feat: self-update of master and agents (#15) (#32)

internal/master/poller/poller.go

@@ -7,6 +7,7 @@ import (
 	"context"
 	"errors"
 	"log/slog"
+	"slices"
 	"strings"
 	"sync"
 	"time"
@@ -209,14 +210,29 @@ func (p *Poller) record(ctx context.Context, l lookup, svcs []model.Service, sta
 	}
 	stats.ok++
 	p.setPollError(ctx, svcs, "", stats, func(s model.Service) bool { return s.LastPollError != "" })
+	var auto []model.Service
 	for _, svc := range svcs {
 		if !p.suggest(ctx, svc, l, stats) {
 			continue
 		}
 		if autoWanted(svc, l.ref, l.digest) {
-			p.startAuto(ctx, svc.ID, l.ref, l.digest, stats)
+			auto = append(auto, svc)
 		}
 	}
+	// An agent's own service goes last: jobs that reach an agent while it
+	// replaces itself are lost, and messages to one agent arrive in order.
+	slices.SortStableFunc(auto, func(a, b model.Service) int { return selfRank(a) - selfRank(b) })
+	for _, svc := range auto {
+		p.startAuto(ctx, svc.ID, l.ref, l.digest, stats)
+	}
+}
+
+// selfRank sorts an agent's own service after all others.
+func selfRank(svc model.Service) int {
+	if svc.Self {
+		return 1
+	}
+	return 0
 }
 
 // suggest marks l.digest as the available version of svc unless the service

internal/master/poller/poller_test.go

@@ -297,6 +297,24 @@ func TestNewDigest(t *testing.T) {
 	}
 }
 
+func TestAgentsOwnServiceIsStartedLast(t *testing.T) {
+	ref := repoA + ":1.4"
+	own := svc(1, ref+"@sha256:old")
+	own.UpdateMode, own.Self = model.ModeAuto, true
+	other := svc(2, ref+"@sha256:old")
+	other.UpdateMode = model.ModeAuto
+	st := &fakeStore{services: []model.Service{own, other}}
+	reg := &fakeRegistry{digests: map[string]string{ref: "sha256:new"}}
+	j := &fakeJobs{}
+	p, _ := newPoller(st, j, reg, Config{})
+
+	p.Cycle(context.Background())
+
+	require.Len(t, j.starts, 2)
+	assert.Equal(t, int64(2), j.starts[0].svcID)
+	assert.Equal(t, int64(1), j.starts[1].svcID)
+}
+
 func TestSameSuggestionIsIdempotent(t *testing.T) {
 	ref := repoA + ":1.4"
 	running := svc(1, ref+"@sha256:old")
@@ -332,7 +350,7 @@ func TestStartErrorsDoNotAbortCycle(t *testing.T) {
 	reg := &fakeRegistry{digests: map[string]string{ref: "sha256:new"}}
 	j := &fakeJobs{errFor: map[int64]error{
 		1: model.ErrJobActive,
-		2: &model.NotUpdatableError{Reason: model.ReasonSelf},
+		2: &model.NotUpdatableError{Reason: model.ReasonContainer},
 		3: errors.New("database down"),
 	}}
 	p, _ := newPoller(st, j, reg, Config{})