diff --git a/nix/host-modules/glue-otel-scrape-targets.nix b/nix/host-modules/glue-otel-scrape-targets.nix index 520864bf..e01e8204 100644 --- a/nix/host-modules/glue-otel-scrape-targets.nix +++ b/nix/host-modules/glue-otel-scrape-targets.nix @@ -1,21 +1,20 @@ -# Glue: declare the loopback scrape targets of grafana and nats on the swarm's -# OTEL collector, wherever one of them shares a host with it. Authelia is a -# `publishedScrapeTargets` job (./swarm-otel-service.nix); a loopback job of +# Glue: declare the loopback scrape target of nats on the swarm's OTEL +# collector, wherever it shares a host with it. Authelia and grafana are +# `publishedScrapeTargets` jobs (./swarm-otel-service.nix); a loopback job of # the same name fails ./swarm-otel.nix's job-name assertion. # -# ONE FILE, TWO PAIRINGS — each service ← the collector, with the same shape. -# Deleting this leaves the collector scraping none of them: no error, no -# metrics. +# ONE PAIRING — nats ← the collector. Deleting this leaves the collector not +# scraping nats: no error, no metrics. # -# Each target is gated on the service AND the collector being enabled here. The +# The target is gated on the service AND the collector being enabled here. The # loopback address is only honest when both run on this host; a target nobody -# can read asserts a collection that is not happening. Both services default -# from `deploy.allSwarmServices`, but `mkDefault` is an invitation to override, -# so co-location is a property of the auto-deployed topology, not the modules. +# can read asserts a collection that is not happening. Both default from +# `deploy.allSwarmServices`, but `mkDefault` is an invitation to override, so +# co-location is a property of the auto-deployed topology, not the modules. # # ⚠️ Silent when split: separate hosts are separate evaluations with no shared -# context, so a host running a service and no collector declares nothing and -# the collector's host never learns of the service. No error, no warning — a +# context, so a host running nats and no collector declares nothing and +# the collector's host never learns of it. No error, no warning — a # healthy exporter and an empty dashboard. Not guardable from here. # # ⚠️ `swarm.otel`, not `hyperhive.otel` — two collectors one word apart, and only @@ -33,7 +32,6 @@ let in { config.services.hyperhive.swarm.otel.scrapeTargets = { - grafana = withCollector "grafana" "127.0.0.1:${toString swarmCfg.grafana.metricsPort}"; nats = withCollector "nats" "127.0.0.1:${toString swarmCfg.nats.metricsPort}"; }; } diff --git a/nix/host-modules/swarm-grafana-service.nix b/nix/host-modules/swarm-grafana-service.nix index 131c1cb0..4ccee30c 100644 --- a/nix/host-modules/swarm-grafana-service.nix +++ b/nix/host-modules/swarm-grafana-service.nix @@ -1,7 +1,7 @@ -# The swarm's metrics UI as every hive sees it: the name it is served under, -# the port its `/metrics` is re-served on, and the OIDC client it is -# registered as, identical on every host. What the host running it decides, -# and the container itself, are in ./swarm-grafana.nix. +# The swarm's metrics UI as every hive sees it: the name it is served under +# and the OIDC client it is registered as, identical on every host. What the +# host running it decides, and the container itself, are in +# ./swarm-grafana.nix. { lib, config, @@ -20,12 +20,11 @@ in # `enable` is `services.hyperhive.deploy.grafana.enable` — see # ./deploy.nix. Whether this host runs the swarm's Grafana is a # deployment decision, and `swarm.*` has to be identical on every host. - # Here is what the service IS to every hive: the name it is served under, - # the port its `/metrics` is re-served on, and the OIDC client it is - # registered as. What the host running it decides — which build it runs, - # where its datasources point, which plugins are in its store path, and - # the socket directory it shares with nginx — is `deploy.grafana`, in - # ./swarm-grafana.nix. + # Here is what the service IS to every hive: the name it is served under + # and the OIDC client it is registered as. What the host running it + # decides — which build it runs, where its datasources point, which plugins + # are in its store path, and the socket directory it shares with nginx — is + # `deploy.grafana`, in ./swarm-grafana.nix. options.services.hyperhive.swarm.grafana = { machine = lib.mkOption { type = lib.types.str; @@ -51,35 +50,13 @@ in ⚠️ Changing this changes the OAuth redirect URI, which authelia matches exactly. Both sides move together because both derive from this option; an operator who pins one by hand breaks the login. - ''; - }; - metricsPort = lib.mkOption { - type = lib.types.port; - default = 9095; - description = '' - Loopback port on which the gateway's nginx re-serves Grafana's - `/metrics`, and nothing else, so the swarm's collector can scrape it. - - ⚠️ **This is nginx's port, not Grafana's.** Grafana still claims none — - see {option}`services.hyperhive.deploy.grafana.socketDir` for why that - matters. A prometheus scrape target is a `host:port`, and it cannot - address a unix socket; rather than undo the socket decision, the one - endpoint a scraper needs gets a listener of its own. - - Bound to loopback and unauthenticated, which is the same posture every - other entry in - {option}`services.hyperhive.swarm.otel.scrapeTargets` has: those - targets are trusted by *proximity* rather than by credential. - Deliberately **not** the published `grafana.` vhost, which - would put an authorization decision in front of a scrape: that vhost - answers `/metrics` with 403, because Grafana serves it without - authentication. - - The number itself is arbitrary and free today; - `state/eval-port-collisions.sh` is what keeps it that way, since a - second claim on a port in this shared namespace produces no bind error - and nothing in any log. + The swarm collector scrapes Grafana's own metrics at + `https:///metrics`, from whichever host it runs on. + Grafana serves that endpoint to anyone, so the gateway puts it + behind authelia, whose rules admit only the collector's OAuth2 + client there: see `publishedScrapeTargets` in + ./swarm-otel-service.nix. ''; }; diff --git a/nix/host-modules/swarm-grafana.nix b/nix/host-modules/swarm-grafana.nix index 36fef4b0..a8e30bf0 100644 --- a/nix/host-modules/swarm-grafana.nix +++ b/nix/host-modules/swarm-grafana.nix @@ -20,6 +20,7 @@ let networkCfg = config.services.hyperhive.network; hyperhiveCfg = config.services.hyperhive; gatewayCfg = hyperhiveCfg.gateway; + autheliaDomain = hyperhiveCfg.swarm.authelia.domain; baoCfg = hyperhiveCfg.swarm.bao; baoDeploy = deployCfg.bao; @@ -459,12 +460,43 @@ in listen = gatewayCfg.lib.listen; extraConfig = gatewayCfg.lib.securityHeaders; # Grafana serves its Prometheus exposition to anyone, signed in or not - # (`metrics.enabled` below, no `basic_auth_*`), so the published name - # refuses it; the scrape goes through the loopback `grafana-metrics` - # vhost instead. `=` is enough: nginx matches the decoded, normalised - # path, so `//metrics`, `/./metrics`, `/%6detrics` and `/metrics?x` all - # land here, and Grafana itself answers `/metrics/` with a login redirect. - locations."= /metrics".return = "403"; + # (`metrics.enabled` below, no `basic_auth_*`), so this location's auth + # is the only gate on it. `=` is enough: nginx matches the decoded, + # normalised path, so `//metrics`, `/./metrics`, `/%6detrics` and + # `/metrics?x` all land here, and Grafana itself answers `/metrics/` with + # a login redirect. + # + # The collector requests exactly this URL, declared as + # `publishedScrapeTargets.grafana` in ./swarm-otel-service.nix; the two + # must agree, since that string is also the token's audience. Authelia's + # rules for it admit the collector's client and deny every other subject + # (`metricsRules` in ./swarm-authelia.nix). + locations."= /metrics" = { + proxyPass = "http://unix:${socketPath}:/metrics"; + extraConfig = '' + auth_request /__grafana_metrics_authz; + ''; + }; + # The subrequest, same shape as the forge's `= /__forge_metrics_authz` + # (./hive-forge/default.nix): no `error_page 401 =302`, so a scraper + # gets the 401 rather than a login page parsed as metrics. + locations."= /__grafana_metrics_authz" = { + proxyPass = "https://${autheliaDomain}/api/authz/auth-request"; + # nixpkgs appends its OWN `Host $host` after extraConfig, which would + # override verifiedProxyTo's — see hive-gateway/vhost-lib.nix. + recommendedProxySettings = false; + extraConfig = '' + internal; + ${gatewayCfg.lib.verifiedProxyTo autheliaDomain} + proxy_pass_request_body off; + proxy_set_header Content-Length ""; + proxy_set_header X-Original-Method $request_method; + proxy_set_header X-Original-URL $scheme://$http_host$request_uri; + proxy_set_header X-Forwarded-Proto $scheme; + proxy_set_header X-Forwarded-Host $http_host; + proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; + ''; + }; locations."/" = { proxyPass = "http://unix:${socketPath}:/"; proxyWebsockets = true; @@ -480,29 +512,6 @@ in }; }; - # The scrape listener: Grafana's `/metrics` and nothing else, on loopback. - # - # No `serverName` and no TLS on purpose — this listener exists for exactly - # one client on the same host, so there is no name to match and nothing to - # verify. It is the only vhost here that is not reachable from outside the - # machine, and that is what lets it skip the authorization the published - # one carries. - # - # ⚠️ `= /metrics` is an EXACT match, not a prefix: it is the difference - # between exposing one endpoint and re-serving the whole of Grafana on an - # unauthenticated port. Widening it would be a silent authorization bypass, - # since nothing else about this block would have to change. The published - # vhost above refuses `/metrics`, so this listener is the only way to it. - services.nginx.virtualHosts."grafana-metrics" = { - listen = [ - { - addr = "127.0.0.1"; - port = cfg.metricsPort; - } - ]; - locations."= /metrics".proxyPass = "http://unix:${socketPath}:/metrics"; - }; - # Order the container after the host CA service so the bind source below # exists before nspawn sets the mount up. systemd.services."container@${cfg.machine}" = caTrust.containerOrdering; diff --git a/nix/host-modules/swarm-otel-service.nix b/nix/host-modules/swarm-otel-service.nix index 87ee68f1..63b992fb 100644 --- a/nix/host-modules/swarm-otel-service.nix +++ b/nix/host-modules/swarm-otel-service.nix @@ -362,5 +362,7 @@ in victoriametrics = "https://${vmCfg.domain}/metrics"; # The vhost location is in ./swarm-victorialogs.nix. victorialogs = "https://${hyperhiveCfg.swarm.victorialogs.domain}/metrics"; + # The vhost location is in ./swarm-grafana.nix. + grafana = "https://${hyperhiveCfg.swarm.grafana.domain}/metrics"; }; } diff --git a/nix/module-eval/forge-placement.nix b/nix/module-eval/forge-placement.nix index cb085e75..f04b5dcd 100644 --- a/nix/module-eval/forge-placement.nix +++ b/nix/module-eval/forge-placement.nix @@ -138,16 +138,15 @@ let && !(refusedOver bare "deploy.forgejo.sso.clientSecretFile"); } { - # Authelia is a published target; ./swarm-otel-identity.nix covers it. - name = "a host running the collector, authelia, grafana and nats scrapes grafana and nats on loopback, authelia not"; + # Authelia and grafana are published targets; ./swarm-otel-identity.nix + # covers them. + name = "a host running the collector, authelia, grafana and nats scrapes nats on loopback, authelia and grafana not"; ok = let t = servicesHere.services.hyperhive.swarm.otel.scrapeTargets; port = n: toString servicesHere.services.hyperhive.swarm.${n}.metricsPort; in - t.grafana == "127.0.0.1:${port "grafana"}" - && t.nats == "127.0.0.1:${port "nats"}" - && !(t ? authelia); + t.nats == "127.0.0.1:${port "nats"}" && !(t ? authelia) && !(t ? grafana); } { name = "hosting the swarm's shared services runs the forge"; diff --git a/nix/module-eval/grafana.nix b/nix/module-eval/grafana.nix index 61520d06..d9cbeebf 100644 --- a/nix/module-eval/grafana.nix +++ b/nix/module-eval/grafana.nix @@ -109,12 +109,6 @@ let && lib.hasInfix option a.message ) m.assertions; cases = [ - { - name = "grafana declares no scrape target on a host with no collector"; - ok = - !(grafanaOldPath.services.hyperhive.deploy.swarm-otel.enable) - && !(grafanaOldPath.services.hyperhive.swarm.otel.scrapeTargets ? grafana); - } { # The socket's directory is its access control, so it must stay dedicated # to this one socket. `readOnly` is what makes that inexpressible: a @@ -124,22 +118,30 @@ let ok = !(builtins.tryEval grafanaSocketDirSet.services.hyperhive.deploy.grafana.socketDir).success && - grafanaOldPath.services.nginx.virtualHosts."grafana-metrics".locations."= /metrics".proxyPass + grafanaOldPath.services.nginx.virtualHosts.${grafanaOldPath.services.hyperhive.swarm.grafana.domain}.locations."= /metrics".proxyPass == "http://unix:/run/swarm-grafana/grafana.sock:/metrics"; } { - # Grafana serves `/metrics` unauthenticated, so the published name must - # answer it itself; the scrape reads the loopback vhost above instead. + # Grafana serves `/metrics` unauthenticated, so the published name gates + # it on the collector's auth subrequest: no `error_page 401 =302` (a + # scraper would parse a login page as metrics) and no `/__hive_authelia`. # `=` is what catches the normalised variants and still leaves the rest # of Grafana proxied. - name = "grafana's published vhost refuses /metrics and still proxies everything else"; + name = "grafana's published vhost serves /metrics only behind the collector's auth subrequest"; ok = let g = grafanaOldPath.services.hyperhive.swarm.grafana; locs = grafanaOldPath.services.nginx.virtualHosts.${g.domain}.locations; + checksOf = l: lib.filter (lib.hasPrefix "auth_request") (lib.splitString "\n" l.extraConfig); + authz = locs."= /__grafana_metrics_authz"; in - locs."= /metrics".return == "403" - && locs."= /metrics".proxyPass == null + locs ? "= /metrics" + && locs."= /metrics".return == null + && checksOf locs."= /metrics" == [ "auth_request /__grafana_metrics_authz;" ] + && !(lib.hasInfix "error_page" locs."= /metrics".extraConfig) + && authz.proxyPass == "https://auth.t.local/api/authz/auth-request" + && lib.hasInfix "internal;" authz.extraConfig + && !(grafanaOldPath.services.nginx.virtualHosts ? "grafana-metrics") && lib.hasPrefix "http://unix:" locs."/".proxyPass; } { diff --git a/nix/module-eval/swarm-otel-identity.nix b/nix/module-eval/swarm-otel-identity.nix index eb2b49c4..04c0d047 100644 --- a/nix/module-eval/swarm-otel-identity.nix +++ b/nix/module-eval/swarm-otel-identity.nix @@ -108,6 +108,7 @@ let forgeMetricsUrl = "https://forge.t.local/metrics"; autheliaMetricsUrl = "https://auth.t.local/metrics"; + grafanaMetricsUrl = "https://grafana.t.local/metrics"; logsMetricsUrl = "https://logs.t.local/metrics"; vmMetricsUrl = "https://metrics.t.local/metrics"; @@ -374,10 +375,11 @@ let lib.sort lib.lessThan (lib.attrValues h.swarm.otel.publishedScrapeTargets) == [ autheliaMetricsUrl forgeMetricsUrl + grafanaMetricsUrl logsMetricsUrl vmMetricsUrl ] - && lib.length targets == 8 + && lib.length targets == 10 && lib.all (t: policy collector t == "one_factor") targets && lib.all (t: policy "user:someone" t == "deny") targets && lib.all (t: policy "group:admins" t == "deny") targets; @@ -425,7 +427,7 @@ let ]; matched = row: builtins.match re row.path != null; in - lib.length metricsRules == 6 + lib.length metricsRules == 8 && lib.all (r: r.resources == [ re ]) metricsRules && re == "^/metrics([?].*)?$" && lib.all (row: matched row == (row.nginx == "= /metrics")) table; @@ -562,6 +564,63 @@ let && lib.length jobs == 1 && (lib.head jobs).static_configs == [ { targets = [ "logs.t.local" ]; } ]; } + { + name = "a collector on a host without grafana scrapes it by name"; + ok = + let + s = otelSettings otelRemoteAuthelia; + job = lib.findFirst (j: j.job_name == "grafana") null s.receivers.prometheus.config.scrape_configs; + in + !otelRemoteAuthelia.services.hyperhive.deploy.grafana.enable + && job != null + && job.static_configs == [ { targets = [ "grafana.t.local" ]; } ] + && job.metrics_path == "/metrics" + && job.oauth2.endpoint_params.audience == grafanaMetricsUrl; + } + { + # The `deny` that confines grafana's `/metrics` is scoped to that path, + # and comes after the collector's rule: every other path on the name + # still reaches `default_policy`, as it did with no rule at all. + name = "authelia confines grafana's /metrics to the collector and leaves its other paths alone"; + ok = + let + h = autheliaOnly.services.hyperhive; + collector = "oauth2:client:${h.swarm.otel.clientId}"; + rules = + autheliaOnly.containers.swarm-authelia.config.services.authelia.instances.swarm.settings.access_control.rules; + grafanaRules = lib.filter (r: r.domain == "grafana.t.local") rules; + policy = subject: autheliaPolicy autheliaOnly subject "grafana.t.local"; + in + map (r: r.policy) grafanaRules == [ + "one_factor" + "deny" + ] + && lib.all (r: r.resources == [ "^/metrics([?].*)?$" ]) grafanaRules + && (lib.head grafanaRules).subject == [ collector ] + && policy collector "/metrics" == "one_factor" + && policy "user:someone" "/metrics" == "deny" + && policy "user:someone" "/metrics?x=1" == "deny" + && policy "group:admins" "/metrics" == "deny" + && policy "user:someone" "/" == "one_factor" + && policy "user:someone" "/login/generic_oauth" == "one_factor"; + } + { + # Single host: grafana is scraped once, by its published name. + name = "a host running grafana and the collector scrapes it once, by name"; + ok = + let + o = allLocal.services.hyperhive.swarm.otel; + jobs = + lib.filter (j: j.job_name == "grafana") + (otelSettings allLocal).receivers.prometheus.config.scrape_configs; + in + allLocal.services.hyperhive.deploy.grafana.enable + && allLocal.services.hyperhive.deploy.swarm-otel.enable + && !(o.scrapeTargets ? grafana) + && (o.publishedScrapeTargets.grafana or null) == grafanaMetricsUrl + && lib.length jobs == 1 + && (lib.head jobs).static_configs == [ { targets = [ "grafana.t.local" ]; } ]; + } { # Read against the roster the fixture declares rather than against # names spelled here: an arm naming `h1` passes on a single-hive