Release operator version: 2.13.0

wavefrontHQ · Sep 15, 2023 · 351e6aa · 351e6aa
1 parent 857e879
commit 351e6aa
Show file tree

Hide file tree

Showing 15 changed files with 106 additions and 175 deletions.
diff --git a/README.md b/README.md
@@ -131,7 +131,6 @@ See below for configuration options.
 We have templates for common scenarios. See the comments in each file for usage instructions.
 
  * [Using a custom private registry](deploy/scenarios/wavefront-custom-private-registry.yaml)
- * [Using an existing Collector ConfigMap](deploy/scenarios/wavefront-collector-existing-configmap.yaml)
  * [With plugin configuration in a secret](deploy/scenarios/wavefront-collector-with-plugin-secret.yaml)
  * [Filtering metrics upon collection](deploy/scenarios/wavefront-collector-filtering.yaml)
  * [Disabling control plane metrics](deploy/scenarios/wavefront-disable-control-plane-metrics.yaml)
@@ -145,7 +144,6 @@ We have templates for common scenarios. See the comments in each file for usage
  * [Getting started with logging configuration](deploy/scenarios/wavefront-logging-getting-started.yaml)
  * [Full logging configuration](deploy/scenarios/wavefront-logging-full-config.yaml)
  * [Bring your own logs shipper](deploy/scenarios/wavefront-bring-your-own-logs-shipper.yaml)
- * [Enabling autotracing support](deploy/scenarios/wavefront-autotracing.yaml)
 
 You can see all configuration options in the [wavefront-full-config.yaml](deploy/scenarios/wavefront-full-config.yaml).
 
@@ -162,6 +160,8 @@ We have alerts on common Kubernetes issues. For details on creating alerts, see
 | [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`. |
+| [Container CPU Throttling](docs/alerts/templates/container-cpu-throttling.json.tmpl) | Workload has a container with high CPU throttling. |
+| [Container CPU Overutilization](docs/alerts/templates/container-cpu-overutilization.json.tmpl) | Workload has a container with high CPU utilization. |
 
 ## Bring Your Own Logs Shipper
 

diff --git a/collector/release/NEXT_RELEASE_VERSION b/collector/release/NEXT_RELEASE_VERSION
@@ -1 +1 @@
-1.25.0
+1.26.0
diff --git a/collector/release/VERSION b/collector/release/VERSION
@@ -1 +1 @@
-1.24.0
+1.25.0
diff --git a/deploy/scenarios/wavefront-full-config.yaml b/deploy/scenarios/wavefront-full-config.yaml
@@ -45,10 +45,6 @@ spec:
             - kube-system
     metrics:
       enable: true
-      # Note on Custom Configuration Precedence
-      #
-      # customConfig will override all top-level metrics config (filters, etc.) except for clusterCollector and nodeCollector
-      customConfig: wavefront-collector-config
       # Can be any key value pair that users can add to all metrics emitted.
       tags:
         userDefinedTag: userDefinedValue
@@ -152,155 +148,6 @@ spec:
 ---
 apiVersion: v1
 kind: ConfigMap
-metadata:
-  labels:
-    app.kubernetes.io/name : wavefront
-    app.kubernetes.io/component: collector
-  name: wavefront-collector-config
-  namespace: observability-system
-data:
-  config.yaml: |
-    clusterName: YOUR_CLUSTER_NAME
-    # Rules based and Prometheus endpoints auto-discovery.
-    enableDiscovery: true 
-    enableEvents: false
-    defaultCollectionInterval: 60s
-
-    sinks:
-    - proxyAddress: wavefront-proxy:2878
-      filters:
-        metricDenyList:
-        - kubernetes.sys_container.*
-        - kubernetes.collector.runtime.*
-        - kubernetes.*.network.rx_rate
-        - kubernetes.*.network.rx_errors_rate
-        - kubernetes.*.network.tx_rate
-        - kubernetes.*.network.tx_errors_rate
-        - kubernetes.*.memory.page_faults
-        - kubernetes.*.memory.page_faults_rate
-        - kubernetes.*.memory.major_page_faults
-        - kubernetes.*.memory.major_page_faults_rate
-        - kubernetes.*.filesystem.inodes
-        - kubernetes.*.filesystem.inodes_free
-        - kubernetes.*.ephemeral_storage.request
-        - kubernetes.*.ephemeral_storage.limit
-        tagExclude:
-        - label?controller?revision*
-        - label?pod?template*
-        - annotation_kubectl_kubernetes_io_last_applied_configuration
-
-    sources:
-      kubernetes_source:
-        url: https://kubernetes.default.svc
-        kubeletPort: 10250
-        kubeletHttps: true
-        useServiceAccount: true
-        insecure: true
-        prefix: kubernetes.
-        filters:
-          metricDenyList:
-          - 'kubernetes.sys_container.*'
-          - 'kubernetes.node.ephemeral_storage.*'
-
-      internal_stats_source:
-        prefix: kubernetes.
-
-      kubernetes_state_source:
-        prefix: kubernetes.
-
-      prometheus_sources:
-       - url: 'https://kubernetes.default.svc:443/metrics'
-         name: 'etcd-workqueue'
-         httpConfig:
-           bearer_token_file: '/var/run/secrets/kubernetes.io/serviceaccount/token'
-           tls_config:
-             ca_file: '/var/run/secrets/kubernetes.io/serviceaccount/ca.crt'
-             insecure_skip_verify: true
-         prefix: 'kubernetes.controlplane.'
-         convertHistograms: true
-         filters:
-           metricAllowList:
-           - 'kubernetes.controlplane.etcd.request.duration.seconds'
-           - 'kubernetes.controlplane.etcd.db.total.size.in.bytes.gauge'
-           - 'kubernetes.controlplane.workqueue.adds.total.counter'
-           - 'kubernetes.controlplane.workqueue.queue.duration.seconds'
-
-       - url: 'https://kubernetes.default.svc:443/metrics'
-         name: 'apiserver'
-         httpConfig:
-           bearer_token_file: '/var/run/secrets/kubernetes.io/serviceaccount/token'
-           tls_config:
-             ca_file: '/var/run/secrets/kubernetes.io/serviceaccount/ca.crt'
-             insecure_skip_verify: true
-         prefix: 'kubernetes.controlplane.'
-         convertHistograms: true
-         filters:
-           metricAllowList:
-           - 'kubernetes.controlplane.apiserver.request.duration.seconds'
-           - 'kubernetes.controlplane.apiserver.request.total.counter'
-           - 'kubernetes.controlplane.apiserver.storage.objects.gauge'
-           metricTagAllowList:
-             resource:
-             - 'customresourcedefinitions'
-             - 'namespaces'
-             - 'lease'
-             - 'nodes'
-             - 'pods'
-             - 'tokenreviews'
-             - 'subjectaccessreviews'
-
-    discovery:
-      enable_runtime_plugins: true
-
-      plugins:
-      # auto-discover kube DNS
-      - name: kube-dns-discovery
-        type: prometheus
-        selectors:
-          images:
-          - '*kube-dns/sidecar*'
-          labels:
-            k8s-app:
-            - kube-dns
-        port: 10054
-        path: /metrics
-        scheme: http
-        prefix: kube.dns.
-        filters:
-          metricAllowList:
-          - 'kube.dns.http.request.duration.microseconds'
-          - 'kube.dns.http.request.size.bytes'
-          - 'kube.dns.http.requests.total.counter'
-          - 'kube.dns.http.response.size.bytes'
-          - 'kube.dns.kubedns.dnsmasq.*'
-          - 'kube.dns.process.*'
-
-      # auto-discover coredns
-      - name: coredns-discovery
-        type: prometheus
-        selectors:
-          images:
-          - '*coredns:*'
-          labels:
-            k8s-app:
-            - kube-dns
-        port: 9153
-        path: /metrics
-        scheme: http
-        prefix: kube.coredns.
-        filters:
-          metricAllowList:
-          - 'kube.coredns.coredns.cache.*'
-          - 'kube.coredns.coredns.dns.request.count.total.counter'
-          - 'kube.coredns.coredns.dns.request.duration.seconds'
-          - 'kube.coredns.coredns.dns.request.size.bytes'
-          - 'kube.coredns.coredns.dns.request.type.count.total.counter'
-          - 'kube.coredns.coredns.dns.response.rcode.count.total.counter'
-          - 'kube.coredns.coredns.dns.response.size.bytes'
-          - 'kube.coredns.process.*'
----
-apiVersion: v1
-kind: ConfigMap
 metadata:
   name: advanced-proxy-preprocessor-rules
   namespace: observability-system

diff --git a/deploy/wavefront-operator.yaml b/deploy/wavefront-operator.yaml
@@ -1441,9 +1441,9 @@ subjects:
 ---
 apiVersion: v1
 data:
-  collector: 1.24.0
-  logging: 2.1.6
-  proxy: 13.0.1
+  collector: 1.25.0
+  logging: 2.1.9
+  proxy: "13.1"
 kind: ConfigMap
 metadata:
   labels:
@@ -1513,7 +1513,7 @@ spec:
             configMapKeyRef:
               key: logging
               name: wavefront-component-versions
-        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.12.0
+        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.13.0
         imagePullPolicy: Always
         livenessProbe:
           httpGet:

diff --git a/docs/alerts/alerts.md b/docs/alerts/alerts.md
@@ -8,6 +8,8 @@ We have alert templates on common Kubernetes issues.
 * [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)
+* [Detect container cpu throttling](templates/container-cpu-throttling.json.tmpl)
+* [Detect container cpu overutilization](templates/container-cpu-overutilization.json.tmpl)
 
 ## Flags
 

diff --git a/docs/alerts/templates/container-cpu-overutilization.json.tmpl b/docs/alerts/templates/container-cpu-overutilization.json.tmpl
@@ -0,0 +1,41 @@
+{
+  "name": "Container CPU Overutilization",
+  "alertType": "THRESHOLD",
+  "alertSources": [
+    {
+      "name": "Alert Condition",
+      "query": "round(sum(mavg(5m, align(1m, ts(\"kubernetes.pod_container.cpu.usage_rate\", cluster=\"K8S_CLUSTER_NAME\"))) by (container_name, pod_name, namespace_name)) / sum(mavg(5m, align(1m, ts(\"kubernetes.pod_container.cpu.limit\", cluster=\"K8S_CLUSTER_NAME\"))) by (container_name, pod_name, namespace_name)) * 100)",
+      "queryType": "WQL",
+      "alertSourceType": ["CONDITION"],
+      "hidden": true
+    },
+    {
+      "name": "Display Condition",
+      "query": "if(${Alert Condition} >= 90, ${Alert Condition})",
+      "queryType": "WQL",
+      "alertSourceType": ["VARIABLE","AUDIT"],
+      "hidden": false
+    }
+  ],
+  "conditions": {
+    "info": "round(sum(mavg(5m, align(1m, ts(\"kubernetes.pod_container.cpu.usage_rate\", cluster=\"K8S_CLUSTER_NAME\"))) by (container_name, pod_name, namespace_name)) / sum(mavg(5m, align(1m, ts(\"kubernetes.pod_container.cpu.limit\", cluster=\"K8S_CLUSTER_NAME\"))) by (container_name, pod_name, namespace_name)) * 100) >= 90"
+  },
+  "displayExpression": "${Display Condition}",
+  "minutes": 15,
+  "resolveAfterMinutes": 2,
+  "tags": {
+    "customerTags": [
+      "integration.kubernetes"
+    ]
+  },
+  "alertTriageDashboards": [
+    {
+     "dashboardId": "integration-kubernetes-workloads",
+     "parameters": {
+       "constants": {
+         "cluster": "K8S_CLUSTER_NAME"
+       }
+     }
+    }
+  ]
+}
diff --git a/docs/alerts/templates/container-cpu-throttling.json.tmpl b/docs/alerts/templates/container-cpu-throttling.json.tmpl
@@ -0,0 +1,41 @@
+{
+  "name": "Container CPU Throttling",
+  "alertType": "THRESHOLD",
+  "alertSources": [
+    {
+      "name": "Alert Condition",
+      "query": "round(sum((mavg(5m, rate(ts(\"kubernetes.cadvisor.container.cpu.cfs.throttled.periods.total.counter\", cluster=\"K8S_CLUSTER_NAME\"))) * 300) by (container, pod, namespace)) / sum((mavg(5m, rate(ts(\"kubernetes.cadvisor.container.cpu.cfs.periods.total.counter\", cluster=\"K8S_CLUSTER_NAME\"))) * 300) by (container, pod, namespace)) * 100)",
+      "queryType": "WQL",
+      "alertSourceType": ["CONDITION"],
+      "hidden": true
+    },
+    {
+      "name": "Display Condition",
+      "query": "if(${Alert Condition} >= 25, ${Alert Condition})",
+      "queryType": "WQL",
+      "alertSourceType": ["VARIABLE","AUDIT"],
+      "hidden": false
+    }
+  ],
+  "conditions": {
+    "info": "round(sum((mavg(5m, rate(ts(\"kubernetes.cadvisor.container.cpu.cfs.throttled.periods.total.counter\", cluster=\"K8S_CLUSTER_NAME\"))) * 300) by (container, pod, namespace)) / sum((mavg(5m, rate(ts(\"kubernetes.cadvisor.container.cpu.cfs.periods.total.counter\", cluster=\"K8S_CLUSTER_NAME\"))) * 300) by (container, pod, namespace)) * 100) >= 25"
+  },
+  "displayExpression": "${Display Condition}",
+  "minutes": 15,
+  "resolveAfterMinutes": 2,
+  "tags": {
+    "customerTags": [
+      "integration.kubernetes"
+    ]
+  },
+  "alertTriageDashboards": [
+    {
+     "dashboardId": "integration-kubernetes-workloads",
+     "parameters": {
+       "constants": {
+         "cluster": "K8S_CLUSTER_NAME"
+       }
+     }
+    }
+  ]
+}
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:2.12.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.12.0` |
-| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.24.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.24.0` |
-| 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` |
+| Observability for Kubernetes Operator | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.13.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.13.0` |
+| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.25.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.25.0` |
+| Wavefront Proxy | `projects.registry.vmware.com/tanzu_observability/proxy:13.1` | `YOUR_IMAGE_REGISTRY/proxy:13.1` |
+| Operations for Applications logging | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator-fluentbit:2.1.9` | `YOUR_IMAGE_REGISTRY/kubernetes-operator-fluentbit:2.1.9` |
 
 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: "1.24.0"
+  collector: "1.25.0"
   logging: "2.1.9"
   proxy: "13.1"
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: 2.12.0
+  newTag: 2.13.0
 
 patches:
 - path: patches.yaml

diff --git a/operator/dev-internal/deploy/wavefront-operator.yaml b/operator/dev-internal/deploy/wavefront-operator.yaml
@@ -1441,9 +1441,9 @@ subjects:
 ---
 apiVersion: v1
 data:
-  collector: 1.24.0
-  logging: 2.1.6
-  proxy: 13.0.1
+  collector: 1.25.0
+  logging: 2.1.9
+  proxy: "13.1"
 kind: ConfigMap
 metadata:
   labels:
@@ -1513,7 +1513,7 @@ spec:
             configMapKeyRef:
               key: logging
               name: wavefront-component-versions
-        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.12.0
+        image: projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.13.0
         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:2.12.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.12.0` |
-| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.24.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.24.0` |
+| Observability for Kubernetes Operator | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator:2.13.0` | `YOUR_IMAGE_REGISTRY/kubernetes-operator:2.13.0` |
+| Kubernetes Metrics Collector | `projects.registry.vmware.com/tanzu_observability/kubernetes-collector:1.25.0` | `YOUR_IMAGE_REGISTRY/kubernetes-collector:1.25.0` |
 | Wavefront Proxy | `projects.registry.vmware.com/tanzu_observability/proxy:13.1` | `YOUR_IMAGE_REGISTRY/proxy:13.1` |
 | Operations for Applications logging | `projects.registry.vmware.com/tanzu_observability/kubernetes-operator-fluentbit:2.1.9` | `YOUR_IMAGE_REGISTRY/kubernetes-operator-fluentbit:2.1.9` |
 

diff --git a/operator/release/NEXT_RELEASE_VERSION b/operator/release/NEXT_RELEASE_VERSION
@@ -1 +1 @@
-2.13.0
+2.14.0
diff --git a/operator/release/OPERATOR_VERSION b/operator/release/OPERATOR_VERSION
@@ -1 +1 @@
-2.12.0
+2.13.0