pseudo-merge: implement support for reading pseudo-merge commits
Implement the basic API for reading pseudo-merge bitmaps, which consists of four basic functions: - pseudo_merge_bitmap() - use_pseudo_merge() - apply_pseudo_merges_for_commit() - cascade_pseudo_merges() These functions are all documented in pseudo-merge.h, but their rough descriptions are as follows: - pseudo_merge_bitmap() reads and inflates the objects EWAH bitmap for a given pseudo-merge - use_pseudo_merge() does the same as pseudo_merge_bitmap(), but on the commits EWAH bitmap, not the objects bitmap - apply_pseudo_merges_for_commit() applies all satisfied pseudo-merge commits for a given result set, and cascades any yet-unsatisfied pseudo-merges if any were applied in the previous step - cascade_pseudo_merges() applies all pseudo-merges which are satisfied but have not been previously applied, repeating this process until no more pseudo-merges can be applied The core of the API is the latter two functions, which are responsible for applying pseudo-merges during the object traversal implemented in the pack-bitmap machinery. The other two functions (pseudo_merge_bitmap(), and use_pseudo_merge()) are low-level ways to interact with the pseudo-merge machinery, which will be useful in future commits. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Taylor Blau committed
May 23, 2024 at 17:26 UTC
955747b4daaac33a11b1f5362227f1839cff41d3
2 files changed
+279
pseudo-merge.c
+235
@@ -10,6 +10,7 @@
10
#include "commit.h"
11
#include "alloc.h"
12
#include "progress.h"
13
+#include "hex.h"
14
15
#define DEFAULT_PSEUDO_MERGE_DECAY 1.0
16
#define DEFAULT_PSEUDO_MERGE_MAX_MERGES 64
@@ -464,3 +465,237 @@ void free_pseudo_merge_map(struct pseudo_merge_map *pm)
465
}
466
free(pm->v);
467
}
468
+
469
+struct pseudo_merge_commit_ext {
470
+ uint32_t nr;
471
+ const unsigned char *ptr;
472
+};
473
+
474
+static int pseudo_merge_ext_at(const struct pseudo_merge_map *pm,
475
+ struct pseudo_merge_commit_ext *ext, size_t at)
476
+{
477
+ if (at >= pm->map_size)
478
+ return error(_("extended pseudo-merge read out-of-bounds "
479
+ "(%"PRIuMAX" >= %"PRIuMAX")"),
480
+ (uintmax_t)at, (uintmax_t)pm->map_size);
481
+ if (at + 4 >= pm->map_size)
482
+ return error(_("extended pseudo-merge entry is too short "
483
+ "(%"PRIuMAX" >= %"PRIuMAX")"),
484
+ (uintmax_t)(at + 4), (uintmax_t)pm->map_size);
485
+
486
+ ext->nr = get_be32(pm->map + at);
487
+ ext->ptr = pm->map + at + sizeof(uint32_t);
488
+
489
+ return 0;
490
+}
491
+
492
+struct ewah_bitmap *pseudo_merge_bitmap(const struct pseudo_merge_map *pm,
493
+ struct pseudo_merge *merge)
494
+{
495
+ if (!merge->loaded_commits)
496
+ BUG("cannot use unloaded pseudo-merge bitmap");
497
+
498
+ if (!merge->loaded_bitmap) {
499
+ size_t at = merge->bitmap_at;
500
+
501
+ merge->bitmap = read_bitmap(pm->map, pm->map_size, &at);
502
+ merge->loaded_bitmap = 1;
503
+ }
504
+
505
+ return merge->bitmap;
506
+}
507
+
508
+struct pseudo_merge *use_pseudo_merge(const struct pseudo_merge_map *pm,
509
+ struct pseudo_merge *merge)
510
+{
511
+ if (!merge->loaded_commits) {
512
+ size_t pos = merge->at;
513
+
514
+ merge->commits = read_bitmap(pm->map, pm->map_size, &pos);
515
+ merge->bitmap_at = pos;
516
+ merge->loaded_commits = 1;
517
+ }
518
+ return merge;
519
+}
520
+
521
+static struct pseudo_merge *pseudo_merge_at(const struct pseudo_merge_map *pm,
522
+ struct object_id *oid,
523
+ size_t want)
524
+{
525
+ size_t lo = 0;
526
+ size_t hi = pm->nr;
527
+
528
+ while (lo < hi) {
529
+ size_t mi = lo + (hi - lo) / 2;
530
+ size_t got = pm->v[mi].at;
531
+
532
+ if (got == want)
533
+ return use_pseudo_merge(pm, &pm->v[mi]);
534
+ else if (got < want)
535
+ hi = mi;
536
+ else
537
+ lo = mi + 1;
538
+ }
539
+
540
+ warning(_("could not find pseudo-merge for commit %s at offset %"PRIuMAX),
541
+ oid_to_hex(oid), (uintmax_t)want);
542
+
543
+ return NULL;
544
+}
545
+
546
+struct pseudo_merge_commit {
547
+ uint32_t commit_pos;
548
+ uint64_t pseudo_merge_ofs;
549
+};
550
+
551
+#define PSEUDO_MERGE_COMMIT_RAWSZ (sizeof(uint32_t)+sizeof(uint64_t))
552
+
553
+static void read_pseudo_merge_commit_at(struct pseudo_merge_commit *merge,
554
+ const unsigned char *at)
555
+{
556
+ merge->commit_pos = get_be32(at);
557
+ merge->pseudo_merge_ofs = get_be64(at + sizeof(uint32_t));
558
+}
559
+
560
+static int nth_pseudo_merge_ext(const struct pseudo_merge_map *pm,
561
+ struct pseudo_merge_commit_ext *ext,
562
+ struct pseudo_merge_commit *merge,
563
+ uint32_t n)
564
+{
565
+ size_t ofs;
566
+
567
+ if (n >= ext->nr)
568
+ return error(_("extended pseudo-merge lookup out-of-bounds "
569
+ "(%"PRIu32" >= %"PRIu32")"), n, ext->nr);
570
+
571
+ ofs = get_be64(ext->ptr + st_mult(n, sizeof(uint64_t)));
572
+ if (ofs >= pm->map_size)
573
+ return error(_("out-of-bounds read: (%"PRIuMAX" >= %"PRIuMAX")"),
574
+ (uintmax_t)ofs, (uintmax_t)pm->map_size);
575
+
576
+ read_pseudo_merge_commit_at(merge, pm->map + ofs);
577
+
578
+ return 0;
579
+}
580
+
581
+static unsigned apply_pseudo_merge(const struct pseudo_merge_map *pm,
582
+ struct pseudo_merge *merge,
583
+ struct bitmap *result,
584
+ struct bitmap *roots)
585
+{
586
+ if (merge->satisfied)
587
+ return 0;
588
+
589
+ if (!ewah_bitmap_is_subset(merge->commits, roots ? roots : result))
590
+ return 0;
591
+
592
+ bitmap_or_ewah(result, pseudo_merge_bitmap(pm, merge));
593
+ if (roots)
594
+ bitmap_or_ewah(roots, pseudo_merge_bitmap(pm, merge));
595
+ merge->satisfied = 1;
596
+
597
+ return 1;
598
+}
599
+
600
+static int pseudo_merge_commit_cmp(const void *va, const void *vb)
601
+{
602
+ struct pseudo_merge_commit merge;
603
+ uint32_t key = *(uint32_t*)va;
604
+
605
+ read_pseudo_merge_commit_at(&merge, vb);
606
+
607
+ if (key < merge.commit_pos)
608
+ return -1;
609
+ if (key > merge.commit_pos)
610
+ return 1;
611
+ return 0;
612
+}
613
+
614
+static struct pseudo_merge_commit *find_pseudo_merge(const struct pseudo_merge_map *pm,
615
+ uint32_t pos)
616
+{
617
+ if (!pm->commits_nr)
618
+ return NULL;
619
+
620
+ return bsearch(&pos, pm->commits, pm->commits_nr,
621
+ PSEUDO_MERGE_COMMIT_RAWSZ, pseudo_merge_commit_cmp);
622
+}
623
+
624
+int apply_pseudo_merges_for_commit(const struct pseudo_merge_map *pm,
625
+ struct bitmap *result,
626
+ struct commit *commit, uint32_t commit_pos)
627
+{
628
+ struct pseudo_merge *merge;
629
+ struct pseudo_merge_commit *merge_commit;
630
+ int ret = 0;
631
+
632
+ merge_commit = find_pseudo_merge(pm, commit_pos);
633
+ if (!merge_commit)
634
+ return 0;
635
+
636
+ if (merge_commit->pseudo_merge_ofs & ((uint64_t)1<<63)) {
637
+ struct pseudo_merge_commit_ext ext = { 0 };
638
+ off_t ofs = merge_commit->pseudo_merge_ofs & ~((uint64_t)1<<63);
639
+ uint32_t i;
640
+
641
+ if (pseudo_merge_ext_at(pm, &ext, ofs) < -1) {
642
+ warning(_("could not read extended pseudo-merge table "
643
+ "for commit %s"),
644
+ oid_to_hex(&commit->object.oid));
645
+ return ret;
646
+ }
647
+
648
+ for (i = 0; i < ext.nr; i++) {
649
+ if (nth_pseudo_merge_ext(pm, &ext, merge_commit, i) < 0)
650
+ return ret;
651
+
652
+ merge = pseudo_merge_at(pm, &commit->object.oid,
653
+ merge_commit->pseudo_merge_ofs);
654
+
655
+ if (!merge)
656
+ return ret;
657
+
658
+ if (apply_pseudo_merge(pm, merge, result, NULL))
659
+ ret++;
660
+ }
661
+ } else {
662
+ merge = pseudo_merge_at(pm, &commit->object.oid,
663
+ merge_commit->pseudo_merge_ofs);
664
+
665
+ if (!merge)
666
+ return ret;
667
+
668
+ if (apply_pseudo_merge(pm, merge, result, NULL))
669
+ ret++;
670
+ }
671
+
672
+ if (ret)
673
+ cascade_pseudo_merges(pm, result, NULL);
674
+
675
+ return ret;
676
+}
677
+
678
+int cascade_pseudo_merges(const struct pseudo_merge_map *pm,
679
+ struct bitmap *result,
680
+ struct bitmap *roots)
681
+{
682
+ unsigned any_satisfied;
683
+ int ret = 0;
684
+
685
+ do {
686
+ struct pseudo_merge *merge;
687
+ uint32_t i;
688
+
689
+ any_satisfied = 0;
690
+
691
+ for (i = 0; i < pm->nr; i++) {
692
+ merge = use_pseudo_merge(pm, &pm->v[i]);
693
+ if (apply_pseudo_merge(pm, merge, result, roots)) {
694
+ any_satisfied |= 1;
695
+ ret++;
696
+ }
697
+ }
698
+ } while (any_satisfied);
699
+
700
+ return ret;
701
+}
pseudo-merge.h
+44
@@ -162,4 +162,48 @@ struct pseudo_merge {
162
*/
163
void free_pseudo_merge_map(struct pseudo_merge_map *pm);
164
165
+/*
166
+ * Loads the bitmap corresponding to the given pseudo-merge from the
167
+ * map, if it has not already been loaded.
168
+ */
169
+struct ewah_bitmap *pseudo_merge_bitmap(const struct pseudo_merge_map *pm,
170
+ struct pseudo_merge *merge);
171
+
172
+/*
173
+ * Loads the pseudo-merge and its commits bitmap from the given
174
+ * pseudo-merge map, if it has not already been loaded.
175
+ */
176
+struct pseudo_merge *use_pseudo_merge(const struct pseudo_merge_map *pm,
177
+ struct pseudo_merge *merge);
178
+
179
+/*
180
+ * Applies pseudo-merge(s) containing the given commit to the bitmap
181
+ * "result".
182
+ *
183
+ * If any pseudo-merge(s) were satisfied, returns the number
184
+ * satisfied, otherwise returns 0. If any were satisfied, the
185
+ * remaining unsatisfied pseudo-merges are cascaded (see below).
186
+ */
187
+int apply_pseudo_merges_for_commit(const struct pseudo_merge_map *pm,
188
+ struct bitmap *result,
189
+ struct commit *commit, uint32_t commit_pos);
190
+
191
+/*
192
+ * Applies pseudo-merge(s) which are satisfied according to the
193
+ * current bitmap in result (or roots, see below). If any
194
+ * pseudo-merges were satisfied, repeat the process over unsatisfied
195
+ * pseudo-merge commits until no more pseudo-merges are satisfied.
196
+ *
197
+ * Result is the bitmap to which the pseudo-merge(s) are applied.
198
+ * Roots (if given) is a bitmap of the traversal tip(s) for either
199
+ * side of a reachability traversal.
200
+ *
201
+ * Roots may given instead of a populated results bitmap at the
202
+ * beginning of a traversal on either side where the reachability
203
+ * closure over tips is not yet known.
204
+ */
205
+int cascade_pseudo_merges(const struct pseudo_merge_map *pm,
206
+ struct bitmap *result,
207
+ struct bitmap *roots);
208
+
209
#endif