tests: rename internal/livedns to livednstest and deny it outside tests (closes #164)

The live-DNS retry and concurrency limit is only for tests, but nothing
stopped program code from importing it and compiling it into the
binary. Its directory name now ends in test, and its import path is on
the test-support deny list in .golangci.yml, so make lint fails when
program code imports it. Every import and mention is updated to the new
name.

Model: opus-5-5

.golangci.yml

@@ -60,6 +60,10 @@ linters:
               desc: >-
                 Test-support code belongs in test files and in packages whose
                 directory name ends in test, not in the shipped binary.
+            - pkg: sneak.berlin/go/dnswatcher/internal/livednstest
+              desc: >-
+                Live-DNS test support belongs in test files and in packages
+                whose directory name ends in test, not in the shipped binary.
     # Only decisions already recorded in the Go package defaults are
     # listed here. Every entry matches the module path exactly.
     gomodguard_v2:

Dockerfile

@@ -41,15 +41,18 @@ RUN make build
 # alpine 3.21, 2026-02-28
 FROM alpine@sha256:c3f8e73fdb79deaebaa2037150150191b9dcbfba68b4a46d70103204c53f4709
 
-RUN apk add --no-cache ca-certificates tzdata su-exec
+RUN apk add --no-cache ca-certificates tzdata
 
 COPY --from=builder /src/bin/dnswatcher /usr/local/bin/dnswatcher
-COPY deploy/docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
 
-# dnswatcher runs as this unprivileged user. The entrypoint creates the
-# data directory and gives it to this user on every start.
+# Run as an unprivileged user that owns the data directory. A fresh named
+# volume inherits this ownership; a bind-mounted host directory must be
+# owned by uid 10001 (see "Running under upaas" in README.md), or startup
+# fails.
 RUN addgroup -S -g 10001 dnswatcher \
-    && adduser -S -G dnswatcher -u 10001 dnswatcher
+    && adduser -S -G dnswatcher -u 10001 dnswatcher \
+    && mkdir -p /var/lib/dnswatcher \
+    && chown dnswatcher:dnswatcher /var/lib/dnswatcher
 
 ENV DNSWATCHER_DATA_DIR=/var/lib/dnswatcher
 
@@ -59,8 +62,7 @@ ENV DNSWATCHER_DATA_DIR=/var/lib/dnswatcher
 # data directory, or the binary's directory, the working directory.
 WORKDIR /
 
-# No USER: the entrypoint must start as root to set up the data
-# directory; it then runs dnswatcher as the dnswatcher user.
+USER dnswatcher
 
 EXPOSE 8080
 
@@ -70,4 +72,4 @@ EXPOSE 8080
 HEALTHCHECK --interval=10s --timeout=5s --start-period=10s --retries=3 \
     CMD wget -q -O /dev/null "http://127.0.0.1:${PORT:-8080}/.well-known/healthcheck" || exit 1
 
-ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]
+ENTRYPOINT ["/usr/local/bin/dnswatcher"]

README.md

@@ -278,7 +278,7 @@ internal/
   tlscheck/tlscheck.go        TLS certificate inspector
   notify/notify.go             Notification service (Slack, Mattermost, ntfy)
   watcher/watcher.go           Main monitoring orchestrator and scheduler
-  livedns/livedns.go           Retry and concurrency limit for tests
+  livednstest/livednstest.go   Retry and concurrency limit for tests
                                against live DNS (imported only by tests)
 ```
 
@@ -533,7 +533,17 @@ repository's `Dockerfile` and runs it. The app needs:
 - **Branch:** `prod`. `prod` is cut from `main`, and merging a `main` to
   `prod` pull request is a deploy.
 - **Volume:** one host directory mounted at `/var/lib/dnswatcher`, where
-  the state file lives.
+  the state file lives. upaas bind-mounts the host path it is given and
+  does not create it. The container runs as uid 10001 and does not start
+  unless it can write there. Create the directory before the first
+  deploy:
+
+  ```sh
+  mkdir -p /path/to/data
+  chown 10001:10001 /path/to/data
+  chmod 700 /path/to/data
+  ```
+
 - **Network and port:** the dashboard is unauthenticated and shows every
   watched name and recent alert, and upaas publishes every mapped port on
   all interfaces of the host

TESTING.md

@@ -25,7 +25,7 @@ real servers ensures the resolver works correctly in production.
 - Query timeout is calibrated to 3× maximum antipodal RTT (~300ms)
   plus processing margin
 - Root server fan-out is limited to reduce parallel query load
-- Live lookups that expect an answer go through `internal/livedns`,
+- 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

TODO.md

@@ -19,11 +19,9 @@ Rationale, Design, TODO, License, Author) if any are still missing.
 
 # Completed Steps
 
-- 2026-09-29: the image sets up its own data directory. Its entrypoint,
-  `deploy/docker-entrypoint.sh`, starts as root, creates the data directory if
-  needed, gives it and everything in it to the `dnswatcher` user with mode 700
-  on the directory, then runs dnswatcher as that user with `su-exec`. A
-  bind-mounted host directory no longer has to be chowned first (closes #166).
+- 2026-09-29: the live-DNS test package is renamed `internal/livednstest` and
+  added to the `test-support` `deny` list in `.golangci.yml`, so `make lint`
+  fails when program code imports it (closes #164).
 - 2026-09-29: `.golangci.yml` re-fetched unchanged from `sneak/prompts`. It
   replaces the deprecated `gomodguard` with `gomodguard_v2`, so `make lint` no
   longer warns about it, and turns on `depguard` with the org `test-support`
@@ -35,8 +33,8 @@ Rationale, Design, TODO, License, Author) if any are still missing.
   record and nameserver changes by preparing the saved state a check starts
   from; the resolver timeout test queries an address that never answers, and
   `NewFromLoggerWithClient`, used only by its stand-in client, is gone. The
-  live-DNS retry and concurrency limit moved to `internal/livedns`, which both
-  test packages use. `TESTING.md` states the README's rule (closes #159).
+  live-DNS retry and concurrency limit moved to `internal/livednstest`, which
+  both test packages use. `TESTING.md` states the README's rule (closes #159).
 - 2026-09-28: the inconsistency alert is sent once, on the check where two
   nameservers start to disagree or where a nameserver that disagrees first
   appears, instead of on every check while they disagree, and not again after

deploy/docker-entrypoint.sh

@@ -1,17 +0,0 @@
-#!/bin/sh
-# deploy/docker-entrypoint.sh: the Docker image's ENTRYPOINT. It runs as
-# root only to give the data directory to the dnswatcher user: a host
-# directory bind-mounted there keeps its host owner, often root, and may
-# hold a state file left by another uid, which dnswatcher could neither
-# read nor replace. dnswatcher itself always runs as the dnswatcher user.
-set -eu
-
-main() {
-    dir="${DNSWATCHER_DATA_DIR:-/var/lib/dnswatcher}"
-    mkdir -p "$dir"
-    chown -R dnswatcher:dnswatcher "$dir"
-    chmod 700 "$dir"
-    exec su-exec dnswatcher /usr/local/bin/dnswatcher "$@"
-}
-
-main "$@"

internal/livednstest/livednstest.go

@@ -1,4 +1,4 @@
-// Package livedns runs the live DNS operations of tests. Tests that
+// Package livednstest runs the live DNS operations of tests. Tests that
 // look something up in DNS query live DNS servers, never a stand-in —
 // see TESTING.md. Nothing here mocks, fakes, stubs, records or replays
 // DNS, and nothing here skips a test: it only changes *how* the live
@@ -22,7 +22,7 @@
 //     first attempt. A fault in the code under test that leaves
 //     nothing to check looks the same as live DNS not answering, and
 //     fails only after the last attempt.
-package livedns
+package livednstest
 
 import (
 	"context"

internal/livednstest/livednstest_test.go

@@ -1,4 +1,4 @@
-package livedns_test
+package livednstest_test
 
 import (
 	"context"
@@ -8,7 +8,7 @@ import (
 
 	"github.com/stretchr/testify/assert"
 
-	"sneak.berlin/go/dnswatcher/internal/livedns"
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
 )
 
 // Tests for the retry and the concurrency limit themselves. They
@@ -21,11 +21,11 @@ func TestRetryRecoversFromTransientFailure(t *testing.T) {
 
 	attempts := 0
 
-	livedns.Retry(t, "transient", func(_ context.Context) error {
+	livednstest.Retry(t, "transient", func(_ context.Context) error {
 		attempts++
 
 		if attempts < wantAttempts {
-			return livedns.ErrNoAnswer
+			return livednstest.ErrNoAnswer
 		}
 
 		return nil
@@ -37,19 +37,19 @@ func TestRetryRecoversFromTransientFailure(t *testing.T) {
 func TestRetryGivesEachAttemptADeadline(t *testing.T) {
 	t.Parallel()
 
-	livedns.Retry(t, "deadline", func(ctx context.Context) error {
+	livednstest.Retry(t, "deadline", func(ctx context.Context) error {
 		deadline, ok := ctx.Deadline()
 		assert.True(t, ok, "attempt should carry a deadline")
 
 		remaining := time.Until(deadline)
 
-		assert.LessOrEqual(t, remaining, livedns.AttemptTimeout)
+		assert.LessOrEqual(t, remaining, livednstest.AttemptTimeout)
 
 		// Lower bound too: without one this passes for a
 		// deadline far shorter than intended, which would
 		// silently turn every live attempt into an instant
 		// timeout.
-		assert.Greater(t, remaining, livedns.AttemptTimeout/2)
+		assert.Greater(t, remaining, livednstest.AttemptTimeout/2)
 
 		return nil
 	})
@@ -73,7 +73,7 @@ func TestRunBoundsConcurrency(t *testing.T) {
 		go func() {
 			defer wg.Done()
 
-			_ = livedns.Run(func(_ context.Context) error {
+			_ = livednstest.Run(func(_ context.Context) error {
 				mu.Lock()
 				inFlight++
 
@@ -97,7 +97,7 @@ func TestRunBoundsConcurrency(t *testing.T) {
 
 	assert.Positive(t, maxSeen)
 	assert.LessOrEqual(
-		t, maxSeen, livedns.Concurrency,
+		t, maxSeen, livednstest.Concurrency,
 		"live queries must stay under the package-wide gate",
 	)
 }

internal/resolver/livedns_test.go

@@ -9,7 +9,7 @@ import (
 	"strings"
 	"testing"
 
-	"sneak.berlin/go/dnswatcher/internal/livedns"
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
 	"sneak.berlin/go/dnswatcher/internal/resolver"
 )
 
@@ -20,9 +20,9 @@ import (
 // Tests that look something up in DNS query live DNS servers, never a
 // stand-in; logic that works on record data may be tested on that
 // data with no lookup (see TESTING.md). Each live operation below goes
-// through livedns.Retry, which bounds how many resolutions are in
+// through livednstest.Retry, which bounds how many resolutions are in
 // flight at once and retries an operation that got no answer (see
-// package livedns).
+// package livednstest).
 //
 // Where an assertion spans several independent nameservers, a quorum
 // is enough: a strict majority answering as expected. A server that
@@ -162,7 +162,7 @@ func liveFindAuthoritative(
 
 	var out []string
 
-	livedns.Retry(
+	livednstest.Retry(
 		t,
 		"FindAuthoritativeNameservers("+domain+")",
 		func(ctx context.Context) error {
@@ -174,7 +174,7 @@ func liveFindAuthoritative(
 			if len(ns) == 0 {
 				return fmt.Errorf(
 					"%w: %s has no nameservers",
-					livedns.ErrNoAnswer, domain,
+					livednstest.ErrNoAnswer, domain,
 				)
 			}
 
@@ -198,7 +198,7 @@ func liveLookupNS(
 
 	var out []string
 
-	livedns.Retry(
+	livednstest.Retry(
 		t,
 		"LookupNS("+domain+")",
 		func(ctx context.Context) error {
@@ -210,7 +210,7 @@ func liveLookupNS(
 			if len(ns) == 0 {
 				return fmt.Errorf(
 					"%w: %s has no nameservers",
-					livedns.ErrNoAnswer, domain,
+					livednstest.ErrNoAnswer, domain,
 				)
 			}
 
@@ -240,7 +240,7 @@ func liveQueryNameserver(
 
 	var out *resolver.NameserverResponse
 
-	livedns.Retry(
+	livednstest.Retry(
 		t,
 		what,
 		func(ctx context.Context) error {
@@ -255,7 +255,7 @@ func liveQueryNameserver(
 				resp.Status == resolver.StatusError {
 				return fmt.Errorf(
 					"%w: %s returned %s: %s",
-					livedns.ErrNoAnswer, nameserver,
+					livednstest.ErrNoAnswer, nameserver,
 					resp.Status, resp.Error,
 				)
 			}
@@ -282,7 +282,7 @@ func liveQueryAllNameservers(
 
 	var out map[string]*resolver.NameserverResponse
 
-	livedns.Retry(
+	livednstest.Retry(
 		t,
 		"QueryAllNameservers("+hostname+")",
 		func(ctx context.Context) error {
@@ -294,7 +294,7 @@ func liveQueryAllNameservers(
 			if len(results) == 0 {
 				return fmt.Errorf(
 					"%w: no nameservers queried for %s",
-					livedns.ErrNoAnswer, hostname,
+					livednstest.ErrNoAnswer, hostname,
 				)
 			}
 
@@ -327,7 +327,7 @@ func liveResolveIPs(
 
 	var out []string
 
-	livedns.Retry(
+	livednstest.Retry(
 		t,
 		"ResolveIPAddresses("+hostname+")",
 		func(ctx context.Context) error {
@@ -339,7 +339,7 @@ func liveResolveIPs(
 			if len(ips) == 0 {
 				return fmt.Errorf(
 					"%w: no addresses for %s",
-					livedns.ErrNoAnswer, hostname,
+					livednstest.ErrNoAnswer, hostname,
 				)
 			}
 
@@ -366,7 +366,7 @@ func liveResolveIPsAllowingEmpty(
 
 	var out []string
 
-	livedns.Retry(
+	livednstest.Retry(
 		t,
 		"ResolveIPAddresses("+hostname+")",
 		func(ctx context.Context) error {

internal/resolver/resolver_test.go

@@ -33,7 +33,7 @@ func newTestResolver(t *testing.T) *resolver.Resolver {
 
 // findOneNSForDomain picks one authoritative nameserver to aim a
 // test at. Quorum handling lives in livedns_test.go, and the live-DNS
-// retry and concurrency limit in package livedns.
+// retry and concurrency limit in package livednstest.
 func findOneNSForDomain(
 	t *testing.T,
 	r *resolver.Resolver,

internal/watcher/watcher_test.go

@@ -10,7 +10,7 @@ import (
 	"time"
 
 	"sneak.berlin/go/dnswatcher/internal/config"
-	"sneak.berlin/go/dnswatcher/internal/livedns"
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
 	"sneak.berlin/go/dnswatcher/internal/portcheck"
 	"sneak.berlin/go/dnswatcher/internal/resolver"
 	"sneak.berlin/go/dnswatcher/internal/state"
@@ -195,7 +195,7 @@ func checkOnce(
 			return fmt.Errorf(
 				"%s: %w, or the watcher saved no fresh "+
 					"result for it",
-				name, livedns.ErrNoAnswer,
+				name, livednstest.ErrNoAnswer,
 			)
 		}
 	}
@@ -219,7 +219,7 @@ func runChecks(
 
 	var deps *testDeps
 
-	livedns.Retry(t, "watcher checks", func(ctx context.Context) error {
+	livednstest.Retry(t, "watcher checks", func(ctx context.Context) error {
 		var w *watcher.Watcher
 
 		w, deps = newTestWatcher(t, cfg)