btrfs: discard: speed up async discard up to iops_limit

Instead of using iops_limit only for cutting off extremes, calculate the
discard delay directly from it, so it closely follows iops_limit and
doesn't under-discard even though quotas are not saturated.

The iops limit could be hit more often in some cases and could increase
the discard rate.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/discard.c

@@ -519,7 +519,6 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
 	s64 discardable_bytes;
 	u32 iops_limit;
 	unsigned long delay;
-	unsigned long lower_limit = BTRFS_DISCARD_MIN_DELAY_MSEC;
 
 	discardable_extents = atomic_read(&discard_ctl->discardable_extents);
 	if (!discardable_extents)
@@ -550,11 +549,12 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
 
 	iops_limit = READ_ONCE(discard_ctl->iops_limit);
 	if (iops_limit)
-		lower_limit = max_t(unsigned long, lower_limit,
-				    MSEC_PER_SEC / iops_limit);
+		delay = MSEC_PER_SEC / iops_limit;
+	else
+		delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents;
 
-	delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents;
-	delay = clamp(delay, lower_limit, BTRFS_DISCARD_MAX_DELAY_MSEC);
+	delay = clamp(delay, BTRFS_DISCARD_MIN_DELAY_MSEC,
+		      BTRFS_DISCARD_MAX_DELAY_MSEC);
 	discard_ctl->delay = msecs_to_jiffies(delay);
 
 	spin_unlock(&discard_ctl->lock);