Add the Alloy dashboards instead of the Agent ones

charts/meta-monitoring/templates/agent/_helpers-agent.tpl

@@ -9,6 +9,15 @@
 {{- define "agent.all_namespaces" -}}
 {{- $list := list }}
 {{- range .Values.namespacesToMonitor }}
+{{- $list = append $list (printf "\"%s\"" .) }}
+{{- end }}
+{{- $list = append $list (printf "\"%s\"" .Release.Namespace) }}
+{{- join ", " $list }}
+{{- end }}
+
+{{- define "agent.all_namespaces_bar" -}}
+{{- $list := list }}
+{{- range .Values.namespacesToMonitor }}
 {{- $list = append $list (printf "%s" .) }}
 {{- end }}
 {{- $list = append $list .Release.Namespace }}

charts/meta-monitoring/templates/agent/config.yaml

@@ -93,7 +93,7 @@ data:
       role = "pod"
       namespaces {
         own_namespace = true
-        names = [ {{ include "agent.namespaces" . }} ]
+        names = [ {{ include "agent.all_namespaces" . }} ]
       }
     }
 
@@ -143,7 +143,7 @@ data:
 
       rule {
         source_labels = ["namespace"]
-        regex = "{{ include "agent.all_namespaces" . }}"
+        regex = "{{ include "agent.all_namespaces_bar" . }}"
 
         action = "keep"
       }

charts/meta-monitoring/templates/grafana/alloy-dashboards-1.yaml

@@ -0,0 +1,21 @@
+{{- if and .Values.local.grafana.enabled .Values.dashboards.logs.enabled }}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: alloy-dashboards-1
+  namespace: {{ $.Release.Namespace }}
+data:
+  "alloy-cluster-node.json": |
+    {{ $.Files.Get "src/dashboards/alloy-cluster-node.json" | fromJson | toJson }}
+  "alloy-cluster-overview.json": |
+    {{ $.Files.Get "src/dashboards/alloy-cluster-overview.json" | fromJson | toJson }}
+  "alloy-controller.json": |
+    {{ $.Files.Get "src/dashboards/alloy-controller.json" | fromJson | toJson }}
+  "alloy-opentelemetry.json": |
+    {{ $.Files.Get "src/dashboards/alloy-opentelemetry.json" | fromJson | toJson }}
+  "alloy-prometheus.json": |
+    {{ $.Files.Get "src/dashboards/alloy-prometheus.json" | fromJson | toJson }}
+  "alloy-resources.json": |
+    {{ $.Files.Get "src/dashboards/alloy-resources.json" | fromJson | toJson }}
+{{- end }}

charts/meta-monitoring/templates/grafana/dashboard.yaml

@@ -30,10 +30,10 @@ data:
 {{- end }}
       - disableDeletion: true
         editable: false
-        folder: Agent
-        name: agent-1
+        folder: Alloy
+        name: alloy-1
         options:
-          path: /var/lib/grafana/dashboards/agent-1
+          path: /var/lib/grafana/dashboards/alloy-1
         orgId: 1
         type: file
 {{- end }}

charts/meta-monitoring/templates/grafana/grafana-deployment.yaml

@@ -63,8 +63,8 @@ spec:
             - mountPath: /var/lib/grafana/dashboards/loki-2
               name: loki-dashboards-2
             {{- end }}
-            - mountPath: /var/lib/grafana/dashboards/agent-1
-              name: agent-dashboards-1
+            - mountPath: /var/lib/grafana/dashboards/alloy-1
+              name: alloy-dashboards-1
       volumes:
         - name: grafana-pv
           persistentVolumeClaim:
@@ -83,7 +83,7 @@ spec:
           configMap:
             name: loki-dashboards-2
         {{- end }}
-        - name: agent-dashboards-1
+        - name: alloy-dashboards-1
           configMap:
-            name: agent-dashboards-1
+            name: alloy-dashboards-1
 {{- end }}

charts/meta-monitoring/templates/grafana/loki-dashboards-1.yaml

@@ -12,8 +12,6 @@ data:
     {{ $.Files.Get "src/dashboards/loki-deletion.json" | fromJson | toJson }}
   "loki-logs.json": |
     {{ $.Files.Get "src/dashboards/loki-logs.json" | fromJson | toJson }}
-  "loki-mixin-recording-rules.json": |
-    {{ $.Files.Get "src/dashboards/loki-mixin-recording-rules.json" | fromJson | toJson }}
   "loki-operational.json": |
     {{ $.Files.Get "src/dashboards/loki-operational.json" | fromJson | toJson }}
 {{- end }}

charts/meta-monitoring/values.yaml

@@ -75,9 +75,46 @@ logs:
 metrics:
   # The list of metrics to retain for logging dashboards
   retain:
-  - agent_config_last_load_success_timestamp_seconds
-  - agent_config_last_load_successful
-  - agent_config_load_failures_total
+  - alloy_build_info
+  - alloy_config_last_load_success_timestamp_seconds
+  - alloy_config_last_load_successful
+  - alloy_config_load_failures_total
+  - alloy_component_controller_evaluating
+  - alloy_component_dependencies_wait_seconds
+  - alloy_component_dependencies_wait_seconds_bucket
+  - alloy_component_evaluation_seconds
+  - alloy_component_evaluation_seconds_bucket
+  - alloy_component_evaluation_seconds_count
+  - alloy_component_evaluation_seconds_sum
+  - alloy_component_evaluation_slow_seconds
+  - alloy_component_controller_running_components
+  - alloy_resources_machine_rx_bytes_total
+  - alloy_resources_machine_tx_bytes_total
+  - alloy_resources_process_cpu_seconds_total
+  - alloy_resources_process_resident_memory_bytes
+  - prometheus_remote_write_wal_samples_appended_total
+  - prometheus_remote_write_wal_storage_active_series
+  - cluster_node_info
+  - cluster_node_lamport_time
+  - cluster_node_update_observers
+  - cluster_node_gossip_health_score
+  - cluster_node_gossip_proto_version
+  - cluster_node_gossip_received_events_total
+  - cluster_node_peers
+  - cluster_transport_rx_bytes_total
+  - cluster_transport_rx_packets_total
+  - cluster_transport_rx_packets_failed_total
+  - cluster_transport_stream_rx_bytes_total
+  - cluster_transport_stream_rx_packets_failed_total
+  - cluster_transport_stream_rx_packets_total
+  - cluster_transport_stream_tx_bytes_total
+  - cluster_transport_stream_tx_packets_total
+  - cluster_transport_stream_tx_packets_failed_total
+  - cluster_transport_streams
+  - cluster_transport_tx_packets_total
+  - cluster_transport_tx_packets_failed_total
+  - cluster_transport_rx_packet_queue_length
+  - cluster_transport_tx_packet_queue_length
   - container_cpu_usage_seconds_total
   - container_fs_writes_bytes_total
   - container_memory_working_set_bytes
@@ -93,7 +130,10 @@ metrics:
   - cortex_prometheus_rule_group_last_duration_seconds
   - cortex_prometheus_rule_group_last_evaluation_timestamp_seconds
   - cortex_prometheus_rule_group_iterations_missed_total
+  - exporter_send_failed_spans_ratio_total
+  - exporter_sent_spans_ratio_total
   - go_gc_duration_seconds
+  - go_gc_duration_seconds_count
   - go_goroutines
   - go_memstats_heap_inuse_bytes
   - kubelet_volume_stats_used_bytes
@@ -130,6 +170,7 @@ metrics:
   - loki_compactor_oldest_pending_delete_request_age_seconds
   - loki_compactor_pending_delete_requests_count
   - loki_discarded_samples_total
+  - loki_discarded_bytes_total
   - loki_distributor_bytes_received_total
   - loki_distributor_lines_received_total
   - loki_distributor_structured_metadata_bytes_received_total
@@ -169,7 +210,58 @@ metrics:
   - loki_write_sent_entries_total
   - node_disk_read_bytes_total
   - node_disk_written_bytes_total
+  - process_start_time_seconds
+  - processor_batch_batch_send_size_ratio_bucket
+  - processor_batch_metadata_cardinality_ratio
+  - processor_batch_timeout_trigger_send_ratio_total
+  - prometheus_remote_storage_bytes_total
+  - prometheus_remote_storage_enqueue_retries_total
+  - prometheus_remote_storage_highest_timestamp_in_seconds
+  - prometheus_remote_storage_metadata_bytes_total
+  - prometheus_remote_storage_queue_highest_sent_timestamp_seconds
+  - prometheus_remote_storage_samples_dropped_total
+  - prometheus_remote_storage_samples_failed_total
+  - prometheus_remote_storage_samples_pending
+  - prometheus_remote_storage_samples_retried_total
+  - prometheus_remote_storage_samples_total
+  - prometheus_remote_storage_sent_batch_duration_seconds_bucket
+  - prometheus_remote_storage_sent_batch_duration_seconds_count
+  - prometheus_remote_storage_sent_batch_duration_seconds_sum
+  - prometheus_remote_storage_shard_capacity
+  - prometheus_remote_storage_shards
+  - prometheus_remote_storage_shards_desired
+  - prometheus_remote_storage_shards_max
+  - prometheus_remote_storage_shards_min
+  - prometheus_remote_storage_succeeded_samples_total
+  - prometheus_remote_write_wal_samples_appended_total
+  - prometheus_remote_write_wal_storage_active_series
+  - prometheus_sd_discovered_targets
+  - prometheus_target_interval_length_seconds_count
+  - prometheus_target_interval_length_seconds_sum
+  - prometheus_target_scrapes_exceeded_sample_limit_total
+  - prometheus_target_scrapes_sample_duplicate_timestamp_total
+  - prometheus_target_scrapes_sample_out_of_bounds_total
+  - prometheus_target_scrapes_sample_out_of_order_total
+  - prometheus_target_sync_length_seconds_sum
+  - prometheus_wal_watcher_current_segment
   - promtail_custom_bad_words_total
+  - promtail_dropped_bytes_total
+  - promtail_files_active_total
+  - promtail_read_bytes_total
+  - promtail_read_lines_total
+  - promtail_request_duration_seconds_bucket
+  - promtail_sent_entries_total
+  - rpc_server_duration_milliseconds_bucket
+  - receiver_accepted_spans_ratio_total
+  - receiver_refused_spans_ratio_total
+  - scrape_duration_seconds
+  - traces_exporter_sent_spans
+  - traces_exporter_send_failed_spans
+  - traces_loadbalancer_backend_outcome
+  - traces_loadbalancer_num_backends
+  - traces_receiver_accepted_spans
+  - traces_receiver_refused_spans
+  - up
   # Additional metrics to retain
   extraMetrics: []
 # Set enabled = true to add the default logs dashboards to the local Grafana