1 files changed, 27 insertions, 26 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 210b59007d98..3ed39c823826 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -89,8 +89,9 @@
  * Test module load/unload
  */
 
-#define MAX_GC_TIMES		100
-#define MIN_GC_NODES		100
+#define MAX_GC_TIMES_SHIFT	7  /* 128 loops */
+#define GC_NODES_MIN		10
+#define GC_SLEEP_MS_MIN		10
 #define GC_SLEEP_MS		100
 
 #define PTR_DIRTY_BIT		(((uint64_t) 1 << 36))
@@ -371,7 +372,7 @@ static void do_btree_node_write(struct btree *b)
 	SET_PTR_OFFSET(&k.key, 0, PTR_OFFSET(&k.key, 0) +
 		       bset_sector_offset(&b->keys, i));
 
-	if (!bch_bio_alloc_pages(b->bio, __GFP_NOWARN|GFP_NOWAIT)) {
+	if (!bch_bio_alloc_pages(b->bio, GFP_NOWAIT)) {
 		struct bio_vec *bv;
 		void *addr = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
 		struct bvec_iter_all iter_all;
@@ -1578,29 +1579,29 @@ static unsigned int btree_gc_count_keys(struct btree *b)
 
 static size_t btree_gc_min_nodes(struct cache_set *c)
 {
-	size_t min_nodes;
+	size_t min_nodes = GC_NODES_MIN;
 
-	/*
-	 * Since incremental GC would stop 100ms when front
-	 * side I/O comes, so when there are many btree nodes,
-	 * if GC only processes constant (100) nodes each time,
-	 * GC would last a long time, and the front side I/Os
-	 * would run out of the buckets (since no new bucket
-	 * can be allocated during GC), and be blocked again.
-	 * So GC should not process constant nodes, but varied
-	 * nodes according to the number of btree nodes, which
-	 * realized by dividing GC into constant(100) times,
-	 * so when there are many btree nodes, GC can process
-	 * more nodes each time, otherwise, GC will process less
-	 * nodes each time (but no less than MIN_GC_NODES)
-	 */
-	min_nodes = c->gc_stats.nodes / MAX_GC_TIMES;
-	if (min_nodes < MIN_GC_NODES)
-		min_nodes = MIN_GC_NODES;
+	if (atomic_read(&c->search_inflight) == 0) {
+		size_t n = c->gc_stats.nodes >> MAX_GC_TIMES_SHIFT;
+
+		if (min_nodes < n)
+			min_nodes = n;
+	}
 
 	return min_nodes;
 }
 
+static uint64_t btree_gc_sleep_ms(struct cache_set *c)
+{
+	uint64_t sleep_ms;
+
+	if (atomic_read(&c->bucket_wait_cnt) > 0)
+		sleep_ms = GC_SLEEP_MS_MIN;
+	else
+		sleep_ms = GC_SLEEP_MS;
+
+	return sleep_ms;
+}
 
 static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 			    struct closure *writes, struct gc_stat *gc)
@@ -1668,8 +1669,7 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
 		r->b = NULL;
 
-		if (atomic_read(&b->c->search_inflight) &&
-		    gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) {
+		if (gc->nodes >= (gc->nodes_pre + btree_gc_min_nodes(b->c))) {
 			gc->nodes_pre =  gc->nodes;
 			ret = -EAGAIN;
 			break;
@@ -1846,8 +1846,8 @@ static void bch_btree_gc(struct cache_set *c)
 		cond_resched();
 
 		if (ret == -EAGAIN)
-			schedule_timeout_interruptible(msecs_to_jiffies
-						       (GC_SLEEP_MS));
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(btree_gc_sleep_ms(c)));
 		else if (ret)
 			pr_warn("gc failed!\n");
 	} while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
@@ -2822,7 +2822,8 @@ void bch_btree_exit(void)
 
 int __init bch_btree_init(void)
 {
-	btree_io_wq = alloc_workqueue("bch_btree_io", WQ_MEM_RECLAIM, 0);
+	btree_io_wq = alloc_workqueue("bch_btree_io",
+				      WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!btree_io_wq)
 		return -ENOMEM;