Compare commits
12
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
12bc6a56a3 | ||
|
|
cdcfcd9380 | ||
|
|
130c5d98a6 | ||
|
|
8108dd5c23 | ||
|
|
f0d39b4a4a | ||
|
|
89fd0c06e1 | ||
|
|
17038b2a07 | ||
|
|
4dde21f0ab | ||
|
|
7d1d6bffe3 | ||
|
|
7283209d1a | ||
|
|
64f0ab4051 | ||
|
|
5f147fe6b9 |
@@ -116,6 +116,8 @@ const usage = `mesh-bootstrap — make a bare machine into a mesh
|
||||
|
||||
--tools-source the repository the shared base is built from
|
||||
--tools-ref what of it to build (default main)
|
||||
--tools-go-source the repository the Go toolchain is built from (default: mesh-tools-go beside --tools-source)
|
||||
--tools-go-ref what of it to build (default main)
|
||||
--catalog-source the catalogue REPOSITORY, for building its modules;
|
||||
--catalog is the checkout that says what they are
|
||||
--catalog-ref what of it to build (default main)
|
||||
@@ -308,6 +310,10 @@ func newFlagSet(opts *bootstrap.Options, jsonOut *bool) *flag.FlagSet {
|
||||
"the repository the shared base is built from")
|
||||
set.StringVar(&opts.ToolsSource.Ref, "tools-ref", opts.ToolsSource.Ref,
|
||||
"what of it to build (default main)")
|
||||
set.StringVar(&opts.ToolsGoSource.Repository, "tools-go-source", opts.ToolsGoSource.Repository,
|
||||
"the repository the Go toolchain is built from (default: mesh-tools-go beside --tools-source)")
|
||||
set.StringVar(&opts.ToolsGoSource.Ref, "tools-go-ref", opts.ToolsGoSource.Ref,
|
||||
"what of it to build (default main)")
|
||||
set.StringVar(&opts.CatalogSource.Repository, "catalog-source", opts.CatalogSource.Repository,
|
||||
"the catalogue REPOSITORY, for building its modules — --catalog is the checkout that says what they are")
|
||||
set.StringVar(&opts.CatalogSource.Ref, "catalog-ref", opts.CatalogSource.Ref,
|
||||
|
||||
@@ -49,7 +49,7 @@ func TestTheBundleCarriesTheFoundationAndTheControlPlaneAndNothingElse(t *testin
|
||||
}
|
||||
sort.Strings(images)
|
||||
|
||||
want := []string{"mesh-controller", "nats", "postgres"}
|
||||
want := []string{"mesh-controller", "nats", "pgvector"}
|
||||
if strings.Join(images, ",") != strings.Join(want, ",") {
|
||||
t.Fatalf("the bundle carries %v; expected exactly %v.\n\n"+
|
||||
"Adding one is a change to what every first node becomes, and to ADR 0006's "+
|
||||
|
||||
@@ -28,11 +28,12 @@
|
||||
// image, and this file is applied on a machine with no mesh to ask about anything (ADR 0006). The
|
||||
// registry prefix is the lab's; the digests are upstream's.
|
||||
//
|
||||
// The store's data is a NAMED VOLUME, not a directory on the machine. A directory the host
|
||||
// creates is owned by root, and the database runs as somebody else inside the container — so it
|
||||
// could not write, and the container crash-looped. A named volume lets the image set up its own
|
||||
// ownership, and outlives the container, which is what you want for the thing holding the mesh's
|
||||
// state.
|
||||
// **The store is raised where the `postgres` module keeps it** (novox/hq ADR 0338): the container
|
||||
// `postgres`, on the module's pgvector image, its data in the directory /var/lib/mesh-store owned by
|
||||
// the image's postgres user, its superuser password read from the module's own-secret file — so the
|
||||
// store step adopts it as it runs. Pinned upstream by the module's own digest, not through the lab's
|
||||
// registry prefix, because the two must be the same reference (mesh-host internal/bootstrap holds
|
||||
// them to each other against the module's manifest).
|
||||
|
||||
{
|
||||
"declaration": 1,
|
||||
@@ -83,17 +84,28 @@
|
||||
"boot": "enabled",
|
||||
"restart-on": ["base-filter"]
|
||||
},
|
||||
// The store's data is a directory owned by the image's postgres user (999), made before the
|
||||
// container starts: a directory the runtime made would be root's, and the database could not
|
||||
// write it. Measured on the module's image 2026-10-13: it initialises a new store on a directory
|
||||
// made so (novox/hq ADR 0338 §5).
|
||||
{
|
||||
"id": "store-data",
|
||||
"type": "directory",
|
||||
"path": "/var/lib/mesh-store",
|
||||
"mode": "0700",
|
||||
"owner": "999:70"
|
||||
},
|
||||
{
|
||||
"id": "store",
|
||||
"type": "container",
|
||||
"name": "mesh-store",
|
||||
"image": "192.0.2.250:5000/postgres@sha256:7abf537131b66ed5af448d90653abf1679b0c7e9a1f07efdd4c3108a401b259a",
|
||||
"name": "postgres",
|
||||
"image": "pgvector/pgvector@sha256:cf134a767f474095eeba57e0117be8e568e011a63f33fbf252f14c9b760f8e6f",
|
||||
"env": {
|
||||
"POSTGRES_PASSWORD": "bootstrap",
|
||||
"PGDATA": "/var/lib/postgresql/data/pgdata"
|
||||
},
|
||||
"ports": ["5432:5432"],
|
||||
"volumes": ["mesh-store-data:/var/lib/postgresql/data"]
|
||||
"volumes": ["/var/lib/mesh-store:/var/lib/postgresql/data"]
|
||||
},
|
||||
// Over TCP, not the socket. While the store initialises it runs a temporary server on the
|
||||
// socket ONLY, then stops it and starts the real one — so a socket check passes, the action
|
||||
@@ -102,21 +114,21 @@
|
||||
{
|
||||
"id": "store-ready",
|
||||
"type": "action",
|
||||
"in": "mesh-store",
|
||||
"in": "postgres",
|
||||
"command": ["sh", "-c", "for i in $(seq 1 180); do pg_isready -h 127.0.0.1 -U postgres >/dev/null 2>&1 && exit 0; sleep 1; done; echo 'the store did not answer within 180s; its own last words follow'; pg_isready -h 127.0.0.1 -U postgres; tail -n 20 /var/lib/postgresql/data/log/*.log 2>/dev/null; exit 1"],
|
||||
"verify": ["pg_isready", "-h", "127.0.0.1", "-U", "postgres"]
|
||||
},
|
||||
{
|
||||
"id": "inventory-database",
|
||||
"type": "action",
|
||||
"in": "mesh-store",
|
||||
"in": "postgres",
|
||||
"command": ["sh", "-c", "psql -U postgres -c 'CREATE DATABASE inventory'"],
|
||||
"verify": ["sh", "-c", "psql -U postgres -lqt | cut -d'|' -f1 | grep -qw inventory"]
|
||||
},
|
||||
{
|
||||
"id": "identity-database",
|
||||
"type": "action",
|
||||
"in": "mesh-store",
|
||||
"in": "postgres",
|
||||
"command": ["sh", "-c", "psql -U postgres -c 'CREATE DATABASE identity'"],
|
||||
"verify": ["sh", "-c", "psql -U postgres -lqt | cut -d'|' -f1 | grep -qw identity"]
|
||||
},
|
||||
@@ -126,20 +138,20 @@
|
||||
{
|
||||
"id": "licences-database",
|
||||
"type": "action",
|
||||
"in": "mesh-store",
|
||||
"in": "postgres",
|
||||
"command": ["sh", "-c", "psql -U postgres -c 'CREATE DATABASE licences'"],
|
||||
"verify": ["sh", "-c", "psql -U postgres -lqt | cut -d'|' -f1 | grep -qw licences"]
|
||||
},
|
||||
{
|
||||
"id": "context-schemas",
|
||||
"type": "action",
|
||||
"command": ["docker", "run", "--rm", "--network", "container:mesh-store",
|
||||
"command": ["docker", "run", "--rm", "--network", "container:postgres",
|
||||
"-e", "MESH_STORE_INVENTORY=postgres://postgres:bootstrap@127.0.0.1:5432/inventory?sslmode=disable",
|
||||
"-e", "MESH_STORE_IDENTITY=postgres://postgres:bootstrap@127.0.0.1:5432/identity?sslmode=disable",
|
||||
"-e", "MESH_STORE_LICENCES=postgres://postgres:bootstrap@127.0.0.1:5432/licences?sslmode=disable",
|
||||
"192.0.2.250:5000/mesh-controller@sha256:c67db38439ff0aee242b467486765467bb95801f52175fc5727cc4e437338ace",
|
||||
"migrate"],
|
||||
"verify": ["sh", "-c", "docker exec mesh-store psql -U postgres -d inventory -tAc \"select to_regclass('public.node')\" | grep -qx node && docker exec mesh-store psql -U postgres -d identity -tAc \"select to_regclass('public.signing_key')\" | grep -qx signing_key && docker exec mesh-store psql -U postgres -d licences -tAc \"select to_regclass('public.licence')\" | grep -qx licence"]
|
||||
"verify": ["sh", "-c", "docker exec postgres psql -U postgres -d inventory -tAc \"select to_regclass('public.node')\" | grep -qx node && docker exec postgres psql -U postgres -d identity -tAc \"select to_regclass('public.signing_key')\" | grep -qx signing_key && docker exec postgres psql -U postgres -d licences -tAc \"select to_regclass('public.licence')\" | grep -qx licence"]
|
||||
},
|
||||
// **The bus is raised where the `nats` module keeps it** (novox/hq ADR 0333 §1): the container
|
||||
// `mesh-broker-nats`, its configuration and user list in /var/lib/nats-module/conf, its streams in
|
||||
@@ -212,14 +224,17 @@
|
||||
"content": "// The first user list, carried by the installer because at genesis there is no mesh to\n// compose one. A bootstrap credential, rotated with the store's and replaced by the\n// controller's own composition from its first start onward.\naccounts {\n MESH {\n jetstream: enabled\n users = [\n { user: \"controller\", password: \"$2a$10$AHqJgOifIVbU41KmATiMhuXFs8xa7Wl2HuN4UVBCXdN2jIQzjqApy\", permissions: {\n publish: { allow: [\"$JS.ACK.CONTROL.controller.>\", \"$JS.ACK.EVENTS.controller.>\", \"$JS.ACK.DEAD_LETTER_NOTICES.controller.>\", \"$JS.API.>\", \"$KV.mesh-controller_asked.>\", \"$KV.mesh-controller_calls.>\", \"$KV.mesh-controller_hand-acts.>\", \"$KV.mesh-controller_conditions.>\", \"$KV.mesh-controller_condition-history.>\", \"$KV.mesh-controller_lease.>\", \"$KV.SEAT_MESH_BUILD_MACHINE_cancelled.>\", \"$KV.SEAT_NODE_BUILD_AGENT_cancelled.>\", \"_INBOX.enrol.>\", \"mesh.assignment.>\", \"mesh.mod.*.tool.>\", \"mesh.node.>\", \"mesh.seat.mesh-build-machine.accept.>\", \"mesh.seat.node-build-agent.accept.>\", \"mesh.seat.mesh-build-machine.tool.>\", \"mesh.seat.node-build-agent.tool.>\", \"mesh.seat.mesh-controller.event.applied\", \"mesh.seat.mesh-controller.event.built-before\", \"mesh.seat.mesh-controller.event.refused\", \"mesh.seat.mesh-controller.event.rolled-back\", \"mesh.seat.mesh-controller.event.checked\", \"mesh.seat.mesh-controller.event.plan-moved\", \"mesh.seat.mesh-controller.event.condition-raised\", \"mesh.seat.mesh-controller.event.condition-changed\", \"mesh.seat.mesh-controller.event.condition-cleared\", \"mesh.seat.mesh-controller.event.doctor-heartbeat\", \"mesh.seat.mesh-controller.event.secret-replaced\", \"mesh.seat.mesh-controller.event.healer-acted\", \"$SRV.INFO\", \"mesh.seat.node-intrusion-prevention.tool.banned.*\", \"mesh.seat.node-backup.tool.backed-up.*\", \"mesh.seat.node-backup.tool.now.*\", \"mesh.seat.mesh-delivery.tool.stalled\", \"mesh.seat.mesh-delivery.tool.close\", \"mesh.seat.node-launcher.tool.secret.*\", \"mesh.seat.mesh-delivery.tool.release\", \"mesh.seat.mesh-delivery.tool.stop\", \"mesh.seat.mesh-delivery.tool.times\", \"mesh.seat.mesh-delivery.tool.groups\", \"mesh.seat.node-service-manager.tool.restart.*\", \"mesh.seat.mesh-controller.tool.plans\", \"mesh.events.dead.>\", \"mesh.again.>\"] }\n subscribe: { allow: [\"$JS.API.>\", \"$JS.EVENT.ADVISORY.CONSUMER.MAX_DELIVERIES.>\", \"$JS.EVENT.ADVISORY.CONSUMER.DELETED.>\", \"_DELIVER.controller\", \"_DELIVER.controller.>\", \"_INBOX.controller.>\", \"mesh.control.>\", \"mesh.mod.*.event.provisioner.failing\", \"mesh.mod.*.event.provisioner.recovered\", \"mesh.mod.*.event.provisioner.retirement\", \"mesh.mod.gitea.event.pull.merged\", \"mesh.mod.gitea.event.pull.updated\", \"mesh.mod.mesh-catalog.event.catching-up\", \"mesh.mod.mesh-catalog.event.upgraded\", \"mesh.seat.mesh-build-machine.event.built\", \"mesh.seat.node-build-agent.event.built\", \"mesh.seat.operator-channel.event.decided.mesh-controller\", \"mesh.seat.mesh-controller.tool.>\", \"$SRV.PING\", \"$SRV.INFO\", \"$SRV.PING.mesh-controller\", \"$SRV.PING.mesh-controller.>\", \"$SRV.INFO.mesh-controller\", \"$SRV.INFO.mesh-controller.>\", \"$SRV.STATS\", \"$SRV.STATS.mesh-controller\", \"$SRV.STATS.mesh-controller.>\"] }\n allow_responses: { max: 1, ttl: \"1m\" }\n } }\n ]\n }\n}\n"
|
||||
},
|
||||
// The upstream server, until the broker step adopts it: the `nats` module's own image, built by the
|
||||
// mesh, takes its place there once, on these same directories (ADR 0333 §3). The published port is the
|
||||
// mesh, takes its place there once, on these same directories (ADR 0333 §3), as the bus's planned
|
||||
// step (ADR 0236). The release is the one the module's image is built on (its NATS_BASE, 2.11.17),
|
||||
// pinned upstream by that same digest: the adoption changes no server release, so it can be undone
|
||||
// by putting the old image back and is said reversible. The published port is the
|
||||
// node's bus port, 5671 unless given, which every enrolment token names; the installer gives the
|
||||
// module the setting that maps its declared 4222 to it (ADR 0333 §2).
|
||||
{
|
||||
"id": "broker",
|
||||
"type": "container",
|
||||
"name": "mesh-broker-nats",
|
||||
"image": "192.0.2.250:5000/nats@sha256:b83efabe3e7def1e0a4a31ec6e078999bb17c80363f881df35edc70fcb6bb927",
|
||||
"image": "nats@sha256:e4bf19f15fd3218814a4e3c9e0064e1334bd8aa20d5984b9f1a0afd084f8cc00",
|
||||
"ports": ["5671:4222", "127.0.0.1:8222:8222"],
|
||||
"volumes": ["/var/lib/mesh-broker-nats:/data", "/var/lib/nats-module/conf:/etc/nats:ro", "/var/lib/mesh-broker-tls:/tls:ro"],
|
||||
"args": ["-c", "/etc/nats/nats.conf", "-js"]
|
||||
@@ -227,8 +242,8 @@
|
||||
{
|
||||
"id": "broker-ready",
|
||||
"type": "action",
|
||||
"command": ["sh", "-c", "for i in $(seq 1 60); do docker run --rm --network host --entrypoint sh 192.0.2.250:5000/nats@sha256:b83efabe3e7def1e0a4a31ec6e078999bb17c80363f881df35edc70fcb6bb927 -c 'nc -z 127.0.0.1 5671' >/dev/null 2>&1 && exit 0; sleep 1; done; exit 1"],
|
||||
"verify": ["sh", "-c", "docker run --rm --network host --entrypoint sh 192.0.2.250:5000/nats@sha256:b83efabe3e7def1e0a4a31ec6e078999bb17c80363f881df35edc70fcb6bb927 -c 'nc -z 127.0.0.1 5671'"]
|
||||
"command": ["sh", "-c", "for i in $(seq 1 60); do docker run --rm --network host --entrypoint sh nats@sha256:e4bf19f15fd3218814a4e3c9e0064e1334bd8aa20d5984b9f1a0afd084f8cc00 -c 'nc -z 127.0.0.1 5671' >/dev/null 2>&1 && exit 0; sleep 1; done; exit 1"],
|
||||
"verify": ["sh", "-c", "docker run --rm --network host --entrypoint sh nats@sha256:e4bf19f15fd3218814a4e3c9e0064e1334bd8aa20d5984b9f1a0afd084f8cc00 -c 'nc -z 127.0.0.1 5671'"]
|
||||
},
|
||||
{
|
||||
"id": "control-plane",
|
||||
|
||||
@@ -174,6 +174,10 @@ type Options struct {
|
||||
// ToolsSource is where the shared base is built from. Everything with code of its own
|
||||
// compiles against it, so it is the first thing the mesh builds for itself.
|
||||
ToolsSource Source
|
||||
// ToolsGoSource is where the Go toolchain is built from (`mesh-tools-go`, ADR 0142): every Go
|
||||
// bundle compiles in it, and genesis's own modules have Go code (issue 616). Empty means the
|
||||
// repository beside ToolsSource named mesh-tools-go, as the mesh keeps it.
|
||||
ToolsGoSource Source
|
||||
// CatalogSource is where the catalogue REPOSITORY is, for building its modules. The catalogue
|
||||
// CHECKOUT (Catalogue, above) says what a module is; this is where a builder clones it.
|
||||
CatalogSource Source
|
||||
|
||||
@@ -38,27 +38,6 @@ func recording(t *testing.T) (*controlRecorder, controlPlane) {
|
||||
return c, controlPlane{container: "temp-mesh-controller", run: c.run, timeout: time.Second}
|
||||
}
|
||||
|
||||
func TestTheBuildersPackageRegistryPortIsASettingAndNotTheManifest(t *testing.T) {
|
||||
c, control := recording(t)
|
||||
o := Options{Node: "anchor", Ports: FoundationPorts{Packages: 3100}, Wait: time.Second}
|
||||
if _, err := installModule(context.Background(), o, control, BuilderModule,
|
||||
[]byte(theBuildersBinding), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got := c.settings[BuilderModule+"-settings.json"]; got != `{"serves":{"port":3100}}` {
|
||||
t.Errorf("the builder was told %q about the package registry's port", got)
|
||||
}
|
||||
// The manifest reaches the mesh as the catalogue wrote it. A port rewritten into it here is a
|
||||
// port the next registration from the catalogue silently takes back.
|
||||
if got := c.settings[BuilderModule+"-module.json"]; got != theBuildersBinding {
|
||||
t.Errorf("the installer changed the builder's manifest:\n%s", got)
|
||||
}
|
||||
set, push := c.index("settings set "+BuilderModule), c.index("push anchor")
|
||||
if set < 0 || push < 0 || set > push {
|
||||
t.Fatalf("the port was not set before the push that raises the builder: %v", c.told)
|
||||
}
|
||||
}
|
||||
|
||||
func TestTheBuilderOnTheDefaultPackagesPortIsToldNothing(t *testing.T) {
|
||||
c, control := recording(t)
|
||||
o := Options{Node: "anchor", Wait: time.Second}
|
||||
|
||||
@@ -0,0 +1,179 @@
|
||||
package bootstrap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"encoding/json"
|
||||
"encoding/pem"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"regexp"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/novox/mesh-host/internal/declaration"
|
||||
)
|
||||
|
||||
// Adopting the bus is the mesh's planned step for replacing it (novox/hq ADR 0333 §3, ADR 0236).
|
||||
//
|
||||
// The adoption replaces the bus's image once: the module's built image takes the place of the upstream
|
||||
// one the bundle raised, on the same streams, users and certificate. The controller refuses a push that
|
||||
// would replace the bus — "a planned step: `bus upgrade --why …` snapshots its streams first and checks
|
||||
// them after" — so genesis stopped at step 18 (issue 590). The installer takes that step: it snapshots the
|
||||
// streams itself, because at genesis no backup holder exists to be asked, and hands the snapshot to
|
||||
// `bus upgrade`, which sends the machine, opens `bus-maintenance`, and ends the step done only once the
|
||||
// bus answers healthy again — every stream, every durable consumer, a round trip (H-bus). The installer
|
||||
// waits for that end.
|
||||
|
||||
// adoptionWhy is what the step is recorded as, for the record of hand acts and the bus's step.
|
||||
const adoptionWhy = "genesis adopts its bus as the nats module (ADR 0333)"
|
||||
|
||||
// Where the installer keeps the streams' snapshot before the adoption, and the credential the snapshot
|
||||
// program reads while it runs. Beside genesis's own credentials; variables so a test writes elsewhere.
|
||||
var (
|
||||
busSnapshotFile = "/var/lib/mesh-genesis/bus-before-adoption.tar"
|
||||
busSnapshotCredential = "/var/lib/mesh-genesis/bus-snapshot.credential"
|
||||
busCertificateFile = "/var/lib/mesh-broker-tls/tls.crt"
|
||||
busControllerSecret = BusControllerFile
|
||||
// busStepWithin bounds the wait for the controller to say the step ended: its own bound (15 min,
|
||||
// mesh-controller busStepBound), and its doctor's next look after that.
|
||||
busStepWithin = 17 * time.Minute
|
||||
)
|
||||
|
||||
// adoptTheBus sends the nats module to this machine through the bus's planned step. A bus already on the
|
||||
// module's image is the module's: it is sent like any module, and nothing is replaced.
|
||||
func adoptTheBus(ctx context.Context, o Options, control controlPlane, bus *declaration.Container,
|
||||
say func(string)) error {
|
||||
|
||||
if running := runningImage(ctx, control, bus.Name); running != "" && running != bus.Image {
|
||||
say(" already adopted " + bus.Name + " — it runs the module's image")
|
||||
_, err := pushNode(ctx, o, control, say)
|
||||
return err
|
||||
}
|
||||
image, err := theModulesBusImage(ctx, o, control)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if err := snapshotTheBus(ctx, o, control, image, say); err != nil {
|
||||
return err
|
||||
}
|
||||
say(" restarting " + bus.Name + " — once, onto the " + BusModule + " module's image, as the bus's " +
|
||||
"planned step; its streams, users and certificate stay where they are (novox/hq ADR 0333 §3, ADR 0236)")
|
||||
if _, err := control.within(2*o.Wait).tell(ctx, "bus", "upgrade", "--why", adoptionWhy,
|
||||
"--reversible", "--snapshot-taken", busSnapshotFile); err != nil {
|
||||
return fmt.Errorf("the bus's planned step was refused, so the bus is not replaced: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// meshBuiltImage is an image the mesh built, as it records it: `artifact-store://<module>/<artifact>@sha256:…`.
|
||||
var meshBuiltImage = regexp.MustCompile(`artifact-store://([a-z0-9][a-z0-9-]*/[a-z0-9][a-z0-9-]*@sha256:[0-9a-f]{64})`)
|
||||
|
||||
// theModulesBusImage is the nats module's server image, as the build just made it, pulled from this
|
||||
// mesh's registry: the image that carries the snapshot program.
|
||||
func theModulesBusImage(ctx context.Context, o Options, control controlPlane) (string, error) {
|
||||
said, err := control.tell(ctx, "builds", BusModule, "-n", "1")
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
for _, m := range meshBuiltImage.FindAllStringSubmatch(said, -1) {
|
||||
if strings.HasPrefix(m[1], BusModule+"/") {
|
||||
return strings.TrimSuffix(o.Registry, "/") + "/" + m[1], nil
|
||||
}
|
||||
}
|
||||
return "", fmt.Errorf("the mesh says no image it built for the %s module, so its snapshot program cannot "+
|
||||
"be run before the bus is replaced:\n%s", BusModule, indent(strings.TrimSpace(said)))
|
||||
}
|
||||
|
||||
// snapshotTheBus writes every stream of the running bus to busSnapshotFile with the module's own snapshot
|
||||
// program (mesh-catalog modules/nats, ADR 0235), as the controller's account, pinned to the bus's
|
||||
// certificate. The credential is written for the program's one run and removed after it.
|
||||
func snapshotTheBus(ctx context.Context, o Options, control controlPlane, image string, say func(string)) error {
|
||||
password, err := readCredentialFile(busControllerSecret)
|
||||
if err != nil {
|
||||
return fmt.Errorf("the controller's bus credential is not at %s, so the streams cannot be snapshotted "+
|
||||
"before the bus is replaced: %w", busControllerSecret, err)
|
||||
}
|
||||
fingerprint, err := certificateFingerprint(busCertificateFile)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
port := o.Ports.orDefaults().Bus
|
||||
server := "tls://127.0.0.1:" + strconv.Itoa(port)
|
||||
credential, err := json.Marshal(map[string]string{"url": server, "fingerprint": fingerprint,
|
||||
"user": busControllerUser, "password": password})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
if err := os.WriteFile(busSnapshotCredential, credential, 0o600); err != nil {
|
||||
return fmt.Errorf("the snapshot's credential could not be written: %w", err)
|
||||
}
|
||||
defer os.Remove(busSnapshotCredential)
|
||||
|
||||
script := "docker run --rm -i --network host --entrypoint /usr/local/bin/mesh-nats-snapshot " + image +
|
||||
" snapshot --server " + server + " --credential - < " + busSnapshotCredential + " > " + busSnapshotFile +
|
||||
".partial && mv " + busSnapshotFile + ".partial " + busSnapshotFile
|
||||
running, cancel := context.WithTimeout(ctx, busStepWithin)
|
||||
defer cancel()
|
||||
if out, err := control.run(running, "sh", "-c", script); err != nil {
|
||||
_, _ = control.run(ctx, "rm", "-f", busSnapshotFile+".partial")
|
||||
return fmt.Errorf("the bus's streams could not be snapshotted, so the bus is not replaced: %w\n%s",
|
||||
err, indent(strings.TrimSpace(out)))
|
||||
}
|
||||
say(" snapshotted every stream of the bus, at " + busSnapshotFile + " (its module's snapshot program)")
|
||||
return nil
|
||||
}
|
||||
|
||||
// certificateFingerprint is the pin of the bus's certificate: sha256 of its DER, as every machine pins it.
|
||||
func certificateFingerprint(path string) (string, error) {
|
||||
raw, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("the bus's certificate is not at %s, so it cannot be pinned for the snapshot: %w", path, err)
|
||||
}
|
||||
block, _ := pem.Decode(raw)
|
||||
if block == nil {
|
||||
return "", fmt.Errorf("%s holds no PEM certificate", path)
|
||||
}
|
||||
sum := sha256.Sum256(block.Bytes)
|
||||
return "sha256:" + hex.EncodeToString(sum[:]), nil
|
||||
}
|
||||
|
||||
// waitForTheBusStep waits until the controller says the bus's planned step ended: done once the bus
|
||||
// answered healthy — every stream, every durable consumer, a round trip — or failed, with its snapshot as
|
||||
// the way back. The step's own bound is the controller's; this waits a little past it.
|
||||
func waitForTheBusStep(ctx context.Context, o Options, control controlPlane, say func(string)) error {
|
||||
deadline := time.Now().Add(busStepWithin)
|
||||
var last string
|
||||
for {
|
||||
said, err := control.tell(ctx, "bus")
|
||||
if err == nil {
|
||||
for _, line := range strings.Split(said, "\n") {
|
||||
if strings.HasPrefix(strings.TrimSpace(line), "last step ") {
|
||||
last = strings.TrimSpace(line)
|
||||
}
|
||||
}
|
||||
switch {
|
||||
case strings.Contains(last, ": done at "):
|
||||
say(" bus step done " + last)
|
||||
return nil
|
||||
case strings.Contains(last, ": failed at "):
|
||||
return fmt.Errorf("the bus's planned step ended failed: %s\n%s", last, indent(strings.TrimSpace(said)))
|
||||
}
|
||||
}
|
||||
if !time.Now().Before(deadline) {
|
||||
break
|
||||
}
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return ctx.Err()
|
||||
case <-time.After(answerEvery):
|
||||
}
|
||||
}
|
||||
if last == "" {
|
||||
return errors.New("the controller says no bus step after the adoption was sent; `mesh-controller bus` says how it stands")
|
||||
}
|
||||
return fmt.Errorf("the bus's planned step did not end within %s: %s", busStepWithin, last)
|
||||
}
|
||||
@@ -0,0 +1,135 @@
|
||||
package bootstrap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"os"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Defends novox/hq issue 590 at its broker step (ADR 0333 §3, ADR 0236): the adoption replaces the bus's
|
||||
// image, and the mesh replaces its bus only as a planned step. A plain push was refused — "sending anchor
|
||||
// would replace the bus … a planned step: `bus upgrade --why …`" — and genesis stopped at step 18.
|
||||
|
||||
func TestTheBrokerStepAdoptsTheBusThroughItsPlannedStep(t *testing.T) {
|
||||
catalogue := aCatalogue(t, map[string]string{BusModule: aBusModule(theModulesLayout)})
|
||||
rewritten, err := Rewrite(theRealBundle(t), held)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
bundleImage := containerNamed(rewritten.Declaration, "mesh-broker-nats").Image
|
||||
upgraded := false
|
||||
var credential []byte
|
||||
runtime := &asked{}
|
||||
agrees := aMeshThatAgrees(nil)
|
||||
runtime.answer = func(name string, args []string) (string, error) {
|
||||
joined := strings.Join(args, " ")
|
||||
switch {
|
||||
case name == "sh" && strings.Contains(joined, "mesh-nats-snapshot"):
|
||||
credential, _ = os.ReadFile(busSnapshotCredential) // as the program reads it
|
||||
case strings.Contains(joined, "bus upgrade --why"):
|
||||
upgraded = true
|
||||
case strings.Contains(joined, "inspect --format {{.Config.Image}} mesh-broker-nats"):
|
||||
if upgraded {
|
||||
return theModulesImage + "\n", nil
|
||||
}
|
||||
return bundleImage + "\n", nil
|
||||
}
|
||||
return agrees(name, args)
|
||||
}
|
||||
_, fetch := aBusThatAdopts()
|
||||
o := installing(t, catalogue)
|
||||
o.CatalogSource = Source{Repository: "git://forge/mesh-catalog.git"}
|
||||
o.Wait = 5 * time.Second
|
||||
said, err := busStepWith(t, o, runtime, fetch)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
snapshot, upgrade := -1, -1
|
||||
for i, c := range runtime.commands {
|
||||
switch {
|
||||
case strings.HasPrefix(c, "sh -c") && strings.Contains(c, "mesh-nats-snapshot"):
|
||||
snapshot = i
|
||||
for _, want := range []string{"127.0.0.1:5000/nats/server@sha256:" + strings.Repeat("4", 64),
|
||||
"snapshot --server tls://127.0.0.1:5671 --credential - < " + busSnapshotCredential,
|
||||
"> " + busSnapshotFile + ".partial && mv " + busSnapshotFile + ".partial " + busSnapshotFile} {
|
||||
if !strings.Contains(c, want) {
|
||||
t.Errorf("the snapshot is not taken with %q: %s", want, c)
|
||||
}
|
||||
}
|
||||
case strings.Contains(c, "/mesh-controller bus upgrade"):
|
||||
upgrade = i
|
||||
if want := "bus upgrade --why " + adoptionWhy + " --reversible --snapshot-taken " + busSnapshotFile; !strings.HasSuffix(c, want) {
|
||||
t.Errorf("the planned step is asked as %q; want it to end %q", c, want)
|
||||
}
|
||||
case strings.HasSuffix(c, "/mesh-controller push anchor"):
|
||||
t.Errorf("the bus's module was sent by a plain push, which the mesh refuses for the bus: %v", runtime.commands)
|
||||
}
|
||||
}
|
||||
if snapshot < 0 || upgrade < 0 || snapshot > upgrade {
|
||||
t.Fatalf("the streams were not snapshotted before the bus's planned step (snapshot %d, upgrade %d): %v",
|
||||
snapshot, upgrade, runtime.commands)
|
||||
}
|
||||
var cred map[string]string
|
||||
if err := json.Unmarshal(credential, &cred); err != nil {
|
||||
t.Fatalf("the snapshot program was given no credential: %v", err)
|
||||
}
|
||||
fingerprint, _ := certificateFingerprint(busCertificateFile)
|
||||
if cred["user"] != "controller" || cred["password"] != "BUS-PW" || cred["fingerprint"] != fingerprint ||
|
||||
cred["url"] != "tls://127.0.0.1:5671" {
|
||||
t.Errorf("the snapshot's credential is %v", cred)
|
||||
}
|
||||
if _, err := os.Stat(busSnapshotCredential); !os.IsNotExist(err) {
|
||||
t.Error("the snapshot's credential was left on the machine")
|
||||
}
|
||||
text := strings.Join(said, "\n")
|
||||
for _, want := range []string{"snapshotted every stream", "restarting mesh-broker-nats — once",
|
||||
"bus answers mesh-broker-nats", "bus step done last step 1", "adopted mesh-broker-nats"} {
|
||||
if !strings.Contains(text, want) {
|
||||
t.Errorf("the step did not say %q:\n%s", want, text)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// A planned step the controller ends failed is the broker step failing, with the controller's words.
|
||||
func TestABusStepThatEndsFailedIsRefused(t *testing.T) {
|
||||
aGenesisBusOnDisk(t)
|
||||
runtime := &asked{answer: func(name string, args []string) (string, error) {
|
||||
return "last step 1: not known → 53e51864 on anchor by installer (x): failed at 2026-10-13 11:59; snapshot s\n" +
|
||||
" stream KV_x has no messages\n", nil
|
||||
}}
|
||||
control := controlPlane{container: "mesh-controller", run: runtime.run, timeout: time.Second}
|
||||
err := waitForTheBusStep(context.Background(), Options{}, control, quietly)
|
||||
if err == nil || !strings.Contains(err.Error(), "failed at") || !strings.Contains(err.Error(), "KV_x") {
|
||||
t.Fatalf("a failed bus step was not refused with its words: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
// The bundle's bus runs the release the module's image is built on, pinned by the same digest, so the
|
||||
// adoption changes no server release and is reversible as the step says (ADR 0333 §3).
|
||||
func TestTheBundlesBusRunsTheReleaseTheModulesImageIsBuiltOn(t *testing.T) {
|
||||
var m struct {
|
||||
Build struct {
|
||||
On []struct{ Arg, Image string } `json:"on"`
|
||||
} `json:"build"`
|
||||
}
|
||||
if err := json.Unmarshal(theCataloguesModule(t, BusModule), &m); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
base := ""
|
||||
for _, on := range m.Build.On {
|
||||
if on.Arg == "NATS_BASE" {
|
||||
base = on.Image
|
||||
}
|
||||
}
|
||||
rewritten, err := Rewrite(theRealBundle(t), held)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got := containerNamed(rewritten.Declaration, "mesh-broker-nats").Image; got != base {
|
||||
t.Errorf("the bundle raises the bus on %s; the nats module's image is built on %s", got, base)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,65 @@
|
||||
package bootstrap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Genesis seals the build agent the forge it raised (novox/hq ADR 0336 §3, issue 121): the agent's
|
||||
// npm-package-registry requirement is optional and binds only once the gitea module is assigned, after
|
||||
// the base, so until then the packages step's genesis document is how the sdk and base steps reach the
|
||||
// forge.
|
||||
|
||||
func TestThePackagesStepSealsTheGenesisDocumentToTheBuildAgent(t *testing.T) {
|
||||
if BuilderModule != "build-agent" {
|
||||
t.Fatalf("genesis installs %q; the document is the build agent's", BuilderModule)
|
||||
}
|
||||
c, control := recording(t)
|
||||
o := Options{Node: "anchor", Ports: FoundationPorts{Packages: 3100}, Wait: time.Second}
|
||||
doc := genesisRegistry(o.Ports.orDefaults(), "builder-password")
|
||||
if err := deliverGenesisRegistry(context.Background(), o, control, doc, quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
carried := c.settings["accepting-"+GenesisRegistrySecret]
|
||||
var got GenesisRegistry
|
||||
if err := json.Unmarshal([]byte(carried), &got); err != nil {
|
||||
t.Fatalf("the genesis document carried is not JSON: %q", carried)
|
||||
}
|
||||
want := GenesisRegistry{Scheme: "http", At: "127.0.0.1", Port: 3100, NpmPath: "/api/packages/novox/npm/",
|
||||
As: "mesh-builder", Password: "builder-password"}
|
||||
if got != want {
|
||||
t.Fatalf("the genesis document says %+v, want %+v", got, want)
|
||||
}
|
||||
accept := c.index("secret accept anchor build-agent genesis-package-registry --from /accepting-genesis-package-registry")
|
||||
push := c.index("push anchor")
|
||||
if accept < 0 || push < 0 || accept > push {
|
||||
t.Fatalf("the genesis document was not sealed to the build agent before the push: %v", c.told)
|
||||
}
|
||||
}
|
||||
|
||||
// What the retired builder was given and the build agent declares neither of: an `npm-password`
|
||||
// own-secret and a `serves` setting for its carried binding (ADR 0336 §3).
|
||||
func TestNoStepGivesTheBuildAgentAServesSettingOrAnNpmPassword(t *testing.T) {
|
||||
for _, module := range []string{BuilderModule} {
|
||||
c, control := recording(t)
|
||||
o := Options{Node: "anchor", Ports: FoundationPorts{Packages: 3100}, Wait: time.Second}
|
||||
if _, err := installModule(context.Background(), o, control, module, []byte(`{"module":"`+module+`"}`), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if got, set := c.settings[module+"-settings.json"]; set {
|
||||
t.Errorf("%s was given a setting on a node with a non-default packages port: %s", module, got)
|
||||
}
|
||||
if err := deliverGenesisRegistry(context.Background(), o, control,
|
||||
genesisRegistry(o.Ports.orDefaults(), "p"), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, told := range c.told {
|
||||
if strings.Contains(told, "npm-password") || strings.Contains(told, "serves") {
|
||||
t.Errorf("genesis told the controller %q", told)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
package bootstrap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Defends novox/hq issue 616: genesis's base step builds the toolchain of every language a module
|
||||
// genesis installs is compiled in. It built only mesh-tools, and the store's module, with Go code,
|
||||
// stopped genesis at step 17: "this mesh holds no copy of it. Build mesh-tools-go first".
|
||||
|
||||
// genesisModules is every catalogue module genesis installs on its own, read from the steps that
|
||||
// install them: the registry, the build agent, the store, the bus, the vault, the catalogue and the
|
||||
// filter (extras are the operator's choice and come after the base too, but are not genesis's own).
|
||||
var genesisModules = []string{RegistryModule, BuilderModule, "postgres", BusModule, "mesh-vault", "mesh-catalog", "nftables"}
|
||||
|
||||
// Every genesis module's bundles are compiled in a toolchain the base step builds, read from the real
|
||||
// catalogue's manifests: a module that gains a language genesis does not build fails here, not at a
|
||||
// genesis.
|
||||
func TestTheBaseStepBuildsEveryToolchainAGenesisModuleIsCompiledIn(t *testing.T) {
|
||||
built := map[string]bool{}
|
||||
for _, tc := range genesisToolchains {
|
||||
built[tc.Language] = true
|
||||
}
|
||||
for _, module := range genesisModules {
|
||||
var m struct {
|
||||
Build struct {
|
||||
Artifacts []struct {
|
||||
Name, Kind, Language string
|
||||
} `json:"artifacts"`
|
||||
} `json:"build"`
|
||||
}
|
||||
if err := json.Unmarshal(theCataloguesModule(t, module), &m); err != nil {
|
||||
t.Fatalf("%s: %v", module, err)
|
||||
}
|
||||
for _, a := range m.Build.Artifacts {
|
||||
if a.Kind != "bundle" {
|
||||
continue // an image builds on the bases its Dockerfile names, pinned upstream
|
||||
}
|
||||
if !built[a.Language] {
|
||||
t.Errorf("%s's %q is a %s bundle, and genesis's base step builds no %s toolchain",
|
||||
module, a.Name, a.Language, a.Language)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// And the base step asks for each toolchain's build: the base, then the Go toolchain beside it.
|
||||
func TestTheBaseStepBuildsTheGoToolchainBesideTheBase(t *testing.T) {
|
||||
runtime := &asked{answer: aMeshThatAgrees(nil)}
|
||||
control := controlPlane{container: "mesh-controller", run: runtime.run, timeout: time.Second}
|
||||
o := Options{ToolsSource: Source{Repository: "git://192.0.2.30/mesh-tools.git"}}
|
||||
if err := BuildBase(context.Background(), o, control, quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var builds []string
|
||||
for _, c := range runtime.commands {
|
||||
if strings.Contains(c, "/mesh-controller build ") {
|
||||
builds = append(builds, c[strings.Index(c, "build "):])
|
||||
}
|
||||
}
|
||||
want := []string{
|
||||
"build git://192.0.2.30/mesh-tools.git --ref main --wait 1200s",
|
||||
"build git://192.0.2.30/mesh-tools-go.git --ref main --wait 1200s",
|
||||
}
|
||||
if strings.Join(builds, "\n") != strings.Join(want, "\n") {
|
||||
t.Fatalf("the base step built\n%s\nand not\n%s", strings.Join(builds, "\n"), strings.Join(want, "\n"))
|
||||
}
|
||||
}
|
||||
|
||||
func TestTheGoToolchainIsAsGivenOrBesideTheBase(t *testing.T) {
|
||||
for _, c := range []struct{ tools, given, want string }{
|
||||
{"http://forge/novox/mesh-tools.git", "", "http://forge/novox/mesh-tools-go.git"},
|
||||
{"http://forge/novox/mesh-tools", "", "http://forge/novox/mesh-tools-go"},
|
||||
{"http://forge/other/base.git", "http://forge/other/go.git", "http://forge/other/go.git"},
|
||||
} {
|
||||
got, err := toolsGoSource(Options{ToolsSource: Source{Repository: c.tools}, ToolsGoSource: Source{Repository: c.given}})
|
||||
if err != nil || got.Repository != c.want {
|
||||
t.Errorf("tools %s, given %q: %q %v; want %s", c.tools, c.given, got.Repository, err, c.want)
|
||||
}
|
||||
}
|
||||
if _, err := toolsGoSource(Options{ToolsSource: Source{Repository: "http://forge/other/base.git"}}); err == nil ||
|
||||
!strings.Contains(err.Error(), "--tools-go-source") {
|
||||
t.Errorf("a base not named mesh-tools, and no Go toolchain given, was not refused naming the flag: %v", err)
|
||||
}
|
||||
}
|
||||
@@ -137,7 +137,26 @@ func registerAndAssign(ctx context.Context, o Options, control controlPlane, mod
|
||||
// should hold, seals every secret in them and publishes them, and on a first node that is the
|
||||
// slowest thing the mesh does.
|
||||
func pushNode(ctx context.Context, o Options, control controlPlane, say func(string)) (string, error) {
|
||||
said, err := control.within(o.Wait).tell(ctx, "push", o.Node)
|
||||
return pushing(ctx, o, control, false, say)
|
||||
}
|
||||
|
||||
// pushNodeApplied is pushNode that returns only once the node reports it applied exactly what it was
|
||||
// sent (`push <node> --wait`, novox/hq ADR 0010): for a push whose content the very next step reads
|
||||
// on the machine. A plain push returns as soon as the declaration is sent, and the node applies it a
|
||||
// moment later (issue 615).
|
||||
func pushNodeApplied(ctx context.Context, o Options, control controlPlane, say func(string)) (string, error) {
|
||||
return pushing(ctx, o, control, true, say)
|
||||
}
|
||||
|
||||
func pushing(ctx context.Context, o Options, control controlPlane, applied bool, say func(string)) (string, error) {
|
||||
args := []string{"push", o.Node}
|
||||
patience := o.Wait
|
||||
if applied {
|
||||
args = append(args, "--wait", o.Wait.String())
|
||||
// The controller's own wait, and time to compose and send before it starts.
|
||||
patience = 2 * o.Wait
|
||||
}
|
||||
said, err := control.within(patience).tell(ctx, args...)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf(
|
||||
"%w\n\nWhat was registered and assigned is registered and assigned, and this node has "+
|
||||
@@ -145,7 +164,20 @@ func pushNode(ctx context.Context, o Options, control controlPlane, say func(str
|
||||
"at all. Fix what it named and run this installer again: it will find the module "+
|
||||
"already registered and try the push again", err)
|
||||
}
|
||||
say(" pushed " + o.Node)
|
||||
if applied {
|
||||
say(" pushed " + o.Node + ", and it applied it")
|
||||
} else {
|
||||
say(" pushed " + o.Node)
|
||||
}
|
||||
// **Every push may carry a new bus user, and until the adoption the bus hears of it only from here**
|
||||
// (novox/hq issue 608, ADR 0331 §5, ADR 0333 §4). A module's account is minted into the mesh's
|
||||
// records and sealed to this node with the push; the bus reads its user list from a file, and until
|
||||
// the broker step adopts the bus as the nats module nothing but this installer writes that file. The
|
||||
// list was placed only when the node enrolled, so the build agent's account (step 13) never reached
|
||||
// the bus and the agent was refused ("Authorization Violation") until the sdk step gave up.
|
||||
if err := placeUntilAdopted(ctx, control, say); err != nil {
|
||||
return "", err
|
||||
}
|
||||
return strings.TrimSpace(said), nil
|
||||
}
|
||||
|
||||
|
||||
@@ -25,20 +25,62 @@ import (
|
||||
// buildWait bounds one module build. Generous, because the first build compiles a toolchain.
|
||||
const buildWait = 20 * time.Minute
|
||||
|
||||
// BuildBase asks the mesh to build the shared base every module with code of its own stands on.
|
||||
// BuildBase asks the mesh to build the shared base every module with code of its own stands on, and
|
||||
// the toolchain of every language genesis's own modules are written in.
|
||||
//
|
||||
// **First, because until it exists nothing else with code can be built.** Not registered as a
|
||||
// module here: it is never assigned — it runs nowhere — and the build itself records what was
|
||||
// made, which is all anything downstream reads.
|
||||
//
|
||||
// **Every toolchain a genesis module compiles in** (novox/hq issue 616). A bundle is compiled in its
|
||||
// language's base (mesh-controller internal/builder toolchain.go): TypeScript in mesh-tools, Go in
|
||||
// mesh-tools-go. The store's and the bus's modules carry Go code, so a genesis that built only
|
||||
// mesh-tools stopped at the store step: "this mesh holds no copy of it. Build mesh-tools-go first".
|
||||
// The bases are the ones genesisToolchains names, and a test holds them to the languages of every
|
||||
// module genesis installs, read from the catalogue.
|
||||
func BuildBase(ctx context.Context, o Options, control controlPlane, say func(string)) error {
|
||||
if o.ToolsSource.Repository == "" {
|
||||
return fmt.Errorf("phase two needs --tools-source: the shared base is built from its " +
|
||||
"own repository, and an installer told nothing cannot know where that is")
|
||||
}
|
||||
say(" building " + o.ToolsSource.Repository + " at " + refOr(o.ToolsSource.Ref))
|
||||
_, err := control.within(buildWait).tell(ctx,
|
||||
"build", o.ToolsSource.Repository, "--ref", refOr(o.ToolsSource.Ref), "--wait", "1200s")
|
||||
return err
|
||||
goSource, err := toolsGoSource(o)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
for _, src := range []Source{o.ToolsSource, goSource} {
|
||||
say(" building " + src.Repository + " at " + refOr(src.Ref))
|
||||
if _, err := control.within(buildWait).tell(ctx,
|
||||
"build", src.Repository, "--ref", refOr(src.Ref), "--wait", "1200s"); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// genesisToolchains is the base each language's bundles compile in, for the languages genesis's own
|
||||
// modules are written in — the same pairs as mesh-controller internal/builder toolchain.go — in the
|
||||
// order BuildBase builds them.
|
||||
var genesisToolchains = []struct{ Language, Base string }{
|
||||
{"typescript", "mesh-tools"},
|
||||
{"go", "mesh-tools-go"},
|
||||
}
|
||||
|
||||
// toolsGoSource is where the Go toolchain is built from: as given, or the repository beside the base's
|
||||
// named mesh-tools-go, which is how the mesh keeps its repositories side by side.
|
||||
func toolsGoSource(o Options) (Source, error) {
|
||||
if o.ToolsGoSource.Repository != "" {
|
||||
return o.ToolsGoSource, nil
|
||||
}
|
||||
repo := strings.TrimSuffix(o.ToolsSource.Repository, "/")
|
||||
suffix := ""
|
||||
if strings.HasSuffix(repo, ".git") {
|
||||
repo, suffix = strings.TrimSuffix(repo, ".git"), ".git"
|
||||
}
|
||||
if !strings.HasSuffix(repo, "mesh-tools") {
|
||||
return Source{}, fmt.Errorf("the Go toolchain is built from mesh-tools-go, and --tools-source (%s) is not a "+
|
||||
"repository named mesh-tools to find it beside; give --tools-go-source", o.ToolsSource.Repository)
|
||||
}
|
||||
return Source{Repository: repo + "-go" + suffix, Ref: o.ToolsGoSource.Ref}, nil
|
||||
}
|
||||
|
||||
// InstallFromCatalogue builds a catalogue module and installs it on this machine.
|
||||
|
||||
@@ -84,7 +84,7 @@ func InstallStore(ctx context.Context, o Options, control controlPlane,
|
||||
say); err != nil {
|
||||
return err
|
||||
}
|
||||
say(" adopted mesh-store — the foundation's store is now the " + module + " module")
|
||||
say(" adopted " + store.Name + " — the foundation's store is now the " + module + " module")
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -93,7 +93,8 @@ func InstallStore(ctx context.Context, o Options, control controlPlane,
|
||||
// be in it. InstallFromCatalogue is the same sequence without that moment; the store, the broker
|
||||
// and the vault each need it or need the shape, and three copies of it drifted.
|
||||
func installProvider(ctx context.Context, o Options, control controlPlane, module string,
|
||||
manifest []byte, buildNote string, beforePush func() error, say func(string)) error {
|
||||
manifest []byte, buildNote string, beforePush func() error, say func(string),
|
||||
send ...func() error) error {
|
||||
|
||||
remote := "/" + module + "-module.json"
|
||||
if err := control.carrying(ctx, module+"-module.json", manifest, remote); err != nil {
|
||||
@@ -132,6 +133,11 @@ func installProvider(ctx context.Context, o Options, control controlPlane, modul
|
||||
return err
|
||||
}
|
||||
}
|
||||
// A module whose first send is not a plain push says how it is sent: the bus, whose replacement is a
|
||||
// planned step (ADR 0236), is sent by that step (adoptTheBus).
|
||||
if len(send) > 0 && send[0] != nil {
|
||||
return send[0]()
|
||||
}
|
||||
_, err := pushNode(ctx, o, control, say)
|
||||
return err
|
||||
}
|
||||
@@ -176,9 +182,10 @@ const BusModule = "nats"
|
||||
// **The image is the one thing that changes, once** (ADR 0333 §3). The store's module pins the upstream
|
||||
// postgres the foundation runs; the bus's module builds its server image (it carries the mesh's snapshot
|
||||
// tool), so no pinned reference can be equal to the foundation's. The applier recreates the container on
|
||||
// the module's image, on the same streams, users and certificate. This says so before the push and waits
|
||||
// after it until the container runs the module's image and the bus answers, so nothing after this step
|
||||
// dials a bus that is restarting.
|
||||
// the module's image, on the same streams, users and certificate. The mesh replaces its bus only as a
|
||||
// planned step (ADR 0236), so the module is sent by that step: its streams snapshotted first, the restart
|
||||
// said, and the installer waits until the container runs the module's image, the bus answers, and the
|
||||
// controller ends the step done (bus_adoption.go), so nothing after this step dials a bus that is restarting.
|
||||
func InstallBroker(ctx context.Context, o Options, control controlPlane,
|
||||
foundation *declaration.Declaration, fetch func(context.Context, string) (int, string, error),
|
||||
say func(string)) error {
|
||||
@@ -197,20 +204,15 @@ func InstallBroker(ctx context.Context, o Options, control controlPlane,
|
||||
}
|
||||
say(" adopting " + bus.Name + " — the bus the foundation raised, its streams kept")
|
||||
if err := installProvider(ctx, o, control, module, manifest, "(the server, adopting the foundation's bus)",
|
||||
func() error {
|
||||
if running := runningImage(ctx, control, bus.Name); running != "" && running != bus.Image {
|
||||
say(" already restarted " + bus.Name + " — it runs the module's image")
|
||||
return nil
|
||||
}
|
||||
say(" restarting " + bus.Name + " — once, onto the " + module + " module's image; its " +
|
||||
"streams, users and certificate stay where they are (novox/hq ADR 0333 §3)")
|
||||
return nil
|
||||
}, say); err != nil {
|
||||
nil, say, func() error { return adoptTheBus(ctx, o, control, bus, say) }); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := waitForTheAdoptedBus(ctx, o, control, bus, fetch, say); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := waitForTheBusStep(ctx, o, control, say); err != nil {
|
||||
return err
|
||||
}
|
||||
say(" adopted " + bus.Name + " — the foundation's bus is now the " + module +
|
||||
" module, and its user list is the module's from here on")
|
||||
return nil
|
||||
|
||||
@@ -69,6 +69,7 @@ func aBusThatAdopts() (*asked, func(context.Context, string) (int, string, error
|
||||
func busStepWith(t *testing.T, o Options, runtime *asked,
|
||||
fetch func(context.Context, string) (int, string, error)) ([]string, error) {
|
||||
t.Helper()
|
||||
aGenesisBusOnDisk(t)
|
||||
rewritten, err := Rewrite(theRealBundle(t), held)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
@@ -222,7 +223,7 @@ func TestTheBrokerStepSaysTheRestartAndWaitsForTheBusToAnswer(t *testing.T) {
|
||||
runtime.answer = func(name string, args []string) (string, error) {
|
||||
joined := strings.Join(args, " ")
|
||||
switch {
|
||||
case strings.Contains(joined, "push anchor"):
|
||||
case strings.Contains(joined, "bus upgrade --why"):
|
||||
pushed = true
|
||||
case strings.Contains(joined, "inspect --format {{.Config.Image}} mesh-broker-nats"):
|
||||
if !pushed {
|
||||
@@ -304,7 +305,7 @@ func TestARerunAfterTheAdoptionSaysTheBusIsTheModulesAlready(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
text := strings.Join(said, "\n")
|
||||
if strings.Contains(text, "restarting") || !strings.Contains(text, "already restarted mesh-broker-nats") {
|
||||
if strings.Contains(text, "restarting") || !strings.Contains(text, "already adopted mesh-broker-nats") {
|
||||
t.Errorf("a re-run announced a restart, or did not say the bus is the module's already:\n%s", text)
|
||||
}
|
||||
}
|
||||
@@ -417,3 +418,30 @@ func TestTheBundlesBusFilesAreSeeds(t *testing.T) {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// aGenesisBusOnDisk puts what the adoption reads on the machine in a test's own directory: the bus's
|
||||
// certificate, the controller's bus credential, and where the snapshot goes. The step's wait is short.
|
||||
func aGenesisBusOnDisk(t *testing.T) {
|
||||
t.Helper()
|
||||
dir := t.TempDir()
|
||||
cert := filepath.Join(dir, "tls.crt")
|
||||
if err := os.WriteFile(cert, []byte(aCertificatePEM), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
secret := filepath.Join(dir, "bus-controller.secret")
|
||||
if err := os.WriteFile(secret, []byte("BUS-PW"), 0o600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
was := []string{busSnapshotFile, busSnapshotCredential, busCertificateFile, busControllerSecret}
|
||||
wasWithin := busStepWithin
|
||||
busSnapshotFile, busSnapshotCredential = filepath.Join(dir, "bus.tar"), filepath.Join(dir, "bus.credential")
|
||||
busCertificateFile, busControllerSecret = cert, secret
|
||||
busStepWithin = 50 * time.Millisecond
|
||||
t.Cleanup(func() {
|
||||
busSnapshotFile, busSnapshotCredential, busCertificateFile, busControllerSecret = was[0], was[1], was[2], was[3]
|
||||
busStepWithin = wasWithin
|
||||
})
|
||||
}
|
||||
|
||||
// aCertificatePEM is a PEM block standing for the bus's certificate; its pin is the sha256 of these bytes.
|
||||
const aCertificatePEM = "-----BEGIN CERTIFICATE-----\nAAECAwQFBgcICQ==\n-----END CERTIFICATE-----\n"
|
||||
|
||||
@@ -2,6 +2,7 @@ package bootstrap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"os"
|
||||
@@ -24,7 +25,7 @@ import (
|
||||
const (
|
||||
// foundationStore is the foundation's postgres container — the mesh's own memory, raised from the
|
||||
// bundle. gitea's bootstrap database lives here too, so a mesh runs one postgres (issue 051).
|
||||
foundationStore = "mesh-store"
|
||||
foundationStore = "postgres"
|
||||
// giteaBootstrap is the gitea server raised directly at genesis, before gitea is a module —
|
||||
// under the name the gitea MODULE declares for its container, so the module finds it and holds
|
||||
// it rather than raising a second forge beside it (novox/hq ADR 0163, rule 7; issue 090).
|
||||
@@ -49,8 +50,8 @@ const (
|
||||
packagesTeam = "packages"
|
||||
// giteaAdminUser is the admin the bootstrap creates and the provisioner later authenticates as.
|
||||
giteaAdminUser = "mesh-admin"
|
||||
// builderGiteaUser is the gitea account the builder publishes and pulls with at genesis. It is
|
||||
// the `as` the builder's static package binding names.
|
||||
// builderGiteaUser is the gitea account the build agent publishes and pulls with at genesis: the
|
||||
// `as` of the genesis document (novox/hq ADR 0336 §3). Retiring it is issue 602.
|
||||
builderGiteaUser = "mesh-builder"
|
||||
// giteaDBRole/giteaDBName is gitea's own database in the foundation store.
|
||||
giteaDBRole = "mesh_gitea"
|
||||
@@ -133,8 +134,8 @@ func RaisePackageRegistry(ctx context.Context, o Options, d Deps, control contro
|
||||
return err
|
||||
}
|
||||
|
||||
say(" delivering the builder its registry credential")
|
||||
if err := deliverBuilderNpm(ctx, o, control, builderPassword, say); err != nil {
|
||||
say(" sealing the build agent the genesis document for the forge it raised")
|
||||
if err := deliverGenesisRegistry(ctx, o, control, genesisRegistry(ports, builderPassword), say); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
@@ -362,27 +363,69 @@ func packagePasswords() (db, admin, builder string, err error) {
|
||||
return db, admin, builder, nil
|
||||
}
|
||||
|
||||
// deliverBuilderNpm seals the builder's registry password to this node as its `npm-password`
|
||||
// own-secret, the same way the control plane's store connections are delivered — carry the value in,
|
||||
// `secret accept`, and the next push writes it sealed where the builder reads it.
|
||||
func deliverBuilderNpm(ctx context.Context, o Options, control controlPlane, password string,
|
||||
say func(string)) error {
|
||||
at := "/accepting-npm-password"
|
||||
if err := control.carryingSecret(ctx, "mesh-accepting-npm-password", []byte(password), at); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := control.tell(ctx, "secret", "accept", o.Node, BuilderModule, "npm-password", "--from", at); err != nil {
|
||||
return err
|
||||
}
|
||||
// Push so the sealed secret reaches the builder, which restarts on it and comes back credentialed.
|
||||
if _, err := control.tell(ctx, "push", o.Node); err != nil {
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
// GenesisRegistrySecret is the build agent's own-secret the genesis document is sealed as (novox/hq
|
||||
// ADR 0336 §3). The build-agent manifest declares it, issued outside the mesh: only this installer
|
||||
// gives one, on genesis's node.
|
||||
const GenesisRegistrySecret = "genesis-package-registry"
|
||||
|
||||
// GenesisRegistry is the genesis document (novox/hq ADR 0336 §3): the forge this step raised, the port
|
||||
// this node gave the package registry, its npm path, and the account this step made with its password.
|
||||
// mesh-controller's cmd/mesh-builder reads it under the same field names while the build agent's
|
||||
// npm-package-registry requirement is unbound, and prefers the binding once the gitea module is
|
||||
// assigned and it binds.
|
||||
type GenesisRegistry struct {
|
||||
Scheme string `json:"scheme"`
|
||||
At string `json:"at"`
|
||||
Port int `json:"port"`
|
||||
NpmPath string `json:"npm-path"`
|
||||
As string `json:"as"`
|
||||
Password string `json:"password"`
|
||||
}
|
||||
|
||||
// PublishTheSDK dispatches a build of the SDK to the builder. The builder has its registry
|
||||
// credential by now, so the build's `npm publish` authenticates; the artifact is a `package`, built
|
||||
// genesisRegistry is the document for the forge raised here: on the machine's own loopback, where it
|
||||
// answers on the host network and where its ROOT_URL says it is (raiseGiteaServer), on the port this
|
||||
// node gave the package registry.
|
||||
func genesisRegistry(ports FoundationPorts, password string) GenesisRegistry {
|
||||
return GenesisRegistry{Scheme: "http", At: "127.0.0.1", Port: ports.Packages,
|
||||
NpmPath: "/api/packages/" + packagesOrg + "/npm/", As: builderGiteaUser, Password: password}
|
||||
}
|
||||
|
||||
// deliverGenesisRegistry seals the genesis document to the build agent on this node as its
|
||||
// `genesis-package-registry` own-secret (novox/hq ADR 0336 §3), the same way the control plane's store
|
||||
// connections are delivered — carry the value in, `secret accept`, and the next push writes it sealed
|
||||
// where the build agent reads it.
|
||||
//
|
||||
// **The build agent's one way to the forge until the registry binds.** Its npm-package-registry
|
||||
// requirement is optional (ADR 0336 §1), and nothing provides it until the gitea module is assigned
|
||||
// after the base, so the sdk step (15) publishes and the base step (16) resolves with the account in
|
||||
// this document. It replaces the retired builder's `npm-password` own-secret and the `serves.port`
|
||||
// setting its carried binding took, neither of which the build agent declares.
|
||||
func deliverGenesisRegistry(ctx context.Context, o Options, control controlPlane, doc GenesisRegistry,
|
||||
say func(string)) error {
|
||||
raw, err := json.Marshal(doc)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
at := "/accepting-" + GenesisRegistrySecret
|
||||
if err := control.carryingSecret(ctx, "mesh-accepting-"+GenesisRegistrySecret, raw, at); err != nil {
|
||||
return err
|
||||
}
|
||||
if _, err := control.tell(ctx, "secret", "accept", o.Node, BuilderModule, GenesisRegistrySecret, "--from", at); err != nil {
|
||||
return err
|
||||
}
|
||||
// Push so the sealed document reaches the build agent, which reads it at its next build — and,
|
||||
// like every push before the adoption, the bus hears the users it carries (issue 608).
|
||||
//
|
||||
// **Waited for until the node applied it** (issue 615). The next step asks the build agent to
|
||||
// publish the SDK, and the agent reads the document from the file the node writes when it applies
|
||||
// this push. A push that returned on sending let the ask race the apply: one genesis found the
|
||||
// document in time, the next was refused, "neither its binding nor the genesis document".
|
||||
_, err = pushNodeApplied(ctx, o, control, say)
|
||||
return err
|
||||
}
|
||||
|
||||
// PublishTheSDK dispatches a build of the SDK to the build agent. The agent has the genesis document by
|
||||
// now (novox/hq ADR 0336 §7), so the build's `npm publish` authenticates; the artifact is a `package`, built
|
||||
// on a public base, so this needs no toolchain — which is the whole point of doing it before the base.
|
||||
func PublishTheSDK(ctx context.Context, o Options, control controlPlane, say func(string)) error {
|
||||
if o.SDKSource.Repository == "" {
|
||||
|
||||
@@ -117,24 +117,6 @@ const busModulePort = 4222
|
||||
// PortsSetting is the controller's settings key for a module's given ports.
|
||||
const PortsSetting = "ports"
|
||||
|
||||
// ServesSetting is the settings key that carries what a provider serves, inside the one binding a
|
||||
// module carries rather than resolves — the builder's package binding (novox/hq 04-ISSUES/085).
|
||||
//
|
||||
// **A port given at genesis has to be a setting wherever it is read, or something puts it back.**
|
||||
// The builder reaches the package registry through a binding written in its own manifest, because
|
||||
// at genesis no module yet provides `package-registry` and so there is nothing for the controller
|
||||
// to resolve it from. That binding used to be rewritten, as text, when the installer registered the
|
||||
// builder — which a later registration from the catalogue undid silently. Set as a node's setting
|
||||
// instead, it is held by the controller rather than by the manifest, so re-registering the builder
|
||||
// leaves it where it was.
|
||||
//
|
||||
// **A settings layer is the module's, not one resource's.** The controller lays it over every file
|
||||
// of that module which merges as JSON, so `serves` lands in the package binding only because that
|
||||
// binding is the builder's one mergeable file. A second mergeable file added to the builder would
|
||||
// be given a `serves` key too, meaning nothing to whatever reads it. Worth knowing before adding
|
||||
// one.
|
||||
const ServesSetting = "serves"
|
||||
|
||||
// setFoundationSettings tells the controller the ports this node gave a foundation module — and,
|
||||
// on an adopted node, that the registry is reached from anywhere, as a node pulls from it before it
|
||||
// has a private-network address (novox/hq ADR 0100). Done after the module is registered and before
|
||||
@@ -148,13 +130,8 @@ func setFoundationSettings(ctx context.Context, o Options, control controlPlane,
|
||||
if o.Adopted && module == RegistryModule {
|
||||
values["expose"] = map[string]string{strconv.Itoa(DefaultPorts().Registry): "anywhere"}
|
||||
}
|
||||
if packages := o.Ports.orDefaults().Packages; module == BuilderModule &&
|
||||
packages != DefaultPorts().Packages {
|
||||
// The one binding nothing resolves: the builder dials the forge by a number it carries.
|
||||
// The rest of the binding — the provision, the forge it is from, the account it presents —
|
||||
// is the manifest's and stays there.
|
||||
values[ServesSetting] = map[string]int{"port": packages}
|
||||
}
|
||||
// No `serves` setting for the build agent: the port given for the package registry reaches it in
|
||||
// the genesis document (novox/hq ADR 0336 §3), and from the binding once the registry binds.
|
||||
if len(values) == 0 {
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -68,7 +68,7 @@ func TestGivenPortsMoveOnlyTheMachinesSide(t *testing.T) {
|
||||
if got.Places == 0 {
|
||||
t.Fatal("nothing was rewritten")
|
||||
}
|
||||
storeC := containerNamed(r.Declaration, "mesh-store")
|
||||
storeC := containerNamed(r.Declaration, "postgres")
|
||||
if len(storeC.Ports) != 1 || storeC.Ports[0] != "5433:5432" {
|
||||
t.Errorf("the store publishes %v", storeC.Ports)
|
||||
}
|
||||
@@ -239,6 +239,12 @@ func (c *controlRecorder) run(_ context.Context, name string, args ...string) (s
|
||||
}
|
||||
if name == "docker" && args[0] == "exec" {
|
||||
c.told = append(c.told, strings.Join(args[3:], " "))
|
||||
if strings.Join(args[3:], " ") == "broker accounts" {
|
||||
return "accounts {}\n", nil // the composed user list, placed after every push (issue 608)
|
||||
}
|
||||
}
|
||||
if name == "sh" {
|
||||
c.told = append(c.told, "placed the bus's users")
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
|
||||
@@ -0,0 +1,134 @@
|
||||
package bootstrap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Defends novox/hq issue 608 (ADR 0331 §5, ADR 0333 §4): until the bus is adopted as the nats module,
|
||||
// every push genesis makes is followed by the installer placing the composed user list where the bus
|
||||
// reads it, and making the bus re-read it. The build agent's account was minted at step 13 and sealed
|
||||
// with that push, and the list was placed only at enrolment, so the bus refused the agent
|
||||
// ("Authorization Violation") and genesis stopped at step 15.
|
||||
|
||||
// placing answers the controller as a mesh whose bus is or is not the nats module yet, and records
|
||||
// what was run, in order.
|
||||
func placing(adopted bool) (*asked, controlPlane) {
|
||||
listed := "build-agent 1\n"
|
||||
if adopted {
|
||||
listed += "nats 1\n"
|
||||
}
|
||||
runtime := &asked{}
|
||||
runtime.answer = func(name string, args []string) (string, error) {
|
||||
joined := strings.Join(args, " ")
|
||||
switch {
|
||||
case name == "sh":
|
||||
return "", nil
|
||||
case strings.HasSuffix(joined, "module list"):
|
||||
return listed, nil
|
||||
case strings.HasSuffix(joined, "broker accounts"):
|
||||
return "accounts {\n MESH { users = [ { user: \"anchor.build-agent\" } ] }\n}\n", nil
|
||||
}
|
||||
return "", nil
|
||||
}
|
||||
return runtime, controlPlane{container: "mesh-controller", run: runtime.run, timeout: time.Second}
|
||||
}
|
||||
|
||||
// placedAfterThePush is whether the bus's users were placed — written at the module's bus-users path,
|
||||
// the bus told to re-read them — after the push, and how often.
|
||||
func placedAfterThePush(t *testing.T, commands []string) int {
|
||||
t.Helper()
|
||||
pushed, placed := -1, 0
|
||||
for i, c := range commands {
|
||||
if strings.Contains(c, "/mesh-controller push anchor") && pushed < 0 {
|
||||
pushed = i
|
||||
}
|
||||
if strings.HasPrefix(c, "sh -c") && strings.Contains(c, busAccounts) &&
|
||||
strings.Contains(c, "kill -s HUP "+busContainer) {
|
||||
if pushed < 0 || i < pushed {
|
||||
t.Fatalf("the bus's users were placed before the push that carries the account: %v", commands)
|
||||
}
|
||||
placed++
|
||||
}
|
||||
}
|
||||
if pushed < 0 {
|
||||
t.Fatalf("nothing was pushed: %v", commands)
|
||||
}
|
||||
return placed
|
||||
}
|
||||
|
||||
func TestTheBusHearsTheBuildAgentsAccountAfterItsPush(t *testing.T) {
|
||||
t.Setenv("TMPDIR", t.TempDir())
|
||||
runtime, control := placing(false)
|
||||
o := Options{Node: "anchor", Wait: time.Second}
|
||||
if _, err := installModule(context.Background(), o, control, BuilderModule, []byte(`{}`), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if n := placedAfterThePush(t, runtime.commands); n != 1 {
|
||||
t.Fatalf("the bus's users were placed %d time(s) after the build agent's push; once: %v", n, runtime.commands)
|
||||
}
|
||||
}
|
||||
|
||||
func TestTheGenesisDocumentsPushIsHeardByTheBusToo(t *testing.T) {
|
||||
t.Setenv("TMPDIR", t.TempDir())
|
||||
runtime, control := placing(false)
|
||||
o := Options{Node: "anchor", Wait: time.Second}
|
||||
if err := deliverGenesisRegistry(context.Background(), o, control, genesisRegistry(DefaultPorts(), "pw"), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if n := placedAfterThePush(t, runtime.commands); n != 1 {
|
||||
t.Fatalf("the bus's users were placed %d time(s) after the genesis document's push; once: %v", n, runtime.commands)
|
||||
}
|
||||
}
|
||||
|
||||
// From the adoption on the nats module writes the list, and the installer does not (ADR 0333 §4).
|
||||
func TestOnceTheBusIsTheNatsModulesThePushPlacesNothing(t *testing.T) {
|
||||
t.Setenv("TMPDIR", t.TempDir())
|
||||
runtime, control := placing(true)
|
||||
o := Options{Node: "anchor", Wait: time.Second}
|
||||
if _, err := installModule(context.Background(), o, control, BuilderModule, []byte(`{}`), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if n := placedAfterThePush(t, runtime.commands); n != 0 {
|
||||
t.Fatalf("the installer placed the bus's users over the nats module's: %v", runtime.commands)
|
||||
}
|
||||
}
|
||||
|
||||
// Defends novox/hq issue 615: the packages step's push is waited for until the node applied it, because
|
||||
// the sdk step right after asks the build agent for a build that reads the genesis document from the
|
||||
// file that apply writes. A push that returned on sending let the ask race the apply.
|
||||
func TestThePackagesStepWaitsUntilTheNodeAppliedTheGenesisDocument(t *testing.T) {
|
||||
t.Setenv("TMPDIR", t.TempDir())
|
||||
runtime, control := placing(false)
|
||||
o := Options{Node: "anchor", Wait: 3 * time.Minute}
|
||||
if err := deliverGenesisRegistry(context.Background(), o, control, genesisRegistry(DefaultPorts(), "pw"), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, c := range runtime.commands {
|
||||
if strings.Contains(c, "/mesh-controller push anchor") {
|
||||
if !strings.HasSuffix(c, "push anchor --wait 3m0s") {
|
||||
t.Fatalf("the genesis document's push does not wait for the node to apply it: %s", c)
|
||||
}
|
||||
return
|
||||
}
|
||||
}
|
||||
t.Fatalf("the genesis document was never pushed: %v", runtime.commands)
|
||||
}
|
||||
|
||||
// Every other push of genesis still returns on sending: only a push whose content the next step reads on
|
||||
// the machine waits.
|
||||
func TestAnOrdinaryPushDoesNotWait(t *testing.T) {
|
||||
t.Setenv("TMPDIR", t.TempDir())
|
||||
runtime, control := placing(false)
|
||||
o := Options{Node: "anchor", Wait: time.Second}
|
||||
if _, err := installModule(context.Background(), o, control, BuilderModule, []byte(`{}`), quietly); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
for _, c := range runtime.commands {
|
||||
if strings.Contains(c, "push anchor --wait") {
|
||||
t.Fatalf("an ordinary push waits: %s", c)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -58,8 +58,20 @@ func aMeshThatAgrees(answers map[string]string) func(string, []string) (string,
|
||||
}
|
||||
}
|
||||
switch {
|
||||
case name == "sh" && len(args) == 2 && strings.Contains(args[1], "accounts.conf"):
|
||||
return "", nil // the bus's users placed after a push (issue 608)
|
||||
case name == "sh" && len(args) == 2 && strings.Contains(args[1], "mesh-nats-snapshot"):
|
||||
return "", nil // the streams snapshotted before the bus's planned step (issue 590)
|
||||
case name == "docker" && strings.HasSuffix(joined, "/mesh-controller bus"):
|
||||
return "the bus is nats, built 53e51864, on anchor\nlast step 1: not known → 53e51864 on anchor by installer (" +
|
||||
adoptionWhy + "): done at 2026-10-13 11:40; snapshot " + busSnapshotFile + "\n", nil
|
||||
case name == "docker" && strings.Contains(joined, "/mesh-controller builds nats -n 1"):
|
||||
return "nats built 53e51864 anchor\n image artifact-store://nats/server@sha256:" +
|
||||
strings.Repeat("4", 64) + "\n bundle artifact-store://nats/tools/blobs/sha256:" + strings.Repeat("5", 64) + "\n", nil
|
||||
case name != "docker":
|
||||
return "", fmt.Errorf("unexpected program %q", name)
|
||||
case strings.HasSuffix(joined, "broker accounts"):
|
||||
return "accounts {}\n", nil
|
||||
case args[0] == "cp":
|
||||
return "", nil
|
||||
case args[0] == "container":
|
||||
|
||||
@@ -47,6 +47,9 @@ const (
|
||||
// StoreSuperuserFile is where the store's superuser password lives on the machine — the
|
||||
// postgres module's own-secret path, so genesis and adoption write the same file.
|
||||
StoreSuperuserFile = "/var/lib/postgres/superuser.secret"
|
||||
// StoreDataDir is where the store keeps its data — the postgres module's data directory, so
|
||||
// genesis raises the store where the module adopts it (novox/hq ADR 0338 §1).
|
||||
StoreDataDir = "/var/lib/mesh-store"
|
||||
// BusControllerFile is where the controller's password on the bus lives on the machine. Not a
|
||||
// module's path: no module reads it — the permanent controller is handed the address the
|
||||
// temporary one was given — and genesis keeps it only so a second run puts the same account
|
||||
@@ -62,7 +65,7 @@ const (
|
||||
// What the template says, matched exactly. A template that says something else is a template
|
||||
// this installer does not know how to make safe, and it says so rather than guessing.
|
||||
templateStorePassword = `"POSTGRES_PASSWORD": "bootstrap"`
|
||||
templateStoreVolumes = `"volumes": ["mesh-store-data:/var/lib/postgresql/data"]`
|
||||
templateStoreVolumes = `"volumes": ["` + StoreDataDir + `:/var/lib/postgresql/data"]`
|
||||
templateStoreURL = "postgres:bootstrap@"
|
||||
|
||||
// BusURLPlaceholder is the controller's account in its bus address, as the template names it.
|
||||
@@ -265,8 +268,8 @@ func Masking(say func(string), c RootCredentials) func(string) {
|
||||
// RefuseExistingServers stops a run that would put a made credential in front of a store raised
|
||||
// by an earlier installer with the template's.
|
||||
//
|
||||
// The store's password is set by initdb, once, on an empty volume. A machine that already holds
|
||||
// `mesh-store-data` and has no credential file was raised with `bootstrap`, and minting a new
|
||||
// The store's password is set by initdb, once, on an empty data directory. A machine that already holds
|
||||
// a cluster in the store's data directory and has no credential file was raised with `bootstrap`, and minting a new
|
||||
// value here would make a bundle that dials with a password the server does not have — failing
|
||||
// three steps later, in the schemas, with nothing pointing back here. Refused by name instead,
|
||||
// with the way forward.
|
||||
@@ -278,11 +281,14 @@ func RefuseExistingServers(ctx context.Context, run Runner, c RootCredentials) e
|
||||
if !c.StoreMade {
|
||||
return nil
|
||||
}
|
||||
if _, err := run(ctx, "docker", "volume", "inspect", "mesh-store-data"); err != nil {
|
||||
return nil // no such volume: a fresh machine, which is the case this installer makes
|
||||
// Where the store keeps its data, as the postgres module does (novox/hq ADR 0338 §2): a cluster
|
||||
// there is one initdb already set a password for. The docker volume genesis used before is not
|
||||
// the store's data any more, and a machine holding only that is not refused.
|
||||
if _, err := run(ctx, "test", "-e", StoreDataDir+"/pgdata/PG_VERSION"); err != nil {
|
||||
return nil // no cluster there: a fresh machine, which is the case this installer makes
|
||||
}
|
||||
return fmt.Errorf(
|
||||
"this machine already holds the store's data (volume mesh-store-data) and no credential at %s, so it was raised "+
|
||||
"this machine already holds the store's data (in "+StoreDataDir+") and no credential at %s, so it was raised "+
|
||||
"by an earlier installer with the template's password. A new one made here would not open it. "+
|
||||
"Put the password the store has into %s (0600, the value alone) and run again; then change it "+
|
||||
"on the server and accept the new value — this installer does not rotate a running store",
|
||||
@@ -311,7 +317,7 @@ func RewriteRoot(r *Rewritten, c RootCredentials) (RootRewrite, error) {
|
||||
return out, err
|
||||
}
|
||||
if bundle, err = replaceOnce(bundle, templateStoreVolumes,
|
||||
`"volumes": ["mesh-store-data:/var/lib/postgresql/data", "`+StoreSuperuserFile+":"+storeSuperuserMount+`:ro"]`,
|
||||
`"volumes": ["`+StoreDataDir+`:/var/lib/postgresql/data", "`+StoreSuperuserFile+":"+storeSuperuserMount+`:ro"]`,
|
||||
"the store's volumes"); err != nil {
|
||||
return out, err
|
||||
}
|
||||
|
||||
@@ -59,7 +59,7 @@ func TestTheProducedBundleCarriesNoWellKnownCredential(t *testing.T) {
|
||||
switch x := res.(type) {
|
||||
case *declaration.Container:
|
||||
switch x.Name {
|
||||
case "mesh-store":
|
||||
case "postgres":
|
||||
store = true
|
||||
if _, has := x.Env["POSTGRES_PASSWORD"]; has {
|
||||
t.Error("the store still takes its password from its environment")
|
||||
|
||||
@@ -0,0 +1,163 @@
|
||||
package bootstrap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/novox/mesh-host/internal/declaration"
|
||||
)
|
||||
|
||||
// Defends novox/hq ADR 0338 (issue 609): genesis raises its store as the postgres module's server, so
|
||||
// the store step adopts it as it runs. Until then the bundle raised `mesh-store`, on another image, in a
|
||||
// docker volume, and genesis stopped at step 17 of 24.
|
||||
|
||||
// theStoreGenesisRaises is the store container of the bundle as the installer applies it: rewritten for
|
||||
// this machine's credentials, so its password is the file the module reads too.
|
||||
func theStoreGenesisRaises(t *testing.T) *declaration.Container {
|
||||
t.Helper()
|
||||
r := producedBundle(t)
|
||||
store, err := storeIn(r.Declaration)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return store
|
||||
}
|
||||
|
||||
// The bundle's store is exactly the catalogue's postgres module's server, read from the module's own
|
||||
// manifest (ADR 0338 §1): its name, its image (so a drift of either pin fails here), where its data is,
|
||||
// and the file its superuser password is read from, with the environment that says so.
|
||||
func TestTheBundleRaisesTheStoreAsTheCataloguesPostgresModuleDeclaresIt(t *testing.T) {
|
||||
manifest := theCataloguesModule(t, "postgres")
|
||||
var m struct {
|
||||
Resources []struct {
|
||||
ID string `json:"id"`
|
||||
Type string `json:"type"`
|
||||
Name string `json:"name"`
|
||||
Image string `json:"image"`
|
||||
Env map[string]string `json:"env"`
|
||||
Ports []string `json:"ports"`
|
||||
Volumes []string `json:"volumes"`
|
||||
} `json:"resources"`
|
||||
}
|
||||
if err := json.Unmarshal(manifest, &m); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
ours := theStoreGenesisRaises(t)
|
||||
found := false
|
||||
for _, r := range m.Resources {
|
||||
if r.Type != "container" || r.ID != "server" {
|
||||
continue
|
||||
}
|
||||
found = true
|
||||
if ours.Name != r.Name {
|
||||
t.Errorf("the bundle raises the store as %q; the module's server is %q", ours.Name, r.Name)
|
||||
}
|
||||
if ours.Image != r.Image {
|
||||
t.Errorf("the bundle raises the store on %s; the module pins %s — the two pins move together", ours.Image, r.Image)
|
||||
}
|
||||
for _, key := range []string{"POSTGRES_PASSWORD_FILE", "PGDATA"} {
|
||||
if ours.Env[key] != r.Env[key] {
|
||||
t.Errorf("the bundle's store has %s=%q; the module's %q", key, ours.Env[key], r.Env[key])
|
||||
}
|
||||
}
|
||||
if _, has := ours.Env["POSTGRES_PASSWORD"]; has {
|
||||
t.Error("the bundle's store takes its password from its environment; the module reads a file")
|
||||
}
|
||||
// The module's own directory for its state is <data root>/<module>, where genesis keeps the
|
||||
// superuser's file (StoreSuperuserFile).
|
||||
var theirs []string
|
||||
for _, v := range r.Volumes {
|
||||
theirs = append(theirs, strings.ReplaceAll(v, "${dir:state}", "/var/lib/postgres"))
|
||||
}
|
||||
if strings.Join(ours.Volumes, " ") != strings.Join(theirs, " ") {
|
||||
t.Errorf("the bundle's store mounts %v; the module's %v", ours.Volumes, theirs)
|
||||
}
|
||||
if strings.Join(ours.Ports, " ") != strings.Join(r.Ports, " ") {
|
||||
t.Errorf("the bundle publishes the store on %v; the module on %v", ours.Ports, r.Ports)
|
||||
}
|
||||
// And the store step's own check agrees: by name and image, before anything is registered.
|
||||
if err := serverMatchesFoundation(manifest, ours, "postgres"); err != nil {
|
||||
t.Errorf("the store step would refuse the store the bundle raises: %v", err)
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Fatal("the postgres module declares no server container")
|
||||
}
|
||||
}
|
||||
|
||||
// The store's data directory is made by the bundle before the store starts, owned by the image's
|
||||
// postgres user, as the module declares it (ADR 0338 §1, and the measurement under its §5).
|
||||
func TestTheBundleMakesTheStoresDataDirectoryAsTheModuleDoes(t *testing.T) {
|
||||
r := producedBundle(t)
|
||||
at, store := -1, -1
|
||||
for i, res := range r.Declaration.Resources {
|
||||
if d, ok := res.(*declaration.Directory); ok && d.Path == StoreDataDir {
|
||||
at = i
|
||||
if d.Mode != "0700" || d.Owner != "999:70" {
|
||||
t.Errorf("the store's data directory is made %s %s; the module makes it 0700 999:70", d.Mode, d.Owner)
|
||||
}
|
||||
}
|
||||
if res.Identity() == StoreID {
|
||||
store = i
|
||||
}
|
||||
}
|
||||
if at < 0 || store < 0 || at > store {
|
||||
t.Fatalf("the store's data directory %s is not made before the store (directory at %d, store at %d)", StoreDataDir, at, store)
|
||||
}
|
||||
}
|
||||
|
||||
// No step of the bundle and no step of the installer names `mesh-store`, which is the seat's name only
|
||||
// (ADR 0338 §2): every step that reaches the store reaches the container the bundle raised.
|
||||
func TestNoStepReachesTheStoreByTheSeatsName(t *testing.T) {
|
||||
text := string(theRealBundle(t))
|
||||
for _, by := range []string{`"in": "mesh-store"`, `container:mesh-store`, `exec mesh-store`, `"name": "mesh-store"`, `mesh-store-data`} {
|
||||
if strings.Contains(text, by) {
|
||||
t.Errorf("the bundle still reaches the store as %s", by)
|
||||
}
|
||||
}
|
||||
store := theStoreGenesisRaises(t)
|
||||
if foundationStore != store.Name {
|
||||
t.Errorf("the packages step reaches the store as %q; the bundle raises it as %q", foundationStore, store.Name)
|
||||
}
|
||||
r := producedBundle(t)
|
||||
for _, res := range r.Declaration.Resources {
|
||||
if a, ok := res.(*declaration.Action); ok && a.In != "" && a.In != store.Name && strings.Contains(a.ID, "database") {
|
||||
t.Errorf("the step %s reaches the store in %q", a.ID, a.In)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The installer's refusal to raise a store over data it cannot open looks where the store keeps its data
|
||||
// (ADR 0338 §2): a cluster there and no credential is refused; the old docker volume alone is not.
|
||||
func TestTheRefusalOverExistingDataLooksInTheStoresDirectory(t *testing.T) {
|
||||
made := RootCredentials{Store: "s", Bus: "b", StoreMade: true}
|
||||
machine := func(cluster, volume bool) Runner {
|
||||
return func(_ context.Context, name string, args ...string) (string, error) {
|
||||
joined := name + " " + strings.Join(args, " ")
|
||||
switch {
|
||||
case joined == "test -e "+StoreDataDir+"/pgdata/PG_VERSION":
|
||||
if cluster {
|
||||
return "", nil
|
||||
}
|
||||
case strings.HasPrefix(joined, "docker volume inspect"):
|
||||
if volume {
|
||||
return "[]", nil
|
||||
}
|
||||
}
|
||||
return "", errors.New("exit status 1")
|
||||
}
|
||||
}
|
||||
err := RefuseExistingServers(context.Background(), machine(true, false), made)
|
||||
if err == nil || !strings.Contains(err.Error(), StoreDataDir) {
|
||||
t.Fatalf("a cluster in %s and no credential was not refused naming it: %v", StoreDataDir, err)
|
||||
}
|
||||
if err := RefuseExistingServers(context.Background(), machine(false, true), made); err != nil {
|
||||
t.Fatalf("a machine holding only the old volume was refused: %v", err)
|
||||
}
|
||||
if err := RefuseExistingServers(context.Background(), machine(true, false), RootCredentials{Store: "s"}); err != nil {
|
||||
t.Fatalf("a kept credential was refused: %v", err)
|
||||
}
|
||||
}
|
||||
@@ -89,7 +89,7 @@ func TestAFoundationThatIsUpAndAnsweringIsAccepted(t *testing.T) {
|
||||
// run-once and scheduled shapes are excluded on purpose — a step that has exited is not a
|
||||
// fault. The name is `temp-mesh-controller` because the permanent one is a module and takes the
|
||||
// plain name (novox/hq ADR 0067), which is what makes the two of them coexist at all.
|
||||
want := []string{"mesh-store", "mesh-broker-nats", "temp-mesh-controller"}
|
||||
want := []string{"postgres", "mesh-broker-nats", "temp-mesh-controller"}
|
||||
if len(verified.Running) != len(want) {
|
||||
t.Fatalf("confirmed %v running, want %v", verified.Running, want)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user