btrfs: remove root usage from can_overcommit
can_overcommit using the root to determine the allocation profile is the only use of a root in the call graph below reserve_metadata_bytes. It turns out that we only need to know whether the allocation is for the chunk root or not -- and we can pass that around as a bool instead. This allows us to pull root usage out of the reservation path all the way up to reserve_metadata_bytes itself, which uses it only to compare against fs_info->chunk_root to set the bool. In turn, this eliminates a bunch of races where we use a particular root too early in the mount process. Signed-off-by: Jeff Mahoney <jeffm@suse.com> Reviewed-by: Liu Bo <bo.li.liu@oracle.com> Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
parent
1b86826d12
commit
c1c4919b11
|
@ -97,10 +97,11 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
|
|||
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);
|
||||
|
@ -4628,11 +4629,11 @@ out:
|
|||
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;
|
||||
|
@ -4643,7 +4644,11 @@ static int can_overcommit(struct btrfs_root *root,
|
|||
if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
|
||||
return 0;
|
||||
|
||||
profile = get_alloc_profile_by_root(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);
|
||||
|
||||
/*
|
||||
|
@ -4728,10 +4733,9 @@ static inline int calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
|
|||
/*
|
||||
* 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;
|
||||
|
@ -4788,7 +4792,7 @@ skip_async:
|
|||
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;
|
||||
}
|
||||
|
@ -4898,7 +4902,7 @@ static int flush_space(struct btrfs_fs_info *fs_info,
|
|||
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:
|
||||
|
@ -4929,8 +4933,9 @@ static int flush_space(struct btrfs_fs_info *fs_info,
|
|||
}
|
||||
|
||||
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;
|
||||
|
@ -4945,14 +4950,15 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
|
|||
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))
|
||||
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);
|
||||
|
@ -4966,17 +4972,18 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
|
|||
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) &&
|
||||
|
@ -5013,8 +5020,8 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
|
|||
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);
|
||||
|
@ -5036,8 +5043,9 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
|
|||
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) {
|
||||
|
@ -5075,8 +5083,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
|
|||
int flush_state = FLUSH_DELAYED_ITEMS_NR;
|
||||
|
||||
spin_lock(&space_info->lock);
|
||||
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root,
|
||||
space_info);
|
||||
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
|
||||
false);
|
||||
if (!to_reclaim) {
|
||||
spin_unlock(&space_info->lock);
|
||||
return;
|
||||
|
@ -5155,12 +5163,12 @@ static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
|
|||
* 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;
|
||||
|
@ -5182,7 +5190,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root,
|
|||
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);
|
||||
|
@ -5209,7 +5218,7 @@ static int __reserve_metadata_bytes(struct btrfs_root *root,
|
|||
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,
|
||||
|
@ -5223,7 +5232,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root,
|
|||
* 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");
|
||||
|
@ -5281,9 +5291,10 @@ static int reserve_metadata_bytes(struct btrfs_root *root,
|
|||
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 &&
|
||||
|
@ -5406,8 +5417,7 @@ 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);
|
||||
|
|
Loading…
Reference in New Issue