BTRFS hot relocation support

index 1c11be1..956115d 100644
@@ -1636,6 +1636,8 @@ struct btrfs_fs_info {
 	struct btrfs_dev_replace dev_replace;
 
 	atomic_t mutually_exclusive_operation_running;
+
+	void *hot_reloc;
 };
 
 /*

713 lines not on this page · raw message

43 lines not on this page · raw message

index 9ee751f..31e1d17 100644
@@ -309,8 +309,13 @@ static void btrfs_put_super(struct super_block *sb)
 	 * process...  Whom would you report that to?
 	 */
 
+	/* Hot data relocation */
+	if (btrfs_test_opt(btrfs_sb(sb)->tree_root, HOT_MOVE))
+		hot_relocate_exit(btrfs_sb(sb));
+
 	/* Hot data tracking */
-	if (btrfs_test_opt(btrfs_sb(sb)->tree_root, HOT_TRACK))
+	if (btrfs_test_opt(btrfs_sb(sb)->tree_root, HOT_MOVE)
+		|| btrfs_test_opt(btrfs_sb(sb)->tree_root, HOT_TRACK))
 		hot_track_exit(sb);
 }
 

@@ -325,7 +330,7 @@ enum {
 	Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
 	Opt_check_integrity, Opt_check_integrity_including_extent_data,
 	Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_hot_track,
-	Opt_err,
+	Opt_hot_move, Opt_err,
 };
 
 static match_table_t tokens = {

@@ -366,6 +371,7 @@ static match_table_t tokens = {
 	{Opt_check_integrity_print_mask, "check_int_print_mask=%d"},
 	{Opt_fatal_errors, "fatal_errors=%s"},
 	{Opt_hot_track, "hot_track"},
+	{Opt_hot_move, "hot_move"},
 	{Opt_err, NULL},
 };
 

@@ -634,6 +640,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		case Opt_hot_track:
 			btrfs_set_opt(info->mount_opt, HOT_TRACK);
 			break;
+		case Opt_hot_move:
+			btrfs_set_opt(info->mount_opt, HOT_MOVE);
+			break;
 		case Opt_err:
 			printk(KERN_INFO "btrfs: unrecognized mount option "
 			       "'%s'\n", p);

@@ -853,17 +862,26 @@ static int btrfs_fill_super(struct super_block *sb,
 		goto fail_close;
 	}
 
-	if (btrfs_test_opt(fs_info->tree_root, HOT_TRACK)) {
+	if (btrfs_test_opt(fs_info->tree_root, HOT_MOVE)
+		|| btrfs_test_opt(fs_info->tree_root, HOT_TRACK)) {
 		err = hot_track_init(sb);
 		if (err)
 			goto fail_hot;
 	}
 
+	if (btrfs_test_opt(fs_info->tree_root, HOT_MOVE)) {
+		err = hot_relocate_init(fs_info);
+		if (err)
+			goto fail_reloc;
+	}
+
 	save_mount_options(sb, data);
 	cleancache_init_fs(sb);
 	sb->s_flags |= MS_ACTIVE;
 	return 0;
 
+fail_reloc:
+	hot_track_exit(sb);
 fail_hot:
 	dput(sb->s_root);
 	sb->s_root = NULL;

@@ -964,6 +982,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",fatal_errors=panic");
 	if (btrfs_test_opt(root, HOT_TRACK))
 		seq_puts(seq, ",hot_track");
+	if (btrfs_test_opt(root, HOT_MOVE))
+		seq_puts(seq, ",hot_move");
 	return 0;
 }
 

index dbc90d4..f013182 100644
@@ -44,6 +44,7 @@ static void hot_comm_item_init(struct hot_comm_item *ci, int type)
 	clear_bit(HOT_IN_LIST, &ci->delete_flag);
 	clear_bit(HOT_DELETING, &ci->delete_flag);
 	INIT_LIST_HEAD(&ci->track_list);
+	INIT_LIST_HEAD(&ci->reloc_list);
 	memset(&ci->hot_freq_data, 0, sizeof(struct hot_freq_data));
 	ci->hot_freq_data.avg_delta_reads = (u64) -1;
 	ci->hot_freq_data.avg_delta_writes = (u64) -1;

index 1009377..98bb092 100644
@@ -75,6 +75,7 @@ struct hot_comm_item {
 	unsigned long delete_flag;
 	struct rcu_head c_rcu;
 	struct list_head track_list;		/* link to *_map[] */
+	struct list_head reloc_list;		/* used in hot relocation*/
 };
 
 /* An item representing an inode and its access frequency */

index 745cac4..1c11be1 100644
@@ -963,6 +963,12 @@ struct btrfs_dev_replace_item {
 #define BTRFS_BLOCK_GROUP_RAID10	(1ULL << 6)
 #define BTRFS_BLOCK_GROUP_RAID5    (1 << 7)
 #define BTRFS_BLOCK_GROUP_RAID6    (1 << 8)
+/*
+ * New block groups for use with BTRFS hot relocation feature.
+ * When BTRFS hot relocation is enabled, *_NONROT block group is
+ * forced to nonrotating drives.
+ */
+#define BTRFS_BLOCK_GROUP_DATA_NONROT	(1ULL << 9)
 #define BTRFS_BLOCK_GROUP_RESERVED	BTRFS_AVAIL_ALLOC_BIT_SINGLE
 
 enum btrfs_raid_types {

@@ -978,7 +984,8 @@ enum btrfs_raid_types {
 
 #define BTRFS_BLOCK_GROUP_TYPE_MASK	(BTRFS_BLOCK_GROUP_DATA |    \
 					 BTRFS_BLOCK_GROUP_SYSTEM |  \
-					 BTRFS_BLOCK_GROUP_METADATA)
+					 BTRFS_BLOCK_GROUP_METADATA | \
+					 BTRFS_BLOCK_GROUP_DATA_NONROT)
 
 #define BTRFS_BLOCK_GROUP_PROFILE_MASK	(BTRFS_BLOCK_GROUP_RAID0 |   \
 					 BTRFS_BLOCK_GROUP_RAID1 |   \

@@ -1521,6 +1528,7 @@ struct btrfs_fs_info {
 	struct list_head space_info;
 
 	struct btrfs_space_info *data_sinfo;
+	struct btrfs_space_info *nonrot_data_sinfo;
 
 	struct reloc_control *reloc_ctl;
 

@@ -1545,6 +1553,7 @@ struct btrfs_fs_info {
 	u64 avail_data_alloc_bits;
 	u64 avail_metadata_alloc_bits;
 	u64 avail_system_alloc_bits;
+	u64 avail_data_nonrot_alloc_bits;
 
 	/* restriper state */
 	spinlock_t balance_lock;

@@ -1557,6 +1566,7 @@ struct btrfs_fs_info {
 
 	unsigned data_chunk_allocations;
 	unsigned metadata_ratio;
+	unsigned data_nonrot_chunk_allocations;
 
 	void *bdev_holder;
 

@@ -1928,6 +1938,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
 #define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR	(1 << 22)
 #define BTRFS_MOUNT_HOT_TRACK		(1 << 23)
+#define BTRFS_MOUNT_HOT_MOVE		(1 << 24)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)

@@ -3043,6 +3054,8 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_root *root,
 int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root,
 			  u64 objectid, u64 offset, u64 bytenr);
+struct btrfs_block_group_cache *btrfs_lookup_first_block_group(
+				struct btrfs_fs_info *info, u64 bytenr);
 struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 struct btrfs_fs_info *info,
 						 u64 bytenr);

@@ -3093,6 +3106,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
 			 u64 root_objectid, u64 owner, u64 offset, int for_cow);
+struct btrfs_block_group_cache *next_block_group(struct btrfs_root *root,
+			 struct btrfs_block_group_cache *cache);
 
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				    struct btrfs_root *root);

@@ -3122,8 +3137,14 @@ enum btrfs_reserve_flush_enum {
 	BTRFS_RESERVE_FLUSH_ALL,
 };
 
-int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
-void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes);
+enum {
+	TYPE_ROT = 0,	/* rot -> rotating */
+	TYPE_NONROT,	/* nonrot -> nonrotating */
+	MAX_RELOC_TYPES,
+};
+
+int btrfs_check_data_free_space(struct inode *inode, u64 bytes, int *flag);
+void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes, int flag);
 void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,

@@ -3138,8 +3159,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
 				      u64 qgroup_reserved);
 int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);
 void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes, int *flag);
+void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes, int flag);
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
 struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root,
 					      unsigned short type);

@@ -3612,7 +3633,7 @@ int btrfs_release_file(struct inode *inode, struct file *file);
 int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
 		      struct page **pages, size_t num_pages,
 		      loff_t pos, size_t write_bytes,
-		      struct extent_state **cached);
+		      struct extent_state **cached, int flag);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,

279 lines not on this page · raw message

90 lines not on this page · raw message

index 41fb81e..ef63452 100644
@@ -19,6 +19,8 @@
 #define EXTENT_FIRST_DELALLOC (1 << 12)
 #define EXTENT_NEED_WAIT (1 << 13)
 #define EXTENT_DAMAGED (1 << 14)
+#define EXTENT_HOT (1 << 15)
+#define EXTENT_COLD (1 << 16)
 #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
 #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 

@@ -51,6 +53,8 @@
 #define EXTENT_END_WRITEBACK	 0x20
 #define EXTENT_SET_PRIVATE2	 0x40
 #define EXTENT_CLEAR_ACCOUNTING  0x80
+#define EXTENT_CLEAR_HOT	 0x100
+#define EXTENT_CLEAR_COLD	 0x200
 
 /*
  * page->private values.  Every page that is controlled by the extent

@@ -237,6 +241,9 @@ int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask);
 int set_extent_defrag(struct extent_io_tree *tree, u64 start, u64 end,
 		      struct extent_state **cached_state, gfp_t mask);
+void set_extent_hot(struct inode *inode, u64 start, u64 end,
+			struct extent_state **cached_state,
+			int type, int flag);
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
 			  u64 *start_ret, u64 *end_ret, unsigned long bits,
 			  struct extent_state **cached_state);

index 4205ba7..e3c58c4 100644
@@ -41,6 +41,7 @@
 #include "locking.h"
 #include "compat.h"
 #include "volumes.h"
+#include "hot_relocate.h"
 
 static struct kmem_cache *btrfs_inode_defrag_cachep;
 /*

@@ -500,7 +501,7 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages)
 int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
 			     struct page **pages, size_t num_pages,
 			     loff_t pos, size_t write_bytes,
-			     struct extent_state **cached)
+			     struct extent_state **cached, int flag)
 {
 	int err = 0;
 	int i;

@@ -514,6 +515,11 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
 	num_bytes = ALIGN(write_bytes + pos - start_pos, root->sectorsize);
 
 	end_of_last_block = start_pos + num_bytes - 1;
+
+	if (btrfs_test_opt(root, HOT_MOVE))
+		set_extent_hot(inode, start_pos, end_of_last_block,
+				cached, flag, 0);
+
 	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
 					cached);
 	if (err)

@@ -1294,7 +1300,8 @@ again:
 
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos,
 				  last_pos - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
-				  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
+				  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG |
+				  EXTENT_HOT | EXTENT_COLD,
 				  0, 0, &cached_state, GFP_NOFS);
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 				     start_pos, last_pos - 1, &cached_state,

@@ -1350,6 +1357,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 				    PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 		size_t dirty_pages;
 		size_t copied;
+		int flag = TYPE_ROT;
 
 		WARN_ON(num_pages > nrptrs);
 

@@ -1363,7 +1371,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		}
 
 		ret = btrfs_delalloc_reserve_space(inode,
-					num_pages << PAGE_CACHE_SHIFT);
+					num_pages << PAGE_CACHE_SHIFT, &flag);
 		if (ret)
 			break;
 

@@ -1377,7 +1385,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 				    force_page_uptodate);
 		if (ret) {
 			btrfs_delalloc_release_space(inode,
-					num_pages << PAGE_CACHE_SHIFT);
+					num_pages << PAGE_CACHE_SHIFT, flag);
 			break;
 		}
 

@@ -1416,16 +1424,16 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			}
 			btrfs_delalloc_release_space(inode,
 					(num_pages - dirty_pages) <<
-					PAGE_CACHE_SHIFT);
+					PAGE_CACHE_SHIFT, flag);
 		}
 
 		if (copied > 0) {
 			ret = btrfs_dirty_pages(root, inode, pages,
 						dirty_pages, pos, copied,
-						NULL);
+						NULL, flag);
 			if (ret) {
 				btrfs_delalloc_release_space(inode,
-					dirty_pages << PAGE_CACHE_SHIFT);
+					dirty_pages << PAGE_CACHE_SHIFT, flag);
 				btrfs_drop_pages(pages, num_pages);
 				break;
 			}

@@ -2150,6 +2158,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	u64 locked_end;
 	struct extent_map *em;
 	int blocksize = BTRFS_I(inode)->root->sectorsize;
+	int flag = TYPE_ROT;
 	int ret;
 
 	alloc_start = round_down(offset, blocksize);

@@ -2166,7 +2175,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 	 * Make sure we have enough space before we do the
 	 * allocation.
 	 */
-	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
+	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start, &flag);
 	if (ret)
 		return ret;
 	if (root->fs_info->quota_enabled) {

@@ -2281,7 +2290,7 @@ out:
 		btrfs_qgroup_free(root, alloc_end - alloc_start);
 out_reserve_fail:
 	/* Let go of our reservation. */
-	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
+	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start, flag);
 	return ret;
 }
 

index e530096..18f0467 100644
@@ -1004,7 +1004,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	io_ctl_zero_remaining_pages(&io_ctl);
 
 	ret = btrfs_dirty_pages(root, inode, io_ctl.pages, io_ctl.num_pages,
-				0, i_size_read(inode), &cached_state);
+				0, i_size_read(inode), &cached_state, TYPE_ROT);
 	io_ctl_drop_pages(&io_ctl);
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
 			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);

index 2c66ddb..0f8268c 100644
@@ -403,6 +403,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	u64 alloc_hint = 0;
 	int ret;
 	int prealloc;
+	int flag = TYPE_ROT;
 	bool retry = false;
 
 	/* only fs tree and subvol/snap needs ino cache */

@@ -492,17 +493,17 @@ again:
 	/* Just to make sure we have enough space */
 	prealloc += 8 * PAGE_CACHE_SIZE;
 
-	ret = btrfs_delalloc_reserve_space(inode, prealloc);
+	ret = btrfs_delalloc_reserve_space(inode, prealloc, &flag);
 	if (ret)
 		goto out_put;
 
 	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
 					      prealloc, prealloc, &alloc_hint);
 	if (ret) {
-		btrfs_delalloc_release_space(inode, prealloc);
+		btrfs_delalloc_release_space(inode, prealloc, flag);
 		goto out_put;
 	}
-	btrfs_free_reserved_data_space(inode, prealloc);
+	btrfs_free_reserved_data_space(inode, prealloc, flag);
 
 	ret = btrfs_write_out_ino_cache(root, trans, path);
 out_put:

274 lines not on this page · raw message

index 0f81d67..9401229 100644
@@ -56,6 +56,7 @@
 #include "rcu-string.h"
 #include "send.h"
 #include "dev-replace.h"
+#include "hot_relocate.h"
 
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)

@@ -1001,6 +1002,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	int ret;
 	int i;
 	int i_done;
+	int flag = TYPE_ROT;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
 	struct extent_io_tree *tree;

@@ -1013,7 +1015,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
 
 	ret = btrfs_delalloc_reserve_space(inode,
-					   page_cnt << PAGE_CACHE_SHIFT);
+					   page_cnt << PAGE_CACHE_SHIFT, &flag);
 	if (ret)
 		return ret;
 	i_done = 0;

@@ -1101,9 +1103,12 @@ again:
 		BTRFS_I(inode)->outstanding_extents++;
 		spin_unlock(&BTRFS_I(inode)->lock);
 		btrfs_delalloc_release_space(inode,
-				     (page_cnt - i_done) << PAGE_CACHE_SHIFT);
+			     (page_cnt - i_done) << PAGE_CACHE_SHIFT, flag);
 	}
 
+	if (btrfs_test_opt(BTRFS_I(inode)->root, HOT_MOVE))
+		set_extent_hot(inode, page_start, page_end - 1,
+				&cached_state, flag, 0);
 
 	set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
 			  &cached_state, GFP_NOFS);

@@ -1126,7 +1131,8 @@ out:
 		unlock_page(pages[i]);
 		page_cache_release(pages[i]);
 	}
-	btrfs_delalloc_release_space(inode, page_cnt << PAGE_CACHE_SHIFT);
+	btrfs_delalloc_release_space(inode,
+				page_cnt << PAGE_CACHE_SHIFT, flag);
 	return ret;
 
 }

@@ -3021,8 +3027,9 @@ static long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
 	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
 		       BTRFS_BLOCK_GROUP_SYSTEM,
 		       BTRFS_BLOCK_GROUP_METADATA,
-		       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
-	int num_types = 4;
+		       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA,
+		       BTRFS_BLOCK_GROUP_DATA_NONROT};
+	int num_types = 5;
 	int alloc_size;
 	int ret = 0;
 	u64 slot_count = 0;

index 4febca4..9ea9d6c 100644
@@ -31,6 +31,7 @@
 #include "async-thread.h"
 #include "free-space-cache.h"
 #include "inode-map.h"
+#include "hot_relocate.h"
 
 /*
  * backref_node, mapping_node and tree_block start with this

@@ -2938,12 +2939,13 @@ int prealloc_file_extent_cluster(struct inode *inode,
 	u64 num_bytes;
 	int nr = 0;
 	int ret = 0;
+	int flag = TYPE_ROT;
 
 	BUG_ON(cluster->start != cluster->boundary[0]);
 	mutex_lock(&inode->i_mutex);
 
 	ret = btrfs_check_data_free_space(inode, cluster->end +
-					  1 - cluster->start);
+					  1 - cluster->start, &flag);
 	if (ret)
 		goto out;
 

@@ -2965,7 +2967,7 @@ int prealloc_file_extent_cluster(struct inode *inode,
 		nr++;
 	}
 	btrfs_free_reserved_data_space(inode, cluster->end +
-				       1 - cluster->start);
+				       1 - cluster->start, flag);
 out:
 	mutex_unlock(&inode->i_mutex);
 	return ret;

index f13517b..9ee751f 100644
@@ -58,6 +58,7 @@
 #include "rcu-string.h"
 #include "dev-replace.h"
 #include "free-space-cache.h"
+#include "hot_relocate.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/btrfs.h>

@@ -1521,7 +1522,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	mutex_lock(&fs_info->chunk_mutex);
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
-		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
+		if ((found->flags & BTRFS_BLOCK_GROUP_DATA) ||
+			(found->flags & BTRFS_BLOCK_GROUP_DATA_NONROT)) {
 			total_free_data += found->disk_total - found->disk_used;
 			total_free_data -=
 				btrfs_account_ro_block_groups_free_space(found);

index 8bffb91..8b6beec 100644
@@ -1451,6 +1451,9 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		all_avail = root->fs_info->avail_data_alloc_bits |
 			    root->fs_info->avail_system_alloc_bits |
 			    root->fs_info->avail_metadata_alloc_bits;
+		if (btrfs_test_opt(root, HOT_MOVE))
+			all_avail |=
+				root->fs_info->avail_data_nonrot_alloc_bits;
 	} while (read_seqretry(&root->fs_info->profiles_lock, seq));
 
 	num_devices = root->fs_info->fs_devices->num_devices;

@@ -3728,7 +3731,8 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	devs_increment = btrfs_raid_array[index].devs_increment;
 	ncopies = btrfs_raid_array[index].ncopies;
 
-	if (type & BTRFS_BLOCK_GROUP_DATA) {
+	if (type & BTRFS_BLOCK_GROUP_DATA ||
+		type & BTRFS_BLOCK_GROUP_DATA_NONROT) {
 		max_stripe_size = 1024 * 1024 * 1024;
 		max_chunk_size = 10 * max_stripe_size;
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {

@@ -3767,9 +3771,30 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		struct btrfs_device *device;
 		u64 max_avail;
 		u64 dev_offset;
+		int dev_rot;
+		int skip = 0;
 
 		device = list_entry(cur, struct btrfs_device, dev_alloc_list);
 
+		/*
+		 * If HOT_MOVE is set, the chunk type being allocated
+		 * determines which disks the data may be allocated on.
+		 * This can cause problems if, for example, the data alloc
+		 * profile is RAID0 and there are only two devices, 1 SSD +
+		 * 1 HDD. All allocations to BTRFS_BLOCK_GROUP_DATA_NONROT
+		 * in this config will return -ENOSPC as the allocation code
+		 * can't find allowable space for the second stripe.
+		 */
+		dev_rot = !blk_queue_nonrot(bdev_get_queue(device->bdev));
+		if (btrfs_test_opt(extent_root, HOT_MOVE)) {
+			int ret1 = type & (BTRFS_BLOCK_GROUP_DATA |
+				BTRFS_BLOCK_GROUP_METADATA |
+				BTRFS_BLOCK_GROUP_SYSTEM) && !dev_rot;
+			int ret2 = type & BTRFS_BLOCK_GROUP_DATA_NONROT && dev_rot;
+			if (ret1 || ret2)
+				skip = 1;
+		}
+
 		cur = cur->next;
 
 		if (!device->writeable) {

@@ -3778,7 +3803,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			continue;
 		}
 
-		if (!device->in_fs_metadata ||
+		if (skip || !device->in_fs_metadata ||
 		    device->is_tgtdev_for_dev_replace)
 			continue;
 

index ae28b86..debf580 100644
@@ -25,7 +25,7 @@
  * The relocation code below operates on the heat map lists to identify
  * hot or cold data logical file ranges that are candidates for relocation.
  * The triggering mechanism for relocation is controlled by a global heat
- * threshold integer value (HOT_RELOC_THRESHOLD). Ranges are
+ * threshold integer value (sysctl_hot_reloc_thresh). Ranges are
  * queued for relocation by the periodically executing relocate kthread,
  * which updates the global heat threshold and responds to space pressure
  * on the nonrotating disks.

@@ -53,6 +53,15 @@
  * (assuming, critically, the HOT_MOVE option is set at mount time).
  */
 
+int sysctl_hot_reloc_thresh = 150;
+EXPORT_SYMBOL_GPL(sysctl_hot_reloc_thresh);
+
+int sysctl_hot_reloc_interval __read_mostly = 120;
+EXPORT_SYMBOL_GPL(sysctl_hot_reloc_interval);
+
+int sysctl_hot_reloc_max_items __read_mostly = 250;
+EXPORT_SYMBOL_GPL(sysctl_hot_reloc_max_items);
+
 /*
  * Returns the ratio of nonrotating disks that are full.
  * If no nonrotating disk is found, returns THRESH_MAX_VALUE + 1.

@@ -103,7 +112,7 @@ static int hot_calc_nonrot_ratio(struct hot_reloc *hot_reloc)
 static int hot_update_threshold(struct hot_reloc *hot_reloc,
 				int update)
 {
-	int thresh = hot_reloc->thresh;
+	int thresh = sysctl_hot_reloc_thresh;
 	int ratio = hot_calc_nonrot_ratio(hot_reloc);
 
 	/* Sometimes update global threshold, others not */

@@ -127,7 +136,7 @@ static int hot_update_threshold(struct hot_reloc *hot_reloc,
 			thresh = 0;
 	}
 
-	hot_reloc->thresh = thresh;
+	sysctl_hot_reloc_thresh = thresh;
 	return ratio;
 }
 

@@ -215,7 +224,7 @@ static int hot_queue_extent(struct hot_reloc *hot_reloc,
 			*counter = *counter + 1;
 		}
 
-		if (*counter >= HOT_RELOC_MAX_ITEMS)
+		if (*counter >= sysctl_hot_reloc_max_items)
 			break;
 
 		if (kthread_should_stop()) {

@@ -293,7 +302,7 @@ again:
 		while (1) {
 			lock_extent(tree, page_start, page_end);
 			ordered = btrfs_lookup_ordered_extent(inode,
-							page_start);
+							      page_start);
 			unlock_extent(tree, page_start, page_end);
 			if (!ordered)
 				break;

@@ -559,7 +568,7 @@ void hot_do_relocate(struct hot_reloc *hot_reloc)
 
 	run++;
 	ratio = hot_update_threshold(hot_reloc, !(run % 15));
-	thresh = hot_reloc->thresh;
+	thresh = sysctl_hot_reloc_thresh;
 
 	INIT_LIST_HEAD(&hot_reloc->hot_relocq[TYPE_NONROT]);
 

@@ -569,7 +578,7 @@ void hot_do_relocate(struct hot_reloc *hot_reloc)
 	if (count_to_hot == 0)
 		return;
 
-	count_to_cold = HOT_RELOC_MAX_ITEMS;
+	count_to_cold = sysctl_hot_reloc_max_items;
 
 	/* Don't move cold data to HDD unless there's space pressure */
 	if (ratio < HIGH_WATER_LEVEL)

@@ -653,7 +662,7 @@ static int hot_relocate_kthread(void *arg)
 	unsigned long delay;
 
 	do {
-		delay = HZ * HOT_RELOC_INTERVAL;
+		delay = HZ * sysctl_hot_reloc_interval;
 		if (mutex_trylock(&hot_reloc->hot_reloc_mutex)) {
 			hot_do_relocate(hot_reloc);
 			mutex_unlock(&hot_reloc->hot_reloc_mutex);

@@ -685,7 +694,6 @@ int hot_relocate_init(struct btrfs_fs_info *fs_info)
 
 	fs_info->hot_reloc = hot_reloc;
 	hot_reloc->fs_info = fs_info;
-	hot_reloc->thresh = HOT_RELOC_THRESHOLD;
 	for (i = 0; i < MAX_RELOC_TYPES; i++)
 		INIT_LIST_HEAD(&hot_reloc->hot_relocq[i]);
 	mutex_init(&hot_reloc->hot_reloc_mutex);

index 1b1cfb5..94defe6 100644
@@ -18,10 +18,6 @@
 #include "btrfs_inode.h"
 #include "volumes.h"
 
-#define HOT_RELOC_INTERVAL  120
-#define HOT_RELOC_THRESHOLD 150
-#define HOT_RELOC_MAX_ITEMS 250
-
 #define HEAT_MAX_VALUE    (MAP_SIZE - 1)
 #define HIGH_WATER_LEVEL  75 /* when to raise the threshold */
 #define LOW_WATER_LEVEL   50 /* when to lower the threshold */

@@ -32,7 +28,6 @@
 struct hot_reloc {
 	struct btrfs_fs_info *fs_info;
 	struct list_head hot_relocq[MAX_RELOC_TYPES];
-	int thresh;
 	struct task_struct *hot_reloc_kthread;
 	struct mutex hot_reloc_mutex;
 };

index 22d7991..a713514 100644
@@ -3,4 +3,8 @@
 
 #include <uapi/linux/btrfs.h>
 
+extern int sysctl_hot_reloc_thresh;
+extern int sysctl_hot_reloc_interval;
+extern int sysctl_hot_reloc_max_items;
+
 #endif /* _LINUX_BTRFS_H */

index 753585d..7050086 100644
@@ -62,6 +62,7 @@
 #include <linux/capability.h>
 #include <linux/binfmts.h>
 #include <linux/sched/sysctl.h>
+#include <linux/btrfs.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>

@@ -1637,6 +1638,27 @@ static struct ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "hot-reloc-thresh",
+		.data		= &sysctl_hot_reloc_thresh,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "hot-reloc-interval",
+		.data		= &sysctl_hot_reloc_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "hot-reloc-max-items",
+		.data		= &sysctl_hot_reloc_max_items,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };