deploy: separate "what this host deploys" from swarm-wide truth

`services.hyperhive.swarm.*` is meant to be identical on every host in a
swarm — it describes the swarm, and every hive needs all of it to be a
client. But it also carried the `enable` toggles, which are precisely the
values that must differ per machine. The namespace that should be the
same everywhere held the one thing that cannot be.

Adds `services.hyperhive.deploy.*` for a host's deployment decisions, and
moves the first of them (`swarm.grafana.enable` -> `deploy.grafana`) as
the pattern for the rest. Flat and named for the thing deployed rather
than grouped under a "swarm services" attribute: from the deploy side it
does not matter what kind of thing each one is, and a grouping by service
kind would re-encode the service-side taxonomy into a layer that does not
care about it.

Behaviour is unchanged. The move is a rename in the strict sense — same
type, same meaning, new path — so `mkRenamedOptionModule` carries it and
existing configs keep evaluating with one warning naming both paths. The
renames live in the new module rather than the service modules, so the
whole migration has a single home and a single file to delete when the
deprecation window closes.
This commit is contained in:
atlas 2026-08-30 03:08:18 +02:00 committed by mara
commit b422367942
6 changed files with 73 additions and 16 deletions

View file

@ -12,6 +12,7 @@
{
imports = [
./hyperhive.nix
./deploy.nix
./local-defaults.nix
./hive-c0re
./hive-ci.nix

View file

@ -0,0 +1,53 @@
# "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" would
# re-encode the service-side taxonomy into a layer that does not care
# about it: from here, a host deploys forgejo, or a hive, or the lot, and
# what *kind* of thing each one is belongs to the service module.
#
# ⚠️ 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, ... }:
{
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" ]
)
];
options.services.hyperhive.deploy = {
grafana = 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.
'';
};
};
}

View file

@ -16,6 +16,7 @@
}:
let
cfg = config.services.hyperhive.swarm.grafana;
deployCfg = config.services.hyperhive.deploy;
networkCfg = config.services.hyperhive.network;
hyperhiveCfg = config.services.hyperhive;
gatewayCfg = hyperhiveCfg.gateway;
@ -106,18 +107,12 @@ let
in
{
# `enable` moved to `services.hyperhive.deploy.grafana` — see
# ./deploy.nix. Whether this host runs the swarm's Grafana is a
# deployment decision, and `swarm.*` has to be identical on every host.
# What stays here is what the service IS: its package, domain, and
# wiring.
options.services.hyperhive.swarm.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 enabling it is a decision about swarm topology rather
than about whether hyperhive is installed.
'';
};
package = lib.mkOption {
type = lib.types.package;
default = pkgs.grafana;
@ -312,8 +307,8 @@ in
};
};
config = lib.mkIf (hyperhiveCfg.enable && cfg.enable) {
# The gateway name and the quick-link, both inside `cfg.enable` — that
config = lib.mkIf (hyperhiveCfg.enable && deployCfg.grafana) {
# The gateway name and the quick-link, both inside `deploy.grafana` — that
# guard is the load-bearing part. Every hive in a swarm may know this UI
# exists, but only the host that RUNS it may claim the name; a client
# hive declaring the vhost would answer for a service it does not have.

View file

@ -69,7 +69,8 @@ in
# takes one and not the other from this switch. An operator who wants
# exactly one still sets it directly, which `mkDefault` allows.
victoriametrics.enable = lib.mkDefault swarmCfg.enableRequiredServices;
grafana.enable = lib.mkDefault swarmCfg.enableRequiredServices;
# (grafana's half of the pair derives below — it lives in `deploy.*`
# now, which is a different attribute path, not a different rule.)
# The log store, deriving from the same switch for the same reason —
# and deliberately in the same commit as the collector pipeline that
@ -88,4 +89,10 @@ in
# The collector that feeds the pair above (note: no `swarm.` prefix,
# this is ./otel.nix's existing per-hive option).
config.services.hyperhive.otel.enable = lib.mkDefault swarmCfg.enableRequiredServices;
# Grafana, the UI half of the metrics pair. Same derivation and the same
# reasoning as `victoriametrics.enable` above; it reads differently only
# because "does this host run it" now lives in `deploy.*` (./deploy.nix)
# rather than under `swarm.*`, which has to be identical on every host.
config.services.hyperhive.deploy.grafana = lib.mkDefault swarmCfg.enableRequiredServices;
}

View file

@ -23,6 +23,7 @@
let
cfg = config.services.hyperhive;
swarmCfg = cfg.swarm;
deployCfg = cfg.deploy;
# Public hostnames of the swarm's own services, in declaration order.
# `serviceDomains` below is this set sorted + deduplicated.
@ -57,7 +58,7 @@ let
# metrics UI and store looked fine for as long as only people opened
# them; the collector's exporter — same defect, no human in the loop —
# failed every POST and dropped the samples.
++ lib.optional swarmCfg.grafana.enable swarmCfg.grafana.domain
++ lib.optional deployCfg.grafana swarmCfg.grafana.domain
++ lib.optional swarmCfg.victoriametrics.enable swarmCfg.victoriametrics.domain
++ lib.optional swarmCfg.otel.enable swarmCfg.otel.domain
# VictoriaLogs' vhost is new (was previously unpublished entirely — see