git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Phillip Wood via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: "Phillip Wood" <phillip.wood@dunelm.org.uk>,
	"Ævar Arnfjörð Bjarmason" <avarab@gmail.com>,
	"Phillip Wood" <phillip.wood@dunelm.org.uk>,
	"Phillip Wood" <phillip.wood@dunelm.org.uk>
Subject: [PATCH v2 10/12] diff --color-moved-ws=allow-indentation-change: improve hash lookups
Date: Tue, 20 Jul 2021 10:36:31 +0000	[thread overview]
Message-ID: <dd365ad115ffcf3ce5b4b14864ac3ff0ac292214.1626777394.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.981.v2.git.1626777393.gitgitgadget@gmail.com>

From: Phillip Wood <phillip.wood@dunelm.org.uk>

As libxdiff does not have a whitespace flag to ignore the indentation
the code for --color-moved-ws=allow-indentation-change uses
XDF_IGNORE_WHITESPACE and then filters out any hash lookups where
there are non-indentation changes. This filtering is inefficient as
we have to perform another string comparison.

By using the offset data that we have already computed to skip the
indentation we can avoid using XDF_IGNORE_WHITESPACE and safely remove
the extra checks which improves the performance by 11% and paves the
way for the elimination of string comparisons in the next commit.

This change slightly increases the run time of other --color-moved
modes. This could be avoided by using different comparison functions
for the different modes but after the next two commits there is no
measurable benefit in doing so.

Test                                                                  HEAD^             HEAD
--------------------------------------------------------------------------------------------------------------
4002.1: diff --no-color-moved --no-color-moved-ws large change        0.41(0.38+0.03)   0.41(0.36+0.04) +0.0%
4002.2: diff --color-moved --no-color-moved-ws large change           0.82(0.76+0.05)   0.84(0.79+0.04) +2.4%
4002.3: diff --color-moved-ws=allow-indentation-change large change   0.91(0.88+0.03)   0.81(0.74+0.06) -11.0%
4002.4: log --no-color-moved --no-color-moved-ws                      1.32(1.21+0.10)   1.31(1.19+0.11) -0.8%
4002.5: log --color-moved --no-color-moved-ws                         1.47(1.37+0.10)   1.47(1.36+0.11) +0.0%
4002.6: log --color-moved-ws=allow-indentation-change                 1.51(1.42+0.09)   1.48(1.37+0.10) -2.0%

Signed-off-by: Phillip Wood <phillip.wood@dunelm.org.uk>
---
 diff.c | 66 +++++++++++++++++-----------------------------------------
 1 file changed, 19 insertions(+), 47 deletions(-)

diff --git a/diff.c b/diff.c
index 4b5776a5a0a..f899083d028 100644
--- a/diff.c
+++ b/diff.c
@@ -850,28 +850,15 @@ static void fill_es_indent_data(struct emitted_diff_symbol *es)
 }
 
 static int compute_ws_delta(const struct emitted_diff_symbol *a,
-			    const struct emitted_diff_symbol *b,
-			    int *out)
-{
-	int a_len = a->len,
-	    b_len = b->len,
-	    a_off = a->indent_off,
-	    a_width = a->indent_width,
-	    b_off = b->indent_off,
+			    const struct emitted_diff_symbol *b)
+{
+	int a_width = a->indent_width,
 	    b_width = b->indent_width;
 
-	if (a_width == INDENT_BLANKLINE && b_width == INDENT_BLANKLINE) {
-		*out = INDENT_BLANKLINE;
-		return 1;
-	}
-
-	if (a_len - a_off != b_len - b_off ||
-	    memcmp(a->line + a_off, b->line + b_off, a_len - a_off))
-		return 0;
-
-	*out = a_width - b_width;
+	if (a_width == INDENT_BLANKLINE && b_width == INDENT_BLANKLINE)
+		return INDENT_BLANKLINE;
 
-	return 1;
+	return a_width - b_width;
 }
 
 static int cmp_in_block_with_wsd(const struct diff_options *o,
@@ -917,26 +904,17 @@ static int moved_entry_cmp(const void *hashmap_cmp_fn_data,
 			   const void *keydata)
 {
 	const struct diff_options *diffopt = hashmap_cmp_fn_data;
-	const struct moved_entry *a, *b;
+	const struct emitted_diff_symbol *a, *b;
 	unsigned flags = diffopt->color_moved_ws_handling
 			 & XDF_WHITESPACE_FLAGS;
 
-	a = container_of(eptr, const struct moved_entry, ent);
-	b = container_of(entry_or_key, const struct moved_entry, ent);
-
-	if (diffopt->color_moved_ws_handling &
-	    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
-		/*
-		 * As there is not specific white space config given,
-		 * we'd need to check for a new block, so ignore all
-		 * white space. The setup of the white space
-		 * configuration for the next block is done else where
-		 */
-		flags |= XDF_IGNORE_WHITESPACE;
+	a = container_of(eptr, const struct moved_entry, ent)->es;
+	b = container_of(entry_or_key, const struct moved_entry, ent)->es;
 
-	return !xdiff_compare_lines(a->es->line, a->es->len,
-				    b->es->line, b->es->len,
-				    flags);
+	return !xdiff_compare_lines(a->line + a->indent_off,
+				    a->len - a->indent_off,
+				    b->line + b->indent_off,
+				    b->len - b->indent_off, flags);
 }
 
 static struct moved_entry *prepare_entry(struct diff_options *o,
@@ -945,7 +923,8 @@ static struct moved_entry *prepare_entry(struct diff_options *o,
 	struct moved_entry *ret = xmalloc(sizeof(*ret));
 	struct emitted_diff_symbol *l = &o->emitted_symbols->buf[line_no];
 	unsigned flags = o->color_moved_ws_handling & XDF_WHITESPACE_FLAGS;
-	unsigned int hash = xdiff_hash_string(l->line, l->len, flags);
+	unsigned int hash = xdiff_hash_string(l->line + l->indent_off,
+					      l->len - l->indent_off, flags);
 
 	hashmap_entry_init(&ret->ent, hash);
 	ret->es = l;
@@ -1113,14 +1092,11 @@ static void mark_color_as_moved(struct diff_options *o,
 			hashmap_for_each_entry_from(hm, match, ent) {
 				ALLOC_GROW(pmb, pmb_nr + 1, pmb_alloc);
 				if (o->color_moved_ws_handling &
-				    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE) {
-					if (compute_ws_delta(l, match->es,
-							     &pmb[pmb_nr].wsd))
-						pmb[pmb_nr++].match = match;
-				} else {
+				    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
+					pmb[pmb_nr].wsd = compute_ws_delta(l, match->es);
+				else
 					pmb[pmb_nr].wsd = 0;
-					pmb[pmb_nr++].match = match;
-				}
+				pmb[pmb_nr++].match = match;
 			}
 
 			if (adjust_last_block(o, n, block_length) &&
@@ -6240,10 +6216,6 @@ static void diff_flush_patch_all_file_pairs(struct diff_options *o)
 		if (o->color_moved) {
 			struct hashmap add_lines, del_lines;
 
-			if (o->color_moved_ws_handling &
-			    COLOR_MOVED_WS_ALLOW_INDENTATION_CHANGE)
-				o->color_moved_ws_handling |= XDF_IGNORE_WHITESPACE;
-
 			hashmap_init(&del_lines, moved_entry_cmp, o, 0);
 			hashmap_init(&add_lines, moved_entry_cmp, o, 0);
 
-- 
gitgitgadget


  parent reply	other threads:[~2021-07-20 10:42 UTC|newest]

Thread overview: 92+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-14 13:04 [PATCH 00/10] diff --color-moved[-ws] speedups Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 01/10] diff --color-moved=zerba: fix alternate coloring Phillip Wood via GitGitGadget
2021-06-15  3:24   ` Junio C Hamano
2021-06-15 11:22     ` Phillip Wood
2021-06-14 13:04 ` [PATCH 02/10] diff --color-moved: avoid false short line matches and bad zerba coloring Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 03/10] diff: simplify allow-indentation-change delta calculation Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 04/10] diff --color-moved-ws=allow-indentation-change: simplify and optimize Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 05/10] diff --color-moved: call comparison function directly Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 06/10] diff --color-moved: unify moved block growth functions Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 07/10] diff --color-moved: shrink potential moved blocks as we go Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 08/10] diff --color-moved: stop clearing potential moved blocks Phillip Wood via GitGitGadget
2021-06-14 13:04 ` [PATCH 09/10] diff --color-moved-ws=allow-indentation-change: improve hash lookups Phillip Wood via GitGitGadget
2021-07-09 15:36   ` Elijah Newren
2021-06-14 13:04 ` [PATCH 10/10] diff --color-moved: intern strings Phillip Wood via GitGitGadget
2021-06-16 14:24 ` [PATCH 00/10] diff --color-moved[-ws] speedups Ævar Arnfjörð Bjarmason
2021-06-21 10:03   ` Phillip Wood
2021-07-20 10:36 ` [PATCH v2 00/12] " Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 01/12] diff --color-moved: add perf tests Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 02/12] diff --color-moved=zebra: fix alternate coloring Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 03/12] diff --color-moved: avoid false short line matches and bad zerba coloring Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 04/12] diff: simplify allow-indentation-change delta calculation Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 05/12] diff --color-moved-ws=allow-indentation-change: simplify and optimize Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 06/12] diff --color-moved: call comparison function directly Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 07/12] diff --color-moved: unify moved block growth functions Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 08/12] diff --color-moved: shrink potential moved blocks as we go Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 09/12] diff --color-moved: stop clearing potential moved blocks Phillip Wood via GitGitGadget
2021-07-20 10:36   ` Phillip Wood via GitGitGadget [this message]
2021-07-20 10:36   ` [PATCH v2 11/12] diff: use designated initializers for emitted_diff_symbol Phillip Wood via GitGitGadget
2021-07-20 10:36   ` [PATCH v2 12/12] diff --color-moved: intern strings Phillip Wood via GitGitGadget
2021-07-20 13:38   ` [PATCH v2 00/12] diff --color-moved[-ws] speedups Phillip Wood
2021-10-27 12:04   ` [PATCH v3 00/15] " Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 01/15] diff --color-moved: add perf tests Phillip Wood via GitGitGadget
2021-10-28 21:32       ` Junio C Hamano
2021-10-29 10:24         ` Phillip Wood
2021-10-29 11:06           ` Ævar Arnfjörð Bjarmason
2021-11-10 11:05             ` Phillip Wood
2021-10-27 12:04     ` [PATCH v3 02/15] diff --color-moved: clear all flags on blocks that are too short Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 03/15] diff --color-moved: factor out function Phillip Wood via GitGitGadget
2021-10-28 21:51       ` Junio C Hamano
2021-10-29 10:35         ` Phillip Wood
2021-10-27 12:04     ` [PATCH v3 04/15] diff --color-moved: rewind when discarding pmb Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 05/15] diff --color-moved=zebra: fix alternate coloring Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 06/15] diff --color-moved: avoid false short line matches and bad zerba coloring Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 07/15] diff: simplify allow-indentation-change delta calculation Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 08/15] diff --color-moved-ws=allow-indentation-change: simplify and optimize Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 09/15] diff --color-moved: call comparison function directly Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 10/15] diff --color-moved: unify moved block growth functions Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 11/15] diff --color-moved: shrink potential moved blocks as we go Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 12/15] diff --color-moved: stop clearing potential moved blocks Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 13/15] diff --color-moved-ws=allow-indentation-change: improve hash lookups Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 14/15] diff: use designated initializers for emitted_diff_symbol Phillip Wood via GitGitGadget
2021-10-27 12:04     ` [PATCH v3 15/15] diff --color-moved: intern strings Phillip Wood via GitGitGadget
2021-10-27 13:28     ` [PATCH v3 00/15] diff --color-moved[-ws] speedups Phillip Wood
2021-11-16  9:49     ` [PATCH v4 " Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 01/15] diff --color-moved: add perf tests Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 02/15] diff --color-moved: clear all flags on blocks that are too short Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 03/15] diff --color-moved: factor out function Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 04/15] diff --color-moved: rewind when discarding pmb Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 05/15] diff --color-moved=zebra: fix alternate coloring Phillip Wood via GitGitGadget
2021-11-22 13:34         ` Johannes Schindelin
2021-11-16  9:49       ` [PATCH v4 06/15] diff --color-moved: avoid false short line matches and bad zerba coloring Phillip Wood via GitGitGadget
2021-11-22 14:18         ` Johannes Schindelin
2021-11-22 19:00           ` Phillip Wood
2021-11-22 21:54             ` Johannes Schindelin
2021-11-16  9:49       ` [PATCH v4 07/15] diff: simplify allow-indentation-change delta calculation Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 08/15] diff --color-moved-ws=allow-indentation-change: simplify and optimize Phillip Wood via GitGitGadget
2021-11-23 14:51         ` Johannes Schindelin
2021-11-16  9:49       ` [PATCH v4 09/15] diff --color-moved: call comparison function directly Phillip Wood via GitGitGadget
2021-11-23 15:09         ` Johannes Schindelin
2021-11-16  9:49       ` [PATCH v4 10/15] diff --color-moved: unify moved block growth functions Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 11/15] diff --color-moved: shrink potential moved blocks as we go Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 12/15] diff --color-moved: stop clearing potential moved blocks Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 13/15] diff --color-moved-ws=allow-indentation-change: improve hash lookups Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 14/15] diff: use designated initializers for emitted_diff_symbol Phillip Wood via GitGitGadget
2021-11-16  9:49       ` [PATCH v4 15/15] diff --color-moved: intern strings Phillip Wood via GitGitGadget
2021-12-08 12:30       ` [PATCH v4 00/15] diff --color-moved[-ws] speedups Johannes Schindelin
2021-12-09 10:29       ` [PATCH v5 " Phillip Wood via GitGitGadget
2021-12-09 10:29         ` [PATCH v5 01/15] diff --color-moved: add perf tests Phillip Wood via GitGitGadget
2021-12-09 10:29         ` [PATCH v5 02/15] diff --color-moved: clear all flags on blocks that are too short Phillip Wood via GitGitGadget
2021-12-09 10:29         ` [PATCH v5 03/15] diff --color-moved: factor out function Phillip Wood via GitGitGadget
2021-12-09 10:29         ` [PATCH v5 04/15] diff --color-moved: rewind when discarding pmb Phillip Wood via GitGitGadget
2021-12-09 10:29         ` [PATCH v5 05/15] diff --color-moved=zebra: fix alternate coloring Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 06/15] diff --color-moved: avoid false short line matches and bad zebra coloring Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 07/15] diff: simplify allow-indentation-change delta calculation Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 08/15] diff --color-moved-ws=allow-indentation-change: simplify and optimize Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 09/15] diff --color-moved: call comparison function directly Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 10/15] diff --color-moved: unify moved block growth functions Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 11/15] diff --color-moved: shrink potential moved blocks as we go Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 12/15] diff --color-moved: stop clearing potential moved blocks Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 13/15] diff --color-moved-ws=allow-indentation-change: improve hash lookups Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 14/15] diff: use designated initializers for emitted_diff_symbol Phillip Wood via GitGitGadget
2021-12-09 10:30         ` [PATCH v5 15/15] diff --color-moved: intern strings Phillip Wood via GitGitGadget

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=dd365ad115ffcf3ce5b4b14864ac3ff0ac292214.1626777394.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=avarab@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=phillip.wood@dunelm.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).