@@ -1275,7 +1275,7 @@ static int maybe_changed_path(struct repository *r,
if (commit_graph_generation(origin->commit) == GENERATION_NUMBER_INFINITY)
return 1;
- filter = get_bloom_filter(r, origin->commit, 0);
+ filter = get_bloom_filter(r, origin->commit);
if (!filter)
return 1;
@@ -177,9 +177,10 @@ static int pathmap_cmp(const void *hashmap_cmp_fn_data,
return strcmp(e1->path, e2->path);
}
-struct bloom_filter *get_bloom_filter(struct repository *r,
- struct commit *c,
- int compute_if_not_present)
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+ struct commit *c,
+ int compute_if_not_present,
+ int *computed)
{
struct bloom_filter *filter;
struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
@@ -187,6 +188,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
struct diff_options diffopt;
int max_changes = 512;
+ if (computed)
+ *computed = 0;
+
if (!bloom_filters.slab_size)
return NULL;
@@ -273,6 +277,9 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
filter->len = 0;
}
+ if (computed)
+ *computed = 1;
+
free(diff_queued_diff.queue);
DIFF_QUEUE_CLEAR(&diff_queued_diff);
@@ -89,9 +89,13 @@ void add_key_to_filter(const struct bloom_key *key,
void init_bloom_filters(void);
-struct bloom_filter *get_bloom_filter(struct repository *r,
- struct commit *c,
- int compute_if_not_present);
+struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
+ struct commit *c,
+ int compute_if_not_present,
+ int *computed);
+
+#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
+ (r), (c), 0, NULL)
int bloom_filter_contains(const struct bloom_filter *filter,
const struct bloom_key *key,
@@ -964,6 +964,9 @@ struct write_commit_graph_context {
const struct split_commit_graph_opts *split_opts;
size_t total_bloom_filter_data_size;
const struct bloom_filter_settings *bloom_settings;
+
+ int count_bloom_filter_found_large;
+ int count_bloom_filter_computed;
};
static int write_graph_chunk_fanout(struct hashfile *f,
@@ -1175,7 +1178,7 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f,
uint32_t cur_pos = 0;
while (list < last) {
- struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+ struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
size_t len = filter ? filter->len : 0;
cur_pos += len;
display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1215,7 +1218,7 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
hashwrite_be32(f, ctx->bloom_settings->bits_per_entry);
while (list < last) {
- struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+ struct bloom_filter *filter = get_bloom_filter(ctx->r, *list);
size_t len = filter ? filter->len : 0;
display_progress(ctx->progress, ++ctx->progress_cnt);
@@ -1385,6 +1388,22 @@ static void compute_generation_numbers(struct write_commit_graph_context *ctx)
stop_progress(&ctx->progress);
}
+static void trace2_bloom_filter_write_statistics(struct write_commit_graph_context *ctx)
+{
+ struct json_writer jw = JSON_WRITER_INIT;
+
+ jw_object_begin(&jw, 0);
+ jw_object_intmax(&jw, "filter_found_large",
+ ctx->count_bloom_filter_found_large);
+ jw_object_intmax(&jw, "filter_computed",
+ ctx->count_bloom_filter_computed);
+ jw_end(&jw);
+
+ trace2_data_json("commit-graph", the_repository, "bloom_statistics", &jw);
+
+ jw_release(&jw);
+}
+
static void compute_bloom_filters(struct write_commit_graph_context *ctx)
{
int i;
@@ -1407,12 +1426,25 @@ static void compute_bloom_filters(struct write_commit_graph_context *ctx)
QSORT(sorted_commits, ctx->commits.nr, commit_gen_cmp);
for (i = 0; i < ctx->commits.nr; i++) {
+ int computed = 0;
struct commit *c = sorted_commits[i];
- struct bloom_filter *filter = get_bloom_filter(ctx->r, c, 1);
+ struct bloom_filter *filter = get_or_compute_bloom_filter(
+ ctx->r,
+ c,
+ 1,
+ &computed);
+ if (computed) {
+ ctx->count_bloom_filter_computed++;
+ if (filter && !filter->len)
+ ctx->count_bloom_filter_found_large++;
+ }
ctx->total_bloom_filter_data_size += sizeof(unsigned char) * filter->len;
display_progress(progress, i + 1);
}
+ if (trace2_is_enabled())
+ trace2_bloom_filter_write_statistics(ctx);
+
free(sorted_commits);
stop_progress(&progress);
}
@@ -1159,7 +1159,7 @@ static int bloom_filter_check(struct rev_info *rev,
return 1;
if (!rev->bloom_filter_settings ||
- !(filter = get_bloom_filter(rev->repo, commit, 0)))
+ !(filter = get_bloom_filter(rev->repo, commit)))
return 1;
if (!range)
@@ -751,7 +751,7 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY)
return -1;
- filter = get_bloom_filter(revs->repo, commit, 0);
+ filter = get_bloom_filter(revs->repo, commit);
if (!filter) {
count_bloom_filter_not_present++;
@@ -39,7 +39,8 @@ static void get_bloom_filter_for_commit(const struct object_id *commit_oid)
struct bloom_filter *filter;
setup_git_directory();
c = lookup_commit(the_repository, commit_oid);
- filter = get_bloom_filter(the_repository, c, 1);
+ filter = get_or_compute_bloom_filter(the_repository, c, 1,
+ NULL);
print_bloom_filter(filter);
}
'get_bloom_filter' takes a flag to control whether it will compute a Bloom filter if the requested one is missing. In the next patch, we'll add yet another parameter to this method, which would force all but one caller to specify an extra 'NULL' parameter at the end. Instead of doing this, split 'get_bloom_filter' into two functions: 'get_bloom_filter' and 'get_or_compute_bloom_filter'. The former only looks up a Bloom filter (and does not compute one if it's missing, thus dropping the 'compute_if_not_present' flag). The latter does compute missing Bloom filters, with an additional parameter to store whether or not it needed to do so. This simplifies many call-sites, since the majority of existing callers to 'get_bloom_filter' do not want missing Bloom filters to be computed (so they can drop the parameter entirely and use the simpler version of the function). While we're at it, instrument the new 'get_or_compute_bloom_filter()' with two counters in the 'write_commit_graph_context' struct which store the number of filters that we computed, and the number of those which were too large to store. It would be nice to drop the 'compute_if_not_present' flag entirely, since all remaining callers of 'get_or_compute_bloom_filter' pass it as '1', but this will change in a future patch and hence cannot be removed. Signed-off-by: Taylor Blau <me@ttaylorr.com> --- blame.c | 2 +- bloom.c | 13 ++++++++++--- bloom.h | 10 +++++++--- commit-graph.c | 38 +++++++++++++++++++++++++++++++++++--- line-log.c | 2 +- revision.c | 2 +- t/helper/test-bloom.c | 3 ++- 7 files changed, 57 insertions(+), 13 deletions(-)