bcachefs: BCH_WATERMARK_interior_updates

This adds a new watermark, higher priority than BCH_WATERMARK_reclaim,
for interior btree updates. We've seen a deadlock where journal replay
triggers a ton of btree node merges, and these use up all available open
buckets and then interior updates get stuck.

One cause of this is that we're currently lacking btree node merging on
write buffer btrees - that needs to be fixed as well.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

6 files changed, 12 insertions, 7 deletions

diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index 214b15c84d1f32..a1fc30adf9129d 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -188,8 +188,10 @@ long bch2_bucket_alloc_new_fs(struct bch_dev *ca)
 static inline unsigned open_buckets_reserved(enum bch_watermark watermark)
 {
 	switch (watermark) {
-	case BCH_WATERMARK_reclaim:
+	case BCH_WATERMARK_interior_updates:
 		return 0;
+	case BCH_WATERMARK_reclaim:
+		return OPEN_BUCKETS_COUNT / 6;
 	case BCH_WATERMARK_btree:
 	case BCH_WATERMARK_btree_copygc:
 		return OPEN_BUCKETS_COUNT / 4;
diff --git a/fs/bcachefs/alloc_types.h b/fs/bcachefs/alloc_types.h
index b91b7a46105608..c2226e947c41fb 100644
--- a/fs/bcachefs/alloc_types.h
+++ b/fs/bcachefs/alloc_types.h
@@ -22,7 +22,8 @@ struct bucket_alloc_state {
 	x(copygc)			\
 	x(btree)			\
 	x(btree_copygc)			\
-	x(reclaim)
+	x(reclaim)			\
+	x(interior_updates)
 
 enum bch_watermark {
 #define x(name)	BCH_WATERMARK_##name,
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 9c71e6fb9c41b6..f3f27bb85a5ba4 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1861,7 +1861,7 @@ static void btree_node_write_work(struct work_struct *work)
 	} else {
 		ret = bch2_trans_do(c, NULL, NULL, 0,
 			bch2_btree_node_update_key_get_iter(trans, b, &wbio->key,
-					BCH_WATERMARK_reclaim|
+					BCH_WATERMARK_interior_updates|
 					BCH_TRANS_COMMIT_journal_reclaim|
 					BCH_TRANS_COMMIT_no_enospc|
 					BCH_TRANS_COMMIT_no_check_rw,
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 96669fede7d344..aa9da497074040 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -887,6 +887,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
 			    int ret, unsigned long trace_ip)
 {
 	struct bch_fs *c = trans->c;
+	enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
 
 	switch (ret) {
 	case -BCH_ERR_btree_insert_btree_node_full:
@@ -905,7 +906,7 @@ int bch2_trans_commit_error(struct btree_trans *trans, unsigned flags,
 		 * flag
 		 */
 		if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
-		    (flags & BCH_WATERMARK_MASK) != BCH_WATERMARK_reclaim) {
+		    watermark < BCH_WATERMARK_reclaim) {
 			ret = -BCH_ERR_journal_reclaim_would_deadlock;
 			break;
 		}
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 29aee215384a68..9fd2dd0f468259 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -687,7 +687,7 @@ static void btree_update_nodes_written(struct btree_update *as)
 	 * which may require allocations as well.
 	 */
 	ret = commit_do(trans, &as->disk_res, &journal_seq,
-			BCH_WATERMARK_reclaim|
+			BCH_WATERMARK_interior_updates|
 			BCH_TRANS_COMMIT_no_enospc|
 			BCH_TRANS_COMMIT_no_check_rw|
 			BCH_TRANS_COMMIT_journal_reclaim,
@@ -1121,7 +1121,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 		unsigned journal_flags = watermark|JOURNAL_RES_GET_CHECK;
 
 		if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
-		    watermark != BCH_WATERMARK_reclaim)
+		    watermark < BCH_WATERMARK_reclaim)
 			journal_flags |= JOURNAL_RES_GET_NONBLOCK;
 
 		ret = drop_locks_do(trans,
@@ -1217,7 +1217,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 		 */
 		if (bch2_err_matches(ret, ENOSPC) &&
 		    (flags & BCH_TRANS_COMMIT_journal_reclaim) &&
-		    watermark != BCH_WATERMARK_reclaim) {
+		    watermark < BCH_WATERMARK_reclaim) {
 			ret = -BCH_ERR_journal_reclaim_would_deadlock;
 			goto err;
 		}
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 6387e039f78975..00aaf4bb513974 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -226,6 +226,7 @@ static inline u64 bch2_dev_buckets_reserved(struct bch_dev *ca, enum bch_waterma
 		fallthrough;
 	case BCH_WATERMARK_btree_copygc:
 	case BCH_WATERMARK_reclaim:
+	case BCH_WATERMARK_interior_updates:
 		break;
 	}