merge-ort: reuse path strings in pool_alloc_filespec

pool_alloc_filespec() was written so that the code when pool != NULL
mimicked the code from alloc_filespec(), which including allocating
enough extra space for the path and then copying it.  However, the path
passed to pool_alloc_filespec() is always going to already be in the
same memory pool, so we may as well reuse it instead of copying it.

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:       198.5 ms ±  3.4 ms     198.3 ms ±  2.9 ms
    mega-renames:     679.1 ms ±  5.6 ms     661.8 ms ±  5.9 ms
    just-one-mega:    271.9 ms ±  2.8 ms     264.6 ms ±  2.5 ms

Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/merge-ort.c b/merge-ort.c
index f4f0a3d57f036fd2837f47be3439d393c3166537..86ab8f601211f08023b049c6cf628cba62d20b99 100644 (file)
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -694,17 +694,13 @@ static struct diff_filespec *pool_alloc_filespec(struct mem_pool *pool,
                                                 const char *path)
 {
        struct diff_filespec *spec;
-       size_t len;
 
        if (!pool)
                return alloc_filespec(path);
 
-       /* Same code as alloc_filespec, except allocate from pool */
-       len = strlen(path);
-
-       spec = mem_pool_calloc(pool, 1, st_add3(sizeof(*spec), len, 1));
-       memcpy(spec+1, path, len);
-       spec->path = (void*)(spec+1);
+       /* Similar to alloc_filespec, but allocate from pool and reuse path */
+       spec = mem_pool_calloc(pool, 1, sizeof(*spec));
+       spec->path = (char*)path; /* spec won't modify it */
 
        spec->count = 1;
        spec->is_binary = -1;
@@ -2904,6 +2900,25 @@ static void use_cached_pairs(struct merge_options *opt,
                const char *new_name = entry->value;
                if (!new_name)
                        new_name = old_name;
+               if (pool) {
+                       /*
+                        * cached_pairs has _copies* of old_name and new_name,
+                        * because it has to persist across merges.  When
+                        *   pool != NULL
+                        * pool_alloc_filespec() will just re-use the existing
+                        * filenames, which will also get re-used by
+                        * opt->priv->paths if they become renames, and then
+                        * get freed at the end of the merge, leaving the copy
+                        * in cached_pairs dangling.  Avoid this by making a
+                        * copy here.
+                        *
+                        * When pool == NULL, pool_alloc_filespec() calls
+                        * alloc_filespec(), which makes a copy; we don't want
+                        * to add another.
+                        */
+                       old_name = mem_pool_strdup(pool, old_name);
+                       new_name = mem_pool_strdup(pool, new_name);
+               }
 
                /* We don't care about oid/mode, only filenames and status */
                one = pool_alloc_filespec(pool, old_name);