@@ -8,7 +8,8 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
export.o tree-log.o free-space-cache.o zlib.o lzo.o \
compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
- reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o
+ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
+ hot_relocate.o
btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
@@ -961,6 +961,16 @@ 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 hot data relocation feature. When hot data
+ * relocation is on, *_SSD block groups are forced to nonrotating drives and
+ * the plain DATA and METADATA block groups are forced to rotating drives.
+ *
+ * This should be further optimized, i.e. force metadata to SSD or relocate
+ * inode metadata to SSD when any of its subfile ranges are relocated to SSD
+ * so that reads and writes aren't delayed by HDD seeks.
+ */
+#define BTRFS_BLOCK_GROUP_DATA_SSD (1ULL << 9)
#define BTRFS_BLOCK_GROUP_RESERVED BTRFS_AVAIL_ALLOC_BIT_SINGLE
enum btrfs_raid_types {
@@ -976,7 +986,8 @@ 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_SSD)
#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \
BTRFS_BLOCK_GROUP_RAID1 | \
@@ -1508,6 +1519,7 @@ struct btrfs_fs_info {
struct list_head space_info;
struct btrfs_space_info *data_sinfo;
+ struct btrfs_space_info *hot_data_sinfo;
struct reloc_control *reloc_ctl;
@@ -1532,6 +1544,7 @@ struct btrfs_fs_info {
u64 avail_data_alloc_bits;
u64 avail_metadata_alloc_bits;
u64 avail_system_alloc_bits;
+ u64 avail_data_ssd_alloc_bits;
/* restriper state */
spinlock_t balance_lock;
@@ -1544,6 +1557,7 @@ struct btrfs_fs_info {
unsigned data_chunk_allocations;
unsigned metadata_ratio;
+ unsigned data_ssd_chunk_allocations;
void *bdev_holder;
@@ -1901,6 +1915,7 @@ 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)
@@ -1922,6 +1937,7 @@ struct btrfs_ioctl_defrag_range_args {
#define BTRFS_INODE_NOATIME (1 << 9)
#define BTRFS_INODE_DIRSYNC (1 << 10)
#define BTRFS_INODE_COMPRESS (1 << 11)
+#define BTRFS_INODE_HOT (1 << 12)
#define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31)
@@ -3014,6 +3030,8 @@ 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);
@@ -3070,6 +3088,8 @@ 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);
@@ -3102,6 +3122,7 @@ enum btrfs_reserve_flush_enum {
int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes);
+void btrfs_free_reserved_ssd_data_space(struct inode *inode, u64 bytes);
void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
@@ -3118,6 +3139,7 @@ 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);
+void btrfs_delalloc_release_ssd_space(struct inode *inode, u64 num_bytes);
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);
@@ -598,7 +598,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
/*
* return the block group that starts at or after bytenr
*/
-static struct btrfs_block_group_cache *
+struct btrfs_block_group_cache *
btrfs_lookup_first_block_group(struct btrfs_fs_info *info, u64 bytenr)
{
struct btrfs_block_group_cache *cache;
@@ -2961,7 +2961,7 @@ fail:
}
-static struct btrfs_block_group_cache *
+struct btrfs_block_group_cache *
next_block_group(struct btrfs_root *root,
struct btrfs_block_group_cache *cache)
{
@@ -3082,7 +3082,12 @@ again:
&alloc_hint);
if (!ret)
dcs = BTRFS_DC_SETUP;
- btrfs_free_reserved_data_space(inode, num_pages);
+
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_free_reserved_ssd_data_space(inode, num_pages);
+ } else
+ btrfs_free_reserved_data_space(inode, num_pages);
out_put:
iput(inode);
@@ -3284,6 +3289,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
list_add_rcu(&found->list, &info->space_info);
if (flags & BTRFS_BLOCK_GROUP_DATA)
info->data_sinfo = found;
+ else if (flags & BTRFS_BLOCK_GROUP_DATA_SSD)
+ info->hot_data_sinfo = found;
return 0;
}
@@ -3299,6 +3306,8 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
fs_info->avail_metadata_alloc_bits |= extra_flags;
if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
fs_info->avail_system_alloc_bits |= extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_DATA_SSD)
+ fs_info->avail_data_ssd_alloc_bits |= extra_flags;
write_sequnlock(&fs_info->profiles_lock);
}
@@ -3405,18 +3414,27 @@ static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
flags |= root->fs_info->avail_system_alloc_bits;
else if (flags & BTRFS_BLOCK_GROUP_METADATA)
flags |= root->fs_info->avail_metadata_alloc_bits;
+ else if (flags & BTRFS_BLOCK_GROUP_DATA_SSD)
+ flags |= root->fs_info->avail_data_ssd_alloc_bits;
} while (read_seqretry(&root->fs_info->profiles_lock, seq));
return btrfs_reduce_alloc_profile(root, flags);
}
+/*
+ * Turns a chunk_type integer into set of block group flags (a profile).
+ * Hot data relocation code adds chunk_types 2 and 3 for hot data specific
+ * block group types.
+ */
u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
{
u64 flags;
u64 ret;
- if (data)
+ if (data == 1)
flags = BTRFS_BLOCK_GROUP_DATA;
+ else if (data == 2)
+ flags = BTRFS_BLOCK_GROUP_DATA_SSD;
else if (root == root->fs_info->chunk_root)
flags = BTRFS_BLOCK_GROUP_SYSTEM;
else
@@ -3437,6 +3455,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
struct btrfs_fs_info *fs_info = root->fs_info;
u64 used;
int ret = 0, committed = 0, alloc_chunk = 1;
+ int data, tried = 0;
/* make sure bytes are sectorsize aligned */
bytes = ALIGN(bytes, root->sectorsize);
@@ -3447,7 +3466,15 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
committed = 1;
}
- data_sinfo = fs_info->data_sinfo;
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+try_hot:
+ data = 2;
+ data_sinfo = fs_info->hot_data_sinfo;
+ } else {
+ data = 1;
+ data_sinfo = fs_info->data_sinfo;
+ }
+
if (!data_sinfo)
goto alloc;
@@ -3465,13 +3492,22 @@ again:
* if we don't have enough free bytes in this space then we need
* to alloc a new chunk.
*/
- if (!data_sinfo->full && alloc_chunk) {
+ if (alloc_chunk) {
u64 alloc_target;
+ if (data_sinfo->full) {
+ if (!tried) {
+ tried = 1;
+ spin_unlock(&data_sinfo->lock);
+ goto try_hot;
+ } else
+ goto non_alloc;
+ }
+
data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
spin_unlock(&data_sinfo->lock);
alloc:
- alloc_target = btrfs_get_alloc_profile(root, 1);
+ alloc_target = btrfs_get_alloc_profile(root, data);
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
return PTR_ERR(trans);
@@ -3488,11 +3524,13 @@ alloc:
}
if (!data_sinfo)
- data_sinfo = fs_info->data_sinfo;
+ data_sinfo = (data == 1) ? fs_info->data_sinfo :
+ fs_info->hot_data_sinfo;
goto again;
}
+non_alloc:
/*
* If we have less pinned bytes than we want to allocate then
* don't bother committing the transaction, it won't help us.
@@ -3503,7 +3541,7 @@ alloc:
/* commit the current transaction and try again */
commit_trans:
- if (!committed &&
+ if (!committed && data_sinfo &&
!atomic_read(&root->fs_info->open_ioctl_trans)) {
committed = 1;
trans = btrfs_join_transaction(root);
@@ -3517,6 +3555,10 @@ commit_trans:
return -ENOSPC;
}
+
+ if (tried)
+ BTRFS_I(inode)->flags |= BTRFS_INODE_HOT;
+
data_sinfo->bytes_may_use += bytes;
trace_btrfs_space_reservation(root->fs_info, "space_info",
data_sinfo->flags, bytes, 1);
@@ -3544,6 +3586,22 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes)
spin_unlock(&data_sinfo->lock);
}
+void btrfs_free_reserved_ssd_data_space(struct inode *inode, u64 bytes)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_space_info *data_sinfo;
+
+ /* make sure bytes are sectorsize aligned */
+ bytes = ALIGN(bytes, root->sectorsize);
+
+ data_sinfo = root->fs_info->hot_data_sinfo;
+ spin_lock(&data_sinfo->lock);
+ data_sinfo->bytes_may_use -= bytes;
+ trace_btrfs_space_reservation(root->fs_info, "space_info",
+ data_sinfo->flags, bytes, 0);
+ spin_unlock(&data_sinfo->lock);
+}
+
static void force_metadata_allocation(struct btrfs_fs_info *info)
{
struct list_head *head = &info->space_info;
@@ -3715,6 +3773,13 @@ again:
force_metadata_allocation(fs_info);
}
+ if (flags & BTRFS_BLOCK_GROUP_DATA_SSD && fs_info->metadata_ratio) {
+ fs_info->data_ssd_chunk_allocations++;
+ if (!(fs_info->data_ssd_chunk_allocations %
+ fs_info->metadata_ratio))
+ force_metadata_allocation(fs_info);
+ }
+
/*
* Check if we have enough space in SYSTEM chunk because we may need
* to update devices.
@@ -4422,6 +4487,13 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info)
meta_used = sinfo->bytes_used;
spin_unlock(&sinfo->lock);
+ sinfo = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA_SSD);
+ if (sinfo) {
+ spin_lock(&sinfo->lock);
+ data_used += sinfo->bytes_used;
+ spin_unlock(&sinfo->lock);
+ }
+
num_bytes = (data_used >> fs_info->sb->s_blocksize_bits) *
csum_size * 2;
num_bytes += div64_u64(data_used + meta_used, 50);
@@ -4916,7 +4988,11 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 num_bytes)
ret = btrfs_delalloc_reserve_metadata(inode, num_bytes);
if (ret) {
- btrfs_free_reserved_data_space(inode, num_bytes);
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_free_reserved_ssd_data_space(inode, num_bytes);
+ } else
+ btrfs_free_reserved_data_space(inode, num_bytes);
return ret;
}
@@ -4942,6 +5018,12 @@ void btrfs_delalloc_release_space(struct inode *inode, u64 num_bytes)
btrfs_free_reserved_data_space(inode, num_bytes);
}
+void btrfs_delalloc_release_ssd_space(struct inode *inode, u64 num_bytes)
+{
+ btrfs_delalloc_release_metadata(inode, num_bytes);
+ btrfs_free_reserved_ssd_data_space(inode, num_bytes);
+}
+
static int update_block_group(struct btrfs_root *root,
u64 bytenr, u64 num_bytes, int alloc)
{
@@ -5770,7 +5852,8 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_space_info *space_info;
int loop = 0;
int index = __get_raid_index(data);
- int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
+ int alloc_type = ((data & BTRFS_BLOCK_GROUP_DATA)
+ || (data & BTRFS_BLOCK_GROUP_DATA_SSD)) ?
RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
bool found_uncached_bg = false;
bool failed_cluster_refill = false;
@@ -8189,6 +8272,8 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
fs_info->avail_metadata_alloc_bits &= ~extra_flags;
if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
fs_info->avail_system_alloc_bits &= ~extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_DATA_SSD)
+ fs_info->avail_data_ssd_alloc_bits &= ~extra_flags;
write_sequnlock(&fs_info->profiles_lock);
}
@@ -1400,9 +1400,11 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
{
struct rb_node *node;
struct extent_state *state;
+ struct btrfs_root *root;
u64 cur_start = *start;
u64 found = 0;
u64 total_bytes = 0;
+ int flag = EXTENT_DELALLOC;
spin_lock(&tree->lock);
@@ -1417,13 +1419,27 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
goto out;
}
+ root = BTRFS_I(tree->mapping->host)->root;
while (1) {
state = rb_entry(node, struct extent_state, rb_node);
if (found && (state->start != cur_start ||
(state->state & EXTENT_BOUNDARY))) {
goto out;
}
- if (!(state->state & EXTENT_DELALLOC)) {
+ if (btrfs_test_opt(root, HOT_MOVE)) {
+ if (!(state->state & EXTENT_DELALLOC) ||
+ (!(state->state & EXTENT_HOT) &&
+ !(state->state & EXTENT_COLD))) {
+ if (!found)
+ *end = state->end;
+ goto out;
+ } else {
+ if (!found)
+ flag = (state->state & EXTENT_HOT) ?
+ EXTENT_HOT : EXTENT_COLD;
+ }
+ }
+ if (!(state->state & flag)) {
if (!found)
*end = state->end;
goto out;
@@ -1610,7 +1626,13 @@ again:
lock_extent_bits(tree, delalloc_start, delalloc_end, 0, &cached_state);
/* then test to make sure it is all still delalloc */
- ret = test_range_bit(tree, delalloc_start, delalloc_end,
+ if (btrfs_test_opt(BTRFS_I(inode)->root, HOT_MOVE)) {
+ ret = test_range_bit(tree, delalloc_start, delalloc_end,
+ EXTENT_DELALLOC | EXTENT_HOT, 1, cached_state);
+ ret |= test_range_bit(tree, delalloc_start, delalloc_end,
+ EXTENT_DELALLOC | EXTENT_COLD, 1, cached_state);
+ } else
+ ret = test_range_bit(tree, delalloc_start, delalloc_end,
EXTENT_DELALLOC, 1, cached_state);
if (!ret) {
unlock_extent_cached(tree, delalloc_start, delalloc_end,
@@ -1644,7 +1666,10 @@ int extent_clear_unlock_delalloc(struct inode *inode,
clear_bits |= EXTENT_LOCKED;
if (op & EXTENT_CLEAR_DIRTY)
clear_bits |= EXTENT_DIRTY;
-
+ if (op & EXTENT_CLEAR_HOT)
+ clear_bits |= EXTENT_HOT;
+ if (op & EXTENT_CLEAR_COLD)
+ clear_bits |= EXTENT_COLD;
if (op & EXTENT_CLEAR_DELALLOC)
clear_bits |= EXTENT_DELALLOC;
@@ -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
@@ -40,6 +40,7 @@
#include "locking.h"
#include "compat.h"
#include "volumes.h"
+#include "hot_relocate.h"
static struct kmem_cache *btrfs_inode_defrag_cachep;
/*
@@ -513,6 +514,10 @@ 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))
+ hot_set_extent(inode, start_pos, end_of_last_block, cached, 1);
+
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
cached);
if (err)
@@ -1372,7 +1377,12 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
pos, first_index, write_bytes,
force_page_uptodate);
if (ret) {
- btrfs_delalloc_release_space(inode,
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode,
+ num_pages << PAGE_CACHE_SHIFT);
+ } else
+ btrfs_delalloc_release_space(inode,
num_pages << PAGE_CACHE_SHIFT);
break;
}
@@ -1410,7 +1420,12 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
}
- btrfs_delalloc_release_space(inode,
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT)
+ btrfs_delalloc_release_ssd_space(inode,
+ (num_pages - dirty_pages) <<
+ PAGE_CACHE_SHIFT);
+ else
+ btrfs_delalloc_release_space(inode,
(num_pages - dirty_pages) <<
PAGE_CACHE_SHIFT);
}
@@ -1420,8 +1435,13 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
dirty_pages, pos, copied,
NULL);
if (ret) {
- btrfs_delalloc_release_space(inode,
- dirty_pages << PAGE_CACHE_SHIFT);
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode,
+ dirty_pages << PAGE_CACHE_SHIFT);
+ } else
+ btrfs_delalloc_release_space(inode,
+ dirty_pages << PAGE_CACHE_SHIFT);
btrfs_drop_pages(pages, num_pages);
break;
}
@@ -2282,7 +2302,13 @@ 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);
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_free_reserved_ssd_data_space(inode,
+ alloc_end - alloc_start);
+ } else
+ btrfs_free_reserved_data_space(inode,
+ alloc_end - alloc_start);
return ret;
}
new file mode 100644
@@ -0,0 +1,78 @@
+/*
+ * fs/btrfs/hot_relocate.c
+ *
+ * Copyright (C) 2013 IBM Corp. All rights reserved.
+ * Written by Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
+ * Ben Chociej <bchociej@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ */
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include "hot_relocate.h"
+
+static void hot_set_extent_bits(struct extent_io_tree *tree, u64 start,
+ u64 end, struct extent_state **cached_state,
+ gfp_t mask, int storage_type, int flag)
+{
+ int set_bits = 0, clear_bits = 0;
+
+ if (flag) {
+ set_bits = EXTENT_DELALLOC | EXTENT_UPTODATE;
+ clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING;
+ }
+
+ if (storage_type == ON_ROT_DISK) {
+ set_bits |= EXTENT_COLD;
+ clear_bits |= EXTENT_HOT;
+ } else if (storage_type == ON_NONROT_DISK) {
+ set_bits |= EXTENT_HOT;
+ clear_bits |= EXTENT_COLD;
+ }
+
+ clear_extent_bit(tree, start, end, clear_bits,
+ 0, 0, cached_state, mask);
+ set_extent_bit(tree, start, end, set_bits, NULL,
+ cached_state, mask);
+}
+
+void hot_set_extent(struct inode *inode, u64 start, u64 end,
+ struct extent_state **cached_state, int flag)
+{
+ int storage_type;
+
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ if (flag)
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ storage_type = TYPE_NONROT;
+ } else
+ storage_type = TYPE_ROT;
+
+ hot_set_extent_bits(&BTRFS_I(inode)->io_tree, start,
+ end, cached_state, GFP_NOFS, storage_type, 0);
+}
+
+int hot_get_chunk_type(struct inode *inode, u64 start, u64 end)
+{
+ int hot, cold, ret = 1;
+
+ hot = test_range_bit(&BTRFS_I(inode)->io_tree,
+ start, end, EXTENT_HOT, 1, NULL);
+ cold = test_range_bit(&BTRFS_I(inode)->io_tree,
+ start, end, EXTENT_COLD, 1, NULL);
+
+ WARN_ON(hot && cold);
+
+ if (hot)
+ ret = 2;
+ else if (cold)
+ ret = 1;
+ else
+ WARN_ON(1);
+
+ return ret;
+}
new file mode 100644
@@ -0,0 +1,31 @@
+/*
+ * fs/btrfs/hot_relocate.h
+ *
+ * Copyright (C) 2013 IBM Corp. All rights reserved.
+ * Written by Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
+ * Ben Chociej <bchociej@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ */
+
+#ifndef __HOT_RELOCATE__
+#define __HOT_RELOCATE__
+
+#include <linux/hot_tracking.h>
+#include "ctree.h"
+#include "btrfs_inode.h"
+#include "volumes.h"
+
+enum {
+ TYPE_ROT, /* rot -> rotating */
+ TYPE_NONROT, /* nonrot -> nonrotating */
+ MAX_RELOC_TYPES
+};
+
+void hot_set_extent(struct inode *inode, u64 start, u64 end,
+ struct extent_state **cached_state, int flag);
+int hot_get_chunk_type(struct inode *inode, u64 start, u64 end);
+
+#endif /* __HOT_RELOCATE__ */
@@ -497,10 +497,19 @@ again:
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
prealloc, prealloc, &alloc_hint);
if (ret) {
- btrfs_delalloc_release_space(inode, prealloc);
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode, prealloc);
+ } else
+ btrfs_delalloc_release_space(inode, prealloc);
goto out_put;
}
- btrfs_free_reserved_data_space(inode, prealloc);
+
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_free_reserved_ssd_data_space(inode, prealloc);
+ } else
+ btrfs_free_reserved_data_space(inode, prealloc);
ret = btrfs_write_out_ino_cache(root, trans, path);
out_put:
@@ -56,6 +56,7 @@
#include "free-space-cache.h"
#include "inode-map.h"
#include "backref.h"
+#include "hot_relocate.h"
struct btrfs_iget_args {
u64 ino;
@@ -857,13 +858,14 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans,
{
u64 alloc_hint = 0;
u64 num_bytes;
- unsigned long ram_size;
+ unsigned long ram_size, hot_flag = 0;
u64 disk_num_bytes;
u64 cur_alloc_size;
u64 blocksize = root->sectorsize;
struct btrfs_key ins;
struct extent_map *em;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+ int chunk_type = 1;
int ret = 0;
BUG_ON(btrfs_is_free_space_inode(inode));
@@ -871,6 +873,7 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans,
num_bytes = ALIGN(end - start + 1, blocksize);
num_bytes = max(blocksize, num_bytes);
disk_num_bytes = num_bytes;
+ ret = 0;
/* if this is a small write inside eof, kick off defrag */
if (num_bytes < 64 * 1024 &&
@@ -890,7 +893,8 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans,
EXTENT_CLEAR_DELALLOC |
EXTENT_CLEAR_DIRTY |
EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
+ EXTENT_END_WRITEBACK |
+ hot_flag);
*nr_written = *nr_written +
(end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE;
@@ -912,9 +916,25 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans,
unsigned long op;
cur_alloc_size = disk_num_bytes;
+
+ /*
+ * Use COW operations to move hot data to SSD and cold data
+ * back to rotating disk. Sets chunk_type to 1 to indicate
+ * to write to BTRFS_BLOCK_GROUP_DATA or 2 to indicate
+ * BTRFS_BLOCK_GROUP_DATA_SSD.
+ */
+ if (btrfs_test_opt(root, HOT_MOVE)) {
+ chunk_type = hot_get_chunk_type(inode, start,
+ start + cur_alloc_size - 1);
+ if (chunk_type == 1)
+ hot_flag = EXTENT_CLEAR_COLD;
+ if (chunk_type == 2)
+ hot_flag = EXTENT_CLEAR_HOT;
+ }
+
ret = btrfs_reserve_extent(trans, root, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
- &ins, 1);
+ &ins, chunk_type);
if (ret < 0) {
btrfs_abort_transaction(trans, root, ret);
goto out_unlock;
@@ -978,7 +998,7 @@ static noinline int __cow_file_range(struct btrfs_trans_handle *trans,
*/
op = unlock ? EXTENT_CLEAR_UNLOCK_PAGE : 0;
op |= EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC |
- EXTENT_SET_PRIVATE2;
+ EXTENT_SET_PRIVATE2 | hot_flag;
extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
start, start + ram_size - 1,
@@ -1000,7 +1020,8 @@ out_unlock:
EXTENT_CLEAR_DELALLOC |
EXTENT_CLEAR_DIRTY |
EXTENT_SET_WRITEBACK |
- EXTENT_END_WRITEBACK);
+ EXTENT_END_WRITEBACK |
+ hot_flag);
goto out;
}
@@ -1593,8 +1614,12 @@ static void btrfs_clear_bit_hook(struct inode *inode,
btrfs_delalloc_release_metadata(inode, len);
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
- && do_list)
- btrfs_free_reserved_data_space(inode, len);
+ && do_list) {
+ if ((state->state & EXTENT_HOT) && (*bits & EXTENT_HOT))
+ btrfs_free_reserved_ssd_data_space(inode, len);
+ else
+ btrfs_free_reserved_data_space(inode, len);
+ }
__percpu_counter_add(&root->fs_info->delalloc_bytes, -len,
root->fs_info->delalloc_batch);
@@ -1828,6 +1853,9 @@ again:
goto out;
}
+ if (btrfs_test_opt(BTRFS_I(inode)->root, HOT_MOVE))
+ hot_set_extent(inode, page_start, page_end, &cached_state, 1);
+
btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state);
ClearPageChecked(page);
set_page_dirty(page);
@@ -4282,7 +4310,12 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
again:
page = find_or_create_page(mapping, index, mask);
if (!page) {
- btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode,
+ PAGE_CACHE_SIZE);
+ } else
+ btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
ret = -ENOMEM;
goto out;
}
@@ -4324,6 +4357,9 @@ again:
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
+ if (btrfs_test_opt(root, HOT_MOVE))
+ hot_set_extent(inode, page_start, page_end, &cached_state, 0);
+
ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
&cached_state);
if (ret) {
@@ -4332,6 +4368,8 @@ again:
goto out_unlock;
}
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+
if (offset != PAGE_CACHE_SIZE) {
if (!len)
len = PAGE_CACHE_SIZE - offset;
@@ -4349,8 +4387,14 @@ again:
GFP_NOFS);
out_unlock:
- if (ret)
- btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+ if (ret) {
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode,
+ PAGE_CACHE_SIZE);
+ } else
+ btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+ }
unlock_page(page);
page_cache_release(page);
out:
@@ -7373,12 +7417,21 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (rw & WRITE) {
- if (ret < 0 && ret != -EIOCBQUEUED)
- btrfs_delalloc_release_space(inode, count);
- else if (ret >= 0 && (size_t)ret < count)
- btrfs_delalloc_release_space(inode,
+ if (ret < 0 && ret != -EIOCBQUEUED) {
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode, count);
+ } else
+ btrfs_delalloc_release_space(inode, count);
+ } else if (ret >= 0 && (size_t)ret < count) {
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode,
count - (size_t)ret);
- else
+ } else
+ btrfs_delalloc_release_space(inode,
+ count - (size_t)ret);
+ } else
btrfs_delalloc_release_metadata(inode, 0);
}
out:
@@ -7618,6 +7671,9 @@ again:
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
+ if (btrfs_test_opt(root, HOT_MOVE))
+ hot_set_extent(inode, page_start, page_end, &cached_state, 0);
+
ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
&cached_state);
if (ret) {
@@ -7657,7 +7713,11 @@ out_unlock:
}
unlock_page(page);
out:
- btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode, PAGE_CACHE_SIZE);
+ } else
+ btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
out_noreserve:
sb_end_pagefault(inode->i_sb);
return ret;
@@ -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)
@@ -1098,10 +1099,17 @@ again:
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
- btrfs_delalloc_release_space(inode,
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ btrfs_delalloc_release_ssd_space(inode,
+ (page_cnt - i_done) << PAGE_CACHE_SHIFT);
+ } else
+ btrfs_delalloc_release_space(inode,
(page_cnt - i_done) << PAGE_CACHE_SHIFT);
}
+ if (btrfs_test_opt(BTRFS_I(inode)->root, HOT_MOVE))
+ hot_set_extent(inode, page_start,
+ page_end - 1, &cached_state, 1);
set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
&cached_state, GFP_NOFS);
@@ -1124,7 +1132,13 @@ out:
unlock_page(pages[i]);
page_cache_release(pages[i]);
}
- btrfs_delalloc_release_space(inode, page_cnt << PAGE_CACHE_SHIFT);
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_delalloc_release_ssd_space(inode,
+ page_cnt << PAGE_CACHE_SHIFT);
+ } else
+ btrfs_delalloc_release_space(inode,
+ page_cnt << PAGE_CACHE_SHIFT);
return ret;
}
@@ -3014,8 +3028,9 @@ 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_SSD};
+ int num_types = 5;
int alloc_size;
int ret = 0;
u64 slot_count = 0;
@@ -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
@@ -2935,8 +2936,14 @@ int prealloc_file_extent_cluster(struct inode *inode,
break;
nr++;
}
- btrfs_free_reserved_data_space(inode, cluster->end +
- 1 - cluster->start);
+
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_HOT) {
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_HOT;
+ btrfs_free_reserved_ssd_data_space(inode,
+ cluster->end + 1 - cluster->start);
+ } else
+ btrfs_free_reserved_data_space(inode,
+ cluster->end + 1 - cluster->start);
out:
mutex_unlock(&inode->i_mutex);
return ret;
@@ -3065,6 +3072,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
nr++;
}
+ if (btrfs_test_opt(BTRFS_I(inode)->root, HOT_MOVE))
+ hot_set_extent(inode, page_start, page_end, NULL, 1);
+
btrfs_set_extent_delalloc(inode, page_start, page_end, NULL);
set_page_dirty(page);
@@ -1527,7 +1527,8 @@ 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_SSD)) {
total_free_data += found->disk_total - found->disk_used;
total_free_data -=
btrfs_account_ro_block_groups_free_space(found);
@@ -1450,6 +1450,8 @@ 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_ssd_alloc_bits;
} while (read_seqretry(&root->fs_info->profiles_lock, seq));
num_devices = root->fs_info->fs_devices->num_devices;
@@ -3736,7 +3738,8 @@ 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_SSD) {
max_stripe_size = 1024 * 1024 * 1024;
max_chunk_size = 10 * max_stripe_size;
} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
@@ -3775,9 +3778,30 @@ 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_SSD
+ * 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_SSD && dev_rot;
+ if (ret1 || ret2)
+ skip = 1;
+ }
+
cur = cur->next;
if (!device->writeable) {
@@ -3786,7 +3810,7 @@ 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;