265f8a47cc
A pki start refused by its start limit failed every reader that Requires= it with `dependency`. That leaves a unit inactive, not failed, so Restart=on-failure never fired and readers without a refresh timer never ran again (#5381: grafana 502 for ~43 min). Readers and granting units now Wants= + After= pki; one whose leaf is still missing fails its login with exit 1 into its existing retry. pki gets StartLimitIntervalSec=0: it is deliberately not RemainAfterExit, so each reader's start re-runs it.
82 lines
3 KiB
Nix
82 lines
3 KiB
Nix
# Glue: where the store and one of its readers share a host, the reader waits
|
|
# for the store's container and `swarm-bao-pki`, which mints the leaf the
|
|
# reader logs in with.
|
|
#
|
|
# ONE PAIRING PER FILE — the store's container and PKI unit ← the readers that
|
|
# log in to it, and nothing else. The waits on the store's policy units are
|
|
# ./glue-bao-readers-policy-order.nix's.
|
|
#
|
|
# `Wants=` on `swarm-bao-pki`, not `Requires=`: a pki start that fails or is
|
|
# refused fails each requirer's job with `dependency`, which leaves the reader
|
|
# inactive rather than failed, so its `Restart=on-failure` never fires. Here
|
|
# the reader runs anyway; with its leaf still missing, its login exits 1 into
|
|
# ./lib/store-retry.nix's retries.
|
|
#
|
|
# ⚠️ Gated on BOTH the store and that reader being here. Off the store's host
|
|
# neither unit exists, and the reader's own start timeout bounds the attempt
|
|
# instead. On the store's host without the reader, setting
|
|
# `systemd.services.<reader>.after` would define a unit with no ExecStart, so
|
|
# each gate below restates the one the reader's own module puts on it. A
|
|
# reader whose gate changes must change here too.
|
|
{
|
|
lib,
|
|
config,
|
|
...
|
|
}:
|
|
let
|
|
hyperhiveCfg = config.services.hyperhive;
|
|
deployCfg = hyperhiveCfg.deploy;
|
|
baoDeploy = deployCfg.bao;
|
|
baoCfg = hyperhiveCfg.swarm.bao;
|
|
otel = hyperhiveCfg.otel;
|
|
|
|
havePair = cert: key: cert != null && key != null;
|
|
|
|
# Reader unit → the gate its own module defines it under.
|
|
readersHere = {
|
|
# ./hive-forge/default.nix
|
|
swarm-bao-forge-oidc = deployCfg.forgejo.enable;
|
|
# ./hive-matrix.nix
|
|
swarm-bao-matrix-oidc = deployCfg.matrix.enable;
|
|
# ./otel.nix: `fetches`, the collector loading the file this unit writes
|
|
# under the hive's own leaf.
|
|
swarm-bao-hive-otel-oidc =
|
|
otel.enable
|
|
&& hyperhiveCfg.hiveName != null
|
|
&& havePair baoDeploy.clientCertFile baoDeploy.clientKeyFile
|
|
&&
|
|
otel.clientSecretFile
|
|
== "/var/lib/hive-otel-oidc/${hyperhiveCfg.swarm.authelia.hiveClientPrefix}${toString hyperhiveCfg.hiveName}.secret";
|
|
# ./swarm-grafana.nix
|
|
swarm-bao-grafana-oidc = deployCfg.grafana.enable;
|
|
swarm-bao-grafana-admin = deployCfg.grafana.enable;
|
|
swarm-bao-grafana-metrics-bearer = deployCfg.grafana.enable;
|
|
swarm-bao-grafana-controller-token = deployCfg.grafana.enable;
|
|
# ./swarm-nats.nix
|
|
swarm-bao-nats-callout-xkey = deployCfg.nats.enable;
|
|
# ./swarm-ci-runner.nix
|
|
swarm-bao-ci-runner = deployCfg.ci-runner.enable;
|
|
# ./swarm-otel.nix
|
|
swarm-bao-otel-oidc =
|
|
deployCfg.swarm-otel.enable
|
|
&& havePair baoDeploy.otelOidcClientCertFile baoDeploy.otelOidcClientKeyFile;
|
|
};
|
|
|
|
orderAfterStore =
|
|
reader: here:
|
|
lib.mkIf (baoDeploy.enable && here) {
|
|
systemd.services.${reader} = {
|
|
after = [
|
|
"swarm-bao-pki.service"
|
|
"container@${baoCfg.machine}.service"
|
|
];
|
|
wants = [
|
|
"swarm-bao-pki.service"
|
|
"container@${baoCfg.machine}.service"
|
|
];
|
|
};
|
|
};
|
|
in
|
|
{
|
|
config = lib.mkMerge (lib.mapAttrsToList orderAfterStore readersHere);
|
|
}
|