README: page address, failed-check band, timestamp form, YAML keys (closes #210)

Getting Started names the address to open for `make dev` and the image,
and says `make run` serves no page. Rows, colors and controls says a
failed check is a faint red band in the graph. Reporting gives the
`timestamp` form. Settings gives an example line of the YAML file.

Model: opus-5-5

README.md

@@ -114,9 +114,6 @@ Below it, a summary line covers the WAN hosts only:
   history
 - `Checks`: the rounds run since the page loaded or the interval changed
 
-The health box and the summary take in a WAN host's result as soon as its row
-shows it.
-
 When no WAN host answers, the page checks 4 of them, picked at random, every
 half second. As soon as one answers, a new round starts.
 
@@ -350,10 +347,6 @@ The backend logs JSON to stdout, or plain text when stdout is a terminal. Each
 request is logged with its method, URL, status, client address and duration.
 Every value taken from a request is cut to 128 bytes before it is logged.
 
-The steps `fx` takes to start and stop the backend are logged at debug level, so
-they show only with `DEBUG` set. When the backend refuses a setting, its last
-log line is one error that names the setting and the reason.
-
 ## Design
 
 The repository holds the page, the backend and the image:
@@ -381,8 +374,7 @@ The page is built with Vite and Tailwind CSS v4. All its code is in
 - `HostState` and `AppState`: one host's history and status, and the whole
   page's state.
 - `measureLatency`: one check. `tick`: one round, which checks every host in
-  parallel. It draws each row as soon as its check ends, and with a WAN host's
+  parallel and draws each row as soon as its check ends.
-  row also the summary and the health box.
 - `SparklineRenderer`: the graphs. `buildUI`, `updateHostRow`, `updateSummary`
   and `updateHealthBox`: the page and its parts.
 - `Reporter`: builds and posts the reports. `buildReport` is a pure function of

cmd/netwatch-server/main_test.go

@@ -36,103 +36,16 @@ func TestMain(m *testing.M) {
 	os.Exit(m.Run())
 }
 
-// TestOutputIsJSONWithoutFxLines: off a terminal, every line the server
+// TestOutputIsJSON: off a terminal, every line the server writes from
-// writes from start to stop is JSON, and without DEBUG none of them is
+// start to stop is JSON, fx's own lines included.
-// one of fx's.
+func TestOutputIsJSON(t *testing.T) {
-func TestOutputIsJSONWithoutFxLines(t *testing.T) {
 	t.Parallel()
 
-	stdout, stderr := runServerUntilStopped(t)
-
-	requireJSONLines(t, stdout, stderr)
-
-	if !strings.Contains(stdout.String(), `"msg":"starting"`) {
-		t.Fatalf("no startup line in stdout:\n%s", stdout)
-	}
-
-	if strings.Contains(stdout.String(), `"msg":"started"`) {
-		t.Fatalf("fx line in stdout without DEBUG:\n%s", stdout)
-	}
-}
-
-// TestDebugLogsFxLines: with DEBUG set, fx's lines are logged, as
-// JSON, from the start to the signal that stops the server.
-func TestDebugLogsFxLines(t *testing.T) {
-	t.Parallel()
-
-	stdout, stderr := runServerUntilStopped(t, "DEBUG=1")
-
-	requireJSONLines(t, stdout, stderr)
-
-	for _, msg := range []string{"started", "received signal"} {
-		if !strings.Contains(stdout.String(), `"msg":"`+msg+`"`) {
-			t.Fatalf("no fx line %q in stdout with DEBUG set:\n%s",
-				msg, stdout)
-		}
-	}
-}
-
-// TestRefusedSettingIsLastLine: a setting the server refuses stops the
-// start, and the one error line logged is the last, naming the setting
-// and why, without fx's text around it.
-func TestRefusedSettingIsLastLine(t *testing.T) {
-	t.Parallel()
-
-	ctx, cancel := context.WithTimeout(t.Context(), childTimeout)
-	defer cancel()
-
-	child, stdout, stderr := startServer(ctx, t, t.TempDir(),
-		freePort(ctx, t), "REPORTS_PER_MINUTE=0")
-
-	err := child.Wait()
-	if child.ProcessState.ExitCode() != 1 {
-		t.Fatalf("server exit = %v, want exit status 1", err)
-	}
-
-	if stderr.Len() != 0 {
-		t.Fatalf("stderr = %q, want nothing", stderr)
-	}
-
-	lines := strings.Split(strings.TrimSpace(stdout.String()), "\n")
-
-	for _, line := range lines[:len(lines)-1] {
-		if strings.Contains(line, `"level":"ERROR"`) {
-			t.Fatalf("an error line before the last line:\n%s", stdout)
-		}
-	}
-
-	var last struct {
-		Level string `json:"level"`
-		Error string `json:"error"`
-	}
-
-	err = json.Unmarshal([]byte(lines[len(lines)-1]), &last)
-	if err != nil {
-		t.Fatalf("last line is not JSON: %v\n%s", err, stdout)
-	}
-
-	want := `REPORTS_PER_MINUTE "0": must be a positive whole number`
-	if last.Level != "ERROR" || last.Error != want {
-		t.Fatalf("last line has level %q, error %q; want ERROR, %q\n%s",
-			last.Level, last.Error, want, stdout)
-	}
-}
-
-// runServerUntilStopped runs main() in a child process with env added
-// to its environment, waits until it answers its health check, stops it
-// with SIGTERM and returns its stdout and stderr. It fails the test if
-// the child does not exit cleanly.
-func runServerUntilStopped(
-	t *testing.T,
-	env ...string,
-) (*bytes.Buffer, *bytes.Buffer) {
-	t.Helper()
-
 	ctx, cancel := context.WithTimeout(t.Context(), childTimeout)
 	defer cancel()
 
 	port := freePort(ctx, t)
-	child, stdout, stderr := startServer(ctx, t, t.TempDir(), port, env...)
+	child, stdout, stderr := startServer(ctx, t, t.TempDir(), port)
 
 	waitForHealthcheck(ctx, t, port)
 
@@ -159,7 +72,11 @@ func runServerUntilStopped(
 		t.Fatalf("server exit = %v, want success", err)
 	}
 
-	return stdout, stderr
+	requireJSONLines(t, stdout, stderr)
+
+	if !strings.Contains(stdout.String(), `"msg":"starting"`) {
+		t.Fatalf("no startup line in stdout:\n%s", stdout)
+	}
 }
 
 // TestMalformedConfigFileStopsTheStart: a config file the server finds
@@ -220,40 +137,9 @@ func TestRefusedSentryDSNStopsTheStart(t *testing.T) {
 	}
 }
 
-// TestPortInUseExitsWithStatus1: a server whose port is already taken
-// cannot listen, and stops with exit status 1.
-func TestPortInUseExitsWithStatus1(t *testing.T) {
-	t.Parallel()
-
-	ctx, cancel := context.WithTimeout(t.Context(), childTimeout)
-	defer cancel()
-
-	var lc net.ListenConfig
-
-	taken, err := lc.Listen(ctx, "tcp", "127.0.0.1:0")
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	defer func() { _ = taken.Close() }()
-
-	_, port, err := net.SplitHostPort(taken.Addr().String())
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	child, stdout, _ := startServer(ctx, t, t.TempDir(), port)
-
-	err = child.Wait()
-	if child.ProcessState.ExitCode() != 1 {
-		t.Fatalf("server exit = %v, want exit status 1\n%s", err, stdout)
-	}
-}
-
 // startServer runs main() in a child process listening on
 // 127.0.0.1:port, with home as its HOME and working directory and its
-// data directory in home, so it touches nothing outside home. env is
+// data directory in home, so it touches nothing outside home. Its
-// added to its environment, as NAME=value strings. Its
 // stdout and stderr go to the two buffers returned, which hold all of
 // it once child.Wait returns. The child is killed when ctx ends, and
 // killed and reaped when the test ends if nothing waited for it.
@@ -261,7 +147,6 @@ func startServer(
 	ctx context.Context,
 	t *testing.T,
 	home, port string,
-	env ...string,
 ) (*exec.Cmd, *bytes.Buffer, *bytes.Buffer) {
 	t.Helper()
 
@@ -281,7 +166,6 @@ func startServer(
 		"BIND_ADDRESS=127.0.0.1",
 		"PORT="+port,
 	)
-	child.Env = append(child.Env, env...)
 	child.Stdout = &stdout
 	child.Stderr = &stderr
 

go.mod

@@ -16,7 +16,6 @@ require (
 	github.com/prometheus/client_golang v1.24.1
 	github.com/slok/go-http-metrics v0.13.0
 	github.com/spf13/viper v1.21.0
-	go.uber.org/dig v1.19.0
 	go.uber.org/fx v1.24.0
 	golang.org/x/sys v0.47.0
 )
@@ -39,6 +38,7 @@ require (
 	github.com/spf13/pflag v1.0.10 // indirect
 	github.com/subosito/gotenv v1.6.0 // indirect
 	github.com/zeebo/xxh3 v1.0.2 // indirect
+	go.uber.org/dig v1.19.0 // indirect
 	go.uber.org/multierr v1.10.0 // indirect
 	go.uber.org/zap v1.26.0 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect

internal/cli/cli.go

@@ -5,11 +5,8 @@
 package cli
 
 import (
-	"context"
 	"fmt"
 	"io"
-	"log/slog"
-	"os"
 	"os/user"
 
 	"sneak.berlin/go/netwatch/internal/config"
@@ -21,7 +18,6 @@ import (
 	"sneak.berlin/go/netwatch/internal/reportbuf"
 	"sneak.berlin/go/netwatch/internal/server"
 
-	"go.uber.org/dig"
 	"go.uber.org/fx"
 	"go.uber.org/fx/fxevent"
 )
@@ -33,17 +29,19 @@ const usageExitCode = 2
 // Main runs netwatch-server with args, its command line after the
 // program's name, and returns the exit code. With no args, Main runs
 // the server by calling serve with appname and version, the name and
-// version the server logs and reports, and returns serve's exit code.
+// version the server logs and reports. With "check-cidr CIDR" or
-// With "check-cidr CIDR" or "prepare-data-dir DATA_DIR" it runs that
+// "prepare-data-dir DATA_DIR" it runs that subcommand, which writes its
-// subcommand, which writes its errors to stderr. Any other args get a
+// errors to stderr. Any other args get a one-line usage message on
-// one-line usage message on stderr and exit code 2. main passes
+// stderr and exit code 2. main passes os.Stderr and RunServer; the
-// os.Stderr and RunServer; the tests pass a buffer and a function of
+// tests pass a buffer and a function of their own, so that no test
-// their own, so that no test starts the server.
+// starts the server. When serve is RunServer and the server fails to
+// start, to listen or to stop, fx's Run exits the process with status 1
+// and Main never returns.
 func Main(
 	stderr io.Writer,
 	appname, version string,
 	args []string,
-	serve func(appname, version string) int,
+	serve func(appname, version string),
 ) int {
 	// "netwatch-server check-cidr CIDR" exits 1, with the error, if
 	// this server would refuse CIDR in its TRUSTED_PROXIES.
@@ -69,7 +67,9 @@ func Main(
 		return usageExitCode
 	}
 
-	return serve(appname, version)
+	serve(appname, version)
+
+	return 0
 }
 
 // checkCIDR returns 0 if the server would take cidr in its
@@ -109,30 +109,19 @@ func prepareDataDir(stderr io.Writer, volume, dataDir, username string) int {
 }
 
 // RunServer runs the server until it is told to stop, with appname and
-// version as the name and version it logs and reports, and returns the
+// version as the name and version it logs and reports. If the server
-// exit code. If the server fails to start, to listen or to stop, it
+// fails to start, to listen or to stop, fx's Run exits the process
-// returns 1. A failed start logs one line with the error's cause, such
+// with status 1 itself.
-// as the setting refused and why, as the server's last line.
+func RunServer(appname, version string) {
-func RunServer(appname, version string) int {
 	globals.Appname = appname
 	globals.Version = version
 
-	var (
+	fx.New(
-		log   *logger.Logger
+		// fx logs each step of starting and stopping through the
-		fxLog *fxevent.SlogLogger
+		// server's own logger, so off a terminal those lines are
-	)
+		// JSON like every other line.
-
-	app := fx.New(
-		// fx logs each step of starting and stopping, errors included,
-		// at debug level through the server's own logger: they show
-		// only with DEBUG set, and off a terminal they are JSON like
-		// every other line.
 		fx.WithLogger(func(log *logger.Logger) fxevent.Logger {
-			fxLog = &fxevent.SlogLogger{Logger: log.Get()}
+			return &fxevent.SlogLogger{Logger: log.Get()}
-			fxLog.UseLogLevel(slog.LevelDebug)
-			fxLog.UseErrorLevel(slog.LevelDebug)
-
-			return fxLog
 		}),
 		fx.Provide(
 			config.New,
@@ -144,51 +133,11 @@ func RunServer(appname, version string) int {
 			reportbuf.New,
 			server.New,
 		),
-		// First, so that log is set for the error below even when a
-		// setting stops the start.
-		fx.Populate(&log),
 		fx.Invoke(
-			// Before the server, so that the name and version are
+			// First, so the name and version are logged even when
-			// logged even when a setting stops the start.
+			// a setting stops the start.
 			func(log *logger.Logger) { log.Identify() },
 			func(*server.Server) {},
 		),
-	)
+	).Run()
-
-	startCtx, cancelStart := context.WithTimeout(
-		context.Background(), app.StartTimeout())
-	defer cancelStart()
-
-	err := app.Start(startCtx)
-	if err != nil {
-		// fx wraps a constructor's error in its own text; the cause
-		// alone names the setting. log is nil only if fx failed
-		// before it built the logger.
-		cause := dig.RootCause(err)
-		if log == nil {
-			_, _ = fmt.Fprintln(os.Stderr, cause)
-		} else {
-			log.Get().Error("cannot start", "error", cause)
-		}
-
-		return 1
-	}
-
-	// A signal, or the server asking to stop after a listen error.
-	// fx's Run logs the signal here, so this does too.
-	shutdown := <-app.Wait()
-	fxLog.LogEvent(&fxevent.Stopping{Signal: shutdown.Signal})
-
-	stopCtx, cancelStop := context.WithTimeout(
-		context.Background(), app.StopTimeout())
-	defer cancelStop()
-
-	err = app.Stop(stopCtx)
-	if err != nil {
-		log.Get().Error("cannot stop cleanly", "error", err)
-
-		return 1
-	}
-
-	return shutdown.ExitCode
 }

internal/cli/cli_test.go

@@ -63,7 +63,7 @@ func TestMainRunsPrepareDataDir(t *testing.T) {
 
 // TestMainRunsServerWithNoArguments: Main given no arguments starts the
 // server with the name and version it was given, writes nothing and
-// returns the server's exit code.
+// returns 0.
 func TestMainRunsServerWithNoArguments(t *testing.T) {
 	t.Parallel()
 
@@ -73,13 +73,11 @@ func TestMainRunsServerWithNoArguments(t *testing.T) {
 	)
 
 	code := cli.Main(&stderr, "netwatch", "test", []string{},
-		func(appname, version string) int {
+		func(appname, version string) {
 			gotAppname, gotVersion = appname, version
-
-			return 3
 		})
-	if code != 3 || stderr.Len() != 0 {
+	if code != 0 || stderr.Len() != 0 {
-		t.Errorf("exit %d, stderr %q; want exit 3 and no output",
+		t.Errorf("exit %d, stderr %q; want exit 0 and no output",
 			code, stderr.String())
 	}
 
@@ -212,12 +210,10 @@ func currentUsername(t *testing.T) string {
 
 // failIfServerStarts is what the tests give Main in place of
 // cli.RunServer: it fails the test instead of starting the server.
-func failIfServerStarts(t *testing.T) func(appname, version string) int {
+func failIfServerStarts(t *testing.T) func(appname, version string) {
 	t.Helper()
 
-	return func(string, string) int {
+	return func(string, string) {
 		t.Error("Main started the server")
-
-		return 0
 	}
 }

test/unit/main.test.js

@@ -868,88 +868,6 @@ test("once every WAN target's check has failed, the summary's Reachable slot rea
     assert.equal(elements["#summary-reachable"].className, "text-red-400");
 });
 
-// The network has just come back: every WAN target's last check failed, so
-// the health box reads OFFLINE. In this round every WAN target but one
-// answers after 10ms, and the one never answers. Each element of the summary
-// and the health box is a plain object, as in the tests above; the debug
-// log's panel is not there.
-test("at a 30000ms interval, the summary and the health box take in each WAN target's answer while another WAN target's check is still waiting", async (t) => {
-    CONFIG.updateInterval = 30000;
-    t.mock.method(globalThis.document, "getElementById", (id) =>
-        id.startsWith("summary-") || id.startsWith("health-")
-            ? (elements[`#${id}`] ??= {})
-            : null,
-    );
-    const state = new AppState([]);
-    for (const host of state.wan) {
-        host.pushSample(Date.now(), { latency: null, error: "timeout" });
-    }
-    const silent = state.wan[0];
-    mockTargets(t, (url) => (url === silent.url ? Infinity : 10));
-    // The third tick, as in the tests above.
-    state.tickCount = 2;
-
-    const round = tick(state, new AbortController().signal);
-    t.mock.timers.tick(10);
-    assert.equal(await settled(round), "still waiting");
-    assert.equal(elements["#health-text"].textContent, "HEALTHY");
-    assert.equal(
-        elements["#summary-reachable"].textContent,
-        `${state.wan.length - 1}/${state.wan.length}`,
-    );
-    assert.equal(elements["#summary-max"].textContent, "10");
-    // Checks counts finished rounds only.
-    assert.equal(elements["#summary-checks"].textContent, 2);
-
-    t.mock.timers.tick(CONFIG.requestTimeout - 10);
-    assert.notEqual(await settled(round), "still waiting");
-    assert.equal(elements["#summary-checks"].textContent, 3);
-});
-
-// The user pauses during the first recorded round after the page loads.
-// Every WAN target's check ends during the pause. Silent never answers, and
-// the user resumes before its check times out. Every element the page looks
-// up by id is a plain object, except the debug log's panel, which is not
-// there.
-test(`at a 30000ms interval, after the user pauses and resumes during a round that records no WAN target's check, the debug log has no "Health:" line`, async (t) => {
-    CONFIG.updateInterval = 30000;
-    t.mock.method(globalThis.document, "getElementById", (id) =>
-        id === "debug-panel" ? null : (elements[`#${id}`] ??= {}),
-    );
-    t.mock.method(log, "notice");
-    t.mock.method(log, "warning");
-    const state = new AppState([
-        { name: "Silent", url: "https://silent.test" },
-    ]);
-    const silent = state.local[0];
-    mockTargets(t, (url) => (url === silent.url ? Infinity : 10));
-    // The second tick: the first that is recorded.
-    state.tickCount = 1;
-
-    const round = tick(state, new AbortController().signal);
-    // The user pauses, which greys out the summary and the health box, as
-    // togglePause does.
-    state.paused = true;
-    greyOutUI(state);
-    t.mock.timers.tick(10);
-    assert.equal(await settled(round), "still waiting");
-    // The user resumes, which leaves the page as it is.
-    state.paused = false;
-
-    t.mock.timers.tick(CONFIG.requestTimeout - 10);
-    assert.notEqual(await settled(round), "still waiting");
-    assert.equal(state.tickCount, 2);
-    const lines = [...log.notice.mock.calls, ...log.warning.mock.calls].map(
-        (call) => call.arguments[0],
-    );
-    assert.deepEqual(
-        lines.filter((line) => line.startsWith("Health:")),
-        [],
-    );
-    assert.equal(elements["#health-text"].textContent, "---");
-    assert.equal(elements["#summary-reachable"].textContent, "--/--");
-});
-
 // In the next two tests each of the header's clocks is a plain object, made
 // the first time updateClocks looks it up and kept in elements under "#" and
 // its id.

web/src/main.js

@@ -924,7 +924,7 @@ export function buildUI(state) {
       </div>
 
       <footer class="mt-8 text-center text-gray-600 text-xs">
-        <p>Latency: the time until a target's response headers arrive</p>
+        <p>Latency measured via GET requests | CORS restrictions may affect some measurements</p>
         <p class="mt-2">
           <span class="inline-block w-3 h-3 rounded-full bg-green-500 mr-1 align-middle"></span>&lt;50ms
           <span class="inline-block w-3 h-3 rounded-full bg-lime-500 mr-1 ml-3 align-middle"></span>&lt;100ms
@@ -1128,6 +1128,11 @@ function updateHealthBox(state) {
     el.textContent = labels[health];
     el.className = textColors[health];
     box.className = `mt-4 p-3 rounded-lg border font-mono text-sm text-center ${boxColors[health]}`;
+
+    if (health === "offline" || health === "degraded")
+        log.warning(`Health: ${labels[health]}`);
+    else if (health === "slow") log.warning(`Health: ${labels[health]}`);
+    else if (health === "healthy") log.notice(`Health: ${labels[health]}`);
 }
 
 // Writes the local time, with its time zone's name, and the UTC time into
@@ -1298,13 +1303,12 @@ export async function tick(state, signal, onOffline) {
 
     log.debug(`Tick #${state.tickCount + 1} started`);
 
-    // Each host's row shows its result as soon as its check ends, and a WAN
+    // Each host's row shows its result as soon as its check ends. The
-    // host's result goes into the summary and the health box at the same
+    // result is discarded if by then the user has paused or the next round
-    // time. The result is discarded if by then the user has paused or the
+    // has given up this one's checks, and in the first tick (tickCount is
-    // next round has given up this one's checks, and in the first tick
+    // still 0), which is discarded as a whole below. The row is looked up
-    // (tickCount is still 0), which is discarded as a whole below. The row
+    // when the check ends, as a pin click may have re-sorted the rows since
-    // is looked up when the check ends, as a pin click may have re-sorted
+    // the round started.
-    // the rows since the round started.
     await Promise.all(
         state.allHosts.map(async (host) => {
             const r = await measureLatency(host.url, signal, host.method);
@@ -1314,10 +1318,6 @@ export async function tick(state, signal, onOffline) {
             logCheck(host, r);
             host.pushSample(ts, r);
             updateHostRow(host, state.allHosts.indexOf(host));
-            if (state.wan.includes(host)) {
-                updateSummary(state);
-                updateHealthBox(state);
-            }
             log.debug(`${host.name}: ${r.error ? r.error : r.latency + "ms"}`);
         }),
     );
@@ -1344,19 +1344,9 @@ export async function tick(state, signal, onOffline) {
         sortAndRebuildWAN(state);
     }
 
-    // Redraw the summary and the health box: a pause greys them out too, and
-    // Checks now counts this round.
     updateSummary(state);
     updateHealthBox(state);
 
-    // Like the health box, the log gives no health until a WAN host's check
-    // is recorded: a pause may have discarded every WAN check so far.
-    if (state.wan.some((h) => h.status !== "pending")) {
-        const health = state.healthStatus();
-        if (health === "healthy") log.notice("Health: HEALTHY");
-        else log.warning(`Health: ${health.toUpperCase()}`);
-    }
-
     const reachable = state.allHosts.filter(
         (h) => h.status === "online",
     ).length;