add grafana-agent

kustomize/bases/grafana-agent/grafana-agent-volume.yaml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: grafana-agent-wal-pvc
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 5Gi

kustomize/bases/grafana-agent/kustomization.yaml

@@ -0,0 +1,18 @@
+resources:
+  - https://raw.githubusercontent.com/grafana/agent/v0.24.2/production/kubernetes/agent-bare.yaml
+  - grafana-agent-volume.yaml
+
+secretGenerator:
+  - name: grafana-agent
+    behavior: create
+    literals:
+      - agent.yaml=
+
+patchesJson6902:
+  - target:
+      version: v1
+      kind: StatefulSet
+      name: grafana-agent
+    path: patches/grafana-agent-statefulset-patch.yaml
+
+namespace: default

kustomize/bases/grafana-agent/patches/grafana-agent-statefulset-patch.yaml

@@ -0,0 +1,13 @@
+- op: remove
+  path: /spec/volumeClaimTemplates
+- op: add
+  path: /spec/template/spec/volumes
+  value:
+    - name: grafana-agent
+      secret:
+        secretName: grafana-agent
+    - name: agent-wal
+      persistentVolumeClaim:
+        claimName: grafana-agent-wal-pvc
+
+

kustomize/namespaces/monitoring/kustomization.yaml

@@ -3,6 +3,7 @@ bases:
   - ../../bases/node-exporter
   - ../../bases/blackbox-exporter
   - ../../bases/kube-state-metrics
+  - ../../bases/grafana-agent
   - servicemonitors/any-namespaces-http.yaml
   - servicemonitors/kubelet.yaml
   - servicemonitors/longhorn.yaml

kustomize/overlays/prod/configurations/grafana-agent/agent.yaml

@@ -0,0 +1,88 @@
+metrics:
+  wal_directory: /var/lib/agent/wal
+  global:
+    scrape_interval: 60s
+    external_labels:
+      cluster: cloud
+  configs:
+    - name: integrations
+      remote_write:
+        - url: https://prometheus-prod-10-prod-us-central-0.grafana.net/api/prom/push
+          basic_auth:
+            username: 443422
+            password: ${ssm:/k3s/prod/monitoring/grafana-cloud/password}
+      scrape_configs:
+        - bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+          job_name: integrations/kubernetes/cadvisor
+          kubernetes_sd_configs:
+            - role: node
+          metric_relabel_configs:
+            - source_labels: [__name__]
+              regex: namespace_memory:kube_pod_container_resource_requests:sum|kubelet_running_containers|container_cpu_usage_seconds_total|kube_pod_container_info|container_network_receive_packets_dropped_total|kube_pod_status_phase|kubelet_pod_start_duration_seconds_count|kubelet_cgroup_manager_duration_seconds_bucket|kube_horizontalpodautoscaler_status_desired_replicas|cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits|node_namespace_pod_container:container_memory_swap|kube_statefulset_status_replicas_ready|kube_horizontalpodautoscaler_spec_max_replicas|cluster:namespace:pod_memory:active:kube_pod_container_resource_requests|process_cpu_seconds_total|process_resident_memory_bytes|kubelet_server_expiration_renew_errors|kube_daemonset.*|container_fs_reads_total|machine_memory_bytes|kubelet_volume_stats_inodes_used|volume_manager_total_volumes|kube_statefulset_status_replicas|namespace_cpu:kube_pod_container_resource_limits:sum|kube_pod_container_resource_requests|kube_pod_container_resource_limits|kubelet_pod_worker_duration_seconds_count|namespace_workload_pod:kube_pod_owner:relabel|kubelet_cgroup_manager_duration_seconds_count|container_cpu_cfs_throttled_periods_total|kube_node_spec_taint|container_fs_reads_bytes_total|kubelet_certificate_manager_client_ttl_seconds|container_network_receive_bytes_total|kubelet_running_container_count|kube_daemonset_status_number_available|kube_node_status_allocatable|container_fs_writes_total|kube_namespace_status_phase|kubelet_volume_stats_available_bytes|kubelet_pleg_relist_duration_seconds_bucket|kubelet_runtime_operations_errors_total|kube_pod_container_status_waiting_reason|kube_replicaset_owner|kube_resourcequota|kube_pod_info|kubelet_pleg_relist_duration_seconds_count|kube_deployment_status_replicas_available|cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests|kubelet_running_pods|kube_statefulset_status_replicas_updated|kube_deployment_status_replicas_updated|kube_job_spec_completions|kube_daemonset_status_number_misscheduled|kubelet_certificate_manager_server_ttl_seconds|container_network_transmit_bytes_total|container_memory_cache|kubelet_volume_stats_capacity_bytes|node_namespace_pod_container:container_memory_cache|container_memory_rss|container_memory_swap|storage_operation_duration_seconds_count|kube_replicaset.*|kube_pod_owner|cluster:namespace:pod_memory:active:kube_pod_container_resource_limits|kubelet_volume_stats_inodes|kube_daemonset_status_desired_number_scheduled|kube_daemonset_status_updated_number_scheduled|kube_statefulset.*|kube_node_info|go_goroutines|kubelet_pod_worker_duration_seconds_bucket|kubelet_node_config_error|container_cpu_cfs_periods_total|kubelet_pleg_relist_interval_seconds_bucket|kube_job.*|container_network_receive_packets_total|container_fs_writes_bytes_total|kubelet_running_pod_count|kube_deployment_spec_replicas|up|kube_node_status_capacity|namespace_cpu:kube_pod_container_resource_requests:sum|node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate|container_memory_working_set_bytes|kubelet_node_name|node_namespace_pod_container:container_memory_rss|storage_operation_errors_total|kube_statefulset_metadata_generation|container_network_transmit_packets_total|kubelet_runtime_operations_total|kube_statefulset_status_observed_generation|kube_horizontalpodautoscaler_status_current_replicas|kubernetes_build_info|kubelet_certificate_manager_client_expiration_renew_errors|kube_job_failed|namespace_workload_pod|node_namespace_pod_container:container_memory_working_set_bytes|kube_statefulset_replicas|kube_deployment_status_observed_generation|kube_pod_container_status_restarts_total|kube_daemonset_status_current_number_scheduled|kube_pod_start_time|namespace_memory:kube_pod_container_resource_limits:sum|container_network_transmit_packets_dropped_total|rest_client_requests_total|kube_deployment_metadata_generation|kube_statefulset_status_update_revision|kube_job_status_succeeded|kube_horizontalpodautoscaler_spec_min_replicas|kube_statefulset_status_current_revision|node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile|kube_node_status_condition
+              action: keep
+          relabel_configs:
+            - replacement: kubernetes.default.svc.cluster.local:443
+              target_label: __address__
+            - regex: (.+)
+              replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+              source_labels:
+                - __meta_kubernetes_node_name
+              target_label: __metrics_path__
+          scheme: https
+          tls_config:
+            ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+            insecure_skip_verify: false
+            server_name: kubernetes
+        - bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+          job_name: integrations/kubernetes/kubelet
+          kubernetes_sd_configs:
+            - role: node
+          metric_relabel_configs:
+            - source_labels: [__name__]
+              regex: namespace_memory:kube_pod_container_resource_requests:sum|kubelet_running_containers|container_cpu_usage_seconds_total|kube_pod_container_info|container_network_receive_packets_dropped_total|kube_pod_status_phase|kubelet_pod_start_duration_seconds_count|kubelet_cgroup_manager_duration_seconds_bucket|kube_horizontalpodautoscaler_status_desired_replicas|cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits|node_namespace_pod_container:container_memory_swap|kube_statefulset_status_replicas_ready|kube_horizontalpodautoscaler_spec_max_replicas|cluster:namespace:pod_memory:active:kube_pod_container_resource_requests|process_cpu_seconds_total|process_resident_memory_bytes|kubelet_server_expiration_renew_errors|kube_daemonset.*|container_fs_reads_total|machine_memory_bytes|kubelet_volume_stats_inodes_used|volume_manager_total_volumes|kube_statefulset_status_replicas|namespace_cpu:kube_pod_container_resource_limits:sum|kube_pod_container_resource_requests|kube_pod_container_resource_limits|kubelet_pod_worker_duration_seconds_count|namespace_workload_pod:kube_pod_owner:relabel|kubelet_cgroup_manager_duration_seconds_count|container_cpu_cfs_throttled_periods_total|kube_node_spec_taint|container_fs_reads_bytes_total|kubelet_certificate_manager_client_ttl_seconds|container_network_receive_bytes_total|kubelet_running_container_count|kube_daemonset_status_number_available|kube_node_status_allocatable|container_fs_writes_total|kube_namespace_status_phase|kubelet_volume_stats_available_bytes|kubelet_pleg_relist_duration_seconds_bucket|kubelet_runtime_operations_errors_total|kube_pod_container_status_waiting_reason|kube_replicaset_owner|kube_resourcequota|kube_pod_info|kubelet_pleg_relist_duration_seconds_count|kube_deployment_status_replicas_available|cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests|kubelet_running_pods|kube_statefulset_status_replicas_updated|kube_deployment_status_replicas_updated|kube_job_spec_completions|kube_daemonset_status_number_misscheduled|kubelet_certificate_manager_server_ttl_seconds|container_network_transmit_bytes_total|container_memory_cache|kubelet_volume_stats_capacity_bytes|node_namespace_pod_container:container_memory_cache|container_memory_rss|container_memory_swap|storage_operation_duration_seconds_count|kube_replicaset.*|kube_pod_owner|cluster:namespace:pod_memory:active:kube_pod_container_resource_limits|kubelet_volume_stats_inodes|kube_daemonset_status_desired_number_scheduled|kube_daemonset_status_updated_number_scheduled|kube_statefulset.*|kube_node_info|go_goroutines|kubelet_pod_worker_duration_seconds_bucket|kubelet_node_config_error|container_cpu_cfs_periods_total|kubelet_pleg_relist_interval_seconds_bucket|kube_job.*|container_network_receive_packets_total|container_fs_writes_bytes_total|kubelet_running_pod_count|kube_deployment_spec_replicas|up|kube_node_status_capacity|namespace_cpu:kube_pod_container_resource_requests:sum|node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate|container_memory_working_set_bytes|kubelet_node_name|node_namespace_pod_container:container_memory_rss|storage_operation_errors_total|kube_statefulset_metadata_generation|container_network_transmit_packets_total|kubelet_runtime_operations_total|kube_statefulset_status_observed_generation|kube_horizontalpodautoscaler_status_current_replicas|kubernetes_build_info|kubelet_certificate_manager_client_expiration_renew_errors|kube_job_failed|namespace_workload_pod|node_namespace_pod_container:container_memory_working_set_bytes|kube_statefulset_replicas|kube_deployment_status_observed_generation|kube_pod_container_status_restarts_total|kube_daemonset_status_current_number_scheduled|kube_pod_start_time|namespace_memory:kube_pod_container_resource_limits:sum|container_network_transmit_packets_dropped_total|rest_client_requests_total|kube_deployment_metadata_generation|kube_statefulset_status_update_revision|kube_job_status_succeeded|kube_horizontalpodautoscaler_spec_min_replicas|kube_statefulset_status_current_revision|node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile|kube_node_status_condition
+              action: keep
+          relabel_configs:
+            - replacement: kubernetes.default.svc.cluster.local:443
+              target_label: __address__
+            - regex: (.+)
+              replacement: /api/v1/nodes/${1}/proxy/metrics
+              source_labels:
+                - __meta_kubernetes_node_name
+              target_label: __metrics_path__
+          scheme: https
+          tls_config:
+            ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+            insecure_skip_verify: false
+            server_name: kubernetes
+        - job_name: integrations/kubernetes/kube-state-metrics
+          kubernetes_sd_configs:
+            - role: pod
+          metric_relabel_configs:
+            - source_labels: [__name__]
+              regex: namespace_memory:kube_pod_container_resource_requests:sum|kubelet_running_containers|container_cpu_usage_seconds_total|kube_pod_container_info|container_network_receive_packets_dropped_total|kube_pod_status_phase|kubelet_pod_start_duration_seconds_count|kubelet_cgroup_manager_duration_seconds_bucket|kube_horizontalpodautoscaler_status_desired_replicas|cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits|node_namespace_pod_container:container_memory_swap|kube_statefulset_status_replicas_ready|kube_horizontalpodautoscaler_spec_max_replicas|cluster:namespace:pod_memory:active:kube_pod_container_resource_requests|process_cpu_seconds_total|process_resident_memory_bytes|kubelet_server_expiration_renew_errors|kube_daemonset.*|container_fs_reads_total|machine_memory_bytes|kubelet_volume_stats_inodes_used|volume_manager_total_volumes|kube_statefulset_status_replicas|namespace_cpu:kube_pod_container_resource_limits:sum|kube_pod_container_resource_requests|kube_pod_container_resource_limits|kubelet_pod_worker_duration_seconds_count|namespace_workload_pod:kube_pod_owner:relabel|kubelet_cgroup_manager_duration_seconds_count|container_cpu_cfs_throttled_periods_total|kube_node_spec_taint|container_fs_reads_bytes_total|kubelet_certificate_manager_client_ttl_seconds|container_network_receive_bytes_total|kubelet_running_container_count|kube_daemonset_status_number_available|kube_node_status_allocatable|container_fs_writes_total|kube_namespace_status_phase|kubelet_volume_stats_available_bytes|kubelet_pleg_relist_duration_seconds_bucket|kubelet_runtime_operations_errors_total|kube_pod_container_status_waiting_reason|kube_replicaset_owner|kube_resourcequota|kube_pod_info|kubelet_pleg_relist_duration_seconds_count|kube_deployment_status_replicas_available|cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests|kubelet_running_pods|kube_statefulset_status_replicas_updated|kube_deployment_status_replicas_updated|kube_job_spec_completions|kube_daemonset_status_number_misscheduled|kubelet_certificate_manager_server_ttl_seconds|container_network_transmit_bytes_total|container_memory_cache|kubelet_volume_stats_capacity_bytes|node_namespace_pod_container:container_memory_cache|container_memory_rss|container_memory_swap|storage_operation_duration_seconds_count|kube_replicaset.*|kube_pod_owner|cluster:namespace:pod_memory:active:kube_pod_container_resource_limits|kubelet_volume_stats_inodes|kube_daemonset_status_desired_number_scheduled|kube_daemonset_status_updated_number_scheduled|kube_statefulset.*|kube_node_info|go_goroutines|kubelet_pod_worker_duration_seconds_bucket|kubelet_node_config_error|container_cpu_cfs_periods_total|kubelet_pleg_relist_interval_seconds_bucket|kube_job.*|container_network_receive_packets_total|container_fs_writes_bytes_total|kubelet_running_pod_count|kube_deployment_spec_replicas|up|kube_node_status_capacity|namespace_cpu:kube_pod_container_resource_requests:sum|node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate|container_memory_working_set_bytes|kubelet_node_name|node_namespace_pod_container:container_memory_rss|storage_operation_errors_total|kube_statefulset_metadata_generation|container_network_transmit_packets_total|kubelet_runtime_operations_total|kube_statefulset_status_observed_generation|kube_horizontalpodautoscaler_status_current_replicas|kubernetes_build_info|kubelet_certificate_manager_client_expiration_renew_errors|kube_job_failed|namespace_workload_pod|node_namespace_pod_container:container_memory_working_set_bytes|kube_statefulset_replicas|kube_deployment_status_observed_generation|kube_pod_container_status_restarts_total|kube_daemonset_status_current_number_scheduled|kube_pod_start_time|namespace_memory:kube_pod_container_resource_limits:sum|container_network_transmit_packets_dropped_total|rest_client_requests_total|kube_deployment_metadata_generation|kube_statefulset_status_update_revision|kube_job_status_succeeded|kube_horizontalpodautoscaler_spec_min_replicas|kube_statefulset_status_current_revision|node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile|kube_node_status_condition
+              action: keep
+          relabel_configs:
+            - action: keep
+              regex: kube-state-metrics
+              source_labels:
+                - __meta_kubernetes_pod_label_app_kubernetes_io_name
+
+integrations:
+  eventhandler:
+    cache_path: /var/lib/agent/eventhandler.cache
+    logs_instance: integrations
+logs:
+  configs:
+    - name: integrations
+      clients:
+        - url: https://logs-prod3.grafana.net/loki/api/v1/push
+          basic_auth:
+            username: 220681
+            password: ${ssm:/k3s/prod/monitoring/grafana-cloud/password}
+          external_labels:
+            cluster: cloud
+            job: integrations/kubernetes/eventhandler
+      positions:
+        filename: /tmp/positions.yaml
+      target_config:
+        sync_period: 10s

kustomize/overlays/prod/kustomization.yaml

@@ -62,6 +62,11 @@ secretGenerator:
     behavior: replace
     literals:
       - password=${ssm:/k3s/prod/nextcloud/redis/password}
+  - name: grafana-agent
+    namespace: monitoring
+    behavior: replace
+    files:
+      - agent.yaml=configurations/grafana-agent/agent.yaml
   # - name: grafana-cloud-credentials
   #   type: Opaque
   #   namespace: monitoring