@matheusbsbs / matheus-bagliano / commits / 81afdf7a2e

diffcore-rename: compute dir_rename_guess from dir_rename_counts

dir_rename_counts has a mapping of a mapping, in particular, it has old_dir => { new_dir => count } We want a simple mapping of old_dir => new_dir based on which new_dir had the highest count for a given old_dir. Compute this and store it in dir_rename_guess. This is the final piece of the puzzle needed to make our guesses at which directory files have been moved to when basenames aren't unique. For the testcases mentioned in commit 557ac0350d ("merge-ort: begin performance work; instrument with trace2_region_* calls", 2020-10-28), this change improves the performance as follows: Before After no-renames: 12.775 s ± 0.062 s 12.596 s ± 0.061 s mega-renames: 188.754 s ± 0.284 s 130.465 s ± 0.259 s just-one-mega: 5.599 s ± 0.019 s 3.958 s ± 0.010 s Reviewed-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Elijah Newren committed Feb 27, 2021 at 00:30 UTC 81afdf7a2e625a7ecfb17c00c871b409e853694d

1 file changed +41 -4

diffcore-rename.c

+41 -4

@@ -389,6 +389,24 @@ static void dirname_munge(char *filename)

389 *slash = '\0';

390 }

391

392 +static const char *get_highest_rename_path(struct strintmap *counts)

393 +{

394 + int highest_count = 0;

395 + const char *highest_destination_dir = NULL;

396 + struct hashmap_iter iter;

397 + struct strmap_entry *entry;

398 +

399 + strintmap_for_each_entry(counts, &iter, entry) {

400 + const char *destination_dir = entry->key;

401 + intptr_t count = (intptr_t)entry->value;

402 + if (count > highest_count) {

403 + highest_count = count;

404 + highest_destination_dir = destination_dir;

405 + }

406 + }

407 + return highest_destination_dir;

408 +}

409 +

410 static void increment_count(struct dir_rename_info *info,

411 char *old_dir,

412 char *new_dir)

@@ -512,6 +530,8 @@ static void initialize_dir_rename_info(struct dir_rename_info *info,

530 struct strset *dirs_removed,

531 struct strmap *dir_rename_count)

532 {

533 + struct hashmap_iter iter;

534 + struct strmap_entry *entry;

535 int i;

536

537 if (!dirs_removed) {

@@ -558,6 +578,23 @@ static void initialize_dir_rename_info(struct dir_rename_info *info,

578 rename_dst[i].p->one->path,

579 rename_dst[i].p->two->path);

580 }

581 +

582 + /*

583 + * Now we collapse

584 + * dir_rename_count: old_directory -> {new_directory -> count}

585 + * down to

586 + * dir_rename_guess: old_directory -> best_new_directory

587 + * where best_new_directory is the one with the highest count.

588 + */

589 + strmap_for_each_entry(info->dir_rename_count, &iter, entry) {

590 + /* entry->key is source_dir */

591 + struct strintmap *counts = entry->value;

592 + char *best_newdir;

593 +

594 + best_newdir = xstrdup(get_highest_rename_path(counts));

595 + strmap_put(&info->dir_rename_guess, entry->key,

596 + best_newdir);

597 + }

598 }

599

600 void partial_clear_dir_rename_count(struct strmap *dir_rename_count)

@@ -682,10 +719,10 @@ static int idx_possible_rename(char *filename, struct dir_rename_info *info)

719 * rename.

720 *

721 * This function, idx_possible_rename(), is only responsible for (4).

685 - * The conditions/steps in (1)-(3) will be handled via setting up

686 - * dir_rename_count and dir_rename_guess in a future

687 - * initialize_dir_rename_info() function. Steps (0) and (5) are

688 - * handled by the caller of this function.

722 + * The conditions/steps in (1)-(3) are handled via setting up

723 + * dir_rename_count and dir_rename_guess in

724 + * initialize_dir_rename_info(). Steps (0) and (5) are handled by

725 + * the caller of this function.

726 */

727 char *old_dir, *new_dir;

728 struct strbuf new_path = STRBUF_INIT;