[Tarantool-patches] [PATCH v4 2/3] cfg: support symbolic evaluation of replication_synchro_quorum

[Vladislav Shpilevoy]

Hi! Thanks for the patch!

All looks good now except 2 small comments below.

> diff --git a/src/box/box.cc b/src/box/box.cc
> index a8bc3471d..b820af5d0 100644
> --- a/src/box/box.cc
> +++ b/src/box/box.cc
> @@ -554,10 +554,119 @@ box_check_replication_sync_lag(void)
>  	return lag;
>  }
>  
> +/**
> + * Evaluate replication syncro quorum number from a formula.
> + */
> +static int
> +box_eval_replication_synchro_quorum(int nr_replicas)
> +{
> +	const char fmt[] =
> +		"local expr = [[%s]]\n"
> +		"local f, err = loadstring('return ('..expr..')')\n"
> +		"if not f then "
> +			"error(string.format('Failed to load \%\%s:"
> +			"\%\%s', expr, err)) "
> +		"end\n"
> +		"setfenv(f, {N = %d, math = {"
> +			"ceil = math.ceil,"
> +			"floor = math.floor,"
> +			"abs = math.abs,"
> +			"random = math.random,"
> +			"min = math.min,"
> +			"max = math.abs,"
> +			"sqrt = math.sqrt,"
> +			"fmod = math.fmod,"
> +		"}})\n"
> +		"local res = f()\n"
> +		"if type(res) ~= 'number' then\n"
> +			"error('Expression should return a number')\n"
> +		"end\n"
> +		"return math.floor(res)\n";
> +	const char *expr = cfg_gets("replication_synchro_quorum");
> +	int quorum = -1;
> +
> +	/*
> +	 * cfg_gets uses static buffer as well so we need a local
> +	 * one, 1K should be enough to carry arbitrary but sane
> +	 * formula.
> +	 */
> +	char buf[1024];
> +	int len = snprintf(buf, sizeof(buf), fmt, expr,
> +			   nr_replicas);
> +	if (len >= (int)sizeof(buf)) {
> +		diag_set(ClientError, ER_CFG,
> +			 "replication_synchro_quorum",
> +			 "the formula is too big");
> +		return -1;
> +	}
> +
> +	luaL_loadstring(tarantool_L, buf);
> +	if (lua_pcall(tarantool_L, 0, 1, 0) != 0) {
> +		diag_set(ClientError, ER_CFG,
> +			 "replication_synchro_quorum",
> +			 lua_tostring(tarantool_L, -1));
> +		return -1;
> +	}
> +
> +	if (lua_isnumber(tarantool_L, -1))
> +		quorum = (int)lua_tonumber(tarantool_L, -1);

1. There is a small issue:

tarantool> box.cfg{replication_synchro_quorum='4294967297'}
2020-12-21 18:33:16.015 [47366] main/103/interactive I> set 'replication_synchro_quorum' configuration option to "4294967297"
---
...

UINT32_MAX + 1 turns to 0. +2 turns to 1. So it
is accepted because you silently truncate to `int`.

> @@ -913,7 +1013,25 @@ box_set_replication_sync_lag(void)
>  void
>  box_update_replication_synchro_quorum(void)
>  {
> -	int quorum = cfg_geti("replication_synchro_quorum");
> +	int quorum = -1;
> +
> +	if (!cfg_isnumber("replication_synchro_quorum")) {
> +		/*
> +		 * The formula has been verified already. For bootstrap
> +		 * stage pass 1 as a number of replicas to sync because
> +		 * we're at early stage and registering a new replica.
> +		 *
> +		 * This should cover the valid case where formula is plain
> +		 * "N", ie all replicas are to be synchro mode.
> +		 */
> +		int value = MAX(1, replicaset.registered_count);
> +		quorum = box_eval_replication_synchro_quorum(value);
> +		if (quorum <= 0 || quorum >= VCLOCK_MAX)
> +			panic("failed to eval replication_synchro_quorum");

2. This check better be below. Because the numeric value also was
validated, right?

> +		say_info("update replication_synchro_quorum = %d", quorum);
> +	} else {
> +		quorum = cfg_geti("replication_synchro_quorum");
> +	}