bloom: replace struct bloom_key * with struct bloom_keyvec

Previously, we stored bloom keys in a flat array and marked a commit
as NOT TREESAME if any key reported "definitely not changed".

To support multiple pathspec items, we now require that for each
pathspec item, there exists a bloom key reporting "definitely not
changed".

This "for every" condition makes a flat array insufficient, so we
introduce a new structure to group keys by a single pathspec item.
`struct bloom_keyvec` is introduced to replace `struct bloom_key *`
and `bloom_key_nr`. And because we want to support multiple pathspec
items, we added a bloom_keyvec * and a bloom_keyvec_nr field to
`struct rev_info` to represent an array of bloom_keyvecs. This commit
still optimize only one pathspec item, thus bloom_keyvec_nr can only
be 0 or 1.

New bloom_keyvec_* functions are added to create and destroy a keyvec.
bloom_filter_contains_vec() is added to check if all key in keyvec is
contained in a bloom filter.

Signed-off-by: Lidong Yan <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: brandb97

bloom.c

@@ -278,6 +278,55 @@ void deinit_bloom_filters(void)
 	deep_clear_bloom_filter_slab(&bloom_filters, free_one_bloom_filter);
 }
 
+struct bloom_keyvec *bloom_keyvec_new(const char *path, size_t len,
+				      const struct bloom_filter_settings *settings)
+{
+	struct bloom_keyvec *vec;
+	const char *p;
+	size_t sz;
+	size_t nr = 1;
+
+	p = path;
+	while (*p) {
+		/*
+		 * At this point, the path is normalized to use Unix-style
+		 * path separators. This is required due to how the
+		 * changed-path Bloom filters store the paths.
+		 */
+		if (*p == '/')
+			nr++;
+		p++;
+	}
+
+	sz = sizeof(struct bloom_keyvec);
+	sz += nr * sizeof(struct bloom_key);
+	vec = (struct bloom_keyvec *)xcalloc(1, sz);
+	if (!vec)
+		return NULL;
+	vec->count = nr;
+
+	bloom_key_fill(&vec->key[0], path, len, settings);
+	nr = 1;
+	p = path + len - 1;
+	while (p > path) {
+		if (*p == '/') {
+			bloom_key_fill(&vec->key[nr++], path, p - path, settings);
+		}
+		p--;
+	}
+	assert(nr == vec->count);
+	return vec;
+}
+
+void bloom_keyvec_free(struct bloom_keyvec *vec)
+{
+	if (!vec)
+		return;
+	for (size_t nr = 0; nr < vec->count; nr++)
+		bloom_key_clear(&vec->key[nr]);
+	free(vec);
+}
+
 static int pathmap_cmp(const void *hashmap_cmp_fn_data UNUSED,
 		       const struct hashmap_entry *eptr,
 		       const struct hashmap_entry *entry_or_key,
@@ -539,6 +588,18 @@ int bloom_filter_contains(const struct bloom_filter *filter,
 	return 1;
 }
 
+int bloom_filter_contains_vec(const struct bloom_filter *filter,
+			      const struct bloom_keyvec *vec,
+			      const struct bloom_filter_settings *settings)
+{
+	int ret = 1;
+
+	for (size_t nr = 0; ret > 0 && nr < vec->count; nr++)
+		ret = bloom_filter_contains(filter, &vec->key[nr], settings);
+
+	return ret;
+}
+
 uint32_t test_bloom_murmur3_seeded(uint32_t seed, const char *data, size_t len,
 				   int version)
 {

bloom.h

@@ -74,6 +74,16 @@ struct bloom_key {
 	uint32_t *hashes;
 };
 
+/*
+ * A bloom_keyvec is a vector of bloom_keys, which
+ * can be used to store multiple keys for a single
+ * pathspec item.
+ */
+struct bloom_keyvec {
+	size_t count;
+	struct bloom_key key[FLEX_ARRAY];
+};
+
 int load_bloom_filter_from_graph(struct commit_graph *g,
 				 struct bloom_filter *filter,
 				 uint32_t graph_pos);
@@ -82,6 +92,23 @@ void bloom_key_fill(struct bloom_key *key, const char *data, size_t len,
 		    const struct bloom_filter_settings *settings);
 void bloom_key_clear(struct bloom_key *key);
 
+/*
+ * bloom_keyvec_new - Allocate and populate a bloom_keyvec with keys for the
+ * given path.
+ *
+ * This function splits the input path by '/' and generates a bloom key for each
+ * prefix, in reverse order of specificity. For example, given the input
+ * "a/b/c", it will generate bloom keys for:
+ *   - "a/b/c"
+ *   - "a/b"
+ *   - "a"
+ *
+ * The resulting keys are stored in a newly allocated bloom_keyvec.
+ */
+struct bloom_keyvec *bloom_keyvec_new(const char *path, size_t len,
+				      const struct bloom_filter_settings *settings);
+void bloom_keyvec_free(struct bloom_keyvec *vec);
+
 void add_key_to_filter(const struct bloom_key *key,
 		       struct bloom_filter *filter,
 		       const struct bloom_filter_settings *settings);
@@ -126,6 +153,17 @@ int bloom_filter_contains(const struct bloom_filter *filter,
 			  const struct bloom_key *key,
 			  const struct bloom_filter_settings *settings);
 
+/*
+ * bloom_filter_contains_vec - Check if all keys in a key vector are in the
+ * Bloom filter.
+ *
+ * Returns 1 if **all** keys in the vector are present in the filter,
+ * 0 if **any** key is not present.
+ */
+int bloom_filter_contains_vec(const struct bloom_filter *filter,
+			      const struct bloom_keyvec *v,
+			      const struct bloom_filter_settings *settings);
+
 uint32_t test_bloom_murmur3_seeded(uint32_t seed, const char *data, size_t len,
 				   int version);
 

revision.c

@@ -685,13 +685,14 @@ static int forbid_bloom_filters(struct pathspec *spec)
 	return 0;
 }
 
+static void release_revisions_bloom_keyvecs(struct rev_info *revs);
+
 static void prepare_to_use_bloom_filter(struct rev_info *revs)
 {
 	struct pathspec_item *pi;
 	char *path_alloc = NULL;
-	const char *path, *p;
+	const char *path;
 	size_t len;
-	int path_component_nr = 1;
 
 	if (!revs->commits)
 		return;
@@ -708,6 +709,8 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 	if (!revs->pruning.pathspec.nr)
 		return;
 
+	revs->bloom_keyvecs_nr = 1;
+	CALLOC_ARRAY(revs->bloom_keyvecs, 1);
 	pi = &revs->pruning.pathspec.items[0];
 
 	/* remove single trailing slash from path, if needed */
@@ -718,53 +721,30 @@ static void prepare_to_use_bloom_filter(struct rev_info *revs)
 		path = pi->match;
 
 	len = strlen(path);
-	if (!len) {
-		revs->bloom_filter_settings = NULL;
-		free(path_alloc);
-		return;
-	}
-
-	p = path;
-	while (*p) {
-		/*
-		 * At this point, the path is normalized to use Unix-style
-		 * path separators. This is required due to how the
-		 * changed-path Bloom filters store the paths.
-		 */
-		if (*p == '/')
-			path_component_nr++;
-		p++;
-	}
-
-	revs->bloom_keys_nr = path_component_nr;
-	ALLOC_ARRAY(revs->bloom_keys, revs->bloom_keys_nr);
+	if (!len)
+		goto fail;
 
-	bloom_key_fill(&revs->bloom_keys[0], path, len,
-		       revs->bloom_filter_settings);
-	path_component_nr = 1;
-
-	p = path + len - 1;
-	while (p > path) {
-		if (*p == '/')
-			bloom_key_fill(&revs->bloom_keys[path_component_nr++],
-				       path, p - path,
-				       revs->bloom_filter_settings);
-		p--;
-	}
+	revs->bloom_keyvecs[0] =
+		bloom_keyvec_new(path, len, revs->bloom_filter_settings);
 
 	if (trace2_is_enabled() && !bloom_filter_atexit_registered) {
 		atexit(trace2_bloom_filter_statistics_atexit);
 		bloom_filter_atexit_registered = 1;
 	}
 
+	return;
+
+fail:
+	revs->bloom_filter_settings = NULL;
 	free(path_alloc);
+	release_revisions_bloom_keyvecs(revs);
 }
 
 static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 						 struct commit *commit)
 {
 	struct bloom_filter *filter;
-	int result = 1, j;
+	int result = 0;
 
 	if (!revs->repo->objects->commit_graph)
 		return -1;
@@ -779,10 +759,10 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 		return -1;
 	}
 
-	for (j = 0; result && j < revs->bloom_keys_nr; j++) {
-		result = bloom_filter_contains(filter,
-					       &revs->bloom_keys[j],
-					       revs->bloom_filter_settings);
+	for (size_t nr = 0; !result && nr < revs->bloom_keyvecs_nr; nr++) {
+		result = bloom_filter_contains_vec(filter,
+						   revs->bloom_keyvecs[nr],
+						   revs->bloom_filter_settings);
 	}
 
 	if (result)
@@ -823,7 +803,7 @@ static int rev_compare_tree(struct rev_info *revs,
 			return REV_TREE_SAME;
 	}
 
-	if (revs->bloom_keys_nr && !nth_parent) {
+	if (revs->bloom_keyvecs_nr && !nth_parent) {
 		bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);
 
 		if (bloom_ret == 0)
@@ -850,7 +830,7 @@ static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit,
 	if (!t1)
 		return 0;
 
-	if (!nth_parent && revs->bloom_keys_nr) {
+	if (!nth_parent && revs->bloom_keyvecs_nr) {
 		bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);
 		if (!bloom_ret)
 			return 1;
@@ -3200,6 +3180,14 @@ static void release_revisions_mailmap(struct string_list *mailmap)
 
 static void release_revisions_topo_walk_info(struct topo_walk_info *info);
 
+static void release_revisions_bloom_keyvecs(struct rev_info *revs)
+{
+	for (size_t nr = 0; nr < revs->bloom_keyvecs_nr; nr++)
+		bloom_keyvec_free(revs->bloom_keyvecs[nr]);
+	FREE_AND_NULL(revs->bloom_keyvecs);
+	revs->bloom_keyvecs_nr = 0;
+}
+
 static void free_void_commit_list(void *list)
 {
 	free_commit_list(list);
@@ -3228,11 +3216,7 @@ void release_revisions(struct rev_info *revs)
 	clear_decoration(&revs->treesame, free);
 	line_log_free(revs);
 	oidset_clear(&revs->missing_commits);
-
-	for (int i = 0; i < revs->bloom_keys_nr; i++)
-		bloom_key_clear(&revs->bloom_keys[i]);
-	FREE_AND_NULL(revs->bloom_keys);
-	revs->bloom_keys_nr = 0;
+	release_revisions_bloom_keyvecs(revs);
 }
 
 static void add_child(struct rev_info *revs, struct commit *parent, struct commit *child)

revision.h

@@ -62,7 +62,7 @@ struct repository;
 struct rev_info;
 struct string_list;
 struct saved_parents;
-struct bloom_key;
+struct bloom_keyvec;
 struct bloom_filter_settings;
 struct option;
 struct parse_opt_ctx_t;
@@ -360,8 +360,8 @@ struct rev_info {
 
 	/* Commit graph bloom filter fields */
 	/* The bloom filter key(s) for the pathspec */
-	struct bloom_key *bloom_keys;
-	int bloom_keys_nr;
+	struct bloom_keyvec **bloom_keyvecs;
+	int bloom_keyvecs_nr;
 
 	/*
 	 * The bloom filter settings used to generate the key.