Add Alloy dashboards and metrics

Signed-off-by: Michel Hollands <michel.hollands@gmail.com>

charts/meta-monitoring/values.yaml

@@ -75,12 +75,46 @@ logs:
 metrics:
   # The list of metrics to retain for logging dashboards
   retain:
-  - agent_build_info
-  - agent_config_last_load_success_timestamp_seconds
-  - agent_config_last_load_successful
-  - agent_config_load_failures_total
-  - agent_wal_samples_appended_total
-  - agent_wal_storage_active_series
+  - 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
@@ -96,6 +130,8 @@ 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
@@ -175,8 +211,13 @@ metrics:
   - 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
@@ -192,6 +233,8 @@ metrics:
   - 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
@@ -208,12 +251,17 @@ metrics:
   - 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