diff --git a/execution/README.md b/execution/README.md index c099beddffe6661a11a13f117cb80e9b09140e0e..f7df1a32ad8b7898ba34b792095957a8e1362fc8 100644 --- a/execution/README.md +++ b/execution/README.md @@ -46,8 +46,19 @@ helm install grafana stable/grafana -f infrastructure/grafana/values.yaml The official [Grafana Helm Chart repository](https://github.com/helm/charts/tree/master/stable/grafana) provides further documentation including a table of configuration options. -We provide a [ready-to-use Grafana dashboard](infrastructure/grafana/scalability-benchmarking-dashbaord.json), -which can be imported into your Grafana instance. +We provide ConfigMaps for a [Grafana dashboard](infrastructure/grafana/dashboard-config-map.yaml) and a [Grafana data source](infrastructure/grafana/prometheus-datasource-config-map.yaml). + +Create the Configmap for the dashboard: + +```sh +kubectl apply -f infrastructure/grafana/dashboard-config-map.yaml +``` + +Create the Configmap for the data source: + +```sh +kubectl apply -f infrastructure/grafana/prometheus-datasource-config-map.yaml +``` ### A Kafka cluster diff --git a/execution/infrastructure/grafana/dashboard-config-map.yaml b/execution/infrastructure/grafana/dashboard-config-map.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e858ffe7dfdd4fbcdf1592b0f564c305969f6af5 --- /dev/null +++ b/execution/infrastructure/grafana/dashboard-config-map.yaml @@ -0,0 +1,1005 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: scalability + labels: + grafana_dashboard: "1" +data: + k8s-dashboard.json: |- + { + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "id": 2, + "iteration": 1589140028684, + "links": [], + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 0 + }, + "hiddenSeries": false, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cp_kafka_server_brokertopicmetrics_messagesinpersec_topic_input)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{Messages In Per Second}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Messages In Per Second", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 0 + }, + "hiddenSeries": false, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(cp_kafka_server_brokertopicmetrics_messagesinpersec_topic_output)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{Messages Out Per Second}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Messages Out Per Second", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 7 + }, + "hiddenSeries": false, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(group, topic) (kafka_consumergroup_group_lag > 0)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{topic}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Record Lag", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 7 + }, + "hiddenSeries": false, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count(count (kafka_consumer_consumer_fetch_manager_metrics_records_lag) by(pod))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "instances", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Number of Instances", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": 0, + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 15 + }, + "hiddenSeries": false, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(group,topic) (kafka_consumergroup_group_offset > 0)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{topic}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Records Consumed", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 15 + }, + "hiddenSeries": false, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count by(group,topic) (kafka_consumergroup_group_offset > 0)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{topic}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Number of Partitions", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 23 + }, + "hiddenSeries": false, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(group,topic) (kafka_partition_latest_offset)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{topic}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Records Produced (Kafka Lag Exporter)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 23 + }, + "hiddenSeries": false, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "count by(job, topic) (kafka_consumer_consumer_fetch_manager_metrics_records_lag)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{topic}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Number of Partitions (Kafka Streams Export)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "decimals": null, + "format": "short", + "label": "", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 31 + }, + "hiddenSeries": false, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(job, topic) (kafka_consumer_consumer_fetch_manager_metrics_records_lag)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{topic}}", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Record Lag (Kafka Streams Export)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": null, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 31 + }, + "hiddenSeries": false, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(group) (kafka_consumergroup_group_lag > 0)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "total lag", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Total Record Lag (Kafka Lag Exporter)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "refresh": "10s", + "schemaVersion": 21, + "style": "dark", + "tags": [], + "templating": { + "list": [ + { + "allValue": null, + "current": { + "tags": [], + "text": "titan-ccp-aggregation", + "value": "titan-ccp-aggregation" + }, + "datasource": "Prometheus", + "definition": "label_values(kafka_consumer_consumer_fetch_manager_metrics_records_lag, job)", + "hide": 0, + "includeAll": false, + "label": "Job", + "multi": false, + "name": "Job", + "options": [ + { + "selected": true, + "text": "titan-ccp-aggregation", + "value": "titan-ccp-aggregation" + } + ], + "query": "label_values(kafka_consumer_consumer_fetch_manager_metrics_records_lag, job)", + "refresh": 0, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ] + }, + "timezone": "", + "title": "Scalability Benchmarking", + "uid": "dad0CNlZz", + "version": 25 + } \ No newline at end of file diff --git a/execution/infrastructure/grafana/prometheus-datasource-config-map.yaml b/execution/infrastructure/grafana/prometheus-datasource-config-map.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ec9aaba2da3f0d8de7c48be8418de08548184b26 --- /dev/null +++ b/execution/infrastructure/grafana/prometheus-datasource-config-map.yaml @@ -0,0 +1,29 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: prometheus + labels: + grafana_datasource: "1" +data: + datasource.yaml: |- + # config file version + apiVersion: 1 + datasources: + # <string, required> name of the datasource. Required + - name: Prometheus + # <string, required> datasource type. Required + type: prometheus + # <string, required> access mode. proxy or direct (Server or Browser in the UI). Required + access: proxy + # <bool> mark as default datasource. Max one per org + isDefault: true + # <int> org id. will default to orgId 1 if not specified + orgId: 1 + # <string> url + url: http://prometheus-operated:9090 #http://localhost:9090 + # <map> fields that will be converted to json and stored in json_data + jsonData: + timeInterval: "15s" + version: 1 + # <bool> allow users to edit datasources from the UI. + editable: true diff --git a/execution/infrastructure/grafana/values.yaml b/execution/infrastructure/grafana/values.yaml index 74b2c8a713256d39f3001cae635c26d8bc13d7d5..16f075745660e9fd522f37108d0479a8b6f997b4 100644 --- a/execution/infrastructure/grafana/values.yaml +++ b/execution/infrastructure/grafana/values.yaml @@ -1,3 +1,55 @@ +image: + repository: grafana/grafana + tag: 6.7.3 + pullPolicy: IfNotPresent + +# Administrator credentials when not using an existing secret (see below) +adminUser: admin +adminPassword: admin + + +## Sidecars that collect the configmaps with specified label and stores the included files them into the respective folders +## Requires at least Grafana 5 to work and can't be used together with parameters dashboardProviders, datasources and dashboards +sidecar: + image: kiwigrid/k8s-sidecar:0.1.99 + imagePullPolicy: IfNotPresent + dashboards: + enabled: true + SCProvider: true + # label that the configmaps with dashboards are marked with + label: grafana_dashboard + # folder in the pod that should hold the collected dashboards (unless `defaultFolderName` is set) + folder: /tmp/dashboards + # The default folder name, it will create a subfolder under the `folder` and put dashboards in there instead + defaultFolderName: null + # If specified, the sidecar will search for dashboard config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: null + # provider configuration that lets grafana manage the dashboards + provider: + # name of the provider, should be unique + name: sidecarProvider + # orgid as configured in grafana + orgid: 1 + # folder in which the dashboards should be imported in grafana + folder: '' + # type of the provider + type: file + # disableDelete to activate a import-only behaviour + disableDelete: false + # allow updating provisioned dashboards from the UI + allowUiUpdates: true + datasources: + enabled: true + # label that the configmaps with datasources are marked with + label: grafana_datasource + # If specified, the sidecar will search for datasource config-maps inside this namespace. + # Otherwise the namespace in which the sidecar is running will be used. + # It's also possible to specify ALL to search in all namespaces + searchNamespace: default + + service: nodePort: 31199 type: NodePort \ No newline at end of file