File

Statistics: Rewrite statistics backends to use OpenMetrics The metric subsystem of Prosody has had some shortcomings from the perspective of the current state-of-the-art in metric observability. The OpenMetrics standard [0] is a formalization of the data model (and serialization format) of the well-known and widely-used Prometheus [1] software stack. The previous stats subsystem of Prosody did not map well to that format (see e.g. [2] and [3]); the key reason is that it was trying to do too much math on its own ([2]) while lacking first-class support for "families" of metrics ([3]) and structured metric metadata (despite the `extra` argument to metrics, there was no standard way of representing common things like "tags" or "labels"). Even though OpenMetrics has grown from the Prometheus world of monitoring, it maps well to other popular monitoring stacks such as: - InfluxDB (labels can be mapped to tags and fields as necessary) - Carbon/Graphite (labels can be attached to the metric name with dot-separation) - StatsD (see graphite when assuming that graphite is used as backend, which is the default) The util.statsd module has been ported to use the OpenMetrics model as a proof of concept. An implementation which exposes the util.statistics backend data as Prometheus metrics is ready for publishing in prosody-modules (most likely as mod_openmetrics_prometheus to avoid breaking existing 0.11 deployments). At the same time, the previous measure()-based API had one major advantage: It is really simple and easy to use without requiring lots of knowledge about OpenMetrics or similar concepts. For that reason as well as compatibility with existing code, it is preserved and may even be extended in the future. However, code relying on the `stats-updated` event as well as `get_stats` from `statsmanager` will break because the data model has changed completely; in case of `stats-updated`, the code will simply not run (as the event was renamed in order to avoid conflicts); the `get_stats` function has been removed completely (so it will cause a traceback when it is attempted to be used). Note that the measure_*_event methods have been removed from the module API. I was unable to find any uses or documentation and thus deemed they should not be ported. Re-implementation is possible when necessary. [0]: https://openmetrics.io/ [1]: https://prometheus.io/ [2]: #959 [3]: #960

local adns = require "net.adns";
local basic = require "net.resolvers.basic";
local inet_pton = require "util.net".pton;
local idna_to_ascii = require "util.encodings".idna.to_ascii;
local unpack = table.unpack or unpack; -- luacheck: ignore 113

local methods = {};
local resolver_mt = { __index = methods };

-- Find the next target to connect to, and
-- pass it to cb()
function methods:next(cb)
	if self.targets then
		if not self.resolver then
			if #self.targets == 0 then
				cb(nil);
				return;
			end
			local next_target = table.remove(self.targets, 1);
			self.resolver = basic.new(unpack(next_target, 1, 4));
		end
		self.resolver:next(function (...)
			if ... == nil then
				self.resolver = nil;
				self:next(cb);
			else
				cb(...);
			end
		end);
		return;
	end

	if not self.hostname then
		-- FIXME report IDNA error
		cb(nil);
		return;
	end

	local targets = {};
	local function ready()
		self.targets = targets;
		self:next(cb);
	end

	-- Resolve DNS to target list
	local dns_resolver = adns.resolver();
	dns_resolver:lookup(function (answer, err)
		if not answer and not err then
			-- net.adns returns nil if there are zero records or nxdomain
			answer = {};
		end
		if answer then
			if #answer == 0 then
				if self.extra and self.extra.default_port then
					table.insert(targets, { self.hostname, self.extra.default_port, self.conn_type, self.extra });
				end
				ready();
				return;
			end

			if #answer == 1 and answer[1].srv.target == "." then -- No service here
				ready();
				return;
			end

			table.sort(answer, function (a, b) return a.srv.priority < b.srv.priority end);
			for _, record in ipairs(answer) do
				table.insert(targets, { record.srv.target, record.srv.port, self.conn_type, self.extra });
			end
		end
		ready();
	end, "_" .. self.service .. "._" .. self.conn_type .. "." .. self.hostname, "SRV", "IN");
end

local function new(hostname, service, conn_type, extra)
	local is_ip = inet_pton(hostname);
	if not is_ip and hostname:sub(1,1) == '[' then
		is_ip = inet_pton(hostname:sub(2,-2));
	end
	if is_ip and extra and extra.default_port then
		return basic.new(hostname, extra.default_port, conn_type, extra);
	end

	return setmetatable({
		hostname = idna_to_ascii(hostname);
		service = service;
		conn_type = conn_type or "tcp";
		extra = extra;
	}, resolver_mt);
end

return {
	new = new;
};