btrfs: change how we decide to commit transactions during flushing

commit 996478ca9c460886ac147eb0d00e99841b71d31b upstream.

Nikolay reported that generic/273 was failing currently with ENOSPC.
Turns out this is because we get to the point where the outstanding
reservations are greater than the pinned space on the fs.  This is a
mistake, previously we used the current reservation amount in
may_commit_transaction, not the entire outstanding reservation amount.
Fix this to find the minimum byte size needed to make progress in
flushing, and pass that into may_commit_transaction.  From there we can
make a smarter decision on whether to commit the transaction or not.
This fixes the failure in generic/273.

From Nikolai, IOW: when we go to the final stage of deciding whether to
do trans commit, instead of passing all the reservations from all
tickets we just pass the reservation for the current ticket. Otherwise,
in case all reservations exceed pinned space, then we don't commit
transaction and fail prematurely. Before we passed num_bytes from
flush_space, where num_bytes was the sum of all pending reserverations,
but now all we do is take the first ticket and commit the trans if we
can satisfy that.

Fixes: 957780eb2788 ("Btrfs: introduce ticketed enospc infrastructure")
Reported-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
[ added Nikolai's comment ]
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e2d7e86b51d1b24059dda46fda085174ac993a3f..08698105fa4a867f702f70284ee2e873228181b0 100644 (file)
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4919,6 +4919,13 @@ skip_async:
        }
 }
 
+struct reserve_ticket {
+       u64 bytes;
+       int error;
+       struct list_head list;
+       wait_queue_head_t wait;
+};
+
 /**
  * maybe_commit_transaction - possibly commit the transaction if its ok to
  * @root - the root we're allocating for
@@ -4930,18 +4937,29 @@ skip_async:
  * will return -ENOSPC.
  */
 static int may_commit_transaction(struct btrfs_fs_info *fs_info,
-                                 struct btrfs_space_info *space_info,
-                                 u64 bytes, int force)
+                                 struct btrfs_space_info *space_info)
 {
+       struct reserve_ticket *ticket = NULL;
        struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv;
        struct btrfs_trans_handle *trans;
+       u64 bytes;
 
        trans = (struct btrfs_trans_handle *)current->journal_info;
        if (trans)
                return -EAGAIN;
 
-       if (force)
-               goto commit;
+       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 = (ticket) ? ticket->bytes : 0;
+       spin_unlock(&space_info->lock);
+
+       if (!bytes)
+               return 0;
 
        /* See if there is enough pinned space to make this reservation */
        if (percpu_counter_compare(&space_info->total_bytes_pinned,
@@ -4956,8 +4974,12 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
                return -ENOSPC;
 
        spin_lock(&delayed_rsv->lock);
+       if (delayed_rsv->size > bytes)
+               bytes = 0;
+       else
+               bytes -= delayed_rsv->size;
        if (percpu_counter_compare(&space_info->total_bytes_pinned,
-                                  bytes - delayed_rsv->size) < 0) {
+                                  bytes) < 0) {
                spin_unlock(&delayed_rsv->lock);
                return -ENOSPC;
        }
@@ -4971,13 +4993,6 @@ commit:
        return btrfs_commit_transaction(trans);
 }
 
-struct reserve_ticket {
-       u64 bytes;
-       int error;
-       struct list_head list;
-       wait_queue_head_t wait;
-};
-
 /*
  * 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
@@ -5027,8 +5042,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
                        ret = 0;
                break;
        case COMMIT_TRANS:
-               ret = may_commit_transaction(fs_info, space_info,
-                                            num_bytes, 0);
+               ret = may_commit_transaction(fs_info, space_info);
                break;
        default:
                ret = -ENOSPC;