Files
mesh-controller/cmd/mesh-controller/mesh_for_test.go
T
jochen bb1607e424 Say when the mesh is wrong: conditions, watchdogs, the bus's advisories, doctor (hq to-be 45 Phase 1)
Every one of the 48 core failures of research 031 was found by a person
looking; the mesh's answers carried the fact for whoever asked and told
nobody.

- The condition store (to-be 45 §2): mesh-controller_conditions, one key
  per open condition, written by compare-and-set so a person's silence
  and the watchdogs never lose each other's word; every transition kept
  ninety days in mesh-controller_condition-history and said as the
  seat's events condition-raised / condition-changed / condition-cleared
  (the condition at the top level, with event, at, change, why, show),
  offered again while the bus is away. Raised and cleared by observation
  only; a clearing reopened within ten minutes is the same condition with
  its count up, its silence kept. Verbs: conditions, conditions show,
  conditions silence (a hand act, at most a week), conditions history.
- ADR 0224's provider standing is the first kind, provider-failing, held
  by the provider's events; the provider_standing table is no longer read
  or written (left in place: dropping it is the operator's word).
- status leads with the open conditions, urgent first, and says all well
  only with none open; conditions it cannot read are said and not well.
- The signals table compiled in, one watchdog loop over it every 30s: S1
  heartbeat (3 intervals, asleep machines excepted, control node urgent
  after 30 min), S2 report after a send, S3 plan tier, S4 event loop deaf,
  S5 merge not acted, S6 ask lost, S7 call hung, S8 provider silent, S9
  advisories, S10 self-check silent, S11 node tools silent, S13 stale
  refusals; S12, S14, S15 deferred with their reasons. A row that cannot
  see raises probe-failed and clears nothing. A test generated from the
  table suppresses each signal inside and past its bound.
- The bus's advisories (maximum deliveries, a mesh consumer deleted) and
  the controller's own slow consumer and refused subjects, said in the
  mesh's words.
- doctor: the probe registry D1-D10 (D5 deferred) and DW, every five
  minutes, each in thirty seconds; a probe that cannot run is never a
  pass. D1 validates with mesh-host's own validator. Every run ends with
  the doctor-heartbeat event mesh-watcher listens for.
- The controller is granted its new buckets, events, the two advisories
  and $SRV.INFO; the node tools their tools-alive heartbeat. The streams
  and consumers the controller asserts and the ones D6/D7 expect are one
  derivation.
2026-10-06 10:21:11 +02:00

129 lines
4.4 KiB
Go

package main
import (
"context"
"crypto/ecdh"
"crypto/rand"
"encoding/base64"
"encoding/json"
"fmt"
"github.com/novox/mesh-controller/internal/conditions"
"testing"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/licences"
"github.com/novox/mesh-controller/internal/overlay"
)
// A mesh a command can be run against.
//
// The commands here were tested through the pieces they call and never through themselves, so
// three faults that only exist where the pieces meet — an assignment reported as fine while it
// blocked other machines, a read-shaped invocation that wrote, a JSON interface that stopped
// emitting JSON — were invisible to every test in this package. This raises the real stores and
// calls the real functions.
// aMesh is two placed, capable machines on a private network, with nothing assigned but the
// network itself.
//
// `anchor` is the hub. That is not decoration: a mesh whose hub cannot be resolved has no private
// network at all, which is how one machine's problem reaches every other.
func aMesh(t *testing.T) *stores {
t.Helper()
inventory.ForTest(t) // raises the store, migrates it, and points the environment at it
licences.ForTest(t) // planning reaches this one too, by name and never by connection
open, err := openStores(t.Context())
if err != nil {
t.Fatal(err)
}
t.Cleanup(open.Close)
// A condition store of its own, held in memory (novox/hq to-be 45 §2): status leads with what is
// open, and a mesh with no bus would otherwise read as one whose conditions cannot be read.
withConditionsInMemory(t)
for _, m := range provided {
if err := open.inventory.Provide(t.Context(), m); err != nil {
t.Fatal(err)
}
}
for i, name := range []string{"anchor", "laptop"} {
record, err := open.inventory.AddNode(t.Context(), name)
if err != nil {
t.Fatal(err)
}
if err := open.inventory.SetPlace(t.Context(), name, name+".example:51820", "here",
name == "anchor", fmt.Sprintf("10.77.0.%d", i+1)); err != nil {
t.Fatal(err)
}
reported, err := json.Marshal(map[string]any{"capabilities": []map[string]any{
{"name": "container-runtime", "present": true},
{"name": "wireguard", "present": true},
{"name": "systemd", "present": true},
}})
if err != nil {
t.Fatal(err)
}
var profile map[string]any
if err := json.Unmarshal(reported, &profile); err != nil {
t.Fatal(err)
}
if err := open.inventory.RecordProfile(t.Context(), record.ID, profile); err != nil {
t.Fatal(err)
}
if err := open.inventory.RecordSealingKey(t.Context(), record.ID, aPublicKey(t)); err != nil {
t.Fatal(err)
}
if err := open.inventory.RecordOverlayKey(t.Context(), record.ID, aPublicKey(t)); err != nil {
t.Fatal(err)
}
if _, err := open.inventory.Assign(t.Context(), name, overlay.Name); err != nil {
t.Fatal(err)
}
}
return open
}
// aPublicKey is a key a machine could have reported. Its private half is thrown away: nothing here
// opens anything, it only needs the mesh to believe a machine has a key.
func aPublicKey(t *testing.T) string {
t.Helper()
k, err := ecdh.X25519().GenerateKey(rand.Reader)
if err != nil {
t.Fatal(err)
}
return base64.StdEncoding.EncodeToString(k.PublicKey().Bytes())
}
// register puts a manifest in the catalogue.
func register(t *testing.T, open *stores, m catalogue.Manifest) {
t.Helper()
if err := open.inventory.RegisterModule(t.Context(), m, inventory.Source{}); err != nil {
t.Fatal(err)
}
}
// rivals are two modules that cannot share a machine, which is the shortest way to make a node's
// own set of assignments incoherent using nothing but commands a person has.
func rivals() (catalogue.Manifest, catalogue.Manifest) {
claim := []catalogue.Claim{{Name: "the-seat", Scope: catalogue.ScopeNode}}
return catalogue.Manifest{Module: "rival-one", Version: "1", Claims: claim},
catalogue.Manifest{Module: "rival-two", Version: "1", Claims: claim}
}
// withConditionsInMemory gives the test a condition store in memory, as the serving controller's.
func withConditionsInMemory(t *testing.T) (*conditions.Keeper, *conditions.InMemory) {
t.Helper()
store := conditions.NewInMemory()
k := conditions.NewKeeper(t.Context(), conditions.Options{Store: store, History: store})
before := conditionsFrom
conditionsFrom = k
t.Cleanup(func() {
conditionsFrom = before
k.Close(context.Background())
})
return k, store
}