File

net/http/errors.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 11225:8c17c08d100e
child 12974:ba409c67353b
line wrap: on
line source

-- This module returns a table that is suitable for use as a util.error registry,
-- and a function to return a util.error object given callback 'code' and 'body'
-- parameters.

local codes = require "net.http.codes";
local util_error = require "util.error";

local error_templates = {
	-- This code is used by us to report a client-side or connection error.
	-- Instead of using the code, use the supplied body text to get one of
	-- the more detailed errors below.
	[0] = {
		code = 0, type = "cancel", condition = "internal-server-error";
		text = "Connection or internal error";
	};

	-- These are net.http built-in errors, they are returned in
	-- the body parameter when code == 0
	["cancelled"] = {
		code = 0, type = "cancel", condition = "remote-server-timeout";
		text = "Request cancelled";
	};
	["connection-closed"] = {
		code = 0, type = "wait", condition = "remote-server-timeout";
		text = "Connection closed";
	};
	["certificate-chain-invalid"] = {
		code = 0, type = "cancel", condition = "remote-server-timeout";
		text = "Server certificate not trusted";
	};
	["certificate-verify-failed"] = {
		code = 0, type = "cancel", condition = "remote-server-timeout";
		text = "Server certificate invalid";
	};
	["connection failed"] = {
		code = 0, type = "cancel", condition = "remote-server-not-found";
		text = "Connection failed";
	};
	["invalid-url"] = {
		code = 0, type = "modify", condition = "bad-request";
		text = "Invalid URL";
	};
	["unable to resolve service"] = {
		code = 0, type = "cancel", condition = "remote-server-not-found";
		text = "DNS resolution failed";
	};

	-- This doesn't attempt to map every single HTTP code (not all have sane mappings),
	-- but all the common ones should be covered. XEP-0086 was used as reference for
	-- most of these.
	[400] = { type = "modify", condition = "bad-request" };
	[401] = { type = "auth", condition = "not-authorized" };
	[402] = { type = "auth", condition = "payment-required" };
	[403] = { type = "auth", condition = "forbidden" };
	[404] = { type = "cancel", condition = "item-not-found" };
	[405] = { type = "cancel", condition = "not-allowed" };
	[406] = { type = "modify", condition = "not-acceptable" };
	[407] = { type = "auth", condition = "registration-required" };
	[408] = { type = "wait", condition = "remote-server-timeout" };
	[409] = { type = "cancel", condition = "conflict" };
	[410] = { type = "cancel", condition = "gone" };
	[411] = { type = "modify", condition = "bad-request" };
	[412] = { type = "cancel", condition = "conflict" };
	[413] = { type = "modify", condition = "resource-constraint" };
	[414] = { type = "modify", condition = "resource-constraint" };
	[415] = { type = "cancel", condition = "feature-not-implemented" };
	[416] = { type = "modify", condition = "bad-request" };

	[422] = { type = "modify", condition = "bad-request" };
	[423] = { type = "wait", condition = "resource-constraint" };

	[429] = { type = "wait", condition = "resource-constraint" };
	[431] = { type = "modify", condition = "resource-constraint" };
	[451] = { type = "auth", condition = "forbidden" };

	[500] = { type = "wait", condition = "internal-server-error" };
	[501] = { type = "cancel", condition = "feature-not-implemented" };
	[502] = { type = "wait", condition = "remote-server-timeout" };
	[503] = { type = "cancel", condition = "service-unavailable" };
	[504] = { type = "wait", condition = "remote-server-timeout" };
	[507] = { type = "wait", condition = "resource-constraint" };
	[511] = { type = "auth", condition = "not-authorized" };
};

for k, v in pairs(codes) do
	if error_templates[k] then
		error_templates[k].code = k;
		error_templates[k].text = v;
	else
		error_templates[k] = { type = "cancel", condition = "undefined-condition", text = v, code = k };
	end
end

setmetatable(error_templates, {
	__index = function(_, k)
		if type(k) ~= "number" then
			return nil;
		end
		return {
			type = "cancel";
			condition = "undefined-condition";
			text = codes[k] or (k.." Unassigned");
			code = k;
		};
	end
});

local function new(code, body, context)
	if code == 0 then
		return util_error.new(body, context, error_templates);
	else
		return util_error.new(code, context, error_templates);
	end
end

return {
	registry = error_templates;
	new = new;
};