@@ -180,13 +180,12 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
struct commit *c,
int compute_if_not_present,
+ const struct bloom_filter_settings *settings,
enum bloom_filter_computed *computed)
{
struct bloom_filter *filter;
- struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
int i;
struct diff_options diffopt;
- int max_changes = 512;
if (computed)
*computed = BLOOM_NOT_COMPUTED;
@@ -211,7 +210,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
repo_diff_setup(r, &diffopt);
diffopt.flags.recursive = 1;
diffopt.detect_rename = 0;
- diffopt.max_changes = max_changes;
+ diffopt.max_changes = settings->max_changed_paths;
diff_setup_done(&diffopt);
/* ensure commit is parsed so we have parent information */
@@ -223,7 +222,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
diffcore_std(&diffopt);
- if (diffopt.num_changes <= max_changes) {
+ if (diffopt.num_changes <= settings->max_changed_paths) {
struct hashmap pathmap;
struct pathmap_hash_entry *e;
struct hashmap_iter iter;
@@ -260,13 +259,13 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
diff_free_filepair(diff_queued_diff.queue[i]);
}
- filter->len = (hashmap_get_size(&pathmap) * settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
+ filter->len = (hashmap_get_size(&pathmap) * settings->bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
filter->data = xcalloc(filter->len, sizeof(unsigned char));
hashmap_for_each_entry(&pathmap, &iter, e, entry) {
struct bloom_key key;
- fill_bloom_key(e->path, strlen(e->path), &key, &settings);
- add_key_to_filter(&key, filter, &settings);
+ fill_bloom_key(e->path, strlen(e->path), &key, settings);
+ add_key_to_filter(&key, filter, settings);
}
hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
@@ -98,10 +98,11 @@ enum bloom_filter_computed {
struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
struct commit *c,
int compute_if_not_present,
+ const struct bloom_filter_settings *settings,
enum bloom_filter_computed *computed);
#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
- (r), (c), 0, NULL)
+ (r), (c), 0, NULL, NULL)
int bloom_filter_contains(const struct bloom_filter *filter,
const struct bloom_key *key,
@@ -1434,6 +1434,7 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
ctx->r,
c,
1,
+ ctx->bloom_settings,
&computed);
if (computed & BLOOM_COMPUTED) {
ctx->count_bloom_filter_computed++;
@@ -1691,17 +1692,6 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
int num_chunks = 3;
uint64_t chunk_offset;
struct object_id file_hash;
- struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
-
- if (!ctx->bloom_settings) {
- bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
- bloom_settings.bits_per_entry);
- bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
- bloom_settings.num_hashes);
- bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
- bloom_settings.max_changed_paths);
- ctx->bloom_settings = &bloom_settings;
- }
if (ctx->split) {
struct strbuf tmp_file = STRBUF_INIT;
@@ -2147,6 +2137,7 @@ int write_commit_graph(struct object_directory *odb,
uint32_t i, count_distinct = 0;
int res = 0;
int replace = 0;
+ struct bloom_filter_settings bloom_settings = DEFAULT_BLOOM_FILTER_SETTINGS;
if (!commit_graph_compatible(the_repository))
return 0;
@@ -2160,6 +2151,14 @@ int write_commit_graph(struct object_directory *odb,
ctx->split_opts = split_opts;
ctx->total_bloom_filter_data_size = 0;
+ bloom_settings.bits_per_entry = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_BITS_PER_ENTRY",
+ bloom_settings.bits_per_entry);
+ bloom_settings.num_hashes = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_NUM_HASHES",
+ bloom_settings.num_hashes);
+ bloom_settings.max_changed_paths = git_env_ulong("GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS",
+ bloom_settings.max_changed_paths);
+ ctx->bloom_settings = &bloom_settings;
+
if (flags & COMMIT_GRAPH_WRITE_BLOOM_FILTERS)
ctx->changed_paths = 1;
if (!(flags & COMMIT_GRAPH_NO_WRITE_BLOOM_FILTERS)) {
@@ -40,6 +40,7 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
setup_git_directory();
c = lookup_commit(the_repository, commit_oid);
filter = get_or_compute_bloom_filter(the_repository, c, 1,
+ &settings,
NULL);
print_bloom_filter(filter);
}
When 'get_or_compute_bloom_filter()' needs to compute a Bloom filter from scratch, it looks to the default 'struct bloom_filter_settings' in order to determine the maximum number of changed paths, number of bits per entry, and so on. All of these values have so far been constant, and so there was no need to pass in a pointer from the caller (eg., the one that is stored in the 'struct write_commit_graph_context'). Start passing in a 'struct bloom_filter_settings *' instead of using the default values to respect graph-specific settings (eg., in the case of setting 'GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS'). In order to have an initialized value for these settings, move its initialization to earlier in the commit-graph write. Signed-off-by: Taylor Blau <me@ttaylorr.com> --- bloom.c | 13 ++++++------- bloom.h | 3 ++- commit-graph.c | 21 ++++++++++----------- t/helper/test-bloom.c | 1 + 4 files changed, 19 insertions(+), 19 deletions(-)