btrfs: improve delayed refs iterations

This issue was found when I tried to delete a heavily reflinked file,
when deleting such files, other transaction operation will not have a
chance to make progress, for example, start_transaction() will blocked
in wait_current_trans(root) for long time, sometimes it even triggers
soft lockups, and the time taken to delete such heavily reflinked file
is also very large, often hundreds of seconds. Using perf top, it reports
that:

PerfTop:    7416 irqs/sec  kernel:99.8%  exact:  0.0% [4000Hz cpu-clock],  (all, 4 CPUs)
---------------------------------------------------------------------------------------
    84.37%  [btrfs]             [k] __btrfs_run_delayed_refs.constprop.80
    11.02%  [kernel]            [k] delay_tsc
     0.79%  [kernel]            [k] _raw_spin_unlock_irq
     0.78%  [kernel]            [k] _raw_spin_unlock_irqrestore
     0.45%  [kernel]            [k] do_raw_spin_lock
     0.18%  [kernel]            [k] __slab_alloc
It seems __btrfs_run_delayed_refs() took most cpu time, after some debug
work, I found it's select_delayed_ref() causing this issue, for a delayed
head, in our case, it'll be full of BTRFS_DROP_DELAYED_REF nodes, but
select_delayed_ref() will firstly try to iterate node list to find
BTRFS_ADD_DELAYED_REF nodes, obviously it's a disaster in this case, and
waste much time.

To fix this issue, we introduce a new ref_add_list in struct btrfs_delayed_ref_head,
then in select_delayed_ref(), if this list is not empty, we can directly use
nodes in this list. With this patch, it just took about 10~15 seconds to
delte the same file. Now using perf top, it reports that:

PerfTop:    2734 irqs/sec  kernel:99.5%  exact:  0.0% [4000Hz cpu-clock],  (all, 4 CPUs)
----------------------------------------------------------------------------------------

    20.74%  [kernel]          [k] _raw_spin_unlock_irqrestore
    16.33%  [kernel]          [k] __slab_alloc
     5.41%  [kernel]          [k] lock_acquired
     4.42%  [kernel]          [k] lock_acquire
     4.05%  [kernel]          [k] lock_release
     3.37%  [kernel]          [k] _raw_spin_unlock_irq

For normal files, this patch also gives help, at least we do not need to
iterate whole list to found BTRFS_ADD_DELAYED_REF nodes.

Signed-off-by: Wang Xiaoguang <wangxg.fnst@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
Wang Xiaoguang 2016-10-26 18:07:33 +08:00 коммит произвёл David Sterba
Родитель 824d8dff88
Коммит 1d57ee9416
4 изменённых файлов: 37 добавлений и 6 удалений

Просмотреть файл

@ -189,6 +189,8 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
} else {
assert_spin_locked(&head->lock);
list_del(&ref->list);
if (!list_empty(&ref->add_list))
list_del(&ref->add_list);
}
ref->in_tree = 0;
btrfs_put_delayed_ref(ref);
@ -431,6 +433,15 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
exist->action = ref->action;
mod = -exist->ref_mod;
exist->ref_mod = ref->ref_mod;
if (ref->action == BTRFS_ADD_DELAYED_REF)
list_add_tail(&exist->add_list,
&href->ref_add_list);
else if (ref->action == BTRFS_DROP_DELAYED_REF) {
ASSERT(!list_empty(&exist->add_list));
list_del(&exist->add_list);
} else {
ASSERT(0);
}
} else
mod = -ref->ref_mod;
}
@ -444,6 +455,8 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
add_tail:
list_add_tail(&ref->list, &href->ref_list);
if (ref->action == BTRFS_ADD_DELAYED_REF)
list_add_tail(&ref->add_list, &href->ref_add_list);
atomic_inc(&root->num_entries);
trans->delayed_ref_updates++;
spin_unlock(&href->lock);
@ -590,6 +603,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
head_ref->must_insert_reserved = must_insert_reserved;
head_ref->is_data = is_data;
INIT_LIST_HEAD(&head_ref->ref_list);
INIT_LIST_HEAD(&head_ref->ref_add_list);
head_ref->processing = 0;
head_ref->total_ref_mod = count_mod;
head_ref->qgroup_reserved = 0;
@ -671,6 +685,8 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
ref->is_head = 0;
ref->in_tree = 1;
ref->seq = seq;
INIT_LIST_HEAD(&ref->list);
INIT_LIST_HEAD(&ref->add_list);
full_ref = btrfs_delayed_node_to_tree_ref(ref);
full_ref->parent = parent;
@ -726,6 +742,8 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
ref->is_head = 0;
ref->in_tree = 1;
ref->seq = seq;
INIT_LIST_HEAD(&ref->list);
INIT_LIST_HEAD(&ref->add_list);
full_ref = btrfs_delayed_node_to_data_ref(ref);
full_ref->parent = parent;

Просмотреть файл

@ -42,6 +42,12 @@ struct btrfs_delayed_ref_node {
/*data/tree ref use list, stored in ref_head->ref_list. */
struct list_head list;
/*
* If action is BTRFS_ADD_DELAYED_REF, also link this node to
* ref_head->ref_add_list, then we do not need to iterate the
* whole ref_head->ref_list to find BTRFS_ADD_DELAYED_REF nodes.
*/
struct list_head add_list;
/* the starting bytenr of the extent */
u64 bytenr;
@ -99,6 +105,8 @@ struct btrfs_delayed_ref_head {
spinlock_t lock;
struct list_head ref_list;
/* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */
struct list_head ref_add_list;
struct rb_node href_node;

Просмотреть файл

@ -4344,6 +4344,8 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
list) {
ref->in_tree = 0;
list_del(&ref->list);
if (!list_empty(&ref->add_list))
list_del(&ref->add_list);
atomic_dec(&delayed_refs->num_entries);
btrfs_put_delayed_ref(ref);
}

Просмотреть файл

@ -2454,13 +2454,14 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head)
* the extent item from the extent tree, when there still are references
* to add, which would fail because they would not find the extent item.
*/
list_for_each_entry(ref, &head->ref_list, list) {
if (ref->action == BTRFS_ADD_DELAYED_REF)
return ref;
}
if (!list_empty(&head->ref_add_list))
return list_first_entry(&head->ref_add_list,
struct btrfs_delayed_ref_node, add_list);
return list_entry(head->ref_list.next, struct btrfs_delayed_ref_node,
list);
ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
list);
ASSERT(list_empty(&ref->add_list));
return ref;
}
/*
@ -2620,6 +2621,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
actual_count++;
ref->in_tree = 0;
list_del(&ref->list);
if (!list_empty(&ref->add_list))
list_del(&ref->add_list);
}
atomic_dec(&delayed_refs->num_entries);