resolver: try servers in a random order on each resolution (closes #138)

Every resolution walked the root servers in a fixed order, so
a.root-servers.net got every first query and its timeouts were paid on
every lookup. Each list of servers the resolver walks, the root servers
and the nameservers of each zone below them, is now walked in a random
order from the standard library's rand.Shuffle, chosen anew each time.
Failover is unchanged: after a failure the next server is tried, and
the walk fails only when every server has. The shuffle is passed in, so
the tests check the order with a seeded source; which server a live
query reached is not observable, so no test fails if the walk stops
shuffling.

Model: opus-5-5

internal/resolver/export_test.go

@@ -26,3 +26,16 @@ func (r *Resolver) QueryEachNS(
 ) (map[string]*NameserverResponse, error) {
 	return r.queryEachNS(ctx, nameservers, hostname)
 }
+
+// RootServerList exports rootServerList for testing.
+func RootServerList() []string {
+	return rootServerList()
+}
+
+// Shuffled exports shuffled for testing.
+func Shuffled(
+	servers []string,
+	shuffle func(n int, swap func(i, j int)),
+) []string {
+	return shuffled(servers, shuffle)
+}

internal/resolver/iterative.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"math/rand/v2"
 	"net"
+	"slices"
 	"sort"
 	"strings"
 	"time"
@@ -255,6 +257,24 @@ func (r *Resolver) followDelegation(
 	return nil, ErrNoNameservers
 }
 
+// shuffled returns a copy of servers in the order shuffle puts them
+// in. The resolver passes rand.Shuffle, so each time it walks a list of
+// servers it starts at a random one, and no one server gets every
+// first query.
+func shuffled(
+	servers []string,
+	shuffle func(n int, swap func(i, j int)),
+) []string {
+	order := slices.Clone(servers)
+	shuffle(len(order), func(i, j int) {
+		order[i], order[j] = order[j], order[i]
+	})
+
+	return order
+}
+
+// queryServers asks the servers in a random order and returns the
+// first reply; it fails only when every server has failed.
 func (r *Resolver) queryServers(
 	ctx context.Context,
 	servers []string,
@@ -263,7 +283,7 @@ func (r *Resolver) queryServers(
 ) (*dns.Msg, error) {
 	var lastErr error
 
-	for _, ip := range servers {
+	for _, ip := range shuffled(servers, rand.Shuffle) {
 		if checkCtx(ctx) != nil {
 			return nil, ErrContextCanceled
 		}
@@ -279,13 +299,15 @@ func (r *Resolver) queryServers(
 	return nil, fmt.Errorf("all servers failed: %w", lastErr)
 }
 
+// resolveNSIPs returns the addresses of one of the nameservers, trying
+// their names in a random order until one resolves.
 func (r *Resolver) resolveNSIPs(
 	ctx context.Context,
 	nsNames []string,
 ) []string {
 	var ips []string
 
-	for _, ns := range nsNames {
+	for _, ns := range shuffled(nsNames, rand.Shuffle) {
 		resolved, err := r.resolveARecord(ctx, ns)
 		if err == nil {
 			ips = append(ips, resolved...)

internal/resolver/iterative_test.go

@@ -1,6 +1,8 @@
 package resolver_test
 
 import (
+	"math/rand/v2"
+	"slices"
 	"testing"
 
 	"github.com/miekg/dns"
@@ -92,3 +94,30 @@ func TestExtractRecordValue_LetterCase(t *testing.T) {
 		})
 	}
 }
+
+// TestShuffled shuffles the root servers with many seeds. Every order
+// must hold each root server once, so each is tried before a
+// resolution fails; each root server must come first for some seed, so
+// no one root server gets every first query; and the list passed in
+// must be left as it was.
+func TestShuffled(t *testing.T) {
+	t.Parallel()
+
+	const seeds = 1000
+
+	roots := resolver.RootServerList()
+	before := slices.Clone(roots)
+	first := make(map[string]bool)
+
+	for seed := range uint64(seeds) {
+		rng := rand.New(rand.NewPCG(seed, 0)) //nolint:gosec // seeded on purpose
+		order := resolver.Shuffled(roots, rng.Shuffle)
+
+		assert.ElementsMatch(t, roots, order)
+
+		first[order[0]] = true
+	}
+
+	assert.Len(t, first, len(roots))
+	assert.Equal(t, before, roots)
+}