Files
dnswatcher/internal/watcher/watcher_test.go
user 461ab7e06c
All checks were successful
check / check (push) Successful in 46s
fix: enforce DNS-first ordering for port and TLS checks
DNS checks now always complete before port or TLS checks begin,
ensuring those checks use freshly resolved IP addresses instead of
potentially stale ones from a previous cycle.

Changes:
- Extract runDNSChecks() from runDNSAndPortChecks() so DNS resolution
  can be invoked independently
- Run DNS before TLS on the TLS ticker (previously TLS ran alone with
  whatever IPs were in state from the last DNS cycle, up to 12h stale)
- RunOnce uses explicit 3-phase ordering: DNS → ports → TLS
- Add TestDNSRunsBeforePortAndTLSChecks to verify fresh IPs propagate
- Update README monitoring lifecycle to document DNS-first ordering

closes #58
2026-03-01 15:03:02 -08:00

794 lines
17 KiB
Go

package watcher_test
import (
"context"
"errors"
"fmt"
"sync"
"testing"
"time"
"sneak.berlin/go/dnswatcher/internal/config"
"sneak.berlin/go/dnswatcher/internal/portcheck"
"sneak.berlin/go/dnswatcher/internal/state"
"sneak.berlin/go/dnswatcher/internal/tlscheck"
"sneak.berlin/go/dnswatcher/internal/watcher"
)
// errNotFound is returned when mock data is missing.
var errNotFound = errors.New("not found")
// --- Mock implementations ---
type mockResolver struct {
mu sync.Mutex
nsRecords map[string][]string
allRecords map[string]map[string]map[string][]string
ipAddresses map[string][]string
lookupNSErr error
allRecordsErr error
resolveIPErr error
lookupNSCalls int
allRecordCalls int
}
func (m *mockResolver) LookupNS(
_ context.Context,
domain string,
) ([]string, error) {
m.mu.Lock()
defer m.mu.Unlock()
m.lookupNSCalls++
if m.lookupNSErr != nil {
return nil, m.lookupNSErr
}
ns, ok := m.nsRecords[domain]
if !ok {
return nil, fmt.Errorf(
"%w: NS for %s", errNotFound, domain,
)
}
return ns, nil
}
func (m *mockResolver) LookupAllRecords(
_ context.Context,
hostname string,
) (map[string]map[string][]string, error) {
m.mu.Lock()
defer m.mu.Unlock()
m.allRecordCalls++
if m.allRecordsErr != nil {
return nil, m.allRecordsErr
}
recs, ok := m.allRecords[hostname]
if !ok {
return nil, fmt.Errorf(
"%w: records for %s", errNotFound, hostname,
)
}
return recs, nil
}
func (m *mockResolver) ResolveIPAddresses(
_ context.Context,
hostname string,
) ([]string, error) {
m.mu.Lock()
defer m.mu.Unlock()
if m.resolveIPErr != nil {
return nil, m.resolveIPErr
}
ips, ok := m.ipAddresses[hostname]
if !ok {
return nil, fmt.Errorf(
"%w: IPs for %s", errNotFound, hostname,
)
}
return ips, nil
}
type mockPortChecker struct {
mu sync.Mutex
results map[string]bool
err error
calls int
}
func (m *mockPortChecker) CheckPort(
_ context.Context,
address string,
port int,
) (*portcheck.PortResult, error) {
m.mu.Lock()
defer m.mu.Unlock()
m.calls++
if m.err != nil {
return nil, m.err
}
key := fmt.Sprintf("%s:%d", address, port)
open := m.results[key]
return &portcheck.PortResult{Open: open}, nil
}
type mockTLSChecker struct {
mu sync.Mutex
certs map[string]*tlscheck.CertificateInfo
err error
calls int
}
func (m *mockTLSChecker) CheckCertificate(
_ context.Context,
ip string,
hostname string,
) (*tlscheck.CertificateInfo, error) {
m.mu.Lock()
defer m.mu.Unlock()
m.calls++
if m.err != nil {
return nil, m.err
}
key := fmt.Sprintf("%s:%s", ip, hostname)
cert, ok := m.certs[key]
if !ok {
return nil, fmt.Errorf(
"%w: cert for %s", errNotFound, key,
)
}
return cert, nil
}
type notification struct {
Title string
Message string
Priority string
}
type mockNotifier struct {
mu sync.Mutex
notifications []notification
}
func (m *mockNotifier) SendNotification(
_ context.Context,
title, message, priority string,
) {
m.mu.Lock()
defer m.mu.Unlock()
m.notifications = append(m.notifications, notification{
Title: title,
Message: message,
Priority: priority,
})
}
func (m *mockNotifier) getNotifications() []notification {
m.mu.Lock()
defer m.mu.Unlock()
result := make([]notification, len(m.notifications))
copy(result, m.notifications)
return result
}
// --- Helper to build a Watcher for testing ---
type testDeps struct {
resolver *mockResolver
portChecker *mockPortChecker
tlsChecker *mockTLSChecker
notifier *mockNotifier
state *state.State
config *config.Config
}
func newTestWatcher(
t *testing.T,
cfg *config.Config,
) (*watcher.Watcher, *testDeps) {
t.Helper()
deps := &testDeps{
resolver: &mockResolver{
nsRecords: make(map[string][]string),
allRecords: make(map[string]map[string]map[string][]string),
ipAddresses: make(map[string][]string),
},
portChecker: &mockPortChecker{
results: make(map[string]bool),
},
tlsChecker: &mockTLSChecker{
certs: make(map[string]*tlscheck.CertificateInfo),
},
notifier: &mockNotifier{},
config: cfg,
}
deps.state = state.NewForTest()
w := watcher.NewForTest(
deps.config,
deps.state,
deps.resolver,
deps.portChecker,
deps.tlsChecker,
deps.notifier,
)
return w, deps
}
func defaultTestConfig(t *testing.T) *config.Config {
t.Helper()
return &config.Config{
DNSInterval: time.Hour,
TLSInterval: 12 * time.Hour,
TLSExpiryWarning: 7,
DataDir: t.TempDir(),
}
}
func TestFirstRunBaseline(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Domains = []string{"example.com"}
cfg.Hostnames = []string{"www.example.com"}
w, deps := newTestWatcher(t, cfg)
setupBaselineMocks(deps)
w.RunOnce(t.Context())
assertNoNotifications(t, deps)
assertStatePopulated(t, deps)
}
func setupBaselineMocks(deps *testDeps) {
deps.resolver.nsRecords["example.com"] = []string{
"ns1.example.com.",
"ns2.example.com.",
}
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.34"}},
"ns2.example.com.": {"A": {"93.184.216.34"}},
}
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.34"}},
"ns2.example.com.": {"A": {"93.184.216.34"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"93.184.216.34",
}
deps.portChecker.results["93.184.216.34:80"] = true
deps.portChecker.results["93.184.216.34:443"] = true
deps.tlsChecker.certs["93.184.216.34:www.example.com"] = &tlscheck.CertificateInfo{
CommonName: "www.example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"www.example.com",
},
}
deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
CommonName: "example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"example.com",
},
}
}
func assertNoNotifications(
t *testing.T,
deps *testDeps,
) {
t.Helper()
notifications := deps.notifier.getNotifications()
if len(notifications) != 0 {
t.Errorf(
"expected 0 notifications on first run, got %d",
len(notifications),
)
}
}
func assertStatePopulated(
t *testing.T,
deps *testDeps,
) {
t.Helper()
snap := deps.state.GetSnapshot()
if len(snap.Domains) != 1 {
t.Errorf(
"expected 1 domain in state, got %d",
len(snap.Domains),
)
}
// Hostnames includes both explicit hostnames and domains
// (domains now also get hostname state for port/TLS checks).
if len(snap.Hostnames) < 1 {
t.Errorf(
"expected at least 1 hostname in state, got %d",
len(snap.Hostnames),
)
}
}
func TestDomainPortAndTLSChecks(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Domains = []string{"example.com"}
w, deps := newTestWatcher(t, cfg)
deps.resolver.nsRecords["example.com"] = []string{
"ns1.example.com.",
}
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.34"}},
}
deps.portChecker.results["93.184.216.34:80"] = true
deps.portChecker.results["93.184.216.34:443"] = true
deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
CommonName: "example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"example.com",
},
}
w.RunOnce(t.Context())
snap := deps.state.GetSnapshot()
// Domain should have port state populated
if len(snap.Ports) == 0 {
t.Error("expected port state for domain, got none")
}
// Domain should have certificate state populated
if len(snap.Certificates) == 0 {
t.Error("expected certificate state for domain, got none")
}
// Verify port checker was actually called
deps.portChecker.mu.Lock()
calls := deps.portChecker.calls
deps.portChecker.mu.Unlock()
if calls == 0 {
t.Error("expected port checker to be called for domain")
}
// Verify TLS checker was actually called
deps.tlsChecker.mu.Lock()
tlsCalls := deps.tlsChecker.calls
deps.tlsChecker.mu.Unlock()
if tlsCalls == 0 {
t.Error("expected TLS checker to be called for domain")
}
}
func TestNSChangeDetection(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Domains = []string{"example.com"}
w, deps := newTestWatcher(t, cfg)
deps.resolver.nsRecords["example.com"] = []string{
"ns1.example.com.",
"ns2.example.com.",
}
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
"ns2.example.com.": {"A": {"1.2.3.4"}},
}
deps.portChecker.results["1.2.3.4:80"] = false
deps.portChecker.results["1.2.3.4:443"] = false
ctx := t.Context()
w.RunOnce(ctx)
deps.resolver.mu.Lock()
deps.resolver.nsRecords["example.com"] = []string{
"ns1.example.com.",
"ns3.example.com.",
}
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
"ns3.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.mu.Unlock()
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
if len(notifications) == 0 {
t.Error("expected notification for NS change")
}
found := false
for _, n := range notifications {
if n.Priority == "warning" {
found = true
}
}
if !found {
t.Error("expected warning-priority NS change notification")
}
}
func TestRecordChangeDetection(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.34"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"93.184.216.34",
}
deps.portChecker.results["93.184.216.34:80"] = false
deps.portChecker.results["93.184.216.34:443"] = false
ctx := t.Context()
w.RunOnce(ctx)
deps.resolver.mu.Lock()
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"93.184.216.35"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"93.184.216.35",
}
deps.resolver.mu.Unlock()
deps.portChecker.mu.Lock()
deps.portChecker.results["93.184.216.35:80"] = false
deps.portChecker.results["93.184.216.35:443"] = false
deps.portChecker.mu.Unlock()
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
if len(notifications) == 0 {
t.Error("expected notification for record change")
}
}
func TestPortStateChange(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"1.2.3.4",
}
deps.portChecker.results["1.2.3.4:80"] = true
deps.portChecker.results["1.2.3.4:443"] = true
deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
CommonName: "www.example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"www.example.com",
},
}
ctx := t.Context()
w.RunOnce(ctx)
deps.portChecker.mu.Lock()
deps.portChecker.results["1.2.3.4:443"] = false
deps.portChecker.mu.Unlock()
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
if len(notifications) == 0 {
t.Error("expected notification for port state change")
}
}
func TestTLSExpiryWarning(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"1.2.3.4",
}
deps.portChecker.results["1.2.3.4:80"] = true
deps.portChecker.results["1.2.3.4:443"] = true
deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
CommonName: "www.example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(3 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"www.example.com",
},
}
ctx := t.Context()
// First run = baseline
w.RunOnce(ctx)
// Second run should warn about expiry
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
found := false
for _, n := range notifications {
if n.Priority == "warning" {
found = true
}
}
if !found {
t.Errorf(
"expected expiry warning, got: %v",
notifications,
)
}
}
func TestTLSExpiryWarningDedup(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
cfg.TLSInterval = 24 * time.Hour
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"1.2.3.4",
}
deps.portChecker.results["1.2.3.4:80"] = true
deps.portChecker.results["1.2.3.4:443"] = true
deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
CommonName: "www.example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(3 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"www.example.com",
},
}
ctx := t.Context()
// First run = baseline, no notifications
w.RunOnce(ctx)
// Second run should fire one expiry warning
w.RunOnce(ctx)
// Third run should NOT fire another warning (dedup)
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
expiryCount := 0
for _, n := range notifications {
if n.Title == "TLS Expiry Warning: www.example.com" {
expiryCount++
}
}
if expiryCount != 1 {
t.Errorf(
"expected exactly 1 expiry warning (dedup), got %d",
expiryCount,
)
}
}
func TestGracefulShutdown(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Domains = []string{"example.com"}
cfg.DNSInterval = 100 * time.Millisecond
cfg.TLSInterval = 100 * time.Millisecond
w, deps := newTestWatcher(t, cfg)
deps.resolver.nsRecords["example.com"] = []string{
"ns1.example.com.",
}
deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.portChecker.results["1.2.3.4:80"] = false
deps.portChecker.results["1.2.3.4:443"] = false
ctx, cancel := context.WithCancel(t.Context())
done := make(chan struct{})
go func() {
w.Run(ctx)
close(done)
}()
time.Sleep(250 * time.Millisecond)
cancel()
select {
case <-done:
// Shut down cleanly
case <-time.After(5 * time.Second):
t.Error("watcher did not shut down within timeout")
}
}
func setupHostnameIP(
deps *testDeps,
hostname, ip string,
) {
deps.resolver.allRecords[hostname] = map[string]map[string][]string{
"ns1.example.com.": {"A": {ip}},
}
deps.portChecker.results[ip+":80"] = true
deps.portChecker.results[ip+":443"] = true
deps.tlsChecker.certs[ip+":"+hostname] = &tlscheck.CertificateInfo{
CommonName: hostname,
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{hostname},
}
}
func updateHostnameIP(deps *testDeps, hostname, ip string) {
deps.resolver.mu.Lock()
deps.resolver.allRecords[hostname] = map[string]map[string][]string{
"ns1.example.com.": {"A": {ip}},
}
deps.resolver.mu.Unlock()
deps.portChecker.mu.Lock()
deps.portChecker.results[ip+":80"] = true
deps.portChecker.results[ip+":443"] = true
deps.portChecker.mu.Unlock()
deps.tlsChecker.mu.Lock()
deps.tlsChecker.certs[ip+":"+hostname] = &tlscheck.CertificateInfo{
CommonName: hostname,
Issuer: "DigiCert",
NotAfter: time.Now().Add(90 * 24 * time.Hour),
SubjectAlternativeNames: []string{hostname},
}
deps.tlsChecker.mu.Unlock()
}
func TestDNSRunsBeforePortAndTLSChecks(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
w, deps := newTestWatcher(t, cfg)
setupHostnameIP(deps, "www.example.com", "10.0.0.1")
ctx := t.Context()
w.RunOnce(ctx)
snap := deps.state.GetSnapshot()
if _, ok := snap.Ports["10.0.0.1:80"]; !ok {
t.Fatal("expected port state for 10.0.0.1:80")
}
// DNS changes to a new IP; port and TLS must pick it up.
updateHostnameIP(deps, "www.example.com", "10.0.0.2")
w.RunOnce(ctx)
snap = deps.state.GetSnapshot()
if _, ok := snap.Ports["10.0.0.2:80"]; !ok {
t.Error("port check used stale DNS: missing 10.0.0.2:80")
}
certKey := "10.0.0.2:443:www.example.com"
if _, ok := snap.Certificates[certKey]; !ok {
t.Error("TLS check used stale DNS: missing " + certKey)
}
}
func TestNSFailureAndRecovery(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
"ns2.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"1.2.3.4",
}
deps.portChecker.results["1.2.3.4:80"] = false
deps.portChecker.results["1.2.3.4:443"] = false
ctx := t.Context()
w.RunOnce(ctx)
deps.resolver.mu.Lock()
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.mu.Unlock()
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
if len(notifications) == 0 {
t.Error("expected notification for NS disappearance")
}
}