fix: distinguish timeout from negative DNS responses (closes #35)

Reviewed-on: #23

TESTING.md

@@ -0,0 +1,34 @@
+# Testing Policy
+
+## DNS Resolution Tests
+
+All resolver tests **MUST** use live queries against real DNS servers.
+No mocking of the DNS client layer is permitted.
+
+### Rationale
+
+The resolver performs iterative resolution from root nameservers through
+the full delegation chain. Mocked responses cannot faithfully represent
+the variety of real-world DNS behavior (truncation, referrals, glue
+records, DNSSEC, varied response times, EDNS, etc.). Testing against
+real servers ensures the resolver works correctly in production.
+
+### Constraints
+
+- Tests hit real DNS infrastructure and require network access
+- Test duration depends on network conditions; timeout tuning keeps
+  the suite within the 30-second target
+- Query timeout is calibrated to 3× maximum antipodal RTT (~300ms)
+  plus processing margin
+- Root server fan-out is limited to reduce parallel query load
+- Flaky failures from transient network issues are acceptable and
+  should be investigated as potential resolver bugs, not papered over
+  with mocks or skip flags
+
+### What NOT to do
+
+- **Do not mock `DNSClient`** for resolver tests (the mock constructor
+  exists for unit-testing other packages that consume the resolver)
+- **Do not add `-short` flags** to skip slow tests
+- **Do not increase `-timeout`** to hide hanging queries
+- **Do not modify linter configuration** to suppress findings

internal/resolver/errors.go

@@ -4,11 +4,6 @@ import "errors"
 
 // Sentinel errors returned by the resolver.
 var (
-	// ErrNotImplemented indicates a method is stubbed out.
-	ErrNotImplemented = errors.New(
-		"resolver not yet implemented",
-	)
-
 	// ErrNoNameservers is returned when no authoritative NS
 	// could be discovered for a domain.
 	ErrNoNameservers = errors.New(

internal/resolver/iterative.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"math/rand"
 	"net"
 	"sort"
 	"strings"
@@ -13,7 +14,7 @@ import (
 )
 
 const (
-	queryTimeoutDuration = 5 * time.Second
+	queryTimeoutDuration = 2 * time.Second
 	maxRetries           = 2
 	maxDelegation        = 20
 	timeoutMultiplier    = 2
@@ -41,6 +42,22 @@ func rootServerList() []string {
 	}
 }
 
+const maxRootServers = 3
+
+// randomRootServers returns a shuffled subset of root servers.
+func randomRootServers() []string {
+	all := rootServerList()
+	rand.Shuffle(len(all), func(i, j int) {
+		all[i], all[j] = all[j], all[i]
+	})
+
+	if len(all) > maxRootServers {
+		return all[:maxRootServers]
+	}
+
+	return all
+}
+
 func checkCtx(ctx context.Context) error {
 	err := ctx.Err()
 	if err != nil {
@@ -302,7 +319,7 @@ func (r *Resolver) resolveNSRecursive(
 	msg.SetQuestion(domain, dns.TypeNS)
 	msg.RecursionDesired = true
 
-	for _, ip := range rootServerList()[:3] {
+	for _, ip := range randomRootServers() {
 		if checkCtx(ctx) != nil {
 			return nil, ErrContextCanceled
 		}
@@ -333,7 +350,7 @@ func (r *Resolver) resolveARecord(
 	msg.SetQuestion(hostname, dns.TypeA)
 	msg.RecursionDesired = true
 
-	for _, ip := range rootServerList()[:3] {
+	for _, ip := range randomRootServers() {
 		if checkCtx(ctx) != nil {
 			return nil, ErrContextCanceled
 		}
@@ -385,7 +402,7 @@ func (r *Resolver) FindAuthoritativeNameservers(
 		candidate := strings.Join(labels[i:], ".") + "."
 
 		nsNames, err := r.followDelegation(
-			ctx, candidate, rootServerList(),
+			ctx, candidate, randomRootServers(),
 		)
 		if err == nil && len(nsNames) > 0 {
 			sort.Strings(nsNames)
@@ -418,6 +435,23 @@ func (r *Resolver) QueryNameserver(
 	return r.queryAllTypes(ctx, nsHostname, nsIPs[0], hostname)
 }
 
+// QueryNameserverIP queries a nameserver by its IP address directly,
+// bypassing NS hostname resolution.
+func (r *Resolver) QueryNameserverIP(
+	ctx context.Context,
+	nsHostname string,
+	nsIP string,
+	hostname string,
+) (*NameserverResponse, error) {
+	if checkCtx(ctx) != nil {
+		return nil, ErrContextCanceled
+	}
+
+	hostname = dns.Fqdn(hostname)
+
+	return r.queryAllTypes(ctx, nsHostname, nsIP, hostname)
+}
+
 func (r *Resolver) queryAllTypes(
 	ctx context.Context,
 	nsHostname string,
@@ -445,6 +479,7 @@ func (r *Resolver) queryAllTypes(
 type queryState struct {
 	gotNXDomain bool
 	gotSERVFAIL bool
+	gotTimeout  bool
 	hasRecords  bool
 }
 
@@ -482,6 +517,10 @@ func (r *Resolver) querySingleType(
 ) {
 	msg, err := r.queryDNS(ctx, nsIP, hostname, qtype)
 	if err != nil {
+		if isTimeout(err) {
+			state.gotTimeout = true
+		}
+
 		return
 	}
 
@@ -519,12 +558,26 @@ func collectAnswerRecords(
 	}
 }
 
+// isTimeout checks whether an error is a network timeout.
+func isTimeout(err error) bool {
+	var netErr net.Error
+	if errors.As(err, &netErr) {
+		return netErr.Timeout()
+	}
+
+	return false
+}
+
 func classifyResponse(resp *NameserverResponse, state queryState) {
 	switch {
 	case state.gotNXDomain && !state.hasRecords:
 		resp.Status = StatusNXDomain
+	case state.gotTimeout && !state.hasRecords:
+		resp.Status = StatusTimeout
+		resp.Error = "all queries timed out"
 	case state.gotSERVFAIL && !state.hasRecords:
 		resp.Status = StatusError
+		resp.Error = "server returned SERVFAIL"
 	case !state.hasRecords && !state.gotNXDomain:
 		resp.Status = StatusNoData
 	}

internal/resolver/resolver.go

@@ -17,6 +17,7 @@ const (
 	StatusError    = "error"
 	StatusNXDomain = "nxdomain"
 	StatusNoData   = "nodata"
+	StatusTimeout  = "timeout"
 )
 
 // MaxCNAMEDepth is the maximum CNAME chain depth to follow.

internal/resolver/resolver_test.go

@@ -2,7 +2,6 @@ package resolver_test
 
 import (
 	"context"
-	"fmt"
 	"log/slog"
 	"net"
 	"os"
@@ -18,497 +17,6 @@ import (
 	"sneak.berlin/go/dnswatcher/internal/resolver"
 )
 
-// ----------------------------------------------------------------
-// Mock DNS client
-// ----------------------------------------------------------------
-
-// mockDNSClient implements resolver.DNSClient with canned responses.
-type mockDNSClient struct {
-	handlers map[string]func(msg *dns.Msg) *dns.Msg
-}
-
-func newMockClient() *mockDNSClient {
-	return &mockDNSClient{
-		handlers: make(map[string]func(msg *dns.Msg) *dns.Msg),
-	}
-}
-
-func (m *mockDNSClient) ExchangeContext(
-	ctx context.Context,
-	msg *dns.Msg,
-	addr string,
-) (*dns.Msg, time.Duration, error) {
-	err := ctx.Err()
-	if err != nil {
-		return nil, 0, err
-	}
-
-	host, _, _ := net.SplitHostPort(addr)
-	if host == "" {
-		host = addr
-	}
-
-	qname := msg.Question[0].Name
-	qtype := dns.TypeToString[msg.Question[0].Qtype]
-
-	resp := m.findHandler(host, qname, qtype, msg)
-
-	return resp, time.Millisecond, nil
-}
-
-func (m *mockDNSClient) findHandler(
-	host, qname, qtype string,
-	msg *dns.Msg,
-) *dns.Msg {
-	key := fmt.Sprintf(
-		"%s|%s|%s", host, strings.ToLower(qname), qtype,
-	)
-
-	if h, ok := m.handlers[key]; ok {
-		return h(msg)
-	}
-
-	wildKey := fmt.Sprintf(
-		"*|%s|%s", strings.ToLower(qname), qtype,
-	)
-
-	if h, ok := m.handlers[wildKey]; ok {
-		return h(msg)
-	}
-
-	resp := new(dns.Msg)
-	resp.SetReply(msg)
-
-	return resp
-}
-
-func (m *mockDNSClient) on(
-	server, qname, qtype string,
-	handler func(msg *dns.Msg) *dns.Msg,
-) {
-	key := fmt.Sprintf(
-		"%s|%s|%s",
-		server, dns.Fqdn(strings.ToLower(qname)), qtype,
-	)
-	m.handlers[key] = handler
-}
-
-// ----------------------------------------------------------------
-// Response builders
-// ----------------------------------------------------------------
-
-func referralResponse(
-	msg *dns.Msg,
-	nsNames []string,
-	glue map[string]string,
-) *dns.Msg {
-	resp := new(dns.Msg)
-	resp.SetReply(msg)
-
-	for _, ns := range nsNames {
-		resp.Ns = append(resp.Ns, &dns.NS{
-			Hdr: dns.RR_Header{
-				Name:   msg.Question[0].Name,
-				Rrtype: dns.TypeNS,
-				Class:  dns.ClassINET,
-				Ttl:    3600,
-			},
-			Ns: dns.Fqdn(ns),
-		})
-	}
-
-	for name, ip := range glue {
-		resp.Extra = append(resp.Extra, &dns.A{
-			Hdr: dns.RR_Header{
-				Name:   dns.Fqdn(name),
-				Rrtype: dns.TypeA,
-				Class:  dns.ClassINET,
-				Ttl:    3600,
-			},
-			A: net.ParseIP(ip),
-		})
-	}
-
-	return resp
-}
-
-func nsAnswerResponse(
-	msg *dns.Msg, nsNames []string,
-) *dns.Msg {
-	resp := new(dns.Msg)
-	resp.SetReply(msg)
-
-	for _, ns := range nsNames {
-		resp.Answer = append(resp.Answer, &dns.NS{
-			Hdr: dns.RR_Header{
-				Name:   msg.Question[0].Name,
-				Rrtype: dns.TypeNS,
-				Class:  dns.ClassINET,
-				Ttl:    3600,
-			},
-			Ns: dns.Fqdn(ns),
-		})
-	}
-
-	return resp
-}
-
-func nxdomainResponse(msg *dns.Msg) *dns.Msg {
-	resp := new(dns.Msg)
-	resp.SetReply(msg)
-	resp.Rcode = dns.RcodeNameError
-
-	return resp
-}
-
-func aResponse(
-	msg *dns.Msg, name string, ip string,
-) *dns.Msg {
-	resp := new(dns.Msg)
-	resp.SetReply(msg)
-	resp.Answer = append(resp.Answer, &dns.A{
-		Hdr: dns.RR_Header{
-			Name: dns.Fqdn(name), Rrtype: dns.TypeA,
-			Class: dns.ClassINET, Ttl: 300,
-		},
-		A: net.ParseIP(ip),
-	})
-
-	return resp
-}
-
-func aaaaResponse(
-	msg *dns.Msg, name string, ip string,
-) *dns.Msg {
-	resp := new(dns.Msg)
-	resp.SetReply(msg)
-	resp.Answer = append(resp.Answer, &dns.AAAA{
-		Hdr: dns.RR_Header{
-			Name: dns.Fqdn(name), Rrtype: dns.TypeAAAA,
-			Class: dns.ClassINET, Ttl: 300,
-		},
-		AAAA: net.ParseIP(ip),
-	})
-
-	return resp
-}
-
-func emptyResponse(msg *dns.Msg) *dns.Msg {
-	resp := new(dns.Msg)
-	resp.SetReply(msg)
-
-	return resp
-}
-
-// ----------------------------------------------------------------
-// Mock DNS hierarchy setup
-// ----------------------------------------------------------------
-
-// mockData holds all test DNS hierarchy configuration.
-type mockData struct {
-	tldNS   []string
-	tldGlue map[string]string
-	exNS    []string
-	exGlue  map[string]string
-	cfNS    []string
-	cfGlue  map[string]string
-}
-
-func newMockData() mockData {
-	return mockData{
-		tldNS: []string{"ns1.tld.com", "ns2.tld.com"},
-		tldGlue: map[string]string{
-			"ns1.tld.com": "10.0.0.1",
-			"ns2.tld.com": "10.0.0.2",
-		},
-		exNS: []string{
-			"ns1.example.com", "ns2.example.com",
-			"ns3.example.com",
-		},
-		exGlue: map[string]string{
-			"ns1.example.com": "10.1.0.1",
-			"ns2.example.com": "10.1.0.2",
-			"ns3.example.com": "10.1.0.3",
-		},
-		cfNS: []string{
-			"ns1.cloudflare.com", "ns2.cloudflare.com",
-		},
-		cfGlue: map[string]string{
-			"ns1.cloudflare.com": "10.2.0.1",
-			"ns2.cloudflare.com": "10.2.0.2",
-		},
-	}
-}
-
-func rootIPList() []string {
-	return []string{
-		"198.41.0.4", "170.247.170.2", "192.33.4.12",
-		"199.7.91.13", "192.203.230.10", "192.5.5.241",
-		"192.112.36.4", "198.97.190.53", "192.36.148.17",
-		"192.58.128.30", "193.0.14.129", "199.7.83.42",
-		"202.12.27.33",
-	}
-}
-
-func allQueryTypes() []string {
-	return []string{
-		"NS", "A", "AAAA", "CNAME", "MX", "TXT", "SRV", "CAA",
-	}
-}
-
-func setupRootDelegations(
-	m *mockDNSClient,
-	tNS []string,
-	tGlue map[string]string,
-) {
-	domains := []string{
-		"example.com.", "www.example.com.",
-		"this-surely-does-not-exist-xyz.example.com.",
-		"cloudflare.com.",
-	}
-
-	for _, rootIP := range rootIPList() {
-		for _, domain := range domains {
-			for _, qtype := range allQueryTypes() {
-				m.on(rootIP, domain, qtype,
-					func(msg *dns.Msg) *dns.Msg {
-						return referralResponse(
-							msg, tNS, tGlue,
-						)
-					},
-				)
-			}
-		}
-	}
-}
-
-func setupRootARecords(m *mockDNSClient) {
-	nsIPs := map[string]string{
-		"ns1.example.com.":    "10.1.0.1",
-		"ns2.example.com.":    "10.1.0.2",
-		"ns3.example.com.":    "10.1.0.3",
-		"ns1.cloudflare.com.": "10.2.0.1",
-		"ns2.cloudflare.com.": "10.2.0.2",
-	}
-
-	for _, rootIP := range rootIPList() {
-		for nsName, nsIP := range nsIPs {
-			ip := nsIP
-			name := nsName
-
-			m.on(rootIP, name, "A",
-				func(msg *dns.Msg) *dns.Msg {
-					return aResponse(msg, name, ip)
-				},
-			)
-		}
-	}
-}
-
-func setupTLDDelegations(
-	m *mockDNSClient,
-	exNS []string,
-	exGlue map[string]string,
-	cfNS []string,
-	cfGlue map[string]string,
-) {
-	tldIPs := []string{"10.0.0.1", "10.0.0.2"}
-
-	exDomains := []string{
-		"example.com.", "www.example.com.",
-		"this-surely-does-not-exist-xyz.example.com.",
-	}
-
-	for _, tldIP := range tldIPs {
-		for _, domain := range exDomains {
-			for _, qtype := range allQueryTypes() {
-				m.on(tldIP, domain, qtype,
-					func(msg *dns.Msg) *dns.Msg {
-						return referralResponse(
-							msg, exNS, exGlue,
-						)
-					},
-				)
-			}
-		}
-
-		for _, qtype := range allQueryTypes() {
-			m.on(tldIP, "cloudflare.com.", qtype,
-				func(msg *dns.Msg) *dns.Msg {
-					return referralResponse(
-						msg, cfNS, cfGlue,
-					)
-				},
-			)
-		}
-	}
-}
-
-func setupExampleNSAndA(
-	m *mockDNSClient, exNS []string,
-) {
-	exIPs := []string{"10.1.0.1", "10.1.0.2", "10.1.0.3"}
-
-	for _, authIP := range exIPs {
-		m.on(authIP, "example.com.", "NS",
-			func(msg *dns.Msg) *dns.Msg {
-				return nsAnswerResponse(msg, exNS)
-			},
-		)
-
-		m.on(authIP, "example.com.", "A",
-			func(msg *dns.Msg) *dns.Msg {
-				return aResponse(
-					msg, "example.com.", "93.184.216.34",
-				)
-			},
-		)
-
-		m.on(authIP, "example.com.", "AAAA",
-			func(msg *dns.Msg) *dns.Msg {
-				return aaaaResponse(
-					msg, "example.com.",
-					"2606:2800:220:1:248:1893:25c8:1946",
-				)
-			},
-		)
-	}
-}
-
-func setupExampleMXAndTXT(m *mockDNSClient) {
-	exIPs := []string{"10.1.0.1", "10.1.0.2", "10.1.0.3"}
-
-	for _, authIP := range exIPs {
-		m.on(authIP, "example.com.", "MX",
-			func(msg *dns.Msg) *dns.Msg {
-				resp := new(dns.Msg)
-				resp.SetReply(msg)
-				resp.Answer = append(resp.Answer,
-					&dns.MX{
-						Hdr: dns.RR_Header{
-							Name:   "example.com.",
-							Rrtype: dns.TypeMX,
-							Class:  dns.ClassINET,
-							Ttl:    300,
-						},
-						Preference: 10,
-						Mx:         "mail.example.com.",
-					},
-					&dns.MX{
-						Hdr: dns.RR_Header{
-							Name:   "example.com.",
-							Rrtype: dns.TypeMX,
-							Class:  dns.ClassINET,
-							Ttl:    300,
-						},
-						Preference: 20,
-						Mx:         "mail2.example.com.",
-					},
-				)
-
-				return resp
-			},
-		)
-
-		m.on(authIP, "example.com.", "TXT",
-			func(msg *dns.Msg) *dns.Msg {
-				resp := new(dns.Msg)
-				resp.SetReply(msg)
-				resp.Answer = append(resp.Answer, &dns.TXT{
-					Hdr: dns.RR_Header{
-						Name:   "example.com.",
-						Rrtype: dns.TypeTXT,
-						Class:  dns.ClassINET,
-						Ttl:    300,
-					},
-					Txt: []string{
-						"v=spf1 include:_spf.example.com ~all",
-					},
-				})
-
-				return resp
-			},
-		)
-	}
-}
-
-func setupExampleSubdomains(
-	m *mockDNSClient, exNS []string,
-) {
-	exIPs := []string{"10.1.0.1", "10.1.0.2", "10.1.0.3"}
-
-	for _, authIP := range exIPs {
-		m.on(authIP, "www.example.com.", "NS",
-			func(msg *dns.Msg) *dns.Msg {
-				return nsAnswerResponse(msg, exNS)
-			},
-		)
-
-		m.on(authIP, "www.example.com.", "A",
-			func(msg *dns.Msg) *dns.Msg {
-				return aResponse(
-					msg, "www.example.com.", "93.184.216.34",
-				)
-			},
-		)
-
-		nxName := "this-surely-does-not-exist-xyz.example.com."
-		for _, qtype := range allQueryTypes() {
-			m.on(authIP, nxName, qtype, nxdomainResponse)
-		}
-	}
-}
-
-func setupCloudflareAuthRecords(
-	m *mockDNSClient, cfNS []string,
-) {
-	cfIPs := []string{"10.2.0.1", "10.2.0.2"}
-
-	for _, authIP := range cfIPs {
-		m.on(authIP, "cloudflare.com.", "NS",
-			func(msg *dns.Msg) *dns.Msg {
-				return nsAnswerResponse(msg, cfNS)
-			},
-		)
-
-		m.on(authIP, "cloudflare.com.", "A",
-			func(msg *dns.Msg) *dns.Msg {
-				return aResponse(
-					msg, "cloudflare.com.", "104.16.132.229",
-				)
-			},
-		)
-
-		m.on(authIP, "cloudflare.com.", "AAAA",
-			func(msg *dns.Msg) *dns.Msg {
-				return aaaaResponse(
-					msg, "cloudflare.com.",
-					"2606:4700::6810:84e5",
-				)
-			},
-		)
-
-		m.on(authIP, "cloudflare.com.", "MX", emptyResponse)
-		m.on(authIP, "cloudflare.com.", "TXT", emptyResponse)
-	}
-}
-
-func setupMockDNS() *mockDNSClient {
-	m := newMockClient()
-
-	d := newMockData()
-
-	setupRootDelegations(m, d.tldNS, d.tldGlue)
-	setupRootARecords(m)
-	setupTLDDelegations(m, d.exNS, d.exGlue, d.cfNS, d.cfGlue)
-	setupExampleNSAndA(m, d.exNS)
-	setupExampleMXAndTXT(m)
-	setupExampleSubdomains(m, d.exNS)
-	setupCloudflareAuthRecords(m, d.cfNS)
-
-	return m
-}
-
 // ----------------------------------------------------------------
 // Test helpers
 // ----------------------------------------------------------------
@@ -521,14 +29,14 @@ func newTestResolver(t *testing.T) *resolver.Resolver {
 		&slog.HandlerOptions{Level: slog.LevelDebug},
 	))
 
-	return resolver.NewFromLoggerWithClient(log, setupMockDNS())
+	return resolver.NewFromLogger(log)
 }
 
 func testContext(t *testing.T) context.Context {
 	t.Helper()
 
 	ctx, cancel := context.WithTimeout(
-		context.Background(), 10*time.Second,
+		context.Background(), 60*time.Second,
 	)
 	t.Cleanup(cancel)
 
@@ -565,23 +73,23 @@ func TestFindAuthoritativeNameservers_ValidDomain(
 	ctx := testContext(t)
 
 	nameservers, err := r.FindAuthoritativeNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 	require.NotEmpty(t, nameservers)
 
-	hasExampleNS := false
+	hasGoogleNS := false
 
 	for _, ns := range nameservers {
-		if strings.Contains(ns, "example") {
+		if strings.Contains(ns, "google") {
-			hasExampleNS = true
+			hasGoogleNS = true
 
 			break
 		}
 	}
 
-	assert.True(t, hasExampleNS,
+	assert.True(t, hasGoogleNS,
-		"expected example nameservers, got: %v", nameservers,
+		"expected google nameservers, got: %v", nameservers,
 	)
 }
 
@@ -594,7 +102,7 @@ func TestFindAuthoritativeNameservers_Subdomain(
 	ctx := testContext(t)
 
 	nameservers, err := r.FindAuthoritativeNameservers(
-		ctx, "www.example.com",
+		ctx, "www.google.com",
 	)
 	require.NoError(t, err)
 	require.NotEmpty(t, nameservers)
@@ -609,7 +117,7 @@ func TestFindAuthoritativeNameservers_ReturnsSorted(
 	ctx := testContext(t)
 
 	nameservers, err := r.FindAuthoritativeNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 
@@ -629,12 +137,12 @@ func TestFindAuthoritativeNameservers_Deterministic(
 	ctx := testContext(t)
 
 	first, err := r.FindAuthoritativeNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 
 	second, err := r.FindAuthoritativeNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 
@@ -650,12 +158,12 @@ func TestFindAuthoritativeNameservers_TrailingDot(
 	ctx := testContext(t)
 
 	ns1, err := r.FindAuthoritativeNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 
 	ns2, err := r.FindAuthoritativeNameservers(
-		ctx, "example.com.",
+		ctx, "google.com.",
 	)
 	require.NoError(t, err)
 
@@ -692,10 +200,10 @@ func TestQueryNameserver_BasicA(t *testing.T) {
 
 	r := newTestResolver(t)
 	ctx := testContext(t)
-	ns := findOneNSForDomain(t, r, ctx, "example.com")
+	ns := findOneNSForDomain(t, r, ctx, "google.com")
 
 	resp, err := r.QueryNameserver(
-		ctx, ns, "www.example.com",
+		ctx, ns, "www.google.com",
 	)
 	require.NoError(t, err)
 	require.NotNil(t, resp)
@@ -706,7 +214,7 @@ func TestQueryNameserver_BasicA(t *testing.T) {
 	hasRecords := len(resp.Records["A"]) > 0 ||
 		len(resp.Records["CNAME"]) > 0
 	assert.True(t, hasRecords,
-		"expected A or CNAME records for www.example.com",
+		"expected A or CNAME records for www.google.com",
 	)
 }
 
@@ -740,16 +248,16 @@ func TestQueryNameserver_MX(t *testing.T) {
 
 	r := newTestResolver(t)
 	ctx := testContext(t)
-	ns := findOneNSForDomain(t, r, ctx, "example.com")
+	ns := findOneNSForDomain(t, r, ctx, "google.com")
 
 	resp, err := r.QueryNameserver(
-		ctx, ns, "example.com",
+		ctx, ns, "google.com",
 	)
 	require.NoError(t, err)
 
 	mxRecords := resp.Records["MX"]
 	require.NotEmpty(t, mxRecords,
-		"example.com should have MX records",
+		"google.com should have MX records",
 	)
 }
 
@@ -758,16 +266,16 @@ func TestQueryNameserver_TXT(t *testing.T) {
 
 	r := newTestResolver(t)
 	ctx := testContext(t)
-	ns := findOneNSForDomain(t, r, ctx, "example.com")
+	ns := findOneNSForDomain(t, r, ctx, "google.com")
 
 	resp, err := r.QueryNameserver(
-		ctx, ns, "example.com",
+		ctx, ns, "google.com",
 	)
 	require.NoError(t, err)
 
 	txtRecords := resp.Records["TXT"]
 	require.NotEmpty(t, txtRecords,
-		"example.com should have TXT records",
+		"google.com should have TXT records",
 	)
 
 	hasSPF := false
@@ -781,7 +289,7 @@ func TestQueryNameserver_TXT(t *testing.T) {
 	}
 
 	assert.True(t, hasSPF,
-		"example.com should have SPF TXT record",
+		"google.com should have SPF TXT record",
 	)
 }
 
@@ -790,11 +298,11 @@ func TestQueryNameserver_NXDomain(t *testing.T) {
 
 	r := newTestResolver(t)
 	ctx := testContext(t)
-	ns := findOneNSForDomain(t, r, ctx, "example.com")
+	ns := findOneNSForDomain(t, r, ctx, "google.com")
 
 	resp, err := r.QueryNameserver(
 		ctx, ns,
-		"this-surely-does-not-exist-xyz.example.com",
+		"this-surely-does-not-exist-xyz.google.com",
 	)
 	require.NoError(t, err)
 
@@ -806,10 +314,10 @@ func TestQueryNameserver_RecordsSorted(t *testing.T) {
 
 	r := newTestResolver(t)
 	ctx := testContext(t)
-	ns := findOneNSForDomain(t, r, ctx, "example.com")
+	ns := findOneNSForDomain(t, r, ctx, "google.com")
 
 	resp, err := r.QueryNameserver(
-		ctx, ns, "example.com",
+		ctx, ns, "google.com",
 	)
 	require.NoError(t, err)
 
@@ -846,11 +354,11 @@ func TestQueryNameserver_EmptyRecordsOnNXDomain(
 
 	r := newTestResolver(t)
 	ctx := testContext(t)
-	ns := findOneNSForDomain(t, r, ctx, "example.com")
+	ns := findOneNSForDomain(t, r, ctx, "google.com")
 
 	resp, err := r.QueryNameserver(
 		ctx, ns,
-		"this-surely-does-not-exist-xyz.example.com",
+		"this-surely-does-not-exist-xyz.google.com",
 	)
 	require.NoError(t, err)
 
@@ -867,15 +375,15 @@ func TestQueryNameserver_TrailingDotHandling(t *testing.T) {
 
 	r := newTestResolver(t)
 	ctx := testContext(t)
-	ns := findOneNSForDomain(t, r, ctx, "example.com")
+	ns := findOneNSForDomain(t, r, ctx, "google.com")
 
 	resp1, err := r.QueryNameserver(
-		ctx, ns, "example.com",
+		ctx, ns, "google.com",
 	)
 	require.NoError(t, err)
 
 	resp2, err := r.QueryNameserver(
-		ctx, ns, "example.com.",
+		ctx, ns, "google.com.",
 	)
 	require.NoError(t, err)
 
@@ -893,7 +401,7 @@ func TestQueryAllNameservers_ReturnsAllNS(t *testing.T) {
 	ctx := testContext(t)
 
 	results, err := r.QueryAllNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 	require.NotEmpty(t, results)
@@ -912,7 +420,7 @@ func TestQueryAllNameservers_AllReturnOK(t *testing.T) {
 	ctx := testContext(t)
 
 	results, err := r.QueryAllNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 
@@ -934,7 +442,7 @@ func TestQueryAllNameservers_NXDomainFromAllNS(
 
 	results, err := r.QueryAllNameservers(
 		ctx,
-		"this-surely-does-not-exist-xyz.example.com",
+		"this-surely-does-not-exist-xyz.google.com",
 	)
 	require.NoError(t, err)
 
@@ -956,7 +464,7 @@ func TestLookupNS_ValidDomain(t *testing.T) {
 	r := newTestResolver(t)
 	ctx := testContext(t)
 
-	nameservers, err := r.LookupNS(ctx, "example.com")
+	nameservers, err := r.LookupNS(ctx, "google.com")
 	require.NoError(t, err)
 	require.NotEmpty(t, nameservers)
 
@@ -973,7 +481,7 @@ func TestLookupNS_Sorted(t *testing.T) {
 	r := newTestResolver(t)
 	ctx := testContext(t)
 
-	nameservers, err := r.LookupNS(ctx, "example.com")
+	nameservers, err := r.LookupNS(ctx, "google.com")
 	require.NoError(t, err)
 
 	assert.True(t, sort.StringsAreSorted(nameservers))
@@ -985,11 +493,11 @@ func TestLookupNS_MatchesFindAuthoritative(t *testing.T) {
 	r := newTestResolver(t)
 	ctx := testContext(t)
 
-	fromLookup, err := r.LookupNS(ctx, "example.com")
+	fromLookup, err := r.LookupNS(ctx, "google.com")
 	require.NoError(t, err)
 
 	fromFind, err := r.FindAuthoritativeNameservers(
-		ctx, "example.com",
+		ctx, "google.com",
 	)
 	require.NoError(t, err)
 
@@ -1006,7 +514,7 @@ func TestResolveIPAddresses_ReturnsIPs(t *testing.T) {
 	r := newTestResolver(t)
 	ctx := testContext(t)
 
-	ips, err := r.ResolveIPAddresses(ctx, "example.com")
+	ips, err := r.ResolveIPAddresses(ctx, "google.com")
 	require.NoError(t, err)
 	require.NotEmpty(t, ips)
 
@@ -1024,7 +532,7 @@ func TestResolveIPAddresses_Deduplicated(t *testing.T) {
 	r := newTestResolver(t)
 	ctx := testContext(t)
 
-	ips, err := r.ResolveIPAddresses(ctx, "example.com")
+	ips, err := r.ResolveIPAddresses(ctx, "google.com")
 	require.NoError(t, err)
 
 	seen := make(map[string]bool)
@@ -1041,7 +549,7 @@ func TestResolveIPAddresses_Sorted(t *testing.T) {
 	r := newTestResolver(t)
 	ctx := testContext(t)
 
-	ips, err := r.ResolveIPAddresses(ctx, "example.com")
+	ips, err := r.ResolveIPAddresses(ctx, "google.com")
 	require.NoError(t, err)
 
 	assert.True(t, sort.StringsAreSorted(ips))
@@ -1057,7 +565,7 @@ func TestResolveIPAddresses_NXDomainReturnsEmpty(
 
 	ips, err := r.ResolveIPAddresses(
 		ctx,
-		"this-surely-does-not-exist-xyz.example.com",
+		"this-surely-does-not-exist-xyz.google.com",
 	)
 	require.NoError(t, err)
 	assert.Empty(t, ips)
@@ -1087,9 +595,7 @@ func TestFindAuthoritativeNameservers_ContextCanceled(
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()
 
-	_, err := r.FindAuthoritativeNameservers(
+	_, err := r.FindAuthoritativeNameservers(ctx, "google.com")
-		ctx, "example.com",
-	)
 	assert.Error(t, err)
 }
 
@@ -1101,7 +607,7 @@ func TestQueryNameserver_ContextCanceled(t *testing.T) {
 	cancel()
 
 	_, err := r.QueryNameserver(
-		ctx, "ns1.example.com.", "example.com",
+		ctx, "ns1.google.com.", "google.com",
 	)
 	assert.Error(t, err)
 }
@@ -1113,10 +619,63 @@ func TestQueryAllNameservers_ContextCanceled(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()
 
-	_, err := r.QueryAllNameservers(ctx, "example.com")
+	_, err := r.QueryAllNameservers(ctx, "google.com")
 	assert.Error(t, err)
 }
 
+// ----------------------------------------------------------------
+// Timeout tests
+// ----------------------------------------------------------------
+
+func TestQueryNameserverIP_Timeout(t *testing.T) {
+	t.Parallel()
+
+	log := slog.New(slog.NewTextHandler(
+		os.Stderr,
+		&slog.HandlerOptions{Level: slog.LevelDebug},
+	))
+
+	r := resolver.NewFromLoggerWithClient(
+		log, &timeoutClient{},
+	)
+
+	ctx, cancel := context.WithTimeout(
+		context.Background(), 10*time.Second,
+	)
+	t.Cleanup(cancel)
+
+	// Query any IP — the client always returns a timeout error.
+	resp, err := r.QueryNameserverIP(
+		ctx, "unreachable.test.", "192.0.2.1",
+		"example.com",
+	)
+	require.NoError(t, err)
+
+	assert.Equal(t, resolver.StatusTimeout, resp.Status)
+	assert.NotEmpty(t, resp.Error)
+}
+
+// timeoutClient simulates DNS timeout errors for testing.
+type timeoutClient struct{}
+
+func (c *timeoutClient) ExchangeContext(
+	_ context.Context,
+	_ *dns.Msg,
+	_ string,
+) (*dns.Msg, time.Duration, error) {
+	return nil, 0, &net.OpError{
+		Op:  "read",
+		Net: "udp",
+		Err: &timeoutError{},
+	}
+}
+
+type timeoutError struct{}
+
+func (e *timeoutError) Error() string   { return "i/o timeout" }
+func (e *timeoutError) Timeout() bool   { return true }
+func (e *timeoutError) Temporary() bool { return true }
+
 func TestResolveIPAddresses_ContextCanceled(t *testing.T) {
 	t.Parallel()
 
@@ -1124,6 +683,6 @@ func TestResolveIPAddresses_ContextCanceled(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	cancel()
 
-	_, err := r.ResolveIPAddresses(ctx, "example.com")
+	_, err := r.ResolveIPAddresses(ctx, "google.com")
 	assert.Error(t, err)
 }

internal/watcher/watcher.go

@@ -6,6 +6,7 @@ import (
 	"log/slog"
 	"sort"
 	"strings"
+	"sync"
 	"time"
 
 	"go.uber.org/fx"
@@ -40,15 +41,17 @@ type Params struct {
 
 // Watcher orchestrates all monitoring checks on a schedule.
 type Watcher struct {
-	log       *slog.Logger
+	log              *slog.Logger
-	config    *config.Config
+	config           *config.Config
-	state     *state.State
+	state            *state.State
-	resolver  DNSResolver
+	resolver         DNSResolver
-	portCheck PortChecker
+	portCheck        PortChecker
-	tlsCheck  TLSChecker
+	tlsCheck         TLSChecker
-	notify    Notifier
+	notify           Notifier
-	cancel    context.CancelFunc
+	cancel           context.CancelFunc
-	firstRun  bool
+	firstRun         bool
+	expiryNotifiedMu sync.Mutex
+	expiryNotified   map[string]time.Time
 }
 
 // New creates a new Watcher instance wired into the fx lifecycle.
@@ -57,14 +60,15 @@ func New(
 	params Params,
 ) (*Watcher, error) {
 	w := &Watcher{
-		log:       params.Logger.Get(),
+		log:            params.Logger.Get(),
-		config:    params.Config,
+		config:         params.Config,
-		state:     params.State,
+		state:          params.State,
-		resolver:  params.Resolver,
+		resolver:       params.Resolver,
-		portCheck: params.PortCheck,
+		portCheck:      params.PortCheck,
-		tlsCheck:  params.TLSCheck,
+		tlsCheck:       params.TLSCheck,
-		notify:    params.Notify,
+		notify:         params.Notify,
-		firstRun:  true,
+		firstRun:       true,
+		expiryNotified: make(map[string]time.Time),
 	}
 
 	lifecycle.Append(fx.Hook{
@@ -100,14 +104,15 @@ func NewForTest(
 	n Notifier,
 ) *Watcher {
 	return &Watcher{
-		log:       slog.Default(),
+		log:            slog.Default(),
-		config:    cfg,
+		config:         cfg,
-		state:     st,
+		state:          st,
-		resolver:  res,
+		resolver:       res,
-		portCheck: pc,
+		portCheck:      pc,
-		tlsCheck:  tc,
+		tlsCheck:       tc,
-		notify:    n,
+		notify:         n,
-		firstRun:  true,
+		firstRun:       true,
+		expiryNotified: make(map[string]time.Time),
 	}
 }
 
@@ -206,6 +211,28 @@ func (w *Watcher) checkDomain(
 		Nameservers: nameservers,
 		LastChecked: now,
 	})
+
+	// Also look up A/AAAA records for the apex domain so that
+	// port and TLS checks (which read HostnameState) can find
+	// the domain's IP addresses.
+	records, err := w.resolver.LookupAllRecords(ctx, domain)
+	if err != nil {
+		w.log.Error(
+			"failed to lookup records for domain",
+			"domain", domain,
+			"error", err,
+		)
+
+		return
+	}
+
+	prevHS, hasPrevHS := w.state.GetHostnameState(domain)
+	if hasPrevHS && !w.firstRun {
+		w.detectHostnameChanges(ctx, domain, prevHS, records)
+	}
+
+	newState := buildHostnameState(records, now)
+	w.state.SetHostnameState(domain, newState)
 }
 
 func (w *Watcher) detectNSChanges(
@@ -691,6 +718,22 @@ func (w *Watcher) checkTLSExpiry(
 		return
 	}
 
+	// Deduplicate expiry warnings: don't re-notify for the same
+	// hostname within the TLS check interval.
+	dedupKey := fmt.Sprintf("expiry:%s:%s", hostname, ip)
+
+	w.expiryNotifiedMu.Lock()
+
+	lastNotified, seen := w.expiryNotified[dedupKey]
+	if seen && time.Since(lastNotified) < w.config.TLSInterval {
+		w.expiryNotifiedMu.Unlock()
+
+		return
+	}
+
+	w.expiryNotified[dedupKey] = time.Now()
+	w.expiryNotifiedMu.Unlock()
+
 	msg := fmt.Sprintf(
 		"Host: %s\nIP: %s\nCN: %s\n"+
 			"Expires: %s (%.0f days)",

internal/watcher/watcher_test.go

@@ -273,6 +273,10 @@ func setupBaselineMocks(deps *testDeps) {
 		"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"}},
@@ -290,6 +294,14 @@ func setupBaselineMocks(deps *testDeps) {
 			"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(
@@ -322,14 +334,74 @@ func assertStatePopulated(
 		)
 	}
 
-	if len(snap.Hostnames) != 1 {
+	// 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 1 hostname in state, got %d",
+			"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()
 
@@ -342,6 +414,12 @@ func TestNSChangeDetection(t *testing.T) {
 		"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)
@@ -351,6 +429,10 @@ func TestNSChangeDetection(t *testing.T) {
 		"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)
@@ -506,6 +588,61 @@ func TestTLSExpiryWarning(t *testing.T) {
 	}
 }
 
+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()
 
@@ -519,6 +656,11 @@ func TestGracefulShutdown(t *testing.T) {
 	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())