Merge pull request 'A no-move tier waits for no new report, so its walk asks the next tier (issue 648)' (#309) from fix/648-a-no-move-tier-waits-for-nothing into main

cmd/mesh-controller/issue648_test.go

@@ -0,0 +1,87 @@
+package main
+
+import (
+	"encoding/json"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/novox/mesh-controller/internal/catalogue"
+	"github.com/novox/mesh-controller/internal/inventory"
+)
+
+// A tier whose module is no move — made from the source every machine running it runs, so nothing is
+// sent — is not waited on for a report after its marking (novox/hq issue 648). Its machines answered the
+// send that last carried that build before the walk got there, and nothing will make them report again:
+// the walk asks the next tier in the same step, rather than "waiting for app on anchor, laptop" for ever.
+func TestANoMoveTierWaitsForNoNewReport(t *testing.T) {
+	judgeLeavesAsTheCore(t)
+	g := aGateMesh(t)
+	ctx := t.Context()
+	inv := g.open.inventory
+
+	// app is the build machine, so a module of the next tier is built by it: the tier gates the next on app
+	// running on its machines.
+	for _, m := range []catalogue.Manifest{
+		{Module: "app", Version: "c2", Claims: []catalogue.Claim{{Name: "node-build-agent", Scope: catalogue.ScopeNode}}},
+		{Module: "web", Version: "w1"},
+	} {
+		if err := inv.RegisterModule(ctx, m, inventory.Source{Repository: "novox/mesh-catalog", Seat: "git",
+			Path: "modules/" + m.Module, BuiltFrom: m.Version, Head: m.Version, Asked: time.Now().Add(-time.Minute)}); err != nil {
+			t.Fatal(err)
+		}
+	}
+	// What anchor and laptop were last sent (c1) was made from the source the plan's build of c2 is.
+	for _, b := range []inventory.Build{
+		{ID: "build-1s", Module: "app", Commit: "c1", SourceFingerprint: "src1:app",
+			Asked: time.Now().Add(-30 * time.Second), At: time.Now().Add(-30 * time.Second)},
+		{ID: "build-2s", Module: "app", Commit: "c2", SourceFingerprint: "src1:app", Asked: time.Now(), At: time.Now()},
+	} {
+		b.Manifest, _ = json.Marshal(catalogue.Manifest{Module: "app", Version: "1"})
+		if err := inv.RecordBuild(ctx, b); err != nil {
+			t.Fatal(err)
+		}
+	}
+	// Each machine answered that send, applied, before the walk's tier was built.
+	for _, n := range []string{"anchor", "laptop"} {
+		if _, err := inv.RecordDoing(ctx, nodeID(t, g.open, n), inventory.Doing{Node: n,
+			Outcome: inventory.OutcomeApplied, Declared: "d-" + n + "-c1", Applied: 1,
+			At: time.Now().Add(-10 * time.Second)}); err != nil {
+			t.Fatal(err)
+		}
+	}
+	built := time.Now().UTC()
+	p := g.plan(t)
+	p.Tiers = [][]string{{"app"}, {"web"}}
+	p.Modules["app"].Build, p.Modules["app"].BuiltAt = "build-2s", &built
+	if err := inv.SavePlan(ctx, &p); err != nil {
+		t.Fatal(err)
+	}
+
+	advancePlans(ctx, g.open)
+
+	if len(g.sent) != 0 {
+		t.Fatalf("a no-move build was sent: %v", g.sent)
+	}
+	p = g.plan(t)
+	if s := p.Modules["app"]; s == nil || !strings.HasPrefix(s.Why, "no move") {
+		t.Fatalf("the build was not marked no move: %+v", s)
+	}
+	if p.Tier < 1 || strings.Contains(p.Note, "waiting for app") {
+		t.Fatalf("the walk waits on a no-move tier for a report nothing will cause: tier %d, %s %q", p.Tier, p.State, p.Note)
+	}
+
+	// A machine that has not answered its last send is still waited on: no move is not "never sent".
+	p.Tier, p.State, p.Note = 0, inventory.PlanRolling, ""
+	if err := inv.RecordSent(ctx, nodeID(t, g.open, "laptop"), "d-laptop-later", map[string]string{"app": "c1"}); err != nil {
+		t.Fatal(err)
+	}
+	if err := inv.SavePlan(ctx, &p); err != nil {
+		t.Fatal(err)
+	}
+	advancePlans(ctx, g.open)
+	p = g.plan(t)
+	if p.Tier != 0 || !strings.Contains(p.Note, "waiting for app on laptop") {
+		t.Fatalf("a machine that has not answered its last send was not waited on: tier %d, %q", p.Tier, p.Note)
+	}
+}

cmd/mesh-controller/release_plan.go

@@ -251,6 +251,20 @@ func gates(p inventory.Plan, edges []inventory.Edge, rollsOut func(string) bool)
 	return out
 }
 
+// noMoveWhy is what a plan says of a module of its tier whose build was made from the source every machine
+// running it runs (novox/hq issue 280): nothing is sent for it.
+// noMovePrefix opens it, and is what noMove reads: one prefix for the writer and the reader.
+const (
+	noMovePrefix = "no move"
+	noMoveWhy    = noMovePrefix + ": made from the source every machine running it runs"
+)
+
+// noMove is whether the plan marked the module no move and sent it nothing. Read from what the plan says,
+// so a plan kept before the mark had a name of its own is read the same (novox/hq issue 648).
+func noMove(s *inventory.PlanModule) bool {
+	return s != nil && s.FirstAt == nil && s.Gate == nil && strings.HasPrefix(s.Why, noMovePrefix)
+}
+
 // applied says whether every machine running the module has reported since the module was built.
 // appliedEach is applied with a moment of its own for each machine: the reports that count are the ones
 // after that machine was sent the build (novox/hq issue 256).
@@ -805,7 +819,7 @@ func advanceOnce(ctx context.Context, open *stores, p *inventory.Plan,
 			} else if same {
 				now := time.Now().UTC()
 				state.SentAt = &now
-				state.Why = "no move: made from the source every machine running it runs"
+				state.Why = noMoveWhy
 				fmt.Printf("%s: %s built from the source every machine running it runs: no move, nothing sent\n", p.ID, m)
 				continue
 			}
@@ -995,6 +1009,25 @@ func advanceOnce(ctx context.Context, open *stores, p *inventory.Plan,
 			if state.BuiltAt != nil {
 				since = *state.BuiltAt
 			}
+			// **A build that is no move is waited on by the send that last carried it** (novox/hq issue 648).
+			// Nothing was sent for it, so no report follows its marking or its build: a machine that does not
+			// happen to report again held the walk for ever. Each machine runs it once it answered its last
+			// send — the one whose builds made it no move — whenever that was.
+			if noMove(state) {
+				byNode := map[string]inventory.Reported{}
+				for _, r := range reports {
+					byNode[r.Node] = r
+				}
+				if ok, on := appliedEach(m, func(node string) time.Time {
+					if s := byNode[node].Sent; s != nil {
+						return *s
+					}
+					return time.Time{}
+				}, running, reports); !ok {
+					waiting = append(waiting, fmt.Sprintf("%s on %s", m, strings.Join(on, ", ")))
+				}
+				continue
+			}
 			// **Each machine from its own send** (novox/hq issue 256). With one machine first (ADR 0218)
 			// a module is sent twice — the first machine, then the rest — and SentAt is the second.
 			// Asked of every machine, the first machine's report, made between the two sends, read as

testdata/store-tests

@@ -69,3 +69,4 @@
 ./cmd/mesh-controller TestAFirstMachineThatFailsStillStopsTheWalk
 ./cmd/mesh-controller TestTheControlNodeIsSentLastInAStep
 ./cmd/mesh-controller TestARestMachineSilentPastItsBoundIsLeftAndSaid
+./cmd/mesh-controller TestANoMoveTierWaitsForNoNewReport