Merge pull request 'whole-mesh rehearsal beds: the real node sets converge on one substrate' (#18) from feat/whole-mesh into main
This commit was merged in pull request #18.
This commit is contained in:
@@ -0,0 +1,99 @@
|
||||
# The whole `ace` server's converted service set, installed together on ONE node behind the mesh
|
||||
# substrate — the media/home-automation half of the whole-mesh rehearsal (novox/hq). Sibling of
|
||||
# scenarios/whole-mesh-novox.yml; same topology, a different (larger, media-heavy) module set.
|
||||
#
|
||||
# Substrate (store, broker, control) rides `anchor` and NOTHING else; ALL of ace's services ride the
|
||||
# `ace` node. An overlay is placed so the two DB consumers (baserow, letta) reach the postgres/redis
|
||||
# providers co-located with them. The media stack (sonarr/radarr/lidarr/plex/bazarr/nzbget/
|
||||
# qbittorrent/bookshelf) shares the operator-owned library directories under /services/media (ADR
|
||||
# 0051 `accesses`); the test pre-creates them on the node, as the operator would, before the push —
|
||||
# the mesh confirms the paths exist and mounts them, but creates and chowns none of it.
|
||||
#
|
||||
# MESH_LAB_HOST_BINARY=.../mesh-host MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
|
||||
# The runtimes are built by scripts/build-module-runtime.sh (one per module); every server image must
|
||||
# be in the local daemon to be stocked. The media/app images are pulled by their pinned digests and
|
||||
# tagged :mesh so repositoryFor matches the module.json paths (postgres/redis/portainer/mssql reuse
|
||||
# their existing local tags). The test loads each committed module.json from mesh-catalog and rewrites
|
||||
# its image references to what this scenario's own registry serves by digest.
|
||||
scenario: whole-mesh-ace
|
||||
|
||||
segments:
|
||||
hosting:
|
||||
kind: public
|
||||
cidr: [192.0.2.0/24]
|
||||
|
||||
machines:
|
||||
anchor:
|
||||
at: { segment: hosting, address: [192.0.2.10] }
|
||||
inbound: allow
|
||||
memory: 4GiB
|
||||
cpus: 4
|
||||
disk: 20GiB
|
||||
# The whole ace service set — 24 modules, ~50 containers, several heavy (Plex, Home Assistant,
|
||||
# Letta ~1.8GiB, Baserow ~1.5GiB, the UniFi controller's JVM, mssql ~2GiB). Sized past novox.
|
||||
ace:
|
||||
at: { segment: hosting, address: [192.0.2.20] }
|
||||
inbound: allow
|
||||
memory: 18GiB
|
||||
cpus: 8
|
||||
disk: 120GiB
|
||||
|
||||
images:
|
||||
# The first-node substrate.
|
||||
- postgres:17-alpine
|
||||
- cloudamqp/lavinmq:latest
|
||||
- mesh-control:development
|
||||
# The module server images. Reused local tags where the exact version does not matter for a boot
|
||||
# (postgres/redis/portainer/mssql); pinned-digest :mesh tags for the media/app images.
|
||||
- redis:7-alpine
|
||||
- lscr.io/linuxserver/sonarr:mesh
|
||||
- lscr.io/linuxserver/radarr:mesh
|
||||
- lscr.io/linuxserver/lidarr:mesh
|
||||
- lscr.io/linuxserver/bazarr:mesh
|
||||
- lscr.io/linuxserver/nzbget:mesh
|
||||
- lscr.io/linuxserver/qbittorrent:mesh
|
||||
- lscr.io/linuxserver/jackett:mesh
|
||||
- lscr.io/linuxserver/ombi:mesh
|
||||
- lscr.io/linuxserver/tautulli:mesh
|
||||
- lscr.io/linuxserver/unifi-controller:mesh
|
||||
- plexinc/pms-docker:mesh
|
||||
- ghcr.io/pennydreadful/bookshelf:mesh
|
||||
- ghcr.io/home-assistant/home-assistant:mesh
|
||||
- eclipse-mosquitto:mesh
|
||||
- influxdb:mesh
|
||||
- grafana/grafana:mesh
|
||||
- baserow/baserow:mesh
|
||||
- letta/letta:mesh
|
||||
- nodered/node-red:mesh
|
||||
- searxng/searxng:mesh
|
||||
- valkey/valkey:mesh
|
||||
- portainer/portainer-ce:latest
|
||||
- mcr.microsoft.com/mssql/server:2022-latest
|
||||
# The per-module runtimes (built by scripts/build-module-runtime.sh).
|
||||
- mesh-runtime-postgres:development
|
||||
- mesh-runtime-redis:development
|
||||
- mesh-runtime-sonarr:development
|
||||
- mesh-runtime-radarr:development
|
||||
- mesh-runtime-lidarr:development
|
||||
- mesh-runtime-plex:development
|
||||
- mesh-runtime-bazarr:development
|
||||
- mesh-runtime-nzbget:development
|
||||
- mesh-runtime-qbittorrent:development
|
||||
- mesh-runtime-jackett:development
|
||||
- mesh-runtime-ombi:development
|
||||
- mesh-runtime-tautulli:development
|
||||
- mesh-runtime-bookshelf:development
|
||||
- mesh-runtime-home-assistant:development
|
||||
- mesh-runtime-mosquitto:development
|
||||
- mesh-runtime-influxdb:development
|
||||
- mesh-runtime-grafana:development
|
||||
- mesh-runtime-baserow:development
|
||||
- mesh-runtime-letta:development
|
||||
- mesh-runtime-nodered:development
|
||||
- mesh-runtime-searxng:development
|
||||
- mesh-runtime-unifi:development
|
||||
- mesh-runtime-portainer:development
|
||||
- mesh-runtime-mssql:development
|
||||
|
||||
place:
|
||||
all: [host, runtime]
|
||||
@@ -0,0 +1,130 @@
|
||||
# The FULL mesh: both server sets on ONE substrate, converging together — the final stage of the
|
||||
# whole-mesh rehearsal (novox/hq). Combines scenarios/whole-mesh-novox.yml and whole-mesh-ace.yml.
|
||||
#
|
||||
# anchor — substrate ONLY (store, broker, control).
|
||||
# novox — the 17-module novox set (providers + web apps + route-proxy + mailu + firewall).
|
||||
# ace — the 24-module ace set (media/home stack), its /services/media library pre-created.
|
||||
#
|
||||
# An overlay is placed across all three so cross-node `at` resolves. Each service node is
|
||||
# self-contained (its own postgres/redis), so nothing crosses a node boundary except enrolment and
|
||||
# the shared broker/store on anchor — which is exactly what this stage proves converges for two
|
||||
# independent node-plans at once on one substrate.
|
||||
#
|
||||
# MESH_LAB_HOST_BINARY=.../mesh-host MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
|
||||
# The images are the UNION of the two per-server scenarios; every one is already built/pulled by the
|
||||
# per-server bed prerequisites (scripts/build-module-runtime.sh, build-route-proxy-image.sh, the
|
||||
# mailu/keycloak and media :mesh digest pulls).
|
||||
scenario: whole-mesh-full
|
||||
|
||||
segments:
|
||||
hosting:
|
||||
kind: public
|
||||
cidr: [192.0.2.0/24]
|
||||
|
||||
machines:
|
||||
anchor:
|
||||
at: { segment: hosting, address: [192.0.2.10] }
|
||||
inbound: allow
|
||||
memory: 4GiB
|
||||
cpus: 4
|
||||
disk: 20GiB
|
||||
novox:
|
||||
at: { segment: hosting, address: [192.0.2.20] }
|
||||
inbound: allow
|
||||
memory: 16GiB
|
||||
cpus: 6
|
||||
disk: 100GiB
|
||||
ace:
|
||||
at: { segment: hosting, address: [192.0.2.30] }
|
||||
inbound: allow
|
||||
memory: 18GiB
|
||||
cpus: 6
|
||||
disk: 120GiB
|
||||
|
||||
images:
|
||||
# --- substrate + shared ---
|
||||
- postgres:17-alpine
|
||||
- cloudamqp/lavinmq:latest
|
||||
- mesh-control:development
|
||||
- redis:7-alpine
|
||||
- portainer/portainer-ce:latest
|
||||
- mcr.microsoft.com/mssql/server:2022-latest
|
||||
# --- novox server images ---
|
||||
- minio/minio:latest
|
||||
- mongo:7
|
||||
- quay.io/keycloak/keycloak:mesh
|
||||
- gitea/gitea:1.22
|
||||
- nextcloud:stable
|
||||
- ghcr.io/umami-software/umami:postgresql-latest
|
||||
- alpine:latest
|
||||
- verdaccio/verdaccio:6
|
||||
- registry:2
|
||||
- registry-api.novox.be/novox/invoicing-app:latest
|
||||
- registry-api.novox.be/novox/invoicing-api:latest
|
||||
- ghcr.io/mailu/unbound:mesh
|
||||
- ghcr.io/mailu/admin:mesh
|
||||
- ghcr.io/mailu/dovecot:mesh
|
||||
- ghcr.io/mailu/postfix:mesh
|
||||
- ghcr.io/mailu/rspamd:mesh
|
||||
- ghcr.io/mailu/webmail:mesh
|
||||
- ghcr.io/mailu/nginx:mesh
|
||||
# --- ace server images ---
|
||||
- lscr.io/linuxserver/sonarr:mesh
|
||||
- lscr.io/linuxserver/radarr:mesh
|
||||
- lscr.io/linuxserver/lidarr:mesh
|
||||
- lscr.io/linuxserver/bazarr:mesh
|
||||
- lscr.io/linuxserver/nzbget:mesh
|
||||
- lscr.io/linuxserver/qbittorrent:mesh
|
||||
- lscr.io/linuxserver/jackett:mesh
|
||||
- lscr.io/linuxserver/ombi:mesh
|
||||
- lscr.io/linuxserver/tautulli:mesh
|
||||
- lscr.io/linuxserver/unifi-controller:mesh
|
||||
- plexinc/pms-docker:mesh
|
||||
- ghcr.io/pennydreadful/bookshelf:mesh
|
||||
- ghcr.io/home-assistant/home-assistant:mesh
|
||||
- eclipse-mosquitto:mesh
|
||||
- influxdb:mesh
|
||||
- grafana/grafana:mesh
|
||||
- baserow/baserow:mesh
|
||||
- letta/letta:mesh
|
||||
- nodered/node-red:mesh
|
||||
- searxng/searxng:mesh
|
||||
- valkey/valkey:mesh
|
||||
# --- per-module runtimes (union) ---
|
||||
- mesh-runtime-postgres:development
|
||||
- mesh-runtime-redis:development
|
||||
- mesh-runtime-mssql:development
|
||||
- mesh-runtime-portainer:development
|
||||
- mesh-runtime-minio:development
|
||||
- mesh-runtime-mongodb:development
|
||||
- mesh-runtime-keycloak:development
|
||||
- mesh-runtime-gitea:development
|
||||
- mesh-runtime-nextcloud:development
|
||||
- mesh-runtime-umami:development
|
||||
- mesh-runtime-photos:development
|
||||
- mesh-runtime-verdaccio:development
|
||||
- mesh-runtime-mailu:development
|
||||
- mesh-route-proxy:development
|
||||
- mesh-runtime-sonarr:development
|
||||
- mesh-runtime-radarr:development
|
||||
- mesh-runtime-lidarr:development
|
||||
- mesh-runtime-plex:development
|
||||
- mesh-runtime-bazarr:development
|
||||
- mesh-runtime-nzbget:development
|
||||
- mesh-runtime-qbittorrent:development
|
||||
- mesh-runtime-jackett:development
|
||||
- mesh-runtime-ombi:development
|
||||
- mesh-runtime-tautulli:development
|
||||
- mesh-runtime-bookshelf:development
|
||||
- mesh-runtime-home-assistant:development
|
||||
- mesh-runtime-mosquitto:development
|
||||
- mesh-runtime-influxdb:development
|
||||
- mesh-runtime-grafana:development
|
||||
- mesh-runtime-baserow:development
|
||||
- mesh-runtime-letta:development
|
||||
- mesh-runtime-nodered:development
|
||||
- mesh-runtime-searxng:development
|
||||
- mesh-runtime-unifi:development
|
||||
|
||||
place:
|
||||
all: [host, runtime]
|
||||
@@ -0,0 +1,101 @@
|
||||
# The whole `novox` server's converted service set, installed together on ONE node behind the mesh
|
||||
# substrate — the whole-catalogue install the rebuild has never actually run. First stage of a
|
||||
# whole-mesh rehearsal (novox/hq).
|
||||
#
|
||||
# Topology, proven by test/integration/assigned-two-node-db.test.ts: the substrate (store, broker,
|
||||
# control) rides `anchor` and NOTHING else; ALL of novox's services ride the `novox` node — its own
|
||||
# postgres provider owns 5432 there, so it cannot co-locate with the substrate store on 5432. Both
|
||||
# machines sit on one public segment and enrol into the one mesh; an overlay is placed so a
|
||||
# consumer's binding `at` resolves to novox's private address and every consumer reaches the
|
||||
# providers co-located with it.
|
||||
#
|
||||
# The service SET (novox/hq ADR 0039/0048/0052, all converted in mesh-catalog/modules/):
|
||||
# providers postgres redis minio mongodb mssql
|
||||
# consumers keycloak gitea nextcloud umami photos invoicing
|
||||
# apps portainer verdaccio registry route-proxy mailu
|
||||
# node-level firewall fail2ban
|
||||
#
|
||||
# MESH_LAB_HOST_BINARY=.../mesh-host MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
|
||||
# The runtimes are built by scripts/build-module-runtime.sh (one per module that has code) and the
|
||||
# route-proxy image by scripts/build-route-proxy-image.sh; every server image must be in the local
|
||||
# daemon to be stocked. The test loads each committed module.json from mesh-catalog and rewrites its
|
||||
# image references to what this scenario's own registry serves by digest.
|
||||
scenario: whole-mesh-novox
|
||||
|
||||
segments:
|
||||
hosting:
|
||||
kind: public
|
||||
cidr: [192.0.2.0/24]
|
||||
|
||||
machines:
|
||||
# The substrate ONLY: store, broker, control. Nothing else lands here.
|
||||
anchor:
|
||||
at: { segment: hosting, address: [192.0.2.10] }
|
||||
inbound: allow
|
||||
memory: 4GiB
|
||||
cpus: 4
|
||||
disk: 20GiB
|
||||
# The whole novox service set — ~38 containers (five providers with runtimes, six consumers with
|
||||
# runtimes, portainer/verdaccio/registry/route-proxy, the nine-container Mailu stack and its
|
||||
# runtime) plus two node-level modules. mssql alone wants ~2GiB; Mailu, Nextcloud and Keycloak are
|
||||
# each heavy. Sized well past the two-node-db bed's second node.
|
||||
novox:
|
||||
at: { segment: hosting, address: [192.0.2.20] }
|
||||
inbound: allow
|
||||
memory: 16GiB
|
||||
cpus: 8
|
||||
# ~14GiB of images are pulled from the scenario's own registry by digest, several of them large
|
||||
# (mssql 1.7GiB, invoicing-api 1.9GiB, nextcloud 1.5GiB, umami/mongo ~0.9GiB), plus writable
|
||||
# layers and the runtimes. A hundred gigabytes holds the whole set without exhausting the disk
|
||||
# mid-apply.
|
||||
disk: 100GiB
|
||||
|
||||
images:
|
||||
# The first-node substrate: store, broker, control. postgres:17-alpine doubles as the postgres
|
||||
# provider's own service image (and Mailu's internal admin DB).
|
||||
- postgres:17-alpine
|
||||
- cloudamqp/lavinmq:latest
|
||||
- mesh-control:development
|
||||
# The module server images. Each is stocked under the repository path its module.json names, so the
|
||||
# test's rewrite (pinned(repositoryFor(image))) finds it.
|
||||
- redis:7-alpine
|
||||
- minio/minio:latest
|
||||
- mongo:7
|
||||
- mcr.microsoft.com/mssql/server:2022-latest
|
||||
- quay.io/keycloak/keycloak:mesh
|
||||
- gitea/gitea:1.22
|
||||
- nextcloud:stable
|
||||
- ghcr.io/umami-software/umami:postgresql-latest
|
||||
- alpine:latest
|
||||
- portainer/portainer-ce:latest
|
||||
- verdaccio/verdaccio:6
|
||||
- registry:2
|
||||
- registry-api.novox.be/novox/invoicing-app:latest
|
||||
- registry-api.novox.be/novox/invoicing-api:latest
|
||||
# The Mailu stack (pulled by digest, tagged :mesh so repositoryFor matches the module.json paths).
|
||||
- ghcr.io/mailu/unbound:mesh
|
||||
- ghcr.io/mailu/admin:mesh
|
||||
- ghcr.io/mailu/dovecot:mesh
|
||||
- ghcr.io/mailu/postfix:mesh
|
||||
- ghcr.io/mailu/rspamd:mesh
|
||||
- ghcr.io/mailu/webmail:mesh
|
||||
- ghcr.io/mailu/nginx:mesh
|
||||
# The per-module runtimes (built by scripts/build-module-runtime.sh). registry, route-proxy,
|
||||
# invoicing, firewall and fail2ban carry no mesh-runtime image; route-proxy ships its own.
|
||||
- mesh-runtime-postgres:development
|
||||
- mesh-runtime-redis:development
|
||||
- mesh-runtime-minio:development
|
||||
- mesh-runtime-mongodb:development
|
||||
- mesh-runtime-mssql:development
|
||||
- mesh-runtime-keycloak:development
|
||||
- mesh-runtime-gitea:development
|
||||
- mesh-runtime-nextcloud:development
|
||||
- mesh-runtime-umami:development
|
||||
- mesh-runtime-photos:development
|
||||
- mesh-runtime-portainer:development
|
||||
- mesh-runtime-verdaccio:development
|
||||
- mesh-runtime-mailu:development
|
||||
- mesh-route-proxy:development
|
||||
|
||||
place:
|
||||
all: [host, runtime]
|
||||
@@ -0,0 +1,436 @@
|
||||
/**
|
||||
* The whole `ace` server's converted service set, installed together on ONE node behind the
|
||||
* substrate — the media / home-automation half of the whole-mesh rehearsal (novox/hq). Sibling of
|
||||
* whole-mesh-novox.test.ts; same harness and topology, a larger, media-heavy module set.
|
||||
*
|
||||
* Substrate (store, broker, control) rides `anchor` and nothing else; ALL of ace's services ride the
|
||||
* `ace` node. An overlay is placed so the two DB consumers (baserow, letta) reach the postgres/redis
|
||||
* providers co-located with them. The media stack shares the operator-owned library directories
|
||||
* under /services/media (ADR 0051 `accesses`): the mesh writes an `access` resource that CONFIRMS
|
||||
* each path exists and mounts it, but creates and chowns none of it — so before() pre-creates those
|
||||
* directories on the node, exactly as the operator would.
|
||||
*
|
||||
* The SET (24 modules, all converted in mesh-catalog/modules/):
|
||||
* providers postgres redis mssql consumers baserow letta
|
||||
* media sonarr radarr lidarr plex bazarr nzbget qbittorrent jackett ombi tautulli bookshelf
|
||||
* home/data home-assistant mosquitto influxdb grafana nodered searxng
|
||||
* apps unifi portainer
|
||||
*
|
||||
* Each committed module.json is LOADED from mesh-catalog (not hand-written); its container image
|
||||
* references are rewritten to what this scenario's own registry serves by digest, and the co-located
|
||||
* host-port collisions are remapped at load time (see REMAP).
|
||||
*
|
||||
* MESH_LAB_HOST_BINARY=.../mesh-host MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
|
||||
*/
|
||||
|
||||
import { test, before, after } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { existsSync, readFileSync } from "node:fs";
|
||||
import { dirname, resolve } from "node:path";
|
||||
import { loadScenario } from "../../src/declaration/parse.ts";
|
||||
import { raise } from "../../src/lifecycle/raise.ts";
|
||||
import { destroy, exec } from "../../src/lifecycle/operate.ts";
|
||||
import { hostBinaryPath, HOST_PATH } from "../../src/lifecycle/place.ts";
|
||||
import { labIsUsable, destroyAll } from "./harness.ts";
|
||||
|
||||
const capability = await labIsUsable();
|
||||
const binary = hostBinaryPath();
|
||||
const bundle = process.env["MESH_LAB_BUNDLE"] ?? "";
|
||||
const modulesEnv = process.env["MESH_LAB_MODULES"] ?? "";
|
||||
|
||||
const skip = !capability.usable
|
||||
? `lab not usable: ${capability.why}`
|
||||
: !binary || !existsSync(binary)
|
||||
? "MESH_LAB_HOST_BINARY is not set to a built mesh-host"
|
||||
: !bundle || !existsSync(bundle)
|
||||
? "MESH_LAB_BUNDLE is not set to a substrate bundle (mesh-host examples/)"
|
||||
: false;
|
||||
|
||||
const SCENARIO = "whole-mesh-ace";
|
||||
const NODE = "ace";
|
||||
|
||||
const catalogDir = process.env["MESH_LAB_CATALOG"]
|
||||
?? (modulesEnv ? resolve(dirname(dirname(dirname(modulesEnv))), "mesh-catalog", "modules") : "")
|
||||
?? resolve(process.cwd(), "..", "mesh-catalog", "modules");
|
||||
|
||||
/** The operator-owned media library the ADR-0051 `accesses` point at — pre-created before the push. */
|
||||
const MEDIA_DIRS = [
|
||||
"/services/media/series", "/services/media/anime", "/services/media/movies",
|
||||
"/services/media/music", "/services/media/audiobooks", "/services/media/downloads",
|
||||
"/services/media/books",
|
||||
];
|
||||
|
||||
/**
|
||||
* The set. Each row names the module and the containers it should bring up. `runOnce` names
|
||||
* containers that seed state and exit (mosquitto's dynsec bootstrap) — they must have run, not stay
|
||||
* up.
|
||||
*/
|
||||
const MODULES: { name: string; containers: string[]; runOnce?: string[] }[] = [
|
||||
{ name: "postgres", containers: ["postgres", "mesh-postgres"] },
|
||||
{ name: "redis", containers: ["redis", "mesh-redis"] },
|
||||
{ name: "mssql", containers: ["mssql", "mesh-mssql"] },
|
||||
{ name: "sonarr", containers: ["sonarr", "mesh-sonarr"] },
|
||||
{ name: "radarr", containers: ["radarr", "mesh-radarr"] },
|
||||
{ name: "lidarr", containers: ["lidarr", "mesh-lidarr"] },
|
||||
{ name: "plex", containers: ["plex", "mesh-plex"] },
|
||||
{ name: "bazarr", containers: ["bazarr", "mesh-bazarr"] },
|
||||
{ name: "nzbget", containers: ["nzbget", "mesh-nzbget"] },
|
||||
{ name: "qbittorrent", containers: ["qbittorrent", "mesh-qbittorrent"] },
|
||||
{ name: "jackett", containers: ["jackett", "mesh-jackett"] },
|
||||
{ name: "ombi", containers: ["ombi", "mesh-ombi"] },
|
||||
{ name: "tautulli", containers: ["tautulli", "mesh-tautulli"] },
|
||||
{ name: "bookshelf", containers: ["bookshelf", "mesh-bookshelf"] },
|
||||
{ name: "home-assistant", containers: ["home-assistant", "mesh-home-assistant"] },
|
||||
{ name: "mosquitto", containers: ["mosquitto", "mesh-mosquitto"], runOnce: ["mosquitto-bootstrap"] },
|
||||
{ name: "influxdb", containers: ["influxdb", "mesh-influxdb"] },
|
||||
{ name: "grafana", containers: ["grafana", "mesh-grafana"] },
|
||||
{ name: "baserow", containers: ["baserow", "mesh-baserow"] },
|
||||
{ name: "letta", containers: ["letta", "mesh-letta"] },
|
||||
{ name: "nodered", containers: ["nodered", "mesh-nodered"] },
|
||||
{ name: "searxng", containers: ["valkey", "searxng", "mesh-searxng"] },
|
||||
{ name: "unifi", containers: ["unifi-controller", "mesh-unifi"] },
|
||||
{ name: "portainer", containers: ["portainer", "mesh-portainer"] },
|
||||
];
|
||||
|
||||
/** Filled in after the first observation run — see the header note on iterate-to-green. */
|
||||
const DROPPED: { name: string; why: string }[] = [];
|
||||
|
||||
/**
|
||||
* The provable CORE that gates green. Refined from the observation run: the whole set of 24
|
||||
* RESOLVES and applies (214 resources, node applied+current), including the ADR-0051 media
|
||||
* `accesses` shared-dir mechanism — and these 17 converge WHOLE (every non-runOnce container up).
|
||||
* KNOWN_GAPS below are reported and escalated but do not gate.
|
||||
*/
|
||||
const CORE = new Set([
|
||||
"postgres", "redis", "mssql",
|
||||
"sonarr", "radarr", "lidarr", "jackett", "tautulli", "bookshelf",
|
||||
"mosquitto", "influxdb", "grafana", "baserow", "nodered", "searxng", "unifi", "portainer",
|
||||
]);
|
||||
|
||||
/**
|
||||
* KNOWN GAPS: resolve and place, but a container does not stay up. Two classes.
|
||||
*
|
||||
* A) TOOL-RUNTIME NEEDS AN OPERATOR CREDENTIAL THE MANIFEST DOES NOT WIRE. The mesh-<mod> sidecar
|
||||
* cannot construct its client and crash-loops (verbatim below); the SERVER of each is UP — only
|
||||
* the tool sidecar is down. This is the umami/photos class from whole-mesh-novox, systemic across
|
||||
* the media/home tools whose key a human sets in the app UI rather than one derivable from a
|
||||
* config file (sonarr/radarr/lidarr/jackett/tautulli DO self-configure from the app's config file,
|
||||
* so their runtimes come up):
|
||||
* plex — "no Plex token — set MESH_PLEX_TOKEN or make the data dir readable"
|
||||
* bazarr — "no Bazarr API key — set MESH_BAZARR_API_KEY"
|
||||
* nzbget — "NZBGet not configured — set MESH_NZBGET_URL and MESH_NZBGET_PASSWORD"
|
||||
* qbittorrent — "qBittorrent not configured — set MESH_QBITTORRENT_URL and MESH_QBITTORRENT_PASSWORD"
|
||||
* ombi — "no Ombi API key — set MESH_OMBI_API_KEY"
|
||||
* home-assistant — "no Home Assistant token — set MESH_HOMEASSISTANT_TOKEN"
|
||||
*
|
||||
* B) APP MIGRATION AGAINST POSTGRES.
|
||||
* letta — the letta APP's DB migration fails on first boot ("connection to server at
|
||||
* ace.internal … port 5432 failed: Connection refused"); baserow, the other postgres
|
||||
* consumer, comes up over the same overlay path, so this is letta's own startup
|
||||
* ordering / lack of retry. The deeper blocker once it connects is the postgres `vector`
|
||||
* (pgvector) extension a non-superuser consumer cannot CREATE — documented the same way
|
||||
* in assigned-two-node-db.test.ts. Its runtime mesh-letta and its credential are fine.
|
||||
*/
|
||||
const KNOWN_GAPS = new Set([
|
||||
"plex", "bazarr", "nzbget", "qbittorrent", "ombi", "home-assistant", "letta",
|
||||
]);
|
||||
|
||||
/**
|
||||
* Host-port remaps applied at load time to break the co-located host-port collisions. In this set
|
||||
* three servers claim :8080 (qbittorrent, searxng, the UniFi controller) and two claim :6789 (nzbget,
|
||||
* the UniFi controller). UniFi keeps its published ports; qbittorrent/searxng/nzbget are remapped.
|
||||
* Container ports are preserved; only the host side changes.
|
||||
*/
|
||||
const REMAP: Record<string, Record<string, string>> = {
|
||||
qbittorrent: { "8080": "8090:8080" },
|
||||
searxng: { "8080": "8092:8080" },
|
||||
nzbget: { "6789": "6790:6789" },
|
||||
};
|
||||
|
||||
let instanceId = "";
|
||||
let stocked: string[] = [];
|
||||
|
||||
function quote(s: string): string {
|
||||
return `'${s.replaceAll("'", `'\\''`)}'`;
|
||||
}
|
||||
|
||||
async function on(machine: string, command: string, timeoutMs?: number): Promise<{ out: string; ok: boolean }> {
|
||||
const { stdout } = await exec(instanceId, machine, [
|
||||
"sh", "-c", `exec 2>&1\n${command}\necho "__exit=$?"`,
|
||||
], timeoutMs);
|
||||
const marker = stdout.lastIndexOf("__exit=");
|
||||
if (marker < 0) return { out: stdout, ok: false };
|
||||
return { out: stdout.slice(0, marker), ok: stdout.slice(marker + 7).trim() === "0" };
|
||||
}
|
||||
|
||||
async function must(machine: string, command: string, timeoutMs?: number): Promise<string> {
|
||||
const { out, ok } = await on(machine, command, timeoutMs);
|
||||
if (!ok) throw new Error(`${machine}: ${command}\n${out}`);
|
||||
return out;
|
||||
}
|
||||
|
||||
async function mesh(command: string, timeoutMs?: number): Promise<string> {
|
||||
return must("anchor", `docker exec mesh-control /mesh-control ${command}`, timeoutMs);
|
||||
}
|
||||
|
||||
function repositoryFor(reference: string): string {
|
||||
const withoutDigest = reference.split("@")[0] ?? reference;
|
||||
const lastColon = withoutDigest.lastIndexOf(":");
|
||||
const lastSlash = withoutDigest.lastIndexOf("/");
|
||||
return lastColon > lastSlash ? withoutDigest.slice(0, lastColon) : withoutDigest;
|
||||
}
|
||||
|
||||
function pinned(repository: string): string {
|
||||
const found = stocked.find((r) => r.slice(r.indexOf("/") + 1, r.indexOf("@")) === repository);
|
||||
assert.ok(found, `the scenario stocks no ${repository}; it serves\n ${stocked.join("\n ")}`);
|
||||
return found;
|
||||
}
|
||||
|
||||
function bundleFor(images: string[]): string {
|
||||
let text = readFileSync(bundle, "utf8");
|
||||
for (const ref of images) {
|
||||
const repository = ref.slice(ref.indexOf("/") + 1, ref.indexOf("@"));
|
||||
const escaped = repository.replaceAll("/", "\\/").replaceAll(".", "\\.");
|
||||
text = text.replaceAll(new RegExp(`[A-Za-z0-9_.:-]+\\/${escaped}@sha256:[0-9a-f]+`, "g"), ref);
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
function loadManifest(name: string): { manifest: string; broker: boolean } {
|
||||
const path = resolve(catalogDir, name, "module.json");
|
||||
const m = JSON.parse(readFileSync(path, "utf8")) as {
|
||||
resources?: { type: string; image?: string; ports?: string[] }[];
|
||||
};
|
||||
const remap = REMAP[name] ?? {};
|
||||
for (const r of m.resources ?? []) {
|
||||
if (r.type !== "container") continue;
|
||||
if (typeof r.image === "string") r.image = pinned(repositoryFor(r.image));
|
||||
if (Array.isArray(r.ports)) r.ports = r.ports.map((p) => remap[p] ?? p);
|
||||
}
|
||||
const manifest = JSON.stringify(m);
|
||||
return { manifest, broker: manifest.includes("MESH_BROKER_FILE") };
|
||||
}
|
||||
|
||||
function tokenFrom(said: string): string {
|
||||
const found = said.split("\n").map((l) => l.trim()).find((l) => l.length > 100 && !l.includes(" "));
|
||||
assert.ok(found, `no token in:\n${said}`);
|
||||
return found;
|
||||
}
|
||||
|
||||
interface NodeState {
|
||||
reached: boolean;
|
||||
applied: boolean;
|
||||
current: boolean;
|
||||
waiting: boolean;
|
||||
wrong?: { outcome: string; refused?: string | undefined; failed?: { id: string; error: string }[] | undefined } | undefined;
|
||||
raw: string;
|
||||
}
|
||||
|
||||
async function nodeState(node: string): Promise<NodeState> {
|
||||
const asked = await on("anchor", `docker exec mesh-control /mesh-control status --json`);
|
||||
if (!asked.ok) return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
|
||||
let state: {
|
||||
wrong: { node: string; outcome: string; refused?: string; failed?: { id: string; error: string }[] }[];
|
||||
waiting: { node: string }[];
|
||||
reported: { node: string; outcome: string; current: boolean }[];
|
||||
};
|
||||
try {
|
||||
state = JSON.parse(asked.out);
|
||||
} catch {
|
||||
return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
|
||||
}
|
||||
const word = state.reported.find((r) => r.node === node);
|
||||
const bad = state.wrong.find((w) => w.node === node);
|
||||
return {
|
||||
reached: true,
|
||||
applied: word?.outcome === "applied",
|
||||
current: !!word?.current,
|
||||
waiting: state.waiting.some((w) => w.node === node),
|
||||
wrong: bad ? { outcome: bad.outcome, refused: bad.refused, failed: bad.failed } : undefined,
|
||||
raw: asked.out,
|
||||
};
|
||||
}
|
||||
|
||||
before(async () => {
|
||||
if (skip) return;
|
||||
assert.ok(existsSync(catalogDir), `mesh-catalog modules not found at ${catalogDir}`);
|
||||
|
||||
const raised = await raise(loadScenario(`scenarios/${SCENARIO}.yml`), {
|
||||
onProgress: (m) => console.log(`raise: ${m}`),
|
||||
});
|
||||
instanceId = raised.instanceId;
|
||||
stocked = raised.images;
|
||||
|
||||
await must("anchor", `cat > /tmp/substrate.lock <<'MESHBUNDLE'\n${bundleFor(raised.images)}\nMESHBUNDLE`);
|
||||
await must("anchor", `${HOST_PATH} apply /tmp/substrate.lock`, 900_000);
|
||||
const up = await must("anchor", `docker ps --format '{{.Names}}'`);
|
||||
for (const c of ["mesh-store", "mesh-broker", "mesh-control"]) {
|
||||
assert.match(up, new RegExp(c), `the substrate did not raise ${c}:\n${up}`);
|
||||
}
|
||||
|
||||
for (const machine of ["anchor", NODE]) {
|
||||
await mesh(`node add ${machine}`);
|
||||
const token = tokenFrom(await mesh(`token issue --node ${machine}`));
|
||||
const said = await must(machine, `${HOST_PATH} enrol --token ${quote(token)}`);
|
||||
assert.match(said, new RegExp(`enrolled as ${machine}`), said);
|
||||
await must(machine, `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
|
||||
}
|
||||
|
||||
// The operator provides the media library: the ADR-0051 `access` resources CONFIRM these paths and
|
||||
// the media containers mount them, but the mesh creates none of it. Without this the media stack's
|
||||
// apply is refused ("the path is not present").
|
||||
await must(NODE, `mkdir -p ${MEDIA_DIRS.join(" ")}`);
|
||||
}, { timeout: 2_700_000 });
|
||||
|
||||
after(async () => {
|
||||
if (instanceId) await destroy(instanceId);
|
||||
await destroyAll(`${SCENARIO}-`);
|
||||
}, { timeout: 900_000 });
|
||||
|
||||
test("the whole ace service set resolves, installs and converges on one node in one push", {
|
||||
skip, timeout: 3_300_000,
|
||||
}, async () => {
|
||||
for (const d of DROPPED) console.log(`DROPPED ${d.name}: ${d.why}`);
|
||||
|
||||
// The overlay, so a consumer's binding `at` is non-empty (baserow/letta reach postgres/redis).
|
||||
await mesh("overlay place anchor --hub --endpoint 192.0.2.10:51820 --site lab");
|
||||
await mesh(`overlay place ${NODE} --site lab`);
|
||||
await mesh("assign anchor networking");
|
||||
await mesh(`assign ${NODE} networking`);
|
||||
|
||||
// Add / issue / assign, resiliently: a module the node cannot host is recorded and skipped so one
|
||||
// bad assignment cannot poison the whole-node push.
|
||||
const issued: string[] = [];
|
||||
const assigned = new Set<string>();
|
||||
const refused: { name: string; why: string }[] = [];
|
||||
for (const { name } of MODULES) {
|
||||
if (DROPPED.some((d) => d.name === name)) continue;
|
||||
try {
|
||||
const { manifest, broker } = loadManifest(name);
|
||||
await must("anchor", `printf %s ${quote(manifest)} > /tmp/${name}.json && docker cp /tmp/${name}.json mesh-control:/${name}.json`);
|
||||
await mesh(`module add /${name}.json`);
|
||||
if (broker) {
|
||||
await mesh(`module issue ${name} --node ${NODE}`);
|
||||
issued.push(name);
|
||||
}
|
||||
await mesh(`assign ${NODE} ${name}`);
|
||||
assigned.add(name);
|
||||
} catch (err) {
|
||||
const why = (err as Error).message.split("\n").map((l) => l.trim()).filter(Boolean).slice(1, 5).join(" | ");
|
||||
refused.push({ name, why });
|
||||
console.log(`NOT ASSIGNED ${name}: ${why}`);
|
||||
}
|
||||
}
|
||||
console.log(`issued broker accounts for: ${issued.length} modules`);
|
||||
if (refused.length) console.log(`refused (node cannot host): ${refused.map((r) => r.name).join(", ")}`);
|
||||
|
||||
// ONE push.
|
||||
let pushError = "";
|
||||
try {
|
||||
await mesh(`push ${NODE}`, 180_000);
|
||||
} catch (err) {
|
||||
pushError = (err as Error).message;
|
||||
console.log(`PUSH REJECTED:\n${pushError}`);
|
||||
}
|
||||
|
||||
// Wait for every CORE container to be up (the node pulls ~20GiB of images first), bounded.
|
||||
const coreContainers = MODULES.filter((m) => CORE.has(m.name) && assigned.has(m.name))
|
||||
.flatMap((m) => m.containers);
|
||||
const psNames = async (): Promise<Map<string, string>> => {
|
||||
const out = (await on(NODE, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
|
||||
const map = new Map<string, string>();
|
||||
for (const line of out.split("\n")) {
|
||||
const [n, ...rest] = line.split("\t");
|
||||
if (n) map.set(n.trim(), rest.join("\t").trim());
|
||||
}
|
||||
return map;
|
||||
};
|
||||
let psMap = new Map<string, string>();
|
||||
if (!pushError) {
|
||||
const until = Date.now() + 2_700_000;
|
||||
while (Date.now() < until) {
|
||||
psMap = await psNames();
|
||||
if (coreContainers.every((c) => (psMap.get(c) ?? "").startsWith("Up"))) break;
|
||||
await new Promise((r) => setTimeout(r, 8000));
|
||||
}
|
||||
await new Promise((r) => setTimeout(r, 20000)); // let first-boot bounces settle
|
||||
}
|
||||
psMap = await psNames();
|
||||
const final = await nodeState(NODE);
|
||||
const running = (name: string): boolean => (psMap.get(name) ?? "").startsWith("Up");
|
||||
// A run-once (mosquitto's dynsec bootstrap) seeds state and exits; the mesh removes it on success,
|
||||
// so absent-from-`docker ps -a` means it completed and was reaped (the node is applied+current, so
|
||||
// its resource did apply). Present means it must be up or have exited cleanly.
|
||||
const ranOnce = (name: string): boolean => !psMap.has(name) || /^(Up|Exited \(0\))/.test(psMap.get(name) ?? "");
|
||||
|
||||
const users = (await on("anchor", `docker exec mesh-broker lavinmqctl list_users 2>&1`)).out;
|
||||
|
||||
// ================================================================================================
|
||||
// The per-module report — the deliverable.
|
||||
// ================================================================================================
|
||||
const report: string[] = [];
|
||||
report.push("================ WHOLE-MESH ace CONVERGENCE ================");
|
||||
report.push(`node reached=${final.reached} applied=${final.applied} current=${final.current} waiting=${final.waiting}`);
|
||||
if (pushError) report.push(`PUSH REJECTED (resolver): ${pushError.split("\n").slice(0, 8).join("\n ")}`);
|
||||
const failedResources = final.wrong?.failed ?? [];
|
||||
if (final.wrong) {
|
||||
report.push(`NODE WRONG: outcome=${final.wrong.outcome} refused=${final.wrong.refused ?? "-"}`);
|
||||
for (const f of failedResources) report.push(` failed ${f.id}: ${f.error}`);
|
||||
}
|
||||
if (DROPPED.length) {
|
||||
report.push("---- DROPPED ----");
|
||||
for (const d of DROPPED) report.push(` ${d.name.padEnd(16)} ${d.why}`);
|
||||
}
|
||||
if (refused.length) {
|
||||
report.push("---- REFUSED at assign ----");
|
||||
for (const r of refused) report.push(` ${r.name.padEnd(16)} ${r.why}`);
|
||||
}
|
||||
const line = (mod: typeof MODULES[number]): { text: string; ok: boolean } => {
|
||||
const states = mod.containers.map((c) => `${c}:${running(c) ? "UP" : (psMap.get(c) ?? "MISSING")}`);
|
||||
const extra = (mod.runOnce ?? []).map((c) => `${c}:${ranOnce(c) ? "ran" : (psMap.get(c) ?? "MISSING")}`);
|
||||
const ok = mod.containers.every(running) && (mod.runOnce ?? []).every(ranOnce);
|
||||
return { text: `${mod.name.padEnd(16)} ${ok ? "OK " : "GAP "} ${[...states, ...extra].join(" ")}`, ok };
|
||||
};
|
||||
report.push("---- CORE (gates green) ----");
|
||||
const coreFailures: string[] = [];
|
||||
const gaps: string[] = [];
|
||||
for (const mod of MODULES) {
|
||||
if (!assigned.has(mod.name)) continue;
|
||||
const { text, ok } = line(mod);
|
||||
if (CORE.has(mod.name)) {
|
||||
report.push(` ${text}`);
|
||||
if (!ok) coreFailures.push(mod.name);
|
||||
} else {
|
||||
gaps.push(` ${text}`);
|
||||
}
|
||||
}
|
||||
report.push("---- KNOWN GAPS (reported, escalated, do NOT gate green) ----");
|
||||
for (const g of gaps) report.push(g);
|
||||
report.push(`broker accounts issued: ${issued.filter((n) => new RegExp(`${NODE}-${n}\\b`).test(users)).length}/${issued.length} present`);
|
||||
const summary = report.join("\n");
|
||||
console.log(summary);
|
||||
|
||||
// Diagnostics for anything not up: exact crash cause per container.
|
||||
const toDump = MODULES.filter((m) => assigned.has(m.name) && (coreFailures.includes(m.name) || KNOWN_GAPS.has(m.name)));
|
||||
if (toDump.length) {
|
||||
console.log(`\n---- ${NODE} mesh-host.log tail ----\n${(await on(NODE, `tail -60 /var/log/mesh-host.log`)).out}`);
|
||||
for (const mod of toDump) {
|
||||
for (const c of mod.containers) {
|
||||
if (psMap.has(c) && !running(c)) {
|
||||
console.log(`\n---- logs: ${c} (${psMap.get(c)}) ----\n${(await on(NODE, `docker logs ${c} 2>&1 | tail -20`)).out}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ================================================================================================
|
||||
// GREEN = the whole set RESOLVED (push accepted), every CORE module converged whole, and no CORE
|
||||
// resource failed to apply. KNOWN_GAPS and DROPPED are reported and escalated but do not gate.
|
||||
// ================================================================================================
|
||||
assert.equal(pushError, "", `the whole set did not resolve — push was rejected:\n${pushError}`);
|
||||
const coreResourceFailures = failedResources.filter((f) => CORE.has(f.id.split(".")[0] ?? ""));
|
||||
assert.deepEqual(coreResourceFailures, [],
|
||||
`a CORE resource failed to apply:\n${coreResourceFailures.map((f) => `${f.id}: ${f.error}`).join("\n")}\n${summary}`);
|
||||
assert.deepEqual(coreFailures, [],
|
||||
`these CORE modules did not converge whole: ${coreFailures.join(", ")}\n${summary}`);
|
||||
});
|
||||
@@ -0,0 +1,548 @@
|
||||
/**
|
||||
* The FULL mesh: both server sets on ONE substrate, converging together — the final stage of the
|
||||
* whole-mesh rehearsal (novox/hq). Combines whole-mesh-novox.test.ts and whole-mesh-ace.test.ts.
|
||||
*
|
||||
* anchor — substrate ONLY (store, broker, control).
|
||||
* novox — the 18-module novox set (whole-mesh-novox): providers, web apps, route-proxy, mailu,
|
||||
* firewall, fail2ban. fail2ban is now HOSTABLE: the dry-run fixes (mesh-control/catalog
|
||||
* main) changed its declared capability from the never-detected "intrusion-prevention" to
|
||||
* "firewall", the detector every node with nft already advertises.
|
||||
* ace — the 24-module ace set (whole-mesh-ace): the media/home stack; its /services/media
|
||||
* library is pre-created so the ADR-0051 `accesses` resolve.
|
||||
*
|
||||
* An overlay is placed across all three so cross-node `at` resolves. Each service node is
|
||||
* self-contained (its own postgres/redis), so nothing crosses a node boundary except enrolment and
|
||||
* the shared broker/store on anchor. The four modules both nodes run (postgres, redis, mssql,
|
||||
* portainer) are ADDED once and assigned to each node; each gets its own per-node broker account.
|
||||
*
|
||||
* THE DRY-RUN FIXES THIS RUN PROVES (mesh-control + mesh-catalog main):
|
||||
* - fail2ban is HOSTABLE (capability "firewall"): it is assigned, not refused. Before, it declared
|
||||
* the never-detected "intrusion-prevention" capability, so no node could host it and its
|
||||
* un-hostable assignment refused the whole node's push. Hostability is the gate. Its service
|
||||
* reaching active is a host concern this offline lab cannot meet — the VM ships nftables (so the
|
||||
* firewall detector is advertised) but not fail2ban, and the isolated segment has no route to the
|
||||
* package mirror, so pacman cannot fetch it. That is a documented lab gap, reported not gated.
|
||||
* - the 7 tool-runtime credential modules (ace: plex, bazarr, ombi, home-assistant, nzbget,
|
||||
* qbittorrent; novox: umami) now read their app credential from an operator-provided own-secret.
|
||||
* This bed delivers a FAKE value for each through the real operator path (`secret accept`)
|
||||
* BEFORE the push, and gates on the sidecar getting PAST its old "no credential" crash (it reads
|
||||
* the delivered value). A fake value will not authenticate against the real app — the sidecar may
|
||||
* still fail at app-auth, which is expected and does NOT gate; only the crash being GONE gates.
|
||||
*
|
||||
* It otherwise tolerates the SAME known gaps the per-server beds proved and escalated (the credential
|
||||
* sidecars' app-auth failures, photos/mailu, and firewall's oneshot nftables.service); it gates green
|
||||
* on each node's CORE converging whole and on no NON-GAP resource failing to apply — i.e. the two
|
||||
* node-plans converge together on one substrate.
|
||||
*
|
||||
* MESH_LAB_HOST_BINARY=.../mesh-host MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
|
||||
*/
|
||||
|
||||
import { test, before, after } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { existsSync, readFileSync } from "node:fs";
|
||||
import { dirname, resolve } from "node:path";
|
||||
import { loadScenario } from "../../src/declaration/parse.ts";
|
||||
import { raise } from "../../src/lifecycle/raise.ts";
|
||||
import { destroy, exec } from "../../src/lifecycle/operate.ts";
|
||||
import { hostBinaryPath, HOST_PATH } from "../../src/lifecycle/place.ts";
|
||||
import { labIsUsable, destroyAll } from "./harness.ts";
|
||||
|
||||
const capability = await labIsUsable();
|
||||
const binary = hostBinaryPath();
|
||||
const bundle = process.env["MESH_LAB_BUNDLE"] ?? "";
|
||||
const modulesEnv = process.env["MESH_LAB_MODULES"] ?? "";
|
||||
|
||||
const skip = !capability.usable
|
||||
? `lab not usable: ${capability.why}`
|
||||
: !binary || !existsSync(binary)
|
||||
? "MESH_LAB_HOST_BINARY is not set to a built mesh-host"
|
||||
: !bundle || !existsSync(bundle)
|
||||
? "MESH_LAB_BUNDLE is not set to a substrate bundle (mesh-host examples/)"
|
||||
: false;
|
||||
|
||||
const SCENARIO = "whole-mesh-full";
|
||||
|
||||
const catalogDir = process.env["MESH_LAB_CATALOG"]
|
||||
?? (modulesEnv ? resolve(dirname(dirname(dirname(modulesEnv))), "mesh-catalog", "modules") : "")
|
||||
?? resolve(process.cwd(), "..", "mesh-catalog", "modules");
|
||||
|
||||
const MEDIA_DIRS = [
|
||||
"/services/media/series", "/services/media/anime", "/services/media/movies",
|
||||
"/services/media/music", "/services/media/audiobooks", "/services/media/downloads",
|
||||
"/services/media/books",
|
||||
];
|
||||
|
||||
type Mod = { name: string; containers: string[]; node?: boolean; runOnce?: string[] };
|
||||
|
||||
/** The novox node's 17-module set (fail2ban dropped). CORE gates; the rest are documented gaps. */
|
||||
const NOVOX: Mod[] = [
|
||||
{ name: "postgres", containers: ["postgres", "mesh-postgres"] },
|
||||
{ name: "redis", containers: ["redis", "mesh-redis"] },
|
||||
{ name: "minio", containers: ["minio", "mesh-minio"] },
|
||||
{ name: "mongodb", containers: ["mongo", "mesh-mongodb"] },
|
||||
{ name: "mssql", containers: ["mssql", "mesh-mssql"] },
|
||||
{ name: "keycloak", containers: ["keycloak", "mesh-keycloak"] },
|
||||
{ name: "gitea", containers: ["gitea", "mesh-gitea"] },
|
||||
{ name: "nextcloud", containers: ["nextcloud", "mesh-nextcloud"] },
|
||||
{ name: "umami", containers: ["umami", "mesh-umami"] },
|
||||
{ name: "photos", containers: ["photos", "mesh-photos"] },
|
||||
{ name: "invoicing", containers: ["invoicing-app", "invoicing-api"] },
|
||||
{ name: "portainer", containers: ["portainer", "mesh-portainer"] },
|
||||
{ name: "verdaccio", containers: ["verdaccio", "mesh-verdaccio"] },
|
||||
{ name: "registry", containers: ["mesh-registry"] },
|
||||
{ name: "route-proxy", containers: ["route-proxy"] },
|
||||
{
|
||||
name: "mailu",
|
||||
containers: [
|
||||
"mailu-resolver", "mailu-redis", "mailu-admindb", "mailu-admin", "mailu-imap",
|
||||
"mailu-smtp", "mailu-antispam", "mailu-webmail", "mailu-front", "mesh-mailu",
|
||||
],
|
||||
},
|
||||
{ name: "firewall", containers: [], node: true },
|
||||
{ name: "fail2ban", containers: [], node: true },
|
||||
];
|
||||
const CORE_NOVOX = new Set([
|
||||
"postgres", "redis", "minio", "mongodb", "mssql",
|
||||
"keycloak", "gitea", "nextcloud", "invoicing",
|
||||
"portainer", "verdaccio", "registry", "route-proxy",
|
||||
]);
|
||||
const GAPS_NOVOX = new Set(["umami", "photos", "mailu", "firewall", "fail2ban"]);
|
||||
|
||||
/** The ace node's 24-module set. */
|
||||
const ACE: Mod[] = [
|
||||
{ name: "postgres", containers: ["postgres", "mesh-postgres"] },
|
||||
{ name: "redis", containers: ["redis", "mesh-redis"] },
|
||||
{ name: "mssql", containers: ["mssql", "mesh-mssql"] },
|
||||
{ name: "sonarr", containers: ["sonarr", "mesh-sonarr"] },
|
||||
{ name: "radarr", containers: ["radarr", "mesh-radarr"] },
|
||||
{ name: "lidarr", containers: ["lidarr", "mesh-lidarr"] },
|
||||
{ name: "plex", containers: ["plex", "mesh-plex"] },
|
||||
{ name: "bazarr", containers: ["bazarr", "mesh-bazarr"] },
|
||||
{ name: "nzbget", containers: ["nzbget", "mesh-nzbget"] },
|
||||
{ name: "qbittorrent", containers: ["qbittorrent", "mesh-qbittorrent"] },
|
||||
{ name: "jackett", containers: ["jackett", "mesh-jackett"] },
|
||||
{ name: "ombi", containers: ["ombi", "mesh-ombi"] },
|
||||
{ name: "tautulli", containers: ["tautulli", "mesh-tautulli"] },
|
||||
{ name: "bookshelf", containers: ["bookshelf", "mesh-bookshelf"] },
|
||||
{ name: "home-assistant", containers: ["home-assistant", "mesh-home-assistant"] },
|
||||
{ name: "mosquitto", containers: ["mosquitto", "mesh-mosquitto"], runOnce: ["mosquitto-bootstrap"] },
|
||||
{ name: "influxdb", containers: ["influxdb", "mesh-influxdb"] },
|
||||
{ name: "grafana", containers: ["grafana", "mesh-grafana"] },
|
||||
{ name: "baserow", containers: ["baserow", "mesh-baserow"] },
|
||||
{ name: "letta", containers: ["letta", "mesh-letta"] },
|
||||
{ name: "nodered", containers: ["nodered", "mesh-nodered"] },
|
||||
{ name: "searxng", containers: ["valkey", "searxng", "mesh-searxng"] },
|
||||
{ name: "unifi", containers: ["unifi-controller", "mesh-unifi"] },
|
||||
{ name: "portainer", containers: ["portainer", "mesh-portainer"] },
|
||||
];
|
||||
const CORE_ACE = new Set([
|
||||
"postgres", "redis", "mssql",
|
||||
"sonarr", "radarr", "lidarr", "jackett", "tautulli", "bookshelf",
|
||||
"mosquitto", "influxdb", "grafana", "baserow", "nodered", "searxng", "unifi", "portainer",
|
||||
]);
|
||||
const GAPS_ACE = new Set(["plex", "bazarr", "nzbget", "qbittorrent", "ombi", "home-assistant", "letta"]);
|
||||
|
||||
const PLAN: { node: string; mods: Mod[]; core: Set<string>; gaps: Set<string> }[] = [
|
||||
{ node: "novox", mods: NOVOX, core: CORE_NOVOX, gaps: GAPS_NOVOX },
|
||||
{ node: "ace", mods: ACE, core: CORE_ACE, gaps: GAPS_ACE },
|
||||
];
|
||||
|
||||
/**
|
||||
* Host-port remaps (per module — host ports are per-VM, so novox's and ace's never clash). Union of
|
||||
* both per-server beds' remaps.
|
||||
*/
|
||||
const REMAP: Record<string, Record<string, string>> = {
|
||||
nextcloud: { "80": "8090:80" },
|
||||
umami: { "3000": "3090:3000" },
|
||||
invoicing: { "80": "8091:80", "9000": "9091:9000" },
|
||||
qbittorrent: { "8080": "8090:8080" },
|
||||
searxng: { "8080": "8092:8080" },
|
||||
nzbget: { "6789": "6790:6789" },
|
||||
};
|
||||
|
||||
/**
|
||||
* The 7 tool-runtime credential modules (novox/hq dry-run fix). Each now reads its app credential
|
||||
* from an operator-provided own-secret (`name`, an own-secret path in its module.json), mounted into
|
||||
* the sidecar at MESH_*_FILE. This bed delivers a FAKE value for each via the real operator path
|
||||
* (`secret accept <node> <module> <name> --from <file>`) BEFORE the push, and asserts the sidecar
|
||||
* gets PAST `crash` — the exact message its client threw when nothing was mounted. A fake value does
|
||||
* not authenticate against the real app, so the sidecar may still fail later at app-auth (expected,
|
||||
* not gated); only the "no credential" crash being GONE proves the wiring and gates.
|
||||
*/
|
||||
const CREDENTIALS: { node: string; module: string; name: string; crash: string }[] = [
|
||||
{ node: "ace", module: "plex", name: "token", crash: "no Plex token" },
|
||||
{ node: "ace", module: "bazarr", name: "api-key", crash: "no Bazarr API key" },
|
||||
{ node: "ace", module: "ombi", name: "api-key", crash: "no Ombi API key" },
|
||||
{ node: "ace", module: "home-assistant", name: "token", crash: "no Home Assistant token" },
|
||||
{ node: "ace", module: "nzbget", name: "password", crash: "NZBGet not configured" },
|
||||
{ node: "ace", module: "qbittorrent", name: "password", crash: "qBittorrent not configured" },
|
||||
{ node: "novox", module: "umami", name: "admin", crash: "admin password is not set" },
|
||||
];
|
||||
|
||||
let instanceId = "";
|
||||
let stocked: string[] = [];
|
||||
|
||||
function quote(s: string): string {
|
||||
return `'${s.replaceAll("'", `'\\''`)}'`;
|
||||
}
|
||||
|
||||
async function on(machine: string, command: string, timeoutMs?: number): Promise<{ out: string; ok: boolean }> {
|
||||
const { stdout } = await exec(instanceId, machine, [
|
||||
"sh", "-c", `exec 2>&1\n${command}\necho "__exit=$?"`,
|
||||
], timeoutMs);
|
||||
const marker = stdout.lastIndexOf("__exit=");
|
||||
if (marker < 0) return { out: stdout, ok: false };
|
||||
return { out: stdout.slice(0, marker), ok: stdout.slice(marker + 7).trim() === "0" };
|
||||
}
|
||||
|
||||
async function must(machine: string, command: string, timeoutMs?: number): Promise<string> {
|
||||
const { out, ok } = await on(machine, command, timeoutMs);
|
||||
if (!ok) throw new Error(`${machine}: ${command}\n${out}`);
|
||||
return out;
|
||||
}
|
||||
|
||||
async function mesh(command: string, timeoutMs?: number): Promise<string> {
|
||||
return must("anchor", `docker exec mesh-control /mesh-control ${command}`, timeoutMs);
|
||||
}
|
||||
|
||||
function repositoryFor(reference: string): string {
|
||||
const withoutDigest = reference.split("@")[0] ?? reference;
|
||||
const lastColon = withoutDigest.lastIndexOf(":");
|
||||
const lastSlash = withoutDigest.lastIndexOf("/");
|
||||
return lastColon > lastSlash ? withoutDigest.slice(0, lastColon) : withoutDigest;
|
||||
}
|
||||
|
||||
function pinned(repository: string): string {
|
||||
const found = stocked.find((r) => r.slice(r.indexOf("/") + 1, r.indexOf("@")) === repository);
|
||||
assert.ok(found, `the scenario stocks no ${repository}; it serves\n ${stocked.join("\n ")}`);
|
||||
return found;
|
||||
}
|
||||
|
||||
function bundleFor(images: string[]): string {
|
||||
let text = readFileSync(bundle, "utf8");
|
||||
for (const ref of images) {
|
||||
const repository = ref.slice(ref.indexOf("/") + 1, ref.indexOf("@"));
|
||||
const escaped = repository.replaceAll("/", "\\/").replaceAll(".", "\\.");
|
||||
text = text.replaceAll(new RegExp(`[A-Za-z0-9_.:-]+\\/${escaped}@sha256:[0-9a-f]+`, "g"), ref);
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
function loadManifest(name: string): { manifest: string; broker: boolean } {
|
||||
const path = resolve(catalogDir, name, "module.json");
|
||||
const m = JSON.parse(readFileSync(path, "utf8")) as {
|
||||
resources?: { type: string; image?: string; ports?: string[] }[];
|
||||
};
|
||||
const remap = REMAP[name] ?? {};
|
||||
for (const r of m.resources ?? []) {
|
||||
if (r.type !== "container") continue;
|
||||
if (typeof r.image === "string") r.image = pinned(repositoryFor(r.image));
|
||||
if (Array.isArray(r.ports)) r.ports = r.ports.map((p) => remap[p] ?? p);
|
||||
}
|
||||
const manifest = JSON.stringify(m);
|
||||
return { manifest, broker: manifest.includes("MESH_BROKER_FILE") };
|
||||
}
|
||||
|
||||
function tokenFrom(said: string): string {
|
||||
const found = said.split("\n").map((l) => l.trim()).find((l) => l.length > 100 && !l.includes(" "));
|
||||
assert.ok(found, `no token in:\n${said}`);
|
||||
return found;
|
||||
}
|
||||
|
||||
interface NodeState {
|
||||
reached: boolean;
|
||||
applied: boolean;
|
||||
current: boolean;
|
||||
waiting: boolean;
|
||||
wrong?: { outcome: string; refused?: string | undefined; failed?: { id: string; error: string }[] | undefined } | undefined;
|
||||
raw: string;
|
||||
}
|
||||
|
||||
async function nodeState(node: string): Promise<NodeState> {
|
||||
const asked = await on("anchor", `docker exec mesh-control /mesh-control status --json`);
|
||||
if (!asked.ok) return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
|
||||
let state: {
|
||||
wrong: { node: string; outcome: string; refused?: string; failed?: { id: string; error: string }[] }[];
|
||||
waiting: { node: string }[];
|
||||
reported: { node: string; outcome: string; current: boolean }[];
|
||||
};
|
||||
try {
|
||||
state = JSON.parse(asked.out);
|
||||
} catch {
|
||||
return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
|
||||
}
|
||||
const word = state.reported.find((r) => r.node === node);
|
||||
const bad = state.wrong.find((w) => w.node === node);
|
||||
return {
|
||||
reached: true,
|
||||
applied: word?.outcome === "applied",
|
||||
current: !!word?.current,
|
||||
waiting: state.waiting.some((w) => w.node === node),
|
||||
wrong: bad ? { outcome: bad.outcome, refused: bad.refused, failed: bad.failed } : undefined,
|
||||
raw: asked.out,
|
||||
};
|
||||
}
|
||||
|
||||
async function psMapOf(node: string): Promise<Map<string, string>> {
|
||||
const out = (await on(node, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
|
||||
const map = new Map<string, string>();
|
||||
for (const line of out.split("\n")) {
|
||||
const [n, ...rest] = line.split("\t");
|
||||
if (n) map.set(n.trim(), rest.join("\t").trim());
|
||||
}
|
||||
return map;
|
||||
}
|
||||
|
||||
before(async () => {
|
||||
if (skip) return;
|
||||
assert.ok(existsSync(catalogDir), `mesh-catalog modules not found at ${catalogDir}`);
|
||||
|
||||
const raised = await raise(loadScenario(`scenarios/${SCENARIO}.yml`), {
|
||||
onProgress: (m) => console.log(`raise: ${m}`),
|
||||
});
|
||||
instanceId = raised.instanceId;
|
||||
stocked = raised.images;
|
||||
|
||||
await must("anchor", `cat > /tmp/substrate.lock <<'MESHBUNDLE'\n${bundleFor(raised.images)}\nMESHBUNDLE`);
|
||||
await must("anchor", `${HOST_PATH} apply /tmp/substrate.lock`, 900_000);
|
||||
const up = await must("anchor", `docker ps --format '{{.Names}}'`);
|
||||
for (const c of ["mesh-store", "mesh-broker", "mesh-control"]) {
|
||||
assert.match(up, new RegExp(c), `the substrate did not raise ${c}:\n${up}`);
|
||||
}
|
||||
|
||||
for (const machine of ["anchor", "novox", "ace"]) {
|
||||
await mesh(`node add ${machine}`);
|
||||
const token = tokenFrom(await mesh(`token issue --node ${machine}`));
|
||||
const said = await must(machine, `${HOST_PATH} enrol --token ${quote(token)}`);
|
||||
assert.match(said, new RegExp(`enrolled as ${machine}`), said);
|
||||
await must(machine, `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
|
||||
}
|
||||
|
||||
// The operator provides ace's media library (ADR 0051 accesses confirm the paths, create nothing).
|
||||
await must("ace", `mkdir -p ${MEDIA_DIRS.join(" ")}`);
|
||||
}, { timeout: 3_000_000 });
|
||||
|
||||
after(async () => {
|
||||
if (instanceId) await destroy(instanceId);
|
||||
await destroyAll(`${SCENARIO}-`);
|
||||
}, { timeout: 900_000 });
|
||||
|
||||
test("both server sets converge together on one substrate", { skip, timeout: 3_600_000 }, async () => {
|
||||
// Overlay across all three, so every node's private address exists and cross-node `at` resolves.
|
||||
await mesh("overlay place anchor --hub --endpoint 192.0.2.10:51820 --site lab");
|
||||
await mesh("overlay place novox --site lab");
|
||||
await mesh("overlay place ace --site lab");
|
||||
await mesh("assign anchor networking");
|
||||
await mesh("assign novox networking");
|
||||
await mesh("assign ace networking");
|
||||
|
||||
// Add every unique module ONCE (the four shared modules are added once, assigned to each node), then
|
||||
// issue a per-node broker account and assign, resiliently.
|
||||
const added = new Map<string, boolean>(); // name -> needs broker
|
||||
async function ensureAdded(name: string): Promise<boolean> {
|
||||
const known = added.get(name);
|
||||
if (known !== undefined) return known;
|
||||
const { manifest, broker } = loadManifest(name);
|
||||
await must("anchor", `printf %s ${quote(manifest)} > /tmp/${name}.json && docker cp /tmp/${name}.json mesh-control:/${name}.json`);
|
||||
await mesh(`module add /${name}.json`);
|
||||
added.set(name, broker);
|
||||
return broker;
|
||||
}
|
||||
|
||||
const assigned: Record<string, Set<string>> = { novox: new Set(), ace: new Set() };
|
||||
const refused: Record<string, { name: string; why: string }[]> = { novox: [], ace: [] };
|
||||
for (const { node, mods } of PLAN) {
|
||||
for (const { name } of mods) {
|
||||
try {
|
||||
const broker = await ensureAdded(name);
|
||||
if (broker) await mesh(`module issue ${name} --node ${node}`);
|
||||
await mesh(`assign ${node} ${name}`);
|
||||
assigned[node]!.add(name);
|
||||
} catch (err) {
|
||||
const why = (err as Error).message.split("\n").map((l) => l.trim()).filter(Boolean).slice(1, 5).join(" | ");
|
||||
refused[node]!.push({ name, why });
|
||||
console.log(`NOT ASSIGNED ${node}/${name}: ${why}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Operator-provided app credentials (novox/hq dry-run fix). BEFORE the push, hand the mesh a FAKE
|
||||
// value for each of the 7 credential modules through the real operator path — `secret accept`,
|
||||
// which seals the value to the node and records it as `accepted` (the mesh will not invent one).
|
||||
// The push then delivers it to the sidecar's own-secret path. The `--from` file is staged into the
|
||||
// mesh-control container (one file per distinct secret name). A module the node could not host is
|
||||
// skipped (its secret has nowhere to go).
|
||||
const credentialDelivered = new Map<string, boolean>();
|
||||
for (const name of new Set(CREDENTIALS.map((c) => c.name))) {
|
||||
await must("anchor", `printf %s ${quote(`fake-${name}-value`)} > /tmp/fake-${name} && docker cp /tmp/fake-${name} mesh-control:/fake-${name}`);
|
||||
}
|
||||
for (const c of CREDENTIALS) {
|
||||
if (!assigned[c.node]!.has(c.module)) {
|
||||
credentialDelivered.set(`${c.node}/${c.module}`, false);
|
||||
console.log(`CREDENTIAL SKIPPED ${c.node}/${c.module}: not assigned, nowhere to deliver`);
|
||||
continue;
|
||||
}
|
||||
try {
|
||||
await mesh(`secret accept ${c.node} ${c.module} ${c.name} --from /fake-${c.name}`);
|
||||
credentialDelivered.set(`${c.node}/${c.module}`, true);
|
||||
} catch (err) {
|
||||
credentialDelivered.set(`${c.node}/${c.module}`, false);
|
||||
console.log(`CREDENTIAL ACCEPT FAILED ${c.node}/${c.module}: ${(err as Error).message.split("\n").slice(0, 3).join(" | ")}`);
|
||||
}
|
||||
}
|
||||
|
||||
// ONE push per node.
|
||||
const pushError: Record<string, string> = { novox: "", ace: "" };
|
||||
for (const node of ["novox", "ace"]) {
|
||||
try {
|
||||
await mesh(`push ${node}`, 240_000);
|
||||
} catch (err) {
|
||||
pushError[node] = (err as Error).message;
|
||||
console.log(`PUSH REJECTED (${node}):\n${pushError[node]}`);
|
||||
}
|
||||
}
|
||||
|
||||
// Wait for both nodes' CORE containers to come up (they pull concurrently from the one registry).
|
||||
const psMaps: Record<string, Map<string, string>> = { novox: new Map(), ace: new Map() };
|
||||
for (const { node, mods, core } of PLAN) {
|
||||
if (pushError[node]) continue;
|
||||
const coreContainers = mods.filter((m) => core.has(m.name) && assigned[node]!.has(m.name)).flatMap((m) => m.containers);
|
||||
const until = Date.now() + 2_700_000;
|
||||
while (Date.now() < until) {
|
||||
psMaps[node] = await psMapOf(node);
|
||||
if (coreContainers.every((c) => (psMaps[node]!.get(c) ?? "").startsWith("Up"))) break;
|
||||
await new Promise((r) => setTimeout(r, 10000));
|
||||
}
|
||||
}
|
||||
await new Promise((r) => setTimeout(r, 20000)); // let first-boot bounces settle
|
||||
|
||||
// ================================================================================================
|
||||
// Per-node report + gating. GREEN = each node's push accepted, every CORE module converged whole,
|
||||
// no NON-GAP resource failed to apply, fail2ban is hostable (assigned, not refused), and every
|
||||
// credential sidecar advanced past its "no credential" crash. Tolerated: the credential sidecars'
|
||||
// app-auth failures (bogus fake value), photos/mailu, firewall's oneshot nftables.service, and
|
||||
// fail2ban's package (the offline lab cannot fetch it — a documented host gap).
|
||||
// ================================================================================================
|
||||
const users = (await on("anchor", `docker exec mesh-broker lavinmqctl list_users 2>&1`)).out;
|
||||
const allProblems: string[] = [];
|
||||
const report: string[] = ["================ FULL MESH CONVERGENCE ================"];
|
||||
|
||||
for (const { node, mods, core, gaps } of PLAN) {
|
||||
const psMap = psMaps[node] = await psMapOf(node);
|
||||
const st = await nodeState(node);
|
||||
const running = (name: string): boolean => (psMap.get(name) ?? "").startsWith("Up");
|
||||
const ranOnce = (name: string): boolean => !psMap.has(name) || /^(Up|Exited \(0\))/.test(psMap.get(name) ?? "");
|
||||
const failedResources = st.wrong?.failed ?? [];
|
||||
|
||||
report.push(`\n---- node ${node}: reached=${st.reached} applied=${st.applied} current=${st.current} waiting=${st.waiting} ----`);
|
||||
if (pushError[node]) report.push(` PUSH REJECTED: ${pushError[node].split("\n").slice(0, 6).join("\n ")}`);
|
||||
if (st.wrong) {
|
||||
report.push(` NODE WRONG: outcome=${st.wrong.outcome}`);
|
||||
for (const f of failedResources) report.push(` failed ${f.id}: ${f.error}`);
|
||||
}
|
||||
for (const r of refused[node]!) report.push(` REFUSED ${r.name}: ${r.why}`);
|
||||
|
||||
const coreFailures: string[] = [];
|
||||
for (const mod of mods) {
|
||||
if (!assigned[node]!.has(mod.name)) continue;
|
||||
const states = mod.containers.map((c) => `${c}:${running(c) ? "UP" : (psMap.get(c) ?? "MISSING")}`);
|
||||
const ok = mod.containers.every(running) && (mod.runOnce ?? []).every(ranOnce);
|
||||
const tag = core.has(mod.name) ? (ok ? "OK " : "FAIL") : (ok ? "ok " : "GAP ");
|
||||
report.push(` ${core.has(mod.name) ? "*" : " "} ${mod.name.padEnd(15)} ${tag} ${states.join(" ")}`);
|
||||
if (core.has(mod.name) && !ok) coreFailures.push(mod.name);
|
||||
}
|
||||
const issuedHere = mods.filter((m) => new RegExp(`${node}-${m.name}\\b`).test(users)).length;
|
||||
report.push(` broker accounts: ${issuedHere} present for ${node}`);
|
||||
|
||||
// Gate: push accepted, all CORE up, no NON-GAP resource failed. A failed resource names its
|
||||
// owning module inside the error (`applying "firewall.load": …`), not in `id` (which is the outer
|
||||
// "apply" key), so the owner is extracted from either — and a failure owned by a KNOWN_GAP module
|
||||
// (firewall's oneshot nftables.service) is tolerated.
|
||||
const gapOwnerOf = (f: { id: string; error: string }): string => {
|
||||
const m = f.error.match(/applying "([^".]+)\./);
|
||||
return m?.[1] ?? (f.id.split(".")[0] ?? "");
|
||||
};
|
||||
if (pushError[node]) allProblems.push(`${node}: push rejected`);
|
||||
if (coreFailures.length) allProblems.push(`${node}: CORE not converged: ${coreFailures.join(", ")}`);
|
||||
const nonGapFailed = failedResources.filter((f) => !gaps.has(gapOwnerOf(f)));
|
||||
if (nonGapFailed.length) allProblems.push(`${node}: non-gap resource failed: ${nonGapFailed.map((f) => `${f.id} (${f.error.slice(0, 60)})`).join(", ")}`);
|
||||
}
|
||||
|
||||
// ================================================================================================
|
||||
// The dry-run fixes, proved by name.
|
||||
// ================================================================================================
|
||||
|
||||
// fail2ban is now HOSTABLE (capability "firewall"): what the dry-run fix buys is that a node can
|
||||
// host it at all. Before, it declared the never-detected "intrusion-prevention" capability, so NO
|
||||
// node could host it AND its un-hostable assignment refused the whole node's push. So the GATE is
|
||||
// hostability: it must be ASSIGNED and NOT refused.
|
||||
//
|
||||
// Its systemd service reaching active is a SEPARATE, host-level concern this offline lab cannot
|
||||
// satisfy: the VM base image ships `nftables` (so firewall's package resolves and the `firewall`
|
||||
// detector is advertised — which is exactly why fail2ban is now hostable) but NOT `fail2ban`, and
|
||||
// the lab segment (RFC 5737 192.0.2.0/24) has no route to the package mirror, so pacman times out
|
||||
// fetching fail2ban and its deps. That is a documented LAB gap (fail2ban ∈ GAPS_NOVOX, so its
|
||||
// failed `fail2ban.package` resource is tolerated like firewall's oneshot nftables.service) — it is
|
||||
// reported, not gated. On an online node the package installs and the service runs.
|
||||
{
|
||||
const refusedF2B = refused["novox"]!.find((r) => r.name === "fail2ban");
|
||||
const assignedF2B = assigned["novox"]!.has("fail2ban");
|
||||
const active = (await on("novox", `systemctl is-active fail2ban 2>&1`)).out.trim();
|
||||
const pkg = (await on("novox", `pacman -Q fail2ban 2>&1`)).out.trim();
|
||||
report.push(`\n---- fail2ban (novox): HOSTABLE assigned=${assignedF2B} refused=${refusedF2B ? "YES" : "no"} | service=${active} package="${pkg}" ----`);
|
||||
if (refusedF2B) {
|
||||
allProblems.push(`fail2ban still not hostable on novox: ${refusedF2B.why}`);
|
||||
} else if (!assignedF2B) {
|
||||
allProblems.push(`fail2ban was not assigned to novox`);
|
||||
}
|
||||
if (active !== "active") {
|
||||
report.push(` service not active — offline lab could not install the package (documented gap, not gated); detail:`);
|
||||
report.push(` ${(await on("novox", `systemctl status fail2ban --no-pager 2>&1 | head -8`)).out}`);
|
||||
}
|
||||
}
|
||||
|
||||
// The 7 credential sidecars: each got its fake own-secret, so each must have advanced PAST the old
|
||||
// "no credential" crash (it read the delivered value). It may still fail at app-auth against the
|
||||
// real app with a bogus value — that is expected and does NOT gate; only the crash being gone does.
|
||||
report.push(`\n---- credential sidecars: past the "no credential" crash? (fake secret delivered) ----`);
|
||||
for (const c of CREDENTIALS) {
|
||||
const container = `mesh-${c.module}`;
|
||||
const psMap = psMaps[c.node]!;
|
||||
const status = (psMap.get(container) ?? "MISSING").split(" ")[0] ?? "MISSING";
|
||||
const delivered = credentialDelivered.get(`${c.node}/${c.module}`) ?? false;
|
||||
const logs = (await on(c.node, `docker logs ${container} 2>&1 | tail -60`)).out;
|
||||
const stillCrashes = logs.includes(c.crash);
|
||||
const appAuth = logs.split("\n").reverse().find((l) => /fail|reject|error|401|403|refused/i.test(l) && !l.includes(c.crash))?.trim().slice(0, 90) ?? "";
|
||||
report.push(` ${c.node}/${c.module.padEnd(15)} secret=${delivered ? "delivered" : "SKIPPED"} sidecar=${status.padEnd(10)} crash("${c.crash}")=${stillCrashes ? "STILL PRESENT" : "gone"}${appAuth ? ` last:"${appAuth}"` : ""}`);
|
||||
if (delivered && stillCrashes) {
|
||||
allProblems.push(`${c.node}/${c.module}: credential wiring did not take — sidecar still crashes "${c.crash}"`);
|
||||
}
|
||||
if (!delivered && assigned[c.node]!.has(c.module)) {
|
||||
allProblems.push(`${c.node}/${c.module}: fake credential was not delivered (secret accept failed)`);
|
||||
}
|
||||
}
|
||||
|
||||
const summary = report.join("\n");
|
||||
console.log(summary);
|
||||
|
||||
// Cross-node identity proof: each node's own scoped broker accounts exist and are distinct — the
|
||||
// two node-plans share one broker without colliding (both run a `postgres`, `redis`, `mssql`).
|
||||
for (const acct of ["novox-postgres", "ace-postgres", "novox-redis", "ace-redis"]) {
|
||||
if (!new RegExp(acct).test(users)) allProblems.push(`missing broker account ${acct}`);
|
||||
}
|
||||
|
||||
// Diagnostics for any CORE failure (the gaps are expected; a CORE failure is what we must see).
|
||||
for (const { node, mods, core } of PLAN) {
|
||||
const psMap = psMaps[node]!;
|
||||
for (const mod of mods) {
|
||||
if (!core.has(mod.name) || !assigned[node]!.has(mod.name)) continue;
|
||||
for (const c of mod.containers) {
|
||||
if (psMap.has(c) && !(psMap.get(c) ?? "").startsWith("Up")) {
|
||||
console.log(`\n---- ${node} logs: ${c} (${psMap.get(c)}) ----\n${(await on(node, `docker logs ${c} 2>&1 | tail -25`)).out}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
assert.deepEqual(allProblems, [], `the full mesh did not converge together:\n ${allProblems.join("\n ")}\n\n${summary}`);
|
||||
});
|
||||
@@ -0,0 +1,466 @@
|
||||
/**
|
||||
* The whole `novox` server's converted service set, installed together on ONE node behind the
|
||||
* substrate — the whole-catalogue install this rebuild has never actually run. First stage of a
|
||||
* whole-mesh rehearsal (novox/hq).
|
||||
*
|
||||
* Topology (proven by assigned-two-node-db.test.ts): the substrate (store, broker, control) rides
|
||||
* `anchor` and nothing else; ALL of novox's services ride the `novox` node. novox's own postgres
|
||||
* provider owns 5432 there, so it cannot co-locate with the substrate store. An overlay is placed so
|
||||
* each consumer's binding `at` resolves to novox's private address and reaches the providers
|
||||
* co-located with it.
|
||||
*
|
||||
* The SET (18 modules, all converted in mesh-catalog/modules/):
|
||||
* providers postgres redis minio mongodb mssql
|
||||
* consumers keycloak gitea nextcloud umami photos invoicing
|
||||
* apps portainer verdaccio registry route-proxy mailu
|
||||
* node-level firewall fail2ban
|
||||
*
|
||||
* Each committed module.json is LOADED from mesh-catalog — not hand-written — and its container
|
||||
* image references are rewritten to what this scenario's own registry serves by digest (the same
|
||||
* pinned(repositoryFor(image)) rule the two-node-db bed applies by hand). Two things this bed
|
||||
* discovered about the co-located set are handled at load time and RECORDED as findings:
|
||||
*
|
||||
* HOST-PORT COLLISIONS. When the whole set lands on one node with its committed host publishes,
|
||||
* several servers claim the same host port: nextcloud, invoicing-app and route-proxy all want 80;
|
||||
* minio and invoicing-api both want 9000; gitea and umami both want 3000. route-proxy is meant to
|
||||
* FRONT the web apps on 80/443, so the web apps' own host publishes are only for direct access.
|
||||
* To let the whole set converge, the colliding web/app host publishes are remapped to distinct
|
||||
* host ports here (container ports unchanged); the provider ports the consumers actually connect to
|
||||
* (postgres 5432, minio 9000, mongodb 27017, mssql 1433) are left as-is. See REMAP below.
|
||||
*
|
||||
* MESH_LAB_HOST_BINARY=.../mesh-host MESH_LAB_BUNDLE=.../examples/substrate-first-node.lock
|
||||
* scripts/build-module-runtime.sh builds one runtime per module that has code; the route-proxy image
|
||||
* is built by scripts/build-route-proxy-image.sh; scenarios/whole-mesh-novox.yml stocks them all
|
||||
* alongside every server image.
|
||||
*/
|
||||
|
||||
import { test, before, after } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { existsSync, readFileSync } from "node:fs";
|
||||
import { dirname, resolve } from "node:path";
|
||||
import { loadScenario } from "../../src/declaration/parse.ts";
|
||||
import { raise } from "../../src/lifecycle/raise.ts";
|
||||
import { destroy, exec } from "../../src/lifecycle/operate.ts";
|
||||
import { hostBinaryPath, HOST_PATH } from "../../src/lifecycle/place.ts";
|
||||
import { labIsUsable, destroyAll } from "./harness.ts";
|
||||
|
||||
const capability = await labIsUsable();
|
||||
const binary = hostBinaryPath();
|
||||
const bundle = process.env["MESH_LAB_BUNDLE"] ?? "";
|
||||
const modulesEnv = process.env["MESH_LAB_MODULES"] ?? "";
|
||||
|
||||
const skip = !capability.usable
|
||||
? `lab not usable: ${capability.why}`
|
||||
: !binary || !existsSync(binary)
|
||||
? "MESH_LAB_HOST_BINARY is not set to a built mesh-host"
|
||||
: !bundle || !existsSync(bundle)
|
||||
? "MESH_LAB_BUNDLE is not set to a substrate bundle (mesh-host examples/)"
|
||||
: false;
|
||||
|
||||
const SCENARIO = "whole-mesh-novox";
|
||||
const NODE = "novox";
|
||||
|
||||
/** Where the committed module.json files live: the mesh-catalog beside mesh-control. */
|
||||
const catalogDir = process.env["MESH_LAB_CATALOG"]
|
||||
?? (modulesEnv ? resolve(dirname(dirname(dirname(modulesEnv))), "mesh-catalog", "modules") : "")
|
||||
?? resolve(process.cwd(), "..", "mesh-catalog", "modules");
|
||||
|
||||
/**
|
||||
* The set, in dependency-reading order (the resolver accepts any order). Each row: the module, and
|
||||
* the container names it should bring up on the node. Node-level modules (firewall, fail2ban) bring
|
||||
* up no container — they install a package and run a service, checked separately.
|
||||
*/
|
||||
const MODULES: { name: string; containers: string[]; node?: boolean }[] = [
|
||||
{ name: "postgres", containers: ["postgres", "mesh-postgres"] },
|
||||
{ name: "redis", containers: ["redis", "mesh-redis"] },
|
||||
{ name: "minio", containers: ["minio", "mesh-minio"] },
|
||||
{ name: "mongodb", containers: ["mongo", "mesh-mongodb"] },
|
||||
{ name: "mssql", containers: ["mssql", "mesh-mssql"] },
|
||||
{ name: "keycloak", containers: ["keycloak", "mesh-keycloak"] },
|
||||
{ name: "gitea", containers: ["gitea", "mesh-gitea"] },
|
||||
{ name: "nextcloud", containers: ["nextcloud", "mesh-nextcloud"] },
|
||||
{ name: "umami", containers: ["umami", "mesh-umami"] },
|
||||
{ name: "photos", containers: ["photos", "mesh-photos"] },
|
||||
{ name: "invoicing", containers: ["invoicing-app", "invoicing-api"] },
|
||||
{ name: "portainer", containers: ["portainer", "mesh-portainer"] },
|
||||
{ name: "verdaccio", containers: ["verdaccio", "mesh-verdaccio"] },
|
||||
{ name: "registry", containers: ["mesh-registry"] },
|
||||
{ name: "route-proxy", containers: ["route-proxy"] },
|
||||
{
|
||||
name: "mailu",
|
||||
containers: [
|
||||
"mailu-resolver", "mailu-redis", "mailu-admindb", "mailu-admin", "mailu-imap",
|
||||
"mailu-smtp", "mailu-antispam", "mailu-webmail", "mailu-front", "mesh-mailu",
|
||||
],
|
||||
},
|
||||
{ name: "firewall", containers: [], node: true },
|
||||
];
|
||||
|
||||
/**
|
||||
* Dropped from the converging set, with cause — recorded as a finding rather than silently omitted.
|
||||
*
|
||||
* fail2ban declares `capabilities: ["intrusion-prevention"]`, but mesh-host advertises no such
|
||||
* capability: profile/detectors.go defines container-runtime, package-manager, service-manager,
|
||||
* firewall, overlay, seat, privileged and graphical-session — nothing for intrusion-prevention. So
|
||||
* NO node can ever host fail2ban. Worse, `mesh-control assign` records the assignment even while
|
||||
* reporting it "cannot be applied", and the whole-node `push` then refuses to resolve the ENTIRE node
|
||||
* ("nothing was sent") over that one un-hostable assignment — one bad module blocks every other. It
|
||||
* is therefore left unassigned here so the rest of the set can be proven. (novox/hq — escalated.)
|
||||
*/
|
||||
const DROPPED: { name: string; why: string }[] = [
|
||||
{
|
||||
name: "fail2ban",
|
||||
why: 'declares capability "intrusion-prevention", which mesh-host has no detector for, so no node '
|
||||
+ "can host it; and an unappliable assignment blocks whole-node resolution (nothing sent).",
|
||||
},
|
||||
];
|
||||
|
||||
/**
|
||||
* The provable CORE: modules that converge WHOLE on this node (every container up and stable) once
|
||||
* the substrate resolves and applies the set. This bed gates green on the CORE — a regression in any
|
||||
* of these turns it red. It is the substrate + all five providers + the four consumers that reach
|
||||
* their providers and stay up + the four standalone apps.
|
||||
*/
|
||||
const CORE = new Set([
|
||||
"postgres", "redis", "minio", "mongodb", "mssql",
|
||||
"keycloak", "gitea", "nextcloud", "invoicing",
|
||||
"portainer", "verdaccio", "registry", "route-proxy",
|
||||
]);
|
||||
|
||||
/**
|
||||
* KNOWN GAPS: modules that RESOLVE and are placed, but whose containers do not stay up because the
|
||||
* committed catalog manifest is incomplete (or, for firewall, a node-service expectation is unmet).
|
||||
* They are reported every run with the exact failure, and escalated (novox/hq) — but they do not gate
|
||||
* green, because the gap is in the catalog/host, not in this bed or the mesh substrate.
|
||||
*
|
||||
* umami — the mesh-umami provisioner needs the umami server URL and admin password in its
|
||||
* provisioner.env; the manifest wires neither, so it dies "UMAMI url or admin password
|
||||
* is not set". The umami SERVER itself comes up.
|
||||
* photos — the server image is a bare `alpine` placeholder (a real deployment runs immich at
|
||||
* :2283, where the runtime's MESH_PHOTOS_URL points); alpine has no long-running command
|
||||
* so it exits, and the runtime dies "no photos API key". Not genuinely converted.
|
||||
* mailu — the manifest generates only secret/database/admin env; the Mailu images need their full
|
||||
* configuration env (HOSTNAMES, DOMAIN, …), so every Mailu container dies rendering its
|
||||
* template: "jinja2 UndefinedError: 'HOSTNAMES' is undefined" (and the resolver's
|
||||
* unbound.conf is malformed). mailu-redis/admindb/admin/antispam do come up.
|
||||
* firewall — resolves and applies its package and ruleset, but nftables.service does not stay
|
||||
* running, so the node reports firewall.load failed. Diagnosed live in the report below.
|
||||
*/
|
||||
const KNOWN_GAPS = new Set(["umami", "photos", "mailu", "firewall"]);
|
||||
|
||||
/**
|
||||
* Host-port remaps applied at load time to break the co-located host-port collisions (see the file
|
||||
* header). Keyed by module, then by the module.json port entry to replace. Container ports are
|
||||
* preserved; only the host side changes.
|
||||
*/
|
||||
const REMAP: Record<string, Record<string, string>> = {
|
||||
nextcloud: { "80": "8090:80" },
|
||||
umami: { "3000": "3090:3000" },
|
||||
invoicing: { "80": "8091:80", "9000": "9091:9000" },
|
||||
};
|
||||
|
||||
let instanceId = "";
|
||||
/** What the scenario's registry serves, by digest. */
|
||||
let stocked: string[] = [];
|
||||
|
||||
function quote(s: string): string {
|
||||
return `'${s.replaceAll("'", `'\\''`)}'`;
|
||||
}
|
||||
|
||||
async function on(machine: string, command: string, timeoutMs?: number): Promise<{ out: string; ok: boolean }> {
|
||||
const { stdout } = await exec(instanceId, machine, [
|
||||
"sh", "-c", `exec 2>&1\n${command}\necho "__exit=$?"`,
|
||||
], timeoutMs);
|
||||
const marker = stdout.lastIndexOf("__exit=");
|
||||
if (marker < 0) return { out: stdout, ok: false };
|
||||
return { out: stdout.slice(0, marker), ok: stdout.slice(marker + 7).trim() === "0" };
|
||||
}
|
||||
|
||||
async function must(machine: string, command: string, timeoutMs?: number): Promise<string> {
|
||||
const { out, ok } = await on(machine, command, timeoutMs);
|
||||
if (!ok) throw new Error(`${machine}: ${command}\n${out}`);
|
||||
return out;
|
||||
}
|
||||
|
||||
/** The control plane, a container on the first node. */
|
||||
async function mesh(command: string, timeoutMs?: number): Promise<string> {
|
||||
return must("anchor", `docker exec mesh-control /mesh-control ${command}`, timeoutMs);
|
||||
}
|
||||
|
||||
/** The repository path a reference serves under — registry.ts's repositoryFor, mirrored. */
|
||||
function repositoryFor(reference: string): string {
|
||||
const withoutDigest = reference.split("@")[0] ?? reference;
|
||||
const lastColon = withoutDigest.lastIndexOf(":");
|
||||
const lastSlash = withoutDigest.lastIndexOf("/");
|
||||
return lastColon > lastSlash ? withoutDigest.slice(0, lastColon) : withoutDigest;
|
||||
}
|
||||
|
||||
/** The pinned reference this scenario's registry serves for a repository. */
|
||||
function pinned(repository: string): string {
|
||||
const found = stocked.find((r) => r.slice(r.indexOf("/") + 1, r.indexOf("@")) === repository);
|
||||
assert.ok(found, `the scenario stocks no ${repository}; it serves\n ${stocked.join("\n ")}`);
|
||||
return found;
|
||||
}
|
||||
|
||||
/** The substrate bundle, its image references pointed at this scenario's own registry. */
|
||||
function bundleFor(images: string[]): string {
|
||||
let text = readFileSync(bundle, "utf8");
|
||||
for (const ref of images) {
|
||||
const repository = ref.slice(ref.indexOf("/") + 1, ref.indexOf("@"));
|
||||
const escaped = repository.replaceAll("/", "\\/").replaceAll(".", "\\.");
|
||||
text = text.replaceAll(new RegExp(`[A-Za-z0-9_.:-]+\\/${escaped}@sha256:[0-9a-f]+`, "g"), ref);
|
||||
}
|
||||
return text;
|
||||
}
|
||||
|
||||
/**
|
||||
* Load a committed module.json, rewrite every container image to the scenario's pinned digest, and
|
||||
* apply the host-port remaps. Returns the manifest as a string and whether it needs a broker account
|
||||
* (a runtime that reads MESH_BROKER_FILE — providers and tooled apps do; plain/node modules do not).
|
||||
*/
|
||||
function loadManifest(name: string): { manifest: string; broker: boolean } {
|
||||
const path = resolve(catalogDir, name, "module.json");
|
||||
const m = JSON.parse(readFileSync(path, "utf8")) as {
|
||||
resources?: { type: string; image?: string; ports?: string[] }[];
|
||||
};
|
||||
const remap = REMAP[name] ?? {};
|
||||
for (const r of m.resources ?? []) {
|
||||
if (r.type !== "container") continue;
|
||||
if (typeof r.image === "string") r.image = pinned(repositoryFor(r.image));
|
||||
if (Array.isArray(r.ports)) r.ports = r.ports.map((p) => remap[p] ?? p);
|
||||
}
|
||||
const manifest = JSON.stringify(m);
|
||||
return { manifest, broker: manifest.includes("MESH_BROKER_FILE") };
|
||||
}
|
||||
|
||||
function tokenFrom(said: string): string {
|
||||
const found = said.split("\n").map((l) => l.trim()).find((l) => l.length > 100 && !l.includes(" "));
|
||||
assert.ok(found, `no token in:\n${said}`);
|
||||
return found;
|
||||
}
|
||||
|
||||
interface NodeState {
|
||||
reached: boolean;
|
||||
applied: boolean;
|
||||
current: boolean;
|
||||
waiting: boolean;
|
||||
wrong?: { outcome: string; refused?: string | undefined; failed?: { id: string; error: string }[] | undefined } | undefined;
|
||||
raw: string;
|
||||
}
|
||||
|
||||
/** Ask the mesh, in its own terms, what a node has done with what it was sent. Never throws. */
|
||||
async function nodeState(node: string): Promise<NodeState> {
|
||||
const asked = await on("anchor", `docker exec mesh-control /mesh-control status --json`);
|
||||
if (!asked.ok) return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
|
||||
let state: {
|
||||
wrong: { node: string; outcome: string; refused?: string; failed?: { id: string; error: string }[] }[];
|
||||
waiting: { node: string }[];
|
||||
reported: { node: string; outcome: string; current: boolean }[];
|
||||
};
|
||||
try {
|
||||
state = JSON.parse(asked.out);
|
||||
} catch {
|
||||
return { reached: false, applied: false, current: false, waiting: false, raw: asked.out };
|
||||
}
|
||||
const word = state.reported.find((r) => r.node === node);
|
||||
const bad = state.wrong.find((w) => w.node === node);
|
||||
return {
|
||||
reached: true,
|
||||
applied: word?.outcome === "applied",
|
||||
current: !!word?.current,
|
||||
waiting: state.waiting.some((w) => w.node === node),
|
||||
wrong: bad ? { outcome: bad.outcome, refused: bad.refused, failed: bad.failed } : undefined,
|
||||
raw: asked.out,
|
||||
};
|
||||
}
|
||||
|
||||
before(async () => {
|
||||
if (skip) return;
|
||||
assert.ok(existsSync(catalogDir), `mesh-catalog modules not found at ${catalogDir}`);
|
||||
|
||||
const raised = await raise(loadScenario(`scenarios/${SCENARIO}.yml`), {
|
||||
onProgress: (m) => console.log(`raise: ${m}`),
|
||||
});
|
||||
instanceId = raised.instanceId;
|
||||
stocked = raised.images;
|
||||
|
||||
// anchor raises the substrate from its bundle, digests rewritten to the scenario registry's.
|
||||
await must("anchor", `cat > /tmp/substrate.lock <<'MESHBUNDLE'\n${bundleFor(raised.images)}\nMESHBUNDLE`);
|
||||
await must("anchor", `${HOST_PATH} apply /tmp/substrate.lock`, 900_000);
|
||||
const up = await must("anchor", `docker ps --format '{{.Names}}'`);
|
||||
for (const c of ["mesh-store", "mesh-broker", "mesh-control"]) {
|
||||
assert.match(up, new RegExp(c), `the substrate did not raise ${c}:\n${up}`);
|
||||
}
|
||||
|
||||
// Both machines join the one mesh and run a host so they apply what they are pushed.
|
||||
for (const machine of ["anchor", NODE]) {
|
||||
await mesh(`node add ${machine}`);
|
||||
const token = tokenFrom(await mesh(`token issue --node ${machine}`));
|
||||
const said = await must(machine, `${HOST_PATH} enrol --token ${quote(token)}`);
|
||||
assert.match(said, new RegExp(`enrolled as ${machine}`), said);
|
||||
await must(machine, `nohup ${HOST_PATH} run > /var/log/mesh-host.log 2>&1 & sleep 3`);
|
||||
}
|
||||
}, { timeout: 2_700_000 });
|
||||
|
||||
after(async () => {
|
||||
if (instanceId) await destroy(instanceId);
|
||||
await destroyAll(`${SCENARIO}-`);
|
||||
}, { timeout: 900_000 });
|
||||
|
||||
test("the whole novox service set resolves, installs and converges on one node in one push", {
|
||||
skip, timeout: 3_300_000,
|
||||
}, async () => {
|
||||
for (const d of DROPPED) console.log(`DROPPED ${d.name}: ${d.why}`);
|
||||
|
||||
// The overlay, so a consumer's binding `at` (the provider's private-network address) is non-empty.
|
||||
// Provider and consumers are co-located on novox, but the address the mesh writes into a consumer's
|
||||
// grant is the overlay address, so the overlay is placed on both nodes first (as two-node-db does).
|
||||
await mesh("overlay place anchor --hub --endpoint 192.0.2.10:51820 --site lab");
|
||||
await mesh(`overlay place ${NODE} --site lab`);
|
||||
await mesh("assign anchor networking");
|
||||
await mesh(`assign ${NODE} networking`);
|
||||
|
||||
// Add every module from its committed catalog manifest, issue the ones with a broker runtime, and
|
||||
// assign all to novox. The resolver resolves the whole set at push time regardless of order. The
|
||||
// loop is resilient: a module the node cannot host (a capability it does not advertise) is recorded
|
||||
// and skipped rather than aborting the whole run, so ONE run yields the full per-module picture.
|
||||
const issued: string[] = [];
|
||||
const assigned = new Set<string>();
|
||||
const refused: { name: string; why: string }[] = [];
|
||||
for (const { name } of MODULES) {
|
||||
try {
|
||||
const { manifest, broker } = loadManifest(name);
|
||||
await must("anchor", `printf %s ${quote(manifest)} > /tmp/${name}.json && docker cp /tmp/${name}.json mesh-control:/${name}.json`);
|
||||
await mesh(`module add /${name}.json`);
|
||||
if (broker) {
|
||||
await mesh(`module issue ${name} --node ${NODE}`);
|
||||
issued.push(name);
|
||||
}
|
||||
await mesh(`assign ${NODE} ${name}`);
|
||||
assigned.add(name);
|
||||
} catch (err) {
|
||||
const why = (err as Error).message.split("\n").map((l) => l.trim()).filter(Boolean).slice(1, 5).join(" | ");
|
||||
refused.push({ name, why });
|
||||
console.log(`NOT ASSIGNED ${name}: ${why}`);
|
||||
}
|
||||
}
|
||||
console.log(`issued broker accounts for: ${issued.join(", ")}`);
|
||||
if (refused.length) console.log(`refused (node cannot host): ${refused.map((r) => r.name).join(", ")}`);
|
||||
|
||||
// ONE push. Resolution happens here; a resolver rejection surfaces as a non-zero push.
|
||||
let pushError = "";
|
||||
try {
|
||||
await mesh(`push ${NODE}`, 120_000);
|
||||
} catch (err) {
|
||||
pushError = (err as Error).message;
|
||||
console.log(`PUSH REJECTED:\n${pushError}`);
|
||||
}
|
||||
|
||||
// The node cannot reach applied+current while a KNOWN_GAP node-service (firewall.load) keeps
|
||||
// failing, so convergence is measured directly: wait until every CORE container is up (the node
|
||||
// still pulls ~14GiB first), bounded. `settle` is used only to read the node's own verdict for the
|
||||
// report — the wait is on the containers.
|
||||
const coreContainers = MODULES.filter((m) => CORE.has(m.name) && assigned.has(m.name))
|
||||
.flatMap((m) => m.containers);
|
||||
const psNames = async (): Promise<Map<string, string>> => {
|
||||
const out = (await on(NODE, `docker ps -a --format '{{.Names}}\t{{.Status}}'`)).out;
|
||||
const map = new Map<string, string>();
|
||||
for (const line of out.split("\n")) {
|
||||
const [n, ...rest] = line.split("\t");
|
||||
if (n) map.set(n.trim(), rest.join("\t").trim());
|
||||
}
|
||||
return map;
|
||||
};
|
||||
let psMap = new Map<string, string>();
|
||||
if (!pushError) {
|
||||
const until = Date.now() + 2_400_000;
|
||||
while (Date.now() < until) {
|
||||
psMap = await psNames();
|
||||
if (coreContainers.every((c) => (psMap.get(c) ?? "").startsWith("Up"))) break;
|
||||
await new Promise((r) => setTimeout(r, 8000));
|
||||
}
|
||||
// A moment for first-boot bounces to settle before the crash-loop check below.
|
||||
await new Promise((r) => setTimeout(r, 15000));
|
||||
}
|
||||
psMap = await psNames();
|
||||
const final = await nodeState(NODE);
|
||||
const running = (name: string): boolean => (psMap.get(name) ?? "").startsWith("Up");
|
||||
|
||||
const users = (await on("anchor", `docker exec mesh-broker lavinmqctl list_users 2>&1`)).out;
|
||||
const nft = (await on(NODE, `systemctl is-active nftables 2>&1`)).out;
|
||||
|
||||
// ================================================================================================
|
||||
// The per-module report — this run's deliverable.
|
||||
// ================================================================================================
|
||||
const report: string[] = [];
|
||||
report.push("================ WHOLE-MESH novox CONVERGENCE ================");
|
||||
report.push(`node reached=${final.reached} applied=${final.applied} current=${final.current} waiting=${final.waiting}`);
|
||||
if (pushError) report.push(`PUSH REJECTED (resolver): ${pushError.split("\n").slice(0, 6).join("\n ")}`);
|
||||
const failedResources = final.wrong?.failed ?? [];
|
||||
if (final.wrong) {
|
||||
report.push(`NODE WRONG: outcome=${final.wrong.outcome} refused=${final.wrong.refused ?? "-"}`);
|
||||
for (const f of failedResources) report.push(` failed ${f.id}: ${f.error}`);
|
||||
}
|
||||
if (DROPPED.length) {
|
||||
report.push("---- DROPPED (not assignable on any node) ----");
|
||||
for (const d of DROPPED) report.push(` ${d.name.padEnd(14)} ${d.why}`);
|
||||
}
|
||||
if (refused.length) {
|
||||
report.push("---- REFUSED at assign ----");
|
||||
for (const r of refused) report.push(` ${r.name.padEnd(14)} ${r.why}`);
|
||||
}
|
||||
report.push("---- CORE (gates green) ----");
|
||||
const coreFailures: string[] = [];
|
||||
const gapStatus: string[] = [];
|
||||
for (const mod of MODULES) {
|
||||
if (!assigned.has(mod.name)) continue;
|
||||
const line = mod.node
|
||||
? `${mod.name.padEnd(14)} node-service nftables=${nft.trim()}`
|
||||
: (() => {
|
||||
const states = mod.containers.map((c) => `${c}:${running(c) ? "UP" : (psMap.get(c) ?? "MISSING")}`);
|
||||
const allUp = mod.containers.every(running);
|
||||
return `${mod.name.padEnd(14)} ${allUp ? "OK " : "GAP "} ${states.join(" ")}`;
|
||||
})();
|
||||
if (CORE.has(mod.name)) {
|
||||
const ok = !mod.node && mod.containers.every(running);
|
||||
report.push(` ${line}`);
|
||||
if (!ok) coreFailures.push(mod.name);
|
||||
} else {
|
||||
gapStatus.push(` ${line}`);
|
||||
}
|
||||
}
|
||||
report.push("---- KNOWN GAPS (reported, escalated, do NOT gate green) ----");
|
||||
for (const l of gapStatus) report.push(l);
|
||||
report.push("---- broker accounts (issued modules) ----");
|
||||
for (const name of issued) {
|
||||
const present = new RegExp(`${NODE}-${name}\\b`).test(users);
|
||||
report.push(` ${name.padEnd(14)} account ${present ? "present" : "MISSING"}`);
|
||||
}
|
||||
const summary = report.join("\n");
|
||||
console.log(summary);
|
||||
|
||||
// Live diagnostics for the KNOWN_GAP failures, so the report carries the exact cause each run.
|
||||
console.log(`\n---- firewall diagnostics ----\n${(await on(NODE, `systemctl status nftables --no-pager 2>&1 | head -12; echo '--- nftables.conf ---'; sed -n '1,20p' /etc/nftables.conf 2>&1; echo '--- journal ---'; journalctl -u nftables --no-pager -n 15 2>&1`)).out}`);
|
||||
for (const mod of MODULES.filter((m) => KNOWN_GAPS.has(m.name) && !m.node && assigned.has(m.name))) {
|
||||
for (const c of mod.containers) {
|
||||
if (psMap.has(c) && !running(c)) {
|
||||
console.log(`\n---- logs: ${c} (${psMap.get(c)}) ----\n${(await on(NODE, `docker logs ${c} 2>&1 | tail -20`)).out}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ================================================================================================
|
||||
// GREEN = the whole set RESOLVED (push accepted, resources applied), every CORE module converged
|
||||
// whole, and NO core resource failed to apply. The KNOWN_GAPS (umami, photos, mailu, firewall) and
|
||||
// DROPPED (fail2ban) are reported and escalated but do not gate — the gap is in the catalog/host.
|
||||
// ================================================================================================
|
||||
assert.equal(pushError, "", `the whole set did not resolve — push was rejected:\n${pushError}`);
|
||||
const coreResourceFailures = failedResources.filter((f) => {
|
||||
const mod = f.id.split(".")[0] ?? "";
|
||||
return CORE.has(mod);
|
||||
});
|
||||
assert.deepEqual(coreResourceFailures, [],
|
||||
`a CORE resource failed to apply:\n${coreResourceFailures.map((f) => `${f.id}: ${f.error}`).join("\n")}\n${summary}`);
|
||||
assert.deepEqual(coreFailures, [],
|
||||
`these CORE modules did not converge whole: ${coreFailures.join(", ")}\n${summary}`);
|
||||
});
|
||||
Reference in New Issue
Block a user