Release operator version: 2.10.0

wavefrontHQ · Jul 17, 2023 · df45cb7 · df45cb7
1 parent d8ad0c1
commit df45cb7
Show file tree

Hide file tree

Showing 18 changed files with 108 additions and 26 deletions.
diff --git a/README.md b/README.md
@@ -159,6 +159,8 @@ We have alerts on common Kubernetes issues. For details on creating alerts, see
 | [Pod Stuck in Pending](docs/alerts/templates/pod-stuck-in-pending.json.tmpl) | Workload has pod stuck in pending. |
 | [Pod Stuck in Terminating](docs/alerts/templates/pod-stuck-in-terminating.json.tmpl) | Workload has pod stuck in terminating. |
 | [Pod Backoff Event](docs/alerts/templates/pod-backoff-event.json.tmpl) | Workload has pod with container status `ImagePullBackOff` or `CrashLoopBackOff`. |
+| [Workload Not Ready](docs/alerts/templates/workload-not-ready.json.tmpl) | Workload has pods that are not ready. |
+| [Pod Out-of-memory Kills](docs/alerts/templates/pod-out-of-memory-kills.json.tmpl) | Workload has pod with container status `OOMKilled`. |
 
 ## Bring Your Own Logs Shipper
 

diff --git a/collector/release/NEXT_RELEASE_VERSION b/collector/release/NEXT_RELEASE_VERSION
@@ -1 +1 @@
-1.22.0
+1.23.0
diff --git a/collector/release/VERSION b/collector/release/VERSION
@@ -1 +1 @@
-1.21.0
+1.22.0
diff --git a/deploy/wavefront-operator.yaml b/deploy/wavefront-operator.yaml
@@ -1078,8 +1078,8 @@ subjects:
 ---
 apiVersion: v1
 data:
-  collector: 1.21.0
-  logging: 2.1.2
+  collector: 1.22.0
+  logging: 2.1.6
   proxy: 13.0.1
 kind: ConfigMap
 metadata:
@@ -1150,7 +1150,7 @@ spec:
             configMapKeyRef:
               key: logging
               name: wavefront-component-versions
-        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.9.0
+        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.10.0
         imagePullPolicy: Always
         livenessProbe:
           httpGet:

diff --git a/docs/alerts/alerts.md b/docs/alerts/alerts.md
@@ -6,6 +6,8 @@ We have alert templates on common Kubernetes issues.
 * [Detect pod stuck in pending](templates/pod-stuck-in-pending.json.tmpl)
 * [Detect pod stuck in terminating](templates/pod-stuck-in-terminating.json.tmpl)
 * [Detect pod backoff event](templates/pod-backoff-event.json.tmpl)
+* [Detect workload with non-ready pods](templates/workload-not-ready.json.tmpl)
+* [Detect pod out-of-memory kills](templates/pod-out-of-memory-kills.json.tmpl)
 
 ## Flags
 

diff --git a/docs/alerts/templates/pod-backoff-event.json.tmpl b/docs/alerts/templates/pod-backoff-event.json.tmpl
@@ -4,7 +4,7 @@
   "alertSources": [
     {
       "name": "Alert Condition",
-      "query": "(mcount(10m, count(ts(\"kubernetes.pod_container.status\", cluster=\"K8S_CLUSTER_NAME\" AND (reason=\"ImagePullBackOff\" OR reason=\"CrashLoopBackOff\")), sources, workload_name, pod_name, namespace_name, cluster, nodename, reason)) >= 5)",
+      "query": "(mcount(10m, count(ts(\"kubernetes.pod_container.status\", cluster=\"K8S_CLUSTER_NAME\" AND (reason=\"ImagePullBackOff\" OR reason=\"CrashLoopBackOff\")), sources, workload_name, pod_name, namespace_name, cluster, cluster_uuid, reason)) >= 5)",
       "queryType": "WQL",
       "alertSourceType": ["CONDITION"],
       "hidden": true
@@ -18,9 +18,14 @@
     }
   ],
   "conditions": {
-    "warn": "(mcount(10m, count(ts(\"kubernetes.pod_container.status\", cluster=\"K8S_CLUSTER_NAME\" AND (reason=\"ImagePullBackOff\" OR reason=\"CrashLoopBackOff\")), sources, workload_name, pod_name, namespace_name, cluster, nodename, reason)) >= 5) >= 1"
+    "warn": "(mcount(10m, count(ts(\"kubernetes.pod_container.status\", cluster=\"K8S_CLUSTER_NAME\" AND (reason=\"ImagePullBackOff\" OR reason=\"CrashLoopBackOff\")), sources, workload_name, pod_name, namespace_name, cluster, cluster_uuid, reason)) >= 5) >= 1"
   },
   "displayExpression": "${Display Condition}",
   "minutes": 10,
-  "resolveAfterMinutes": 2
+  "resolveAfterMinutes": 2,
+  "tags": {
+    "customerTags": [
+      "integration.kubernetes"
+    ]
+  }
 }
diff --git a/docs/alerts/templates/pod-out-of-memory-kills.json.tmpl b/docs/alerts/templates/pod-out-of-memory-kills.json.tmpl
@@ -0,0 +1,31 @@
+{
+  "name": "Pod Out-of-memory Kills",
+  "alertType": "THRESHOLD",
+  "alertSources": [
+    {
+      "name": "Alert Condition",
+      "query": "(mcount(15m, count(ts(\"kubernetes.pod_container.status\", cluster=\"K8S_CLUSTER_NAME\" AND reason=\"OOMKilled\"), sources, workload_name, pod_name, namespace_name, cluster, container_name, cluster_uuid, reason)) >= 2)",
+      "queryType": "WQL",
+      "alertSourceType": ["CONDITION"],
+      "hidden": true
+    },
+    {
+      "name": "Display Condition",
+      "query": "if(${Alert Condition}, ${Alert Condition})",
+      "queryType": "WQL",
+      "alertSourceType": ["VARIABLE","AUDIT"],
+      "hidden": false
+    }
+  ],
+  "conditions": {
+    "warn": "(mcount(15m, count(ts(\"kubernetes.pod_container.status\", cluster=\"K8S_CLUSTER_NAME\" AND reason=\"OOMKilled\"), sources, workload_name, pod_name, namespace_name, cluster, container_name, cluster_uuid, reason)) >= 2) >= 1"
+  },
+  "displayExpression": "${Display Condition}",
+  "minutes": 15,
+  "resolveAfterMinutes": 2,
+  "tags": {
+    "customerTags": [
+      "integration.kubernetes"
+    ]
+  }
+}
diff --git a/docs/alerts/templates/pod-stuck-in-pending.json.tmpl b/docs/alerts/templates/pod-stuck-in-pending.json.tmpl
@@ -4,7 +4,7 @@
   "alertSources": [
     {
       "name": "Alert Condition",
-      "query": "(mcount(10m, count(ts(\"kubernetes.pod.status.phase\", phase=\"Pending\" AND cluster=\"K8S_CLUSTER_NAME\"), sources, pod_name, workload_name, namespace_name, cluster, nodename, message)) >= 10)",
+      "query": "(mcount(10m, count(ts(\"kubernetes.pod.status.phase\", phase=\"Pending\" AND cluster=\"K8S_CLUSTER_NAME\"), sources, pod_name, workload_name, namespace_name, cluster, message, cluster_uuid, reason)) >= 10)",
       "queryType": "WQL",
       "alertSourceType": ["CONDITION"],
       "hidden": true
@@ -18,9 +18,14 @@
     }
   ],
   "conditions": {
-    "warn": "(mcount(10m, count(ts(\"kubernetes.pod.status.phase\", phase=\"Pending\" AND cluster=\"K8S_CLUSTER_NAME\"), sources, pod_name, workload_name, namespace_name, cluster, nodename, message)) >= 10) >= 1"
+    "warn": "(mcount(10m, count(ts(\"kubernetes.pod.status.phase\", phase=\"Pending\" AND cluster=\"K8S_CLUSTER_NAME\"), sources, pod_name, workload_name, namespace_name, cluster, message, cluster_uuid, reason)) >= 10) >= 1"
   },
   "displayExpression": "${Display Condition}",
   "minutes": 5,
-  "resolveAfterMinutes": 2
+  "resolveAfterMinutes": 2,
+  "tags": {
+    "customerTags": [
+      "integration.kubernetes"
+    ]
+  }
 }
diff --git a/docs/alerts/templates/pod-stuck-in-terminating.json.tmpl b/docs/alerts/templates/pod-stuck-in-terminating.json.tmpl
@@ -4,7 +4,7 @@
   "alertSources": [
     {
       "name": "Alert Condition",
-      "query": "(mcount(10m, count(ts(\"kubernetes.pod.terminating\", cluster=\"K8S_CLUSTER_NAME\"), sources, workload_name, pod_name, namespace_name, cluster, DeletionTimestamp)) >= 10)",
+      "query": "(mcount(10m, count(ts(\"kubernetes.pod.terminating\", cluster=\"K8S_CLUSTER_NAME\"), sources, workload_name, pod_name, namespace_name, cluster, DeletionTimestamp, cluster_uuid)) >= 10)",
       "queryType": "WQL",
       "alertSourceType": ["CONDITION"],
       "hidden": true
@@ -18,9 +18,14 @@
     }
   ],
   "conditions": {
-    "warn": "(mcount(10m, count(ts(\"kubernetes.pod.terminating\", cluster=\"K8S_CLUSTER_NAME\"), sources, workload_name, pod_name, namespace_name, cluster, DeletionTimestamp)) >= 10) >= 1"
+    "warn": "(mcount(10m, count(ts(\"kubernetes.pod.terminating\", cluster=\"K8S_CLUSTER_NAME\"), sources, workload_name, pod_name, namespace_name, cluster, DeletionTimestamp, cluster_uuid)) >= 10) >= 1"
   },
   "displayExpression": "${Display Condition}",
   "minutes": 5,
-  "resolveAfterMinutes": 2
+  "resolveAfterMinutes": 2,
+  "tags": {
+    "customerTags": [
+      "integration.kubernetes"
+    ]
+  }
 }
diff --git a/docs/alerts/templates/workload-not-ready.json.tmpl b/docs/alerts/templates/workload-not-ready.json.tmpl
@@ -0,0 +1,31 @@
+{
+  "name": "Workload Not Ready",
+  "alertType": "THRESHOLD",
+  "alertSources": [
+    {
+      "name": "Alert Condition",
+      "query": "(msum(10m, sum(ts(\"kubernetes.workload.status\", cluster=\"K8S_CLUSTER_NAME\"), sources, workload_name, workload_kind, namespace_name, cluster, cluster_uuid) = 0) >= 10)",
+      "queryType": "WQL",
+      "alertSourceType": ["CONDITION"],
+      "hidden": true
+    },
+    {
+      "name": "Display Condition",
+      "query": "if(${Alert Condition}, ${Alert Condition})",
+      "queryType": "WQL",
+      "alertSourceType": ["VARIABLE","AUDIT"],
+      "hidden": false
+    }
+  ],
+  "conditions": {
+    "warn": "(msum(10m, sum(ts(\"kubernetes.workload.status\", cluster=\"K8S_CLUSTER_NAME\"), sources, workload_name, workload_kind, namespace_name, cluster, cluster_uuid) = 0) >= 10) >= 1"
+  },
+  "displayExpression": "${Display Condition}",
+  "minutes": 5,
+  "resolveAfterMinutes": 2,
+  "tags": {
+    "customerTags": [
+      "integration.kubernetes"
+    ]
+  }
+}
diff --git a/docs/collector/metrics.md b/docs/collector/metrics.md
@@ -129,6 +129,7 @@ These are cluster level metrics about the state of Kubernetes objects collected
 | PersistentVolume        | pv.info                                  | Information about PersistentVolume.                                                                             |
 | PersistentVolume        | pv.access_mode                           | The access mode(s) specified by the PersistentVolume.                                                           |
 | Pod                     | pod.terminating                          | A Pod is in the process of terminating.                                                                         |
+| Workload                | workload.status                          | Status of workload pod(s).                                                                                      |
 
 ## Prometheus Source
 

diff --git a/docs/operator/custom-configuration.md b/docs/operator/custom-configuration.md
@@ -9,10 +9,10 @@ Install the Observability for Kubernetes Operator into `observability-system` na
 
 | Component | From | To |
 |---|---|---|
-| Observability for Kubernetes Operator | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.9.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.9.0` |
-| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.21.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.21.0` |
+| Observability for Kubernetes Operator | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.10.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.10.0` |
+| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.22.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.22.0` |
 | Wavefront Proxy | `projects.registry.vmware.com/tanzu_observability/proxy:13.0.1` | `YOUR_IMAGE_REGISTRY/proxy:13.0.1` |
-| Operations for Applications logging | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator-fluentbit:2.1.2` | `YOUR_IMAGE_REGISTRY/kubernetes-operator-fluentbit:2.1.2` |
+| Operations for Applications logging | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator-fluentbit:2.1.6` | `YOUR_IMAGE_REGISTRY/kubernetes-operator-fluentbit:2.1.6` |
 
 2. Create a local directory called `observability`.
 3. Download [wavefront-operator.yaml](https://raw.githubusercontent.com/wavefrontHQ/observability-for-kubernetes/main/deploy/wavefront-operator.yaml) into the `observability` directory.

diff --git a/operator/config/manager/component_versions.yaml b/operator/config/manager/component_versions.yaml
@@ -7,6 +7,6 @@ metadata:
   name: component-versions
   namespace: system
 data:
-  collector: "1.21.0"
+  collector: "1.22.0"
   logging: "2.1.6"
   proxy: "13.0.1"
diff --git a/operator/config/manager/kustomization.yaml b/operator/config/manager/kustomization.yaml
@@ -15,7 +15,7 @@ kind: Kustomization
 images:
 - name: controller
   newName: projects.registry.vmware.com/tanzu_observability/kubernetes-operator
-  newTag: 2.9.0
+  newTag: 2.10.0
 
 patches:
 - path: patches.yaml

diff --git a/operator/dev-internal/deploy/wavefront-operator.yaml b/operator/dev-internal/deploy/wavefront-operator.yaml
@@ -1078,8 +1078,8 @@ subjects:
 ---
 apiVersion: v1
 data:
-  collector: 1.21.0
-  logging: 2.1.2
+  collector: 1.22.0
+  logging: 2.1.6
   proxy: 13.0.1
 kind: ConfigMap
 metadata:
@@ -1150,7 +1150,7 @@ spec:
             configMapKeyRef:
               key: logging
               name: wavefront-component-versions
-        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.9.0
+        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.10.0
         imagePullPolicy: Always
         livenessProbe:
           httpGet:

diff --git a/operator/dev-internal/docs/operator/custom-configuration.md b/operator/dev-internal/docs/operator/custom-configuration.md
@@ -9,8 +9,8 @@ Install the Observability for Kubernetes Operator into `observability-system` na
 
 | Component | From | To |
 |---|---|---|
-| Observability for Kubernetes Operator | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.9.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.9.0` |
-| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.21.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.21.0` |
+| Observability for Kubernetes Operator | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.10.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.10.0` |
+| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.22.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.22.0` |
 | Wavefront Proxy | `projects.registry.vmware.com/tanzu_observability/proxy:13.0.1` | `YOUR_IMAGE_REGISTRY/proxy:13.0.1` |
 | Operations for Applications logging | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator-fluentbit:2.1.6` | `YOUR_IMAGE_REGISTRY/kubernetes-operator-fluentbit:2.1.6` |
 

diff --git a/operator/release/NEXT_RELEASE_VERSION b/operator/release/NEXT_RELEASE_VERSION
@@ -1 +1 @@
-2.10.0
+2.11.0
diff --git a/operator/release/OPERATOR_VERSION b/operator/release/OPERATOR_VERSION
@@ -1 +1 @@
-2.9.0
+2.10.0