[PATCH v2 5/7] memtx: enter small delayed free mode from snapshot iterator

[Vladimir Davydov <vdavydov.dev@gmail.com>]

We must enable SMALL_DELAYED_FREE_MODE to safely use a memtx snapshot
iterator. Currently, we do that in checkpoint related callbacks, but if
we want to reuse snapshot iterators for other purposes, e.g. feeding
a read view to a newly joined replica, we better hide this code behind
snapshot iterator constructors.
---
 src/box/memtx_engine.c | 24 ++++++++++++++++--------
 src/box/memtx_engine.h | 23 +++++++++++++++++++++++
 src/box/memtx_hash.c   |  3 +++
 src/box/memtx_tree.c   |  3 +++
 4 files changed, 45 insertions(+), 8 deletions(-)

diff --git a/src/box/memtx_engine.c b/src/box/memtx_engine.c
index c18177db..ea197cad 100644
--- a/src/box/memtx_engine.c
+++ b/src/box/memtx_engine.c
@@ -610,10 +610,6 @@ memtx_engine_begin_checkpoint(struct engine *engine)
 		memtx->checkpoint = NULL;
 		return -1;
 	}
-
-	/* increment snapshot version; set tuple deletion to delayed mode */
-	memtx->snapshot_version++;
-	small_alloc_setopt(&memtx->alloc, SMALL_DELAYED_FREE_MODE, true);
 	return 0;
 }
 
@@ -661,8 +657,6 @@ memtx_engine_commit_checkpoint(struct engine *engine,
 	/* waitCheckpoint() must have been done. */
 	assert(!memtx->checkpoint->waiting_for_snap_thread);
 
-	small_alloc_setopt(&memtx->alloc, SMALL_DELAYED_FREE_MODE, false);
-
 	if (!memtx->checkpoint->touch) {
 		int64_t lsn = vclock_sum(&memtx->checkpoint->vclock);
 		struct xdir *dir = &memtx->checkpoint->dir;
@@ -703,8 +697,6 @@ memtx_engine_abort_checkpoint(struct engine *engine)
 		memtx->checkpoint->waiting_for_snap_thread = false;
 	}
 
-	small_alloc_setopt(&memtx->alloc, SMALL_DELAYED_FREE_MODE, false);
-
 	/** Remove garbage .inprogress file. */
 	const char *filename =
 		xdir_format_filename(&memtx->checkpoint->dir,
@@ -1014,6 +1006,22 @@ memtx_engine_set_max_tuple_size(struct memtx_engine *memtx, size_t max_size)
 	memtx->max_tuple_size = max_size;
 }
 
+void
+memtx_enter_delayed_free_mode(struct memtx_engine *memtx)
+{
+	memtx->snapshot_version++;
+	if (memtx->delayed_free_mode++ == 0)
+		small_alloc_setopt(&memtx->alloc, SMALL_DELAYED_FREE_MODE, true);
+}
+
+void
+memtx_leave_delayed_free_mode(struct memtx_engine *memtx)
+{
+	assert(memtx->delayed_free_mode > 0);
+	if (--memtx->delayed_free_mode == 0)
+		small_alloc_setopt(&memtx->alloc, SMALL_DELAYED_FREE_MODE, false);
+}
+
 struct tuple *
 memtx_tuple_new(struct tuple_format *format, const char *data, const char *end)
 {
diff --git a/src/box/memtx_engine.h b/src/box/memtx_engine.h
index ccb51678..c092f5d8 100644
--- a/src/box/memtx_engine.h
+++ b/src/box/memtx_engine.h
@@ -137,6 +137,12 @@ struct memtx_engine {
 	size_t max_tuple_size;
 	/** Incremented with each next snapshot. */
 	uint32_t snapshot_version;
+	/**
+	 * Unless zero, freeing of tuples allocated before the last
+	 * call to memtx_enter_delayed_free_mode() is delayed until
+	 * memtx_leave_delayed_free_mode() is called.
+	 */
+	uint32_t delayed_free_mode;
 	/** Memory pool for rtree index iterator. */
 	struct mempool rtree_iterator_pool;
 	/**
@@ -205,6 +211,23 @@ memtx_engine_set_memory(struct memtx_engine *memtx, size_t size);
 void
 memtx_engine_set_max_tuple_size(struct memtx_engine *memtx, size_t max_size);
 
+/**
+ * Enter tuple delayed free mode: tuple allocated before the call
+ * won't be freed until memtx_leave_delayed_free_mode() is called.
+ * This function is reentrant, meaning it's okay to call it multiple
+ * times from the same or different fibers - one just has to leave
+ * the delayed free mode the same amount of times then.
+ */
+void
+memtx_enter_delayed_free_mode(struct memtx_engine *memtx);
+
+/**
+ * Leave tuple delayed free mode. This function undoes the effect
+ * of memtx_enter_delayed_free_mode().
+ */
+void
+memtx_leave_delayed_free_mode(struct memtx_engine *memtx);
+
 /** Allocate a memtx tuple. @sa tuple_new(). */
 struct tuple *
 memtx_tuple_new(struct tuple_format *format, const char *data, const char *end);
diff --git a/src/box/memtx_hash.c b/src/box/memtx_hash.c
index 920f1032..cdd531cb 100644
--- a/src/box/memtx_hash.c
+++ b/src/box/memtx_hash.c
@@ -414,6 +414,8 @@ hash_snapshot_iterator_free(struct snapshot_iterator *iterator)
 	assert(iterator->free == hash_snapshot_iterator_free);
 	struct hash_snapshot_iterator *it =
 		(struct hash_snapshot_iterator *) iterator;
+	memtx_leave_delayed_free_mode((struct memtx_engine *)
+				      it->index->base.engine);
 	light_index_iterator_destroy(&it->index->hash_table, &it->iterator);
 	index_unref(&it->index->base);
 	free(iterator);
@@ -465,6 +467,7 @@ memtx_hash_index_create_snapshot_iterator(struct index *base)
 	index_ref(base);
 	light_index_iterator_begin(&index->hash_table, &it->iterator);
 	light_index_iterator_freeze(&index->hash_table, &it->iterator);
+	memtx_enter_delayed_free_mode((struct memtx_engine *)base->engine);
 	return (struct snapshot_iterator *) it;
 }
 
diff --git a/src/box/memtx_tree.c b/src/box/memtx_tree.c
index 831a2715..e155ecd6 100644
--- a/src/box/memtx_tree.c
+++ b/src/box/memtx_tree.c
@@ -1215,6 +1215,8 @@ tree_snapshot_iterator_free(struct snapshot_iterator *iterator)
 	assert(iterator->free == tree_snapshot_iterator_free);
 	struct tree_snapshot_iterator *it =
 		(struct tree_snapshot_iterator *)iterator;
+	memtx_leave_delayed_free_mode((struct memtx_engine *)
+				      it->index->base.engine);
 	memtx_tree_iterator_destroy(&it->index->tree, &it->tree_iterator);
 	index_unref(&it->index->base);
 	free(iterator);
@@ -1262,6 +1264,7 @@ memtx_tree_index_create_snapshot_iterator(struct index *base)
 	index_ref(base);
 	it->tree_iterator = memtx_tree_iterator_first(&index->tree);
 	memtx_tree_iterator_freeze(&index->tree, &it->tree_iterator);
+	memtx_enter_delayed_free_mode((struct memtx_engine *)base->engine);
 	return (struct snapshot_iterator *) it;
 }
 
-- 
2.20.1