diff mbox series

[v3,10/12] btrfs: implement space clamping for preemptive flushing

Message ID 5ddb5076afa5872f8edf3bb4ea17aacec8e079fd.1602249928.git.josef@toxicpanda.com
State New, archived
Headers show
Series Improve preemptive ENOSPC flushing | expand

Commit Message

Josef Bacik Oct. 9, 2020, 1:28 p.m. UTC
Starting preemptive flushing at 50% of available free space is a good
start, but some workloads are particularly abusive and can quickly
overwhelm the preemptive flushing code and drive us into using tickets.

Handle this by clamping down on our threshold for starting and
continuing to run preemptive flushing.  This is particularly important
for our overcommit case, as we can really drive the file system into
overages and then it's more difficult to pull it back as we start to
actually fill up the file system.

The clamping is essentially 2^CLAMP, but we start at 1 so whatever we
calculate for overcommit is the baseline.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 fs/btrfs/space-info.c | 38 ++++++++++++++++++++++++++++++++++++--
 fs/btrfs/space-info.h |  3 +++
 2 files changed, 39 insertions(+), 2 deletions(-)

Comments

David Sterba Oct. 29, 2020, 5:48 p.m. UTC | #1
On Fri, Oct 09, 2020 at 09:28:27AM -0400, Josef Bacik wrote:
> +static inline void maybe_clamp_preempt(struct btrfs_fs_info *fs_info,
> +				       struct btrfs_space_info *space_info)
> +{
> +	u64 ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes);
> +	u64 delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes);
> +
> +	/*
> +	 * If we're heavy on ordered operations then clamping won't help us.  We
> +	 * need to clamp specifically to keep up with dirty'ing buffered
> +	 * writers, because there's not a 1:1 correlation of writing delalloc
> +	 * and freeing space, like there is with flushing delayed refs or
> +	 * delayed nodes.  If we're already more ordered than delalloc then
> +	 * we're keeping up, otherwise we aren't and should probably clamp.
> +	 */
> +	if (ordered < delalloc)
> +		space_info->clamp = min(space_info->clamp + 1, 8);

So the divisor will go up to 2^8 = 256, is that intentional?

> --- a/fs/btrfs/space-info.h
> +++ b/fs/btrfs/space-info.h
> @@ -22,6 +22,9 @@ struct btrfs_space_info {
>  				   the space info if we had an ENOSPC in the
>  				   allocator. */
>  
> +	int clamp;		/* Used to scale our threshold for preemptive
> +				   flushing. */

Struct comments should go on the line before so we don't have this
awkward formatting but the rest of the struct has that so let it be. One
thing I'm missing is that it's power of two, I'll add it there.

> +
>  	unsigned int full:1;	/* indicates that we cannot allocate any more
>  				   chunks for this space */
>  	unsigned int chunk_alloc:1;	/* set if we are allocating a chunk */
> -- 
> 2.26.2
diff mbox series

Patch

diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index c56a4827956f..5ee698c12a7b 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -206,6 +206,7 @@  static int create_space_info(struct btrfs_fs_info *info, u64 flags)
 	INIT_LIST_HEAD(&space_info->ro_bgs);
 	INIT_LIST_HEAD(&space_info->tickets);
 	INIT_LIST_HEAD(&space_info->priority_tickets);
+	space_info->clamp = 1;
 
 	ret = btrfs_sysfs_add_space_info_type(info, space_info);
 	if (ret)
@@ -806,13 +807,13 @@  static inline bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info,
 	 * because this doesn't quite work how we want.  If we had more than 50%
 	 * of the space_info used by bytes_used and we had 0 available we'd just
 	 * constantly run the background flusher.  Instead we want it to kick in
-	 * if our reclaimable space exceeds 50% of our available free space.
+	 * if our reclaimable space exceeds our clamped free space.
 	 */
 	thresh = calc_available_free_space(fs_info, space_info,
 					   BTRFS_RESERVE_FLUSH_ALL);
 	thresh += (space_info->total_bytes - space_info->bytes_used -
 		   space_info->bytes_reserved - space_info->bytes_readonly);
-	thresh >>= 1;
+	thresh >>= space_info->clamp;
 
 	used = space_info->bytes_pinned;
 
@@ -1036,6 +1037,7 @@  static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 	struct btrfs_block_rsv *delayed_refs_rsv;
 	struct btrfs_block_rsv *global_rsv;
 	struct btrfs_block_rsv *trans_rsv;
+	int loops = 0;
 
 	fs_info = container_of(work, struct btrfs_fs_info,
 			       preempt_reclaim_work);
@@ -1052,6 +1054,8 @@  static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		u64 to_reclaim, block_rsv_size;
 		u64 global_rsv_size = global_rsv->reserved;
 
+		loops++;
+
 		/*
 		 * We don't have a precise counter for the metadata being
 		 * reserved for delalloc, so we'll approximate it by subtracting
@@ -1109,6 +1113,10 @@  static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work)
 		cond_resched();
 		spin_lock(&space_info->lock);
 	}
+
+	/* We only went through once, back off our clamping. */
+	if (loops == 1 && !space_info->reclaim_size)
+		space_info->clamp = max(1, space_info->clamp - 1);
 	spin_unlock(&space_info->lock);
 }
 
@@ -1422,6 +1430,24 @@  static inline bool is_normal_flushing(enum btrfs_reserve_flush_enum flush)
 		(flush == BTRFS_RESERVE_FLUSH_ALL_STEAL);
 }
 
+static inline void maybe_clamp_preempt(struct btrfs_fs_info *fs_info,
+				       struct btrfs_space_info *space_info)
+{
+	u64 ordered = percpu_counter_sum_positive(&fs_info->ordered_bytes);
+	u64 delalloc = percpu_counter_sum_positive(&fs_info->delalloc_bytes);
+
+	/*
+	 * If we're heavy on ordered operations then clamping won't help us.  We
+	 * need to clamp specifically to keep up with dirty'ing buffered
+	 * writers, because there's not a 1:1 correlation of writing delalloc
+	 * and freeing space, like there is with flushing delayed refs or
+	 * delayed nodes.  If we're already more ordered than delalloc then
+	 * we're keeping up, otherwise we aren't and should probably clamp.
+	 */
+	if (ordered < delalloc)
+		space_info->clamp = min(space_info->clamp + 1, 8);
+}
+
 /**
  * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
  * @root - the root we're allocating for
@@ -1514,6 +1540,14 @@  static int __reserve_bytes(struct btrfs_fs_info *fs_info,
 			list_add_tail(&ticket.list,
 				      &space_info->priority_tickets);
 		}
+
+		/*
+		 * We were forced to add a reserve ticket, so our preemptive
+		 * flushing is unable to keep up.  Clamp down on the threshold
+		 * for the preemptive flushing in order to keep up with the
+		 * workload.
+		 */
+		maybe_clamp_preempt(fs_info, space_info);
 	} else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
 		used += orig_bytes;
 		/*
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 5646393b928c..bcbbfae131f6 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -22,6 +22,9 @@  struct btrfs_space_info {
 				   the space info if we had an ENOSPC in the
 				   allocator. */
 
+	int clamp;		/* Used to scale our threshold for preemptive
+				   flushing. */
+
 	unsigned int full:1;	/* indicates that we cannot allocate any more
 				   chunks for this space */
 	unsigned int chunk_alloc:1;	/* set if we are allocating a chunk */