diff mbox series

[v2,3/6] btrfs: delayed refs pre-flushing should only run the heads we have

Message ID 4ff8bc928e3770828b2e272e817bc649bf98ab6d.1602863482.git.josef@toxicpanda.com (mailing list archive)
State New, archived
Headers show
Series A variety of lock contention fixes | expand

Commit Message

Josef Bacik Oct. 16, 2020, 3:52 p.m. UTC 
Previously our delayed ref running used the total number of items as the
items to run.  However we changed that to number of heads to run with
the delayed_refs_rsv, as generally we want to run all of the operations
for one bytenr.

But with btrfs_run_delayed_refs(trans, 0) we set our count to 2x the
number of items that we have.  This is generally fine, but if we have
some operation generation loads of delayed refs while we're doing this
pre-flushing in the transaction commit, we'll just spin forever doing
delayed refs.

Fix this to simply pick the number of delayed refs we currently have,
that way we do not end up doing a lot of extra work that's being
generated in other threads.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
---
 fs/btrfs/extent-tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Nikolay Borisov Oct. 20, 2020, 9:08 a.m. UTC | #1 
On 16.10.20 г. 18:52 ч., Josef Bacik wrote:
> Previously our delayed ref running used the total number of items as the
> items to run.  However we changed that to number of heads to run with
> the delayed_refs_rsv, as generally we want to run all of the operations
> for one bytenr.
> 
> But with btrfs_run_delayed_refs(trans, 0) we set our count to 2x the
> number of items that we have.  This is generally fine, but if we have
> some operation generation loads of delayed refs while we're doing this
> pre-flushing in the transaction commit, we'll just spin forever doing
> delayed refs.
> 
> Fix this to simply pick the number of delayed refs we currently have,
> that way we do not end up doing a lot of extra work that's being
> generated in other threads.
> 
> Signed-off-by: Josef Bacik <josef@toxicpanda.com>
> Reviewed-by: Nikolay Borisov <nborisov@suse.com>

Turns out this patch regresses on generic/371 so refrain from merging
for the time being.

<snip>
diff mbox series

Patch

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5fd60b13f4f8..a7f0a1480cd9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2180,7 +2180,7 @@  int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 
 	delayed_refs = &trans->transaction->delayed_refs;
 	if (count == 0)
-		count = atomic_read(&delayed_refs->num_entries) * 2;
+		count = delayed_refs->num_heads_ready;
 
 again:
 #ifdef SCRAMBLE_DELAYED_REFS