btrfs: implement space clamping for preemptive flushing

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>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/space-info.c

@@ -212,6 +212,7 @@ 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)
@@ -815,13 +816,28 @@ static 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.
+	 *
+	 * Our clamping range is 2^1 -> 2^8.  Practically speaking that means
+	 * the following:
+	 *
+	 * Amount of RAM        Minimum threshold       Maximum threshold
+	 *
+	 *        256GiB                     1GiB                  128GiB
+	 *        128GiB                   512MiB                   64GiB
+	 *         64GiB                   256MiB                   32GiB
+	 *         32GiB                   128MiB                   16GiB
+	 *         16GiB                    64MiB                    8GiB
+	 *
+	 * These are the range our thresholds will fall in, corresponding to how
+	 * much delalloc we need for the background flusher to kick in.
 	 */
+
 	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;
 
@@ -1045,6 +1061,7 @@ 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);
@@ -1061,6 +1078,8 @@ 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
@@ -1117,6 +1136,10 @@ 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);
 }
 
@@ -1433,6 +1456,24 @@ 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);
+}
+
 /**
  * Try to reserve bytes from the block_rsv's space
  *
@@ -1526,6 +1567,14 @@ 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;
 		/*

fs/btrfs/space-info.h

@@ -22,6 +22,10 @@ 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. The value is >> clamp, so turns
+				   out to be a 2^clamp divisor. */
+
 	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 */