u64 num_bytes, int delalloc);
static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
u64 num_bytes);
-static int __reserve_metadata_bytes(struct btrfs_root *root,
+static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
u64 orig_bytes,
- enum btrfs_reserve_flush_enum flush);
+ enum btrfs_reserve_flush_enum flush,
+ bool system_chunk);
static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
u64 num_bytes);
return NULL;
}
+static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes,
+ u64 owner, u64 root_objectid)
+{
+ struct btrfs_space_info *space_info;
+ u64 flags;
+
+ if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+ if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID)
+ flags = BTRFS_BLOCK_GROUP_SYSTEM;
+ else
+ flags = BTRFS_BLOCK_GROUP_METADATA;
+ } else {
+ flags = BTRFS_BLOCK_GROUP_DATA;
+ }
+
+ space_info = __find_space_info(fs_info, flags);
+ BUG_ON(!space_info); /* Logic bug */
+ percpu_counter_add(&space_info->total_bytes_pinned, num_bytes);
+}
+
/*
* after adding space to the filesystem, we need to clear the full flags
* on all the space infos.
};
}
-static int update_space_info(struct btrfs_fs_info *info, u64 flags,
- u64 total_bytes, u64 bytes_used,
- u64 bytes_readonly,
- struct btrfs_space_info **space_info)
+static int create_space_info(struct btrfs_fs_info *info, u64 flags,
+ struct btrfs_space_info **new)
{
- struct btrfs_space_info *found;
+
+ struct btrfs_space_info *space_info;
int i;
- int factor;
int ret;
- if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10))
- factor = 2;
- else
- factor = 1;
-
- found = __find_space_info(info, flags);
- if (found) {
- spin_lock(&found->lock);
- found->total_bytes += total_bytes;
- found->disk_total += total_bytes * factor;
- found->bytes_used += bytes_used;
- found->disk_used += bytes_used * factor;
- found->bytes_readonly += bytes_readonly;
- if (total_bytes > 0)
- found->full = 0;
- space_info_add_new_bytes(info, found, total_bytes -
- bytes_used - bytes_readonly);
- spin_unlock(&found->lock);
- *space_info = found;
- return 0;
- }
- found = kzalloc(sizeof(*found), GFP_NOFS);
- if (!found)
+ space_info = kzalloc(sizeof(*space_info), GFP_NOFS);
+ if (!space_info)
return -ENOMEM;
- ret = percpu_counter_init(&found->total_bytes_pinned, 0, GFP_KERNEL);
+ ret = percpu_counter_init(&space_info->total_bytes_pinned, 0,
+ GFP_KERNEL);
if (ret) {
- kfree(found);
+ kfree(space_info);
return ret;
}
for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
- INIT_LIST_HEAD(&found->block_groups[i]);
- init_rwsem(&found->groups_sem);
- spin_lock_init(&found->lock);
- found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
- found->total_bytes = total_bytes;
- found->disk_total = total_bytes * factor;
- found->bytes_used = bytes_used;
- found->disk_used = bytes_used * factor;
- found->bytes_pinned = 0;
- found->bytes_reserved = 0;
- found->bytes_readonly = bytes_readonly;
- found->bytes_may_use = 0;
- found->full = 0;
- found->max_extent_size = 0;
- found->force_alloc = CHUNK_ALLOC_NO_FORCE;
- found->chunk_alloc = 0;
- found->flush = 0;
- init_waitqueue_head(&found->wait);
- INIT_LIST_HEAD(&found->ro_bgs);
- INIT_LIST_HEAD(&found->tickets);
- INIT_LIST_HEAD(&found->priority_tickets);
-
- ret = kobject_init_and_add(&found->kobj, &space_info_ktype,
+ INIT_LIST_HEAD(&space_info->block_groups[i]);
+ init_rwsem(&space_info->groups_sem);
+ spin_lock_init(&space_info->lock);
+ space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+ space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
+ init_waitqueue_head(&space_info->wait);
+ INIT_LIST_HEAD(&space_info->ro_bgs);
+ INIT_LIST_HEAD(&space_info->tickets);
+ INIT_LIST_HEAD(&space_info->priority_tickets);
+
+ ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype,
info->space_info_kobj, "%s",
- alloc_name(found->flags));
+ alloc_name(space_info->flags));
if (ret) {
- kfree(found);
+ percpu_counter_destroy(&space_info->total_bytes_pinned);
+ kfree(space_info);
return ret;
}
- *space_info = found;
- list_add_rcu(&found->list, &info->space_info);
+ *new = space_info;
+ list_add_rcu(&space_info->list, &info->space_info);
if (flags & BTRFS_BLOCK_GROUP_DATA)
- info->data_sinfo = found;
+ info->data_sinfo = space_info;
return ret;
}
+static void update_space_info(struct btrfs_fs_info *info, u64 flags,
+ u64 total_bytes, u64 bytes_used,
+ u64 bytes_readonly,
+ struct btrfs_space_info **space_info)
+{
+ struct btrfs_space_info *found;
+ int factor;
+
+ if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10))
+ factor = 2;
+ else
+ factor = 1;
+
+ found = __find_space_info(info, flags);
+ ASSERT(found);
+ spin_lock(&found->lock);
+ found->total_bytes += total_bytes;
+ found->disk_total += total_bytes * factor;
+ found->bytes_used += bytes_used;
+ found->disk_used += bytes_used * factor;
+ found->bytes_readonly += bytes_readonly;
+ if (total_bytes > 0)
+ found->full = 0;
+ space_info_add_new_bytes(info, found, total_bytes -
+ bytes_used - bytes_readonly);
+ spin_unlock(&found->lock);
+ *space_info = found;
+}
+
static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
u64 extra_flags = chunk_to_extended(flags) &
return btrfs_reduce_alloc_profile(fs_info, flags);
}
-u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
+static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
{
struct btrfs_fs_info *fs_info = root->fs_info;
u64 flags;
return ret;
}
+u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+ return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
+}
+
+u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+ return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
+}
+
+u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+ return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
+}
+
static u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
bool may_use_included)
{
data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
spin_unlock(&data_sinfo->lock);
alloc:
- alloc_target = btrfs_get_alloc_profile(root, 1);
+ alloc_target = btrfs_data_alloc_profile(fs_info);
/*
* It is ugly that we don't call nolock join
* transaction for the free space inode case here.
}
if (left < thresh) {
- u64 flags;
+ u64 flags = btrfs_system_alloc_profile(fs_info);
- flags = btrfs_get_alloc_profile(fs_info->chunk_root, 0);
/*
* Ignore failure to create system chunk. We might end up not
* needing it, as we might not need to COW all nodes/leafs from
space_info = __find_space_info(fs_info, flags);
if (!space_info) {
- ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
- BUG_ON(ret); /* -ENOMEM */
+ ret = create_space_info(fs_info, flags, &space_info);
+ if (ret)
+ return ret;
}
- BUG_ON(!space_info); /* Logic error */
again:
spin_lock(&space_info->lock);
return ret;
}
-static int can_overcommit(struct btrfs_root *root,
+static int can_overcommit(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info, u64 bytes,
- enum btrfs_reserve_flush_enum flush)
+ enum btrfs_reserve_flush_enum flush,
+ bool system_chunk)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
u64 profile;
u64 space_size;
if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
return 0;
- profile = btrfs_get_alloc_profile(root, 0);
+ if (system_chunk)
+ profile = btrfs_system_alloc_profile(fs_info);
+ else
+ profile = btrfs_metadata_alloc_profile(fs_info);
+
used = btrfs_space_info_used(space_info, false);
/*
used += space_info->bytes_may_use;
- spin_lock(&fs_info->free_chunk_lock);
- avail = fs_info->free_chunk_space;
- spin_unlock(&fs_info->free_chunk_lock);
+ avail = atomic64_read(&fs_info->free_chunk_space);
/*
* If we have dup, raid1 or raid10 then only half of the free
/*
* shrink metadata reservation for delalloc
*/
-static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
- bool wait_ordered)
+static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim,
+ u64 orig, bool wait_ordered)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_block_rsv *block_rsv;
struct btrfs_space_info *space_info;
struct btrfs_trans_handle *trans;
else
flush = BTRFS_RESERVE_NO_FLUSH;
spin_lock(&space_info->lock);
- if (can_overcommit(root, space_info, orig, flush)) {
+ if (can_overcommit(fs_info, space_info, orig, flush, false)) {
spin_unlock(&space_info->lock);
break;
}
spin_lock(&delayed_rsv->lock);
if (percpu_counter_compare(&space_info->total_bytes_pinned,
- bytes - delayed_rsv->size) >= 0) {
+ bytes - delayed_rsv->size) < 0) {
spin_unlock(&delayed_rsv->lock);
return -ENOSPC;
}
spin_unlock(&delayed_rsv->lock);
commit:
- trans = btrfs_join_transaction(fs_info->fs_root);
+ trans = btrfs_join_transaction(fs_info->extent_root);
if (IS_ERR(trans))
return -ENOSPC;
struct btrfs_space_info *space_info, u64 num_bytes,
u64 orig_bytes, int state)
{
- struct btrfs_root *root = fs_info->fs_root;
+ struct btrfs_root *root = fs_info->extent_root;
struct btrfs_trans_handle *trans;
int nr;
int ret = 0;
break;
case FLUSH_DELALLOC:
case FLUSH_DELALLOC_WAIT:
- shrink_delalloc(root, num_bytes * 2, orig_bytes,
+ shrink_delalloc(fs_info, num_bytes * 2, orig_bytes,
state == FLUSH_DELALLOC_WAIT);
break;
case ALLOC_CHUNK:
break;
}
ret = do_chunk_alloc(trans, fs_info,
- btrfs_get_alloc_profile(root, 0),
+ btrfs_metadata_alloc_profile(fs_info),
CHUNK_ALLOC_NO_FORCE);
btrfs_end_transaction(trans);
if (ret > 0 || ret == -ENOSPC)
}
static inline u64
-btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
- struct btrfs_space_info *space_info)
+btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info,
+ bool system_chunk)
{
struct reserve_ticket *ticket;
u64 used;
return to_reclaim;
to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
- if (can_overcommit(root, space_info, to_reclaim,
- BTRFS_RESERVE_FLUSH_ALL))
+ if (can_overcommit(fs_info, space_info, to_reclaim,
+ BTRFS_RESERVE_FLUSH_ALL, system_chunk))
return 0;
- used = space_info->bytes_used + space_info->bytes_reserved +
- space_info->bytes_pinned + space_info->bytes_readonly +
- space_info->bytes_may_use;
- if (can_overcommit(root, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
+ used = btrfs_space_info_used(space_info, true);
+
+ if (can_overcommit(fs_info, space_info, SZ_1M,
+ BTRFS_RESERVE_FLUSH_ALL, system_chunk))
expected = div_factor_fine(space_info->total_bytes, 95);
else
expected = div_factor_fine(space_info->total_bytes, 90);
return to_reclaim;
}
-static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
- struct btrfs_root *root, u64 used)
+static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info,
+ u64 used, bool system_chunk)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
u64 thresh = div_factor_fine(space_info->total_bytes, 98);
/* If we're just plain full then async reclaim just slows us down. */
if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
return 0;
- if (!btrfs_calc_reclaim_metadata_size(root, space_info))
+ if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info,
+ system_chunk))
return 0;
return (used >= thresh && !btrfs_fs_closing(fs_info) &&
space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
spin_lock(&space_info->lock);
- to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
- space_info);
+ to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
+ false);
if (!to_reclaim) {
space_info->flush = 0;
spin_unlock(&space_info->lock);
spin_unlock(&space_info->lock);
return;
}
- to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
- space_info);
+ to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info,
+ space_info,
+ false);
ticket = list_first_entry(&space_info->tickets,
struct reserve_ticket, list);
if (last_tickets_id == space_info->tickets_id) {
int flush_state = FLUSH_DELAYED_ITEMS_NR;
spin_lock(&space_info->lock);
- to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
- space_info);
+ to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
+ false);
if (!to_reclaim) {
spin_unlock(&space_info->lock);
return;
* regain reservations will be made and this will fail if there is not enough
* space already.
*/
-static int __reserve_metadata_bytes(struct btrfs_root *root,
+static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
u64 orig_bytes,
- enum btrfs_reserve_flush_enum flush)
+ enum btrfs_reserve_flush_enum flush,
+ bool system_chunk)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
struct reserve_ticket ticket;
u64 used;
int ret = 0;
trace_btrfs_space_reservation(fs_info, "space_info",
space_info->flags, orig_bytes, 1);
ret = 0;
- } else if (can_overcommit(root, space_info, orig_bytes, flush)) {
+ } else if (can_overcommit(fs_info, space_info, orig_bytes, flush,
+ system_chunk)) {
space_info->bytes_may_use += orig_bytes;
trace_btrfs_space_reservation(fs_info, "space_info",
space_info->flags, orig_bytes, 1);
orig_bytes, flush,
"enospc");
queue_work(system_unbound_wq,
- &root->fs_info->async_reclaim_work);
+ &fs_info->async_reclaim_work);
}
} else {
list_add_tail(&ticket.list,
* the async reclaim as we will panic.
*/
if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) &&
- need_do_async_reclaim(space_info, root, used) &&
+ need_do_async_reclaim(fs_info, space_info,
+ used, system_chunk) &&
!work_busy(&fs_info->async_reclaim_work)) {
trace_btrfs_trigger_flush(fs_info, space_info->flags,
orig_bytes, flush, "preempt");
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
int ret;
+ bool system_chunk = (root == fs_info->chunk_root);
- ret = __reserve_metadata_bytes(root, block_rsv->space_info, orig_bytes,
- flush);
+ ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info,
+ orig_bytes, flush, system_chunk);
if (ret == -ENOSPC &&
unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) {
if (block_rsv != global_rsv &&
* overcommit, and if we can't then we just need to free up our space
* and not satisfy any requests.
*/
- used = space_info->bytes_used + space_info->bytes_reserved +
- space_info->bytes_pinned + space_info->bytes_readonly +
- space_info->bytes_may_use;
+ used = btrfs_space_info_used(space_info, true);
if (used - num_bytes >= space_info->total_bytes)
check_overcommit = true;
again:
* adding the ticket space would be a double count.
*/
if (check_overcommit &&
- !can_overcommit(fs_info->extent_root, space_info, 0,
- flush))
+ !can_overcommit(fs_info, space_info, 0, flush, false))
break;
if (num_bytes >= ticket->bytes) {
list_del_init(&ticket->list);
return 0;
}
-static void add_pinned_bytes(struct btrfs_fs_info *fs_info, u64 num_bytes,
- u64 owner, u64 root_objectid)
-{
- struct btrfs_space_info *space_info;
- u64 flags;
-
- if (owner < BTRFS_FIRST_FREE_OBJECTID) {
- if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID)
- flags = BTRFS_BLOCK_GROUP_SYSTEM;
- else
- flags = BTRFS_BLOCK_GROUP_METADATA;
- } else {
- flags = BTRFS_BLOCK_GROUP_DATA;
- }
-
- space_info = __find_space_info(fs_info, flags);
- BUG_ON(!space_info); /* Logic bug */
- percpu_counter_add(&space_info->total_bytes_pinned, num_bytes);
-}
-
-
static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *info,
struct btrfs_delayed_ref_node *node, u64 parent,
u64 flags;
int ret;
- flags = btrfs_get_alloc_profile(root, is_data);
+ flags = get_alloc_profile_by_root(root, is_data);
again:
WARN_ON(num_bytes < fs_info->sectorsize);
ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size,
}
trace_btrfs_add_block_group(info, cache, 0);
- ret = update_space_info(info, cache->flags, found_key.offset,
- btrfs_block_group_used(&cache->item),
- cache->bytes_super, &space_info);
- if (ret) {
- btrfs_remove_free_space_cache(cache);
- spin_lock(&info->block_group_cache_lock);
- rb_erase(&cache->cache_node,
- &info->block_group_cache_tree);
- RB_CLEAR_NODE(&cache->cache_node);
- spin_unlock(&info->block_group_cache_lock);
- btrfs_put_block_group(cache);
- goto error;
- }
+ update_space_info(info, cache->flags, found_key.offset,
+ btrfs_block_group_used(&cache->item),
+ cache->bytes_super, &space_info);
cache->space_info = space_info;
}
#endif
/*
- * Call to ensure the corresponding space_info object is created and
- * assigned to our block group, but don't update its counters just yet.
- * We want our bg to be added to the rbtree with its ->space_info set.
+ * Ensure the corresponding space_info object is created and
+ * assigned to our block group. We want our bg to be added to the rbtree
+ * with its ->space_info set.
*/
- ret = update_space_info(fs_info, cache->flags, 0, 0, 0,
- &cache->space_info);
- if (ret) {
- btrfs_remove_free_space_cache(cache);
- btrfs_put_block_group(cache);
- return ret;
+ cache->space_info = __find_space_info(fs_info, cache->flags);
+ if (!cache->space_info) {
+ ret = create_space_info(fs_info, cache->flags,
+ &cache->space_info);
+ if (ret) {
+ btrfs_remove_free_space_cache(cache);
+ btrfs_put_block_group(cache);
+ return ret;
+ }
}
ret = btrfs_add_block_group_cache(fs_info, cache);
* the rbtree, update the space info's counters.
*/
trace_btrfs_add_block_group(fs_info, cache, 1);
- ret = update_space_info(fs_info, cache->flags, size, bytes_used,
+ update_space_info(fs_info, cache->flags, size, bytes_used,
cache->bytes_super, &cache->space_info);
- if (ret) {
- btrfs_remove_free_space_cache(cache);
- spin_lock(&fs_info->block_group_cache_lock);
- rb_erase(&cache->cache_node,
- &fs_info->block_group_cache_tree);
- RB_CLEAR_NODE(&cache->cache_node);
- spin_unlock(&fs_info->block_group_cache_lock);
- btrfs_put_block_group(cache);
- return ret;
- }
update_global_block_rsv(fs_info);
__link_block_group(cache->space_info, cache);
mixed = 1;
flags = BTRFS_BLOCK_GROUP_SYSTEM;
- ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+ ret = create_space_info(fs_info, flags, &space_info);
if (ret)
goto out;
if (mixed) {
flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
- ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+ ret = create_space_info(fs_info, flags, &space_info);
} else {
flags = BTRFS_BLOCK_GROUP_METADATA;
- ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+ ret = create_space_info(fs_info, flags, &space_info);
if (ret)
goto out;
flags = BTRFS_BLOCK_GROUP_DATA;
- ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+ ret = create_space_info(fs_info, flags, &space_info);
}
out:
return ret;