Health check answers 503 while report files cannot be written (closes #142)

The health check answered 200 "status":"ok" whatever happened, so a
container whose report files could not be written stayed healthy while
every report was refused with 500. The report buffer now says whether
its last write of a report file failed. While it has, the health
check's status is "error" and the handler answers 503 with the same
fields, which fails the image's HEALTHCHECK. At start no write has
failed, and the first write that succeeds brings back 200. A test
removes DATA_DIR to make a write fail and checks the 503, then the 200
once a write succeeds again.

Model: opus-5-5

internal/handlers/healthcheck.go

@@ -3,9 +3,17 @@ package handlers
 import "net/http"
 
 // HandleHealthCheck returns a handler for the health check
-// endpoint.
+// endpoint. It answers 200 while the status is "ok" and 503 otherwise,
+// so that the image's HEALTHCHECK fails.
 func (s *Handlers) HandleHealthCheck() http.HandlerFunc {
 	return func(w http.ResponseWriter, r *http.Request) {
-		s.respondJSON(w, r, s.hc.Healthcheck(), http.StatusOK)
+		resp := s.hc.Healthcheck()
+
+		code := http.StatusOK
+		if resp.Status != "ok" {
+			code = http.StatusServiceUnavailable
+		}
+
+		s.respondJSON(w, r, resp, code)
 	}
 }

internal/handlers/healthcheck_test.go

@@ -9,17 +9,19 @@ import (
 	"testing"
 	"time"
 
+	"sneak.berlin/go/netwatch/internal/config"
 	"sneak.berlin/go/netwatch/internal/globals"
 	"sneak.berlin/go/netwatch/internal/handlers"
 	"sneak.berlin/go/netwatch/internal/healthcheck"
 	"sneak.berlin/go/netwatch/internal/logger"
+	"sneak.berlin/go/netwatch/internal/reportbuf"
 
 	"go.uber.org/fx/fxtest"
 )
 
 // newStartedHandlers builds Handlers with a real health check for the
-// server named in g, and starts them, which records the time the
-// uptime counts from.
+// server named in g, and a report buffer in a temporary directory, and
+// starts them, which records the time the uptime counts from.
 func newStartedHandlers(t *testing.T, g *globals.Globals) *handlers.Handlers {
 	t.Helper()
 
@@ -30,14 +32,23 @@ func newStartedHandlers(t *testing.T, g *globals.Globals) *handlers.Handlers {
 		t.Fatalf("logger: %v", err)
 	}
 
+	buf, err := reportbuf.New(lc, reportbuf.Params{
+		Config: &config.Config{DataDir: t.TempDir(), DataDirMaxBytes: 1 << 20},
+		Logger: log,
+	})
+	if err != nil {
+		t.Fatalf("report buffer: %v", err)
+	}
+
 	hc, err := healthcheck.New(lc,
-		healthcheck.Params{Globals: g, Logger: log})
+		healthcheck.Params{Buffer: buf, Globals: g, Logger: log})
 	if err != nil {
 		t.Fatalf("health check: %v", err)
 	}
 
-	h, err := handlers.New(lc,
-		handlers.Params{Globals: g, Healthcheck: hc, Logger: log})
+	h, err := handlers.New(lc, handlers.Params{
+		Buffer: buf, Globals: g, Healthcheck: hc, Logger: log,
+	})
 	if err != nil {
 		t.Fatalf("handlers: %v", err)
 	}
@@ -48,10 +59,12 @@ func newStartedHandlers(t *testing.T, g *globals.Globals) *handlers.Handlers {
 	return h
 }
 
-// TestHandleHealthCheck checks the health check's answer: 200, a JSON
-// content type, and a JSON object with exactly the fields of
-// healthcheck.HealthcheckResponse, carrying this server's name and
-// version and an uptime counted from its start.
+// TestHandleHealthCheck checks the health check's answer at start, when
+// no write of a report file has failed: 200, a JSON content type, and a
+// JSON object with exactly the fields of healthcheck.HealthcheckResponse,
+// carrying "status":"ok", this server's name and version and an uptime
+// counted from its start. The answer while writes fail is checked in
+// internal/reportbuf, whose tests can make a write fail.
 func TestHandleHealthCheck(t *testing.T) {
 	t.Parallel()