Optionally prefetch referenced data in recovery.

Introduce a new GUC recovery_prefetch, disabled by default.  When
enabled, look ahead in the WAL and try to initiate asynchronous reading
of referenced data blocks that are not yet cached in our buffer pool.
For now, this is done with posix_fadvise(), which has several caveats.
Better mechanisms will follow in later work on the I/O subsystem.

The GUC maintenance_io_concurrency is used to limit the number of
concurrent I/Os we allow ourselves to initiate, based on pessimistic
heuristics used to infer that I/Os have begun and completed.

The GUC wal_decode_buffer_size is used to limit the maximum distance we
are prepared to read ahead in the WAL to find uncached blocks.

Reviewed-by: Alvaro Herrera <alvherre@2ndquadrant.com> (parts)
Reviewed-by: Andres Freund <andres@anarazel.de> (parts)
Reviewed-by: Tomas Vondra <tomas.vondra@2ndquadrant.com> (parts)
Tested-by: Tomas Vondra <tomas.vondra@2ndquadrant.com>
Tested-by: Jakub Wartak <Jakub.Wartak@tomtom.com>
Tested-by: Dmitry Dolgov <9erthalion6@gmail.com>
Tested-by: Sait Talha Nisanci <Sait.Nisanci@microsoft.com>
Discussion: https://postgr.es/m/CA%2BhUKGJ4VJN8ttxScUFM8dOKX0BrBiboo5uz1cq%3DAovOddfHpA%40mail.gmail.com

1 files changed, 19 insertions, 4 deletions

diff --git a/src/backend/access/transam/xlogutils.c b/src/backend/access/transam/xlogutils.c
index eedd95cc137..4d5c9bb08f5 100644
--- a/src/backend/access/transam/xlogutils.c
+++ b/src/backend/access/transam/xlogutils.c
@@ -335,11 +335,13 @@ XLogReadBufferForRedoExtended(XLogReaderState *record,
 	RelFileNode rnode;
 	ForkNumber	forknum;
 	BlockNumber blkno;
+	Buffer		recent_buffer;
 	Page		page;
 	bool		zeromode;
 	bool		willinit;
 
-	if (!XLogRecGetBlockTag(record, block_id, &rnode, &forknum, &blkno))
+	if (!XLogRecGetRecentBuffer(record, block_id, &rnode, &forknum, &blkno,
+								&recent_buffer))
 	{
 		/* Caller specified a bogus block_id */
 		elog(PANIC, "failed to locate backup block with ID %d", block_id);
@@ -361,7 +363,8 @@ XLogReadBufferForRedoExtended(XLogReaderState *record,
 	{
 		Assert(XLogRecHasBlockImage(record, block_id));
 		*buf = XLogReadBufferExtended(rnode, forknum, blkno,
-									  get_cleanup_lock ? RBM_ZERO_AND_CLEANUP_LOCK : RBM_ZERO_AND_LOCK);
+									  get_cleanup_lock ? RBM_ZERO_AND_CLEANUP_LOCK : RBM_ZERO_AND_LOCK,
+									  recent_buffer);
 		page = BufferGetPage(*buf);
 		if (!RestoreBlockImage(record, block_id, page))
 			elog(ERROR, "failed to restore block image");
@@ -390,7 +393,8 @@ XLogReadBufferForRedoExtended(XLogReaderState *record,
 	}
 	else
 	{
-		*buf = XLogReadBufferExtended(rnode, forknum, blkno, mode);
+		*buf = XLogReadBufferExtended(rnode, forknum, blkno, mode,
+									  recent_buffer);
 		if (BufferIsValid(*buf))
 		{
 			if (mode != RBM_ZERO_AND_LOCK && mode != RBM_ZERO_AND_CLEANUP_LOCK)
@@ -437,7 +441,8 @@ XLogReadBufferForRedoExtended(XLogReaderState *record,
  */
 Buffer
 XLogReadBufferExtended(RelFileNode rnode, ForkNumber forknum,
-					   BlockNumber blkno, ReadBufferMode mode)
+					   BlockNumber blkno, ReadBufferMode mode,
+					   Buffer recent_buffer)
 {
 	BlockNumber lastblock;
 	Buffer		buffer;
@@ -445,6 +450,15 @@ XLogReadBufferExtended(RelFileNode rnode, ForkNumber forknum,
 
 	Assert(blkno != P_NEW);
 
+	/* Do we have a clue where the buffer might be already? */
+	if (BufferIsValid(recent_buffer) &&
+		mode == RBM_NORMAL &&
+		ReadRecentBuffer(rnode, forknum, blkno, recent_buffer))
+	{
+		buffer = recent_buffer;
+		goto recent_buffer_fast_path;
+	}
+
 	/* Open the relation at smgr level */
 	smgr = smgropen(rnode, InvalidBackendId);
 
@@ -503,6 +517,7 @@ XLogReadBufferExtended(RelFileNode rnode, ForkNumber forknum,
 		}
 	}
 
+recent_buffer_fast_path:
 	if (mode == RBM_NORMAL)
 	{
 		/* check that page has been initialized */