hyperhive/nix/host-modules/deploy.nix
atlas 09fe94a8ca deploy: name the swarm collector swarm-otel, not otel
Per review: `deploy.otel` does not imply swarm level, and there is a
hive-tier collector too -- `services.hyperhive.otel.enable`, which every
hive runs. The tier is the entire distinction between the two, so the
name has to carry it, matching `deploy.swarm-controller` and
`deploy.swarm-ui`.

15 swarm-tier references renamed across 8 files. The hive-tier
collector's 16 references are deliberately untouched, verified as a
control on the same command.

Three spellings needed three different patterns, all inside this one
rename: the dotted path; the `mkRenamedOptionModule` target written as a
nix LIST (`[ ... "deploy" "otel" "enable" ]`), which no dotted grep can
match; and prose in docs/observability.md spelled `deploy.otel` with
neither `.enable` nor a leading dot. Unanchored `deploy\.otel\b` is the
only pattern that finds all three.
2026-08-30 04:23:22 +02:00

200 lines
7.7 KiB
Nix

# "What does THIS host deploy?"
#
# Separated from `services.hyperhive.swarm.*` because those are two
# different kinds of fact and only one of them varies per machine:
#
# swarm.* — swarm-wide truth. The swarm's name, domain, hives, peers,
# CA, and where each service lives. **Identical on every
# host**, byte for byte; a hive needs all of it to be a
# *client* of the swarm.
# deploy.* — this machine's deployment decisions. Necessarily different
# on every host, because that is what a deployment is.
#
# The `enable` toggles used to live under `swarm.*`, which made the
# namespace that is supposed to be identical everywhere carry the one
# thing that must differ.
#
# Flat and named for the thing deployed — `deploy.forgejo`, not
# `deploy.swarmServices.forgejo`: grouping by "swarm service" re-encodes
# the service-side taxonomy into a layer that does not care about it.
#
# ⚠️ Each entry is an attrset with an `enable`, not a bare bool, so a
# service that grows a second *deployment* decision has somewhere to put
# it — `deploy.forgejo = { enable; ci; }` is then an ordinary addition
# rather than a migration. `ci` ("does this host run the runner too") is
# exactly that shape, and a bare bool leaves it unrepresentable.
#
# ⚠️ The renames below are deliberately in this one file rather than
# spread across the service modules, so the whole move has a single home
# and a single file to delete when the deprecation window closes — the
# shape ./swarm-peers-removed.nix already uses.
{ lib, config, ... }:
let
deployCfg = config.services.hyperhive.deploy;
in
{
imports = [
# Same type, same meaning, new path — so a rename carries it exactly
# and existing configs keep evaluating with one warning naming both
# paths. Precedent: ./hive-forge/default.nix, ./hive-matrix.nix.
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "grafana" "enable" ]
[ "services" "hyperhive" "deploy" "grafana" "enable" ]
)
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "victoriametrics" "enable" ]
[ "services" "hyperhive" "deploy" "victoriametrics" "enable" ]
)
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "victorialogs" "enable" ]
[ "services" "hyperhive" "deploy" "victorialogs" "enable" ]
)
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "controller" "enable" ]
[ "services" "hyperhive" "deploy" "swarm-controller" "enable" ]
)
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "ui" "enable" ]
[ "services" "hyperhive" "deploy" "swarm-ui" "enable" ]
)
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "authelia" "enable" ]
[ "services" "hyperhive" "deploy" "authelia" "enable" ]
)
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "nats" "enable" ]
[ "services" "hyperhive" "deploy" "nats" "enable" ]
)
(lib.mkRenamedOptionModule
[ "services" "hyperhive" "swarm" "otel" "enable" ]
[ "services" "hyperhive" "deploy" "swarm-otel" "enable" ]
)
];
options.services.hyperhive.deploy = {
grafana.enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
Run the swarm's metrics UI on this host.
Off by default and not derived from
{option}`services.hyperhive.enable`: a swarm has one Grafana, so
running it is a decision about this host rather than about
whether hyperhive is installed.
'';
};
victoriametrics.enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
Run the swarm's metrics store on this host.
Derives from
{option}`services.hyperhive.swarm.enableRequiredServices` together
with {option}`services.hyperhive.deploy.grafana.enable`: a store
with no UI is unreadable and a UI with no store is empty, so there
is no sensible deployment that takes one and not the other from
that switch. Set either directly to run exactly one.
'';
};
victorialogs.enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
Run the swarm's log store on this host.
Derives from
{option}`services.hyperhive.swarm.enableRequiredServices` for the
same reason as the metrics pair above: a hive that is not the
service host is a *client* of this store, not a second one.
'';
};
authelia.enable = lib.mkOption {
type = lib.types.bool;
default = false;
example = true;
description = ''
Run the swarm's authelia in a `swarm-authelia` container on this
host. {option}`services.hyperhive.swarm.enableRequiredServices`
turns this on a swarm has one SSO provider, and that says it
lives here.
With it off, this hive is a *client*:
{option}`services.hyperhive.swarm.authelia.url` still points at
whoever runs it, and no container is created. That asymmetry is
why the two live in different namespaces every hive needs the
client half, only one runs the server half.
'';
};
swarm-otel.enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
Run the **swarm's** telemetry collector on this host.
Derives from
{option}`services.hyperhive.swarm.enableRequiredServices` with the
metrics pair it feeds: a swarm has one of these, and it belongs
wherever the shared services live rather than on every hive.
Named `swarm-otel` rather than `otel` because there are two
collectors and the tier is the whole distinction:
{option}`services.hyperhive.otel.enable` is the **hive-tier** one,
which every hive runs. A bare `deploy.otel` would not say which
it meant. A hive that does not run the swarm collector still runs
its own, and reaches this one by name at
{option}`services.hyperhive.swarm.otel.domain`.
'';
};
nats.enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
Run the swarm's message queue in a `swarm-nats` container on this
host. A swarm has one queue, so this belongs on the same host as
the rest of the shared services.
Off by default, and off means *absent*: no container is created
and nothing else in the evaluated config changes.
'';
};
swarm-controller.enable = lib.mkOption {
type = lib.types.bool;
default = false;
description = ''
Run the swarm-controller daemon on this host.
Off by default and deliberately not derived from
{option}`services.hyperhive.enable`: a swarm has one controller,
so running it is a decision about this host rather than about
whether hyperhive is installed.
'';
};
swarm-ui.enable = lib.mkOption {
type = lib.types.bool;
default = deployCfg.swarm-controller.enable;
defaultText = lib.literalExpression "services.hyperhive.deploy.swarm-controller.enable";
example = true;
description = ''
Serve the swarm UI from this host.
Derived from
{option}`services.hyperhive.deploy.swarm-controller.enable` rather
than from
{option}`services.hyperhive.swarm.enableRequiredServices`: the UI
is a view onto the controller's state and reaches it over that
daemon's unix socket, so the host that runs the controller is the
host that can serve the UI. A hive that merely *uses* a swarm has
nothing to serve here.
'';
};
};
}