The controller no longer subscribes to the alive message: HostBeats, its handler, the heartbeat-gap duration and a fixed silent bound (issue 1183, AC3, AC4, AC5)

cmd/mesh-controller/last_heard_integration_test.go

@@ -0,0 +1,82 @@
+//go:build integration
+
+package main
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	sdkdelivery "git.novox.be/novox/mesh-sdk/go/delivery"
+	"github.com/nats-io/nats.go/jetstream"
+
+	"github.com/novox/mesh-controller/internal/broker"
+	"github.com/novox/mesh-controller/internal/inventory"
+	"github.com/novox/mesh-controller/internal/testbus"
+)
+
+// 1183/AC5: with the watchman's presence bucket holding a node online and no alive message ever sent, the node reads here
+// in `nodes` four minutes later by the controller's clock, however old its last report; and an alive message still sent
+// by a node-engine is published to the same bus without error and changes nothing.
+func TestAnOnlineNodeReadsHereWithNoAliveMessage(t *testing.T) { // 1183/AC5
+	js, err := broker.Dial(testbus.URL(t))
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(js.Close)
+	if _, err := broker.RaiseBuckets(js, []broker.Bucket{
+		{Module: sdkdelivery.WatchmanModule, Name: "presence", History: sdkdelivery.PresenceHistory},
+	}); err != nil {
+		t.Fatal(err)
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+	api, err := jetstream.New(js.Conn())
+	if err != nil {
+		t.Fatal(err)
+	}
+	kv, err := api.KeyValue(ctx, sdkdelivery.PresenceBucket)
+	if err != nil {
+		t.Fatal(err)
+	}
+	put := func(node string, online bool) {
+		t.Helper()
+		key, err := sdkdelivery.PresenceNodeKey(node)
+		if err != nil {
+			t.Fatal(err)
+		}
+		body, err := sdkdelivery.EncodePresence(sdkdelivery.Presence{Online: online})
+		if err != nil {
+			t.Fatal(err)
+		}
+		if _, err := kv.Put(ctx, key, body); err != nil {
+			t.Fatal(err)
+		}
+	}
+	put("ace", true)
+	put("laptop", false)
+	// A node-engine still sending its alive message: harmless.
+	if err := js.Conn().Publish("mesh.control.ace.alive", []byte(`{"node":"ace"}`)); err != nil {
+		t.Fatalf("an alive message could not be published: %v", err)
+	}
+	if err := js.Conn().Flush(); err != nil {
+		t.Fatal(err)
+	}
+
+	later := time.Now().Add(4 * time.Minute)
+	nodes := []inventory.Node{{Name: "ace", LastSeen: time.Now().Add(-time.Hour)},
+		{Name: "laptop", LastSeen: time.Now().Add(-time.Hour)}}
+	read := func(ctx context.Context, names []string) (map[string]presenceEntry, error) {
+		return readPresence(ctx, js.Conn(), names)
+	}
+	heard, err := nodesHeard(ctx, nodes, read, later)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if got := heardFromAt(heard[0], later); got != "here" {
+		t.Fatalf("a node online by presence reads %q four minutes later", got)
+	}
+	if got := heardFromAt(heard[1], later); got == "here" {
+		t.Fatalf("a node offline by presence reads %q", got)
+	}
+}