Add storagedriver section to health check configuration

Add default storagedriver health check to example configuration files
with parameters matching the previous hardcoded configuration.

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

cmd/registry/config-cache.yml

@@ -48,3 +48,8 @@ proxy:
   remoteurl: https://registry-1.docker.io
   username: username
   password: password
+health:
+  storagedriver:
+    enabled: true
+    interval: 10s
+    threshold: 3

cmd/registry/config-dev.yml

@@ -59,4 +59,8 @@ notifications:
           threshold: 10
           backoff: 1s
           disabled: true 
-
+health:
+  storagedriver:
+    enabled: true
+    interval: 10s
+    threshold: 3

cmd/registry/config-example.yml

@@ -11,3 +11,8 @@ http:
     addr: :5000
     headers:
         X-Content-Type-Options: [nosniff]
+health:
+  storagedriver:
+    enabled: true
+    interval: 10s
+    threshold: 3

configuration/configuration.go

@@ -210,6 +210,17 @@ type Health struct {
 	FileCheckers []FileChecker `yaml:"file,omitempty"`
 	// HTTPChecker is a list of URIs to check
 	HTTPCheckers []HTTPChecker `yaml:"http,omitempty"`
+	// StorageDriver configures a health check on the configured storage
+	// driver
+	StorageDriver struct {
+		// Enabled turns on the health check for the storage driver
+		Enabled bool `yaml:"enabled,omitempty"`
+		// Interval is the number of seconds in between checks
+		Interval time.Duration `yaml:"interval,omitempty"`
+		// Threshold is the number of times a check must fail to trigger an
+		// unhealthy state
+		Threshold int `yaml:"threshold,omitempty"`
+	} `yaml:"storagedriver,omitempty"`
 }
 
 // v0_1Configuration is a Version 0.1 Configuration struct

docs/configuration.md

@@ -196,6 +196,10 @@ information about each option that appears later in this page.
         maxactive: 64
         idletimeout: 300s
     health:
+      storagedriver:
+        enabled: true
+        interval: 10s
+        threshold: 3
       file:
         - file: /path/to/checked/file
           interval: 10s
@@ -1600,6 +1604,10 @@ Configure the behavior of the Redis connection pool.
 ## health
 
     health:
+      storagedriver:
+        enabled: true
+        interval: 10s
+        threshold: 3
       file:
         - file: /path/to/checked/file
           interval: 10s
@@ -1609,8 +1617,72 @@ Configure the behavior of the Redis connection pool.
           interval: 10s
           threshold: 3
 
-The health option is **optional**. It may contain lists of file checkers
-and/or HTTP checkers.
+The health option is **optional**. It may contain preferences for a periodic
+health check on the storage driver's backend storage, and optional periodic
+checks on local files and/or HTTP URIs. The results of the health checks are
+available at /debug/health on the debug HTTP server if the debug HTTP server is
+enabled (see http section).
+
+### storagedriver
+
+storagedriver contains options for a health check on the configured storage
+driver's backend storage. enabled must be set to true for this health check to
+be active.
+
+<table>
+  <tr>
+    <th>Parameter</th>
+    <th>Required</th>
+    <th>Description</th>
+  </tr>
+  <tr>
+    <td>
+      <code>enabled</code>
+    </td>
+    <td>
+      yes
+    </td>
+    <td>
+"true" to enable the storage driver health check or "false" to disable it.
+</td>
+  </tr>
+  <tr>
+    <td>
+      <code>interval</code>
+    </td>
+    <td>
+      no
+    </td>
+    <td>
+      The length of time to wait between repetitions of the check. This field
+      takes a positive integer and an optional suffix indicating the unit of
+      time. Possible units are:
+      <ul>
+        <li><code>ns</code> (nanoseconds)</li>
+        <li><code>us</code> (microseconds)</li>
+        <li><code>ms</code> (milliseconds)</li>
+        <li><code>s</code> (seconds)</li>
+        <li><code>m</code> (minutes)</li>
+        <li><code>h</code> (hours)</li>
+      </ul>
+    If you omit the suffix, the system interprets the value as nanoseconds.
+    The default value is 10 seconds if this field is omitted.
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <code>threshold</code>
+    </td>
+    <td>
+      no
+    </td>
+    <td>
+      An integer specifying the number of times the check must fail before the
+      check triggers an unhealthy state. If this filed is not specified, a
+      single failure will trigger an unhealthy state.
+    </td>
+  </tr>
+</table>
 
 ### file
 

registry/handlers/app.go

@@ -235,10 +235,23 @@ 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(), defaultCheckInterval, 3, func() error {
+	if app.Config.Health.StorageDriver.Enabled {
+		interval := app.Config.Health.StorageDriver.Interval
+		if interval == 0 {
+			interval = defaultCheckInterval
+		}
+
+		storageDriverCheck := func() error {
 			_, err := app.driver.List(app, "/") // "/" should always exist
 			return err                          // any error will be treated as failure
-	})
+		}
+
+		if app.Config.Health.StorageDriver.Threshold != 0 {
+			health.RegisterPeriodicThresholdFunc("storagedriver_"+app.Config.Storage.Type(), interval, app.Config.Health.StorageDriver.Threshold, storageDriverCheck)
+		} else {
+			health.RegisterPeriodicFunc("storagedriver_"+app.Config.Storage.Type(), interval, storageDriverCheck)
+		}
+	}
 
 	for _, fileChecker := range app.Config.Health.FileCheckers {
 		interval := fileChecker.Interval