Merge branch 'tc/last-modified-bloom' into seen

The 'git last-modified' command has been optimized by using Bloom
filters.  It now reuses revision walk filtering logic from 'git log'
to pre-filter commits, and maintains per-path Bloom filters even when
wildcard pathspecs are used.

* tc/last-modified-bloom:
  last-modified: keep per-path Bloom filters for wildcard pathspecs
  last-modified: check pathspec against Bloom filter first
  revision: expose check for paths maybe changed in Bloom filter
  revision: move bloom keyvec precondition into function
seen
Junio C Hamano 2026-07-24 16:12:32 -07:00
commit e8965b160d
3 changed files with 51 additions and 9 deletions

View File

@ -272,6 +272,9 @@ static bool maybe_changed_path(struct last_modified *lm,
if (!filter)
return true;

if (revs_maybe_changed_in_bloom(&lm->rev, filter) == 0)
return false;

hashmap_for_each_entry(&lm->paths, &iter, ent, hashent) {
if (active && !bitmap_get(active, ent->diff_idx))
continue;
@ -358,6 +361,14 @@ static int last_modified_run(struct last_modified *lm)

prepare_revision_walk(&lm->rev);

/*
* prepare_revision_walk() clears bloom_filter_settings for pathspecs
* without a Bloom key. Restore it so the per-path check keeps working.
*/
if (!lm->rev.bloom_filter_settings)
lm->rev.bloom_filter_settings =
get_bloom_filter_settings(lm->rev.repo);

max_count = lm->rev.max_count;

init_active_paths_for_commit(&lm->active_paths);

View File

@ -750,29 +750,43 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
struct commit *commit)
{
struct bloom_filter *filter;
int result = 0;
int result;

if (commit_graph_generation(commit) == GENERATION_NUMBER_INFINITY)
return -1;

filter = get_bloom_filter(revs->repo, commit);

if (!filter) {
count_bloom_filter_not_present++;
return -1;
}

result = revs_maybe_changed_in_bloom(revs, filter);
if (result < 0)
return result;

if (result)
count_bloom_filter_maybe++;
else
count_bloom_filter_definitely_not++;

return result;
}

int revs_maybe_changed_in_bloom(struct rev_info *revs,
struct bloom_filter *filter)
{
int result = 0;

if (!revs->bloom_keyvecs_nr)
return -1;

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)
count_bloom_filter_maybe++;
else
count_bloom_filter_definitely_not++;

return result;
}

@ -806,7 +820,7 @@ static int rev_compare_tree(struct rev_info *revs,
return REV_TREE_SAME;
}

if (revs->bloom_keyvecs_nr && !nth_parent) {
if (!nth_parent) {
bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);

if (bloom_ret == 0)
@ -833,7 +847,7 @@ static int rev_same_tree_as_empty(struct rev_info *revs, struct commit *commit,
if (!t1)
return 0;

if (!nth_parent && revs->bloom_keyvecs_nr) {
if (!nth_parent) {
bloom_ret = check_maybe_different_in_bloom_filter(revs, commit);
if (!bloom_ret)
return 1;

View File

@ -68,6 +68,7 @@ struct string_list;
struct saved_parents;
struct follow_pathspec_slab;
struct bloom_keyvec;
struct bloom_filter;
struct bloom_filter_settings;
struct option;
struct parse_opt_ctx_t;
@ -495,6 +496,22 @@ void reset_revision_walk(void);
*/
int prepare_revision_walk(struct rev_info *revs);

/**
* Take in a changed-path Bloom filter that belongs to a commit, and consult it
* to see if it might have modified any of the paths in the `revs`.
* The caller should look up `filter`, probably with get_bloom_filter().
* prepare_revision_walk() needs to be called in advance to ensure
* pathspec key vectors are set up.
*
* Returns -1 if no sensible answer could be given because of missing
* preconditions (no pathspec key vectors).
* Returns 0 if the commit definitely did not change any of the paths and 1 if
* the commit maybe has changed one of them, although that might be a
* false-positive.
*/
int revs_maybe_changed_in_bloom(struct rev_info *revs,
struct bloom_filter *filter);

/* Drain the commits linked list into the priority queue. */
void rev_info_commit_list_to_queue(struct rev_info *revs);
/**