git diff too slow for a file

René Scharfe · gitster · commit 582aa00bdffb · 2010-05-02T07:59:50.000-07:00
Ever since the xdiff library had been introduced to git, all its callers
have used the flag XDF_NEED_MINIMAL.  It makes sure that the smallest
possible diff is produced, but that takes quite some time if there are
lots of differences that can be expressed in multiple ways.

This flag makes a difference for only 0.1% of the non-merge commits in
the git repo of Linux, both in terms of diff size and execution time.
The patches there are mostly nice and small.

SungHyun Nam however reported a case in a different repo where a diff
took more than 20 times longer to generate with XDF_NEED_MINIMAL than
without.  Rebasing became really slow.

This patch removes this flag from all callers.  The default of xdiff is
saner because it has minimal to no impact in the normal case of small
diffs and doesn't incur that much of a speed penalty for large ones.

A follow-up patch may introduce a command line option to set the flag if
the user needs it, similar to GNU diff's -d/--minimal.

Signed-off-by: Rene Scharfe &lt;rene.scharfe@lsrfire.ath.cx&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/builtin-blame.c b/builtin-blame.c
@@ -39,7 +39,7 @@ static int show_root;
 static int reverse;
 static int blank_boundary;
 static int incremental;
-static int xdl_opts = XDF_NEED_MINIMAL;
+static int xdl_opts;
 
 static enum date_mode blame_date_mode = DATE_ISO8601;
 static size_t blame_date_width;
diff --git a/builtin-merge-file.c b/builtin-merge-file.c
@@ -25,7 +25,7 @@ int cmd_merge_file(int argc, const char **argv, const char *prefix)
 	const char *names[3] = { NULL, NULL, NULL };
 	mmfile_t mmfs[3];
 	mmbuffer_t result = {NULL, 0};
-	xmparam_t xmp = {{XDF_NEED_MINIMAL}};
+	xmparam_t xmp = {{0}};
 	int ret = 0, i = 0, to_stdout = 0;
 	int level = XDL_MERGE_ZEALOUS_ALNUM;
 	int style = 0, quiet = 0;
diff --git a/builtin-merge-tree.c b/builtin-merge-tree.c
@@ -106,7 +106,7 @@ static void show_diff(struct merge_list *entry)
 	xdemitconf_t xecfg;
 	xdemitcb_t ecb;
 
-	xpp.flags = XDF_NEED_MINIMAL;
+	xpp.flags = 0;
 	memset(&xecfg, 0, sizeof(xecfg));
 	xecfg.ctxlen = 3;
 	ecb.outf = show_outf;
diff --git a/builtin-rerere.c b/builtin-rerere.c
@@ -89,7 +89,7 @@ static int diff_two(const char *file1, const char *label1,
 	printf("--- a/%s\n+++ b/%s\n", label1, label2);
 	fflush(stdout);
 	memset(&xpp, 0, sizeof(xpp));
-	xpp.flags = XDF_NEED_MINIMAL;
+	xpp.flags = 0;
 	memset(&xecfg, 0, sizeof(xecfg));
 	xecfg.ctxlen = 3;
 	ecb.outf = outf;
diff --git a/combine-diff.c b/combine-diff.c
@@ -221,7 +221,7 @@ static void combine_diff(const unsigned char *parent, unsigned int mode,
 	parent_file.ptr = grab_blob(parent, mode, &sz);
 	parent_file.size = sz;
 	memset(&xpp, 0, sizeof(xpp));
-	xpp.flags = XDF_NEED_MINIMAL;
+	xpp.flags = 0;
 	memset(&xecfg, 0, sizeof(xecfg));
 	memset(&state, 0, sizeof(state));
 	state.nmask = nmask;
diff --git a/diff.c b/diff.c
@@ -714,7 +714,7 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	memset(&xecfg, 0, sizeof(xecfg));
 	diff_words_fill(&diff_words->minus, &minus, diff_words->word_regex);
 	diff_words_fill(&diff_words->plus, &plus, diff_words->word_regex);
-	xpp.flags = XDF_NEED_MINIMAL;
+	xpp.flags = 0;
 	/* as only the hunk header will be parsed, we need a 0-context */
 	xecfg.ctxlen = 0;
 	xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
@@ -1743,7 +1743,7 @@ static void builtin_diff(const char *name_a,
 			check_blank_at_eof(&mf1, &mf2, &ecbdata);
 		ecbdata.file = o->file;
 		ecbdata.header = header.len ? &header : NULL;
-		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
+		xpp.flags = o->xdl_opts;
 		xecfg.ctxlen = o->context;
 		xecfg.interhunkctxlen = o->interhunkcontext;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
@@ -1833,7 +1833,7 @@ static void builtin_diffstat(const char *name_a, const char *name_b,
 
 		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
-		xpp.flags = XDF_NEED_MINIMAL | o->xdl_opts;
+		xpp.flags = o->xdl_opts;
 		xdi_diff_outf(&mf1, &mf2, diffstat_consume, diffstat,
 			      &xpp, &xecfg, &ecb);
 	}
@@ -1882,7 +1882,7 @@ static void builtin_checkdiff(const char *name_a, const char *name_b,
 		memset(&xpp, 0, sizeof(xpp));
 		memset(&xecfg, 0, sizeof(xecfg));
 		xecfg.ctxlen = 1; /* at least one context line */
-		xpp.flags = XDF_NEED_MINIMAL;
+		xpp.flags = 0;
 		xdi_diff_outf(&mf1, &mf2, checkdiff_consume, &data,
 			      &xpp, &xecfg, &ecb);
 
@@ -3419,7 +3419,7 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 					len2, p->two->path);
 		git_SHA1_Update(&ctx, buffer, len1);
 
-		xpp.flags = XDF_NEED_MINIMAL;
+		xpp.flags = 0;
 		xecfg.ctxlen = 3;
 		xecfg.flags = XDL_EMIT_FUNCNAMES;
 		xdi_diff_outf(&mf1, &mf2, patch_id_consume, &data,
diff --git a/merge-file.c b/merge-file.c
@@ -60,7 +60,7 @@ static int generate_common_file(mmfile_t *res, mmfile_t *f1, mmfile_t *f2)
 	xdemitcb_t ecb;
 
 	memset(&xpp, 0, sizeof(xpp));
-	xpp.flags = XDF_NEED_MINIMAL;
+	xpp.flags = 0;
 	memset(&xecfg, 0, sizeof(xecfg));
 	xecfg.ctxlen = 3;
 	xecfg.flags = XDL_EMIT_COMMON;
