode, ForkNumber *forknum,
  *
  * If the caller has an smgr reference for the buffer's relation, pass it
  * as the second parameter.  If not, pass NULL.
+ *
+ * The third parameter tries to hint the OS that a high priority write is meant,
+ * possibly because io-throttling is already managed elsewhere.
+ * The last parameter holds the current flush context that accumulates flush
+ * requests to be performed in one call, instead of being performed on a buffer
+ * per buffer basis.
  */
 static void
-FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln)
+FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln, bool flush_to_disk,
+	FileFlushContext * context)
 {
 	XLogRecPtr	recptr;
 	ErrorContextCallback errcallback;
@@ -2687,7 +2719,9 @@ FlushBuffer(volatile BufferDesc *buf, SMgrRelation reln)
 			  buf->tag.forkNum,
 			  buf->tag.blockNum,
 			  bufToWrite,
-			  false);
+			  false,
+			  flush_to_disk,
+			  context);

 	if (track_io_timing)
 	{
@@ -3109,7 +3143,9 @@ FlushRelationBuffers(Relation rel)
 						  bufHdr->tag.forkNum,
 						  bufHdr->tag.blockNum,
 						  localpage,
-						  false);
+						  false,
+						  false,
+						  NULL);

 				bufHdr->flags &= ~(BM_DIRTY | BM_JUST_DIRTIED);

@@ -3143,7 +3179,7 @@ FlushRelationBuffers(Relation rel)
 		{
 			PinBuffer_Locked(bufHdr);
 			LWLockAcquire(bufHdr->content_lock, LW_SHARED);
-			FlushBuffer(bufHdr, rel->rd_smgr);
+			FlushBuffer(bufHdr, rel->rd_smgr, false, NULL);
 			LWLockRelease(bufHdr->content_lock);
 			UnpinBuffer(bufHdr, true);
 		}
@@ -3195,7 +3231,7 @@ FlushDatabaseBuffers(Oid dbid)
 		{
 			PinBuffer_Locked(bufHdr);
 			LWLockAcquire(bufHdr->content_lock, LW_SHARED);
-			FlushBuffer(bufHdr, NULL);
+			FlushBuffer(bufHdr, NULL, false, NULL);
 			LWLockRelease(bufHdr->content_lock);
 			UnpinBuffer(bufHdr, true);
 		}
diff --git a/src/backend/storage/buffer/localbuf.c b/src/backend/storage/buffer/localbuf.c
index 3144afe..114a0a6 100644
--- a/src/backend/storage/buffer/localbuf.c
+++ b/src/backend/storage/buffer/localbuf.c
@@ -208,7 +208,9 @@ LocalBufferAlloc(SMgrRelation smgr, ForkNumber forkNum, BlockNumber blockNum,
 				  bufHdr->tag.forkNum,
 				  bufHdr->tag.blockNum,
 				  localpage,
-				  false);
+				  false,
+				  false,
+				  NULL);

 		/* Mark not-dirty now in case we error out below */
 		bufHdr->flags &= ~BM_DIRTY;
diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c
index ea4d689..fb3b383 100644
--- a/src/backend/storage/file/buffile.c
+++ b/src/backend/storage/file/buffile.c
@@ -317,7 +317,7 @@ BufFileDumpBuffer(BufFile *file)
 				return;			/* seek failed, give up */
 			file->offsets[file->curFile] = file->curOffset;
 		}
-		bytestowrite = FileWrite(thisfile, file->buffer + wpos, bytestowrite);
+		bytestowrite = FileWrite(thisfile, file->buffer + wpos, bytestowrite, false, NULL);
 		if (bytestowrite <= 0)
 			return;				/* failed to write */
 		file->offsets[file->curFile] += bytestowrite;
diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
index 1ba4946..e880a9e 100644
--- a/src/backend/storage/file/fd.c
+++ b/src/backend/storage/file/fd.c
@@ -1344,8 +1344,97 @@ retry:
 	return returnCode;
 }

+#if defined(HAVE_SYNC_FILE_RANGE) || defined(HAVE_POSIX_FADVISE)
+
+void
+ResetFileFlushContext(FileFlushContext * context)
+{
+	context->fd = 0;
+	context->ncalls = 0;
+	context->offset = 0;
+	context->nbytes = 0;
+	context->filename = NULL;
+}
+
+void
+PerformFileFlush(FileFlushContext * context)
+{
+	if (context->ncalls != 0)
+	{
+		int rc;
+
+#if defined(HAVE_SYNC_FILE_RANGE)
+
+		/*
+		 * Linux: tell the memory manager to move these blocks to io so
+		 * that they are considered for being actually written to disk.
+		 */
+		rc = sync_file_range(context->fd, context->offset, context->nbytes,
+							 SYNC_FILE_RANGE_WRITE);
+
+#elif defined(HAVE_POSIX_FADVISE)
+
+		/*
+		 * Others: say that data should not be kept in memory...
+		 * This is not exactly what we want to say, because we want to write
+		 * the data for durability but we may need it later nevertheless.
+		 * It seems that Linux would free the memory *if* the data has
+		 * already been written do disk, else the "dontneed" call is ignored.
+		 * For FreeBSD this may have the desired effect of moving the
+		 * data to the io layer, although the system does not seem to
+		 * take into account the provided offset & size, so it is rather
+		 * rough...
+		 */
+		rc = posix_fadvise(context->fd, context->offset, context->nbytes,
+						   POSIX_FADV_DONTNEED);
+
+#endif
+
+		if (rc < 0)
+			ereport(ERROR,
+					(errcode_for_file_access(),
+					 errmsg("could not flush block " INT64_FORMAT
+							" on " INT64_FORMAT " blocks in file \"%s\": %m",
+							context->offset / BLCKSZ,
+							context->nbytes / BLCKSZ,
+							context->filename)));
+	}
+}
+
+void
+FileAsynchronousFlush(FileFlushContext * context,
+					  int fd, off_t offset, off_t nbytes, char * filename)
+{
+	if (context->ncalls != 0 && context->fd == fd)
+	{
+		/* same file: merge current flush with previous ones */
+		off_t new_offset = offset < context->offset? offset: context->offset;
+
+		context->nbytes =
+			(context->offset + context->nbytes > offset + nbytes ?
+			 context->offset + context->nbytes : offset + nbytes) -
+			new_offset;
+		context->offset = new_offset;
+		context->ncalls ++;
+	}
+	else
+	{
+		/* other file: do flush previous file & reset flush accumulator */
+		PerformFileFlush(context);
+
+		context->fd = fd;
+		context->ncalls = 1;
+		context->offset = offset;
+		context->nbytes = nbytes;
+		context->filename = filename;
+	}
+}
+
+#endif /* HAVE_SYNC_FILE_RANGE || HAVE_POSIX_FADVISE */
+
 int
-FileWrite(File file, char *buffer, int amount)
+FileWrite(File file, char *buffer, int amount, bool flush_to_disk,
+		  FileFlushContext * context)
 {
 	int			returnCode;

@@ -1395,6 +1484,28 @@ retry:

 	if (returnCode >= 0)
 	{
+
+#if defined(HAVE_SYNC_FILE_RANGE) || defined(HAVE_POSIX_FADVISE)
+
+		/*
+		 * Calling "write" tells the OS that pg wants to write some page to disk,
+		 * however when it is really done is chosen by the OS.
+		 * Depending on other disk activities this may be delayed significantly,
+		 * maybe up to an "fsync" call, which could induce an IO write surge.
+		 * When checkpointing pg is doing its own throttling and the result
+		 * should really be written to disk with high priority, so as to meet
+		 * the completion target.
+		 * This call hints that such write have a higher priority.
+		 */
+		if (flush_to_disk && returnCode == amount && errno == 0)
+		{
+			FileAsynchronousFlush(context,
+								  VfdCache[file].fd, VfdCache[file].seekPos,
+								  amount, VfdCache[file].fileName);
+		}
+
+#endif /* HAVE_SYNC_FILE_RANGE || HAVE_POSIX_FADVISE */
+
 		VfdCache[file].seekPos += returnCode;

 		/* maintain fileSize and temporary_files_size if it's a temp file */
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 42a43bb..dbf057f 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -531,7 +531,7 @@ mdextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 				 errmsg("could not seek to block %u in file \"%s\": %m",
 						blocknum, FilePathName(v->mdfd_vfd))));

-	if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ)) != BLCKSZ)
+	if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, false, NULL)) != BLCKSZ)
 	{
 		if (nbytes < 0)
 			ereport(ERROR,
@@ -738,7 +738,8 @@ mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
  */
 void
 mdwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
-		char *buffer, bool skipFsync)
+		char *buffer, bool skipFsync, bool flush_to_disk,
+		FileFlushContext * context)
 {
 	off_t		seekpos;
 	int			nbytes;
@@ -767,7 +768,7 @@ mdwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 				 errmsg("could not seek to block %u in file \"%s\": %m",
 						blocknum, FilePathName(v->mdfd_vfd))));

-	nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ);
+	nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, flush_to_disk, context);

 	TRACE_POSTGRESQL_SMGR_MD_WRITE_DONE(forknum, blocknum,
 										reln->smgr_rnode.node.spcNode,
diff --git a/src/backend/storage/smgr/smgr.c b/src/backend/storage/smgr/smgr.c
index 244b4ea..2db3cd3 100644
--- a/src/backend/storage/smgr/smgr.c
+++ b/src/backend/storage/smgr/smgr.c
@@ -52,7 +52,8 @@ typedef struct f_smgr
 	void		(*smgr_read) (SMgrRelation reln, ForkNumber forknum,
 										  BlockNumber blocknum, char *buffer);
 	void		(*smgr_write) (SMgrRelation reln, ForkNumber forknum,
-						 BlockNumber blocknum, char *buffer, bool skipFsync);
+						   BlockNumber blocknum, char *buffer, bool skipFsync,
+							   bool flush_to_disk, FileFlushContext *context);
 	BlockNumber (*smgr_nblocks) (SMgrRelation reln, ForkNumber forknum);
 	void		(*smgr_truncate) (SMgrRelation reln, ForkNumber forknum,
 											  BlockNumber nblocks);
@@ -643,10 +644,11 @@ smgrread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
  */
 void
 smgrwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
-		  char *buffer, bool skipFsync)
+		  char *buffer, bool skipFsync, bool flush_to_disk,
+		  FileFlushContext * context)
 {
 	(*(smgrsw[reln->smgr_which].smgr_write)) (reln, forknum, blocknum,
-											  buffer, skipFsync);
+									buffer, skipFsync, flush_to_disk, context);
 }

 /*
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 1cd2aa0..95deb71 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -158,6 +158,7 @@ static bool check_bonjour(bool *newval, void **extra, GucSource source);
 static bool check_ssl(bool *newval, void **extra, GucSource source);
 static bool check_stage_log_stats(bool *newval, void **extra, GucSource source);
 static bool check_log_stats(bool *newval, void **extra, GucSource source);
+static bool check_flush_to_disk(bool *newval, void **extra, GucSource source);
 static bool check_canonical_path(char **newval, void **extra, GucSource source);
 static bool check_timezone_abbreviations(char **newval, void **extra, GucSource source);
 static void assign_timezone_abbreviations(const char *newval, void *extra);
@@ -1024,6 +1025,17 @@ static struct config_bool ConfigureNamesBool[] =
 	},

 	{
+		{"checkpoint_flush_to_disk", PGC_SIGHUP, WAL_CHECKPOINTS,
+			gettext_noop("Hint that checkpoint's writes are high priority."),
+			NULL
+		},
+		&checkpoint_flush_to_disk,
+		/* see bufmgr.h: true on Linux, false otherwise */
+		DEFAULT_CHECKPOINT_FLUSH_TO_DISK,
+		check_flush_to_disk, NULL, NULL
+	},
+
+	{
 		{"log_connections", PGC_SU_BACKEND, LOGGING_WHAT,
 			gettext_noop("Logs each successful connection."),
 			NULL
@@ -9805,6 +9817,21 @@ check_log_stats(bool *newval, void **extra, GucSource source)
 }

 static bool
+check_flush_to_disk(bool *newval, void **extra, GucSource source)
+{
+/* This test must be consistent with the one in FileWrite (storage/file/fd.c)
+ */
+#if ! (defined(HAVE_SYNC_FILE_RANGE) || defined(HAVE_POSIX_FADVISE))
+	/* just warn if it has no effect */
+	ereport(WARNING,
+			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+			 errmsg("Setting \"checkpoint_flush_to_disk\" has no effect "
+					"on this platform.")));
+#endif /* ! (HAVE_SYNC_FILE_RANGE || HAVE_POSIX_FADVISE) */
+	return true;
+}
+
+static bool
 check_canonical_path(char **newval, void **extra, GucSource source)
 {
 	/*
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 8020c1c..e4cf2a1 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -202,6 +202,8 @@
 #min_wal_size = 80MB
 #checkpoint_completion_target = 0.5	# checkpoint target duration, 0.0 - 1.0
 #checkpoint_sort = on			# sort buffers on checkpoint
+#checkpoint_flush_to_disk = ?		# send buffers to disk on checkpoint
+					# default is on if Linux, off otherwise
 #checkpoint_warning = 30s		# 0 disables

 # - Archiving -
diff --git a/src/include/postmaster/bgwriter.h b/src/include/postmaster/bgwriter.h
index a49c208..f9c8ca1 100644
--- a/src/include/postmaster/bgwriter.h
+++ b/src/include/postmaster/bgwriter.h
@@ -16,6 +16,7 @@
 #define _BGWRITER_H

 #include "storage/block.h"
+#include "storage/fd.h"
 #include "storage/relfilenode.h"

@@ -29,7 +30,8 @@ extern void BackgroundWriterMain(void) pg_attribute_noreturn();
 extern void CheckpointerMain(void) pg_attribute_noreturn();

 extern void RequestCheckpoint(int flags);
-extern void CheckpointWriteDelay(int flags, double progress);
+extern void CheckpointWriteDelay(int flags, double progress,
+								 FileFlushContext * context, int ctx_size);

 extern bool ForwardFsyncRequest(RelFileNode rnode, ForkNumber forknum,
 					BlockNumber segno);
diff --git a/src/include/storage/bufmgr.h b/src/include/storage/bufmgr.h
index b56802b..cd9d130 100644
--- a/src/include/storage/bufmgr.h
+++ b/src/include/storage/bufmgr.h
@@ -54,6 +54,14 @@ extern int	bgwriter_lru_maxpages;
 extern double bgwriter_lru_multiplier;
 extern bool track_io_timing;
 extern int	target_prefetch_pages;
+
+#ifdef HAVE_SYNC_FILE_RANGE
+#define DEFAULT_CHECKPOINT_FLUSH_TO_DISK true
+#else
+#define DEFAULT_CHECKPOINT_FLUSH_TO_DISK false
+#endif /* HAVE_SYNC_FILE_RANGE */
+
+extern bool checkpoint_flush_to_disk;
 extern bool checkpoint_sort;

 /* in buf_init.c */
diff --git a/src/include/storage/fd.h b/src/include/storage/fd.h
index 7eabe09..c7b2a6d 100644
--- a/src/include/storage/fd.h
+++ b/src/include/storage/fd.h
@@ -59,6 +59,24 @@ extern int	max_files_per_process;
  */
 extern int	max_safe_fds;

+/*
+ * FileFlushContext structure:
+ *
+ * This is used to accumulate several flush requests on a file
+ * into a larger flush request.
+ * - fd: file descriptor of the file
+ * - ncalls: number of flushes merged together
+ * - offset: starting offset (minimum of all offsets)
+ * - nbytes: size (minimum extent to cover all flushed data)
+ * - filename: filename of fd for error messages
+ */
+typedef struct FileFlushContext {
+	int fd;
+	int ncalls;
+	off_t offset;
+	off_t nbytes;
+	char * filename;
+} FileFlushContext;

 /*
  * prototypes for functions in fd.c
@@ -70,7 +88,12 @@ extern File OpenTemporaryFile(bool interXact);
 extern void FileClose(File file);
 extern int	FilePrefetch(File file, off_t offset, int amount);
 extern int	FileRead(File file, char *buffer, int amount);
-extern int	FileWrite(File file, char *buffer, int amount);
+extern void ResetFileFlushContext(FileFlushContext * context);
+extern void PerformFileFlush(FileFlushContext * context);
+extern void FileAsynchronousFlush(FileFlushContext * context,
+				int fd, off_t offset, off_t nbytes, char * filename);
+extern int	FileWrite(File file, char *buffer, int amount, bool flush_to_disk,
+	FileFlushContext * context);
 extern int	FileSync(File file);
 extern off_t FileSeek(File file, off_t offset, int whence);
 extern int	FileTruncate(File file, off_t offset);
diff --git a/src/include/storage/smgr.h b/src/include/storage/smgr.h
index 69a624f..a46a70c 100644
--- a/src/include/storage/smgr.h
+++ b/src/include/storage/smgr.h
@@ -16,6 +16,7 @@

 #include "fmgr.h"
 #include "storage/block.h"
+#include "storage/fd.h"
 #include "storage/relfilenode.h"

@@ -95,7 +96,8 @@ extern void smgrprefetch(SMgrRelation reln, ForkNumber forknum,
 extern void smgrread(SMgrRelation reln, ForkNumber forknum,
 		 BlockNumber blocknum, char *buffer);
 extern void smgrwrite(SMgrRelation reln, ForkNumber forknum,
-		  BlockNumber blocknum, char *buffer, bool skipFsync);
+					  BlockNumber blocknum, char *buffer, bool skipFsync,
+					  bool flush_to_disk, FileFlushContext * context);
 extern BlockNumber smgrnblocks(SMgrRelation reln, ForkNumber forknum);
 extern void smgrtruncate(SMgrRelation reln, ForkNumber forknum,
 			 BlockNumber nblocks);
@@ -120,8 +122,9 @@ extern void mdprefetch(SMgrRelation reln, ForkNumber forknum,
 		   BlockNumber blocknum);
 extern void mdread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
 	   char *buffer);
-extern void mdwrite(SMgrRelation reln, ForkNumber forknum,
-		BlockNumber blocknum, char *buffer, bool skipFsync);
+extern void mdwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
+					char *buffer, bool skipFsync, bool flush_to_disk,
+					FileFlushContext * context);
 extern BlockNumber mdnblocks(SMgrRelation reln, ForkNumber forknum);
 extern void mdtruncate(SMgrRelation reln, ForkNumber forknum,
 		   BlockNumber nblocks);