|
@@ -897,24 +897,65 @@
|
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<li class="md-nav__item">
|
|
|
- <a href="#cluster-external-secret-metrics" class="md-nav__link">
|
|
|
|
|
- Cluster External Secret Metrics
|
|
|
|
|
|
|
+ <a href="#external-secret-metrics" class="md-nav__link">
|
|
|
|
|
+ External Secret Metrics
|
|
|
</a>
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
</li>
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<li class="md-nav__item">
|
|
|
- <a href="#external-secret-metrics" class="md-nav__link">
|
|
|
|
|
- External Secret Metrics
|
|
|
|
|
|
|
+ <a href="#dashboard" class="md-nav__link">
|
|
|
|
|
+ Dashboard
|
|
|
</a>
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
</li>
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<li class="md-nav__item">
|
|
|
- <a href="#cluster-secret-store-metrics" class="md-nav__link">
|
|
|
|
|
- Cluster Secret Store Metrics
|
|
|
|
|
|
|
+ <a href="#service-level-indicators-and-alerts" class="md-nav__link">
|
|
|
|
|
+ Service Level Indicators and Alerts
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+ <nav class="md-nav" aria-label="Service Level Indicators and Alerts">
|
|
|
|
|
+ <ul class="md-nav__list">
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#webhook-http-status-codes" class="md-nav__link">
|
|
|
|
|
+ Webhook HTTP Status Codes
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#webhook-http-request-latency" class="md-nav__link">
|
|
|
|
|
+ Webhook HTTP Request Latency
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#controller-workqueue-depth" class="md-nav__link">
|
|
|
|
|
+ Controller Workqueue Depth
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#controller-reconcile-latency" class="md-nav__link">
|
|
|
|
|
+ Controller Reconcile Latency
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#controller-reconcile-error" class="md-nav__link">
|
|
|
|
|
+ Controller Reconcile Error
|
|
|
</a>
|
|
</a>
|
|
|
|
|
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ </ul>
|
|
|
|
|
+ </nav>
|
|
|
|
|
+
|
|
|
</li>
|
|
</li>
|
|
|
|
|
|
|
|
</ul>
|
|
</ul>
|
|
@@ -2124,24 +2165,65 @@
|
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<li class="md-nav__item">
|
|
|
- <a href="#cluster-external-secret-metrics" class="md-nav__link">
|
|
|
|
|
- Cluster External Secret Metrics
|
|
|
|
|
|
|
+ <a href="#external-secret-metrics" class="md-nav__link">
|
|
|
|
|
+ External Secret Metrics
|
|
|
</a>
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
</li>
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<li class="md-nav__item">
|
|
|
- <a href="#external-secret-metrics" class="md-nav__link">
|
|
|
|
|
- External Secret Metrics
|
|
|
|
|
|
|
+ <a href="#dashboard" class="md-nav__link">
|
|
|
|
|
+ Dashboard
|
|
|
</a>
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
</li>
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<li class="md-nav__item">
|
|
|
- <a href="#cluster-secret-store-metrics" class="md-nav__link">
|
|
|
|
|
- Cluster Secret Store Metrics
|
|
|
|
|
|
|
+ <a href="#service-level-indicators-and-alerts" class="md-nav__link">
|
|
|
|
|
+ Service Level Indicators and Alerts
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+ <nav class="md-nav" aria-label="Service Level Indicators and Alerts">
|
|
|
|
|
+ <ul class="md-nav__list">
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#webhook-http-status-codes" class="md-nav__link">
|
|
|
|
|
+ Webhook HTTP Status Codes
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#webhook-http-request-latency" class="md-nav__link">
|
|
|
|
|
+ Webhook HTTP Request Latency
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#controller-workqueue-depth" class="md-nav__link">
|
|
|
|
|
+ Controller Workqueue Depth
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#controller-reconcile-latency" class="md-nav__link">
|
|
|
|
|
+ Controller Reconcile Latency
|
|
|
|
|
+ </a>
|
|
|
|
|
+
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ <li class="md-nav__item">
|
|
|
|
|
+ <a href="#controller-reconcile-error" class="md-nav__link">
|
|
|
|
|
+ Controller Reconcile Error
|
|
|
</a>
|
|
</a>
|
|
|
|
|
|
|
|
|
|
+</li>
|
|
|
|
|
+
|
|
|
|
|
+ </ul>
|
|
|
|
|
+ </nav>
|
|
|
|
|
+
|
|
|
</li>
|
|
</li>
|
|
|
|
|
|
|
|
</ul>
|
|
</ul>
|
|
@@ -2165,29 +2247,7 @@
|
|
|
<h1 id="metrics">Metrics</h1>
|
|
<h1 id="metrics">Metrics</h1>
|
|
|
<p>The External Secrets Operator exposes its Prometheus metrics in the <code>/metrics</code> path. To enable it, set the <code>serviceMonitor.enabled</code> Helm flag to <code>true</code>. In addition you can also set <code>webhook.serviceMonitor.enabled=true</code> and <code>certController.serviceMonitor.enabled=true</code> to create <code>ServiceMonitor</code> resources for the other components.</p>
|
|
<p>The External Secrets Operator exposes its Prometheus metrics in the <code>/metrics</code> path. To enable it, set the <code>serviceMonitor.enabled</code> Helm flag to <code>true</code>. In addition you can also set <code>webhook.serviceMonitor.enabled=true</code> and <code>certController.serviceMonitor.enabled=true</code> to create <code>ServiceMonitor</code> resources for the other components.</p>
|
|
|
<p>If you are using a different monitoring tool that also needs a <code>/metrics</code> endpoint, you can set the <code>metrics.service.enabled</code> Helm flag to <code>true</code>. In addition you can also set <code>webhook.metrics.service.enabled</code> and <code>certController.metrics.service.enabled</code> to scrape the other components.</p>
|
|
<p>If you are using a different monitoring tool that also needs a <code>/metrics</code> endpoint, you can set the <code>metrics.service.enabled</code> Helm flag to <code>true</code>. In addition you can also set <code>webhook.metrics.service.enabled</code> and <code>certController.metrics.service.enabled</code> to scrape the other components.</p>
|
|
|
-<p>The Operator has <a href="https://book.kubebuilder.io/reference/metrics-reference.html">the controller-runtime metrics inherited from kubebuilder</a> plus some custom metrics with a resource name prefix, such as <code>externalsecret_</code>.</p>
|
|
|
|
|
-<h2 id="cluster-external-secret-metrics">Cluster External Secret Metrics</h2>
|
|
|
|
|
-<table>
|
|
|
|
|
-<thead>
|
|
|
|
|
-<tr>
|
|
|
|
|
-<th>Name</th>
|
|
|
|
|
-<th>Type</th>
|
|
|
|
|
-<th>Description</th>
|
|
|
|
|
-</tr>
|
|
|
|
|
-</thead>
|
|
|
|
|
-<tbody>
|
|
|
|
|
-<tr>
|
|
|
|
|
-<td><code>clusterexternalsecret_status_condition</code></td>
|
|
|
|
|
-<td>Gauge</td>
|
|
|
|
|
-<td>The status condition of a specific Cluster External Secret</td>
|
|
|
|
|
-</tr>
|
|
|
|
|
-<tr>
|
|
|
|
|
-<td><code>clusterexternalsecret_reconcile_duration</code></td>
|
|
|
|
|
-<td>Gauge</td>
|
|
|
|
|
-<td>The duration time to reconcile the Cluster External Secret</td>
|
|
|
|
|
-</tr>
|
|
|
|
|
-</tbody>
|
|
|
|
|
-</table>
|
|
|
|
|
|
|
+<p>The Operator has the metrics inherited from Kubebuilder plus some custom metrics with the <code>externalsecret</code> prefix.</p>
|
|
|
<h2 id="external-secret-metrics">External Secret Metrics</h2>
|
|
<h2 id="external-secret-metrics">External Secret Metrics</h2>
|
|
|
<table>
|
|
<table>
|
|
|
<thead>
|
|
<thead>
|
|
@@ -2223,54 +2283,38 @@
|
|
|
<td>Gauge</td>
|
|
<td>Gauge</td>
|
|
|
<td>The duration time to reconcile the External Secret</td>
|
|
<td>The duration time to reconcile the External Secret</td>
|
|
|
</tr>
|
|
</tr>
|
|
|
-</tbody>
|
|
|
|
|
-</table>
|
|
|
|
|
-<h2 id="cluster-secret-store-metrics">Cluster Secret Store Metrics</h2>
|
|
|
|
|
-<table>
|
|
|
|
|
-<thead>
|
|
|
|
|
<tr>
|
|
<tr>
|
|
|
-<th>Name</th>
|
|
|
|
|
-<th>Type</th>
|
|
|
|
|
-<th>Description</th>
|
|
|
|
|
|
|
+<td><code>controller_runtime_reconcile_total</code></td>
|
|
|
|
|
+<td>Counter</td>
|
|
|
|
|
+<td>Holds the totalnumber of reconciliations per controller. It has two labels. controller label refers to the controller name and result label refers to the reconcile result i.e success, error, requeue, requeue_after.</td>
|
|
|
</tr>
|
|
</tr>
|
|
|
-</thead>
|
|
|
|
|
-<tbody>
|
|
|
|
|
<tr>
|
|
<tr>
|
|
|
-<td><code>clustersecretstore_status_condition</code></td>
|
|
|
|
|
-<td>Gauge</td>
|
|
|
|
|
-<td>The status condition of a specific Cluster Secret Store</td>
|
|
|
|
|
|
|
+<td><code>controller_runtime_reconcile_errors_total</code></td>
|
|
|
|
|
+<td>Counter</td>
|
|
|
|
|
+<td>Total number of reconcile errors per controller</td>
|
|
|
</tr>
|
|
</tr>
|
|
|
<tr>
|
|
<tr>
|
|
|
-<td><code>clustersecretstore_reconcile_duration</code></td>
|
|
|
|
|
-<td>Gauge</td>
|
|
|
|
|
-<td>The duration time to reconcile the Cluster Secret Store</td>
|
|
|
|
|
|
|
+<td><code>controller_runtime_reconcile_time_seconds</code></td>
|
|
|
|
|
+<td>Histogram</td>
|
|
|
|
|
+<td>Length of time per reconcile per controller</td>
|
|
|
</tr>
|
|
</tr>
|
|
|
-</tbody>
|
|
|
|
|
-</table>
|
|
|
|
|
-<h1 id="secret-store-metrics">Secret Store Metrics</h1>
|
|
|
|
|
-<table>
|
|
|
|
|
-<thead>
|
|
|
|
|
<tr>
|
|
<tr>
|
|
|
-<th>Name</th>
|
|
|
|
|
-<th>Type</th>
|
|
|
|
|
-<th>Description</th>
|
|
|
|
|
|
|
+<td><code>controller_runtime_reconcile_queue_length</code></td>
|
|
|
|
|
+<td>Gauge</td>
|
|
|
|
|
+<td>Length of reconcile queue per controller</td>
|
|
|
</tr>
|
|
</tr>
|
|
|
-</thead>
|
|
|
|
|
-<tbody>
|
|
|
|
|
<tr>
|
|
<tr>
|
|
|
-<td><code>secretstore_status_condition</code></td>
|
|
|
|
|
|
|
+<td><code>controller_runtime_max_concurrent_reconciles</code></td>
|
|
|
<td>Gauge</td>
|
|
<td>Gauge</td>
|
|
|
-<td>The status condition of a specific Secret Store</td>
|
|
|
|
|
|
|
+<td>Maximum number of concurrent reconciles per controller</td>
|
|
|
</tr>
|
|
</tr>
|
|
|
<tr>
|
|
<tr>
|
|
|
-<td><code>secretstore_reconcile_duration</code></td>
|
|
|
|
|
|
|
+<td><code>controller_runtime_active_workers</code></td>
|
|
|
<td>Gauge</td>
|
|
<td>Gauge</td>
|
|
|
-<td>The duration time to reconcile the Secret Store</td>
|
|
|
|
|
|
|
+<td>Number of currently used workers per controller</td>
|
|
|
</tr>
|
|
</tr>
|
|
|
</tbody>
|
|
</tbody>
|
|
|
</table>
|
|
</table>
|
|
|
-<h2 id="controller-runtime-metrics">Controller Runtime Metrics</h2>
|
|
|
|
|
-<p>See <a href="https://book.kubebuilder.io/reference/metrics-reference.html">the kubebuilder documentation</a> on the default exported metrics by controller-runtime.</p>
|
|
|
|
|
<h2 id="dashboard">Dashboard</h2>
|
|
<h2 id="dashboard">Dashboard</h2>
|
|
|
<p>We provide a <a href="https://raw.githubusercontent.com/external-secrets/external-secrets/main/docs/snippets/dashboard.json">Grafana Dashboard</a> that gives you an overview of External Secrets Operator:</p>
|
|
<p>We provide a <a href="https://raw.githubusercontent.com/external-secrets/external-secrets/main/docs/snippets/dashboard.json">Grafana Dashboard</a> that gives you an overview of External Secrets Operator:</p>
|
|
|
<p><img alt="ESO Dashboard" src="../../pictures/eso-dashboard-1.png" />
|
|
<p><img alt="ESO Dashboard" src="../../pictures/eso-dashboard-1.png" />
|