git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v5 6/6] merge-ort: call diffcore_rename() directly

From
Elijah Newren via GitGitGadget <gitgitgadget@gmail.com>
Date
Feb 14, 2021, 07:51 UTC
Message-ID
<aeca14f748afc7fb5b65bca56ea2ebd970729814.1613289112.git.gitgitgadget@gmail.com>
In-Reply-To
<pull.843.v5.git.1613289112.gitgitgadget@gmail.com>
From: Elijah Newren <newren@gmail.com>

We want to pass additional information to diffcore_rename() (or some variant thereof) without plumbing that extra information through diff_tree_oid() and diffcore_std(). Further, since we will need to gather additional special information related to diffs and are walking the trees anyway in collect_merge_info(), it seems odd to have diff_tree_oid()/diffcore_std() repeat those tree walks. And there may be times where we can avoid traversing into a subtree in collect_merge_info() (based on additional information at our disposal), that the basic diff logic would be unable to take advantage of. For all these reasons, just create the add and delete pairs ourself and then call diffcore_rename() directly.

This change is primarily about enabling future optimizations; the advantage of avoiding extra tree traversals is small compared to the cost of rename detection, and the advantage of avoiding the extra tree traversals is somewhat offset by the extra time spent in collect_merge_info() collecting the additional data anyway. However...

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:       13.294 s ±  0.103 s    12.775 s ±  0.062 s
    mega-renames:    187.248 s ±  0.882 s   188.754 s ±  0.284 s
    just-one-mega:     5.557 s ±  0.017 s     5.599 s ±  0.019 s
Signed-off-by: Elijah Newren <newren@gmail.com>
---
 merge-ort.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 59 insertions(+), 7 deletions(-)
diff --git a/merge-ort.c b/merge-ort.c
index 931b91438cf1..603d30c52170 100644
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -535,6 +535,23 @@ static void setup_path_info(struct merge_options *opt,
 	result->util = mi;
 }
 
+static void add_pair(struct merge_options *opt,
+		     struct name_entry *names,
+		     const char *pathname,
+		     unsigned side,
+		     unsigned is_add /* if false, is_delete */)
+{
+	struct diff_filespec *one, *two;
+	struct rename_info *renames = &opt->priv->renames;
+	int names_idx = is_add ? side : 0;
+
+	one = alloc_filespec(pathname);
+	two = alloc_filespec(pathname);
+	fill_filespec(is_add ? two : one,
+		      &names[names_idx].oid, 1, names[names_idx].mode);
+	diff_queue(&renames->pairs[side], one, two);
+}
+
 static void collect_rename_info(struct merge_options *opt,
 				struct name_entry *names,
 				const char *dirname,
@@ -544,6 +561,7 @@ static void collect_rename_info(struct merge_options *opt,
 				unsigned match_mask)
 {
 	struct rename_info *renames = &opt->priv->renames;
+	unsigned side;
 
 	/* Update dirs_removed, as needed */
 	if (dirmask == 1 || dirmask == 3 || dirmask == 5) {
@@ -554,6 +572,21 @@ static void collect_rename_info(struct merge_options *opt,
 		if (sides & 2)
 			strset_add(&renames->dirs_removed[2], fullname);
 	}
+
+	if (filemask == 0 || filemask == 7)
+		return;
+
+	for (side = MERGE_SIDE1; side <= MERGE_SIDE2; ++side) {
+		unsigned side_mask = (1 << side);
+
+		/* Check for deletion on side */
+		if ((filemask & 1) && !(filemask & side_mask))
+			add_pair(opt, names, fullname, side, 0 /* delete */);
+
+		/* Check for addition on side */
+		if (!(filemask & 1) && (filemask & side_mask))
+			add_pair(opt, names, fullname, side, 1 /* add */);
+	}
 }
 
 static int collect_merge_info_callback(int n,
@@ -2079,6 +2112,27 @@ static int process_renames(struct merge_options *opt,
 	return clean_merge;
 }
 
+static void resolve_diffpair_statuses(struct diff_queue_struct *q)
+{
+	/*
+	 * A simplified version of diff_resolve_rename_copy(); would probably
+	 * just use that function but it's static...
+	 */
+	int i;
+	struct diff_filepair *p;
+
+	for (i = 0; i < q->nr; ++i) {
+		p = q->queue[i];
+		p->status = 0; /* undecided */
+		if (!DIFF_FILE_VALID(p->one))
+			p->status = DIFF_STATUS_ADDED;
+		else if (!DIFF_FILE_VALID(p->two))
+			p->status = DIFF_STATUS_DELETED;
+		else if (DIFF_PAIR_RENAME(p))
+			p->status = DIFF_STATUS_RENAMED;
+	}
+}
+
 static int compare_pairs(const void *a_, const void *b_)
 {
 	const struct diff_filepair *a = *((const struct diff_filepair **)a_);
@@ -2089,8 +2143,6 @@ static int compare_pairs(const void *a_, const void *b_)
 
 /* Call diffcore_rename() to compute which files have changed on given side */
 static void detect_regular_renames(struct merge_options *opt,
-				   struct tree *merge_base,
-				   struct tree *side,
 				   unsigned side_index)
 {
 	struct diff_options diff_opts;
@@ -2108,11 +2160,11 @@ static void detect_regular_renames(struct merge_options *opt,
 	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
 	diff_setup_done(&diff_opts);
 
+	diff_queued_diff = renames->pairs[side_index];
 	trace2_region_enter("diff", "diffcore_rename", opt->repo);
-	diff_tree_oid(&merge_base->object.oid, &side->object.oid, "",
-		      &diff_opts);
-	diffcore_std(&diff_opts);
+	diffcore_rename(&diff_opts);
 	trace2_region_leave("diff", "diffcore_rename", opt->repo);
+	resolve_diffpair_statuses(&diff_queued_diff);
 
 	if (diff_opts.needed_rename_limit > renames->needed_limit)
 		renames->needed_limit = diff_opts.needed_rename_limit;
@@ -2212,8 +2264,8 @@ static int detect_and_process_renames(struct merge_options *opt,
 	memset(&combined, 0, sizeof(combined));
 
 	trace2_region_enter("merge", "regular renames", opt->repo);
-	detect_regular_renames(opt, merge_base, side1, MERGE_SIDE1);
-	detect_regular_renames(opt, merge_base, side2, MERGE_SIDE2);
+	detect_regular_renames(opt, MERGE_SIDE1);
+	detect_regular_renames(opt, MERGE_SIDE2);
 	trace2_region_leave("merge", "regular renames", opt->repo);
 
 	trace2_region_enter("merge", "directory renames", opt->repo);
-- 
gitgitgadget
Previous: Elijah Newren via GitGitGadget
Message 71 of 71 in “Optimization batch 7: use file basenames to guide rename detection”
  1. 0/3 Optimization batch 7: use file basenames to guide rename detectionElijah Newren via GitGitGadget, Feb 6, 2021
  2. 1/3 diffcore-rename: compute basenames of all source and dest candidatesElijah Newren via GitGitGadget, Feb 6, 2021
  3. 2/3 diffcore-rename: complete find_basename_matches()Elijah Newren via GitGitGadget, Feb 6, 2021
  4. 3/3 diffcore-rename: guide inexact rename detection based on basenamesElijah Newren via GitGitGadget, Feb 6, 2021
  5. Derrick StoleeFeb 7, 2021
  6. Junio C HamanoFeb 7, 2021
  7. Elijah NewrenFeb 8, 2021
  8. Derrick StoleeFeb 8, 2021
  9. Elijah NewrenFeb 8, 2021
  10. Junio C HamanoFeb 8, 2021
  11. Elijah NewrenFeb 8, 2021
  12. Junio C HamanoFeb 8, 2021
  13. Elijah NewrenFeb 8, 2021
  14. Elijah NewrenFeb 8, 2021
  15. Derrick StoleeFeb 8, 2021
  16. Elijah NewrenFeb 8, 2021
  17. Junio C HamanoFeb 7, 2021
  18. Elijah NewrenFeb 7, 2021
  19. 0/4 Optimization batch 7: use file basenames to guide rename detectionElijah Newren via GitGitGadget, Feb 9, 2021
  20. 2/4 diffcore-rename: complete find_basename_matches()Elijah Newren via GitGitGadget, Feb 9, 2021
  21. Derrick StoleeFeb 9, 2021
  22. Elijah NewrenFeb 9, 2021
  23. Derrick StoleeFeb 9, 2021
  24. 3/4 diffcore-rename: guide inexact rename detection based on basenamesElijah Newren via GitGitGadget, Feb 9, 2021
  25. Derrick StoleeFeb 9, 2021
  26. Elijah NewrenFeb 9, 2021
  27. Junio C HamanoFeb 9, 2021
  28. 1/4 diffcore-rename: compute basenames of all source and dest candidatesElijah Newren via GitGitGadget, Feb 9, 2021
  29. Derrick StoleeFeb 9, 2021
  30. Elijah NewrenFeb 9, 2021
  31. Derrick StoleeFeb 9, 2021
  32. Elijah NewrenFeb 9, 2021
  33. 4/4 gitdiffcore doc: mention new preliminary step for rename detectionElijah Newren via GitGitGadget, Feb 9, 2021
  34. Derrick StoleeFeb 9, 2021
  35. Junio C HamanoFeb 9, 2021
  36. Elijah NewrenFeb 9, 2021
  37. 0/5 Optimization batch 7: use file basenames to guide rename detectionElijah Newren via GitGitGadget, Feb 10, 2021
  38. 1/5 t4001: add a test comparing basename similarity and content similarityElijah Newren via GitGitGadget, Feb 10, 2021
  39. Junio C HamanoFeb 13, 2021
  40. Elijah NewrenFeb 13, 2021
  41. Junio C HamanoFeb 13, 2021
  42. Elijah NewrenFeb 14, 2021
  43. Junio C HamanoFeb 14, 2021
  44. Elijah NewrenFeb 14, 2021
  45. 2/5 diffcore-rename: compute basenames of all source and dest candidatesElijah Newren via GitGitGadget, Feb 10, 2021
  46. Junio C HamanoFeb 13, 2021
  47. 4/5 diffcore-rename: guide inexact rename detection based on basenamesElijah Newren via GitGitGadget, Feb 10, 2021
  48. Junio C HamanoFeb 13, 2021
  49. 3/5 diffcore-rename: complete find_basename_matches()Elijah Newren via GitGitGadget, Feb 10, 2021
  50. Junio C HamanoFeb 13, 2021
  51. Elijah NewrenFeb 13, 2021
  52. Junio C HamanoFeb 13, 2021
  53. Elijah NewrenFeb 14, 2021
  54. 5/5 gitdiffcore doc: mention new preliminary step for rename detectionElijah Newren via GitGitGadget, Feb 10, 2021
  55. Junio C HamanoFeb 10, 2021
  56. Elijah NewrenFeb 10, 2021
  57. 0/6 Optimization batch 7: use file basenames to guide rename detectionElijah Newren via GitGitGadget, Feb 11, 2021
  58. 1/6 t4001: add a test comparing basename similarity and content similarityElijah Newren via GitGitGadget, Feb 11, 2021
  59. 2/6 diffcore-rename: compute basenames of all source and dest candidatesElijah Newren via GitGitGadget, Feb 11, 2021
  60. 3/6 diffcore-rename: complete find_basename_matches()Elijah Newren via GitGitGadget, Feb 11, 2021
  61. 5/6 gitdiffcore doc: mention new preliminary step for rename detectionElijah Newren via GitGitGadget, Feb 11, 2021
  62. 4/6 diffcore-rename: guide inexact rename detection based on basenamesElijah Newren via GitGitGadget, Feb 11, 2021
  63. 6/6 merge-ort: call diffcore_rename() directlyElijah Newren via GitGitGadget, Feb 11, 2021
  64. Junio C HamanoFeb 13, 2021
  65. 0/6 Optimization batch 7: use file basenames to guide rename detectionElijah Newren via GitGitGadget, Feb 14, 2021
  66. 3/6 diffcore-rename: complete find_basename_matches()Elijah Newren via GitGitGadget, Feb 14, 2021
  67. 5/6 gitdiffcore doc: mention new preliminary step for rename detectionElijah Newren via GitGitGadget, Feb 14, 2021
  68. 1/6 t4001: add a test comparing basename similarity and content similarityElijah Newren via GitGitGadget, Feb 14, 2021
  69. 2/6 diffcore-rename: compute basenames of source and dest candidatesElijah Newren via GitGitGadget, Feb 14, 2021
  70. 4/6 diffcore-rename: guide inexact rename detection based on basenamesElijah Newren via GitGitGadget, Feb 14, 2021
  71. 6/6 merge-ort: call diffcore_rename() directlyElijah Newren via GitGitGadget, Feb 14, 2021

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.