[v7,16/16] bloom: introduce `deinit_bloom_filters()`

Commit Message

Taylor Blau June 25, 2024, 5:40 p.m. UTC

After we are done using Bloom filters, we do not currently clean up any
memory allocated by the commit slab used to store those filters in the
first place.

Besides the bloom_filter structures themselves, there is mostly nothing
to free() in the first place, since in the read-only path all Bloom
filter's `data` members point to a memory mapped region in the
commit-graph file itself.

But when generating Bloom filters from scratch (or initializing
truncated filters) we allocate additional memory to store the filter's
data.

Keep track of when we need to free() this additional chunk of memory by
using an extra pointer `to_free`. Most of the time this will be NULL
(indicating that we are representing an existing Bloom filter stored in
a memory mapped region). When it is non-NULL, free it before discarding
the Bloom filters slab.

Suggested-by: Jonathan Tan <[e-mail]>
Signed-off-by: Taylor Blau <[e-mail]>
Signed-off-by: Junio C Hamano <[e-mail]>
Signed-off-by: Taylor Blau <[e-mail]>
---
 bloom.c        | 16 +++++++++++++++-
 bloom.h        |  3 +++
 commit-graph.c |  4 ++++
 3 files changed, 22 insertions(+), 1 deletion(-)

Patch

diff --git a/bloom.c b/bloom.c
index 740c1767ea..d080a1b616 100644
--- a/bloom.c
+++ b/bloom.c
@@ -92,6 +92,7 @@  int load_bloom_filter_from_graph(struct commit_graph *g,
 					sizeof(unsigned char) * start_index +
 					BLOOMDATA_CHUNK_HEADER_SIZE);
 	filter->version = g->bloom_filter_settings->hash_version;
+	filter->to_free = NULL;
 
 	return 1;
 }
@@ -264,6 +265,18 @@  void init_bloom_filters(void)
 	init_bloom_filter_slab(&bloom_filters);
 }
 
+static void free_one_bloom_filter(struct bloom_filter *filter)
+{
+	if (!filter)
+		return;
+	free(filter->to_free);
+}
+
+void deinit_bloom_filters(void)
+{
+	deep_clear_bloom_filter_slab(&bloom_filters, free_one_bloom_filter);
+}
+
 static int pathmap_cmp(const void *hashmap_cmp_fn_data UNUSED,
 		       const struct hashmap_entry *eptr,
 		       const struct hashmap_entry *entry_or_key,
@@ -280,7 +293,7 @@  static int pathmap_cmp(const void *hashmap_cmp_fn_data UNUSED,
 static void init_truncated_large_filter(struct bloom_filter *filter,
 					int version)
 {
-	filter->data = xmalloc(1);
+	filter->data = filter->to_free = xmalloc(1);
 	filter->data[0] = 0xFF;
 	filter->len = 1;
 	filter->version = version;
@@ -482,6 +495,7 @@  struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
 			filter->len = 1;
 		}
 		CALLOC_ARRAY(filter->data, filter->len);
+		filter->to_free = filter->data;
 
 		hashmap_for_each_entry(&pathmap, &iter, e, entry) {
 			struct bloom_key key;
diff --git a/bloom.h b/bloom.h
index e3a9b68905..d20e64bfbb 100644
--- a/bloom.h
+++ b/bloom.h
@@ -56,6 +56,8 @@  struct bloom_filter {
 	unsigned char *data;
 	size_t len;
 	int version;
+
+	void *to_free;
 };
 
 /*
@@ -96,6 +98,7 @@  void add_key_to_filter(const struct bloom_key *key,
 		       const struct bloom_filter_settings *settings);
 
 void init_bloom_filters(void);
+void deinit_bloom_filters(void);
 
 enum bloom_filter_computed {
 	BLOOM_NOT_COMPUTED = (1 << 0),
diff --git a/commit-graph.c b/commit-graph.c
index 2f0a08f302..c02bef7e72 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -831,6 +831,7 @@  void close_commit_graph(struct raw_object_store *o)
 		return;
 
 	clear_commit_graph_data_slab(&commit_graph_data_slab);
+	deinit_bloom_filters();
 	free_commit_graph(o->commit_graph);
 	o->commit_graph = NULL;
 }
@@ -2647,6 +2648,9 @@  int write_commit_graph(struct object_directory *odb,
 
 	res = write_commit_graph_file(ctx);
 
+	if (ctx->changed_paths)
+		deinit_bloom_filters();
+
 	if (ctx->split)
 		mark_commit_graphs(ctx);