From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 28 Aug 2019 11:12:47 -0400
Subject: btrfs: rework wake_all_tickets
Git-commit: 2341ccd1bf05b3d844c10ad224cd38b06fd53219
Patch-mainline: v5.4-rc1
References: bsc#1165949
Now that we no longer partially fill tickets we need to rework
wake_all_tickets to call btrfs_try_to_wakeup_tickets() in order to see
if any subsequent tickets are able to be satisfied. If our tickets_id
changes we know something happened and we can keep flushing.
Also if we find a ticket that is smaller than the first ticket in our
queue then we want to retry the flushing loop again in case
may_commit_transaction() decides we could satisfy the ticket by
committing the transaction.
Rename this to maybe_fail_all_tickets() while we're at it, to better
reflect what the function is actually doing.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Acked-by: Nikolay Borisov <nborisov@suse.com>
---
fs/btrfs/space-info.c | 56 ++++++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 49 insertions(+), 7 deletions(-)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index fe3d7e30bfca..eb4a926ea7b9 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -679,19 +679,61 @@ static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
}
-static bool wake_all_tickets(struct list_head *head)
+/*
+ * maybe_fail_all_tickets - we've exhausted our flushing, start failing tickets
+ * @fs_info - fs_info for this fs
+ * @space_info - the space info we were flushing
+ *
+ * We call this when we've exhausted our flushing ability and haven't made
+ * progress in satisfying tickets. The reservation code handles tickets in
+ * order, so if there is a large ticket first and then smaller ones we could
+ * very well satisfy the smaller tickets. This will attempt to wake up any
+ * tickets in the list to catch this case.
+ *
+ * This function returns true if it was able to make progress by clearing out
+ * other tickets, or if it stumbles across a ticket that was smaller than the
+ * first ticket.
+ */
+static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info)
{
struct reserve_ticket *ticket;
+ u64 tickets_id = space_info->tickets_id;
+ u64 first_ticket_bytes = 0;
+
+ while (!list_empty(&space_info->tickets) &&
+ tickets_id == space_info->tickets_id) {
+ ticket = list_first_entry(&space_info->tickets,
+ struct reserve_ticket, list);
+
+ /*
+ * may_commit_transaction will avoid committing the transaction
+ * if it doesn't feel like the space reclaimed by the commit
+ * would result in the ticket succeeding. However if we have a
+ * smaller ticket in the queue it may be small enough to be
+ * satisified by committing the transaction, so if any
+ * subsequent ticket is smaller than the first ticket go ahead
+ * and send us back for another loop through the enospc flushing
+ * code.
+ */
+ if (first_ticket_bytes == 0)
+ first_ticket_bytes = ticket->bytes;
+ else if (first_ticket_bytes > ticket->bytes)
+ return true;
- 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;
+
+ /*
+ * We're just throwing tickets away, so more flushing may not
+ * trip over btrfs_try_granting_tickets, so we need to call it
+ * here to see if we can make progress with the next ticket in
+ * the list.
+ */
+ btrfs_try_granting_tickets(fs_info, space_info);
}
- return false;
+ return (tickets_id != space_info->tickets_id);
}
/*
@@ -759,7 +801,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
if (flush_state > COMMIT_TRANS) {
commit_cycles++;
if (commit_cycles > 2) {
- if (wake_all_tickets(&space_info->tickets)) {
+ if (maybe_fail_all_tickets(fs_info, space_info)) {
flush_state = FLUSH_DELAYED_ITEMS_NR;
commit_cycles--;
} else {