Enabling the Alloy integration should truly enable the integration (#941

)

Signed-off-by: Pete Wall <pete.wall@grafana.com>

charts/feature-integrations/default-allow-lists/alloy.yaml

@@ -1,3 +1,105 @@
 ---
-# The minimal set of metrics from Grafana Alloy required for Kubernetes Monitoring
+# The set of metrics from Grafana Alloy required for the Grafana Alloy integration
 - alloy_build_info
+- alloy_component_controller_running_components
+- 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_config_hash
+- alloy_resources_machine_rx_bytes_total
+- alloy_resources_machine_tx_bytes_total
+- alloy_resources_process_cpu_seconds_total
+- alloy_resources_process_resident_memory_bytes
+- alloy_tcp_connections
+- alloy_wal_samples_appended_total
+- alloy_wal_storage_active_series
+- cluster_node_gossip_health_score
+- cluster_node_gossip_proto_version
+- cluster_node_gossip_received_events_total
+- cluster_node_info
+- cluster_node_lamport_time
+- cluster_node_peers
+- cluster_node_update_observers
+- cluster_transport_rx_bytes_total
+- cluster_transport_rx_packet_queue_length
+- cluster_transport_rx_packets_failed_total
+- cluster_transport_rx_packets_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_failed_total
+- cluster_transport_stream_tx_packets_total
+- cluster_transport_streams
+- cluster_transport_tx_bytes_total
+- cluster_transport_tx_packet_queue_length
+- cluster_transport_tx_packets_failed_total
+- cluster_transport_tx_packets_total
+- otelcol_exporter_send_failed_spans_total
+- otelcol_exporter_sent_spans_total
+- go_gc_duration_seconds_count
+- go_goroutines
+- go_memstats_heap_inuse_bytes
+- loki_process_dropped_lines_total
+- loki_write_batch_retries_total
+- loki_write_dropped_bytes_total
+- loki_write_dropped_entries_total
+- loki_write_encoded_bytes_total
+- loki_write_mutated_bytes_total
+- loki_write_mutated_entries_total
+- loki_write_request_duration_seconds_bucket
+- loki_write_sent_bytes_total
+- loki_write_sent_entries_total
+- process_cpu_seconds_total
+- process_start_time_seconds
+- otelcol_processor_batch_batch_send_size_bucket
+- otelcol_processor_batch_metadata_cardinality
+- otelcol_processor_batch_timeout_trigger_send_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
+- otelcol_receiver_accepted_spans_total
+- otelcol_receiver_refused_spans_total
+- rpc_server_duration_milliseconds_bucket
+- scrape_duration_seconds
+- traces_exporter_send_failed_spans
+- traces_exporter_send_failed_spans_total
+- traces_exporter_sent_spans
+- traces_exporter_sent_spans_total
+- traces_loadbalancer_backend_outcome
+- traces_loadbalancer_num_backends
+- traces_receiver_accepted_spans
+- traces_receiver_accepted_spans_total
+- traces_receiver_refused_spans
+- traces_receiver_refused_spans_total

charts/feature-integrations/docs/integrations/alloy.md

@@ -15,8 +15,7 @@
 | maxCacheSize | string | `100000` | Sets the max_cache_size for prometheus.relabel component. This should be at least 2x-5x your largest scrape target or samples appended rate. ([docs](https://grafana.com/docs/alloy/latest/reference/components/prometheus.relabel/#arguments)) Overrides global.maxCacheSize |
 | metricsTuning.excludeMetrics | list | `[]` | Metrics to drop. Can use regular expressions. |
 | metricsTuning.includeMetrics | list | `[]` | Metrics to keep. Can use regular expressions. |
-| metricsTuning.useDefaultAllowList | bool | `true` | Filter the list of metrics from Grafana Alloy to the minimal set required for Kubernetes Monitoring. See [Metrics Tuning and Allow Lists](#metrics-tuning-and-allow-lists) |
-| metricsTuning.useIntegrationAllowList | bool | `false` | Filter the list of metrics from Grafana Alloy to the minimal set required for Kubernetes Monitoring as well as the Grafana Alloy integration. |
+| metricsTuning.useDefaultAllowList | bool | `true` | Filter the list of metrics from Grafana Alloy to the minimal set required for the Grafana Alloy integration. |
 
 ### General Settings
 

charts/feature-integrations/integrations/alloy-values.yaml

@@ -15,13 +15,9 @@ scrapeInterval:
 
 # Adjustments to the scraped metrics to filter the amount of data sent to storage.
 metricsTuning:
-  # -- Filter the list of metrics from Grafana Alloy to the minimal set required for Kubernetes Monitoring.
-  # See [Metrics Tuning and Allow Lists](#metrics-tuning-and-allow-lists)
+  # -- Filter the list of metrics from Grafana Alloy to the minimal set required for the Grafana Alloy integration.
   # @section -- Metric Processing Settings
   useDefaultAllowList: true
-  # -- Filter the list of metrics from Grafana Alloy to the minimal set required for Kubernetes Monitoring as well as the Grafana Alloy integration.
-  # @section -- Metric Processing Settings
-  useIntegrationAllowList: false
   # -- Metrics to keep. Can use regular expressions.
   # @section -- Metric Processing Settings
   includeMetrics: []

charts/feature-integrations/schema-mods/definitions/alloy-integration.schema.json

@@ -18,9 +18,6 @@
                 },
                 "useDefaultAllowList": {
                     "type": "boolean"
-                },
-                "useIntegrationAllowList": {
-                    "type": "boolean"
                 }
             }
         },

charts/feature-integrations/templates/_integration_alloy.tpl

@@ -8,9 +8,6 @@
 {{- if .instance.metricsTuning.useDefaultAllowList -}}
 {{- $allowList = concat $allowList (.Files.Get "default-allow-lists/alloy.yaml" | fromYamlArray) -}}
 {{- end -}}
-{{- if .instance.metricsTuning.useIntegrationAllowList -}}
-{{- $allowList = concat $allowList (.Files.Get "default-allow-lists/alloy-integration.yaml" | fromYamlArray) -}}
-{{- end -}}
 {{- if .instance.metricsTuning.includeMetrics -}}
 {{- $allowList = concat $allowList .instance.metricsTuning.includeMetrics -}}
 {{- end -}}

charts/feature-integrations/tests/alloy_test.yaml

@@ -283,7 +283,7 @@ tests:
               alloy_integration_scrape  "alloy_metrics" {
                 targets = alloy_integration_discovery.alloy_metrics.output
                 clustering = true
-                keep_metrics = "up|alloy_build_info"
+                keep_metrics = "up|alloy_build_info|alloy_component_controller_running_components|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_config_hash|alloy_resources_machine_rx_bytes_total|alloy_resources_machine_tx_bytes_total|alloy_resources_process_cpu_seconds_total|alloy_resources_process_resident_memory_bytes|alloy_tcp_connections|alloy_wal_samples_appended_total|alloy_wal_storage_active_series|cluster_node_gossip_health_score|cluster_node_gossip_proto_version|cluster_node_gossip_received_events_total|cluster_node_info|cluster_node_lamport_time|cluster_node_peers|cluster_node_update_observers|cluster_transport_rx_bytes_total|cluster_transport_rx_packet_queue_length|cluster_transport_rx_packets_failed_total|cluster_transport_rx_packets_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_failed_total|cluster_transport_stream_tx_packets_total|cluster_transport_streams|cluster_transport_tx_bytes_total|cluster_transport_tx_packet_queue_length|cluster_transport_tx_packets_failed_total|cluster_transport_tx_packets_total|otelcol_exporter_send_failed_spans_total|otelcol_exporter_sent_spans_total|go_gc_duration_seconds_count|go_goroutines|go_memstats_heap_inuse_bytes|loki_process_dropped_lines_total|loki_write_batch_retries_total|loki_write_dropped_bytes_total|loki_write_dropped_entries_total|loki_write_encoded_bytes_total|loki_write_mutated_bytes_total|loki_write_mutated_entries_total|loki_write_request_duration_seconds_bucket|loki_write_sent_bytes_total|loki_write_sent_entries_total|process_cpu_seconds_total|process_start_time_seconds|otelcol_processor_batch_batch_send_size_bucket|otelcol_processor_batch_metadata_cardinality|otelcol_processor_batch_timeout_trigger_send_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|otelcol_receiver_accepted_spans_total|otelcol_receiver_refused_spans_total|rpc_server_duration_milliseconds_bucket|scrape_duration_seconds|traces_exporter_send_failed_spans|traces_exporter_send_failed_spans_total|traces_exporter_sent_spans|traces_exporter_sent_spans_total|traces_loadbalancer_backend_outcome|traces_loadbalancer_num_backends|traces_receiver_accepted_spans|traces_receiver_accepted_spans_total|traces_receiver_refused_spans|traces_receiver_refused_spans_total"
                 scrape_interval = "60s"
                 max_cache_size = 100000
                 forward_to = argument.metrics_destinations.value

charts/feature-integrations/values.schema.json

@@ -87,9 +87,6 @@
                         },
                         "useDefaultAllowList": {
                             "type": "boolean"
-                        },
-                        "useIntegrationAllowList": {
-                            "type": "boolean"
                         }
                     }
                 },