Merge branch 'ps/reftable-concurrent-writes'

Give timeout to the locking code to write to reftable.

* ps/reftable-concurrent-writes:
  refs/reftable: reload locked stack when preparing transaction
  reftable/stack: allow locking of outdated stacks
  refs/reftable: introduce "reftable.lockTimeout"

Author: gitster

Documentation/config/reftable.txt

@@ -46,3 +46,11 @@ reftable.geometricFactor::
 By default, the geometric sequence uses a factor of 2, meaning that for any
 table, the next-biggest table must at least be twice as big. A maximum factor
 of 256 is supported.
+
+reftable.lockTimeout::
+	Whenever the reftable backend appends a new table to the stack, it has
+	to lock the central "tables.list" file before updating it. This config
+	controls how long the process will wait to acquire the lock in case
+	another process has already acquired it. Value 0 means not to retry at
+	all; -1 means to try indefinitely. Default is 100 (i.e., retry for
+	100ms).

refs/reftable-backend.c

@@ -260,6 +260,13 @@ static int reftable_be_config(const char *var, const char *value,
 		if (factor > UINT8_MAX)
 			die("reftable geometric factor cannot exceed %u", (unsigned)UINT8_MAX);
 		opts->auto_compaction_factor = factor;
+	} else if (!strcmp(var, "reftable.locktimeout")) {
+		int64_t lock_timeout = git_config_int64(var, value, ctx->kvi);
+		if (lock_timeout > LONG_MAX)
+			die("reftable lock timeout cannot exceed %"PRIdMAX, (intmax_t)LONG_MAX);
+		if (lock_timeout < 0 && lock_timeout != -1)
+			die("reftable lock timeout does not support negative values other than -1");
+		opts->lock_timeout_ms = lock_timeout;
 	}
 
 	return 0;
@@ -286,6 +293,7 @@ static struct ref_store *reftable_be_init(struct repository *repo,
 	refs->write_options.default_permissions = calc_shared_perm(0666 & ~mask);
 	refs->write_options.disable_auto_compact =
 		!git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1);
+	refs->write_options.lock_timeout_ms = 100;
 
 	git_config(reftable_be_config, &refs->write_options);
 
@@ -893,7 +901,8 @@ static int prepare_transaction_update(struct write_transaction_table_arg **out,
 		if (ret)
 			return ret;
 
-		ret = reftable_stack_new_addition(&addition, stack);
+		ret = reftable_stack_new_addition(&addition, stack,
+						  REFTABLE_STACK_NEW_ADDITION_RELOAD);
 		if (ret) {
 			if (ret == REFTABLE_LOCK_ERROR)
 				strbuf_addstr(err, "cannot lock references");
@@ -2330,7 +2339,7 @@ static int reftable_be_reflog_expire(struct ref_store *ref_store,
 	if (ret < 0)
 		goto done;
 
-	ret = reftable_stack_new_addition(&add, stack);
+	ret = reftable_stack_new_addition(&add, stack, 0);
 	if (ret < 0)
 		goto done;
 

reftable/reftable-stack.h

@@ -37,12 +37,21 @@ uint64_t reftable_stack_next_update_index(struct reftable_stack *st);
 /* holds a transaction to add tables at the top of a stack. */
 struct reftable_addition;
 
+enum {
+	/*
+	 * Reload the stack when the stack is out-of-date after locking it.
+	 */
+	REFTABLE_STACK_NEW_ADDITION_RELOAD = (1 << 0),
+};
+
 /*
  * returns a new transaction to add reftables to the given stack. As a side
- * effect, the ref database is locked.
+ * effect, the ref database is locked. Accepts REFTABLE_STACK_NEW_ADDITION_*
+ * flags.
  */
 int reftable_stack_new_addition(struct reftable_addition **dest,
-				struct reftable_stack *st);
+				struct reftable_stack *st,
+				unsigned int flags);
 
 /* Adds a reftable to transaction. */
 int reftable_addition_add(struct reftable_addition *add,

reftable/reftable-writer.h

@@ -51,6 +51,17 @@ struct reftable_write_options {
 	 * tables to compact. Defaults to 2 if unset.
 	 */
 	uint8_t auto_compaction_factor;
+
+	/*
+	 * The number of milliseconds to wait when trying to lock "tables.list".
+	 * Note that this does not apply to locking individual tables, as these
+	 * should only ever be locked when already holding the "tables.list"
+	 * lock.
+	 *
+	 * Passing 0 will fail immediately when the file is locked, passing a
+	 * negative value will cause us to block indefinitely.
+	 */
+	long lock_timeout_ms;
 };
 
 /* reftable_block_stats holds statistics for a single block type */

reftable/stack.c

@@ -596,15 +596,18 @@ struct reftable_addition {
 #define REFTABLE_ADDITION_INIT {0}
 
 static int reftable_stack_init_addition(struct reftable_addition *add,
-					struct reftable_stack *st)
+					struct reftable_stack *st,
+					unsigned int flags)
 {
 	struct strbuf lock_file_name = STRBUF_INIT;
 	int err;
 
 	add->stack = st;
 
-	err = hold_lock_file_for_update(&add->tables_list_lock, st->list_file,
-					LOCK_NO_DEREF);
+	err = hold_lock_file_for_update_timeout(&add->tables_list_lock,
+						st->list_file,
+						LOCK_NO_DEREF,
+						st->opts.lock_timeout_ms);
 	if (err < 0) {
 		if (errno == EEXIST) {
 			err = REFTABLE_LOCK_ERROR;
@@ -624,16 +627,20 @@ static int reftable_stack_init_addition(struct reftable_addition *add,
 	err = stack_uptodate(st);
 	if (err < 0)
 		goto done;
+	if (err > 0 && flags & REFTABLE_STACK_NEW_ADDITION_RELOAD) {
+		err = reftable_stack_reload_maybe_reuse(add->stack, 1);
+		if (err)
+			goto done;
+	}
 	if (err > 0) {
 		err = REFTABLE_OUTDATED_ERROR;
 		goto done;
 	}
 
 	add->next_update_index = reftable_stack_next_update_index(st);
 done:
-	if (err) {
+	if (err)
 		reftable_addition_close(add);
-	}
 	strbuf_release(&lock_file_name);
 	return err;
 }
@@ -737,13 +744,14 @@ int reftable_addition_commit(struct reftable_addition *add)
 }
 
 int reftable_stack_new_addition(struct reftable_addition **dest,
-				struct reftable_stack *st)
+				struct reftable_stack *st,
+				unsigned int flags)
 {
 	int err = 0;
 	struct reftable_addition empty = REFTABLE_ADDITION_INIT;
 	REFTABLE_CALLOC_ARRAY(*dest, 1);
 	**dest = empty;
-	err = reftable_stack_init_addition(*dest, st);
+	err = reftable_stack_init_addition(*dest, st, flags);
 	if (err) {
 		reftable_free(*dest);
 		*dest = NULL;
@@ -757,7 +765,7 @@ static int stack_try_add(struct reftable_stack *st,
 			 void *arg)
 {
 	struct reftable_addition add = REFTABLE_ADDITION_INIT;
-	int err = reftable_stack_init_addition(&add, st);
+	int err = reftable_stack_init_addition(&add, st, 0);
 	if (err < 0)
 		goto done;
 
@@ -1056,8 +1064,10 @@ static int stack_compact_range(struct reftable_stack *st,
 	 * Hold the lock so that we can read "tables.list" and lock all tables
 	 * which are part of the user-specified range.
 	 */
-	err = hold_lock_file_for_update(&tables_list_lock, st->list_file,
-					LOCK_NO_DEREF);
+	err = hold_lock_file_for_update_timeout(&tables_list_lock,
+						st->list_file,
+						LOCK_NO_DEREF,
+						st->opts.lock_timeout_ms);
 	if (err < 0) {
 		if (errno == EEXIST)
 			err = REFTABLE_LOCK_ERROR;
@@ -1156,8 +1166,10 @@ static int stack_compact_range(struct reftable_stack *st,
 	 * "tables.list". We'll then replace the compacted range of tables with
 	 * the new table.
 	 */
-	err = hold_lock_file_for_update(&tables_list_lock, st->list_file,
-					LOCK_NO_DEREF);
+	err = hold_lock_file_for_update_timeout(&tables_list_lock,
+						st->list_file,
+						LOCK_NO_DEREF,
+						st->opts.lock_timeout_ms);
 	if (err < 0) {
 		if (errno == EEXIST)
 			err = REFTABLE_LOCK_ERROR;
@@ -1602,7 +1614,7 @@ static int reftable_stack_clean_locked(struct reftable_stack *st)
 int reftable_stack_clean(struct reftable_stack *st)
 {
 	struct reftable_addition *add = NULL;
-	int err = reftable_stack_new_addition(&add, st);
+	int err = reftable_stack_new_addition(&add, st, 0);
 	if (err < 0) {
 		goto done;
 	}

t/t0610-reftable-basics.sh

@@ -423,6 +423,64 @@ test_expect_success 'ref transaction: fails gracefully when auto compaction fail
 	)
 '
 
+test_expect_success 'ref transaction: timeout acquiring tables.list lock' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit initial &&
+		>.git/reftable/tables.list.lock &&
+		test_must_fail git update-ref refs/heads/branch HEAD 2>err &&
+		test_grep "cannot lock references" err
+	)
+'
+
+test_expect_success 'ref transaction: retry acquiring tables.list lock' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit initial &&
+		LOCK=.git/reftable/tables.list.lock &&
+		>$LOCK &&
+		{
+			( sleep 1 && rm -f $LOCK ) &
+		} &&
+		git -c reftable.lockTimeout=5000 update-ref refs/heads/branch HEAD
+	)
+'
+
+test_expect_success 'ref transaction: many concurrent writers' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		# Set a high timeout such that a busy CI machine will not abort
+		# early. 10 seconds should hopefully be ample of time to make
+		# this non-flaky.
+		git config set reftable.lockTimeout 10000 &&
+		test_commit --no-tag initial &&
+
+		head=$(git rev-parse HEAD) &&
+		for i in $(test_seq 100)
+		do
+			printf "%s commit\trefs/heads/branch-%s\n" "$head" "$i" ||
+			return 1
+		done >expect &&
+		printf "%s commit\trefs/heads/main\n" "$head" >>expect &&
+
+		for i in $(test_seq 100)
+		do
+			{ git update-ref refs/heads/branch-$i HEAD& } ||
+			return 1
+		done &&
+
+		wait &&
+		git for-each-ref --sort=v:refname >actual &&
+		test_cmp expect actual
+	)
+'
+
 test_expect_success 'pack-refs: compacts tables' '
 	test_when_finished "rm -rf repo" &&
 	git init repo &&

t/unit-tests/t-reftable-stack.c

@@ -267,7 +267,7 @@ static void t_reftable_stack_transaction_api(void)
 
 	reftable_addition_destroy(add);
 
-	err = reftable_stack_new_addition(&add, st);
+	err = reftable_stack_new_addition(&add, st, 0);
 	check(!err);
 
 	err = reftable_addition_add(add, write_test_ref, &ref);
@@ -288,6 +288,68 @@ static void t_reftable_stack_transaction_api(void)
 	clear_dir(dir);
 }
 
+static void t_reftable_stack_transaction_with_reload(void)
+{
+	char *dir = get_tmp_dir(__LINE__);
+	struct reftable_stack *st1 = NULL, *st2 = NULL;
+	int err;
+	struct reftable_addition *add = NULL;
+	struct reftable_ref_record refs[2] = {
+		{
+			.refname = (char *) "refs/heads/a",
+			.update_index = 1,
+			.value_type = REFTABLE_REF_VAL1,
+			.value.val1 = { '1' },
+		},
+		{
+			.refname = (char *) "refs/heads/b",
+			.update_index = 2,
+			.value_type = REFTABLE_REF_VAL1,
+			.value.val1 = { '1' },
+		},
+	};
+	struct reftable_ref_record ref = { 0 };
+
+	err = reftable_new_stack(&st1, dir, NULL);
+	check(!err);
+	err = reftable_new_stack(&st2, dir, NULL);
+	check(!err);
+
+	err = reftable_stack_new_addition(&add, st1, 0);
+	check(!err);
+	err = reftable_addition_add(add, write_test_ref, &refs[0]);
+	check(!err);
+	err = reftable_addition_commit(add);
+	check(!err);
+	reftable_addition_destroy(add);
+
+	/*
+	 * The second stack is now outdated, which we should notice. We do not
+	 * create the addition and lock the stack by default, but allow the
+	 * reload to happen when REFTABLE_STACK_NEW_ADDITION_RELOAD is set.
+	 */
+	err = reftable_stack_new_addition(&add, st2, 0);
+	check_int(err, ==, REFTABLE_OUTDATED_ERROR);
+	err = reftable_stack_new_addition(&add, st2, REFTABLE_STACK_NEW_ADDITION_RELOAD);
+	check(!err);
+	err = reftable_addition_add(add, write_test_ref, &refs[1]);
+	check(!err);
+	err = reftable_addition_commit(add);
+	check(!err);
+	reftable_addition_destroy(add);
+
+	for (size_t i = 0; i < ARRAY_SIZE(refs); i++) {
+		err = reftable_stack_read_ref(st2, refs[i].refname, &ref);
+		check(!err);
+		check(reftable_ref_record_equal(&refs[i], &ref, GIT_SHA1_RAWSZ));
+	}
+
+	reftable_ref_record_release(&ref);
+	reftable_stack_destroy(st1);
+	reftable_stack_destroy(st2);
+	clear_dir(dir);
+}
+
 static void t_reftable_stack_transaction_api_performs_auto_compaction(void)
 {
 	char *dir = get_tmp_dir(__LINE__);
@@ -318,7 +380,7 @@ static void t_reftable_stack_transaction_api_performs_auto_compaction(void)
 		 */
 		st->opts.disable_auto_compact = i != n;
 
-		err = reftable_stack_new_addition(&add, st);
+		err = reftable_stack_new_addition(&add, st, 0);
 		check(!err);
 
 		err = reftable_addition_add(add, write_test_ref, &ref);
@@ -1313,6 +1375,7 @@ int cmd_main(int argc UNUSED, const char *argv[] UNUSED)
 	TEST(t_reftable_stack_reload_with_missing_table(), "stack iteration with garbage tables");
 	TEST(t_reftable_stack_tombstone(), "'tombstone' refs in stack");
 	TEST(t_reftable_stack_transaction_api(), "update transaction to stack");
+	TEST(t_reftable_stack_transaction_with_reload(), "transaction with reload");
 	TEST(t_reftable_stack_transaction_api_performs_auto_compaction(), "update transaction triggers auto-compaction");
 	TEST(t_reftable_stack_update_index_check(), "update transactions with equal update indices");
 	TEST(t_reftable_stack_uptodate(), "stack must be reloaded before ref update");