feat: master/agent phase 4 — registry polling and version history (#9) (#23)
Docker Build / docker (push) Successful in 47s

This commit was merged in pull request #23.
This commit is contained in:
2026-10-13 07:02:34 +00:00
parent 41a619b316
commit 1664e47183
46 changed files with 3357 additions and 130 deletions
+72 -5
View File
@@ -11,6 +11,7 @@ import (
"net"
"net/http"
"net/http/httptest"
"regexp"
"sort"
"strings"
"sync"
@@ -31,6 +32,9 @@ import (
"github.com/shcizo/package-updater/internal/protocol"
)
// digestPattern is the digest format the real store records.
var digestPattern = regexp.MustCompile(`^sha256:[0-9a-f]{64}$`)
type memStore struct {
mu sync.Mutex
agents map[string]model.Agent
@@ -44,6 +48,63 @@ type memStore struct {
jobs map[int64]*model.Job
nextJob int64
finishApplied int // FinishJob calls that returned true
versions map[int64]model.ImageVersion
}
// seedVersion adds an image_versions row that GetImageVersion returns.
func (m *memStore) seedVersion(v model.ImageVersion) {
m.mu.Lock()
defer m.mu.Unlock()
if m.versions == nil {
m.versions = map[int64]model.ImageVersion{}
}
m.versions[v.ID] = v
}
func (m *memStore) GetImageVersion(_ context.Context, id int64) (model.ImageVersion, error) {
m.mu.Lock()
defer m.mu.Unlock()
v, ok := m.versions[id]
if !ok {
return model.ImageVersion{}, model.ErrNotFound
}
return v, nil
}
func (m *memStore) ListServices(_ context.Context) ([]model.Service, error) {
m.mu.Lock()
defer m.mu.Unlock()
var out []model.Service
for _, svc := range m.svcRows {
if svc.RemovedAt == nil {
out = append(out, svc)
}
}
sort.Slice(out, func(i, j int) bool { return out[i].ID < out[j].ID })
return out, nil
}
func (m *memStore) SetPollError(_ context.Context, ids []int64, msg string) error {
m.mu.Lock()
defer m.mu.Unlock()
for _, id := range ids {
svc := m.svcRows[id]
svc.LastPollError = msg
m.svcRows[id] = svc
}
return nil
}
func (m *memStore) SetLastTagDigest(_ context.Context, id int64, digest string) error {
m.mu.Lock()
defer m.mu.Unlock()
svc, ok := m.svcRows[id]
if !ok {
return model.ErrNotFound
}
svc.LastTagDigest = digest
m.svcRows[id] = svc
return nil
}
// seedService adds a service row that jobs can be triggered for.
@@ -88,7 +149,7 @@ func (m *memStore) SetAvailable(_ context.Context, id int64, a model.Available)
if !ok {
return model.ErrNotFound
}
svc.AvailableRef, svc.AvailableSource, svc.AvailableAt = a.Ref, a.Source, &a.At
svc.AvailableRef, svc.AvailableDigest, svc.AvailableSource, svc.AvailableAt = a.Ref, a.Digest, a.Source, &a.At
m.svcRows[id] = svc
return nil
}
@@ -184,10 +245,14 @@ func (m *memStore) FinishJob(_ context.Context, agentID, jobID int64, f model.Jo
if f.Status == model.JobSucceeded {
svc := m.svcRows[j.ServiceID]
svc.DesiredRef = f.Ref
if _, d, _ := strings.Cut(f.Ref, "@"); !strings.Contains(requestedRef, "@") && digestPattern.MatchString(d) {
svc.LastTagDigest = d
}
// Same rule as the SQL: the job was created for the suggested ref after it was reported.
requested, _, _ := strings.Cut(requestedRef, "@")
if svc.AvailableAt != nil && svc.AvailableRef == requested && !svc.AvailableAt.After(j.CreatedAt) {
svc.AvailableRef, svc.AvailableSource, svc.AvailableAt = "", "", nil
requested, digest, _ := strings.Cut(requestedRef, "@")
if svc.AvailableAt != nil && svc.AvailableRef == requested && !svc.AvailableAt.After(j.CreatedAt) &&
(digest == "" || svc.AvailableDigest == digest) {
svc.AvailableRef, svc.AvailableDigest, svc.AvailableSource, svc.AvailableAt = "", "", "", nil
}
m.svcRows[j.ServiceID] = svc
}
@@ -282,7 +347,9 @@ type currentHub struct{ p atomic.Pointer[hub.Hub] }
func (c *currentHub) ServeHTTP(w http.ResponseWriter, r *http.Request) { c.p.Load().ServeHTTP(w, r) }
func (c *currentHub) Disconnect(id int64) { c.p.Load().Disconnect(id) }
func (c *currentHub) Route(svc model.Service) (model.Route, error) { return c.p.Load().Route(svc) }
func (c *currentHub) Route(svc model.Service, minProtocol int) (model.Route, error) {
return c.p.Load().Route(svc, minProtocol)
}
func (c *currentHub) StartJob(r model.Route, id int64, s protocol.JobStart) error {
return c.p.Load().StartJob(r, id, s)
}
+11 -5
View File
@@ -32,6 +32,9 @@ const (
lostMessage = "lost: the agent did not know this job when it reconnected"
)
// e2eDigest is the digest the fake executor pins a tag to.
const e2eDigest = "sha256:" + "e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0e2e0"
// gateExecutor writes a line of output, then blocks until release is closed
// or the job is cancelled.
type gateExecutor struct {
@@ -52,7 +55,10 @@ func (g *gateExecutor) Execute(ctx context.Context, job protocol.JobStart, out i
return "", ctx.Err()
}
_, _ = io.WriteString(out, "recreated\n")
return job.Ref + "@sha256:e2e", nil
if strings.Contains(job.Ref, "@") {
return job.Ref, nil
}
return job.Ref + "@" + e2eDigest, nil
}
// jobAgent is a connected agent with a real runner and its two lifetimes: the
@@ -119,7 +125,7 @@ func (e *jobEnv) waitRoutable(t *testing.T) {
t.Helper()
svc, err := e.store.GetService(context.Background(), 1)
require.NoError(t, err)
require.Eventually(t, func() bool { _, err := e.m.hub.Route(svc); return err == nil }, waitFor, pollEvery)
require.Eventually(t, func() bool { _, err := e.m.hub.Route(svc, protocol.MinJobVersion); return err == nil }, waitFor, pollEvery)
}
func (e *jobEnv) job(t *testing.T, id int64) model.Job {
@@ -159,12 +165,12 @@ func TestManualJobFlowsToAgentAndBack(t *testing.T) {
j := e.trigger(t)
done := e.waitStatus(t, j.ID, model.JobSucceeded)
assert.Equal(t, slusk+":1.4.2@sha256:e2e", done.ToRef)
assert.Equal(t, slusk+":1.4.2@"+e2eDigest, done.ToRef)
assert.Contains(t, done.Output, "pulling "+slusk+":1.4.2")
assert.Contains(t, done.Output, "recreated")
svc, err := e.store.GetService(context.Background(), 1)
require.NoError(t, err)
assert.Equal(t, slusk+":1.4.2@sha256:e2e", svc.DesiredRef)
assert.Equal(t, slusk+":1.4.2@"+e2eDigest, svc.DesiredRef)
require.Eventually(t, func() bool { return len(e.agent.runner.Known()) == 0 }, waitFor, pollEvery, "the result must be acked")
}
@@ -240,7 +246,7 @@ func TestPhaseOneAgentGetsNoJobs(t *testing.T) {
require.NoError(t, wsjson.Write(ctx, c, snap))
require.Eventually(t, func() bool {
_, err := m.hub.Route(svcRow)
_, err := m.hub.Route(svcRow, protocol.MinJobVersion)
return errors.Is(err, model.ErrAgentTooOld)
}, waitFor, pollEvery)
+133
View File
@@ -0,0 +1,133 @@
package e2e
import (
"context"
"io"
"log/slog"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/shcizo/package-updater/internal/master/jobs"
"github.com/shcizo/package-updater/internal/master/model"
"github.com/shcizo/package-updater/internal/master/poller"
"github.com/shcizo/package-updater/internal/protocol"
)
// jobCount is the number of jobs created so far.
func (m *memStore) jobCount() int {
m.mu.Lock()
defer m.mu.Unlock()
return len(m.jobs)
}
// fixedRegistry answers every lookup from a fixed table.
type fixedRegistry struct {
digests map[string]string
calls int
}
func (f *fixedRegistry) Digest(_ context.Context, ref string) (string, error) {
f.calls++
return f.digests[ref], nil
}
func TestPickPinnedVersion(t *testing.T) {
env := newJobEnv(t)
env.store.seedVersion(model.ImageVersion{ID: 5, Repo: slusk, Tag: "1.3.0", Digest: "sha256:old130", Source: model.SourceRunning})
job, err := env.jobs.TriggerVersion(context.Background(), 1, 5, "alice")
require.NoError(t, err)
assert.Equal(t, slusk+":1.3.0@sha256:old130", job.ToRef)
select {
case ref := <-env.exec.started:
assert.Equal(t, slusk+":1.3.0@sha256:old130", ref, "the agent receives exactly the picked version")
case <-time.After(waitFor):
t.Fatal("the agent never received the job")
}
close(env.exec.release)
done := env.waitStatus(t, job.ID, model.JobSucceeded)
assert.Equal(t, model.TriggerManual, done.Trigger)
assert.Equal(t, "alice", done.RequestedBy)
}
func TestPickVersionOfAnotherRepoIsRefused(t *testing.T) {
env := newJobEnv(t)
env.store.seedVersion(model.ImageVersion{ID: 6, Repo: "evil/other", Tag: "1", Digest: "sha256:x", Source: model.SourcePoll})
_, err := env.jobs.TriggerVersion(context.Background(), 1, 6, "alice")
assert.ErrorIs(t, err, model.ErrNotFound)
assert.Zero(t, env.store.jobCount(), "no job was created")
}
func TestPollStartsAutoJob(t *testing.T) {
env := newJobEnv(t)
env.store.seedService(model.Service{ID: 1, Kind: protocol.KindCompose, ComposeProject: "slusk", ComposeService: "web",
AgentID: ptr(agentID), ImageRepo: slusk, ActualRef: slusk + ":1.4.2@sha256:old", ActualDigest: "sha256:old",
UpdateMode: model.ModeAuto})
reg := &fixedRegistry{digests: map[string]string{slusk + ":1.4.2": "sha256:new"}}
p := poller.New(env.store, env.jobs, reg, env.m.broker, poller.Config{Workers: 1}, slog.New(slog.NewTextHandler(io.Discard, nil)))
p.Cycle(context.Background())
select {
case ref := <-env.exec.started:
assert.Equal(t, slusk+":1.4.2", ref, "the agent gets repo:tag and resolves the digest itself")
case <-time.After(waitFor):
t.Fatal("the agent never received the job")
}
require.Equal(t, 1, env.store.jobCount())
job := env.job(t, 1)
assert.Equal(t, model.TriggerPoll, job.Trigger)
assert.Equal(t, slusk+":1.4.2", job.ToRef)
svc, err := env.store.GetService(context.Background(), 1)
require.NoError(t, err)
assert.Equal(t, slusk+":1.4.2", svc.AvailableRef)
assert.Equal(t, "sha256:new", svc.AvailableDigest)
assert.Equal(t, model.SourcePoll, svc.AvailableSource)
assert.Equal(t, "sha256:new", svc.LastTagDigest)
p.Cycle(context.Background())
assert.Equal(t, 2, reg.calls, "the registry is asked again")
assert.Equal(t, 1, env.store.jobCount(), "the same digest does not start another job")
close(env.exec.release)
env.waitStatus(t, job.ID, model.JobSucceeded)
}
// An update started by the webhook, then a rollback by hand: polling must not
// redo the update while the registry still shows the digest that was deployed.
func TestPollKeepsARollbackAfterAWebhookUpdate(t *testing.T) {
env := newJobEnv(t)
ctx := context.Background()
close(env.exec.release)
env.store.seedService(model.Service{ID: 1, Kind: protocol.KindCompose, ComposeProject: "slusk", ComposeService: "web",
AgentID: ptr(agentID), ImageRepo: slusk, ActualRef: slusk + ":main@sha256:old", ActualDigest: "sha256:old",
UpdateMode: model.ModeAuto})
env.store.seedVersion(model.ImageVersion{ID: 5, Repo: slusk, Tag: "main", Digest: "sha256:old", Source: model.SourceRunning})
svc, err := env.store.GetService(ctx, 1)
require.NoError(t, err)
hook, err := env.jobs.Start(ctx, svc, jobs.StartRequest{Trigger: model.TriggerWebhook, Ref: slusk + ":main"})
require.NoError(t, err)
env.waitStatus(t, hook.ID, model.JobSucceeded)
svc, err = env.store.GetService(ctx, 1)
require.NoError(t, err)
assert.Equal(t, e2eDigest, svc.LastTagDigest, "the deployed digest of the tag is remembered")
pick, err := env.jobs.TriggerVersion(ctx, 1, 5, "alice")
require.NoError(t, err)
env.waitStatus(t, pick.ID, model.JobSucceeded)
jobsBefore := env.store.jobCount()
reg := &fixedRegistry{digests: map[string]string{slusk + ":main": e2eDigest}}
p := poller.New(env.store, env.jobs, reg, env.m.broker, poller.Config{Workers: 1}, slog.New(slog.NewTextHandler(io.Discard, nil)))
p.Cycle(ctx)
assert.Equal(t, 1, reg.calls)
assert.Equal(t, jobsBefore, env.store.jobCount(), "the rollback stays")
}
+3 -2
View File
@@ -16,6 +16,7 @@ import (
"github.com/shcizo/package-updater/internal/master/model"
"github.com/shcizo/package-updater/internal/master/webhook"
"github.com/shcizo/package-updater/internal/protocol"
)
// webhookServer mounts the webhook handler on a test server, wired to the
@@ -98,7 +99,7 @@ func TestWebhookWaitsForAutoJob(t *testing.T) {
job := e.job(t, r.body.Results[0].JobID)
assert.Equal(t, model.TriggerWebhook, job.Trigger)
assert.Equal(t, model.JobSucceeded, job.Status)
assert.Equal(t, slusk+":2.0.0@sha256:e2e", job.ToRef)
assert.Equal(t, slusk+":2.0.0@"+e2eDigest, job.ToRef)
svc, err := e.store.GetService(context.Background(), 1)
require.NoError(t, err)
assert.Empty(t, svc.AvailableRef, "the job deployed the suggestion, so it is cleared")
@@ -111,7 +112,7 @@ func TestWebhookFailedAutoJobIs500(t *testing.T) {
e.agent.stopConn() // no agent connection: the job fails at once with "agent offline"
require.Eventually(t, func() bool {
svc, _ := e.store.GetService(context.Background(), 1)
_, err := e.m.hub.Route(svc)
_, err := e.m.hub.Route(svc, protocol.MinJobVersion)
return err != nil
}, waitFor, pollEvery)