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 pairs = pairs;
local setmetatable = setmetatable;
local st = require "util.stanza";
local util = module:require "muc/util";

local function get_filtered_presence(stanza)
	return util.filter_muc_x(st.clone(stanza));
end

local occupant_mt = {};
occupant_mt.__index = occupant_mt;

local function new_occupant(bare_real_jid, nick)
	return setmetatable({
		bare_jid = bare_real_jid;
		nick = nick; -- in-room jid
		sessions = {}; -- hash from real_jid to presence stanzas. stanzas should not be modified
		role = nil;
		jid = nil; -- Primary session
	}, occupant_mt);
end

-- Deep copy an occupant
local function copy_occupant(occupant)
	local sessions = {};
	for full_jid, presence_stanza in pairs(occupant.sessions) do
		-- Don't keep unavailable presences, as they'll accumulate; unless they're the primary session
		if presence_stanza.attr.type ~= "unavailable" or full_jid == occupant.jid then
			sessions[full_jid] = presence_stanza;
		end
	end
	return setmetatable({
		bare_jid = occupant.bare_jid;
		nick = occupant.nick;
		sessions = sessions;
		role = occupant.role;
		jid = occupant.jid;
	}, occupant_mt);
end

-- finds another session to be the primary (there might not be one)
function occupant_mt:choose_new_primary()
	for jid, pr in self:each_session() do
		if pr.attr.type == nil then
			return jid;
		end
	end
	return nil;
end

function occupant_mt:set_session(real_jid, presence_stanza, replace_primary)
	local pr = get_filtered_presence(presence_stanza);
	pr.attr.from = self.nick;
	pr.attr.to = real_jid;

	self.sessions[real_jid] = pr;
	if replace_primary then
		self.jid = real_jid;
	elseif self.jid == nil or (pr.attr.type == "unavailable" and self.jid == real_jid) then
		-- Only leave an unavailable presence as primary when there are no other options
		self.jid = self:choose_new_primary() or real_jid;
	end
end

function occupant_mt:remove_session(real_jid)
	-- Delete original session
	self.sessions[real_jid] = nil;
	if self.jid == real_jid then
		self.jid = self:choose_new_primary();
	end
end

function occupant_mt:each_session()
	return pairs(self.sessions)
end

function occupant_mt:get_presence(real_jid)
	return self.sessions[real_jid or self.jid]
end

return {
	new = new_occupant;
	copy = copy_occupant;
	mt = occupant_mt;
}