commit: allow associating auxiliary info on-demand
The "indegree" field in the commit object is only used while sorting a list of commits in topological order, and wasting memory otherwise. We would prefer to shrink the size of individual commit objects, which we may have to hold thousands of in-core. We could eject "indegree" field out from the commit object and represent it as a dynamic table based on the decoration infrastructure, but the decoration is meant for sparse annotation and is not a good match. Instead, let's try a different approach. - Assign an integer (commit->index) to each commit we keep in-core (reuse the space of "indegree" field for it); - When running the topological sort, allocate an array of integers in bulk (called "slab"), use the commit->index as an index into this array, and store the "indegree" information there. This does _not_ reduce the memory footprint of a commit object, but the commit->index can be used as the index to dynamically associate commits with other kinds of information as needed. Signed-off-by: Junio C Hamano <gitster@pobox.com>
Jeff King committed
Apr 9, 2013 at 02:52 UTC
96c4f4a370591b4796628abe18f27f0133b21954
2 files changed
+51
-10
commit.c
+50
-9
@@ -14,6 +14,7 @@ static struct commit_extra_header *read_commit_extra_header_lines(const char *bu
14
int save_commit_buffer = 1;
15
16
const char *commit_type = "commit";
17
+static int commit_count;
18
19
static struct commit *check_commit(struct object *obj,
20
const unsigned char *sha1,
@@ -58,8 +59,11 @@ struct commit *lookup_commit_or_die(const unsigned char *sha1, const char *ref_n
59
struct commit *lookup_commit(const unsigned char *sha1)
60
{
61
struct object *obj = lookup_object(sha1);
61
- if (!obj)
62
- return create_object(sha1, OBJ_COMMIT, alloc_commit_node());
62
+ if (!obj) {
63
+ struct commit *c = alloc_commit_node();
64
+ c->index = commit_count++;
65
+ return create_object(sha1, OBJ_COMMIT, c);
66
+ }
67
if (!obj->type)
68
obj->type = OBJ_COMMIT;
69
return check_commit(obj, sha1, 0);
@@ -497,6 +501,36 @@ struct commit *pop_commit(struct commit_list **stack)
501
return item;
502
}
503
504
+struct commit_slab {
505
+ int *buf;
506
+ int alloc;
507
+};
508
+
509
+static void slab_init(struct commit_slab *s)
510
+{
511
+ memset(s, 0, sizeof(*s));
512
+}
513
+
514
+static void slab_clear(struct commit_slab *s)
515
+{
516
+ free(s->buf);
517
+ slab_init(s);
518
+}
519
+
520
+static inline int *slab_at(struct commit_slab *s, const struct commit *c)
521
+{
522
+ if (s->alloc <= c->index) {
523
+ int new_alloc = alloc_nr(s->alloc);
524
+ if (new_alloc <= c->index)
525
+ new_alloc = c->index + 1;
526
+
527
+ s->buf = xrealloc(s->buf, new_alloc * sizeof(*s->buf));
528
+ memset(s->buf + s->alloc, 0, new_alloc - s->alloc);
529
+ s->alloc = new_alloc;
530
+ }
531
+ return s->buf + c->index;
532
+}
533
+
534
/*
535
* Performs an in-place topological sort on the list supplied.
536
*/
@@ -505,15 +539,18 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
539
struct commit_list *next, *orig = *list;
540
struct commit_list *work, **insert;
541
struct commit_list **pptr;
542
+ struct commit_slab indegree;
543
544
if (!orig)
545
return;
546
*list = NULL;
547
548
+ slab_init(&indegree);
549
+
550
/* Mark them and clear the indegree */
551
for (next = orig; next; next = next->next) {
552
struct commit *commit = next->item;
516
- commit->indegree = 1;
553
+ *slab_at(&indegree, commit) = 1;
554
}
555
556
/* update the indegree */
@@ -521,9 +558,10 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
558
struct commit_list * parents = next->item->parents;
559
while (parents) {
560
struct commit *parent = parents->item;
561
+ int *pi = slab_at(&indegree, parent);
562
525
- if (parent->indegree)
526
- parent->indegree++;
563
+ if (*pi)
564
+ (*pi)++;
565
parents = parents->next;
566
}
567
}
@@ -540,7 +578,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
578
for (next = orig; next; next = next->next) {
579
struct commit *commit = next->item;
580
543
- if (commit->indegree == 1)
581
+ if (*slab_at(&indegree, commit) == 1)
582
insert = &commit_list_insert(commit, insert)->next;
583
}
584
@@ -561,8 +599,9 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
599
commit = work_item->item;
600
for (parents = commit->parents; parents ; parents = parents->next) {
601
struct commit *parent = parents->item;
602
+ int *pi = slab_at(&indegree, parent);
603
565
- if (!parent->indegree)
604
+ if (!*pi)
605
continue;
606
607
/*
@@ -570,7 +609,7 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
609
* when all their children have been emitted thereby
610
* guaranteeing topological order.
611
*/
573
- if (--parent->indegree == 1) {
612
+ if (--(*pi) == 1) {
613
if (!lifo)
614
commit_list_insert_by_date(parent, &work);
615
else
@@ -581,10 +620,12 @@ void sort_in_topological_order(struct commit_list ** list, int lifo)
620
* work_item is a commit all of whose children
621
* have already been emitted. we can emit it now.
622
*/
584
- commit->indegree = 0;
623
+ *slab_at(&indegree, commit) = 0;
624
*pptr = work_item;
625
pptr = &work_item->next;
626
}
627
+
628
+ slab_clear(&indegree);
629
}
630
631
/* merge-base stuff */
commit.h
+1
-1
@@ -14,7 +14,7 @@ struct commit_list {
14
struct commit {
15
struct object object;
16
void *util;
17
- unsigned int indegree;
17
+ unsigned int index;
18
unsigned long date;
19
struct commit_list *parents;
20
struct tree *tree;