3 files changed, 36 insertions, 15 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index b98d7705acb6..a857eb3c10de 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -679,6 +679,8 @@ struct cache_set {
 
 #define BUCKET_HASH_BITS	12
 	struct hlist_head	bucket_hash[1 << BUCKET_HASH_BITS];
+
+	DECLARE_HEAP(struct btree *, flush_btree);
 };
 
 struct bbio {
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index f5296007a9d5..1b736b860739 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -368,6 +368,12 @@ err:
 }
 
 /* Journalling */
+#define journal_max_cmp(l, r) \
+	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) < \
+	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
+#define journal_min_cmp(l, r) \
+	(fifo_idx(&c->journal.pin, btree_current_write(l)->journal) > \
+	 fifo_idx(&(c)->journal.pin, btree_current_write(r)->journal))
 
 static void btree_flush_write(struct cache_set *c)
 {
@@ -375,25 +381,35 @@ static void btree_flush_write(struct cache_set *c)
 	 * Try to find the btree node with that references the oldest journal
 	 * entry, best is our current candidate and is locked if non NULL:
 	 */
-	struct btree *b, *best;
-	unsigned i;
+	struct btree *b;
+	int i;
 
 	atomic_long_inc(&c->flush_write);
+
 retry:
-	best = NULL;
-
-	for_each_cached_btree(b, c, i)
-		if (btree_current_write(b)->journal) {
-			if (!best)
-				best = b;
-			else if (journal_pin_cmp(c,
-					btree_current_write(best)->journal,
-					btree_current_write(b)->journal)) {
-				best = b;
+	spin_lock(&c->journal.lock);
+	if (heap_empty(&c->flush_btree)) {
+		for_each_cached_btree(b, c, i)
+			if (btree_current_write(b)->journal) {
+				if (!heap_full(&c->flush_btree))
+					heap_add(&c->flush_btree, b,
+						 journal_max_cmp);
+				else if (journal_max_cmp(b,
+					 heap_peek(&c->flush_btree))) {
+					c->flush_btree.data[0] = b;
+					heap_sift(&c->flush_btree, 0,
+						  journal_max_cmp);
+				}
 			}
-		}
 
-	b = best;
+		for (i = c->flush_btree.used / 2 - 1; i >= 0; --i)
+			heap_sift(&c->flush_btree, i, journal_min_cmp);
+	}
+
+	b = NULL;
+	heap_pop(&c->flush_btree, b, journal_min_cmp);
+	spin_unlock(&c->journal.lock);
+
 	if (b) {
 		mutex_lock(&b->write_lock);
 		if (!btree_current_write(b)->journal) {
@@ -824,7 +840,8 @@ int bch_journal_alloc(struct cache_set *c)
 	j->w[0].c = c;
 	j->w[1].c = c;
 
-	if (!(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
+	if (!(init_heap(&c->flush_btree, 128, GFP_KERNEL)) ||
+	    !(init_fifo(&j->pin, JOURNAL_PIN, GFP_KERNEL)) ||
 	    !(j->w[0].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)) ||
 	    !(j->w[1].data = (void *) __get_free_pages(GFP_KERNEL, JSET_BITS)))
 		return -ENOMEM;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 4df4c5c1cab2..a6763db7f061 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -112,6 +112,8 @@ do {									\
 
 #define heap_full(h)	((h)->used == (h)->size)
 
+#define heap_empty(h)	((h)->used == 0)
+
 #define DECLARE_FIFO(type, name)					\
 	struct {							\
 		size_t front, back, size, mask;				\