Merge pull request #191 from logzio/logzio-telemetry-0.0.20

Logzio telemetry 0.0.20

charts/logzio-telemetry/Chart.yaml

@@ -23,12 +23,12 @@ dependencies:
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.0.19
+version: 0.0.20
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
-appVersion: 0.64.0
+appVersion: 0.66.0
 
 maintainers:
 - name: yotamloe

charts/logzio-telemetry/README.md

@@ -211,6 +211,13 @@ To enable metrics filtering, set the following flag when deploying the chart, re
 --set enableMetricsFilter.<<cloud-service>>=true
 ```
 
+#### Filtering metrics from `kube-system` namesapce
+
+To Filter out metrics from `kube-system` namesapce, set the following flag when deploying the chart.
+
+```
+--set enableMetricsFilter.kubeSystem=true
+```
 
 #### Disabling kube-dns scraping for EKS clusters
 
@@ -245,6 +252,12 @@ helm uninstall logzio-k8s-telemetry
 
 
 ## Change log
+* 0.0.20
+  - Change the default port for node exporter `9100` -> `9101` to avoid pods stocking on pending state if a user has `node-exporter` daemon set deployed on the cluster
+  - Update otel `0.64.0` -> `0.66.0` 
+  - Add `logzio_agent_version` label
+  - Add `logz.io/app=kubertneters360` annotation to `Kube-state-metrics` and `node-exporter`
+  - Add `filter/kubernetes360` processor for metrics, to avoid duplicated metrics if a user has `Kube-state-metrics` or `node-exporter` deployed on the cluster
 * 0.0.19
   - Drop metrics from `kube-system` namespace
 * 0.0.18

charts/logzio-telemetry/templates/_pod.tpl

@@ -37,6 +37,13 @@ containers:
           fieldRef:
             apiVersion: v1
             fieldPath: status.podIP
+      - name: K8S_360_METRICS
+        valueFrom:
+          secretKeyRef:
+            name: logzio-secret
+            key: kubernetes-360-metrics
+      - name: LOGZIO_AGENT_VERSION
+        value: {{.Chart.Version}}
       - name: REALESE_NAME
         value: {{.Release.Name}}
       - name: REALESE_NS
@@ -171,4 +178,4 @@ affinity:
 tolerations:
   {{- toYaml . | nindent 2 }}
 {{- end }}
-{{- end }}
+{{- end }}

charts/logzio-telemetry/templates/secrets.yaml

@@ -6,6 +6,7 @@ metadata:
   namespace: {{ .Release.Namespace }}
 type: Opaque
 stringData:
+  kubernetes-360-metrics: kube_pod_container_status_terminated_reason|kube_node_labels|kube_pod_container_status_waiting_reason|node_memory_Buffers_bytes|node_memory_Cached_bytes|kube_deployment_labels|i:|kube_deployment_status_replicas|kube_deployment_status_replicas_available|kube_deployment_status_replicas_unavailable|kube_deployment_status_replicas_updated|kube_node_info|kube_node_spec_unschedulable|kube_node_status_allocatable|kube_node_status_capacity|kube_node_status_condition|kube_pod_container_info|kube_pod_container_resource_requests|kube_pod_container_resource_requests_cpu_cores|kube_pod_container_resource_requests_memory_bytes|kube_pod_container_status_ready|kube_pod_container_status_restarts_total|kube_pod_container_status_running|kube_pod_container_status_terminated|kube_pod_container_status_waiting|kube_pod_info|kube_pod_status_phase|machine_cpu_cores|namespace|node_boot_time_seconds|node_cpu_seconds_total|node_disk_io_time_seconds_total|node_filesystem_avail_bytes|node_filesystem_free_bytes|node_filesystem_size_bytes|node_memory_MemFree_bytes|node_memory_MemTotal_bytes|node_network_receive_bytes_total|node_network_transmit_bytes_total|node_time_seconds|p8s_logzio_name|windows_container_cpu_usage_seconds_total|windows_container_memory_usage_commit_bytes|windows_container_network_receive_bytes_total|windows_container_network_transmit_bytes_total|windows_cpu_time_total|windows_cs_hostname|windows_cs_physical_memory_bytes|windows_logical_disk_free_bytes|windows_logical_disk_read_seconds_total|windows_logical_disk_size_bytes|windows_logical_disk_write_seconds_total|windows_net_bytes_received_total|windows_net_bytes_sent_total|windows_os_physical_memory_free_bytes|windows_system_system_up_time|kube_pod_status_ready|kube_pod_container_resource_limits|kube_pod_created|kube_pod_owner|kube_pod_status_reason|node_memory_MemAvailable_bytes|kube_node_role|kube_node_created|node_load1|node_load5|node_load15|node_disk_reads_completed_total|node_disk_writes_completed_total|node_disk_read_bytes_total|node_disk_written_bytes_total|node_disk_read_time_seconds_total|node_disk_write_time_seconds_total|node_network_transmit_packets_total|node_network_receive_packets_total|node_network_transmit_drop_total|node_network_receive_drop_total|kube_replicaset_owner|kube_deployment_created|kube_deployment_status_condition|kube_deployment_spec_replicas|kube_namespace_status_phase
   env_id: {{.Values.secrets.env_id}}
 {{- if .Values.metrics.enabled }}
   logzio-metrics-shipping-token: {{ .Values.secrets.MetricsToken }}

charts/logzio-telemetry/values.yaml

@@ -185,6 +185,9 @@ baseCollectorConfig:
         - key: env_id
           value: ${ENV_ID}
           action: insert
+        - key: logzio_agent_version
+          value: ${LOGZIO_AGENT_VERSION}
+          action: insert
     memory_limiter: null
     tail_sampling:
       policies:
@@ -305,6 +308,11 @@ spmConfig:
 metricsConfig:
   extensions:
     health_check: {}
+  processors:
+    filter/kubernetes360:
+      metrics:
+        datapoint:
+          - 'IsMatch(metric.name, "(${K8S_360_METRICS})") == true and attributes["logzio_app"] != "kubernetes360"'
   exporters:
     prometheusremotewrite:
       endpoint: ${LISTENER_URL}
@@ -375,6 +383,9 @@ metricsConfig:
             - source_labels: [__meta_kubernetes_pod_node_name]
               action: replace
               target_label: kubernetes_node
+            - source_labels: [__meta_kubernetes_service_annotation_logz_io_app]
+              action: replace
+              target_label: logzio_app
           metric_relabel_configs: []
 
         # Job to collect metrics from applications running on pods
@@ -440,6 +451,7 @@ metricsConfig:
         processors:
           - attributes/env_id
           - memory_limiter
+          - filter/kubernetes360
         receivers:
           - prometheus
 
@@ -451,7 +463,7 @@ image:
   repository: otel/opentelemetry-collector-contrib
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
-  tag: "0.64.0"
+  tag: "0.66.0"
 nginxWindowsImage:
   # Reverse proxy image to enable metrics scraping from windows nodes
   repository: logzio/logzio-windows-node-reverse-proxy
@@ -606,12 +618,21 @@ podLabels:  {}
 annotations:  {}
 
 kube-state-metrics:
+  service:
+    annotations:
+      logz.io/app: "kubernetes360"
   nodeSelector:
     kubernetes.io/os: linux
   podSecurityPolicy:
     enabled: false
 
 prometheus-node-exporter:
+  service:
+    port: 9101
+    targetPort: 9101
+    annotations:
+      prometheus.io/scrape: "true"
+      logz.io/app: "kubernetes360"
   nodeSelector:
     kubernetes.io/os: linux
   # Prevent node exporter deamonset deploymment on fargate nodes