localHostsEntry's 127.0.0.1 rows leak into the address= answers dnsmasq gives agent containers now that it runs on the host, sending every agent back to itself instead of the bridge IP.
81 lines
3.9 KiB
Nix
81 lines
3.9 KiB
Nix
# Hive-internal DNS resolver + DHCP, co-located in the gateway
|
|
# container — single front-door for both DNS and HTTP, saves a
|
|
# sibling container. Listens on the bridge interface from
|
|
# `services.hyperhive.network`; authoritative for the hive domain +
|
|
# sub-domains, forwards everything else upstream. Returns the
|
|
# `services.dnsmasq` value for the container config (see
|
|
# ./default.nix); the DHCP pool bounds are computed by hive-network.
|
|
{
|
|
lib,
|
|
networkCfg,
|
|
forgeCfg,
|
|
matrixCfg,
|
|
hyperhiveDomain,
|
|
}:
|
|
{
|
|
enable = true;
|
|
# Don't substitute the container's /etc/resolv.conf — the gateway
|
|
# uses the host's resolver for its own outbound traffic; dnsmasq is
|
|
# purely for incoming queries from agent containers.
|
|
resolveLocalQueries = false;
|
|
settings = {
|
|
# Bind only on the bridge interface (and lo for health-checks).
|
|
# Outside hosts can't even see the listener.
|
|
interface = [
|
|
networkCfg.bridgeName
|
|
"lo"
|
|
];
|
|
bind-interfaces = true;
|
|
port = 53;
|
|
# Authoritative for the hive domain via the `address` rules below —
|
|
# must not fall back to the host's /etc/hosts. dnsmasq reads
|
|
# /etc/hosts by default, and `gateway.localHostsEntry` populates it
|
|
# with 127.0.0.1 for every hive name (host-side dev convenience,
|
|
# see default.nix). Since #3088 moved dnsmasq onto the host, that
|
|
# file is now the *same* /etc/hosts dnsmasq reads for agent queries
|
|
# — its entries win over `address=`, so every agent resolves the
|
|
# hive's own domains back to itself (127.0.0.1 in its own netns)
|
|
# instead of the bridge IP, and can't reach the forge, matrix, or
|
|
# dashboard at all. `no-hosts = true` keeps the authoritative
|
|
# `address=` rules in charge for containers while leaving
|
|
# `networking.hosts` (the actual /etc/hosts entries) untouched for
|
|
# host-side browsing.
|
|
no-hosts = true;
|
|
# Hive authoritative records — answer queries for the hive domain
|
|
# + its sub-domains with the bridge IP, where nginx is reachable
|
|
# from every container netns.
|
|
#
|
|
# The forge / matrix entries are redundant in the common case
|
|
# where `forge.domain` / `matrix.gatewayHost` are sub-domains of
|
|
# `hyperhive.domain` — dnsmasq's `/<domain>/` rule already matches
|
|
# sub-domains. Kept explicit because operators can override either
|
|
# to a cross-domain hostname (e.g. `forge.domain =
|
|
# "git.example.com"`); listing them explicitly keeps that case
|
|
# routed without needing an extra config block.
|
|
address = [
|
|
"/${hyperhiveDomain}/${networkCfg.bridgeIp}"
|
|
]
|
|
++ lib.optional ((forgeCfg.behindGateway or false)) "/${forgeCfg.domain}/${networkCfg.bridgeIp}"
|
|
++ lib.optional (
|
|
matrixCfg.enable && matrixCfg.gatewayHost != null
|
|
) "/${matrixCfg.gatewayHost}/${networkCfg.bridgeIp}";
|
|
# DHCP pool covering all usable host addresses on the bridge
|
|
# subnet — bounds computed by hive-network.nix from
|
|
# bridgeIp/bridgePrefixLength. All containers (agents and service
|
|
# containers such as hive-ci) receive their IPs dynamically.
|
|
dhcp-range = "${networkCfg.dhcpRangeStart},${networkCfg.dhcpRangeEnd},1h";
|
|
dhcp-leasefile = "/var/lib/dnsmasq/dnsmasq.leases";
|
|
# No explicit upstream: non-hive queries follow dnsmasq's
|
|
# resolv.conf default — the gateway container's `/etc/resolv.conf`,
|
|
# which nixos-container copies from the host at every start, so the
|
|
# hive always uses the host's resolvers. resolvconf is disabled in
|
|
# the container (see ./default.nix) so nothing regenerates that
|
|
# copy; the host-side `hive-gateway-resolv` path unit (also in
|
|
# ./default.nix) pushes in a fresh copy and reloads dnsmasq whenever
|
|
# the host's resolvers change, so the copy can't go stale under a
|
|
# network switch. Deliberately no fallback `server=`: dnsmasq queries
|
|
# all known upstreams in parallel, so a hardcoded public resolver
|
|
# would take a share of *normal* traffic, not just fill in when the
|
|
# host file is empty.
|
|
};
|
|
}
|