[RFC PATCH v2 2/2] ext4: fast commit: allocate the range array lazily

[Daejun Park]

Patch 1 keeps the disjoint-range set in a fixed EXT4_FC_MAX_RANGES+1
array.  Embedding that in every ext4_inode_info costs ~140 bytes on
inodes that never use fast commit or only ever touch a single
contiguous range.

Keep the first range inline in i_fc_range and allocate the array only
when a second disjoint range appears; free it when the inode is
evicted.  The tracking path runs under i_fc_lock, so the array is
allocated with GFP_ATOMIC; on allocation failure we coalesce into the
inline range -- i.e. the original single-range behaviour -- so memory
pressure never forces a full commit.  The per-inode fast-commit
footprint drops to 20 bytes.

Signed-off-by: Daejun Park <daejun7.park@xxxxxxxxxxx>
---
 fs/ext4/ext4.h        | 23 +++++++++++-----
 fs/ext4/fast_commit.c | 64 ++++++++++++++++++++++++++++++++++++++++---
 fs/ext4/super.c       |  1 +
 3 files changed, 77 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8e93d30766fd..d93cc52cd01e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1106,14 +1106,23 @@ struct ext4_inode_info {
 					 */
 
 	/*
-	 * Disjoint lblk ranges modified in this fast commit.  Tracking the
+	 * Logical block ranges modified in this fast commit.  Tracking the
 	 * actual modified ranges (instead of one coalesced [min,max]) avoids
 	 * snapshotting the whole spanned extent map for scattered allocations.
-	 * Sorted by start, mutually disjoint.  Bounded by EXT4_FC_MAX_RANGES;
-	 * the extra slot is transient room used while inserting before an
-	 * overflow merge.  Protected by i_fc_lock.
+	 *
+	 * The first range is kept inline in i_fc_range, so the common case of a
+	 * single contiguous dirty region needs no allocation.  When a second
+	 * disjoint range appears the inode is upgraded to the i_fc_ranges array
+	 * (EXT4_FC_MAX_RANGES + 1 entries, sorted and mutually disjoint; the
+	 * extra slot is transient room used while inserting before an overflow
+	 * merge), allocated then and freed when the inode is evicted.  If that
+	 * allocation fails we fall back to coalescing into i_fc_range, i.e. the
+	 * original single coalesced-range behaviour.  i_fc_nr_ranges counts the
+	 * valid ranges; while i_fc_ranges is NULL it is 0 or 1.  Protected by
+	 * i_fc_lock.
 	 */
-	struct ext4_fc_lblk_range i_fc_ranges[EXT4_FC_MAX_RANGES + 1];
+	struct ext4_fc_lblk_range i_fc_range;
+	struct ext4_fc_lblk_range *i_fc_ranges;
 	unsigned int i_fc_nr_ranges;
 
 	/*
@@ -1135,8 +1144,8 @@ struct ext4_inode_info {
 	spinlock_t i_raw_lock;	/* protects updates to the raw inode */
 
 	/*
-	 * Protect concurrent accesses on i_fc_ranges, i_fc_nr_ranges
-	 * and inode's EXT4_FC_STATE_COMMITTING state bit.
+	 * Protect concurrent accesses on i_fc_range, i_fc_ranges,
+	 * i_fc_nr_ranges and inode's EXT4_FC_STATE_COMMITTING state bit.
 	 */
 	spinlock_t i_fc_lock;
 
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 1ea3742a55b1..9d36365eae02 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -230,6 +230,7 @@ void ext4_fc_init_inode(struct inode *inode)
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
 	ext4_fc_reset_inode(inode);
+	ei->i_fc_ranges = NULL;
 	ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING);
 	ext4_clear_inode_state(inode, EXT4_STATE_FC_REQUEUE);
 	INIT_LIST_HEAD(&ei->i_fc_list);
@@ -691,6 +692,8 @@ static int __track_range(handle_t *handle, struct inode *inode, void *arg,
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct __track_range_args *__arg =
 		(struct __track_range_args *)arg;
+	ext4_lblk_t start = __arg->start, end = __arg->end;
+	ext4_lblk_t s0, e0;
 
 	if (inode->i_ino < EXT4_FIRST_INO(inode->i_sb)) {
 		ext4_debug("Special inode %llu being modified\n", inode->i_ino);
@@ -701,12 +704,61 @@ static int __track_range(handle_t *handle, struct inode *inode, void *arg,
 	 * A sub-block punch hole rounds up the start and down the end, passing
 	 * end == start - 1: no whole block changed, so there is nothing to
 	 * track.  (ext4_fc_track_template has already reset the range set for a
-	 * new transaction.)
+	 * new transaction, so we need not do it here.)
 	 */
-	if (__arg->end < __arg->start)
+	if (end < start)
 		return 0;
 
-	ext4_fc_range_add(ei, __arg->start, __arg->end);
+	/* Already upgraded to the heap array: full multi-interval tracking. */
+	if (ei->i_fc_ranges) {
+		ext4_fc_range_add(ei, start, end);
+		return 0;
+	}
+
+	/* First range of this commit stays inline, no allocation needed. */
+	if (ei->i_fc_nr_ranges == 0) {
+		ei->i_fc_range.start = start;
+		ei->i_fc_range.len = end - start + 1;
+		ei->i_fc_nr_ranges = 1;
+		return 0;
+	}
+
+	/* One inline range so far. */
+	s0 = ei->i_fc_range.start;
+	e0 = s0 + ei->i_fc_range.len - 1;
+
+	/* Disjoint from it: try to upgrade to the array for exact tracking. */
+	if (start > e0 + 1 || end + 1 < s0) {
+		struct ext4_fc_lblk_range *heap;
+
+		/*
+		 * GFP_ATOMIC: we hold i_fc_lock.  __GFP_NOWARN: failure is not
+		 * fatal -- we fall back to the single coalesced range below --
+		 * so it must not splat under memory pressure.
+		 */
+		heap = kmalloc_array(EXT4_FC_MAX_RANGES + 1, sizeof(*heap),
+				     GFP_ATOMIC | __GFP_NOWARN);
+		if (heap) {
+			heap[0] = ei->i_fc_range;
+			ei->i_fc_ranges = heap;
+			ext4_fc_range_add(ei, start, end);
+			return 0;
+		}
+		/*
+		 * Out of memory: fall back to the original single coalesced
+		 * range by absorbing the gap below.  This over-logs the spanned
+		 * extents but stays a valid fast commit (no full-commit
+		 * fallback), so there is nothing to mark ineligible.
+		 */
+	}
+
+	/* Overlapping/adjacent, or array allocation failed: coalesce inline. */
+	if (start < s0)
+		s0 = start;
+	if (end > e0)
+		e0 = end;
+	ei->i_fc_range.start = s0;
+	ei->i_fc_range.len = e0 - s0 + 1;
 
 	return 0;
 }
@@ -1178,7 +1230,11 @@ static int ext4_fc_snapshot_inode_data(struct inode *inode,
 			*nr_rangesp = 0;
 		return 0;
 	}
-	memcpy(tracked, ei->i_fc_ranges, nr_tracked * sizeof(tracked[0]));
+	if (ei->i_fc_ranges)
+		memcpy(tracked, ei->i_fc_ranges,
+		       nr_tracked * sizeof(tracked[0]));
+	else
+		tracked[0] = ei->i_fc_range;	/* inline single-range mode */
 	ei->i_fc_nr_ranges = 0;
 	spin_unlock(&ei->i_fc_lock);
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f2c52cc74676..cfa7e6bec385 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1455,6 +1455,7 @@ static void ext4_free_in_core_inode(struct inode *inode)
 		pr_warn("%s: inode %llu still in fc list",
 			__func__, inode->i_ino);
 	}
+	kfree(EXT4_I(inode)->i_fc_ranges);
 	kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
 }
 
-- 
2.43.0