Btrfs devel - Oct 2011 - [PATCH] Btrfs: wait for ordered extents if we're in trouble when shrinking delalloc

The only way we actually reclaim delalloc space is waiting for the IO to
completely finish.  Usually we kick off a bunch of IO and wait for a little bit
and hope we can make our reservation, and usually this works out pretty well.
With overcommit however we can get seriously underwater if we''re
filling up the
disk quickly, so we need to be able to force the delalloc shrinker to wait for
the ordered IO to finish to give us a better chance of actually reclaiming
enough space to get our reservation.  Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>
---
 fs/btrfs/extent-tree.c |   25 +++++++++++++++++--------
 1 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 79365a4..96cbc51 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3334,7 +3334,8 @@ out:
  * shrink metadata reservation for delalloc
  */
 static int shrink_delalloc(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root, u64 to_reclaim, int sync)
+			   struct btrfs_root *root, u64 to_reclaim,
+			   bool wait_ordered)
 {
 	struct btrfs_block_rsv *block_rsv;
 	struct btrfs_space_info *space_info;
@@ -3387,11 +3388,15 @@ static int shrink_delalloc(struct btrfs_trans_handle
*trans,
 		if (trans && trans->transaction->blocked)
 			return -EAGAIN;
 
-		time_left = schedule_timeout_interruptible(1);
+		if (wait_ordered && !trans) {
+			btrfs_wait_ordered_extents(root, 0, 0);
+		} else {
+			time_left = schedule_timeout_interruptible(1);
 
-		/* We were interrupted, exit */
-		if (time_left)
-			break;
+			/* We were interrupted, exit */
+			if (time_left)
+				break;
+		}
 
 		/* we''ve kicked the IO a few times, if anything has been freed,
 		 * exit.  There is no sense in looping here for a long time
@@ -3406,8 +3411,7 @@ static int shrink_delalloc(struct btrfs_trans_handle
*trans,
 		}
 
 	}
-	if (reclaimed < to_reclaim && !trans)
-		btrfs_wait_ordered_extents(root, 0, 0);
+
 	return reclaimed >= to_reclaim;
 }
 
@@ -3438,6 +3442,7 @@ static int reserve_metadata_bytes(struct btrfs_root *root,
 	int ret = 0;
 	bool committed = false;
 	bool flushing = false;
+	bool wait_ordered = false;
 
 	trans = (struct btrfs_trans_handle *)current->journal_info;
 again:
@@ -3496,6 +3501,7 @@ again:
 		 * amount plus the amount of bytes that we need for this
 		 * reservation.
 		 */
+		wait_ordered = true;
 		num_bytes = used - space_info->total_bytes +
 			(orig_bytes * (retries + 1));
 	}
@@ -3530,6 +3536,8 @@ again:
 		if (used + num_bytes < space_info->total_bytes + avail) {
 			space_info->bytes_may_use += orig_bytes;
 			ret = 0;
+		} else {
+			wait_ordered = true;
 		}
 	}
 
@@ -3552,7 +3560,7 @@ again:
 	 * We do synchronous shrinking since we don''t actually unreserve
 	 * metadata until after the IO is completed.
 	 */
-	ret = shrink_delalloc(trans, root, num_bytes, 1);
+	ret = shrink_delalloc(trans, root, num_bytes, wait_ordered);
 	if (ret < 0)
 		goto out;
 
@@ -3564,6 +3572,7 @@ again:
 	 * so go back around and try again.
 	 */
 	if (retries < 2) {
+		wait_ordered = true;
 		retries++;
 		goto again;
 	}
-- 
1.7.5.2

--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs"
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html