nix: move the reader-after-policy edges into their own colocation glue

The four readers' ordering after their policy units only applies where
the store and that reader share a host, so it is colocation glue and
does not belong in the reader modules (two of which are main modules).
glue-bao-readers-policy-order.nix now sets the after+wants edges, gated
on deploy.bao.enable AND the reader's own gate, so a store host without
a reader gains no stub unit.
This commit is contained in:
atlas 2026-09-24 14:04:49 +02:00 • committed by mara
commit 0bfe354b6d
7 changed files with 127 additions and 42 deletions

View file

@ -23,6 +23,7 @@
./hive-priv.nix
./hive-tls.nix
./otel.nix
./glue-bao-readers-policy-order.nix
./glue-bao-tls.nix
./glue-controller-bao-identity.nix
./glue-grafana-oidc-client.nix

View file

@ -0,0 +1,60 @@
# Glue: where the store and one of its readers share a host, the reader waits
# for the unit that writes the cert-auth role it logs in with.
#
# ONE PAIRING PER FILE — the store's four reader policy units ← the readers
# they grant, and nothing else. Deleting this leaves every reader as it is on a
# host whose store is remote: it may log in before its role exists, and its own
# retries are what carry it past that.
#
# ⚠️ Gated on BOTH the store and that reader being here. Off the store's host
# there is no local policy unit to order against. 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.
#
# Ordering, never a requirement: a policy unit skips once the bootstrap token
# is gone, and a skipped unit counts as done. `wants` as well as `after`, so a
# reader started on its own pulls its policy unit into the same transaction.
{
lib,
config,
...
}:
let
hyperhiveCfg = config.services.hyperhive;
deployCfg = hyperhiveCfg.deploy;
baoDeploy = deployCfg.bao;
havePair = cert: key: cert != null && key != null;
# Reader unit → the gate its own module defines it under.
readersHere = {
# ./glue-matrix-bao-token.nix
swarm-bao-matrix-token =
hyperhiveCfg.enable
&& havePair baoDeploy.matrixTokenClientCertFile baoDeploy.matrixTokenClientKeyFile
&& deployCfg.matrix.enable;
# ./glue-queue-agent-credential.nix
swarm-bao-queue-agent =
hyperhiveCfg.enable
&& havePair baoDeploy.queueAgentClientCertFile baoDeploy.queueAgentClientKeyFile;
# ./swarm-grafana.nix
swarm-bao-grafana-oidc = hyperhiveCfg.enable && deployCfg.grafana.enable;
# ./swarm-otel.nix
swarm-bao-otel-oidc =
deployCfg.swarm-otel.enable
&& havePair baoDeploy.otelOidcClientCertFile baoDeploy.otelOidcClientKeyFile;
};
orderAfterPolicy =
reader: here:
lib.mkIf (baoDeploy.enable && here) {
systemd.services.${reader} = {
after = [ "${reader}-policy.service" ];
wants = [ "${reader}-policy.service" ];
};
};
in
{
config = lib.mkMerge (lib.mapAttrsToList orderAfterPolicy readersHere);
}

View file

@ -136,19 +136,11 @@ in
# `Requires=` on an absent unit fails the job outright, so the ordering is
# conditional even though the read is not: off-host there is nothing local
# to wait for, and the timeout below is what bounds the attempt instead.
#
# The policy unit writes the role this reader logs in with. Ordering
# only: it skips once the bootstrap token is gone, and a skipped unit
# counts as done.
after = lib.optionals baoDeploy.enable [
"swarm-bao-pki.service"
"container@${baoCfg.machine}.service"
"swarm-bao-matrix-token-policy.service"
];
wants = lib.optionals baoDeploy.enable [
"container@${baoCfg.machine}.service"
"swarm-bao-matrix-token-policy.service"
];
wants = lib.optionals baoDeploy.enable [ "container@${baoCfg.machine}.service" ];
requires = lib.optionals baoDeploy.enable [ "swarm-bao-pki.service" ];
before = [ "container@${matrixMachine}.service" ];
wantedBy = [ "container@${matrixMachine}.service" ];

View file

@ -161,19 +161,11 @@ in
# `Requires=` on an absent unit fails the job outright, so the ordering is
# conditional even though the read is not: off-host there is nothing local
# to wait for, and the timeout below is what bounds the attempt instead.
#
# The policy unit writes the role this reader logs in with. Ordering
# only: it skips once the bootstrap token is gone, and a skipped unit
# counts as done.
after = lib.optionals baoDeploy.enable [
"swarm-bao-pki.service"
"container@${baoCfg.machine}.service"
"swarm-bao-queue-agent-policy.service"
];
wants = lib.optionals baoDeploy.enable [
"container@${baoCfg.machine}.service"
"swarm-bao-queue-agent-policy.service"
];
wants = lib.optionals baoDeploy.enable [ "container@${baoCfg.machine}.service" ];
requires = lib.optionals baoDeploy.enable [ "swarm-bao-pki.service" ];
# Ordered before hive-c0re, so no agent container renders ahead of an
# attempt at its credential. `Wants=`, not `Requires=`: a store this

View file

@ -583,19 +583,11 @@ in
# `Requires=` on an absent unit fails the job outright, so the ordering
# is conditional even though the read is not: off-host there is nothing
# local to wait for, and the timeout below bounds the attempt instead.
#
# The policy unit writes the role this reader logs in with. Ordering
# only: it skips once the bootstrap token is gone, and a skipped unit
# counts as done.
after = lib.optionals baoDeploy.enable [
"swarm-bao-pki.service"
"container@${baoCfg.machine}.service"
"swarm-bao-grafana-oidc-policy.service"
];
wants = lib.optionals baoDeploy.enable [
"container@${baoCfg.machine}.service"
"swarm-bao-grafana-oidc-policy.service"
];
wants = lib.optionals baoDeploy.enable [ "container@${baoCfg.machine}.service" ];
requires = lib.optionals baoDeploy.enable [ "swarm-bao-pki.service" ];
before = [ "container@${cfg.machine}.service" ];
wantedBy = [

View file

@ -766,19 +766,11 @@ in
# `Requires=` on an absent unit fails the job outright, so the ordering
# is conditional even though the read is not: off-host there is nothing
# local to wait for, and the timeout below bounds the attempt instead.
#
# The policy unit writes the role this reader logs in with. Ordering
# only: it skips once the bootstrap token is gone, and a skipped unit
# counts as done.
after = lib.optionals baoDeploy.enable [
"swarm-bao-pki.service"
"container@${baoCfg.machine}.service"
"swarm-bao-otel-oidc-policy.service"
];
wants = lib.optionals baoDeploy.enable [
"container@${baoCfg.machine}.service"
"swarm-bao-otel-oidc-policy.service"
];
wants = lib.optionals baoDeploy.enable [ "container@${baoCfg.machine}.service" ];
requires = lib.optionals baoDeploy.enable [ "swarm-bao-pki.service" ];
before = [ "container@${cfg.machine}.service" ];
wantedBy = [