diff --git a/charts/meta-monitoring/src/dashboards/alloy-cluster-node.json b/charts/meta-monitoring/src/dashboards/alloy-cluster-node.json index 5423937..3d6f22b 100644 --- a/charts/meta-monitoring/src/dashboards/alloy-cluster-node.json +++ b/charts/meta-monitoring/src/dashboards/alloy-cluster-node.json @@ -16,7 +16,7 @@ { "datasource": "$loki_datasource", "enable": true, - "expr": "{cluster=\"$cluster\", container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", + "expr": "{container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", "iconColor": "rgba(0, 211, 255, 1)", "instant": false, "name": "Deployments", @@ -115,7 +115,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(cluster_node_lamport_time{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "sum(cluster_node_lamport_time{instance=\"$instance\", namespace=\"$namespace\"})", "format": "table", "instant": true, "legendFormat": "__auto", @@ -124,7 +124,7 @@ }, { "datasource": "${datasource}", - "expr": "sum(cluster_node_update_observers{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "sum(cluster_node_update_observers{instance=\"$instance\", namespace=\"$namespace\"})", "format": "table", "instant": true, "legendFormat": "__auto", @@ -133,7 +133,7 @@ }, { "datasource": "${datasource}", - "expr": "sum(cluster_node_gossip_health_score{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "sum(cluster_node_gossip_health_score{instance=\"$instance\", namespace=\"$namespace\"})", "format": "table", "instant": true, "legendFormat": "__auto", @@ -142,7 +142,7 @@ }, { "datasource": "${datasource}", - "expr": "sum(cluster_node_gossip_proto_version{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "sum(cluster_node_gossip_proto_version{instance=\"$instance\", namespace=\"$namespace\"})", "format": "table", "instant": true, "legendFormat": "__auto", @@ -255,7 +255,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(cluster_node_gossip_received_events_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])", + "expr": "rate(cluster_node_gossip_received_events_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])", "instant": false, "legendFormat": "{{event}}", "range": true, @@ -315,7 +315,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(cluster_node_peers{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "sum(cluster_node_peers{instance=\"$instance\", namespace=\"$namespace\"})", "instant": false, "legendFormat": "__auto", "range": true, @@ -405,7 +405,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "cluster_node_peers{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}", + "expr": "cluster_node_peers{instance=\"$instance\", namespace=\"$namespace\"}", "instant": false, "legendFormat": "{{state}}", "range": true, @@ -506,7 +506,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(cluster_transport_rx_bytes_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])", + "expr": "rate(cluster_transport_rx_bytes_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])", "instant": false, "legendFormat": "rx", "range": true, @@ -514,7 +514,7 @@ }, { "datasource": "${datasource}", - "expr": "-1 * rate(cluster_transport_tx_bytes_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])", + "expr": "-1 * rate(cluster_transport_tx_bytes_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])", "instant": false, "legendFormat": "tx", "range": true, @@ -603,7 +603,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "1 - (\nrate(cluster_transport_tx_packets_failed_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) /\nrate(cluster_transport_tx_packets_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n)\n", + "expr": "1 - (\nrate(cluster_transport_tx_packets_failed_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval]) /\nrate(cluster_transport_tx_packets_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])\n)\n", "instant": false, "legendFormat": "Tx success %", "range": true, @@ -611,7 +611,7 @@ }, { "datasource": "${datasource}", - "expr": "1 - (\n rate(cluster_transport_rx_packets_failed_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) /\n rate(cluster_transport_rx_packets_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n )\n", + "expr": "1 - (\n rate(cluster_transport_rx_packets_failed_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval]) /\n rate(cluster_transport_rx_packets_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])\n )\n", "instant": false, "legendFormat": "Rx success %", "range": true, @@ -701,7 +701,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "cluster_transport_tx_packet_queue_length{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}", + "expr": "cluster_transport_tx_packet_queue_length{instance=\"$instance\", namespace=\"$namespace\"}", "instant": false, "legendFormat": "tx queue", "range": true, @@ -709,7 +709,7 @@ }, { "datasource": "${datasource}", - "expr": "cluster_transport_rx_packet_queue_length{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}", + "expr": "cluster_transport_rx_packet_queue_length{instance=\"$instance\", namespace=\"$namespace\"}", "instant": false, "legendFormat": "rx queue", "range": true, @@ -798,7 +798,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(cluster_transport_stream_rx_bytes_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])", + "expr": "rate(cluster_transport_stream_rx_bytes_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])", "instant": false, "legendFormat": "rx", "range": true, @@ -806,7 +806,7 @@ }, { "datasource": "${datasource}", - "expr": "-1 * rate(cluster_transport_stream_tx_bytes_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])", + "expr": "-1 * rate(cluster_transport_stream_tx_bytes_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])", "instant": false, "legendFormat": "tx", "range": true, @@ -895,7 +895,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "1 - (\n rate(cluster_transport_stream_tx_packets_failed_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) /\n rate(cluster_transport_stream_tx_packets_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n )\n", + "expr": "1 - (\n rate(cluster_transport_stream_tx_packets_failed_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval]) /\n rate(cluster_transport_stream_tx_packets_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])\n )\n", "instant": false, "legendFormat": "Tx success %", "range": true, @@ -903,7 +903,7 @@ }, { "datasource": "${datasource}", - "expr": "1 - (\n rate(cluster_transport_stream_rx_packets_failed_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) /\n rate(cluster_transport_stream_rx_packets_total{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n )\n", + "expr": "1 - (\n rate(cluster_transport_stream_rx_packets_failed_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval]) /\n rate(cluster_transport_stream_rx_packets_total{instance=\"$instance\", namespace=\"$namespace\"}[$__rate_interval])\n )\n", "instant": false, "legendFormat": "Rx success %", "range": true, @@ -992,7 +992,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "cluster_transport_streams{instance=\"$instance\", cluster=\"$cluster\", namespace=\"$namespace\"}", + "expr": "cluster_transport_streams{instance=\"$instance\", namespace=\"$namespace\"}", "instant": false, "legendFormat": "Open streams", "range": true, @@ -1122,7 +1122,7 @@ "name": "instance", "options": [], "query": { - "query": "label_values(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\"}, instance)\n", + "query": "label_values(alloy_component_controller_running_components{namespace=\"$namespace\"}, instance)\n", "refId": "instance" }, "refresh": 2, diff --git a/charts/meta-monitoring/src/dashboards/alloy-cluster-overview.json b/charts/meta-monitoring/src/dashboards/alloy-cluster-overview.json index a4f0bbe..a5fa677 100644 --- a/charts/meta-monitoring/src/dashboards/alloy-cluster-overview.json +++ b/charts/meta-monitoring/src/dashboards/alloy-cluster-overview.json @@ -16,7 +16,7 @@ { "datasource": "$loki_datasource", "enable": true, - "expr": "{cluster=\"$cluster\", container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", + "expr": "{container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", "iconColor": "rgba(0, 211, 255, 1)", "instant": false, "name": "Deployments", @@ -99,7 +99,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "count(cluster_node_info{cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "count(cluster_node_info{namespace=\"$namespace\"})", "instant": true, "legendFormat": "__auto", "range": false, @@ -194,7 +194,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "cluster_node_info{cluster=\"$cluster\", namespace=\"$namespace\"}", + "expr": "cluster_node_info{namespace=\"$namespace\"}", "format": "table", "instant": true, "legendFormat": "__auto", @@ -298,7 +298,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "clamp((\n sum(stddev by (state) (cluster_node_peers{cluster=\"$cluster\", namespace=\"$namespace\"}) != 0) or\n (sum(abs(sum without (state) (cluster_node_peers{cluster=\"$cluster\", namespace=\"$namespace\"})) - scalar(count(cluster_node_info{cluster=\"$cluster\", namespace=\"$namespace\"})) != 0))\n ),\n 1, 1\n)\n", + "expr": "clamp((\n sum(stddev by (state) (cluster_node_peers{namespace=\"$namespace\"}) != 0) or\n (sum(abs(sum without (state) (cluster_node_peers{namespace=\"$namespace\"})) - scalar(count(cluster_node_info{namespace=\"$namespace\"})) != 0))\n ),\n 1, 1\n)\n", "format": "time_series", "instant": true, "legendFormat": "__auto", @@ -390,7 +390,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "ceil(clamp((\n sum(stddev by (state) (cluster_node_peers{cluster=\"$cluster\", namespace=\"$namespace\"})) or\n (sum(abs(sum without (state) (cluster_node_peers{cluster=\"$cluster\", namespace=\"$namespace\"})) - scalar(count(cluster_node_info{cluster=\"$cluster\", namespace=\"$namespace\"}))))\n ),\n 0, 1\n))\n", + "expr": "ceil(clamp((\n sum(stddev by (state) (cluster_node_peers{namespace=\"$namespace\"})) or\n (sum(abs(sum without (state) (cluster_node_peers{namespace=\"$namespace\"})) - scalar(count(cluster_node_info{namespace=\"$namespace\"}))))\n ),\n 0, 1\n))\n", "instant": false, "legendFormat": "Converged", "range": true, diff --git a/charts/meta-monitoring/src/dashboards/alloy-controller.json b/charts/meta-monitoring/src/dashboards/alloy-controller.json index 8191007..dad80df 100644 --- a/charts/meta-monitoring/src/dashboards/alloy-controller.json +++ b/charts/meta-monitoring/src/dashboards/alloy-controller.json @@ -16,7 +16,7 @@ { "datasource": "$loki_datasource", "enable": true, - "expr": "{cluster=\"$cluster\", container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", + "expr": "{container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", "iconColor": "rgba(0, 211, 255, 1)", "instant": false, "name": "Deployments", @@ -101,7 +101,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "count(alloy_component_controller_evaluating{cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "count(alloy_component_controller_evaluating{namespace=\"$namespace\"})", "instant": false, "legendFormat": "__auto", "range": true, @@ -232,7 +232,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\", health_type=\"healthy\"}) or vector(0)", + "expr": "sum(alloy_component_controller_running_components{namespace=\"$namespace\", health_type=\"healthy\"}) or vector(0)", "instant": true, "legendFormat": "Healthy", "range": false, @@ -240,7 +240,7 @@ }, { "datasource": "${datasource}", - "expr": "sum(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\", health_type=\"unhealthy\"}) or vector(0)", + "expr": "sum(alloy_component_controller_running_components{namespace=\"$namespace\", health_type=\"unhealthy\"}) or vector(0)", "instant": true, "legendFormat": "Unhealthy", "range": false, @@ -248,7 +248,7 @@ }, { "datasource": "${datasource}", - "expr": "sum(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\", health_type=\"unknown\"}) or vector(0)", + "expr": "sum(alloy_component_controller_running_components{namespace=\"$namespace\", health_type=\"unknown\"}) or vector(0)", "instant": true, "legendFormat": "Unknown", "range": false, @@ -256,7 +256,7 @@ }, { "datasource": "${datasource}", - "expr": "sum(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\", health_type=\"exited\"}) or vector(0)", + "expr": "sum(alloy_component_controller_running_components{namespace=\"$namespace\", health_type=\"exited\"}) or vector(0)", "instant": true, "legendFormat": "Exited", "range": false, @@ -316,7 +316,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\"})", + "expr": "sum(alloy_component_controller_running_components{namespace=\"$namespace\"})", "instant": false, "legendFormat": "__auto", "range": true, @@ -382,7 +382,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\",health_type=\"healthy\"}) /\nsum(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\"})\n", + "expr": "sum(alloy_component_controller_running_components{namespace=\"$namespace\",health_type=\"healthy\"}) /\nsum(alloy_component_controller_running_components{namespace=\"$namespace\"})\n", "instant": false, "legendFormat": "__auto", "range": true, @@ -472,7 +472,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum by (instance) (rate(alloy_component_evaluation_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by (instance) (rate(alloy_component_evaluation_seconds_count{namespace=\"$namespace\"}[$__rate_interval]))", "instant": false, "legendFormat": "__auto", "range": true, @@ -668,7 +668,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum by (component_path, component_id) (rate(alloy_component_evaluation_slow_seconds{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))\n/ scalar(sum(rate(alloy_component_evaluation_seconds_sum{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])))\n", + "expr": "sum by (component_path, component_id) (rate(alloy_component_evaluation_slow_seconds{namespace=\"$namespace\"}[$__rate_interval]))\n/ scalar(sum(rate(alloy_component_evaluation_seconds_sum{namespace=\"$namespace\"}[$__rate_interval])))\n", "instant": false, "legendFormat": "{{component path}} {{component_id}}", "range": true, @@ -743,7 +743,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(increase(alloy_component_evaluation_seconds{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))\nor ignoring (le)\nsum by (le) (increase(alloy_component_evaluation_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))\n", + "expr": "sum(increase(alloy_component_evaluation_seconds{namespace=\"$namespace\"}[$__rate_interval]))\nor ignoring (le)\nsum by (le) (increase(alloy_component_evaluation_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval]))\n", "format": "heatmap", "instant": false, "legendFormat": "{{le}}", @@ -819,7 +819,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(increase(alloy_component_dependencies_wait_seconds{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))\nor ignoring (le)\nsum by (le) (increase(alloy_component_dependencies_wait_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))\n", + "expr": "sum(increase(alloy_component_dependencies_wait_seconds{namespace=\"$namespace\"}[$__rate_interval]))\nor ignoring (le)\nsum by (le) (increase(alloy_component_dependencies_wait_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval]))\n", "format": "heatmap", "instant": false, "legendFormat": "{{le}}", diff --git a/charts/meta-monitoring/src/dashboards/alloy-opentelemetry.json b/charts/meta-monitoring/src/dashboards/alloy-opentelemetry.json index c8e837f..26f5389 100644 --- a/charts/meta-monitoring/src/dashboards/alloy-opentelemetry.json +++ b/charts/meta-monitoring/src/dashboards/alloy-opentelemetry.json @@ -125,7 +125,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(receiver_accepted_spans_ratio_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", + "expr": "rate(receiver_accepted_spans_ratio_total{namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", "instant": false, "legendFormat": "{{ pod }} / {{ transport }}", "range": true, @@ -214,7 +214,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(receiver_refused_spans_ratio_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", + "expr": "rate(receiver_refused_spans_ratio_total{namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", "instant": false, "legendFormat": "{{ pod }} / {{ transport }}", "range": true, @@ -289,7 +289,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum by (le) (increase(rpc_server_duration_milliseconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", rpc_service=\"opentelemetry.proto.collector.trace.v1.TraceService\"}[$__rate_interval]))", + "expr": "sum by (le) (increase(rpc_server_duration_milliseconds_bucket{namespace=\"$namespace\", instance=~\"$instance\", rpc_service=\"opentelemetry.proto.collector.trace.v1.TraceService\"}[$__rate_interval]))", "format": "heatmap", "instant": false, "legendFormat": "{{le}}", @@ -377,7 +377,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum by (le) (increase(processor_batch_batch_send_size_ratio_bucket{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval]))", + "expr": "sum by (le) (increase(processor_batch_batch_send_size_ratio_bucket{namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval]))", "format": "heatmap", "instant": false, "legendFormat": "{{le}}", @@ -467,7 +467,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "processor_batch_metadata_cardinality_ratio{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\"}\n", + "expr": "processor_batch_metadata_cardinality_ratio{namespace=\"$namespace\", instance=~\"$instance\"}\n", "instant": false, "legendFormat": "{{ pod }}", "range": true, @@ -556,7 +556,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(processor_batch_timeout_trigger_send_ratio_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", + "expr": "rate(processor_batch_timeout_trigger_send_ratio_total{namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", "instant": false, "legendFormat": "{{ pod }}", "range": true, @@ -657,7 +657,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(exporter_sent_spans_ratio_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", + "expr": "rate(exporter_sent_spans_ratio_total{namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", "instant": false, "legendFormat": "{{ pod }}", "range": true, @@ -746,7 +746,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "rate(exporter_send_failed_spans_ratio_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", + "expr": "rate(exporter_send_failed_spans_ratio_total{namespace=\"$namespace\", instance=~\"$instance\"}[$__rate_interval])\n", "instant": false, "legendFormat": "{{ pod }}", "range": true, @@ -874,7 +874,7 @@ "name": "instance", "options": [], "query": { - "query": "label_values(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\"}, instance)\n", + "query": "label_values(alloy_component_controller_running_components{namespace=\"$namespace\"}, instance)\n", "refId": "instance" }, "refresh": 2, diff --git a/charts/meta-monitoring/src/dashboards/alloy-prometheus.json b/charts/meta-monitoring/src/dashboards/alloy-prometheus.json index 1f73748..82c7a8c 100644 --- a/charts/meta-monitoring/src/dashboards/alloy-prometheus.json +++ b/charts/meta-monitoring/src/dashboards/alloy-prometheus.json @@ -16,7 +16,7 @@ { "datasource": "$loki_datasource", "enable": true, - "expr": "{cluster=\"$cluster\", container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", + "expr": "{container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", "iconColor": "rgba(0, 211, 255, 1)", "instant": false, "name": "Deployments", @@ -353,7 +353,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum by (instance, component_path, component_id) (\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\"}\n - ignoring(url, remote_name) group_right(instance)\n prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", + "expr": "sum by (instance, component_path, component_id) (\n prometheus_remote_storage_highest_timestamp_in_seconds{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\"}\n - ignoring(url, remote_name) group_right(instance)\n prometheus_remote_storage_queue_highest_sent_timestamp_seconds{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", "instant": false, "legendFormat": "{{instance}} / {{component_path}} {{component_id}}", "range": true, @@ -443,7 +443,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum without (remote_name, url) (\n rate(prometheus_remote_storage_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval]) +\n rate(prometheus_remote_storage_metadata_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", + "expr": "sum without (remote_name, url) (\n rate(prometheus_remote_storage_bytes_total{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval]) +\n rate(prometheus_remote_storage_metadata_bytes_total{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", "instant": false, "legendFormat": "{{instance}} / {{component_path}} {{component_id}}", "range": true, @@ -700,7 +700,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum without (remote_name, url) (\n prometheus_remote_storage_shards{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", + "expr": "sum without (remote_name, url) (\n prometheus_remote_storage_shards{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", "instant": false, "legendFormat": "{{instance}} / {{component_path}} {{component_id}}", "range": true, @@ -708,7 +708,7 @@ }, { "datasource": "${datasource}", - "expr": "min (\n prometheus_remote_storage_shards_min{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", + "expr": "min (\n prometheus_remote_storage_shards_min{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", "instant": false, "legendFormat": "Minimum", "range": true, @@ -716,7 +716,7 @@ }, { "datasource": "${datasource}", - "expr": "max (\n prometheus_remote_storage_shards_max{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", + "expr": "max (\n prometheus_remote_storage_shards_max{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n)\n", "instant": false, "legendFormat": "Maximum", "range": true, @@ -806,7 +806,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum without (url, remote_name) (\n rate(prometheus_remote_storage_samples_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", + "expr": "sum without (url, remote_name) (\n rate(prometheus_remote_storage_samples_total{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", "instant": false, "legendFormat": "{{instance}} / {{component_path}} {{component_id}}", "range": true, @@ -896,7 +896,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum without (url,remote_name) (\n rate(prometheus_remote_storage_samples_failed_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", + "expr": "sum without (url,remote_name) (\n rate(prometheus_remote_storage_samples_failed_total{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", "instant": false, "legendFormat": "{{instance}} / {{component_path}} {{component_id}}", "range": true, @@ -986,7 +986,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum without (url,remote_name) (\n rate(prometheus_remote_storage_samples_retried_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", + "expr": "sum without (url,remote_name) (\n rate(prometheus_remote_storage_samples_retried_total{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}[$__rate_interval])\n)\n", "instant": false, "legendFormat": "{{instance}} / {{component_path}} {{component_id}}", "range": true, @@ -1021,7 +1021,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum(prometheus_remote_write_wal_storage_active_series{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"})\n", + "expr": "sum(prometheus_remote_write_wal_storage_active_series{namespace=\"$namespace\", instance=~\"$instance\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"})\n", "instant": false, "legendFormat": "Series", "range": true, @@ -1050,7 +1050,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "prometheus_remote_write_wal_storage_active_series{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_id!=\"\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n", + "expr": "prometheus_remote_write_wal_storage_active_series{namespace=\"$namespace\", instance=~\"$instance\", component_id!=\"\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"}\n", "instant": false, "legendFormat": "{{instance}} / {{component_path}} {{component_id}}", "range": true, @@ -1079,7 +1079,7 @@ "targets": [ { "datasource": "${datasource}", - "expr": "sum by (component_path, component_id) (prometheus_remote_write_wal_storage_active_series{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_id!=\"\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"})\n", + "expr": "sum by (component_path, component_id) (prometheus_remote_write_wal_storage_active_series{namespace=\"$namespace\", instance=~\"$instance\", component_id!=\"\", component_path=~\"$component_path\", component_id=~\"$component\", url=~\"$url\"})\n", "instant": false, "legendFormat": "{{component_path}} {{component_id}}", "range": true, @@ -1207,7 +1207,7 @@ "name": "instance", "options": [], "query": { - "query": "label_values(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\"}, instance)\n", + "query": "label_values(alloy_component_controller_running_components{namespace=\"$namespace\"}, instance)\n", "refId": "instance" }, "refresh": 2, @@ -1234,7 +1234,7 @@ "name": "component_path", "options": [], "query": { - "query": "label_values(prometheus_remote_write_wal_samples_appended_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_id=~\"prometheus\\\\.remote_write\\\\..*\", component_path=~\".*\"}, component_path)\n", + "query": "label_values(prometheus_remote_write_wal_samples_appended_total{namespace=\"$namespace\", instance=~\"$instance\", component_id=~\"prometheus\\\\.remote_write\\\\..*\", component_path=~\".*\"}, component_path)\n", "refId": "component_path" }, "refresh": 2, @@ -1261,7 +1261,7 @@ "name": "component", "options": [], "query": { - "query": "label_values(prometheus_remote_write_wal_samples_appended_total{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_id=~\"prometheus\\\\.remote_write\\\\..*\"}, component_id)\n", + "query": "label_values(prometheus_remote_write_wal_samples_appended_total{namespace=\"$namespace\", instance=~\"$instance\", component_id=~\"prometheus\\\\.remote_write\\\\..*\"}, component_id)\n", "refId": "component" }, "refresh": 2, @@ -1288,7 +1288,7 @@ "name": "url", "options": [], "query": { - "query": "label_values(prometheus_remote_storage_sent_batch_duration_seconds_sum{cluster=\"$cluster\", namespace=\"$namespace\", instance=~\"$instance\", component_id=~\"$component\"}, url)\n", + "query": "label_values(prometheus_remote_storage_sent_batch_duration_seconds_sum{namespace=\"$namespace\", instance=~\"$instance\", component_id=~\"$component\"}, url)\n", "refId": "url" }, "refresh": 2, diff --git a/charts/meta-monitoring/src/dashboards/alloy-resources.json b/charts/meta-monitoring/src/dashboards/alloy-resources.json index 0071006..e1955f8 100644 --- a/charts/meta-monitoring/src/dashboards/alloy-resources.json +++ b/charts/meta-monitoring/src/dashboards/alloy-resources.json @@ -16,7 +16,7 @@ { "datasource": "$loki_datasource", "enable": true, - "expr": "{cluster=\"$cluster\", container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", + "expr": "{container=\"kube-diff-logger\"} | json | namespace_extracted=\"alloy\" | name_extracted=~\"alloy.*\"", "iconColor": "rgba(0, 211, 255, 1)", "instant": false, "name": "Deployments", @@ -791,7 +791,7 @@ "name": "instance", "options": [], "query": { - "query": "label_values(alloy_component_controller_running_components{cluster=\"$cluster\", namespace=\"$namespace\"}, instance)\n", + "query": "label_values(alloy_component_controller_running_components{namespace=\"$namespace\"}, instance)\n", "refId": "instance" }, "refresh": 2, diff --git a/charts/meta-monitoring/src/dashboards/loki-chunks.json b/charts/meta-monitoring/src/dashboards/loki-chunks.json index a1254e8..5a5f487 100644 --- a/charts/meta-monitoring/src/dashboards/loki-chunks.json +++ b/charts/meta-monitoring/src/dashboards/loki-chunks.json @@ -65,7 +65,7 @@ "span": 6, "targets": [ { - "expr": "sum(loki_ingester_memory_chunks{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"})", + "expr": "sum(loki_ingester_memory_chunks{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"})", "format": "time_series", "legendFormat": "series", "legendLink": null @@ -113,7 +113,7 @@ "span": 6, "targets": [ { - "expr": "sum(loki_ingester_memory_chunks{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}) / sum(loki_ingester_memory_streams{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"})", + "expr": "sum(loki_ingester_memory_chunks{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}) / sum(loki_ingester_memory_streams{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"})", "format": "time_series", "legendFormat": "chunks", "legendLink": null @@ -174,19 +174,19 @@ "span": 6, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", + "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_utilization_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", "format": "time_series", "legendFormat": "99th Percentile", "refId": "A" }, { - "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", + "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_utilization_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", "format": "time_series", "legendFormat": "50th Percentile", "refId": "B" }, { - "expr": "sum(rate(loki_ingester_chunk_utilization_sum{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) * 1 / sum(rate(loki_ingester_chunk_utilization_count{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum(rate(loki_ingester_chunk_utilization_sum{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) * 1 / sum(rate(loki_ingester_chunk_utilization_count{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "time_series", "legendFormat": "Average", "refId": "C" @@ -253,19 +253,19 @@ "span": 6, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_age_seconds_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1e3", + "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_age_seconds_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1e3", "format": "time_series", "legendFormat": "99th Percentile", "refId": "A" }, { - "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_age_seconds_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1e3", + "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_age_seconds_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1e3", "format": "time_series", "legendFormat": "50th Percentile", "refId": "B" }, { - "expr": "sum(rate(loki_ingester_chunk_age_seconds_sum{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) * 1e3 / sum(rate(loki_ingester_chunk_age_seconds_count{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum(rate(loki_ingester_chunk_age_seconds_sum{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) * 1e3 / sum(rate(loki_ingester_chunk_age_seconds_count{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "time_series", "legendFormat": "Average", "refId": "C" @@ -344,19 +344,19 @@ "span": 6, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_entries_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", + "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_entries_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", "format": "time_series", "legendFormat": "99th Percentile", "refId": "A" }, { - "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_entries_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", + "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_entries_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)) * 1", "format": "time_series", "legendFormat": "50th Percentile", "refId": "B" }, { - "expr": "sum(rate(loki_ingester_chunk_entries_sum{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) * 1 / sum(rate(loki_ingester_chunk_entries_count{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum(rate(loki_ingester_chunk_entries_sum{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) * 1 / sum(rate(loki_ingester_chunk_entries_count{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "time_series", "legendFormat": "Average", "refId": "C" @@ -422,7 +422,7 @@ "span": 6, "targets": [ { - "expr": "sum(rate(loki_chunk_store_index_entries_per_chunk_sum{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) / sum(rate(loki_chunk_store_index_entries_per_chunk_count{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum(rate(loki_chunk_store_index_entries_per_chunk_sum{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) / sum(rate(loki_chunk_store_index_entries_per_chunk_count{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "time_series", "legendFormat": "Index Entries", "legendLink": null @@ -482,7 +482,7 @@ "span": 6, "targets": [ { - "expr": "loki_ingester_flush_queue_length{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"} or cortex_ingester_flush_queue_length{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}", + "expr": "loki_ingester_flush_queue_length{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"} or cortex_ingester_flush_queue_length{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}", "format": "time_series", "legendFormat": "{{pod}}", "legendLink": null @@ -681,7 +681,7 @@ "stack": true, "targets": [ { - "expr": "sum by (status) (\n label_replace(label_replace(rate(loki_ingester_chunk_age_seconds_count{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", + "expr": "sum by (status) (\n label_replace(label_replace(rate(loki_ingester_chunk_age_seconds_count{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", "format": "time_series", "legendFormat": "{{status}}", "refId": "A" @@ -741,7 +741,7 @@ "span": 6, "targets": [ { - "expr": "sum(rate(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum(rate(loki_ingester_chunks_flushed_total{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "time_series", "legendFormat": "{{pod}}", "legendLink": null @@ -790,7 +790,7 @@ "stack": true, "targets": [ { - "expr": "sum by (reason) (rate(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum by (reason) (rate(loki_ingester_chunks_flushed_total{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "time_series", "legendFormat": "{{reason}}", "legendLink": null @@ -854,7 +854,7 @@ "span": 12, "targets": [ { - "expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "heatmap", "intervalFactor": 2, "legendFormat": "{{le}}", @@ -917,7 +917,7 @@ "span": 12, "targets": [ { - "expr": "sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)", + "expr": "sum(rate(loki_ingester_chunk_size_bytes_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le)", "format": "heatmap", "intervalFactor": 2, "legendFormat": "{{le}}", @@ -994,19 +994,19 @@ "span": 12, "targets": [ { - "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", + "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_size_bytes_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", "format": "time_series", "legendFormat": "p99", "legendLink": null }, { - "expr": "histogram_quantile(0.90, sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", + "expr": "histogram_quantile(0.90, sum(rate(loki_ingester_chunk_size_bytes_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", "format": "time_series", "legendFormat": "p90", "legendLink": null }, { - "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", + "expr": "histogram_quantile(0.50, sum(rate(loki_ingester_chunk_size_bytes_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", "format": "time_series", "legendFormat": "p50", "legendLink": null @@ -1066,19 +1066,19 @@ "span": 12, "targets": [ { - "expr": "histogram_quantile(0.5, sum(rate(loki_ingester_chunk_bounds_hours_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", + "expr": "histogram_quantile(0.5, sum(rate(loki_ingester_chunk_bounds_hours_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", "format": "time_series", "legendFormat": "p50", "legendLink": null }, { - "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_bounds_hours_bucket{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", + "expr": "histogram_quantile(0.99, sum(rate(loki_ingester_chunk_bounds_hours_bucket{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (le))", "format": "time_series", "legendFormat": "p99", "legendLink": null }, { - "expr": "sum(rate(loki_ingester_chunk_bounds_hours_sum{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) / sum(rate(loki_ingester_chunk_bounds_hours_count{cluster=\"$cluster\", job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum(rate(loki_ingester_chunk_bounds_hours_sum{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) / sum(rate(loki_ingester_chunk_bounds_hours_count{job=~\"$namespace/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "time_series", "legendFormat": "avg", "legendLink": null diff --git a/charts/meta-monitoring/src/dashboards/loki-logs.json b/charts/meta-monitoring/src/dashboards/loki-logs.json index 84ad5a3..9179f53 100644 --- a/charts/meta-monitoring/src/dashboards/loki-logs.json +++ b/charts/meta-monitoring/src/dashboards/loki-logs.json @@ -64,7 +64,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(go_goroutines{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"})", + "expr": "sum(go_goroutines{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"})", "refId": "A" } ], @@ -156,7 +156,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(go_gc_duration_seconds{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}) by (quantile)", + "expr": "sum(go_gc_duration_seconds{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}) by (quantile)", "legendFormat": "{{quantile}}", "refId": "A" } @@ -244,7 +244,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(container_cpu_usage_seconds_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[$__rate_interval]))", + "expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[$__rate_interval]))", "refId": "A" } ], @@ -336,7 +336,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"})", + "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"})", "refId": "A" } ], @@ -428,7 +428,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))", + "expr": "sum(rate(container_network_transmit_bytes_total{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))", "refId": "A" } ], @@ -520,7 +520,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))", + "expr": "sum(rate(container_network_receive_bytes_total{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[$__rate_interval]))", "refId": "A" } ], @@ -607,7 +607,7 @@ "steppedLine": false, "targets": [ { - "expr": "increase(kube_pod_container_status_last_terminated_reason{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[30m]) > 0", + "expr": "increase(kube_pod_container_status_last_terminated_reason{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[30m]) > 0", "legendFormat": "{{reason}}", "refId": "A" } @@ -700,7 +700,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(promtail_custom_bad_words_total{cluster=\"$cluster\", exported_namespace=\"$namespace\", exported_pod=~\"$deployment.*\", exported_pod=~\"$pod\", container=~\"$container\"}[$__rate_interval])) by (level)", + "expr": "sum(rate(promtail_custom_bad_words_total{exported_namespace=\"$namespace\", exported_pod=~\"$deployment.*\", exported_pod=~\"$pod\", container=~\"$container\"}[$__rate_interval])) by (level)", "legendFormat": "{{level}}", "refId": "A" } @@ -810,7 +810,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\" } |logfmt| level=\"$level\" |= \"$filter\" | __error__=\"\" [$__interval])) by (level)", + "expr": "sum(rate({namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\" } |logfmt| level=\"$level\" |= \"$filter\" | __error__=\"\" [$__interval])) by (level)", "intervalFactor": 3, "legendFormat": "{{level}}", "refId": "A" @@ -876,7 +876,7 @@ }, "targets": [ { - "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"} | logfmt | level=\"$level\" |= \"$filter\"", + "expr": "{namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"} | logfmt | level=\"$level\" |= \"$filter\"", "refId": "A" } ], @@ -975,7 +975,7 @@ "multi": false, "name": "deployment", "options": [ ], - "query": "label_values(kube_deployment_created{cluster=\"$cluster\", namespace=\"$namespace\"}, deployment)", + "query": "label_values(kube_deployment_created{namespace=\"$namespace\"}, deployment)", "refresh": 0, "regex": "", "sort": 1, @@ -995,7 +995,7 @@ "multi": false, "name": "pod", "options": [ ], - "query": "label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\"}, pod)", + "query": "label_values(kube_pod_container_info{namespace=\"$namespace\", pod=~\"$deployment.*\"}, pod)", "refresh": 0, "regex": "", "sort": 1, @@ -1015,7 +1015,7 @@ "multi": false, "name": "container", "options": [ ], - "query": "label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\", pod=~\"$deployment.*\"}, container)", + "query": "label_values(kube_pod_container_info{namespace=\"$namespace\", pod=~\"$pod\", pod=~\"$deployment.*\"}, container)", "refresh": 0, "regex": "", "sort": 1, diff --git a/charts/meta-monitoring/src/dashboards/loki-operational.json b/charts/meta-monitoring/src/dashboards/loki-operational.json index e0490b1..045f296 100644 --- a/charts/meta-monitoring/src/dashboards/loki-operational.json +++ b/charts/meta-monitoring/src/dashboards/loki-operational.json @@ -89,7 +89,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum by (status) (\nlabel_replace(\n label_replace(\n rate(loki_request_duration_seconds_count{cluster=\"$cluster\", job=~\"($namespace)/(.*query-frontend|(loki|enterprise-logs)-read|loki-single-binary)\", route=~\"api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n\"status\", \"${1}\", \"status_code\", \"([a-z]+)\")\n)", + "expr": "sum by (status) (\nlabel_replace(\n label_replace(\n rate(loki_request_duration_seconds_count{job=~\"($namespace)/(.*query-frontend|(loki|enterprise-logs)-read|loki-single-binary)\", route=~\"api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n\"status\", \"${1}\", \"status_code\", \"([a-z]+)\")\n)", "legendFormat": "{{status}}", "refId": "A" } @@ -186,7 +186,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum by (status) (\nlabel_replace(\n label_replace(\n rate(loki_request_duration_seconds_count{cluster=\"$cluster\", job=~\"($namespace)/(.*distributor|(loki|enterprise-logs)-write|loki-single-binary)\", route=~\"api_prom_push|loki_api_v1_push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n\"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))", + "expr": "sum by (status) (\nlabel_replace(\n label_replace(\n rate(loki_request_duration_seconds_count{job=~\"($namespace)/(.*distributor|(loki|enterprise-logs)-write|loki-single-binary)\", route=~\"api_prom_push|loki_api_v1_push\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n\"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))", "legendFormat": "{{status}}", "refId": "A" } @@ -281,7 +281,7 @@ "steppedLine": false, "targets": [ { - "expr": "topk(10, sum(rate(loki_distributor_lines_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (tenant))", + "expr": "topk(10, sum(rate(loki_distributor_lines_received_total{namespace=\"$namespace\"}[$__rate_interval])) by (tenant))", "legendFormat": "{{tenant}}", "refId": "A" } @@ -379,7 +379,7 @@ "steppedLine": false, "targets": [ { - "expr": "topk(10, sum(rate(loki_distributor_bytes_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (tenant)) / 1024 / 1024", + "expr": "topk(10, sum(rate(loki_distributor_bytes_received_total{namespace=\"$namespace\"}[$__rate_interval])) by (tenant)) / 1024 / 1024", "legendFormat": "{{tenant}}", "refId": "A" } @@ -474,7 +474,7 @@ "steppedLine": false, "targets": [ { - "expr": "increase(kube_pod_container_status_restarts_total{cluster=\"$cluster\", namespace=\"$namespace\"}[10m]) > 0", + "expr": "increase(kube_pod_container_status_restarts_total{namespace=\"$namespace\"}[10m]) > 0", "hide": false, "interval": "", "legendFormat": "{{container}}-{{pod}}", @@ -789,7 +789,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*distributor|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*distributor|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", + "expr": "sum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*distributor|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*distributor|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", "interval": "", "legendFormat": "{{route}}", "refId": "A" @@ -998,7 +998,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route) > 0", + "expr": "sum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", route=\"/logproto.Pusher/Push\"}[$__rate_interval])) by (route) > 0", "interval": "", "legendFormat": "{{route}}", "refId": "A" @@ -1315,7 +1315,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*querier|(loki|enterprise-logs)-read|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*querier|(loki|enterprise-logs)-read|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", + "expr": "sum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*querier|(loki|enterprise-logs)-read|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*querier|(loki|enterprise-logs)-read|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", "interval": "", "legendFormat": "{{route}}", "refId": "A" @@ -1523,7 +1523,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route) > 0", + "expr": "sum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[$__rate_interval])) by (route) > 0", "interval": "", "legendFormat": "{{route}}", "refId": "A" @@ -1921,7 +1921,7 @@ "steppedLine": false, "targets": [ { - "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"(.*/.*distributor|$namespace/(loki|enterprise-logs)-write|.*/loki|$namespace/loki-single-binary)\"}", + "expr": "go_memstats_heap_inuse_bytes{namespace=\"$namespace\", job=~\"(.*/.*distributor|$namespace/(loki|enterprise-logs)-write|.*/loki|$namespace/loki-single-binary)\"}", "instant": false, "intervalFactor": 3, "legendFormat": "{{pod}}", @@ -2017,7 +2017,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\"} | logfmt | level=\"error\"[$__interval]))", + "expr": "sum(rate({namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\"} | logfmt | level=\"error\"[$__interval]))", "refId": "A" } ], @@ -2081,7 +2081,7 @@ "panels": [ ], "targets": [ { - "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\"} |= \"level=error\"", + "expr": "{namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\"} |= \"level=error\"", "refId": "A" } ], @@ -2133,7 +2133,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", + "expr": "sum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*distributor.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", "interval": "", "intervalFactor": 1, "legendFormat": "{{route}}", @@ -2229,7 +2229,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "expr": "sum(rate(loki_distributor_ingester_append_failures_total{namespace=\"$namespace\"}[$__rate_interval])) by (pod)", "intervalFactor": 1, "legendFormat": "{{pod}}", "refId": "A" @@ -2324,7 +2324,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_distributor_bytes_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "expr": "sum(rate(loki_distributor_bytes_received_total{namespace=\"$namespace\"}[$__rate_interval])) by (pod)", "intervalFactor": 1, "legendFormat": "{{pod}}", "refId": "A" @@ -2419,7 +2419,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_distributor_lines_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "expr": "sum(rate(loki_distributor_lines_received_total{namespace=\"$namespace\"}[$__rate_interval])) by (pod)", "intervalFactor": 1, "legendFormat": "{{pod}}", "refId": "A" @@ -2622,7 +2622,7 @@ "steppedLine": false, "targets": [ { - "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write.*|loki-single-binary|$namespace-[0-9]+)\"}", + "expr": "go_memstats_heap_inuse_bytes{namespace=\"$namespace\", pod=~\"(.*ingester.*|(loki|enterprise-logs)-write.*|loki-single-binary|$namespace-[0-9]+)\"}", "instant": false, "intervalFactor": 3, "legendFormat": "{{pod}}", @@ -2718,7 +2718,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"} | logfmt | level=\"error\"[$__interval]))", + "expr": "sum(rate({namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"} | logfmt | level=\"error\"[$__interval]))", "refId": "A" } ], @@ -2782,7 +2782,7 @@ "panels": [ ], "targets": [ { - "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"} |= \"level=error\"", + "expr": "{namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"} |= \"level=error\"", "refId": "A" } ], @@ -2834,7 +2834,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", + "expr": "sum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", "interval": "", "intervalFactor": 1, "legendFormat": "{{route}}", @@ -3152,7 +3152,7 @@ "refId": "A" }, { - "expr": "sum(increase(loki_chunk_store_deduped_chunks_total{cluster=\"$cluster\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))/sum(increase(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) < 1", + "expr": "sum(increase(loki_chunk_store_deduped_chunks_total{job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))/sum(increase(loki_ingester_chunks_flushed_total{job=~\"($namespace)/(.*ingester.*|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval])) < 1", "interval": "", "legendFormat": "De-Dupe Ratio", "refId": "B" @@ -3388,7 +3388,7 @@ "reverseYBuckets": false, "targets": [ { - "expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", + "expr": "sum by (le) (rate(loki_ingester_chunk_utilization_bucket{job=~\"($namespace)/(.*ingester|(loki|enterprise-logs)-write|loki-single-binary)\"}[$__rate_interval]))", "format": "heatmap", "instant": false, "interval": "", @@ -3578,7 +3578,7 @@ "steppedLine": false, "targets": [ { - "expr": "go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read.*|.*loki-single-binary|$namespace-[0-9]+)\"}", + "expr": "go_memstats_heap_inuse_bytes{namespace=\"$namespace\", pod=~\"(.*querier.*|(loki|enterprise-logs)-read.*|.*loki-single-binary|$namespace-[0-9]+)\"}", "instant": false, "intervalFactor": 3, "legendFormat": "{{pod}}", @@ -3674,7 +3674,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\"} | logfmt | level=\"error\"[$__interval]))", + "expr": "sum(rate({namespace=\"$namespace\", job=~\"($namespace)/(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\"} | logfmt | level=\"error\"[$__interval]))", "refId": "A" } ], @@ -3737,7 +3737,7 @@ "panels": [ ], "targets": [ { - "expr": "{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(querier|(loki|enterprise-logs)-read|loki-single-binary)\"} |= \"level=error\"", + "expr": "{namespace=\"$namespace\", job=~\"($namespace)/(querier|(loki|enterprise-logs)-read|loki-single-binary)\"} |= \"level=error\"", "refId": "A" } ], @@ -3789,7 +3789,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", + "expr": "sum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\", status_code!~\"5[0-9]{2}\"}[$__rate_interval])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{namespace=\"$namespace\", job=~\"($namespace)/(.*querier.*|(loki|enterprise-logs)-read|loki-single-binary)\"}[$__rate_interval])) by (route) > 0", "interval": "", "intervalFactor": 1, "legendFormat": "{{route}}", @@ -3903,19 +3903,19 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(.99, sum(rate(loki_memcache_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (method, name, le, container))", + "expr": "histogram_quantile(.99, sum(rate(loki_memcache_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (method, name, le, container))", "intervalFactor": 1, "legendFormat": "{{container}}: .99-{{method}}-{{name}}", "refId": "A" }, { - "expr": "histogram_quantile(.9, sum(rate(loki_memcache_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (method, name, le, container))", + "expr": "histogram_quantile(.9, sum(rate(loki_memcache_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (method, name, le, container))", "hide": false, "legendFormat": "{{container}}: .9-{{method}}-{{name}}", "refId": "B" }, { - "expr": "histogram_quantile(.5, sum(rate(loki_memcache_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (method, name, le, container))", + "expr": "histogram_quantile(.5, sum(rate(loki_memcache_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (method, name, le, container))", "hide": false, "legendFormat": "{{container}}: .5-{{method}}-{{name}}", "refId": "C" @@ -4007,7 +4007,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_memcache_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (status_code, method, name, container)", + "expr": "sum(rate(loki_memcache_request_duration_seconds_count{namespace=\"$namespace\"}[$__rate_interval])) by (status_code, method, name, container)", "intervalFactor": 1, "legendFormat": "{{container}}: {{status_code}}-{{method}}-{{name}}", "refId": "A" @@ -4120,19 +4120,19 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(.99, sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.99, sum(rate(loki_consul_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "intervalFactor": 1, "legendFormat": ".99-{{operation}}", "refId": "A" }, { - "expr": "histogram_quantile(.9, sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.9, sum(rate(loki_consul_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".9-{{operation}}", "refId": "B" }, { - "expr": "histogram_quantile(.5, sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.5, sum(rate(loki_consul_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".5-{{operation}}", "refId": "C" @@ -4229,7 +4229,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, status_code, method)", + "expr": "sum(rate(loki_consul_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, status_code, method)", "intervalFactor": 1, "legendFormat": "{{status_code}}-{{operation}}", "refId": "A" @@ -4342,19 +4342,19 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(.99, sum(rate(loki_gcs_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.99, sum(rate(loki_gcs_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "intervalFactor": 1, "legendFormat": ".99-{{operation}}", "refId": "A" }, { - "expr": "histogram_quantile(.9, sum(rate(loki_gcs_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.9, sum(rate(loki_gcs_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".9-{{operation}}", "refId": "B" }, { - "expr": "histogram_quantile(.5, sum(rate(loki_gcs_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.5, sum(rate(loki_gcs_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".5-{{operation}}", "refId": "C" @@ -4446,7 +4446,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_gcs_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", + "expr": "sum(rate(loki_gcs_request_duration_seconds_count{namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", "intervalFactor": 1, "legendFormat": "{{status_code}}-{{operation}}", "refId": "A" @@ -4558,19 +4558,19 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(.99, sum(rate(loki_s3_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.99, sum(rate(loki_s3_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "intervalFactor": 1, "legendFormat": ".99-{{operation}}", "refId": "A" }, { - "expr": "histogram_quantile(.9, sum(rate(loki_s3_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.9, sum(rate(loki_s3_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".9-{{operation}}", "refId": "B" }, { - "expr": "histogram_quantile(.5, sum(rate(loki_s3_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.5, sum(rate(loki_s3_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".5-{{operation}}", "refId": "C" @@ -4661,7 +4661,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_s3_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", + "expr": "sum(rate(loki_s3_request_duration_seconds_count{namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", "intervalFactor": 1, "legendFormat": "{{status_code}}-{{operation}}", "refId": "A" @@ -4773,19 +4773,19 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(.99, sum(rate(loki_azure_blob_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.99, sum(rate(loki_azure_blob_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "intervalFactor": 1, "legendFormat": ".99-{{operation}}", "refId": "A" }, { - "expr": "histogram_quantile(.9, sum(rate(loki_azure_blob_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.9, sum(rate(loki_azure_blob_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".9-{{operation}}", "refId": "B" }, { - "expr": "histogram_quantile(.5, sum(rate(loki_azure_blob_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.5, sum(rate(loki_azure_blob_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".5-{{operation}}", "refId": "C" @@ -4876,7 +4876,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_azure_blob_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", + "expr": "sum(rate(loki_azure_blob_request_duration_seconds_count{namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", "intervalFactor": 1, "legendFormat": "{{status_code}}-{{operation}}", "refId": "A" @@ -4988,19 +4988,19 @@ "steppedLine": false, "targets": [ { - "expr": "histogram_quantile(.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "intervalFactor": 1, "legendFormat": ".99-{{operation}}", "refId": "A" }, { - "expr": "histogram_quantile(.9, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.9, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".9-{{operation}}", "refId": "B" }, { - "expr": "histogram_quantile(.5, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", + "expr": "histogram_quantile(.5, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{namespace=\"$namespace\"}[$__rate_interval])) by (operation, le))", "hide": false, "legendFormat": ".5-{{operation}}", "refId": "C" @@ -5091,7 +5091,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", + "expr": "sum(rate(loki_boltdb_shipper_request_duration_seconds_count{namespace=\"$namespace\"}[$__rate_interval])) by (status_code, operation)", "intervalFactor": 1, "legendFormat": "{{status_code}}-{{operation}}", "refId": "A"