Commit 0d9764f6 authored by Josef Bacik's avatar Josef Bacik Committed by David Sterba
Browse files

btrfs: move reserve_metadata_bytes and supporting code to space-info.c



This moves all of the metadata reservation code into space-info.c.

Reviewed-by: default avatarNikolay Borisov <nborisov@suse.com>
Signed-off-by: default avatarJosef Bacik <josef@toxicpanda.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent 5da6afeb
......@@ -4346,701 +4346,6 @@ out:
return ret;
}
static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info,
unsigned long nr_pages, int nr_items)
{
struct super_block *sb = fs_info->sb;
if (down_read_trylock(&sb->s_umount)) {
writeback_inodes_sb_nr(sb, nr_pages, WB_REASON_FS_FREE_SPACE);
up_read(&sb->s_umount);
} else {
/*
* We needn't worry the filesystem going from r/w to r/o though
* we don't acquire ->s_umount mutex, because the filesystem
* should guarantee the delalloc inodes list be empty after
* the filesystem is readonly(all dirty pages are written to
* the disk).
*/
btrfs_start_delalloc_roots(fs_info, nr_items);
if (!current->journal_info)
btrfs_wait_ordered_roots(fs_info, nr_items, 0, (u64)-1);
}
}
static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
u64 to_reclaim)
{
u64 bytes;
u64 nr;
bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
nr = div64_u64(to_reclaim, bytes);
if (!nr)
nr = 1;
return nr;
}
#define EXTENT_SIZE_PER_ITEM SZ_256K
/*
* shrink metadata reservation for delalloc
*/
static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim,
u64 orig, bool wait_ordered)
{
struct btrfs_space_info *space_info;
struct btrfs_trans_handle *trans;
u64 delalloc_bytes;
u64 dio_bytes;
u64 async_pages;
u64 items;
long time_left;
unsigned long nr_pages;
int loops;
/* Calc the number of the pages we need flush for space reservation */
items = calc_reclaim_items_nr(fs_info, to_reclaim);
to_reclaim = items * EXTENT_SIZE_PER_ITEM;
trans = (struct btrfs_trans_handle *)current->journal_info;
space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
delalloc_bytes = percpu_counter_sum_positive(
&fs_info->delalloc_bytes);
dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
if (delalloc_bytes == 0 && dio_bytes == 0) {
if (trans)
return;
if (wait_ordered)
btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
return;
}
/*
* If we are doing more ordered than delalloc we need to just wait on
* ordered extents, otherwise we'll waste time trying to flush delalloc
* that likely won't give us the space back we need.
*/
if (dio_bytes > delalloc_bytes)
wait_ordered = true;
loops = 0;
while ((delalloc_bytes || dio_bytes) && loops < 3) {
nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
/*
* Triggers inode writeback for up to nr_pages. This will invoke
* ->writepages callback and trigger delalloc filling
* (btrfs_run_delalloc_range()).
*/
btrfs_writeback_inodes_sb_nr(fs_info, nr_pages, items);
/*
* We need to wait for the compressed pages to start before
* we continue.
*/
async_pages = atomic_read(&fs_info->async_delalloc_pages);
if (!async_pages)
goto skip_async;
/*
* Calculate how many compressed pages we want to be written
* before we continue. I.e if there are more async pages than we
* require wait_event will wait until nr_pages are written.
*/
if (async_pages <= nr_pages)
async_pages = 0;
else
async_pages -= nr_pages;
wait_event(fs_info->async_submit_wait,
atomic_read(&fs_info->async_delalloc_pages) <=
(int)async_pages);
skip_async:
spin_lock(&space_info->lock);
if (list_empty(&space_info->tickets) &&
list_empty(&space_info->priority_tickets)) {
spin_unlock(&space_info->lock);
break;
}
spin_unlock(&space_info->lock);
loops++;
if (wait_ordered && !trans) {
btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
} else {
time_left = schedule_timeout_killable(1);
if (time_left)
break;
}
delalloc_bytes = percpu_counter_sum_positive(
&fs_info->delalloc_bytes);
dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
}
}
/**
* maybe_commit_transaction - possibly commit the transaction if its ok to
* @root - the root we're allocating for
* @bytes - the number of bytes we want to reserve
* @force - force the commit
*
* This will check to make sure that committing the transaction will actually
* get us somewhere and then commit the transaction if it does. Otherwise it
* will return -ENOSPC.
*/
static int may_commit_transaction(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info)
{
struct reserve_ticket *ticket = NULL;
struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv;
struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
struct btrfs_trans_handle *trans;
u64 bytes_needed;
u64 reclaim_bytes = 0;
trans = (struct btrfs_trans_handle *)current->journal_info;
if (trans)
return -EAGAIN;
spin_lock(&space_info->lock);
if (!list_empty(&space_info->priority_tickets))
ticket = list_first_entry(&space_info->priority_tickets,
struct reserve_ticket, list);
else if (!list_empty(&space_info->tickets))
ticket = list_first_entry(&space_info->tickets,
struct reserve_ticket, list);
bytes_needed = (ticket) ? ticket->bytes : 0;
spin_unlock(&space_info->lock);
if (!bytes_needed)
return 0;
trans = btrfs_join_transaction(fs_info->extent_root);
if (IS_ERR(trans))
return PTR_ERR(trans);
/*
* See if there is enough pinned space to make this reservation, or if
* we have block groups that are going to be freed, allowing us to
* possibly do a chunk allocation the next loop through.
*/
if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags) ||
__percpu_counter_compare(&space_info->total_bytes_pinned,
bytes_needed,
BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
goto commit;
/*
* See if there is some space in the delayed insertion reservation for
* this reservation.
*/
if (space_info != delayed_rsv->space_info)
goto enospc;
spin_lock(&delayed_rsv->lock);
reclaim_bytes += delayed_rsv->reserved;
spin_unlock(&delayed_rsv->lock);
spin_lock(&delayed_refs_rsv->lock);
reclaim_bytes += delayed_refs_rsv->reserved;
spin_unlock(&delayed_refs_rsv->lock);
if (reclaim_bytes >= bytes_needed)
goto commit;
bytes_needed -= reclaim_bytes;
if (__percpu_counter_compare(&space_info->total_bytes_pinned,
bytes_needed,
BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0)
goto enospc;
commit:
return btrfs_commit_transaction(trans);
enospc:
btrfs_end_transaction(trans);
return -ENOSPC;
}
/*
* Try to flush some data based on policy set by @state. This is only advisory
* and may fail for various reasons. The caller is supposed to examine the
* state of @space_info to detect the outcome.
*/
static void flush_space(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info, u64 num_bytes,
int state)
{
struct btrfs_root *root = fs_info->extent_root;
struct btrfs_trans_handle *trans;
int nr;
int ret = 0;
switch (state) {
case FLUSH_DELAYED_ITEMS_NR:
case FLUSH_DELAYED_ITEMS:
if (state == FLUSH_DELAYED_ITEMS_NR)
nr = calc_reclaim_items_nr(fs_info, num_bytes) * 2;
else
nr = -1;
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
break;
}
ret = btrfs_run_delayed_items_nr(trans, nr);
btrfs_end_transaction(trans);
break;
case FLUSH_DELALLOC:
case FLUSH_DELALLOC_WAIT:
shrink_delalloc(fs_info, num_bytes * 2, num_bytes,
state == FLUSH_DELALLOC_WAIT);
break;
case FLUSH_DELAYED_REFS_NR:
case FLUSH_DELAYED_REFS:
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
break;
}
if (state == FLUSH_DELAYED_REFS_NR)
nr = calc_reclaim_items_nr(fs_info, num_bytes);
else
nr = 0;
btrfs_run_delayed_refs(trans, nr);
btrfs_end_transaction(trans);
break;
case ALLOC_CHUNK:
case ALLOC_CHUNK_FORCE:
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
break;
}
ret = btrfs_chunk_alloc(trans,
btrfs_metadata_alloc_profile(fs_info),
(state == ALLOC_CHUNK) ? CHUNK_ALLOC_NO_FORCE :
CHUNK_ALLOC_FORCE);
btrfs_end_transaction(trans);
if (ret > 0 || ret == -ENOSPC)
ret = 0;
break;
case COMMIT_TRANS:
/*
* If we have pending delayed iputs then we could free up a
* bunch of pinned space, so make sure we run the iputs before
* we do our pinned bytes check below.
*/
btrfs_run_delayed_iputs(fs_info);
btrfs_wait_on_delayed_iputs(fs_info);
ret = may_commit_transaction(fs_info, space_info);
break;
default:
ret = -ENOSPC;
break;
}
trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, state,
ret);
return;
}
static inline u64
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;
u64 expected;
u64 to_reclaim = 0;
list_for_each_entry(ticket, &space_info->tickets, list)
to_reclaim += ticket->bytes;
list_for_each_entry(ticket, &space_info->priority_tickets, list)
to_reclaim += ticket->bytes;
if (to_reclaim)
return to_reclaim;
to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
if (btrfs_can_overcommit(fs_info, space_info, to_reclaim,
BTRFS_RESERVE_FLUSH_ALL, system_chunk))
return 0;
used = btrfs_space_info_used(space_info, true);
if (btrfs_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);
if (used > expected)
to_reclaim = used - expected;
else
to_reclaim = 0;
to_reclaim = min(to_reclaim, space_info->bytes_may_use +
space_info->bytes_reserved);
return to_reclaim;
}
static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
u64 used, bool system_chunk)
{
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(fs_info, space_info,
system_chunk))
return 0;
return (used >= thresh && !btrfs_fs_closing(fs_info) &&
!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
}
static bool wake_all_tickets(struct list_head *head)
{
struct reserve_ticket *ticket;
while (!list_empty(head)) {
ticket = list_first_entry(head, struct reserve_ticket, list);
list_del_init(&ticket->list);
ticket->error = -ENOSPC;
wake_up(&ticket->wait);
if (ticket->bytes != ticket->orig_bytes)
return true;
}
return false;
}
/*
* This is for normal flushers, we can wait all goddamned day if we want to. We
* will loop and continuously try to flush as long as we are making progress.
* We count progress as clearing off tickets each time we have to loop.
*/
static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
{
struct btrfs_fs_info *fs_info;
struct btrfs_space_info *space_info;
u64 to_reclaim;
int flush_state;
int commit_cycles = 0;
u64 last_tickets_id;
fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
spin_lock(&space_info->lock);
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
false);
if (!to_reclaim) {
space_info->flush = 0;
spin_unlock(&space_info->lock);
return;
}
last_tickets_id = space_info->tickets_id;
spin_unlock(&space_info->lock);
flush_state = FLUSH_DELAYED_ITEMS_NR;
do {
flush_space(fs_info, space_info, to_reclaim, flush_state);
spin_lock(&space_info->lock);
if (list_empty(&space_info->tickets)) {
space_info->flush = 0;
spin_unlock(&space_info->lock);
return;
}
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info,
space_info,
false);
if (last_tickets_id == space_info->tickets_id) {
flush_state++;
} else {
last_tickets_id = space_info->tickets_id;
flush_state = FLUSH_DELAYED_ITEMS_NR;
if (commit_cycles)
commit_cycles--;
}
/*
* We don't want to force a chunk allocation until we've tried
* pretty hard to reclaim space. Think of the case where we
* freed up a bunch of space and so have a lot of pinned space
* to reclaim. We would rather use that than possibly create a
* underutilized metadata chunk. So if this is our first run
* through the flushing state machine skip ALLOC_CHUNK_FORCE and
* commit the transaction. If nothing has changed the next go
* around then we can force a chunk allocation.
*/
if (flush_state == ALLOC_CHUNK_FORCE && !commit_cycles)
flush_state++;
if (flush_state > COMMIT_TRANS) {
commit_cycles++;
if (commit_cycles > 2) {
if (wake_all_tickets(&space_info->tickets)) {
flush_state = FLUSH_DELAYED_ITEMS_NR;
commit_cycles--;
} else {
space_info->flush = 0;
}
} else {
flush_state = FLUSH_DELAYED_ITEMS_NR;
}
}
spin_unlock(&space_info->lock);
} while (flush_state <= COMMIT_TRANS);
}
void btrfs_init_async_reclaim_work(struct work_struct *work)
{
INIT_WORK(work, btrfs_async_reclaim_metadata_space);
}
static const enum btrfs_flush_state priority_flush_states[] = {
FLUSH_DELAYED_ITEMS_NR,
FLUSH_DELAYED_ITEMS,
ALLOC_CHUNK,
};
static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
struct reserve_ticket *ticket)
{
u64 to_reclaim;
int flush_state;
spin_lock(&space_info->lock);
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
false);
if (!to_reclaim) {
spin_unlock(&space_info->lock);
return;
}
spin_unlock(&space_info->lock);
flush_state = 0;
do {
flush_space(fs_info, space_info, to_reclaim,
priority_flush_states[flush_state]);
flush_state++;
spin_lock(&space_info->lock);
if (ticket->bytes == 0) {
spin_unlock(&space_info->lock);
return;
}
spin_unlock(&space_info->lock);
} while (flush_state < ARRAY_SIZE(priority_flush_states));
}
static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
struct reserve_ticket *ticket)
{
DEFINE_WAIT(wait);
u64 reclaim_bytes = 0;
int ret = 0;
spin_lock(&space_info->lock);
while (ticket->bytes > 0 && ticket->error == 0) {
ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
if (ret) {
ret = -EINTR;
break;
}
spin_unlock(&space_info->lock);
schedule();
finish_wait(&ticket->wait, &wait);
spin_lock(&space_info->lock);
}
if (!ret)
ret = ticket->error;
if (!list_empty(&ticket->list))
list_del_init(&ticket->list);
if (ticket->bytes && ticket->bytes < ticket->orig_bytes)
reclaim_bytes = ticket->orig_bytes - ticket->bytes;
spin_unlock(&space_info->lock);
if (reclaim_bytes)
btrfs_space_info_add_old_bytes(fs_info, space_info,
reclaim_bytes);
return ret;
}
/**
* reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
* @root - the root we're allocating for
* @space_info - the space info we want to allocate from
* @orig_bytes - the number of bytes we want
* @flush - whether or not we can flush to make our reservation
*
* This will reserve orig_bytes number of bytes from the space info associated
* with the block_rsv. If there is not enough space it will make an attempt to
* flush out space to make room. It will do this by flushing delalloc if
* possible or committing the transaction. If flush is 0 then no attempts to
* regain reservations will be made and this will fail if there is not enough
* space already.
*/
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,
bool system_chunk)
{
struct reserve_ticket ticket;
u64 used;
u64 reclaim_bytes = 0;
int ret = 0;
ASSERT(orig_bytes);
ASSERT(!current->journal_info || flush != BTRFS_RESERVE_FLUSH_ALL);
spin_lock(&space_info->lock);
ret = -ENOSPC;
used = btrfs_space_info_used(space_info, true);
/*
* If we have enough space then hooray, make our reservation and carry
* on. If not see if we can overcommit, and if we can, hooray carry on.
* If not things get more complicated.
*/
if (used + orig_bytes <= space_info->total_bytes) {
btrfs_space_info_update_bytes_may_use(fs_info, space_info,
orig_bytes);
trace_btrfs_space_reservation(fs_info, "space_info",
space_info->flags, orig_bytes, 1);
ret = 0;
} else if (btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush,
system_chunk)) {
btrfs_space_info_update_bytes_may_use(fs_info, space_info,
orig_bytes);
trace_btrfs_space_reservation(fs_info, "space_info",
space_info->flags, orig_bytes, 1);
ret = 0;
}
/*
* If we couldn't make a reservation then setup our reservation ticket
* and kick the async worker if it's not already running.
*
* If we are a priority flusher then we just need to add our ticket to
* the list and we will do our own flushing further down.
*/
if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
ticket.orig_bytes = orig_bytes;
ticket.bytes = orig_bytes;
ticket.error = 0;
init_waitqueue_head(&ticket.wait);
if (flush == BTRFS_RESERVE_FLUSH_ALL) {
list_add_tail(&ticket.list, &space_info->tickets);
if (!space_info->flush) {
space_info->flush = 1;
trace_btrfs_trigger_flush(fs_info,
space_info->flags,
orig_bytes, flush,
"enospc");
queue_work(system_unbound_wq,
&fs_info->async_reclaim_work);
}
} else {
list_add_tail(&ticket.list,
&space_info->priority_tickets);
}
<