Merge branch 'mt/parallel-checkout-part-3'

The final part of "parallel checkout".

* mt/parallel-checkout-part-3:
  ci: run test round with parallel-checkout enabled
  parallel-checkout: add tests related to .gitattributes
  t0028: extract encoding helpers to lib-encoding.sh
  parallel-checkout: add tests related to path collisions
  parallel-checkout: add tests for basic operations
  checkout-index: add parallel checkout support
  builtin/checkout.c: complete parallel checkout support
  make_transient_cache_entry(): optionally alloc from mem_pool

builtin/checkout--worker.c

@@ -39,7 +39,7 @@ static void packet_to_pc_item(const char *buffer, int len,
 	}
 
 	memset(pc_item, 0, sizeof(*pc_item));
-	pc_item->ce = make_empty_transient_cache_entry(fixed_portion->name_len);
+	pc_item->ce = make_empty_transient_cache_entry(fixed_portion->name_len, NULL);
 	pc_item->ce->ce_namelen = fixed_portion->name_len;
 	pc_item->ce->ce_mode = fixed_portion->ce_mode;
 	memcpy(pc_item->ce->name, variant, pc_item->ce->ce_namelen);

builtin/checkout-index.c

@@ -12,6 +12,7 @@
 #include "cache-tree.h"
 #include "parse-options.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 #define CHECKOUT_ALL 4
 static int nul_term_line;
@@ -115,7 +116,7 @@ static int checkout_file(const char *name, const char *prefix)
 	return -1;
 }
 
-static void checkout_all(const char *prefix, int prefix_length)
+static int checkout_all(const char *prefix, int prefix_length)
 {
 	int i, errs = 0;
 	struct cache_entry *last_ce = NULL;
@@ -144,11 +145,7 @@ static void checkout_all(const char *prefix, int prefix_length)
 	}
 	if (last_ce && to_tempfile)
 		write_tempfile_record(last_ce->name, prefix);
-	if (errs)
-		/* we have already done our error reporting.
-		 * exit with the same code as die().
-		 */
-		exit(128);
+	return !!errs;
 }
 
 static const char * const builtin_checkout_index_usage[] = {
@@ -184,6 +181,7 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 	int force = 0, quiet = 0, not_new = 0;
 	int index_opt = 0;
 	int err = 0;
+	int pc_workers, pc_threshold;
 	struct option builtin_checkout_index_options[] = {
 		OPT_BOOL('a', "all", &all,
 			N_("check out all files in the index")),
@@ -238,6 +236,10 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 		hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
 	}
 
+	get_parallel_checkout_configs(&pc_workers, &pc_threshold);
+	if (pc_workers > 1)
+		init_parallel_checkout();
+
 	/* Check out named files first */
 	for (i = 0; i < argc; i++) {
 		const char *arg = argv[i];
@@ -277,12 +279,16 @@ int cmd_checkout_index(int argc, const char **argv, const char *prefix)
 		strbuf_release(&buf);
 	}
 
+	if (all)
+		err |= checkout_all(prefix, prefix_length);
+
+	if (pc_workers > 1)
+		err |= run_parallel_checkout(&state, pc_workers, pc_threshold,
+					     NULL, NULL);
+
 	if (err)
 		return 1;
 
-	if (all)
-		checkout_all(prefix, prefix_length);
-
 	if (is_lock_file_locked(&lock_file) &&
 	    write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 		die("Unable to write new index file");

builtin/checkout.c

@@ -27,6 +27,7 @@
 #include "wt-status.h"
 #include "xdiff-interface.h"
 #include "entry.h"
+#include "parallel-checkout.h"
 
 static const char * const checkout_usage[] = {
 	N_("git checkout [<options>] <branch>"),
@@ -230,7 +231,8 @@ static int checkout_stage(int stage, const struct cache_entry *ce, int pos,
 		return error(_("path '%s' does not have their version"), ce->name);
 }
 
-static int checkout_merged(int pos, const struct checkout *state, int *nr_checkouts)
+static int checkout_merged(int pos, const struct checkout *state,
+			   int *nr_checkouts, struct mem_pool *ce_mem_pool)
 {
 	struct cache_entry *ce = active_cache[pos];
 	const char *path = ce->name;
@@ -291,11 +293,10 @@ static int checkout_merged(int pos, const struct checkout *state, int *nr_checko
 	if (write_object_file(result_buf.ptr, result_buf.size, blob_type, &oid))
 		die(_("Unable to add merge result for '%s'"), path);
 	free(result_buf.ptr);
-	ce = make_transient_cache_entry(mode, &oid, path, 2);
+	ce = make_transient_cache_entry(mode, &oid, path, 2, ce_mem_pool);
 	if (!ce)
 		die(_("make_cache_entry failed for path '%s'"), path);
 	status = checkout_entry(ce, state, NULL, nr_checkouts);
-	discard_cache_entry(ce);
 	return status;
 }
 
@@ -359,19 +360,27 @@ static int checkout_worktree(const struct checkout_opts *opts,
 	int nr_checkouts = 0, nr_unmerged = 0;
 	int errs = 0;
 	int pos;
+	int pc_workers, pc_threshold;
+	struct mem_pool ce_mem_pool;
 
 	state.force = 1;
 	state.refresh_cache = 1;
 	state.istate = &the_index;
 
+	mem_pool_init(&ce_mem_pool, 0);
+	get_parallel_checkout_configs(&pc_workers, &pc_threshold);
 	init_checkout_metadata(&state.meta, info->refname,
 			       info->commit ? &info->commit->object.oid : &info->oid,
 			       NULL);
 
 	enable_delayed_checkout(&state);
 
+	if (pc_workers > 1)
+		init_parallel_checkout();
+
 	/* TODO: audit for interaction with sparse-index. */
 	ensure_full_index(&the_index);
+
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
 		if (ce->ce_flags & CE_MATCHED) {
@@ -387,10 +396,15 @@ static int checkout_worktree(const struct checkout_opts *opts,
 						       &nr_checkouts, opts->overlay_mode);
 			else if (opts->merge)
 				errs |= checkout_merged(pos, &state,
-							&nr_unmerged);
+							&nr_unmerged,
+							&ce_mem_pool);
 			pos = skip_same_name(ce, pos) - 1;
 		}
 	}
+	if (pc_workers > 1)
+		errs |= run_parallel_checkout(&state, pc_workers, pc_threshold,
+					      NULL, NULL);
+	mem_pool_discard(&ce_mem_pool, should_validate_cache_entries());
 	remove_marked_cache_entries(&the_index, 1);
 	remove_scheduled_dirs();
 	errs |= finish_delayed_checkout(&state, &nr_checkouts);

builtin/difftool.c

@@ -323,7 +323,7 @@ static int checkout_path(unsigned mode, struct object_id *oid,
 	struct cache_entry *ce;
 	int ret;
 
-	ce = make_transient_cache_entry(mode, oid, path, 0);
+	ce = make_transient_cache_entry(mode, oid, path, 0, NULL);
 	ret = checkout_entry(ce, state, NULL, NULL);
 
 	discard_cache_entry(ce);

cache.h

@@ -370,16 +370,20 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate,
 					   size_t name_len);
 
 /*
- * Create a cache_entry that is not intended to be added to an index.
- * Caller is responsible for discarding the cache_entry
- * with `discard_cache_entry`.
+ * Create a cache_entry that is not intended to be added to an index. If
+ * `ce_mem_pool` is not NULL, the entry is allocated within the given memory
+ * pool. Caller is responsible for discarding "loose" entries with
+ * `discard_cache_entry()` and the memory pool with
+ * `mem_pool_discard(ce_mem_pool, should_validate_cache_entries())`.
  */
 struct cache_entry *make_transient_cache_entry(unsigned int mode,
 					       const struct object_id *oid,
 					       const char *path,
-					       int stage);
+					       int stage,
+					       struct mem_pool *ce_mem_pool);
 
-struct cache_entry *make_empty_transient_cache_entry(size_t name_len);
+struct cache_entry *make_empty_transient_cache_entry(size_t len,
+						     struct mem_pool *ce_mem_pool);
 
 /*
  * Discard cache entry.

ci/run-build-and-tests.sh

@@ -26,6 +26,7 @@ linux-gcc)
 	export GIT_TEST_ADD_I_USE_BUILTIN=1
 	export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master
 	export GIT_TEST_WRITE_REV_INDEX=1
+	export GIT_TEST_CHECKOUT_WORKERS=2
 	make test
 	;;
 linux-clang)

parallel-checkout.c

@@ -8,6 +8,7 @@
 #include "sigchain.h"
 #include "streaming.h"
 #include "thread-utils.h"
+#include "trace2.h"
 
 struct pc_worker {
 	struct child_process cp;
@@ -34,6 +35,20 @@ static const int DEFAULT_NUM_WORKERS = 1;
 
 void get_parallel_checkout_configs(int *num_workers, int *threshold)
 {
+	char *env_workers = getenv("GIT_TEST_CHECKOUT_WORKERS");
+
+	if (env_workers && *env_workers) {
+		if (strtol_i(env_workers, 10, num_workers)) {
+			die("invalid value for GIT_TEST_CHECKOUT_WORKERS: '%s'",
+			    env_workers);
+		}
+		if (*num_workers < 1)
+			*num_workers = online_cpus();
+
+		*threshold = 0;
+		return;
+	}
+
 	if (git_config_get_int("checkout.workers", num_workers))
 		*num_workers = DEFAULT_NUM_WORKERS;
 	else if (*num_workers < 1)
@@ -326,6 +341,7 @@ void write_pc_item(struct parallel_checkout_item *pc_item,
 	if (dir_sep && !has_dirs_only_path(path.buf, dir_sep - path.buf,
 					   state->base_dir_len)) {
 		pc_item->status = PC_ITEM_COLLIDED;
+		trace2_data_string("pcheckout", NULL, "collision/dirname", path.buf);
 		goto out;
 	}
 
@@ -341,6 +357,8 @@ void write_pc_item(struct parallel_checkout_item *pc_item,
 			 * call should have already caught these cases.
 			 */
 			pc_item->status = PC_ITEM_COLLIDED;
+			trace2_data_string("pcheckout", NULL,
+					   "collision/basename", path.buf);
 		} else {
 			error_errno("failed to open file '%s'", path.buf);
 			pc_item->status = PC_ITEM_FAILED;

read-cache.c

@@ -839,8 +839,11 @@ struct cache_entry *make_empty_cache_entry(struct index_state *istate, size_t le
 	return mem_pool__ce_calloc(find_mem_pool(istate), len);
 }
 
-struct cache_entry *make_empty_transient_cache_entry(size_t len)
+struct cache_entry *make_empty_transient_cache_entry(size_t len,
+						     struct mem_pool *ce_mem_pool)
 {
+	if (ce_mem_pool)
+		return mem_pool__ce_calloc(ce_mem_pool, len);
 	return xcalloc(1, cache_entry_size(len));
 }
 
@@ -874,8 +877,11 @@ struct cache_entry *make_cache_entry(struct index_state *istate,
 	return ret;
 }
 
-struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct object_id *oid,
-					       const char *path, int stage)
+struct cache_entry *make_transient_cache_entry(unsigned int mode,
+					       const struct object_id *oid,
+					       const char *path,
+					       int stage,
+					       struct mem_pool *ce_mem_pool)
 {
 	struct cache_entry *ce;
 	int len;
@@ -886,7 +892,7 @@ struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct o
 	}
 
 	len = strlen(path);
-	ce = make_empty_transient_cache_entry(len);
+	ce = make_empty_transient_cache_entry(len, ce_mem_pool);
 
 	oidcpy(&ce->oid, oid);
 	memcpy(ce->name, path, len);

t/README

@@ -439,6 +439,10 @@ GIT_TEST_WRITE_REV_INDEX=<boolean>, when true enables the
 GIT_TEST_SPARSE_INDEX=<boolean>, when true enables index writes to use the
 sparse-index format by default.
 
+GIT_TEST_CHECKOUT_WORKERS=<n> overrides the 'checkout.workers' setting
+to <n> and 'checkout.thresholdForParallelism' to 0, forcing the
+execution of the parallel-checkout code.
+
 Naming Tests
 ------------
 

t/lib-encoding.sh

@@ -0,0 +1,25 @@
+# Encoding helpers
+
+test_lazy_prereq NO_UTF16_BOM '
+	test $(printf abc | iconv -f UTF-8 -t UTF-16 | wc -c) = 6
+'
+
+test_lazy_prereq NO_UTF32_BOM '
+	test $(printf abc | iconv -f UTF-8 -t UTF-32 | wc -c) = 12
+'
+
+write_utf16 () {
+	if test_have_prereq NO_UTF16_BOM
+	then
+		printf '\376\377'
+	fi &&
+	iconv -f UTF-8 -t UTF-16
+}
+
+write_utf32 () {
+	if test_have_prereq NO_UTF32_BOM
+	then
+		printf '\0\0\376\377'
+	fi &&
+	iconv -f UTF-8 -t UTF-32
+}

t/lib-parallel-checkout.sh

@@ -0,0 +1,45 @@
+# Helpers for tests invoking parallel-checkout
+
+# Parallel checkout tests need full control of the number of workers
+unset GIT_TEST_CHECKOUT_WORKERS
+
+set_checkout_config () {
+	if test $# -ne 2
+	then
+		BUG "usage: set_checkout_config <workers> <threshold>"
+	fi &&
+
+	test_config_global checkout.workers $1 &&
+	test_config_global checkout.thresholdForParallelism $2
+}
+
+# Run "${@:2}" and check that $1 checkout workers were used
+test_checkout_workers () {
+	if test $# -lt 2
+	then
+		BUG "too few arguments to test_checkout_workers"
+	fi &&
+
+	local expected_workers=$1 &&
+	shift &&
+
+	local trace_file=trace-test-checkout-workers &&
+	rm -f "$trace_file" &&
+	GIT_TRACE2="$(pwd)/$trace_file" "$@" 2>&8 &&
+
+	local workers=$(grep "child_start\[..*\] git checkout--worker" "$trace_file" | wc -l) &&
+	test $workers -eq $expected_workers &&
+	rm "$trace_file"
+} 8>&2 2>&4
+
+# Verify that both the working tree and the index were created correctly
+verify_checkout () {
+	if test $# -ne 1
+	then
+		BUG "usage: verify_checkout <repository path>"
+	fi &&
+
+	git -C "$1" diff-index --ignore-submodules=none --exit-code HEAD -- &&
+	git -C "$1" status --porcelain >"$1".status &&
+	test_must_be_empty "$1".status
+}

t/t0028-working-tree-encoding.sh

@@ -6,33 +6,10 @@ GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
 export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-encoding.sh"
 
 GIT_TRACE_WORKING_TREE_ENCODING=1 && export GIT_TRACE_WORKING_TREE_ENCODING
 
-test_lazy_prereq NO_UTF16_BOM '
-	test $(printf abc | iconv -f UTF-8 -t UTF-16 | wc -c) = 6
-'
-
-test_lazy_prereq NO_UTF32_BOM '
-	test $(printf abc | iconv -f UTF-8 -t UTF-32 | wc -c) = 12
-'
-
-write_utf16 () {
-	if test_have_prereq NO_UTF16_BOM
-	then
-		printf '\376\377'
-	fi &&
-	iconv -f UTF-8 -t UTF-16
-}
-
-write_utf32 () {
-	if test_have_prereq NO_UTF32_BOM
-	then
-		printf '\0\0\376\377'
-	fi &&
-	iconv -f UTF-8 -t UTF-32
-}
-
 test_expect_success 'setup test files' '
 	git config core.eol lf &&