Files
mesh-host/internal/bootstrap/registry_test.go
jschoubben 5dd439df50 inspect by kind, not the ambiguous bare form — a same-named network stops a container from ever being found
docker inspect <name> resolves across every object kind, not just
containers. A module regularly names a network the same as the
container that joins it (keycloak does this today, ordinarily) — so
when the container does not exist yet but the same-named network
already does, the bare form answers with the network's JSON instead
of reporting the container absent, and the template these callers use
(.State.Running) fails to execute against it entirely.

Live on novox tonight: minio's LB container, named the same as its
network ("minio"), could never be created — every apply crashed on
"the container runtime could not say whether minio is here", stuck
since first push, because the check itself never got a clean answer.

Fixed at every call site asking a container's state by name
(containerState, inspectFound, NamesFree, raiseGiteaServer,
containerRunning) by scoping to `docker container inspect`, matching
the type-scoped form this codebase already uses correctly for
networks, volumes and images elsewhere. Also scoped the one image
inspect that was still bare (publish.go), for the same reason.

mesh-host runs as a host-level service (nox-mesh-host.service), not a
Docker module — merging this does not redeploy it. The live novox
failure persists until the service itself is rebuilt and updated.
2026-09-24 19:50:16 +02:00

217 lines
7.8 KiB
Go

package bootstrap
import (
"context"
"fmt"
"net/http"
"os"
"path/filepath"
"strings"
"testing"
"time"
)
// Step 7 installs the one module whose image can never come from the mesh's own registry, because
// it IS the mesh's own registry (novox/hq 04-ISSUES/029). These tests defend that, and defend the
// distinction the whole verify layer of this program is built on: a container that is up is not a
// service that answers.
// catalogueWith writes a fake catalogue checkout holding one module's manifest.
//
// A fixture here rather than the real catalogue, unlike the foundation example the rewrite tests
// use: the catalogue is a different repository on a different branch, and a test that read it
// would pass or fail according to what somebody else had checked out.
func catalogueWith(t *testing.T, module, manifest string) string {
t.Helper()
root := t.TempDir()
dir := filepath.Join(root, catalogueDir, module)
if err := os.MkdirAll(dir, 0o755); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(dir, "module.json"), []byte(manifest), 0o644); err != nil {
t.Fatal(err)
}
return root
}
const upstreamRegistryManifest = `{
"module": "distribution",
"version": "1",
"provides": [{"name": "artifact-store", "scope": "mesh"}],
"capabilities": ["container-runtime"],
"resources": [
{"id": "state", "type": "directory", "path": "/var/lib/mesh/registry", "mode": "0700"},
{"id": "store", "type": "container", "name": "mesh-registry",
"image": "registry@sha256:a3d8aaa63ed8681a604f1dea0aa03f100d5895b6a58ace528858a7b332415373",
"ports": ["5000:5000"]}
]
}`
// aMeshThatAgrees answers every command the installer issues at steps 7 and 9 the way a working
// mesh would, except for whatever a test overrides.
func aMeshThatAgrees(answers map[string]string) func(string, []string) (string, error) {
return func(name string, args []string) (string, error) {
joined := strings.Join(args, " ")
for fragment, said := range answers {
if strings.Contains(joined, fragment) {
return said, nil
}
}
switch {
case name != "docker":
return "", fmt.Errorf("unexpected program %q", name)
case args[0] == "cp":
return "", nil
case args[0] == "container":
return "true running\n", nil
case args[0] == "exec":
return "", nil
}
return "", fmt.Errorf("unexpected: %v", args)
}
}
func installing(t *testing.T, catalogue string) Options {
t.Helper()
return Options{
Node: "anchor",
Catalogue: catalogue,
Registry: "127.0.0.1:5000",
Timeout: time.Second,
Wait: 0,
}
}
// A container that is up is not a registry that serves. `/v2/` is the registry API's own "yes, I
// am one and I am ready", and the step after this pushes to it — so it is refused here rather than
// discovered inside a `docker push`.
func TestARegistryContainerThatIsUpIsNotARegistryThatServes(t *testing.T) {
previous := answerEvery
answerEvery = time.Millisecond
defer func() { answerEvery = previous }()
runtime := &asked{answer: aMeshThatAgrees(nil)}
deps := Deps{
Run: runtime.run,
Fetch: func(context.Context, string) (int, string, error) {
return http.StatusInternalServerError, "", nil
},
}
_, err := InstallRegistry(context.Background(),
installing(t, catalogueWith(t, RegistryModule, upstreamRegistryManifest)),
deps, controlPlane{container: "temp-mesh-controller", run: runtime.run, timeout: time.Second},
func(string) {})
if err == nil {
t.Fatal("a registry whose container is up and which answers 500 was accepted")
}
for _, wanted := range []string{"/v2/", "Running is not serving"} {
if !strings.Contains(err.Error(), wanted) {
t.Errorf("the refusal does not mention %q:\n%v", wanted, err)
}
}
}
// The whole of step 7, against a mesh that agrees: registered, assigned, pushed, up, and answering.
func TestARegistryThatAnswersIsAccepted(t *testing.T) {
runtime := &asked{answer: aMeshThatAgrees(nil)}
deps := Deps{
Run: runtime.run,
Fetch: func(context.Context, string) (int, string, error) {
return http.StatusOK, "{}", nil
},
}
out, err := InstallRegistry(context.Background(),
installing(t, catalogueWith(t, RegistryModule, upstreamRegistryManifest)),
deps, controlPlane{container: "temp-mesh-controller", run: runtime.run, timeout: time.Second},
func(string) {})
if err != nil {
t.Fatal(err)
}
if out.Container != "mesh-registry" {
t.Errorf("the registry's container is %q", out.Container)
}
if out.Answered != http.StatusOK {
t.Errorf("the registry answered %d", out.Answered)
}
// Registered, assigned and pushed, through the same three commands a person types.
for _, wanted := range []string{
"module add /distribution-module.json",
"assign anchor distribution",
"push anchor",
} {
if !runtime.ran(wanted) {
t.Errorf("the installer never ran %q: %v", wanted, runtime.commands)
}
}
}
// **The registry's image is upstream and it is never built.** A manifest carrying the catalogue's
// placeholder digest would mean somebody had made this module buildable — which is the cycle
// novox/hq 04-ISSUES/029 settled: a module that provides the artifact store cannot be delivered
// through the artifact store.
func TestARegistryManifestThatWantsBuildingIsRefused(t *testing.T) {
wants := strings.Replace(upstreamRegistryManifest,
"registry@sha256:a3d8aaa63ed8681a604f1dea0aa03f100d5895b6a58ace528858a7b332415373",
"mesh-runtime-registry@"+placeholderDigest, 1)
runtime := &asked{answer: aMeshThatAgrees(nil)}
_, err := InstallRegistry(context.Background(),
installing(t, catalogueWith(t, RegistryModule, wants)),
Deps{Run: runtime.run}, controlPlane{container: "temp-mesh-controller", run: runtime.run},
func(string) {})
if err == nil {
t.Fatal("a registry manifest naming an image the mesh would have to build was accepted")
}
if !strings.Contains(err.Error(), "04-ISSUES/029") {
t.Errorf("the refusal does not name the decision it rests on: %v", err)
}
if runtime.ran("module add") {
t.Error("it was registered anyway")
}
}
// A catalogue that is not there is said plainly, with what --catalog is. This is the most likely
// mistake anybody makes at this step and the least interesting to debug.
func TestACatalogueThatIsNotThereIsSaidPlainly(t *testing.T) {
runtime := &asked{answer: aMeshThatAgrees(nil)}
_, err := InstallRegistry(context.Background(),
installing(t, filepath.Join(t.TempDir(), "nowhere")),
Deps{Run: runtime.run}, controlPlane{container: "temp-mesh-controller", run: runtime.run},
func(string) {})
if err == nil {
t.Fatal("a catalogue that does not exist was accepted")
}
if !strings.Contains(err.Error(), "--catalog") {
t.Errorf("the refusal does not say what to fix: %v", err)
}
}
// A refusal from the control plane is repeated verbatim. mesh-controller refuses in paragraphs —
// "nothing provides route, wanted by registry" — and an installer that reported "exit status 1"
// would throw away the only thing a person can act on.
func TestWhatTheMeshRefusedIsRepeated(t *testing.T) {
refusal := "nothing provides \"route\", wanted by registry"
runtime := &asked{answer: func(name string, args []string) (string, error) {
if strings.Contains(strings.Join(args, " "), "push") {
return refusal, fmt.Errorf("exit status 1")
}
return aMeshThatAgrees(nil)(name, args)
}}
_, err := InstallRegistry(context.Background(),
installing(t, catalogueWith(t, RegistryModule, upstreamRegistryManifest)),
Deps{Run: runtime.run}, controlPlane{container: "temp-mesh-controller", run: runtime.run,
timeout: time.Second}, func(string) {})
if err == nil {
t.Fatal("a push the mesh refused was reported as successful")
}
if !strings.Contains(err.Error(), refusal) {
t.Errorf("what the mesh said is not in the failure:\n%v", err)
}
if !strings.Contains(err.Error(), "run this installer again") {
t.Errorf("the failure does not say a re-run continues from here:\n%v", err)
}
}