Merge branch 'pc/range-diff-memory-limit' into seen

* pc/range-diff-memory-limit:
  range-diff: add configurable memory limit for cost matrix
  range-diff: reorder options lexicographically

Author: gitster

builtin/log.c

@@ -1408,6 +1408,7 @@ static void make_cover_letter(struct rev_info *rev, int use_separate_file,
 		struct range_diff_options range_diff_opts = {
 			.creation_factor = rev->creation_factor,
 			.dual_color = 1,
+			.max_memory = RANGE_DIFF_MAX_MEMORY_DEFAULT,
 			.diffopt = &opts,
 			.other_arg = &other_arg
 		};

builtin/range-diff.c

@@ -6,6 +6,7 @@
 #include "parse-options.h"
 #include "range-diff.h"
 #include "config.h"
+#include "parse.h"
 
 
 static const char * const builtin_range_diff_usage[] = {
@@ -15,6 +16,21 @@ N_("git range-diff [<options>] <base> <old-tip> <new-tip>"),
 NULL
 };
 
+static int parse_max_memory(const struct option *opt, const char *arg, int unset)
+{
+	size_t *max_memory = opt->value;
+	uintmax_t val;
+
+	if (unset)
+		return 0;
+
+	if (!git_parse_unsigned(arg, &val, SIZE_MAX))
+		return error(_("invalid max-memory value: %s"), arg);
+
+	*max_memory = (size_t)val;
+	return 0;
+}
+
 int cmd_range_diff(int argc,
 		   const char **argv,
 		   const char *prefix,
@@ -25,6 +41,7 @@ int cmd_range_diff(int argc,
 	struct strvec diff_merges_arg = STRVEC_INIT;
 	struct range_diff_options range_diff_opts = {
 		.creation_factor = RANGE_DIFF_CREATION_FACTOR_DEFAULT,
+		.max_memory = RANGE_DIFF_MAX_MEMORY_DEFAULT,
 		.diffopt = &diffopt,
 		.other_arg = &other_arg
 	};
@@ -33,17 +50,21 @@ int cmd_range_diff(int argc,
 		OPT_INTEGER(0, "creation-factor",
 			    &range_diff_opts.creation_factor,
 			    N_("percentage by which creation is weighted")),
+		OPT_PASSTHRU_ARGV(0, "diff-merges", &diff_merges_arg,
+				  N_("style"), N_("passed to 'git log'"), 0),
+		OPT_BOOL(0, "left-only", &left_only,
+			 N_("only emit output related to the first range")),
+		OPT_CALLBACK(0, "max-memory", &range_diff_opts.max_memory,
+			     N_("size"),
+			     N_("maximum memory for cost matrix (default 4G)"),
+			     parse_max_memory),
 		OPT_BOOL(0, "no-dual-color", &simple_color,
 			    N_("use simple diff colors")),
 		OPT_PASSTHRU_ARGV(0, "notes", &other_arg,
 				  N_("notes"), N_("passed to 'git log'"),
 				  PARSE_OPT_OPTARG),
-		OPT_PASSTHRU_ARGV(0, "diff-merges", &diff_merges_arg,
-				  N_("style"), N_("passed to 'git log'"), 0),
 		OPT_PASSTHRU_ARGV(0, "remerge-diff", &diff_merges_arg, NULL,
 				  N_("passed to 'git log'"), PARSE_OPT_NOARG),
-		OPT_BOOL(0, "left-only", &left_only,
-			 N_("only emit output related to the first range")),
 		OPT_BOOL(0, "right-only", &right_only,
 			 N_("only emit output related to the second range")),
 		OPT_END()

log-tree.c

@@ -717,6 +717,7 @@ static void show_diff_of_diff(struct rev_info *opt)
 		struct range_diff_options range_diff_opts = {
 			.creation_factor = opt->creation_factor,
 			.dual_color = 1,
+			.max_memory = RANGE_DIFF_MAX_MEMORY_DEFAULT,
 			.diffopt = &opts
 		};
 

range-diff.c

@@ -325,13 +325,24 @@ static int diffsize(const char *a, const char *b)
 }
 
 static void get_correspondences(struct string_list *a, struct string_list *b,
-				int creation_factor)
+				int creation_factor, size_t max_memory)
 {
 	int n = a->nr + b->nr;
 	int *cost, c, *a2b, *b2a;
 	int i, j;
-
-	ALLOC_ARRAY(cost, st_mult(n, n));
+	size_t cost_size = st_mult(n, n);
+	size_t cost_bytes = st_mult(sizeof(int), cost_size);
+	if (cost_bytes >= max_memory) {
+		struct strbuf cost_str = STRBUF_INIT;
+		struct strbuf max_str = STRBUF_INIT;
+		strbuf_humanise_bytes(&cost_str, cost_bytes);
+		strbuf_humanise_bytes(&max_str, max_memory);
+		die(_("range-diff: unable to compute the range-diff, since it "
+		      "exceeds the maximum memory for the cost matrix: %s "
+		      "(%"PRIuMAX" bytes) needed, %s (%"PRIuMAX" bytes) available"),
+		    cost_str.buf, (uintmax_t)cost_bytes, max_str.buf, (uintmax_t)max_memory);
+	}
+	ALLOC_ARRAY(cost, cost_size);
 	ALLOC_ARRAY(a2b, n);
 	ALLOC_ARRAY(b2a, n);
 
@@ -591,7 +602,8 @@ int show_range_diff(const char *range1, const char *range2,
 	if (!res) {
 		find_exact_matches(&branch1, &branch2);
 		get_correspondences(&branch1, &branch2,
-				    range_diff_opts->creation_factor);
+				    range_diff_opts->creation_factor,
+				    range_diff_opts->max_memory);
 		output(&branch1, &branch2, range_diff_opts);
 	}
 

range-diff.h

@@ -5,6 +5,10 @@
 #include "strvec.h"
 
 #define RANGE_DIFF_CREATION_FACTOR_DEFAULT 60
+#define RANGE_DIFF_MAX_MEMORY_DEFAULT \
+	(sizeof(void*) >= 8 ? \
+		((size_t)(1024L * 1024L) * (size_t)(4L * 1024L)) : /* 4GB on 64-bit */ \
+		((size_t)(1024L * 1024L) * (size_t)(2L * 1024L)))   /* 2GB on 32-bit */
 
 /*
  * A much higher value than the default, when we KNOW we are comparing
@@ -17,6 +21,7 @@ struct range_diff_options {
 	unsigned dual_color:1;
 	unsigned left_only:1, right_only:1;
 	unsigned include_merges:1;
+	size_t max_memory;
 	const struct diff_options *diffopt; /* may be NULL */
 	const struct strvec *other_arg; /* may be NULL */
 };