diff --git a/bloom.c b/bloom.c index 2d6aef9098..db9fb82437 100644 --- a/bloom.c +++ b/bloom.c @@ -222,7 +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 <= settings->max_changed_paths) { + if (diff_queued_diff.nr <= settings->max_changed_paths) { struct hashmap pathmap; struct pathmap_hash_entry *e; struct hashmap_iter iter; @@ -259,6 +259,12 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, diff_free_filepair(diff_queued_diff.queue[i]); } + if (hashmap_get_size(&pathmap) > settings->max_changed_paths) { + if (computed) + *computed |= BLOOM_TRUNC_LARGE; + goto cleanup; + } + 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)); @@ -268,6 +274,7 @@ struct bloom_filter *get_or_compute_bloom_filter(struct repository *r, add_key_to_filter(&key, filter, settings); } + cleanup: hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry); } else { for (i = 0; i < diff_queued_diff.nr; i++) diff --git a/diff.h b/diff.h index e0c0af6286..1d32b71885 100644 --- a/diff.h +++ b/diff.h @@ -287,8 +287,6 @@ struct diff_options { /* If non-zero, then stop computing after this many changes. */ int max_changes; - /* For internal use only. */ - int num_changes; int ita_invisible_in_index; /* white-space error highlighting */ diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh index ca7cc7afb7..6535a3c5d5 100755 --- a/t/t4216-log-bloom.sh +++ b/t/t4216-log-bloom.sh @@ -176,21 +176,103 @@ test_expect_success 'persist filter settings' ' grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15,\"max_changed_paths\":512" trace2-auto.txt ' +test_max_changed_paths () { + grep "\"max_changed_paths\":$1" $2 +} + +test_filter_computed () { + grep "\"key\":\"filter-computed\",\"value\":\"$1\"" $2 +} + +test_filter_trunc_large () { + grep "\"key\":\"filter-trunc-large\",\"value\":\"$1\"" $2 +} + test_expect_success 'correctly report changes over limit' ' - git init 513changes && + git init limits && ( - cd 513changes && - for i in $(test_seq 1 513) + cd limits && + mkdir d && + mkdir d/e && + + for i in $(test_seq 1 2) do - echo $i >file$i.txt || return 1 + printf $i >d/file$i.txt && + printf $i >d/e/file$i.txt || return 1 done && - git add . && + + mkdir mode && + printf bash >mode/script.sh && + + mkdir foo && + touch foo/bar && + touch foo.txt && + + git add d foo foo.txt mode && git commit -m "files" && - git commit-graph write --reachable --changed-paths && - for i in $(test_seq 1 513) + + # Commit has 7 file and 4 directory adds + GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \ + GIT_TRACE2_EVENT="$(pwd)/trace" \ + git commit-graph write --reachable --changed-paths && + test_max_changed_paths 10 trace && + test_filter_computed 1 trace && + test_filter_trunc_large 1 trace && + + for path in $(git ls-tree -r --name-only HEAD) + do + git -c commitGraph.readChangedPaths=false log \ + -- $path >expect && + git log -- $path >actual && + test_cmp expect actual || return 1 + done && + + # Make a variety of path changes + printf new1 >d/e/file1.txt && + printf new2 >d/file2.txt && + rm d/e/file2.txt && + rm -r foo && + printf text >foo && + mkdir f && + printf new1 >f/file1.txt && + + # including a mode-only change (counts as modified) + git update-index --chmod=+x mode/script.sh && + + git add foo d f && + git commit -m "complicated" && + + # start from scratch and rebuild + rm -f .git/objects/info/commit-graph && + GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=10 \ + GIT_TRACE2_EVENT="$(pwd)/trace-edit" \ + git commit-graph write --reachable --changed-paths && + test_max_changed_paths 10 trace-edit && + test_filter_computed 2 trace-edit && + test_filter_trunc_large 2 trace-edit && + + for path in $(git ls-tree -r --name-only HEAD) + do + git -c commitGraph.readChangedPaths=false log \ + -- $path >expect && + git log -- $path >actual && + test_cmp expect actual || return 1 + done && + + # start from scratch and rebuild + rm -f .git/objects/info/commit-graph && + GIT_TEST_BLOOM_SETTINGS_MAX_CHANGED_PATHS=11 \ + GIT_TRACE2_EVENT="$(pwd)/trace-update" \ + git commit-graph write --reachable --changed-paths && + test_max_changed_paths 11 trace-update && + test_filter_computed 2 trace-update && + test_filter_trunc_large 0 trace-update && + + for path in $(git ls-tree -r --name-only HEAD) do - git -c core.commitGraph=false log -- file$i.txt >expect && - git log -- file$i.txt >actual && + git -c commitGraph.readChangedPaths=false log \ + -- $path >expect && + git log -- $path >actual && test_cmp expect actual || return 1 done ) diff --git a/tree-diff.c b/tree-diff.c index 6ebad1a46f..7cebbb327e 100644 --- a/tree-diff.c +++ b/tree-diff.c @@ -434,7 +434,7 @@ static struct combine_diff_path *ll_diff_tree_paths( if (diff_can_quit_early(opt)) break; - if (opt->max_changes && opt->num_changes > opt->max_changes) + if (opt->max_changes && diff_queued_diff.nr > opt->max_changes) break; if (opt->pathspec.nr) { @@ -521,7 +521,6 @@ static struct combine_diff_path *ll_diff_tree_paths( /* t↓ */ update_tree_entry(&t); - opt->num_changes++; } /* t > p[imin] */ @@ -539,7 +538,6 @@ static struct combine_diff_path *ll_diff_tree_paths( skip_emit_tp: /* ∀ pi=p[imin] pi↓ */ update_tp_entries(tp, nparent); - opt->num_changes++; } } @@ -557,7 +555,6 @@ struct combine_diff_path *diff_tree_paths( const struct object_id **parents_oid, int nparent, struct strbuf *base, struct diff_options *opt) { - opt->num_changes = 0; p = ll_diff_tree_paths(p, oid, parents_oid, nparent, base, opt); /*