Add configurable file-existence and HTTP health checks

Add a section to the config file called "health". Within this section,
"filecheckers" and "httpcheckers" list checks to run. Each check
specifies a file or URI, a time interval for the check, and a threshold
specifying how many times the check must fail to reach an unhealthy
state.

Document the new options in docs/configuration.md.

Add unit testing for both types of checkers. Add an UnregisterAll
function in the health package to support the unit tests, and an
Unregister function for consistency with Register.

Fix a string conversion problem in the health package's HTTP checker.

Signed-off-by: Aaron Lehmann <aaron.lehmann@docker.com>

docs/handlers/app.go

@@ -15,6 +15,7 @@ import (
 	"github.com/docker/distribution/configuration"
 	ctxu "github.com/docker/distribution/context"
 	"github.com/docker/distribution/health"
+	"github.com/docker/distribution/health/checks"
 	"github.com/docker/distribution/notifications"
 	"github.com/docker/distribution/registry/api/errcode"
 	"github.com/docker/distribution/registry/api/v2"
@@ -37,6 +38,9 @@ import (
 // was specified.
 const randomSecretSize = 32
 
+// defaultCheckInterval is the default time in between health checks
+const defaultCheckInterval = 10 * time.Second
+
 // App is a global registry application object. Shared resources can be placed
 // on this object that will be accessible from all requests. Any writable
 // fields should be protected.
@@ -231,10 +235,38 @@ func NewApp(ctx context.Context, configuration configuration.Configuration) *App
 // implementing this properly will require a refactor. This method may panic
 // if called twice in the same process.
 func (app *App) RegisterHealthChecks() {
-	health.RegisterPeriodicThresholdFunc("storagedriver_"+app.Config.Storage.Type(), 10*time.Second, 3, func() error {
+	health.RegisterPeriodicThresholdFunc("storagedriver_"+app.Config.Storage.Type(), defaultCheckInterval, 3, func() error {
 		_, err := app.driver.List(app, "/") // "/" should always exist
 		return err                          // any error will be treated as failure
 	})
+
+	for _, fileChecker := range app.Config.Health.FileCheckers {
+		interval := fileChecker.Interval
+		if interval == 0 {
+			interval = defaultCheckInterval
+		}
+		if fileChecker.Threshold != 0 {
+			ctxu.GetLogger(app).Infof("configuring file health check path=%s, interval=%d, threshold=%d", fileChecker.File, interval/time.Second, fileChecker.Threshold)
+			health.Register(fileChecker.File, health.PeriodicThresholdChecker(checks.FileChecker(fileChecker.File), interval, fileChecker.Threshold))
+		} else {
+			ctxu.GetLogger(app).Infof("configuring file health check path=%s, interval=%d", fileChecker.File, interval/time.Second)
+			health.Register(fileChecker.File, health.PeriodicChecker(checks.FileChecker(fileChecker.File), interval))
+		}
+	}
+
+	for _, httpChecker := range app.Config.Health.HTTPCheckers {
+		interval := httpChecker.Interval
+		if interval == 0 {
+			interval = defaultCheckInterval
+		}
+		if httpChecker.Threshold != 0 {
+			ctxu.GetLogger(app).Infof("configuring HTTP health check uri=%s, interval=%d, threshold=%d", httpChecker.URI, interval/time.Second, httpChecker.Threshold)
+			health.Register(httpChecker.URI, health.PeriodicThresholdChecker(checks.HTTPChecker(httpChecker.URI), interval, httpChecker.Threshold))
+		} else {
+			ctxu.GetLogger(app).Infof("configuring HTTP health check uri=%s, interval=%d", httpChecker.URI, interval/time.Second)
+			health.Register(httpChecker.URI, health.PeriodicChecker(checks.HTTPChecker(httpChecker.URI), interval))
+		}
+	}
 }
 
 // register a handler with the application, by route name. The handler will be

docs/handlers/health_test.go

@@ -0,0 +1,200 @@
+package handlers
+
+import (
+	"encoding/json"
+	"io/ioutil"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"testing"
+	"time"
+
+	"github.com/docker/distribution/configuration"
+	"github.com/docker/distribution/health"
+	"golang.org/x/net/context"
+)
+
+func TestFileHealthCheck(t *testing.T) {
+	// In case other tests registered checks before this one
+	health.UnregisterAll()
+
+	interval := time.Second
+
+	tmpfile, err := ioutil.TempFile(os.TempDir(), "healthcheck")
+	if err != nil {
+		t.Fatalf("could not create temporary file: %v", err)
+	}
+	defer tmpfile.Close()
+
+	config := configuration.Configuration{
+		Storage: configuration.Storage{
+			"inmemory": configuration.Parameters{},
+		},
+		Health: configuration.Health{
+			FileCheckers: []configuration.FileChecker{
+				{
+					Interval: interval,
+					File:     tmpfile.Name(),
+				},
+			},
+		},
+	}
+
+	ctx := context.Background()
+
+	app := NewApp(ctx, config)
+	app.RegisterHealthChecks()
+
+	debugServer := httptest.NewServer(nil)
+
+	// Wait for health check to happen
+	<-time.After(2 * interval)
+
+	resp, err := http.Get(debugServer.URL + "/debug/health")
+	if err != nil {
+		t.Fatalf("error performing HTTP GET: %v", err)
+	}
+	body, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		t.Fatalf("error reading HTTP body: %v", err)
+	}
+	resp.Body.Close()
+	var decoded map[string]string
+	err = json.Unmarshal(body, &decoded)
+	if err != nil {
+		t.Fatalf("error unmarshaling json: %v", err)
+	}
+	if len(decoded) != 1 {
+		t.Fatal("expected 1 item in returned json")
+	}
+	if decoded[tmpfile.Name()] != "file exists" {
+		t.Fatal(`did not get "file exists" result for health check`)
+	}
+
+	os.Remove(tmpfile.Name())
+
+	<-time.After(2 * interval)
+	resp, err = http.Get(debugServer.URL + "/debug/health")
+	if err != nil {
+		t.Fatalf("error performing HTTP GET: %v", err)
+	}
+	body, err = ioutil.ReadAll(resp.Body)
+	if err != nil {
+		t.Fatalf("error reading HTTP body: %v", err)
+	}
+	resp.Body.Close()
+	var decoded2 map[string]string
+	err = json.Unmarshal(body, &decoded2)
+	if err != nil {
+		t.Fatalf("error unmarshaling json: %v", err)
+	}
+	if len(decoded2) != 0 {
+		t.Fatal("expected 0 items in returned json")
+	}
+}
+
+func TestHTTPHealthCheck(t *testing.T) {
+	// In case other tests registered checks before this one
+	health.UnregisterAll()
+
+	interval := time.Second
+	threshold := 3
+
+	stopFailing := make(chan struct{})
+
+	checkedServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.Method != "HEAD" {
+			t.Fatalf("expected HEAD request, got %s", r.Method)
+		}
+		select {
+		case <-stopFailing:
+			w.WriteHeader(http.StatusOK)
+		default:
+			w.WriteHeader(http.StatusInternalServerError)
+		}
+	}))
+
+	config := configuration.Configuration{
+		Storage: configuration.Storage{
+			"inmemory": configuration.Parameters{},
+		},
+		Health: configuration.Health{
+			HTTPCheckers: []configuration.HTTPChecker{
+				{
+					Interval:  interval,
+					URI:       checkedServer.URL,
+					Threshold: threshold,
+				},
+			},
+		},
+	}
+
+	ctx := context.Background()
+
+	app := NewApp(ctx, config)
+	app.RegisterHealthChecks()
+
+	debugServer := httptest.NewServer(nil)
+
+	for i := 0; ; i++ {
+		<-time.After(interval)
+
+		resp, err := http.Get(debugServer.URL + "/debug/health")
+		if err != nil {
+			t.Fatalf("error performing HTTP GET: %v", err)
+		}
+		body, err := ioutil.ReadAll(resp.Body)
+		if err != nil {
+			t.Fatalf("error reading HTTP body: %v", err)
+		}
+		resp.Body.Close()
+		var decoded map[string]string
+		err = json.Unmarshal(body, &decoded)
+		if err != nil {
+			t.Fatalf("error unmarshaling json: %v", err)
+		}
+
+		if i < threshold-1 {
+			// definitely shouldn't have hit the threshold yet
+			if len(decoded) != 0 {
+				t.Fatal("expected 1 items in returned json")
+			}
+			continue
+		}
+		if i < threshold+1 {
+			// right on the threshold - don't expect a failure yet
+			continue
+		}
+
+		if len(decoded) != 1 {
+			t.Fatal("expected 1 item in returned json")
+		}
+		if decoded[checkedServer.URL] != "downstream service returned unexpected status: 500" {
+			t.Fatal("did not get expected result for health check")
+		}
+
+		break
+	}
+
+	// Signal HTTP handler to start returning 200
+	close(stopFailing)
+
+	<-time.After(2 * interval)
+	resp, err := http.Get(debugServer.URL + "/debug/health")
+	if err != nil {
+		t.Fatalf("error performing HTTP GET: %v", err)
+	}
+	body, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		t.Fatalf("error reading HTTP body: %v", err)
+	}
+	resp.Body.Close()
+	var decoded map[string]string
+	err = json.Unmarshal(body, &decoded)
+	if err != nil {
+		t.Fatalf("error unmarshaling json: %v", err)
+	}
+	if len(decoded) != 0 {
+		t.Fatal("expected 0 items in returned json")
+	}
+}