30 files changed, 873 insertions, 101 deletions

diff --git a/Documentation/RelNotes/2.8.0.txt b/Documentation/RelNotes/2.8.0.txt
new file mode 100644
index 0000000000..8444dd509d
--- /dev/null
+++ b/Documentation/RelNotes/2.8.0.txt
@@ -0,0 +1,44 @@
+Git 2.8 Release Notes
+=====================
+
+Updates since v2.7
+------------------
+
+UI, Workflows & Features
+
+ * "branch --delete" has "branch -d" but "push --delete" does not.
+   (merge 38a2559 ps/push-delete-option later to maint).
+
+ * "git blame" learned to produce the progress eye-candy when it takes
+   too much time before emitting the first line of the result.
+   (merge aba37f4 ea/blame-progress later to maint).
+
+ * "git grep" can now be configured (or told from the command line)
+   how many threads to use when searching in the working tree files.
+   (merge 89f09dd vl/grep-configurable-threads later to maint).
+
+
+Performance, Internal Implementation, Development Support etc.
+
+ * Add a framework to spawn a group of processes in parallel, and use
+   it to run "git fetch --recurse-submodules" in parallel.
+
+ * A slight update to the Makefile to mark "phoney" targets
+   as such correctly.
+
+
+Also contains various documentation updates and code clean-ups.
+
+
+Fixes since v2.7
+----------------
+
+Unless otherwise noted, all the fixes since v2.7 in the maintenance
+track are contained in this release (see the maintenance releases'
+notes for details).
+
+ * An earlier change in 2.5.x-era broke users' hooks and aliases by
+   exporting GIT_WORK_TREE to point at the root of the working tree,
+   interfering when they tried to use a different working tree without
+   setting GIT_WORK_TREE environment themselves.
+   (merge df1e6ea nd/stop-setenv-work-tree later to maint).
diff --git a/Documentation/blame-options.txt b/Documentation/blame-options.txt
index 760eab7428..02cb6845cd 100644
--- a/Documentation/blame-options.txt
+++ b/Documentation/blame-options.txt
@@ -69,6 +69,13 @@ include::line-range-format.txt[]
 	iso format is used. For supported values, see the discussion
 	of the --date option at linkgit:git-log[1].
 
+--[no-]progress::
+	Progress status is reported on the standard error stream
+	by default when it is attached to a terminal. This flag
+	enables progress reporting even if not attached to a
+	terminal. Can't use `--progress` together with `--porcelain`
+	or `--incremental`.
+
 -M|<num>|::
 	Detect moved or copied lines within a file. When a commit
 	moves or copies a block of lines (e.g. the original file
diff --git a/Documentation/config.txt b/Documentation/config.txt
index f61788668e..beb18da143 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1450,6 +1450,10 @@ 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/fetch-options.txt b/Documentation/fetch-options.txt
index 45583d8454..6b109f687a 100644
--- a/Documentation/fetch-options.txt
+++ b/Documentation/fetch-options.txt
@@ -100,6 +100,13 @@ ifndef::git-pull[]
 	reference to a commit that isn't already in the local submodule
 	clone.
 
+-j::
+--jobs=<n>::
+	Number of parallel children to be used for fetching submodules.
+	Each will fetch from different submodules, such that fetching many
+	submodules will be faster. By default submodules will be fetched
+	one at a time.
+
 --no-recurse-submodules::
 	Disable recursive fetching of submodules (this has the same effect as
 	using the '--recurse-submodules=no' option).
diff --git a/Documentation/git-blame.txt b/Documentation/git-blame.txt
index e6e947c808..ba5417567c 100644
--- a/Documentation/git-blame.txt
+++ b/Documentation/git-blame.txt
@@ -10,7 +10,8 @@ SYNOPSIS
 [verse]
 'git blame' [-c] [-b] [-l] [--root] [-t] [-f] [-n] [-s] [-e] [-p] [-w] [--incremental]
 	    [-L <range>] [-S <revs-file>] [-M] [-C] [-C] [-C] [--since=<date>]
-	    [--abbrev=<n>] [<rev> | --contents <file> | --reverse <rev>] [--] <file>
+	    [--progress] [--abbrev=<n>] [<rev> | --contents <file> | --reverse <rev>]
+	    [--] <file>
 
 DESCRIPTION
 -----------
diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt
index 4a44d6da13..35aada1447 100644
--- 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/Documentation/git-push.txt b/Documentation/git-push.txt
index 4c775bcec4..32482cec42 100644
--- a/Documentation/git-push.txt
+++ b/Documentation/git-push.txt
@@ -10,7 +10,7 @@ SYNOPSIS
 --------
 [verse]
 'git push' [--all | --mirror | --tags] [--follow-tags] [--atomic] [-n | --dry-run] [--receive-pack=<git-receive-pack>]
-	   [--repo=<repository>] [-f | --force] [--prune] [-v | --verbose]
+	   [--repo=<repository>] [-f | --force] [-d | --delete] [--prune] [-v | --verbose]
 	   [-u | --set-upstream]
 	   [--[no-]signed|--sign=(true|false|if-asked)]
 	   [--force-with-lease[=<refname>[:<expect>]]]
diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN
index 51aa9e6806..5873f163e5 100755
--- a/GIT-VERSION-GEN
+++ b/GIT-VERSION-GEN
@@ -1,7 +1,7 @@
 #!/bin/sh
 
 GVF=GIT-VERSION-FILE
-DEF_VER=v2.7.0
+DEF_VER=v2.7.0.GIT
 
 LF='
 '
diff --git a/Makefile b/Makefile
index fd19b544c2..fc2f1ab2c3 100644
--- a/Makefile
+++ b/Makefile
@@ -2025,6 +2025,7 @@ $(VCSSVN_LIB): $(VCSSVN_OBJS)
 
 export DEFAULT_EDITOR DEFAULT_PAGER
 
+.PHONY: doc man html info pdf
 doc:
 	$(MAKE) -C Documentation all
 
@@ -2068,6 +2069,7 @@ po/git.pot: $(GENERATED_H) FORCE
 		$(LOCALIZED_PERL)
 	mv $@+ $@
 
+.PHONY: pot
 pot: po/git.pot
 
 POFILES := $(wildcard po/*.po)
@@ -2277,6 +2279,7 @@ mergetools_instdir_SQ = $(subst ','\'',$(mergetools_instdir))
 
 install_bindir_programs := $(patsubst %,%$X,$(BINDIR_PROGRAMS_NEED_X)) $(BINDIR_PROGRAMS_NO_X)
 
+.PHONY: profile-install profile-fast-install
 profile-install: profile
 	$(MAKE) install
 
@@ -2343,6 +2346,8 @@ endif
 	done && \
 	./check_bindir "z$$bindir" "z$$execdir" "$$bindir/git-add$X"
 
+.PHONY: install-gitweb install-doc install-man install-html install-info install-pdf
+.PHONY: quick-install-doc quick-install-man quick-install-html
 install-gitweb:
 	$(MAKE) -C gitweb install
 
@@ -2402,6 +2407,7 @@ rpm: dist
 
 htmldocs = git-htmldocs-$(GIT_VERSION)
 manpages = git-manpages-$(GIT_VERSION)
+.PHONY: dist-doc distclean
 dist-doc:
 	$(RM) -r .doc-tmp-dir
 	mkdir .doc-tmp-dir
@@ -2470,6 +2476,8 @@ ALL_COMMANDS += git
 ALL_COMMANDS += gitk
 ALL_COMMANDS += gitweb
 ALL_COMMANDS += git-gui git-citool
+
+.PHONY: check-docs
 check-docs::
 	@(for v in $(ALL_COMMANDS); \
 	do \
@@ -2514,6 +2522,7 @@ check-builtins::
 ### Test suite coverage testing
 #
 .PHONY: coverage coverage-clean coverage-compile coverage-test coverage-report
+.PHONY: coverage-untested-functions cover_db cover_db_html
 .PHONY: coverage-clean-results
 
 coverage:
diff --git a/RelNotes b/RelNotes
index 3ba13ce253..7db30403c3 120000
--- a/RelNotes
+++ b/RelNotes
@@ -1 +1 @@
-Documentation/RelNotes/2.7.0.txt
\ No newline at end of file
+Documentation/RelNotes/2.8.0.txt
\ No newline at end of file
diff --git a/builtin/blame.c b/builtin/blame.c
index 1df13cf7f4..d3fc82c852 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -28,6 +28,7 @@
 #include "line-range.h"
 #include "line-log.h"
 #include "dir.h"
+#include "progress.h"
 
 static char blame_usage[] = N_("git blame [<options>] [<rev-opts>] [<rev>] [--] <file>");
 
@@ -50,6 +51,7 @@ static int incremental;
 static int xdl_opts;
 static int abbrev = -1;
 static int no_whole_file_rename;
+static int show_progress;
 
 static struct date_mode blame_date_mode = { DATE_ISO8601 };
 static size_t blame_date_width;
@@ -127,6 +129,11 @@ struct origin {
 	char path[FLEX_ARRAY];
 };
 
+struct progress_info {
+	struct progress *progress;
+	int blamed_lines;
+};
+
 static int diff_hunks(mmfile_t *file_a, mmfile_t *file_b, long ctxlen,
 		      xdl_emit_hunk_consume_func_t hunk_func, void *cb_data)
 {
@@ -1746,7 +1753,8 @@ static int emit_one_suspect_detail(struct origin *suspect, int repeat)
  * The blame_entry is found to be guilty for the range.
  * Show it in incremental output.
  */
-static void found_guilty_entry(struct blame_entry *ent)
+static void found_guilty_entry(struct blame_entry *ent,
+			   struct progress_info *pi)
 {
 	if (incremental) {
 		struct origin *suspect = ent->suspect;
@@ -1758,6 +1766,8 @@ static void found_guilty_entry(struct blame_entry *ent)
 		write_filename_info(suspect->path);
 		maybe_flush_or_die(stdout, "stdout");
 	}
+	pi->blamed_lines += ent->num_lines;
+	display_progress(pi->progress, pi->blamed_lines);
 }
 
 /*
@@ -1768,6 +1778,11 @@ static void assign_blame(struct scoreboard *sb, int opt)
 {
 	struct rev_info *revs = sb->revs;
 	struct commit *commit = prio_queue_get(&sb->commits);
+	struct progress_info pi = { NULL, 0 };
+
+	if (show_progress)
+		pi.progress = start_progress_delay(_("Blaming lines"),
+						   sb->num_lines, 50, 1);
 
 	while (commit) {
 		struct blame_entry *ent;
@@ -1809,7 +1824,7 @@ static void assign_blame(struct scoreboard *sb, int opt)
 			suspect->guilty = 1;
 			for (;;) {
 				struct blame_entry *next = ent->next;
-				found_guilty_entry(ent);
+				found_guilty_entry(ent, &pi);
 				if (next) {
 					ent = next;
 					continue;
@@ -1825,6 +1840,8 @@ static void assign_blame(struct scoreboard *sb, int opt)
 		if (DEBUG) /* sanity */
 			sanity_check_refcnt(sb);
 	}
+
+	stop_progress(&pi.progress);
 }
 
 static const char *format_time(unsigned long time, const char *tz_str,
@@ -2520,6 +2537,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 		OPT_BOOL('b', NULL, &blank_boundary, N_("Show blank SHA-1 for boundary commits (Default: off)")),
 		OPT_BOOL(0, "root", &show_root, N_("Do not treat root commits as boundaries (Default: off)")),
 		OPT_BOOL(0, "show-stats", &show_stats, N_("Show work cost statistics")),
+		OPT_BOOL(0, "progress", &show_progress, N_("Force progress reporting")),
 		OPT_BIT(0, "score-debug", &output_option, N_("Show output score for blame entries"), OUTPUT_SHOW_SCORE),
 		OPT_BIT('f', "show-name", &output_option, N_("Show original filename (Default: auto)"), OUTPUT_SHOW_NAME),
 		OPT_BIT('n', "show-number", &output_option, N_("Show original linenumber (Default: off)"), OUTPUT_SHOW_NUMBER),
@@ -2555,6 +2573,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix)
 
 	save_commit_buffer = 0;
 	dashdash_pos = 0;
+	show_progress = -1;
 
 	parse_options_start(&ctx, argc, argv, prefix, options,
 			    PARSE_OPT_KEEP_DASHDASH | PARSE_OPT_KEEP_ARGV0);
@@ -2579,6 +2598,13 @@ parse_done:
 	DIFF_OPT_CLR(&revs.diffopt, FOLLOW_RENAMES);
 	argc = parse_options_end(&ctx);
 
+	if (incremental || (output_option & OUTPUT_PORCELAIN)) {
+		if (show_progress > 0)
+			die("--progress can't be used with --incremental or porcelain formats");
+		show_progress = 0;
+	} else if (show_progress < 0)
+		show_progress = isatty(2);
+
 	if (0 < abbrev)
 		/* one more abbrev length is needed for the boundary commit */
 		abbrev++;
@@ -2828,11 +2854,11 @@ parse_done:
 
 	read_mailmap(&mailmap, NULL);
 
+	assign_blame(&sb, opt);
+
 	if (!incremental)
 		setup_pager();
 
-	assign_blame(&sb, opt);
-
 	free(final_commit_name);
 
 	if (incremental)
diff --git a/builtin/fetch.c b/builtin/fetch.c
index c85f3471d4..586840d761 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -37,6 +37,7 @@ static int prune = -1; /* unspecified */
 static int all, append, dry_run, force, keep, multiple, update_head_ok, verbosity;
 static int progress = -1, recurse_submodules = RECURSE_SUBMODULES_DEFAULT;
 static int tags = TAGS_DEFAULT, unshallow, update_shallow;
+static int max_children = 1;
 static const char *depth;
 static const char *upload_pack;
 static struct strbuf default_rla = STRBUF_INIT;
@@ -99,6 +100,8 @@ static struct option builtin_fetch_options[] = {
 		    N_("fetch all tags and associated objects"), TAGS_SET),
 	OPT_SET_INT('n', NULL, &tags,
 		    N_("do not fetch all tags (--no-tags)"), TAGS_UNSET),
+	OPT_INTEGER('j', "jobs", &max_children,
+		    N_("number of submodules fetched in parallel")),
 	OPT_BOOL('p', "prune", &prune,
 		 N_("prune remote-tracking branches no longer on remote")),
 	{ OPTION_CALLBACK, 0, "recurse-submodules", NULL, N_("on-demand"),
@@ -1213,7 +1216,8 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 		result = fetch_populated_submodules(&options,
 						    submodule_prefix,
 						    recurse_submodules,
-						    verbosity < 0);
+						    verbosity < 0,
+						    max_children);
 		argv_array_clear(&options);
 	}
 
diff --git a/builtin/grep.c b/builtin/grep.c
index 4229cae390..760dc8eae9 100644
--- 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;
@@ -697,6 +708,8 @@ 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,
@@ -786,7 +799,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		opt.output_priv = &path_list;
 		opt.output = append_path;
 		string_list_append(&path_list, show_in_pager);
-		use_threads = 0;
 	}
 
 	if (!opt.pattern_list)
@@ -817,14 +829,18 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	}
 
 #ifndef NO_PTHREADS
-	if (list.nr || cached || online_cpus() == 1)
-		use_threads = 0;
+	if (list.nr || cached || show_in_pager)
+		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))
@@ -894,7 +910,7 @@ 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/builtin/pull.c b/builtin/pull.c
index 5145fc60a0..9e3c73809f 100644
--- a/builtin/pull.c
+++ b/builtin/pull.c
@@ -95,6 +95,7 @@ static int opt_force;
 static char *opt_tags;
 static char *opt_prune;
 static char *opt_recurse_submodules;
+static char *max_children;
 static int opt_dry_run;
 static char *opt_keep;
 static char *opt_depth;
@@ -178,6 +179,9 @@ static struct option pull_options[] = {
 		N_("on-demand"),
 		N_("control recursive fetching of submodules"),
 		PARSE_OPT_OPTARG),
+	OPT_PASSTHRU('j', "jobs", &max_children, N_("n"),
+		N_("number of submodules pulled in parallel"),
+		PARSE_OPT_OPTARG),
 	OPT_BOOL(0, "dry-run", &opt_dry_run,
 		N_("dry run")),
 	OPT_PASSTHRU('k', "keep", &opt_keep, NULL,
@@ -525,6 +529,8 @@ static int run_fetch(const char *repo, const char **refspecs)
 		argv_array_push(&args, opt_prune);
 	if (opt_recurse_submodules)
 		argv_array_push(&args, opt_recurse_submodules);
+	if (max_children)
+		argv_array_push(&args, max_children);
 	if (opt_dry_run)
 		argv_array_push(&args, "--dry-run");
 	if (opt_keep)
diff --git a/builtin/push.c b/builtin/push.c
index 8963dbdf3d..960ffc31e1 100644
--- a/builtin/push.c
+++ b/builtin/push.c
@@ -538,7 +538,7 @@ int cmd_push(int argc, const char **argv, const char *prefix)
 		OPT_BIT( 0 , "all", &flags, N_("push all refs"), TRANSPORT_PUSH_ALL),
 		OPT_BIT( 0 , "mirror", &flags, N_("mirror all refs"),
 			    (TRANSPORT_PUSH_MIRROR|TRANSPORT_PUSH_FORCE)),
-		OPT_BOOL( 0, "delete", &deleterefs, N_("delete refs")),
+		OPT_BOOL('d', "delete", &deleterefs, N_("delete refs")),
 		OPT_BOOL( 0 , "tags", &tags, N_("push tags (can't be used with --all or --mirror)")),
 		OPT_BIT('n' , "dry-run", &flags, N_("dry run"), TRANSPORT_PUSH_DRY_RUN),
 		OPT_BIT( 0,  "porcelain", &flags, N_("machine-readable output"), TRANSPORT_PUSH_PORCELAIN),
diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash
index 6956807519..ab4da7f979 100644
--- a/contrib/completion/git-completion.bash
+++ b/contrib/completion/git-completion.bash
@@ -1312,6 +1312,7 @@ _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
diff --git a/environment.c b/environment.c
index 2da7fe2e06..1cc4aab4ea 100644
--- a/environment.c
+++ b/environment.c
@@ -235,8 +235,6 @@ void set_git_work_tree(const char *new_work_tree)
 	}
 	git_work_tree_initialized = 1;
 	work_tree = xstrdup(real_path(new_work_tree));
-	if (setenv(GIT_WORK_TREE_ENVIRONMENT, work_tree, 1))
-		die("could not set GIT_WORK_TREE to '%s'", work_tree);
 }
 
 const char *get_git_work_tree(void)
diff --git a/run-command.c b/run-command.c
index 13fa452e8c..51fd72c427 100644
--- a/run-command.c
+++ b/run-command.c
@@ -3,6 +3,8 @@
 #include "exec_cmd.h"
 #include "sigchain.h"
 #include "argv-array.h"
+#include "thread-utils.h"
+#include "strbuf.h"
 
 void child_process_init(struct child_process *child)
 {
@@ -865,3 +867,336 @@ int capture_command(struct child_process *cmd, struct strbuf *buf, size_t hint)
 	close(cmd->out);
 	return finish_command(cmd);
 }
+
+enum child_state {
+	GIT_CP_FREE,
+	GIT_CP_WORKING,
+	GIT_CP_WAIT_CLEANUP,
+};
+
+struct parallel_processes {
+	void *data;
+
+	int max_processes;
+	int nr_processes;
+
+	get_next_task_fn get_next_task;
+	start_failure_fn start_failure;
+	task_finished_fn task_finished;
+
+	struct {
+		enum child_state state;
+		struct child_process process;
+		struct strbuf err;
+		void *data;
+	} *children;
+	/*
+	 * The struct pollfd is logically part of *children,
+	 * but the system call expects it as its own array.
+	 */
+	struct pollfd *pfd;
+
+	unsigned shutdown : 1;
+
+	int output_owner;
+	struct strbuf buffered_output; /* of finished children */
+};
+
+static int default_start_failure(struct child_process *cp,
+				 struct strbuf *err,
+				 void *pp_cb,
+				 void *pp_task_cb)
+{
+	int i;
+
+	strbuf_addstr(err, "Starting a child failed:");
+	for (i = 0; cp->argv[i]; i++)
+		strbuf_addf(err, " %s", cp->argv[i]);
+
+	return 0;
+}
+
+static int default_task_finished(int result,
+				 struct child_process *cp,
+				 struct strbuf *err,
+				 void *pp_cb,
+				 void *pp_task_cb)
+{
+	int i;
+
+	if (!result)
+		return 0;
+
+	strbuf_addf(err, "A child failed with return code %d:", result);
+	for (i = 0; cp->argv[i]; i++)
+		strbuf_addf(err, " %s", cp->argv[i]);
+
+	return 0;
+}
+
+static void kill_children(struct parallel_processes *pp, int signo)
+{
+	int i, n = pp->max_processes;
+
+	for (i = 0; i < n; i++)
+		if (pp->children[i].state == GIT_CP_WORKING)
+			kill(pp->children[i].process.pid, signo);
+}
+
+static struct parallel_processes *pp_for_signal;
+
+static void handle_children_on_signal(int signo)
+{
+	kill_children(pp_for_signal, signo);
+	sigchain_pop(signo);
+	raise(signo);
+}
+
+static void pp_init(struct parallel_processes *pp,
+		    int n,
+		    get_next_task_fn get_next_task,
+		    start_failure_fn start_failure,
+		    task_finished_fn task_finished,
+		    void *data)
+{
+	int i;
+
+	if (n < 1)
+		n = online_cpus();
+
+	pp->max_processes = n;
+
+	trace_printf("run_processes_parallel: preparing to run up to %d tasks", n);
+
+	pp->data = data;
+	if (!get_next_task)
+		die("BUG: you need to specify a get_next_task function");
+	pp->get_next_task = get_next_task;
+
+	pp->start_failure = start_failure ? start_failure : default_start_failure;
+	pp->task_finished = task_finished ? task_finished : default_task_finished;
+
+	pp->nr_processes = 0;
+	pp->output_owner = 0;
+	pp->shutdown = 0;
+	pp->children = xcalloc(n, sizeof(*pp->children));
+	pp->pfd = xcalloc(n, sizeof(*pp->pfd));
+	strbuf_init(&pp->buffered_output, 0);
+
+	for (i = 0; i < n; i++) {
+		strbuf_init(&pp->children[i].err, 0);
+		child_process_init(&pp->children[i].process);
+		pp->pfd[i].events = POLLIN | POLLHUP;
+		pp->pfd[i].fd = -1;
+	}
+
+	pp_for_signal = pp;
+	sigchain_push_common(handle_children_on_signal);
+}
+
+static void pp_cleanup(struct parallel_processes *pp)
+{
+	int i;
+
+	trace_printf("run_processes_parallel: done");
+	for (i = 0; i < pp->max_processes; i++) {
+		strbuf_release(&pp->children[i].err);
+		child_process_clear(&pp->children[i].process);
+	}
+
+	free(pp->children);
+	free(pp->pfd);
+
+	/*
+	 * When get_next_task added messages to the buffer in its last
+	 * iteration, the buffered output is non empty.
+	 */
+	fputs(pp->buffered_output.buf, stderr);
+	strbuf_release(&pp->buffered_output);
+
+	sigchain_pop_common();
+}
+
+/* returns
+ *  0 if a new task was started.
+ *  1 if no new jobs was started (get_next_task ran out of work, non critical
+ *    problem with starting a new command)
+ * <0 no new job was started, user wishes to shutdown early. Use negative code
+ *    to signal the children.
+ */
+static int pp_start_one(struct parallel_processes *pp)
+{
+	int i, code;
+
+	for (i = 0; i < pp->max_processes; i++)
+		if (pp->children[i].state == GIT_CP_FREE)
+			break;
+	if (i == pp->max_processes)
+		die("BUG: bookkeeping is hard");
+
+	code = pp->get_next_task(&pp->children[i].process,
+				 &pp->children[i].err,
+				 pp->data,
+				 &pp->children[i].data);
+	if (!code) {
+		strbuf_addbuf(&pp->buffered_output, &pp->children[i].err);
+		strbuf_reset(&pp->children[i].err);
+		return 1;
+	}
+	pp->children[i].process.err = -1;
+	pp->children[i].process.stdout_to_stderr = 1;
+	pp->children[i].process.no_stdin = 1;
+
+	if (start_command(&pp->children[i].process)) {
+		code = pp->start_failure(&pp->children[i].process,
+					 &pp->children[i].err,
+					 pp->data,
+					 &pp->children[i].data);
+		strbuf_addbuf(&pp->buffered_output, &pp->children[i].err);
+		strbuf_reset(&pp->children[i].err);
+		if (code)
+			pp->shutdown = 1;
+		return code;
+	}
+
+	pp->nr_processes++;
+	pp->children[i].state = GIT_CP_WORKING;
+	pp->pfd[i].fd = pp->children[i].process.err;
+	return 0;
+}
+
+static void pp_buffer_stderr(struct parallel_processes *pp, int output_timeout)
+{
+	int i;
+
+	while ((i = poll(pp->pfd, pp->max_processes, output_timeout)) < 0) {
+		if (errno == EINTR)
+			continue;
+		pp_cleanup(pp);
+		die_errno("poll");
+	}
+
+	/* Buffer output from all pipes. */
+	for (i = 0; i < pp->max_processes; i++) {
+		if (pp->children[i].state == GIT_CP_WORKING &&
+		    pp->pfd[i].revents & (POLLIN | POLLHUP)) {
+			int n = strbuf_read_once(&pp->children[i].err,
+						 pp->children[i].process.err, 0);
+			if (n == 0) {
+				close(pp->children[i].process.err);
+				pp->children[i].state = GIT_CP_WAIT_CLEANUP;
+			} else if (n < 0)
+				if (errno != EAGAIN)
+					die_errno("read");
+		}
+	}
+}
+
+static void pp_output(struct parallel_processes *pp)
+{
+	int i = pp->output_owner;
+	if (pp->children[i].state == GIT_CP_WORKING &&
+	    pp->children[i].err.len) {
+		fputs(pp->children[i].err.buf, stderr);
+		strbuf_reset(&pp->children[i].err);
+	}
+}
+
+static int pp_collect_finished(struct parallel_processes *pp)
+{
+	int i, code;
+	int n = pp->max_processes;
+	int result = 0;
+
+	while (pp->nr_processes > 0) {
+		for (i = 0; i < pp->max_processes; i++)
+			if (pp->children[i].state == GIT_CP_WAIT_CLEANUP)
+				break;
+		if (i == pp->max_processes)
+			break;
+
+		code = finish_command(&pp->children[i].process);
+
+		code = pp->task_finished(code, &pp->children[i].process,
+					 &pp->children[i].err, pp->data,
+					 &pp->children[i].data);
+
+		if (code)
+			result = code;
+		if (code < 0)
+			break;
+
+		pp->nr_processes--;
+		pp->children[i].state = GIT_CP_FREE;
+		pp->pfd[i].fd = -1;
+		child_process_init(&pp->children[i].process);
+
+		if (i != pp->output_owner) {
+			strbuf_addbuf(&pp->buffered_output, &pp->children[i].err);
+			strbuf_reset(&pp->children[i].err);
+		} else {
+			fputs(pp->children[i].err.buf, stderr);
+			strbuf_reset(&pp->children[i].err);
+
+			/* Output all other finished child processes */
+			fputs(pp->buffered_output.buf, stderr);
+			strbuf_reset(&pp->buffered_output);
+
+			/*
+			 * Pick next process to output live.
+			 * NEEDSWORK:
+			 * For now we pick it randomly by doing a round
+			 * robin. Later we may want to pick the one with
+			 * the most output or the longest or shortest
+			 * running process time.
+			 */
+			for (i = 0; i < n; i++)
+				if (pp->children[(pp->output_owner + i) % n].state == GIT_CP_WORKING)
+					break;
+			pp->output_owner = (pp->output_owner + i) % n;
+		}
+	}
+	return result;
+}
+
+int run_processes_parallel(int n,
+			   get_next_task_fn get_next_task,
+			   start_failure_fn start_failure,
+			   task_finished_fn task_finished,
+			   void *pp_cb)
+{
+	int i, code;
+	int output_timeout = 100;
+	int spawn_cap = 4;
+	struct parallel_processes pp;
+
+	pp_init(&pp, n, get_next_task, start_failure, task_finished, pp_cb);
+	while (1) {
+		for (i = 0;
+		    i < spawn_cap && !pp.shutdown &&
+		    pp.nr_processes < pp.max_processes;
+		    i++) {
+			code = pp_start_one(&pp);
+			if (!code)
+				continue;
+			if (code < 0) {
+				pp.shutdown = 1;
+				kill_children(&pp, -code);
+			}
+			break;
+		}
+		if (!pp.nr_processes)
+			break;
+		pp_buffer_stderr(&pp, output_timeout);
+		pp_output(&pp);
+		code = pp_collect_finished(&pp);
+		if (code) {
+			pp.shutdown = 1;
+			if (code < 0)
+				kill_children(&pp, -code);
+		}
+	}
+
+	pp_cleanup(&pp);
+	return 0;
+}
diff --git a/run-command.h b/run-command.h
index 12bb26c2a6..d5a57f9227 100644
--- a/run-command.h
+++ b/run-command.h
@@ -122,4 +122,84 @@ int start_async(struct async *async);
 int finish_async(struct async *async);
 int in_async(void);
 
+/**
+ * This callback should initialize the child process and preload the
+ * error channel if desired. The preloading of is useful if you want to
+ * have a message printed directly before the output of the child process.
+ * pp_cb is the callback cookie as passed to run_processes_parallel.
+ * You can store a child process specific callback cookie in pp_task_cb.
+ *
+ * Even after returning 0 to indicate that there are no more processes,
+ * this function will be called again until there are no more running
+ * child processes.
+ *
+ * Return 1 if the next child is ready to run.
+ * Return 0 if there are currently no more tasks to be processed.
+ * To send a signal to other child processes for abortion,
+ * return the negative signal number.
+ */
+typedef int (*get_next_task_fn)(struct child_process *cp,
+				struct strbuf *err,
+				void *pp_cb,
+				void **pp_task_cb);
+
+/**
+ * This callback is called whenever there are problems starting
+ * a new process.
+ *
+ * You must not write to stdout or stderr in this function. Add your
+ * message to the strbuf err instead, which will be printed without
+ * messing up the output of the other parallel processes.
+ *
+ * pp_cb is the callback cookie as passed into run_processes_parallel,
+ * pp_task_cb is the callback cookie as passed into get_next_task_fn.
+ *
+ * Return 0 to continue the parallel processing. To abort return non zero.
+ * To send a signal to other child processes for abortion, return
+ * the negative signal number.
+ */
+typedef int (*start_failure_fn)(struct child_process *cp,
+				struct strbuf *err,
+				void *pp_cb,
+				void *pp_task_cb);
+
+/**
+ * This callback is called on every child process that finished processing.
+ *
+ * You must not write to stdout or stderr in this function. Add your
+ * message to the strbuf err instead, which will be printed without
+ * messing up the output of the other parallel processes.
+ *
+ * pp_cb is the callback cookie as passed into run_processes_parallel,
+ * pp_task_cb is the callback cookie as passed into get_next_task_fn.
+ *
+ * Return 0 to continue the parallel processing.  To abort return non zero.
+ * To send a signal to other child processes for abortion, return
+ * the negative signal number.
+ */
+typedef int (*task_finished_fn)(int result,
+				struct child_process *cp,
+				struct strbuf *err,
+				void *pp_cb,
+				void *pp_task_cb);
+
+/**
+ * Runs up to n processes at the same time. Whenever a process can be
+ * started, the callback get_next_task_fn is called to obtain the data
+ * required to start another child process.
+ *
+ * The children started via this function run in parallel. Their output
+ * (both stdout and stderr) is routed to stderr in a manner that output
+ * from different tasks does not interleave.
+ *
+ * If start_failure_fn or task_finished_fn are NULL, default handlers
+ * will be used. The default handlers will print an error message on
+ * error without issuing an emergency stop.
+ */
+int run_processes_parallel(int n,
+			   get_next_task_fn,
+			   start_failure_fn,
+			   task_finished_fn,
+			   void *pp_cb);
+
 #endif
diff --git a/sigchain.c b/sigchain.c
index faa375d5d8..2ac43bbd28 100644
--- a/sigchain.c
+++ b/sigchain.c
@@ -50,3 +50,12 @@ void sigchain_push_common(sigchain_fun f)
 	sigchain_push(SIGQUIT, f);
 	sigchain_push(SIGPIPE, f);
 }
+
+void sigchain_pop_common(void)
+{
+	sigchain_pop(SIGPIPE);
+	sigchain_pop(SIGQUIT);
+	sigchain_pop(SIGTERM);
+	sigchain_pop(SIGHUP);
+	sigchain_pop(SIGINT);
+}
diff --git a/sigchain.h b/sigchain.h
index 618083bce0..138b20f54b 100644
--- a/sigchain.h
+++ b/sigchain.h
@@ -7,5 +7,6 @@ int sigchain_push(int sig, sigchain_fun f);
 int sigchain_pop(int sig);
 
 void sigchain_push_common(sigchain_fun f);
+void sigchain_pop_common(void);
 
 #endif /* SIGCHAIN_H */
diff --git a/strbuf.c b/strbuf.c
index d76f0aed85..38686ffb65 100644
--- a/strbuf.c
+++ b/strbuf.c
@@ -384,6 +384,17 @@ ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint)
 	return sb->len - oldlen;
 }
 
+ssize_t strbuf_read_once(struct strbuf *sb, int fd, size_t hint)
+{
+	ssize_t cnt;
+
+	strbuf_grow(sb, hint ? hint : 8192);
+	cnt = xread(fd, sb->buf + sb->len, sb->alloc - sb->len - 1);
+	if (cnt > 0)
+		strbuf_setlen(sb, sb->len + cnt);
+	return cnt;
+}
+
 #define STRBUF_MAXLINK (2*PATH_MAX)
 
 int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint)
diff --git a/strbuf.h b/strbuf.h
index 7123fca7af..2bf90e70fc 100644
--- a/strbuf.h
+++ b/strbuf.h
@@ -367,6 +367,14 @@ extern size_t strbuf_fread(struct strbuf *, size_t, FILE *);
 extern ssize_t strbuf_read(struct strbuf *, int fd, size_t hint);
 
 /**
+ * Read the contents of a given file descriptor partially by using only one
+ * attempt of xread. The third argument can be used to give a hint about the
+ * file size, to avoid reallocs. Returns the number of new bytes appended to
+ * the sb.
+ */
+extern ssize_t strbuf_read_once(struct strbuf *, int fd, size_t hint);
+
+/**
  * Read the contents of a file, specified by its path. The third argument
  * can be used to give a hint about the file size, to avoid reallocs.
  */
diff --git a/submodule.c b/submodule.c
index 14e76247bf..b83939c294 100644
--- a/submodule.c
+++ b/submodule.c
@@ -12,6 +12,7 @@
 #include "sha1-array.h"
 #include "argv-array.h"
 #include "blob.h"
+#include "thread-utils.h"
 
 static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND;
 static struct string_list changed_submodule_paths;
@@ -610,37 +611,28 @@ static void calculate_changed_submodule_paths(void)
 	initialized_fetch_ref_tips = 0;
 }
 
-int fetch_populated_submodules(const struct argv_array *options,
-			       const char *prefix, int command_line_option,
-			       int quiet)
+struct submodule_parallel_fetch {
+	int count;
+	struct argv_array args;
+	const char *work_tree;
+	const char *prefix;
+	int command_line_option;
+	int quiet;
+	int result;
+};
+#define SPF_INIT {0, ARGV_ARRAY_INIT, NULL, NULL, 0, 0, 0}
+
+static int get_next_submodule(struct child_process *cp,
+			      struct strbuf *err, void *data, void **task_cb)
 {
-	int i, result = 0;
-	struct child_process cp = CHILD_PROCESS_INIT;
-	struct argv_array argv = ARGV_ARRAY_INIT;
-	const char *work_tree = get_git_work_tree();
-	if (!work_tree)
-		goto out;
-
-	if (read_cache() < 0)
-		die("index file corrupt");
-
-	argv_array_push(&argv, "fetch");
-	for (i = 0; i < options->argc; i++)
-		argv_array_push(&argv, options->argv[i]);
-	argv_array_push(&argv, "--recurse-submodules-default");
-	/* default value, "--submodule-prefix" and its value are added later */
-
-	cp.env = local_repo_env;
-	cp.git_cmd = 1;
-	cp.no_stdin = 1;
-
-	calculate_changed_submodule_paths();
+	int ret = 0;
+	struct submodule_parallel_fetch *spf = data;
 
-	for (i = 0; i < active_nr; i++) {
+	for (; spf->count < active_nr; spf->count++) {
 		struct strbuf submodule_path = STRBUF_INIT;
 		struct strbuf submodule_git_dir = STRBUF_INIT;
 		struct strbuf submodule_prefix = STRBUF_INIT;
-		const struct cache_entry *ce = active_cache[i];
+		const struct cache_entry *ce = active_cache[spf->count];
 		const char *git_dir, *default_argv;
 		const struct submodule *submodule;
 
@@ -652,7 +644,7 @@ int fetch_populated_submodules(const struct argv_array *options,
 			submodule = submodule_from_name(null_sha1, ce->name);
 
 		default_argv = "yes";
-		if (command_line_option == RECURSE_SUBMODULES_DEFAULT) {
+		if (spf->command_line_option == RECURSE_SUBMODULES_DEFAULT) {
 			if (submodule &&
 			    submodule->fetch_recurse !=
 						RECURSE_SUBMODULES_NONE) {
@@ -675,40 +667,101 @@ int fetch_populated_submodules(const struct argv_array *options,
 					default_argv = "on-demand";
 				}
 			}
-		} else if (command_line_option == RECURSE_SUBMODULES_ON_DEMAND) {
+		} else if (spf->command_line_option == RECURSE_SUBMODULES_ON_DEMAND) {
 			if (!unsorted_string_list_lookup(&changed_submodule_paths, ce->name))
 				continue;
 			default_argv = "on-demand";
 		}
 
-		strbuf_addf(&submodule_path, "%s/%s", work_tree, ce->name);
+		strbuf_addf(&submodule_path, "%s/%s", spf->work_tree, ce->name);
 		strbuf_addf(&submodule_git_dir, "%s/.git", submodule_path.buf);
-		strbuf_addf(&submodule_prefix, "%s%s/", prefix, ce->name);
+		strbuf_addf(&submodule_prefix, "%s%s/", spf->prefix, ce->name);
 		git_dir = read_gitfile(submodule_git_dir.buf);
 		if (!git_dir)
 			git_dir = submodule_git_dir.buf;
 		if (is_directory(git_dir)) {
-			if (!quiet)
-				printf("Fetching submodule %s%s\n", prefix, ce->name);
-			cp.dir = submodule_path.buf;
-			argv_array_push(&argv, default_argv);
-			argv_array_push(&argv, "--submodule-prefix");
-			argv_array_push(&argv, submodule_prefix.buf);
-			cp.argv = argv.argv;
-			if (run_command(&cp))
-				result = 1;
-			argv_array_pop(&argv);
-			argv_array_pop(&argv);
-			argv_array_pop(&argv);
+			child_process_init(cp);
+			cp->dir = strbuf_detach(&submodule_path, NULL);
+			cp->env = local_repo_env;
+			cp->git_cmd = 1;
+			if (!spf->quiet)
+				strbuf_addf(err, "Fetching submodule %s%s\n",
+					    spf->prefix, ce->name);
+			argv_array_init(&cp->args);
+			argv_array_pushv(&cp->args, spf->args.argv);
+			argv_array_push(&cp->args, default_argv);
+			argv_array_push(&cp->args, "--submodule-prefix");
+			argv_array_push(&cp->args, submodule_prefix.buf);
+			ret = 1;
 		}
 		strbuf_release(&submodule_path);
 		strbuf_release(&submodule_git_dir);
 		strbuf_release(&submodule_prefix);
+		if (ret) {
+			spf->count++;
+			return 1;
+		}
 	}
-	argv_array_clear(&argv);
+	return 0;
+}
+
+static int fetch_start_failure(struct child_process *cp,
+			       struct strbuf *err,
+			       void *cb, void *task_cb)
+{
+	struct submodule_parallel_fetch *spf = cb;
+
+	spf->result = 1;
+
+	return 0;
+}
+
+static int fetch_finish(int retvalue, struct child_process *cp,
+			struct strbuf *err, void *cb, void *task_cb)
+{
+	struct submodule_parallel_fetch *spf = cb;
+
+	if (retvalue)
+		spf->result = 1;
+
+	return 0;
+}
+
+int fetch_populated_submodules(const struct argv_array *options,
+			       const char *prefix, int command_line_option,
+			       int quiet, int max_parallel_jobs)
+{
+	int i;
+	struct submodule_parallel_fetch spf = SPF_INIT;
+
+	spf.work_tree = get_git_work_tree();
+	spf.command_line_option = command_line_option;
+	spf.quiet = quiet;
+	spf.prefix = prefix;
+
+	if (!spf.work_tree)
+		goto out;
+
+	if (read_cache() < 0)
+		die("index file corrupt");
+
+	argv_array_push(&spf.args, "fetch");
+	for (i = 0; i < options->argc; i++)
+		argv_array_push(&spf.args, options->argv[i]);
+	argv_array_push(&spf.args, "--recurse-submodules-default");
+	/* default value, "--submodule-prefix" and its value are added later */
+
+	calculate_changed_submodule_paths();
+	run_processes_parallel(max_parallel_jobs,
+			       get_next_submodule,
+			       fetch_start_failure,
+			       fetch_finish,
+			       &spf);
+
+	argv_array_clear(&spf.args);
 out:
 	string_list_clear(&changed_submodule_paths, 1);
-	return result;
+	return spf.result;
 }
 
 unsigned is_submodule_modified(const char *path, int ignore_untracked)
diff --git a/submodule.h b/submodule.h
index ddff512109..e06eaa5ebb 100644
--- a/submodule.h
+++ b/submodule.h
@@ -32,7 +32,7 @@ void set_config_fetch_recurse_submodules(int value);
 void check_for_new_submodule_commits(unsigned char new_sha1[20]);
 int fetch_populated_submodules(const struct argv_array *options,
 			       const char *prefix, int command_line_option,
-			       int quiet);
+			       int quiet, int max_parallel_jobs);
 unsigned is_submodule_modified(const char *path, int ignore_untracked);
 int submodule_uses_gitfile(const char *path);
 int ok_to_remove_submodule(const char *path);
diff --git a/t/t0002-gitfile.sh b/t/t0002-gitfile.sh
index 9670e8cbe6..3afe0125c9 100755
--- a/t/t0002-gitfile.sh
+++ b/t/t0002-gitfile.sh
@@ -99,7 +99,7 @@ test_expect_success 'check rev-list' '
 	test "$SHA" = "$(git rev-list HEAD)"
 '
 
-test_expect_success 'setup_git_dir twice in subdir' '
+test_expect_failure 'setup_git_dir twice in subdir' '
 	git init sgd &&
 	(
 		cd sgd &&
diff --git a/t/t0061-run-command.sh b/t/t0061-run-command.sh
index 9acf628726..12228b4aa6 100755
--- a/t/t0061-run-command.sh
+++ b/t/t0061-run-command.sh
@@ -47,4 +47,57 @@ test_expect_success POSIXPERM,SANITY 'unreadable directory in PATH' '
 	test_cmp expect actual
 '
 
+cat >expect <<-EOF
+preloaded output of a child
+Hello
+World
+preloaded output of a child
+Hello
+World
+preloaded output of a child
+Hello
+World
+preloaded output of a child
+Hello
+World
+EOF
+
+test_expect_success 'run_command runs in parallel with more jobs available than tasks' '
+	test-run-command run-command-parallel 5 sh -c "printf \"%s\n%s\n\" Hello World" 2>actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'run_command runs in parallel with as many jobs as tasks' '
+	test-run-command run-command-parallel 4 sh -c "printf \"%s\n%s\n\" Hello World" 2>actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'run_command runs in parallel with more tasks than jobs available' '
+	test-run-command run-command-parallel 3 sh -c "printf \"%s\n%s\n\" Hello World" 2>actual &&
+	test_cmp expect actual
+'
+
+cat >expect <<-EOF
+preloaded output of a child
+asking for a quick stop
+preloaded output of a child
+asking for a quick stop
+preloaded output of a child
+asking for a quick stop
+EOF
+
+test_expect_success 'run_command is asked to abort gracefully' '
+	test-run-command run-command-abort 3 false 2>actual &&
+	test_cmp expect actual
+'
+
+cat >expect <<-EOF
+no further jobs available
+EOF
+
+test_expect_success 'run_command outputs ' '
+	test-run-command run-command-no-jobs 3 sh -c "printf \"%s\n%s\n\" Hello World" 2>actual &&
+	test_cmp expect actual
+'
+
 test_done
diff --git a/t/t5526-fetch-submodules.sh b/t/t5526-fetch-submodules.sh
index a4532b00d6..1241146227 100755
--- a/t/t5526-fetch-submodules.sh
+++ b/t/t5526-fetch-submodules.sh
@@ -16,7 +16,8 @@ add_upstream_commit() {
 		git add subfile &&
 		git commit -m new subfile &&
 		head2=$(git rev-parse --short HEAD) &&
-		echo "From $pwd/submodule" > ../expect.err &&
+		echo "Fetching submodule submodule" > ../expect.err &&
+		echo "From $pwd/submodule" >> ../expect.err &&
 		echo "   $head1..$head2  master     -> origin/master" >> ../expect.err
 	) &&
 	(
@@ -27,6 +28,7 @@ add_upstream_commit() {
 		git add deepsubfile &&
 		git commit -m new deepsubfile &&
 		head2=$(git rev-parse --short HEAD) &&
+		echo "Fetching submodule submodule/subdir/deepsubmodule" >> ../expect.err
 		echo "From $pwd/deepsubmodule" >> ../expect.err &&
 		echo "   $head1..$head2  master     -> origin/master" >> ../expect.err
 	)
@@ -56,9 +58,7 @@ test_expect_success setup '
 	(
 		cd downstream &&
 		git submodule update --init --recursive
-	) &&
-	echo "Fetching submodule submodule" > expect.out &&
-	echo "Fetching submodule submodule/subdir/deepsubmodule" >> expect.out
+	)
 '
 
 test_expect_success "fetch --recurse-submodules recurses into submodules" '
@@ -67,10 +67,21 @@ test_expect_success "fetch --recurse-submodules recurses into submodules" '
 		cd downstream &&
 		git fetch --recurse-submodules >../actual.out 2>../actual.err
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
+test_expect_success "fetch --recurse-submodules -j2 has the same output behaviour" '
+	add_upstream_commit &&
+	(
+		cd downstream &&
+		GIT_TRACE=$(pwd)/../trace.out git fetch --recurse-submodules -j2 2>../actual.err
+	) &&
+	test_must_be_empty actual.out &&
+	test_i18ncmp expect.err actual.err &&
+	grep "2 tasks" trace.out
+'
+
 test_expect_success "fetch alone only fetches superproject" '
 	add_upstream_commit &&
 	(
@@ -96,7 +107,7 @@ test_expect_success "using fetchRecurseSubmodules=true in .gitmodules recurses i
 		git config -f .gitmodules submodule.submodule.fetchRecurseSubmodules true &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
@@ -127,7 +138,7 @@ test_expect_success "--recurse-submodules overrides fetchRecurseSubmodules setti
 		git config --unset -f .gitmodules submodule.submodule.fetchRecurseSubmodules &&
 		git config --unset submodule.submodule.fetchRecurseSubmodules
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
@@ -140,13 +151,22 @@ test_expect_success "--quiet propagates to submodules" '
 	! test -s actual.err
 '
 
+test_expect_success "--quiet propagates to parallel submodules" '
+	(
+		cd downstream &&
+		git fetch --recurse-submodules -j 2 --quiet  >../actual.out 2>../actual.err
+	) &&
+	! test -s actual.out &&
+	! test -s actual.err
+'
+
 test_expect_success "--dry-run propagates to submodules" '
 	add_upstream_commit &&
 	(
 		cd downstream &&
 		git fetch --recurse-submodules --dry-run >../actual.out 2>../actual.err
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
@@ -155,7 +175,7 @@ test_expect_success "Without --dry-run propagates to submodules" '
 		cd downstream &&
 		git fetch --recurse-submodules >../actual.out 2>../actual.err
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
@@ -166,7 +186,7 @@ test_expect_success "recurseSubmodules=true propagates into submodules" '
 		git config fetch.recurseSubmodules true
 		git fetch >../actual.out 2>../actual.err
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
@@ -180,7 +200,7 @@ test_expect_success "--recurse-submodules overrides config in submodule" '
 		) &&
 		git fetch --recurse-submodules >../actual.out 2>../actual.err
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
@@ -214,16 +234,15 @@ test_expect_success "Recursion stops when no new submodule commits are fetched"
 	git add submodule &&
 	git commit -m "new submodule" &&
 	head2=$(git rev-parse --short HEAD) &&
-	echo "Fetching submodule submodule" > expect.out.sub &&
 	echo "From $pwd/." > expect.err.sub &&
 	echo "   $head1..$head2  master     -> origin/master" >>expect.err.sub &&
-	head -2 expect.err >> expect.err.sub &&
+	head -3 expect.err >> expect.err.sub &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
 	test_i18ncmp expect.err.sub actual.err &&
-	test_i18ncmp expect.out.sub actual.out
+	test_must_be_empty actual.out
 '
 
 test_expect_success "Recursion doesn't happen when new superproject commits don't change any submodules" '
@@ -269,7 +288,7 @@ test_expect_success "Recursion picks up config in submodule" '
 		)
 	) &&
 	test_i18ncmp expect.err.sub actual.err &&
-	test_i18ncmp expect.out actual.out
+	test_must_be_empty actual.out
 '
 
 test_expect_success "Recursion picks up all submodules when necessary" '
@@ -285,7 +304,8 @@ test_expect_success "Recursion picks up all submodules when necessary" '
 		git add subdir/deepsubmodule &&
 		git commit -m "new deepsubmodule"
 		head2=$(git rev-parse --short HEAD) &&
-		echo "From $pwd/submodule" > ../expect.err.sub &&
+		echo "Fetching submodule submodule" > ../expect.err.sub &&
+		echo "From $pwd/submodule" >> ../expect.err.sub &&
 		echo "   $head1..$head2  master     -> origin/master" >> ../expect.err.sub
 	) &&
 	head1=$(git rev-parse --short HEAD) &&
@@ -295,13 +315,13 @@ test_expect_success "Recursion picks up all submodules when necessary" '
 	echo "From $pwd/." > expect.err.2 &&
 	echo "   $head1..$head2  master     -> origin/master" >> expect.err.2 &&
 	cat expect.err.sub >> expect.err.2 &&
-	tail -2 expect.err >> expect.err.2 &&
+	tail -3 expect.err >> expect.err.2 &&
 	(
 		cd downstream &&
 		git fetch >../actual.out 2>../actual.err
 	) &&
 	test_i18ncmp expect.err.2 actual.err &&
-	test_i18ncmp expect.out actual.out
+	test_must_be_empty actual.out
 '
 
 test_expect_success "'--recurse-submodules=on-demand' doesn't recurse when no new commits are fetched in the superproject (and ignores config)" '
@@ -317,7 +337,8 @@ test_expect_success "'--recurse-submodules=on-demand' doesn't recurse when no ne
 		git add subdir/deepsubmodule &&
 		git commit -m "new deepsubmodule" &&
 		head2=$(git rev-parse --short HEAD) &&
-		echo "From $pwd/submodule" > ../expect.err.sub &&
+		echo Fetching submodule submodule > ../expect.err.sub &&
+		echo "From $pwd/submodule" >> ../expect.err.sub &&
 		echo "   $head1..$head2  master     -> origin/master" >> ../expect.err.sub
 	) &&
 	(
@@ -335,7 +356,7 @@ test_expect_success "'--recurse-submodules=on-demand' recurses as deep as necess
 	git add submodule &&
 	git commit -m "new submodule" &&
 	head2=$(git rev-parse --short HEAD) &&
-	tail -2 expect.err > expect.err.deepsub &&
+	tail -3 expect.err > expect.err.deepsub &&
 	echo "From $pwd/." > expect.err &&
 	echo "   $head1..$head2  master     -> origin/master" >>expect.err &&
 	cat expect.err.sub >> expect.err &&
@@ -354,7 +375,7 @@ test_expect_success "'--recurse-submodules=on-demand' recurses as deep as necess
 			git config --unset -f .gitmodules submodule.subdir/deepsubmodule.fetchRecursive
 		)
 	) &&
-	test_i18ncmp expect.out actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err actual.err
 '
 
@@ -388,7 +409,7 @@ test_expect_success "'fetch.recurseSubmodules=on-demand' overrides global config
 	head2=$(git rev-parse --short HEAD) &&
 	echo "From $pwd/." > expect.err.2 &&
 	echo "   $head1..$head2  master     -> origin/master" >>expect.err.2 &&
-	head -2 expect.err >> expect.err.2 &&
+	head -3 expect.err >> expect.err.2 &&
 	(
 		cd downstream &&
 		git config fetch.recurseSubmodules on-demand &&
@@ -399,7 +420,7 @@ test_expect_success "'fetch.recurseSubmodules=on-demand' overrides global config
 		cd downstream &&
 		git config --unset fetch.recurseSubmodules
 	) &&
-	test_i18ncmp expect.out.sub actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err.2 actual.err
 '
 
@@ -416,7 +437,7 @@ test_expect_success "'submodule.<sub>.fetchRecurseSubmodules=on-demand' override
 	head2=$(git rev-parse --short HEAD) &&
 	echo "From $pwd/." > expect.err.2 &&
 	echo "   $head1..$head2  master     -> origin/master" >>expect.err.2 &&
-	head -2 expect.err >> expect.err.2 &&
+	head -3 expect.err >> expect.err.2 &&
 	(
 		cd downstream &&
 		git config submodule.submodule.fetchRecurseSubmodules on-demand &&
@@ -427,7 +448,7 @@ test_expect_success "'submodule.<sub>.fetchRecurseSubmodules=on-demand' override
 		cd downstream &&
 		git config --unset submodule.submodule.fetchRecurseSubmodules
 	) &&
-	test_i18ncmp expect.out.sub actual.out &&
+	test_must_be_empty actual.out &&
 	test_i18ncmp expect.err.2 actual.err
 '
 
diff --git a/test-run-command.c b/test-run-command.c
index 89c7de2c60..fbe0a27ef3 100644
--- a/test-run-command.c
+++ b/test-run-command.c
@@ -10,16 +10,54 @@
 
 #include "git-compat-util.h"
 #include "run-command.h"
+#include "argv-array.h"
+#include "strbuf.h"
 #include <string.h>
 #include <errno.h>
 
+static int number_callbacks;
+static int parallel_next(struct child_process *cp,
+			 struct strbuf *err,
+			 void *cb,
+			 void **task_cb)
+{
+	struct child_process *d = cb;
+	if (number_callbacks >= 4)
+		return 0;
+
+	argv_array_pushv(&cp->args, d->argv);
+	strbuf_addf(err, "preloaded output of a child\n");
+	number_callbacks++;
+	return 1;
+}
+
+static int no_job(struct child_process *cp,
+		  struct strbuf *err,
+		  void *cb,
+		  void **task_cb)
+{
+	strbuf_addf(err, "no further jobs available\n");
+	return 0;
+}
+
+static int task_finished(int result,
+			 struct child_process *cp,
+			 struct strbuf *err,
+			 void *pp_cb,
+			 void *pp_task_cb)
+{
+	strbuf_addf(err, "asking for a quick stop\n");
+	return 1;
+}
+
 int main(int argc, char **argv)
 {
 	struct child_process proc = CHILD_PROCESS_INIT;
+	int jobs;
 
 	if (argc < 3)
 		return 1;
-	proc.argv = (const char **)argv+2;
+	proc.argv = (const char **)argv + 2;
 
 	if (!strcmp(argv[1], "start-command-ENOENT")) {
 		if (start_command(&proc) < 0 && errno == ENOENT)
@@ -30,6 +68,21 @@ int main(int argc, char **argv)
 	if (!strcmp(argv[1], "run-command"))
 		exit(run_command(&proc));
 
+	jobs = atoi(argv[2]);
+	proc.argv = (const char **)argv + 3;
+
+	if (!strcmp(argv[1], "run-command-parallel"))
+		exit(run_processes_parallel(jobs, parallel_next,
+					    NULL, NULL, &proc));
+
+	if (!strcmp(argv[1], "run-command-abort"))
+		exit(run_processes_parallel(jobs, parallel_next,
+					    NULL, task_finished, &proc));
+
+	if (!strcmp(argv[1], "run-command-no-jobs"))
+		exit(run_processes_parallel(jobs, no_job,
+					    NULL, task_finished, &proc));
+
 	fprintf(stderr, "check usage\n");
 	return 1;
 }
diff --git a/wrapper.c b/wrapper.c
index c95e2906b8..b43d437630 100644
--- a/wrapper.c
+++ b/wrapper.c
@@ -236,8 +236,24 @@ ssize_t xread(int fd, void *buf, size_t len)
 	    len = MAX_IO_SIZE;
 	while (1) {
 		nr = read(fd, buf, len);
-		if ((nr < 0) && (errno == EAGAIN || errno == EINTR))
-			continue;
+		if (nr < 0) {
+			if (errno == EINTR)
+				continue;
+			if (errno == EAGAIN || errno == EWOULDBLOCK) {
+				struct pollfd pfd;
+				pfd.events = POLLIN;
+				pfd.fd = fd;
+				/*
+				 * it is OK if this poll() failed; we
+				 * want to leave this infinite loop
+				 * only when read() returns with
+				 * success, or an expected failure,
+				 * which would be checked by the next
+				 * call to read(2).
+				 */
+				poll(&pfd, 1, -1);
+			}
+		}
 		return nr;
 	}
 }