btrfs: avoid blocking on space revervation when doing nowait dio writes

When doing a NOWAIT direct IO write, if we can NOCOW then it means we can
proceed with the non-blocking, NOWAIT path. However reserving the metadata
space and qgroup meta space can often result in blocking - flushing
delalloc, wait for ordered extents to complete, trigger transaction
commits, etc, going against the semantics of a NOWAIT write.

So make the NOWAIT write path to try to reserve all the metadata it needs
without resulting in a blocking behaviour - if we get -ENOSPC or -EDQUOT
then return -EAGAIN to make the caller fallback to a blocking direct IO
write.

This is part of a patchset comprised of the following patches:

  btrfs: avoid blocking on page locks with nowait dio on compressed range
  btrfs: avoid blocking nowait dio when locking file range
  btrfs: avoid double nocow check when doing nowait dio writes
  btrfs: stop allocating a path when checking if cross reference exists
  btrfs: free path at can_nocow_extent() before checking for checksum items
  btrfs: release path earlier at can_nocow_extent()
  btrfs: avoid blocking when allocating context for nowait dio read/write
  btrfs: avoid blocking on space revervation when doing nowait dio writes

The following test was run before and after applying this patchset:

  $ cat io-uring-nodatacow-test.sh
  #!/bin/bash

  DEV=/dev/sdc
  MNT=/mnt/sdc

  MOUNT_OPTIONS="-o ssd -o nodatacow"
  MKFS_OPTIONS="-R free-space-tree -O no-holes"

  NUM_JOBS=4
  FILE_SIZE=8G
  RUN_TIME=300

  cat <<EOF > /tmp/fio-job.ini
  [io_uring_rw]
  rw=randrw
  fsync=0
  fallocate=posix
  group_reporting=1
  direct=1
  ioengine=io_uring
  iodepth=64
  bssplit=4k/20:8k/20:16k/20:32k/10:64k/10:128k/5:256k/5:512k/5:1m/5
  filesize=$FILE_SIZE
  runtime=$RUN_TIME
  time_based
  filename=foobar
  directory=$MNT
  numjobs=$NUM_JOBS
  thread
  EOF

  echo performance | \
     tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor

  umount $MNT &> /dev/null
  mkfs.btrfs -f $MKFS_OPTIONS $DEV &> /dev/null
  mount $MOUNT_OPTIONS $DEV $MNT

  fio /tmp/fio-job.ini

  umount $MNT

The test was run a 12 cores box with 64G of ram, using a non-debug kernel
config (Debian's default config) and a spinning disk.

Result before the patchset:

 READ: bw=407MiB/s (427MB/s), 407MiB/s-407MiB/s (427MB/s-427MB/s), io=119GiB (128GB), run=300175-300175msec
WRITE: bw=407MiB/s (427MB/s), 407MiB/s-407MiB/s (427MB/s-427MB/s), io=119GiB (128GB), run=300175-300175msec

Result after the patchset:

 READ: bw=436MiB/s (457MB/s), 436MiB/s-436MiB/s (457MB/s-457MB/s), io=128GiB (137GB), run=300044-300044msec
WRITE: bw=435MiB/s (456MB/s), 435MiB/s-435MiB/s (456MB/s-456MB/s), io=128GiB (137GB), run=300044-300044msec

That's about +7.2% throughput for reads and +6.9% for writes.

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/ctree.h

@@ -2893,7 +2893,7 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
 void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
-				    u64 disk_num_bytes);
+				    u64 disk_num_bytes, bool noflush);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
 int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 end);

fs/btrfs/delalloc-space.c

@@ -289,7 +289,7 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
-				    u64 disk_num_bytes)
+				    u64 disk_num_bytes, bool noflush)
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -308,7 +308,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	 * If we have a transaction open (can happen if we call truncate_block
 	 * from truncate), then we need FLUSH_LIMIT so we don't deadlock.
 	 */
-	if (btrfs_is_free_space_inode(inode)) {
+	if (noflush || btrfs_is_free_space_inode(inode)) {
 		flush = BTRFS_RESERVE_NO_FLUSH;
 	} else {
 		if (current->journal_info)
@@ -333,7 +333,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	 */
 	calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
 				&meta_reserve, &qgroup_reserve);
-	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
+	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true,
+						 noflush);
 	if (ret)
 		return ret;
 	ret = btrfs_reserve_metadata_bytes(fs_info, block_rsv, meta_reserve, flush);
@@ -456,7 +457,7 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 	ret = btrfs_check_data_free_space(inode, reserved, start, len);
 	if (ret < 0)
 		return ret;
-	ret = btrfs_delalloc_reserve_metadata(inode, len, len);
+	ret = btrfs_delalloc_reserve_metadata(inode, len, len, false);
 	if (ret < 0) {
 		btrfs_free_reserved_data_space(inode, *reserved, start, len);
 		extent_changeset_free(*reserved);

fs/btrfs/file.c

@@ -1684,7 +1684,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 		WARN_ON(reserve_bytes == 0);
 		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
 						      reserve_bytes,
-						      reserve_bytes);
+						      reserve_bytes, false);
 		if (ret) {
 			if (!only_release_metadata)
 				btrfs_free_reserved_data_space(BTRFS_I(inode),

fs/btrfs/inode.c

@@ -4705,7 +4705,7 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 			goto out;
 		}
 	}
-	ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize);
+	ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize, false);
 	if (ret < 0) {
 		if (!only_release_metadata)
 			btrfs_free_reserved_data_space(inode, data_reserved,
@@ -7415,6 +7415,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 					 u64 start, u64 len,
 					 unsigned int iomap_flags)
 {
+	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map *em = *map;
 	int type;
@@ -7454,12 +7455,15 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		struct extent_map *em2;
 
 		/* We can NOCOW, so only need to reserve metadata space. */
-		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len);
+		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len,
+						      nowait);
 		if (ret < 0) {
 			/* Our caller expects us to free the input extent map. */
 			free_extent_map(em);
 			*map = NULL;
 			btrfs_dec_nocow_writers(fs_info, block_start);
+			if (nowait && (ret == -ENOSPC || ret == -EDQUOT))
+				ret = -EAGAIN;
 			goto out;
 		}
 		space_reserved = true;
@@ -7483,7 +7487,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		free_extent_map(em);
 		*map = NULL;
 
-		if (iomap_flags & IOMAP_NOWAIT)
+		if (nowait)
 			return -EAGAIN;
 
 		/* We have to COW, so need to reserve metadata and data space. */
@@ -10801,7 +10805,8 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	ret = btrfs_qgroup_reserve_data(inode, &data_reserved, start, num_bytes);
 	if (ret)
 		goto out_free_data_space;
-	ret = btrfs_delalloc_reserve_metadata(inode, num_bytes, disk_num_bytes);
+	ret = btrfs_delalloc_reserve_metadata(inode, num_bytes, disk_num_bytes,
+					      false);
 	if (ret)
 		goto out_qgroup_free_data;
 

fs/btrfs/qgroup.c

@@ -3939,12 +3939,13 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 }
 
 int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
-				enum btrfs_qgroup_rsv_type type, bool enforce)
+				enum btrfs_qgroup_rsv_type type, bool enforce,
+				bool noflush)
 {
 	int ret;
 
 	ret = btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce);
-	if (ret <= 0 && ret != -EDQUOT)
+	if ((ret <= 0 && ret != -EDQUOT) || noflush)
 		return ret;
 
 	ret = try_flush_qgroup(root);

fs/btrfs/qgroup.h

@@ -364,19 +364,23 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode,
 int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 			      enum btrfs_qgroup_rsv_type type, bool enforce);
 int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
-				enum btrfs_qgroup_rsv_type type, bool enforce);
+				enum btrfs_qgroup_rsv_type type, bool enforce,
+				bool noflush);
 /* Reserve metadata space for pertrans and prealloc type */
 static inline int btrfs_qgroup_reserve_meta_pertrans(struct btrfs_root *root,
 				int num_bytes, bool enforce)
 {
 	return __btrfs_qgroup_reserve_meta(root, num_bytes,
-			BTRFS_QGROUP_RSV_META_PERTRANS, enforce);
+					   BTRFS_QGROUP_RSV_META_PERTRANS,
+					   enforce, false);
 }
 static inline int btrfs_qgroup_reserve_meta_prealloc(struct btrfs_root *root,
-				int num_bytes, bool enforce)
+						     int num_bytes, bool enforce,
+						     bool noflush)
 {
 	return __btrfs_qgroup_reserve_meta(root, num_bytes,
-			BTRFS_QGROUP_RSV_META_PREALLOC, enforce);
+					   BTRFS_QGROUP_RSV_META_PREALLOC,
+					   enforce, noflush);
 }
 
 void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,

fs/btrfs/relocation.c

@@ -2997,7 +2997,8 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 
 		/* Reserve metadata for this range */
 		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
-						      clamped_len, clamped_len);
+						      clamped_len, clamped_len,
+						      false);
 		if (ret)
 			goto release_page;
 

fs/btrfs/root-tree.c

@@ -509,7 +509,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 		/* One for parent inode, two for dir entries */
 		qgroup_num_bytes = 3 * fs_info->nodesize;
 		ret = btrfs_qgroup_reserve_meta_prealloc(root,
-				qgroup_num_bytes, true);
+							 qgroup_num_bytes, true,
+							 false);
 		if (ret)
 			return ret;
 	}