bcachefs: Allocator prefers not to expand mi.btree_allocated bitmap

We now have a small bitmap in the member info section of the superblock
for "regions that have btree nodes", so that if we ever have to scan for
btree nodes in repair we don't have to scan the whole device(s).

This tweaks the allocator to prefer allocating from regions that are
already marked in this bitmap.

Signed-off-by: Kent Overstreet <[email protected]>

Author: Kent Overstreet

fs/bcachefs/alloc_foreground.c

@@ -71,7 +71,7 @@ void bch2_reset_alloc_cursors(struct bch_fs *c)
 {
 	rcu_read_lock();
 	for_each_member_device_rcu(c, ca, NULL)
-		ca->alloc_cursor = 0;
+		memset(ca->alloc_cursor, 0, sizeof(ca->alloc_cursor));
 	rcu_read_unlock();
 }
 
@@ -389,7 +389,8 @@ bch2_bucket_alloc_early(struct btree_trans *trans,
 	struct bkey_s_c k, ck;
 	struct open_bucket *ob = NULL;
 	u64 first_bucket = max_t(u64, ca->mi.first_bucket, ca->new_fs_bucket_idx);
-	u64 alloc_start = max(first_bucket, READ_ONCE(ca->alloc_cursor));
+	u64 *dev_alloc_cursor = &ca->alloc_cursor[s->btree_bitmap];
+	u64 alloc_start = max(first_bucket, *dev_alloc_cursor);
 	u64 alloc_cursor = alloc_start;
 	int ret;
 
@@ -405,8 +406,7 @@ bch2_bucket_alloc_early(struct btree_trans *trans,
 again:
 	for_each_btree_key_norestart(trans, iter, BTREE_ID_alloc, POS(ca->dev_idx, alloc_cursor),
 			   BTREE_ITER_slots, k, ret) {
-		struct bch_alloc_v4 a_convert;
-		const struct bch_alloc_v4 *a;
+		u64 bucket = k.k->p.offset;
 
 		if (bkey_ge(k.k->p, POS(ca->dev_idx, ca->mi.nbuckets)))
 			break;
@@ -415,7 +415,24 @@ bch2_bucket_alloc_early(struct btree_trans *trans,
 		    is_superblock_bucket(ca, k.k->p.offset))
 			continue;
 
-		a = bch2_alloc_to_v4(k, &a_convert);
+		if (s->btree_bitmap != BTREE_BITMAP_ANY &&
+		    s->btree_bitmap != bch2_dev_btree_bitmap_marked_sectors(ca,
+				bucket_to_sector(ca, bucket), ca->mi.bucket_size)) {
+			if (s->btree_bitmap == BTREE_BITMAP_YES &&
+			    bucket_to_sector(ca, bucket) > 64ULL << ca->mi.btree_bitmap_shift)
+				break;
+
+			bucket = sector_to_bucket(ca,
+					round_up(bucket_to_sector(ca, bucket) + 1,
+						 1ULL << ca->mi.btree_bitmap_shift));
+			bch2_btree_iter_set_pos(&iter, POS(ca->dev_idx, bucket));
+			s->buckets_seen++;
+			s->skipped_mi_btree_bitmap++;
+			continue;
+		}
+
+		struct bch_alloc_v4 a_convert;
+		const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &a_convert);
 		if (a->data_type != BCH_DATA_free)
 			continue;
 
@@ -441,7 +458,6 @@ bch2_bucket_alloc_early(struct btree_trans *trans,
 	bch2_trans_iter_exit(trans, &iter);
 
 	alloc_cursor = iter.pos.offset;
-	ca->alloc_cursor = alloc_cursor;
 
 	if (!ob && ret)
 		ob = ERR_PTR(ret);
@@ -451,6 +467,8 @@ bch2_bucket_alloc_early(struct btree_trans *trans,
 		goto again;
 	}
 
+	*dev_alloc_cursor = alloc_cursor;
+
 	return ob;
 }
 
@@ -463,7 +481,8 @@ static struct open_bucket *bch2_bucket_alloc_freelist(struct btree_trans *trans,
 	struct btree_iter iter;
 	struct bkey_s_c k;
 	struct open_bucket *ob = NULL;
-	u64 alloc_start = max_t(u64, ca->mi.first_bucket, READ_ONCE(ca->alloc_cursor));
+	u64 *dev_alloc_cursor = &ca->alloc_cursor[s->btree_bitmap];
+	u64 alloc_start = max_t(u64, ca->mi.first_bucket, READ_ONCE(*dev_alloc_cursor));
 	u64 alloc_cursor = alloc_start;
 	int ret;
 
@@ -485,6 +504,26 @@ static struct open_bucket *bch2_bucket_alloc_freelist(struct btree_trans *trans,
 
 			s->buckets_seen++;
 
+			u64 bucket = alloc_cursor & ~(~0ULL << 56);
+			if (s->btree_bitmap != BTREE_BITMAP_ANY &&
+			    s->btree_bitmap != bch2_dev_btree_bitmap_marked_sectors(ca,
+					bucket_to_sector(ca, bucket), ca->mi.bucket_size)) {
+				if (s->btree_bitmap == BTREE_BITMAP_YES &&
+				    bucket_to_sector(ca, bucket) > 64ULL << ca->mi.btree_bitmap_shift)
+					goto fail;
+
+				bucket = sector_to_bucket(ca,
+						round_up(bucket_to_sector(ca, bucket) + 1,
+							 1ULL << ca->mi.btree_bitmap_shift));
+				u64 genbits = alloc_cursor >> 56;
+				alloc_cursor = bucket | (genbits << 56);
+
+				if (alloc_cursor > k.k->p.offset)
+					bch2_btree_iter_set_pos(&iter, POS(ca->dev_idx, alloc_cursor));
+				s->skipped_mi_btree_bitmap++;
+				continue;
+			}
+
 			ob = try_alloc_bucket(trans, ca, watermark,
 					      alloc_cursor, s, k, cl);
 			if (ob) {
@@ -496,10 +535,9 @@ static struct open_bucket *bch2_bucket_alloc_freelist(struct btree_trans *trans,
 		if (ob || ret)
 			break;
 	}
+fail:
 	bch2_trans_iter_exit(trans, &iter);
 
-	ca->alloc_cursor = alloc_cursor;
-
 	if (!ob && ret)
 		ob = ERR_PTR(ret);
 
@@ -508,6 +546,8 @@ static struct open_bucket *bch2_bucket_alloc_freelist(struct btree_trans *trans,
 		goto again;
 	}
 
+	*dev_alloc_cursor = alloc_cursor;
+
 	return ob;
 }
 
@@ -537,6 +577,7 @@ static noinline void trace_bucket_alloc2(struct bch_fs *c, struct bch_dev *ca,
 	prt_printf(&buf, "need journal commit\t%llu\n", s->skipped_need_journal_commit);
 	prt_printf(&buf, "nocow\t%llu\n",	s->skipped_nocow);
 	prt_printf(&buf, "nouse\t%llu\n",	s->skipped_nouse);
+	prt_printf(&buf, "mi_btree_bitmap\t%llu\n", s->skipped_mi_btree_bitmap);
 
 	if (!IS_ERR(ob)) {
 		prt_printf(&buf, "allocated\t%llu\n", ob->bucket);
@@ -571,7 +612,9 @@ static struct open_bucket *bch2_bucket_alloc_trans(struct btree_trans *trans,
 	struct open_bucket *ob = NULL;
 	bool freespace = READ_ONCE(ca->mi.freespace_initialized);
 	u64 avail;
-	struct bucket_alloc_state s = { 0 };
+	struct bucket_alloc_state s = {
+		.btree_bitmap = data_type == BCH_DATA_btree,
+	};
 	bool waiting = false;
 again:
 	bch2_dev_usage_read_fast(ca, usage);
@@ -609,6 +652,11 @@ static struct open_bucket *bch2_bucket_alloc_trans(struct btree_trans *trans,
 	if (s.skipped_need_journal_commit * 2 > avail)
 		bch2_journal_flush_async(&c->journal, NULL);
 
+	if (!ob && s.btree_bitmap != BTREE_BITMAP_ANY) {
+		s.btree_bitmap = BTREE_BITMAP_ANY;
+		goto alloc;
+	}
+
 	if (!ob && freespace && c->curr_recovery_pass <= BCH_RECOVERY_PASS_check_alloc_info) {
 		freespace = false;
 		goto alloc;

fs/bcachefs/alloc_types.h

@@ -9,11 +9,18 @@
 #include "fifo.h"
 
 struct bucket_alloc_state {
+	enum {
+		BTREE_BITMAP_NO,
+		BTREE_BITMAP_YES,
+		BTREE_BITMAP_ANY,
+	}	btree_bitmap;
+
 	u64	buckets_seen;
 	u64	skipped_open;
 	u64	skipped_need_journal_commit;
 	u64	skipped_nocow;
 	u64	skipped_nouse;
+	u64	skipped_mi_btree_bitmap;
 };
 
 #define BCH_WATERMARKS()		\

fs/bcachefs/bcachefs.h

@@ -587,7 +587,7 @@ struct bch_dev {
 
 	/* Allocator: */
 	u64			new_fs_bucket_idx;
-	u64			alloc_cursor;
+	u64			alloc_cursor[3];
 
 	unsigned		nr_open_buckets;
 	unsigned		nr_btree_reserve;