dm snapshot: use dm-bufio prefetch

This patch modifies dm-snapshot so that it prefetches the buffers when
loading the exceptions.

The number of buffers read ahead is specified in the DM_PREFETCH_CHUNKS
macro.  The current value for DM_PREFETCH_CHUNKS (12) was found to
provide the best performance on a single 15k SCSI spindle.  In the
future we may modify this default or make it configurable.

Also, introduce the function dm_bufio_set_minimum_buffers to setup
bufio's number of internal buffers before freeing happens.  dm-bufio may
hold more buffers if enough memory is available.  There is no guarantee
that the specified number of buffers will be available - if you need a
guarantee, use the argument reserved_buffers for
dm_bufio_client_create.

Signed-off-by: Mikulas Patocka <[email protected]>
Signed-off-by: Mike Snitzer <[email protected]>

drivers/md/dm-bufio.c

@@ -104,6 +104,8 @@ struct dm_bufio_client {
 	struct list_head reserved_buffers;
 	unsigned need_reserved_buffers;
 
+	unsigned minimum_buffers;
+
 	struct hlist_head *cache_hash;
 	wait_queue_head_t free_buffer_wait;
 
@@ -861,8 +863,8 @@ static void __get_memory_limit(struct dm_bufio_client *c,
 	buffers = dm_bufio_cache_size_per_client >>
 		  (c->sectors_per_block_bits + SECTOR_SHIFT);
 
-	if (buffers < DM_BUFIO_MIN_BUFFERS)
-		buffers = DM_BUFIO_MIN_BUFFERS;
+	if (buffers < c->minimum_buffers)
+		buffers = c->minimum_buffers;
 
 	*limit_buffers = buffers;
 	*threshold_buffers = buffers * DM_BUFIO_WRITEBACK_PERCENT / 100;
@@ -1372,6 +1374,12 @@ void dm_bufio_forget(struct dm_bufio_client *c, sector_t block)
 }
 EXPORT_SYMBOL(dm_bufio_forget);
 
+void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n)
+{
+	c->minimum_buffers = n;
+}
+EXPORT_SYMBOL(dm_bufio_set_minimum_buffers);
+
 unsigned dm_bufio_get_block_size(struct dm_bufio_client *c)
 {
 	return c->block_size;
@@ -1568,6 +1576,8 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 	INIT_LIST_HEAD(&c->reserved_buffers);
 	c->need_reserved_buffers = reserved_buffers;
 
+	c->minimum_buffers = DM_BUFIO_MIN_BUFFERS;
+
 	init_waitqueue_head(&c->free_buffer_wait);
 	c->async_write_error = 0;
 

drivers/md/dm-bufio.h

@@ -115,6 +115,11 @@ void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block);
  */
 void dm_bufio_forget(struct dm_bufio_client *c, sector_t block);
 
+/*
+ * Set the minimum number of buffers before cleanup happens.
+ */
+void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n);
+
 unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
 sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
 sector_t dm_bufio_get_block_number(struct dm_buffer *b);

drivers/md/dm-snap-persistent.c

@@ -18,6 +18,8 @@
 #define DM_MSG_PREFIX "persistent snapshot"
 #define DM_CHUNK_SIZE_DEFAULT_SECTORS 32	/* 16KB */
 
+#define DM_PREFETCH_CHUNKS		12
+
 /*-----------------------------------------------------------------
  * Persistent snapshots, by persistent we mean that the snapshot
  * will survive a reboot.
@@ -497,6 +499,7 @@ static int read_exceptions(struct pstore *ps,
 {
 	int r, full = 1;
 	struct dm_bufio_client *client;
+	chunk_t prefetch_area = 0;
 
 	client = dm_bufio_client_create(dm_snap_cow(ps->store->snap)->bdev,
 					ps->store->chunk_size << SECTOR_SHIFT,
@@ -505,14 +508,34 @@ static int read_exceptions(struct pstore *ps,
 	if (IS_ERR(client))
 		return PTR_ERR(client);
 
+	/*
+	 * Setup for one current buffer + desired readahead buffers.
+	 */
+	dm_bufio_set_minimum_buffers(client, 1 + DM_PREFETCH_CHUNKS);
+
 	/*
 	 * Keeping reading chunks and inserting exceptions until
 	 * we find a partially full area.
 	 */
 	for (ps->current_area = 0; full; ps->current_area++) {
 		struct dm_buffer *bp;
 		void *area;
-		chunk_t chunk = area_location(ps, ps->current_area);
+		chunk_t chunk;
+
+		if (unlikely(prefetch_area < ps->current_area))
+			prefetch_area = ps->current_area;
+
+		if (DM_PREFETCH_CHUNKS) do {
+			chunk_t pf_chunk = area_location(ps, prefetch_area);
+			if (unlikely(pf_chunk >= dm_bufio_get_device_size(client)))
+				break;
+			dm_bufio_prefetch(client, pf_chunk, 1);
+			prefetch_area++;
+			if (unlikely(!prefetch_area))
+				break;
+		} while (prefetch_area <= ps->current_area + DM_PREFETCH_CHUNKS);
+
+		chunk = area_location(ps, ps->current_area);
 
 		area = dm_bufio_read(client, chunk, &bp);
 		if (unlikely(IS_ERR(area))) {