autonomic-bot
16d177e73a
Removes virtualisation.docker.autoPrune (daily `docker system prune --all` evicted in-use base images → cold re-pull → Hub rate-limit churn, JOURNAL-2). Adds modules/docker-prune.nix: daily timer + oneshot that prunes only dangling+until=24h, gated on disk pressure (>=80%) AND no run-app live AND no swarm service converging; never --all, never --volumes. Teardown unchanged (never removes images). Registry pull-through cache dropped per operator scope correction. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
48 lines
2.2 KiB
Nix
48 lines
2.2 KiB
Nix
# Docker + single-node Swarm — the deploy target for recipes under test (M1).
|
|
# Traefik (modules/traefik.nix) and abra layer on top; recipes attach to the `proxy`
|
|
# overlay network, exactly as a real Co-op Cloud host expects.
|
|
{ pkgs, ... }:
|
|
{
|
|
virtualisation.docker = {
|
|
enable = true;
|
|
# Image pruning is handled by modules/docker-prune.nix (Phase 2pc / PC1), NOT by
|
|
# `virtualisation.docker.autoPrune`. The old autoPrune ran `docker system prune --all` daily;
|
|
# `--all` evicts every image not used by a *running* container — between runs that wiped the
|
|
# cached recipe base images and forced a cold re-pull → the Docker-Hub-rate-limit churn in
|
|
# JOURNAL-2. The replacement keeps Docker's local store warm (it IS our cache on this single
|
|
# host) and prunes only dangling+old layers, gated on genuine disk pressure and nothing in
|
|
# flight. NEVER --volumes either: Phase-2w keeps DATA-WARM undeployed canonical volumes, reaped
|
|
# only by the warm reconcilers. autoPrune left OFF (the default) on purpose.
|
|
};
|
|
|
|
environment.systemPackages = [ pkgs.docker ];
|
|
|
|
# Gateway forwards 80/443 to cc-ci over the public interface (enp5s0); the coop-cloud
|
|
# traefik stack (deployed via abra, see docs/install.md) publishes these ports.
|
|
networking.firewall.allowedTCPPorts = [ 80 443 ];
|
|
|
|
# Bring up a single-node swarm + the shared `proxy` overlay network. Idempotent:
|
|
# safe to re-run every boot/rebuild. advertise-addr 127.0.0.1 is fine for a lone node.
|
|
systemd.services.swarm-init = {
|
|
description = "Initialise single-node Docker Swarm + proxy overlay network";
|
|
after = [ "docker.service" ];
|
|
requires = [ "docker.service" ];
|
|
wantedBy = [ "multi-user.target" ];
|
|
path = [ pkgs.docker ];
|
|
serviceConfig = {
|
|
Type = "oneshot";
|
|
RemainAfterExit = true;
|
|
};
|
|
script = ''
|
|
set -eu
|
|
state="$(docker info --format '{{.Swarm.LocalNodeState}}' 2>/dev/null || echo error)"
|
|
if [ "$state" != "active" ]; then
|
|
docker swarm init --advertise-addr 127.0.0.1
|
|
fi
|
|
if ! docker network inspect proxy >/dev/null 2>&1; then
|
|
docker network create --driver overlay --attachable proxy
|
|
fi
|
|
'';
|
|
};
|
|
}
|