From 7399a12518e2021bc8f7cf3fc1f2996099f787b6 Mon Sep 17 00:00:00 2001 From: Kristofer Karlsson Date: Sat, 16 May 2026 10:39:00 +0200 Subject: [PATCH 1/2] commit-reach: use object flags for tips_reachable_from_bases() tips_reachable_from_bases() walks the commit graph from a set of base commits to find which tip commits are reachable. The inner loop does a linear scan over the tips array to check whether each visited commit is a tip, making the overall cost O(C * T) where C is commits walked and T is the number of tips. Use the RESULT object flag to mark tip commits, replacing the linear scan with a single flag test per visited commit. This reduces the per-commit tip check from O(T) to O(1) and the overall cost from O(C * T) to O(C + T). When multiple refs point to the same commit, the shared object gets the flag once, so all duplicates are handled automatically. The early-termination advancement loop checks the flag on the sorted commits array directly, which naturally handles duplicates since the flag is on the shared commit object. This also removes the index field from struct commit_and_index, since the indirection through the original tips array is no longer needed. This function is called by `git for-each-ref --merged` and `git branch/tag --contains/--no-contains` via reach_filter() in ref-filter.c. Benchmark on a merge-heavy monorepo (2.3M commits, 10,000 refs): Command Before After Speedup for-each-ref --merged HEAD 6.57s 1.59s 4.1x for-each-ref --no-merged HEAD 6.67s 1.66s 4.0x branch --merged HEAD 0.68s 0.61s 10% branch --no-merged HEAD 0.65s 0.61s 8% tag --merged HEAD 0.12s 0.12s - On linux.git with 10,000 synthetic branches at the root commit (worst case for the DFS walk): Command Before After Speedup for-each-ref --merged HEAD 1.35s 0.35s 3.9x for-each-ref --no-merged HEAD 1.82s 0.31s 5.9x The large speedup for for-each-ref is because it checks all 10,000 refs as tips, making the O(T) inner loop expensive. The branch subcommand only checks local branches (fewer tips), so the improvement is smaller. Signed-off-by: Kristofer Karlsson --- commit-reach.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/commit-reach.c b/commit-reach.c index d3a9b3ed6fe561..82614d24096304 100644 --- a/commit-reach.c +++ b/commit-reach.c @@ -1125,7 +1125,6 @@ void ahead_behind(struct repository *r, struct commit_and_index { struct commit *commit; - unsigned int index; timestamp_t generation; }; @@ -1165,7 +1164,6 @@ void tips_reachable_from_bases(struct repository *r, for (size_t i = 0; i < tips_nr; i++) { commits[i].commit = tips[i]; - commits[i].index = i; commits[i].generation = commit_graph_generation(tips[i]); } @@ -1173,6 +1171,9 @@ void tips_reachable_from_bases(struct repository *r, QSORT(commits, tips_nr, compare_commit_and_index_by_generation); min_generation = commits[0].generation; + for (size_t i = 0; i < tips_nr; i++) + commits[i].commit->object.flags |= RESULT; + while (bases) { repo_parse_commit(r, bases->item); commit_list_insert(bases->item, &stack); @@ -1183,20 +1184,16 @@ void tips_reachable_from_bases(struct repository *r, int explored_all_parents = 1; struct commit_list *p; struct commit *c = stack->item; - timestamp_t c_gen = commit_graph_generation(c); /* Does it match any of our tips? */ - for (size_t j = min_generation_index; j < tips_nr; j++) { - if (c_gen < commits[j].generation) - break; - - if (commits[j].commit == c) { - tips[commits[j].index]->object.flags |= mark; + { + if (c->object.flags & RESULT) { + c->object.flags |= mark; - if (j == min_generation_index) { - unsigned int k = j + 1; + if (commits[min_generation_index].commit->object.flags & mark) { + unsigned int k = min_generation_index + 1; while (k < tips_nr && - (tips[commits[k].index]->object.flags & mark)) + (commits[k].commit->object.flags & mark)) k++; /* Terminate early if all found. */ @@ -1232,6 +1229,8 @@ void tips_reachable_from_bases(struct repository *r, } done: + for (size_t i = 0; i < tips_nr; i++) + commits[i].commit->object.flags &= ~RESULT; free(commits); repo_clear_commit_marks(r, SEEN); commit_list_free(stack); From 4d11ebb79ea780c1ce619c66cf9693d819d86d4b Mon Sep 17 00:00:00 2001 From: Kristofer Karlsson Date: Sat, 16 May 2026 17:56:38 +0200 Subject: [PATCH 2/2] t6600: add tests for duplicate tips in tips_reachable_from_bases() When multiple refs point to the same commit, the reachability check must handle them correctly. Add three tests: - duplicate tips, all reachable - duplicate tips, none reachable - duplicate tips at the minimum generation (exercises the early-termination advancement logic) Suggested-by: Derrick Stolee Signed-off-by: Kristofer Karlsson --- t/t6600-test-reach.sh | 45 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/t/t6600-test-reach.sh b/t/t6600-test-reach.sh index dc0421ed2f3726..9486002866fb13 100755 --- a/t/t6600-test-reach.sh +++ b/t/t6600-test-reach.sh @@ -612,6 +612,51 @@ test_expect_success 'for-each-ref merged:none' ' --format="%(refname)" --stdin ' +test_expect_success 'for-each-ref merged:duplicate, all reachable' ' + git branch dup-a commit-3-3 && + git branch dup-b commit-3-3 && + cat >input <<-\EOF && + refs/heads/commit-1-1 + refs/heads/dup-a + refs/heads/dup-b + EOF + cat >expect <<-\EOF && + refs/heads/commit-1-1 + refs/heads/dup-a + refs/heads/dup-b + EOF + run_all_modes git for-each-ref --merged=commit-5-5 \ + --format="%(refname)" --stdin +' + +test_expect_success 'for-each-ref merged:duplicate, none reachable' ' + cat >input <<-\EOF && + refs/heads/dup-a + refs/heads/dup-b + refs/heads/commit-9-9 + EOF + >expect && + run_all_modes git for-each-ref --merged=commit-2-2 \ + --format="%(refname)" --stdin +' + +test_expect_success 'for-each-ref merged:duplicate at min generation' ' + git branch dup-c commit-1-1 && + git branch dup-d commit-1-1 && + cat >input <<-\EOF && + refs/heads/dup-c + refs/heads/dup-d + refs/heads/commit-5-5 + EOF + cat >expect <<-\EOF && + refs/heads/commit-5-5 + refs/heads/dup-c + refs/heads/dup-d + EOF + run_all_modes git for-each-ref --merged=commit-5-5 \ + --format="%(refname)" --stdin +' + # For get_branch_base_for_tip, we only care about # first-parent history. Here is the test graph with # second parents removed: