File

plugins/mod_net_multiplex.lua @ 11523:5f15ab7c6ae5

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
author Jonas Schäfer <jonas@wielicki.name>
date Sun, 18 Apr 2021 11:47:41 +0200
parent 11024:1c7602c70d1f
child 12977:74b9e05af71e
line wrap: on
line source

module:set_global();

local array = require "util.array";
local max_buffer_len = module:get_option_number("multiplex_buffer_size", 1024);
local default_mode = module:get_option_number("network_default_read_size", 4096);

local portmanager = require "core.portmanager";

local available_services = {};
local service_by_protocol = {};
local available_protocols = array();

local function add_service(service)
	local multiplex_pattern = service.multiplex and service.multiplex.pattern;
	local protocol_name = service.multiplex and service.multiplex.protocol;
	if protocol_name then
		module:log("debug", "Adding multiplex service %q with protocol %q", service.name, protocol_name);
		service_by_protocol[protocol_name] = service;
		available_protocols:push(protocol_name);
	end
	if multiplex_pattern then
		module:log("debug", "Adding multiplex service %q with pattern %q", service.name, multiplex_pattern);
		available_services[service] = multiplex_pattern;
	elseif not protocol_name then
		module:log("debug", "Service %q is not multiplex-capable", service.name);
	end
end
module:hook("service-added", function (event) add_service(event.service); end);
module:hook("service-removed", function (event)
	available_services[event.service] = nil;
	if event.service.multiplex and event.service.multiplex.protocol then
		available_protocols:filter(function (p) return p ~= event.service.multiplex.protocol end);
		service_by_protocol[event.service.multiplex.protocol] = nil;
	end
end);

for _, services in pairs(portmanager.get_registered_services()) do
	for _, service in ipairs(services) do
		add_service(service);
	end
end

local buffers = {};

local listener = { default_mode = max_buffer_len };

function listener.onconnect(conn)
	local sock = conn:socket();
	if sock.getalpn then
		local selected_proto = sock:getalpn();
		local service = service_by_protocol[selected_proto];
		if service then
			module:log("debug", "Routing incoming connection to %s based on ALPN %q", service.name, selected_proto);
			local next_listener = service.listener;
			conn:setlistener(next_listener);
			conn:set_mode(next_listener.default_mode or default_mode);
			local onconnect = next_listener.onconnect;
			if onconnect then return onconnect(conn) end
		end
	end
end

function listener.onincoming(conn, data)
	if not data then return; end
	local buf = buffers[conn];
	buf = buf and buf..data or data;
	for service, multiplex_pattern in pairs(available_services) do
		if buf:match(multiplex_pattern) then
			module:log("debug", "Routing incoming connection to %s", service.name);
			local next_listener = service.listener;
			conn:setlistener(next_listener);
			conn:set_mode(next_listener.default_mode or default_mode);
			local onconnect = next_listener.onconnect;
			if onconnect then onconnect(conn) end
			return next_listener.onincoming(conn, buf);
		end
	end
	if #buf > max_buffer_len then -- Give up
		conn:close();
	else
		buffers[conn] = buf;
	end
end

function listener.ondisconnect(conn)
	buffers[conn] = nil; -- warn if no buffer?
end

listener.ondetach = listener.ondisconnect;

module:provides("net", {
	name = "multiplex";
	config_prefix = "";
	listener = listener;
});

module:provides("net", {
	name = "multiplex_ssl";
	config_prefix = "ssl";
	encryption = "ssl";
	ssl_config = {
		alpn = function ()
			return available_protocols;
		end;
	};
	listener = listener;
});