Files
mesh-controller/cmd/mesh-controller/untaken_test.go
T
jschoubben bfd983e3f8 A held module is in status, and it stops the mesh reading as well
novox/hq 04-ISSUES/125. A module assigned to a machine and never taken
runs none of what it declares. Status had no vocabulary for it: the
machine was heard from, current, and doing what it was told, so the mesh
printed "all doing what they were told" — which was true, and was acted
on, and every public name on the machine went dark.

Status now names each module a machine is holding rather than running,
per machine and with a count, read from what the MACHINE reported rather
than from the mesh's take-time listing — the machine is the only thing
that knows what it found. The JSON form carries the same rows, absent
rather than empty when nothing is held.

And a hold suppresses the all-well sentence, where being adopted does
not: adopted is a mode somebody chose, a module assigned and never taken
is a half-finished action with nothing left to finish it. The condition
is now a named function so the rule lives in one place and a test binds
to the real thing rather than a copy of it.

untakenModules raises a read it cannot make rather than answering "holding
nothing" from a failed query, which is the shape this whole issue is.
2026-09-30 08:46:20 +02:00

123 lines
4.1 KiB
Go

package main
import (
"encoding/json"
"strings"
"testing"
"github.com/novox/mesh-controller/internal/inventory"
)
// A module assigned to an adopted machine and never taken runs none of what it declares, and every
// surface called that success — a push reporting sent, a journal reporting applied, status reporting
// a machine doing what it was told (novox/hq 04-ISSUES/125). The holds were only ever in the
// machine's own state file.
// heldOn makes a machine report that it is holding resources for a module, the way an adopted node
// does after an apply.
func heldOn(t *testing.T, open *stores, node, module string, ids ...string) {
t.Helper()
record, err := open.inventory.NodeByName(t.Context(), node)
if err != nil {
t.Fatal(err)
}
held := make([]inventory.Held, 0, len(ids))
for _, id := range ids {
held = append(held, inventory.Held{ID: id, Module: module, Kind: "container", Target: id})
}
if err := open.inventory.RecordAdoption(t.Context(), record.ID, held, "ufw", nil); err != nil {
t.Fatal(err)
}
}
func TestStatusNamesAModuleHeldBecauseNothingTookIt(t *testing.T) {
open := aMesh(t)
heldOn(t, open, "anchor", "route-proxy", "ca", "certs", "server")
asked, err := theThreeQuestions(t.Context(), open)
if err != nil {
t.Fatal(err)
}
if got := asked.untaken["anchor"]["route-proxy"]; got != 3 {
t.Fatalf("status counted %d resources held for route-proxy, wanted 3", got)
}
}
func TestAHeldModuleStopsTheMeshReadingAsWell(t *testing.T) {
// The whole of the fault. "all doing what they were told" was true throughout the outage, and
// true is not the same as safe to act on: the machine was doing what it was told, and what it
// was told had not started. Asserted against the production condition, not a copy of it.
quiet := answers{}
if !quiet.well() {
t.Fatal("a mesh with nothing to say does not read as well, so nothing below means anything")
}
holding := answers{untaken: map[string]map[string]int{"anchor": {"route-proxy": 3}}}
if holding.well() {
t.Fatal("a machine holding a module's resources still reads as doing what it was told, " +
"which is the sentence that cost every public name on the machine")
}
// And being adopted does not suppress it: that is a mode somebody chose, not work outstanding.
// Kept as an assertion so the difference between the two is deliberate rather than incidental.
if !quiet.well() {
t.Fatal("the well condition is not stable")
}
}
func TestAHeldModuleIsFoundFromWhatTheMachineReported(t *testing.T) {
// End to end through the store, so the condition above is reached by real data and not only by
// a constructed value: the machine reports, the mesh records, status asks.
open := aMesh(t)
heldOn(t, open, "anchor", "route-proxy", "ca", "server")
asked, err := theThreeQuestions(t.Context(), open)
if err != nil {
t.Fatal(err)
}
if len(asked.untaken) == 0 {
t.Fatal("what the machine reported holding did not reach status")
}
if asked.well() {
t.Fatal("a mesh whose machine reported holds reads as well")
}
}
func TestTheJSONStatusCarriesWhatIsHeldAndForWhichModule(t *testing.T) {
open := aMesh(t)
heldOn(t, open, "anchor", "route-proxy", "ca", "certs")
asked, err := theThreeQuestions(t.Context(), open)
if err != nil {
t.Fatal(err)
}
body, err := statusAsJSON(asked)
if err != nil {
t.Fatal(err)
}
var doc struct {
Untaken []struct {
Node string `json:"node"`
Module string `json:"module"`
Held int `json:"held"`
} `json:"untaken"`
}
if err := json.Unmarshal(body, &doc); err != nil {
t.Fatal(err)
}
if len(doc.Untaken) != 1 {
t.Fatalf("the document carries %d untaken rows, wanted 1: %s", len(doc.Untaken), body)
}
row := doc.Untaken[0]
if row.Node != "anchor" || row.Module != "route-proxy" || row.Held != 2 {
t.Fatalf("the row is %+v, wanted anchor/route-proxy/2", row)
}
// Absent rather than empty when nothing is held, so a well mesh's document does not carry a
// field a reader has to interpret.
clean, err := statusAsJSON(answers{})
if err != nil {
t.Fatal(err)
}
if strings.Contains(string(clean), "untaken") {
t.Fatalf("a mesh holding nothing still names untaken: %s", clean)
}
}