@matheusbsbs / matheus-bagliano / commits / e369698016

Fork 0

diff: halt tree-diff early after max_changes

When computing the changed-paths bloom filters for the commit-graph, we limit the size of the filter by restricting the number of paths in the diff. Instead of computing a large diff and then ignoring the result, it is better to halt the diff computation early. Create a new "max_changes" option in struct diff_options. If non-zero, then halt the diff computation after discovering strictly more changed paths. This includes paths corresponding to trees that change. Use this max_changes option in the bloom filter calculations. This reduces the time taken to compute the filters for the Linux kernel repo from 2m50s to 2m35s. On a large internal repository with ~500 commits that perform tree-wide changes, the time reduced from 6m15s to 3m48s. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Derrick Stolee committed Mar 30, 2020 at 00:31 UTC e3696980163bdbd3bc56e5ffc69e8770015f366f

3 files changed +14 -1

bloom.c

+3 -1

@@ -133,6 +133,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,

133 struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;

134 int i;

135 struct diff_options diffopt;

136 + int max_changes = 512;

137

138 if (bloom_filters.slab_size == 0)

139 return NULL;

@@ -141,6 +142,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,

142

143 repo_diff_setup(r, &diffopt);

144 diffopt.flags.recursive = 1;

145 + diffopt.max_changes = max_changes;

146 diff_setup_done(&diffopt);

147

148 if (c->parents)

@@ -149,7 +151,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,

151 diff_tree_oid(NULL, &c->object.oid, "", &diffopt);

152 diffcore_std(&diffopt);

153

152 - if (diff_queued_diff.nr <= 512) {

154 + if (diff_queued_diff.nr <= max_changes) {

155 struct hashmap pathmap;

156 struct pathmap_hash_entry *e;

157 struct hashmap_iter iter;

diff.h

@@ -285,6 +285,11 @@ struct diff_options {

285 /* Number of hexdigits to abbreviate raw format output to. */

286 int abbrev;

287

288 + /* If non-zero, then stop computing after this many changes. */

289 + int max_changes;

290 + /* For internal use only. */

291 + int num_changes;

292 +

293 int ita_invisible_in_index;

294 /* white-space error highlighting */

295 #define WSEH_NEW (1<<12)

tree-diff.c

@@ -434,6 +434,9 @@ static struct combine_diff_path *ll_diff_tree_paths(

434 if (diff_can_quit_early(opt))

435 break;

436

437 + if (opt->max_changes && opt->num_changes > opt->max_changes)

438 + break;

439 +

440 if (opt->pathspec.nr) {

441 skip_uninteresting(&t, base, opt);

442 for (i = 0; i < nparent; i++)

@@ -518,6 +521,7 @@ static struct combine_diff_path *ll_diff_tree_paths(

521

522 /* t↓ */

523 update_tree_entry(&t);

524 + opt->num_changes++;

525 }

526

527 /* t > p[imin] */

@@ -535,6 +539,7 @@ static struct combine_diff_path *ll_diff_tree_paths(

539 skip_emit_tp:

540 /* ∀ pi=p[imin] pi↓ */

541 update_tp_entries(tp, nparent);

542 + opt->num_changes++;

543 }

544 }

545

@@ -552,6 +557,7 @@ struct combine_diff_path *diff_tree_paths(

557 const struct object_id **parents_oid, int nparent,

558 struct strbuf *base, struct diff_options *opt)

559 {

560 + opt->num_changes = 0;

561 p = ll_diff_tree_paths(p, oid, parents_oid, nparent, base, opt);

562

563 /*