grep: add --threads=<num> option and grep.threads configuration

vleschuk · gitster · commit 89f09dd34e61 · 2015-12-16T12:03:23.000-08:00
"git grep" can now be configured (or told from the command line) how
many threads to use when searching in the working tree files.

Signed-off-by: Victor Leschuk &lt;vleschuk@accesssoftek.com&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/Documentation/config.txt b/Documentation/config.txt
@@ -1447,6 +1447,10 @@ grep.extendedRegexp::
 	option is ignored when the 'grep.patternType' option is set to a value
 	other than 'default'.
 
+grep.threads::
+	Number of grep worker threads to use.
+	See `grep.threads` in linkgit:git-grep[1] for more information.
+
 gpg.program::
 	Use this custom program instead of "gpg" found on $PATH when
 	making or verifying a PGP signature. The program must support the
diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt
@@ -23,6 +23,7 @@ SYNOPSIS
 	   [--break] [--heading] [-p | --show-function]
 	   [-A <post-context>] [-B <pre-context>] [-C <context>]
 	   [-W | --function-context]
+	   [--threads <num>]
 	   [-f <file>] [-e] <pattern>
 	   [--and|--or|--not|(|)|-e <pattern>...]
 	   [ [--[no-]exclude-standard] [--cached | --no-index | --untracked] | <tree>...]
@@ -53,6 +54,10 @@ grep.extendedRegexp::
 	option is ignored when the 'grep.patternType' option is set to a value
 	other than 'default'.
 
+grep.threads::
+	Number of grep worker threads to use.  If unset (or set to 0),
+	8 threads are used by default (for now).
+
 grep.fullName::
 	If set to true, enable '--full-name' option by default.
 
@@ -227,6 +232,10 @@ OPTIONS
 	effectively showing the whole function in which the match was
 	found.
 
+--threads <num>::
+	Number of grep worker threads to use.
+	See `grep.threads` in 'CONFIGURATION' for more information.
+
 -f <file>::
 	Read patterns from <file>, one per line.
 
diff --git a/builtin/grep.c b/builtin/grep.c
@@ -24,11 +24,11 @@ static char const * const grep_usage[] = {
 	NULL
 };
 
-static int use_threads = 1;
+#define GREP_NUM_THREADS_DEFAULT 8
+static int num_threads;
 
 #ifndef NO_PTHREADS
-#define THREADS 8
-static pthread_t threads[THREADS];
+static pthread_t *threads;
 
 /* We use one producer thread and THREADS consumer
  * threads. The producer adds struct work_items to 'todo' and the
@@ -63,13 +63,13 @@ static pthread_mutex_t grep_mutex;
 
 static inline void grep_lock(void)
 {
-	if (use_threads)
+	if (num_threads)
 		pthread_mutex_lock(&grep_mutex);
 }
 
 static inline void grep_unlock(void)
 {
-	if (use_threads)
+	if (num_threads)
 		pthread_mutex_unlock(&grep_mutex);
 }
 
@@ -206,7 +206,8 @@ static void start_threads(struct grep_opt *opt)
 		strbuf_init(&todo[i].out, 0);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+	threads = xcalloc(num_threads, sizeof(*threads));
+	for (i = 0; i < num_threads; i++) {
 		int err;
 		struct grep_opt *o = grep_opt_dup(opt);
 		o->output = strbuf_out;
@@ -238,12 +239,14 @@ static int wait_all(void)
 	pthread_cond_broadcast(&cond_add);
 	grep_unlock();
 
-	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+	for (i = 0; i < num_threads; i++) {
 		void *h;
 		pthread_join(threads[i], &h);
 		hit |= (int) (intptr_t) h;
 	}
 
+	free(threads);
+
 	pthread_mutex_destroy(&grep_mutex);
 	pthread_mutex_destroy(&grep_read_mutex);
 	pthread_mutex_destroy(&grep_attr_mutex);
@@ -267,6 +270,14 @@ static int grep_cmd_config(const char *var, const char *value, void *cb)
 	int st = grep_config(var, value, cb);
 	if (git_color_default_config(var, value, cb) < 0)
 		st = -1;
+
+	if (!strcmp(var, "grep.threads")) {
+		num_threads = git_config_int(var, value);
+		if (num_threads < 0)
+			die(_("invalid number of threads specified (%d) for %s"),
+			    num_threads, var);
+	}
+
 	return st;
 }
 
@@ -294,7 +305,7 @@ static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1,
 	}
 
 #ifndef NO_PTHREADS
-	if (use_threads) {
+	if (num_threads) {
 		add_work(opt, GREP_SOURCE_SHA1, pathbuf.buf, path, sha1);
 		strbuf_release(&pathbuf);
 		return 0;
@@ -323,7 +334,7 @@ static int grep_file(struct grep_opt *opt, const char *filename)
 		strbuf_addstr(&buf, filename);
 
 #ifndef NO_PTHREADS
-	if (use_threads) {
+	if (num_threads) {
 		add_work(opt, GREP_SOURCE_FILE, buf.buf, filename, filename);
 		strbuf_release(&buf);
 		return 0;
@@ -702,6 +713,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			N_("show <n> context lines before matches")),
 		OPT_INTEGER('A', "after-context", &opt.post_context,
 			N_("show <n> context lines after matches")),
+		OPT_INTEGER(0, "threads", &num_threads,
+			N_("use <n> worker threads")),
 		OPT_NUMBER_CALLBACK(&opt, N_("shortcut for -C NUM"),
 			context_callback),
 		OPT_BOOL('p', "show-function", &opt.funcname,
@@ -832,13 +845,17 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 
 #ifndef NO_PTHREADS
 	if (list.nr || cached || show_in_pager)
-		use_threads = 0;
+		num_threads = 0;
+	else if (num_threads == 0)
+		num_threads = GREP_NUM_THREADS_DEFAULT;
+	else if (num_threads < 0)
+		die(_("invalid number of threads specified (%d)"), num_threads);
 #else
-	use_threads = 0;
+	num_threads = 0;
 #endif
 
 #ifndef NO_PTHREADS
-	if (use_threads) {
+	if (num_threads) {
 		if (!(opt.name_only || opt.unmatch_name_only || opt.count)
 		    && (opt.pre_context || opt.post_context ||
 			opt.file_break || opt.funcbody))
@@ -908,7 +925,7 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		hit = grep_objects(&opt, &pathspec, &list);
 	}
 
-	if (use_threads)
+	if (num_threads)
 		hit |= wait_all();
 	if (hit && show_in_pager)
 		run_pager(&opt, prefix);
diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash
@@ -1310,6 +1310,7 @@ _git_grep ()
 			--full-name --line-number
 			--extended-regexp --basic-regexp --fixed-strings
 			--perl-regexp
+			--threads
 			--files-with-matches --name-only
 			--files-without-match
 			--max-depth
