resolver: a query cut short by the caller's context records no reason (closes #298)

When the caller's context ends, the next query returns
ErrContextCanceled before anything is sent. querySingleType recorded
that as a network error, which outranks a timeout, so a nameserver that
had only timed out could be reported as "network error: context
canceled". It now records no reason for it.

A try the context's deadline cuts short ends as a timeout. When the
context has ended before a further try, tryExchange now returns that
try's error instead of ErrContextCanceled, so such a nameserver is
reported as timed out, not as answering.

Model: opus-5-5

TESTING.md

@@ -19,16 +19,18 @@ 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 60-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
+- Test duration depends on network conditions. `make test` must finish in under
+  60 seconds, the hard cap in `REPO_POLICIES.md`; under 20 seconds is the target
+- Each query to a nameserver has a 2-second timeout, and a query over UDP that
+  gets no reply is sent once more (`queryTimeoutDuration` and `maxRetries` in
+  `internal/resolver/iterative.go`)
+- In the walk to a name's nameservers, the servers of each zone are asked one at
+  a time in a random order, as the README's DNS Resolution Strategy describes
 - Live lookups that expect an answer go through `internal/livednstest`, which
   limits how many run at once in a test binary and retries a lookup that got
   none
-- Flaky failures from transient network issues are acceptable and should be
-  investigated as potential resolver bugs, not papered over with mocks or skip
+- A flaky live test is a robustness problem, fixed with retries with backoff,
+  several independent nameservers or longer timeouts, never with mocks or skip
   flags
 
 ### What NOT to do

TODO.md

@@ -19,6 +19,17 @@ milestone: https://git.eeqj.de/sneak/dnswatcher/milestone/7
 
 # Completed Steps
 
+- 2026-10-15: a query its caller's context ends before it is sent records no
+  reason about the nameserver, and a try the context's deadline cuts short is a
+  timeout, so a nameserver whose only failures were timeouts is `timeout`, not a
+  network error or `ok` (closes #298).
+- 2026-10-15: the resolver no longer says its query timeout grows on each try;
+  every try waits the same 2 seconds, and the unused `timeoutMultiplier` is gone
+  (closes #296).
+- 2026-10-15: `TESTING.md` Constraints give the resolver's 2-second query
+  timeout and second try, say a zone's servers are asked one at a time in a
+  random order, give the 60-second cap and 20-second target for `make test`, and
+  say a flaky live test is fixed with robustness, not with mocks (closes #289).
 - 2026-10-15: a request under `/s/` that names a directory, such as `/s/` or
   `/s/css`, answers 404 instead of a listing of its files (closes #286).
 - 2026-10-15: a notification endpoint that answers with a redirect, or any

internal/resolver/iterative.go

@@ -19,7 +19,6 @@ const (
 	queryTimeoutDuration = 2 * time.Second
 	maxRetries           = 2
 	maxDelegation        = 20
-	timeoutMultiplier    = 2
 
 	// maxLookupDepth is how many lookups of nameserver addresses may be
 	// under way one inside another. Looking up a nameserver's address
@@ -62,19 +61,11 @@ func checkCtx(ctx context.Context) error {
 	return nil
 }
 
-func (r *Resolver) exchangeWithTimeout(
-	ctx context.Context,
-	msg *dns.Msg,
-	addr string,
-	attempt int,
-) (*dns.Msg, error) {
-	_ = attempt // timeout escalation handled by client config
-
-	resp, _, err := r.client.ExchangeContext(ctx, msg, addr)
-
-	return resp, err
-}
-
+// tryExchange sends msg to addr over UDP, up to maxRetries times, until
+// a reply comes. Every try waits the same queryTimeoutDuration, or less
+// when ctx's deadline comes first. When ctx has ended before a further
+// try, it returns the error of the try already made, such as a timeout,
+// or ErrContextCanceled when none was made.
 func (r *Resolver) tryExchange(
 	ctx context.Context,
 	msg *dns.Msg,
@@ -84,14 +75,16 @@ func (r *Resolver) tryExchange(
 
 	var err error
 
-	for attempt := range maxRetries {
+	for range maxRetries {
 		if checkCtx(ctx) != nil {
-			return nil, ErrContextCanceled
+			if err == nil {
+				return nil, ErrContextCanceled
+			}
+
+			return nil, err
 		}
 
-		resp, err = r.exchangeWithTimeout(
-			ctx, msg, addr, attempt,
-		)
+		resp, _, err = r.client.ExchangeContext(ctx, msg, addr)
 		if err == nil {
 			break
 		}
@@ -877,6 +870,10 @@ func (r *Resolver) querySingleType(
 			if err != nil {
 				err = fmt.Errorf("query %s @%s: %w", hostname, nsIP, err)
 			}
+		case errors.Is(err, ErrContextCanceled):
+			// The caller's context ended before the query was sent.
+			// That says nothing about the nameserver, so no reason is
+			// recorded.
 		case isTimeout(err):
 			state.gotTimeout = true
 		case errors.Is(err, ErrRefused):

internal/resolver/iterative_internal_test.go

@@ -1,6 +1,8 @@
 package resolver
 
 import (
+	"context"
+	"log/slog"
 	"strconv"
 	"syscall"
 	"testing"
@@ -132,3 +134,33 @@ func TestReadReply(t *testing.T) {
 		})
 	}
 }
+
+// TestQuerySingleType_ContextEnded asks a nameserver about one record
+// type with a context that has already ended, so no query is sent. A
+// query the context ended before it was sent says nothing about the
+// nameserver and records no reason: a nameserver whose earlier query
+// timed out is still reported as timed out, not as a network error.
+func TestQuerySingleType_ContextEnded(t *testing.T) {
+	t.Parallel()
+
+	r := NewFromLogger(slog.New(slog.DiscardHandler))
+
+	ctx, cancel := context.WithCancel(t.Context())
+	cancel()
+
+	resp := &NameserverResponse{Records: map[string][]string{}, Status: StatusOK}
+
+	// The query for an earlier record type timed out.
+	state := queryState{gotTimeout: true}
+
+	_, err := r.querySingleType(
+		ctx, []string{"192.0.2.1"}, "example.com.", dns.TypeA, resp, &state,
+	)
+	require.ErrorIs(t, err, ErrContextCanceled)
+	assert.Equal(t, queryState{gotTimeout: true}, state)
+
+	classifyResponse(resp, state)
+
+	assert.Equal(t, StatusTimeout, resp.Status)
+	assert.Equal(t, "all queries timed out", resp.Error)
+}

internal/resolver/resolver_test.go

@@ -1380,10 +1380,10 @@ func TestQueryNameserverIP_Timeout(t *testing.T) {
 	r := newTestResolver(t)
 
 	// Nothing answers at 192.0.2.1, a documentation address. The
-	// resolver tries each query twice, and the first try gives up
-	// after two seconds. A deadline that ends during the first try
-	// makes the status vary from run to run between error and
-	// timeout, so the deadline must outlast the first try.
+	// resolver tries each query twice, and each try gives up after two
+	// seconds. This deadline ends during the second try of the first
+	// record type; TestQueryNameserverIP_DeadlineDuringFirstTry covers
+	// one that ends during the first.
 	ctx, cancel := context.WithTimeout(
 		context.Background(), 3*time.Second,
 	)
@@ -1399,6 +1399,62 @@ func TestQueryNameserverIP_Timeout(t *testing.T) {
 	assert.NotEmpty(t, resp.Error)
 }
 
+// TestQueryNameserverIP_DeadlineDuringFirstTry gives a query to
+// 192.0.2.1, where nothing answers, a deadline that ends during its
+// first try. That try ends at the deadline as a timeout, so the
+// nameserver is reported as timed out, not as answering.
+func TestQueryNameserverIP_DeadlineDuringFirstTry(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	// Well under the two seconds one try waits.
+	ctx, cancel := context.WithTimeout(
+		context.Background(), 500*time.Millisecond,
+	)
+	t.Cleanup(cancel)
+
+	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)
+}
+
+// TestQueryNameserverIP_CancelDuringFirstTry cancels the context while
+// the first try of a query to 192.0.2.1, where nothing answers, waits
+// for a reply. That try's timeout is all that is learned about the
+// nameserver, so it is reported as timed out, not as answering.
+func TestQueryNameserverIP_CancelDuringFirstTry(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	// The first try starts at once and waits two seconds for a reply;
+	// the cancel comes a second in. The DNS client cuts a try short at
+	// the context's deadline but not at a cancel, so the try still
+	// waits its full two seconds and ends as a timeout a second after
+	// the cancel. By then the context has certainly ended, so no second
+	// try is made. With a deadline instead, the try ends at the moment
+	// the context does, and whether a second try is made depends on
+	// which the resolver sees first.
+	ctx, cancel := context.WithCancel(context.Background())
+	t.Cleanup(cancel)
+	time.AfterFunc(time.Second, cancel)
+
+	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)
+}
+
 // TestQueryNameserverIP_CancelledLogsNothing cancels the context while
 // a query to 192.0.2.1, where nothing answers, is waiting for a reply,
 // as shutdown does. The query was cut short, not failed, so nothing is