diff --git a/doc/source/configuration/openbao.rst b/doc/source/configuration/openbao.rst index 0248f8bd69..2d5945bfd6 100644 --- a/doc/source/configuration/openbao.rst +++ b/doc/source/configuration/openbao.rst @@ -221,6 +221,34 @@ cannot be unsealed with an expired certificate. kayobe playbook run $KAYOBE_CONFIG_PATH/ansible/secret-store/secret-store-unseal-overcloud.yml +Monitoring +---------- + +OpenBao monitoring is enabled by default when ``stackhpc_ca_secret_store`` is +set to ``openbao``. This adds Prometheus scrape targets for the overcloud +OpenBao instances, and alerting for sealed or unhealthy OpenBao nodes. + +Existing deployments must rerun the overcloud secret store deployment playbook +so that the OpenBao configuration exposes the metrics unauthenticated for +Prometheus: + +.. code-block:: bash + + kayobe playbook run $KAYOBE_CONFIG_PATH/ansible/secret-store/secret-store-deploy-overcloud.yml + +Then reconfigure Prometheus and Grafana: + +.. code-block:: bash + + kayobe overcloud service reconfigure -kt prometheus,grafana + +To opt out of OpenBao monitoring (Prometheus targets and alerts) while still +using OpenBao for PKI, set the following in ``stackhpc-monitoring.yml``: + +.. code-block:: yaml + + stackhpc_enable_openbao_monitoring: false + Certificates generation ======================= diff --git a/etc/kayobe/kolla/config/grafana/dashboards/openstack/openbao.json b/etc/kayobe/kolla/config/grafana/dashboards/openstack/openbao.json new file mode 100644 index 0000000000..0873473ab6 --- /dev/null +++ b/etc/kayobe/kolla/config/grafana/dashboards/openstack/openbao.json @@ -0,0 +1,4494 @@ +{% raw %} +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "grafana", + "uid": "-- Grafana --" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 1, + "id": 7908745, + "links": [], + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 5, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 55, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "name", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_core_active==1", + "instant": false, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Cluster Leader", + "type": "stat" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 5 + }, + "id": 1, + "panels": [], + "title": "Cluster Overview", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "fieldMinMax": false, + "mappings": [], + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 3 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 0, + "y": 6 + }, + "id": 2, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "sum(up{job=~\"$job\"})", + "legendFormat": "up", + "range": true, + "refId": "A" + } + ], + "title": "Nodes Up", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "fieldMinMax": false, + "mappings": [], + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 1 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 5, + "y": 6 + }, + "id": 4, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "sum(vault_core_active{job=~\"$job\"})", + "legendFormat": "active", + "range": true, + "refId": "A" + } + ], + "title": "Active Nodes", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "fieldMinMax": false, + "mappings": [], + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 1 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 10, + "y": 6 + }, + "id": 3, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "count(min by (node_id) (vault_autopilot_node_healthy{job=~\"$job\"}) == 0) or vector(0)", + "legendFormat": "unhealthy", + "range": true, + "refId": "A" + } + ], + "title": "Unhealthy Nodes", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "fieldMinMax": false, + "mappings": [], + "min": 0, + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 3 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 5, + "x": 15, + "y": 6 + }, + "id": 5, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "sum(vault_core_unsealed{job=~\"$job\"})", + "legendFormat": "unsealed", + "range": true, + "refId": "A" + } + ], + "title": "Unsealed Nodes", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 4, + "x": 20, + "y": 6 + }, + "id": 6, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "sum(vault_core_in_flight_requests{job=~\"$job\", instance=~\"$instance\"})", + "legendFormat": "requests", + "range": true, + "refId": "A" + } + ], + "title": "In-flight Requests", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 10 + }, + "id": 7, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "up{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} up", + "range": true, + "refId": "A" + } + ], + "title": "Uptime By Node", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 10 + }, + "id": 8, + "options": { + "displayMode": "gradient", + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": false + }, + "maxVizHeight": 300, + "minVizHeight": 10, + "minVizWidth": 0, + "namePlacement": "auto", + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showUnfilled": true, + "sizing": "auto", + "valueMode": "color" + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "time() - process_start_time_seconds{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Node Uptime", + "type": "bargauge" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 19 + }, + "id": 54, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_core_unsealed{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} unsealed", + "range": true, + "refId": "B" + } + ], + "title": "Seal State By Node", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 19 + }, + "id": 53, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_core_active{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} active", + "range": true, + "refId": "C" + } + ], + "title": "Active State By Node", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 28 + }, + "id": 9, + "panels": [], + "title": "Leader Workload", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ops" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 29 + }, + "id": 10, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_core_handle_request_count{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Request Rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 29 + }, + "id": 11, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_core_handle_request{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Request Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ops" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 29 + }, + "id": 12, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_cache_hit{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Cache Hit Rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 36 + }, + "id": 13, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_core_check_token{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Token Check Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 36 + }, + "id": 14, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_core_fetch_acl_and_token{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "ACL And Token Fetch Latency", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 43 + }, + "id": 15, + "panels": [], + "title": "Leases", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 44 + }, + "id": 16, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_expire_num_leases{job=~\"$job\"}", + "legendFormat": "{{instance}} active leases", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_expire_num_irrevocable_leases{job=~\"$job\"}", + "legendFormat": "{{instance}} irrevocable leases", + "range": true, + "refId": "B" + } + ], + "title": "Lease Counts", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 51 + }, + "id": 17, + "panels": [], + "title": "Audit Health", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ops" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 52 + }, + "id": 18, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_audit_log_request_count{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{instance}} request", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_audit_log_response_count{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{instance}} response", + "range": true, + "refId": "B" + } + ], + "title": "Audit Request And Response Rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 52 + }, + "id": 19, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "increase(vault_audit_log_request_failure{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{instance}} request failure", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "increase(vault_audit_log_response_failure{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{instance}} response failure", + "range": true, + "refId": "B" + } + ], + "title": "Audit Failures", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 52 + }, + "id": 20, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_audit_log_request{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{instance}} request p{{quantile}}", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_audit_log_response{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{instance}} response p{{quantile}}", + "range": true, + "refId": "B" + } + ], + "title": "Audit Latency", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 21, + "panels": [], + "title": "Raft Cluster Health", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "mappings": [ + { + "options": { + "0": { + "color": "red", + "index": 0, + "text": "Unhealthy" + }, + "1": { + "color": "green", + "index": 1, + "text": "Healthy" + } + }, + "type": "value" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 1 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 0, + "y": 60 + }, + "id": 22, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "min(vault_autopilot_healthy{job=~\"$job\"})", + "legendFormat": "healthy", + "range": true, + "refId": "A" + } + ], + "title": "Autopilot Healthy", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 6, + "y": 60 + }, + "id": 23, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "min(vault_autopilot_failure_tolerance{job=~\"$job\"})", + "legendFormat": "failure tolerance", + "range": true, + "refId": "A" + } + ], + "title": "Failure Tolerance", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 12, + "y": 60 + }, + "id": 24, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "sum(vault_raft_storage_stats_fsm_pending{job=~\"$job\", instance=~\"$instance\"})", + "legendFormat": "pending", + "range": true, + "refId": "A" + } + ], + "title": "FSM Pending", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 18, + "y": 60 + }, + "id": 25, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "max(vault_raft_storage_stats_term{job=~\"$job\", instance=~\"$instance\"})", + "legendFormat": "term", + "range": true, + "refId": "A" + } + ], + "title": "Current Raft Term", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 64 + }, + "id": 27, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_storage_stats_commit_index{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} commit", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_storage_stats_applied_index{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} applied", + "range": true, + "refId": "B" + } + ], + "title": "Commit And Applied Index", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 64 + }, + "id": 28, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_storage_follower_last_heartbeat_ms{job=~\"$job\"}", + "legendFormat": "{{peer_id}} heartbeat ms", + "range": true, + "refId": "B" + } + ], + "title": "Follower Heartbeat", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisPlacement": "auto", + "fillOpacity": 100, + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1 + }, + "mappings": [ + { + "options": { + "0": { + "color": "red", + "index": 0, + "text": "Unhealthy" + }, + "1": { + "color": "green", + "index": 1, + "text": "Healthy" + } + }, + "type": "value" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red" + }, + { + "color": "green", + "value": 1 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 71 + }, + "id": 26, + "options": { + "colWidth": 0.9, + "legend": { + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "mergeValues": true, + "rowHeight": 0.9, + "showValue": "never", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "min by (node_id) (vault_autopilot_node_healthy{job=~\"$job\", instance=~\"$instance\"})", + "legendFormat": "{{node_id}}", + "range": true, + "refId": "A" + } + ], + "title": "Node Health", + "type": "status-history" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 78 + }, + "id": 29, + "panels": [], + "title": "Raft Replication", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 79 + }, + "id": 30, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_leader_lastContact{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Leader Last Contact", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 79 + }, + "id": 31, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_leader_oldestLogAge{job=~\"$job\"}", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Oldest Log Age", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 79 + }, + "id": 32, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_replication_appendEntries_logs{job=~\"$job\"}", + "legendFormat": "{{peer_id}}", + "range": true, + "refId": "A" + } + ], + "title": "AppendEntries Logs", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 86 + }, + "id": 33, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_replication_appendEntries_rpc{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{peer_id}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "AppendEntries RPC Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 86 + }, + "id": 34, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_replication_heartbeat{job=~\"$job\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{peer_id}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Heartbeat Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ops" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 93 + }, + "id": 35, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_raft_replication_appendEntries_rpc_count{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{peer_id}} appendEntries", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_raft_replication_heartbeat_count{job=~\"$job\"}[$__rate_interval])", + "legendFormat": "{{peer_id}} heartbeat", + "range": true, + "refId": "B" + } + ], + "title": "Raft Replication RPC Rates", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 100 + }, + "id": 36, + "panels": [], + "title": "Standby HA Health", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 101 + }, + "id": 37, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_ha_rpc_client_echo{job=~\"$job\", instance=~\"$instance\", quantile=~\"0.5|0.9|0.99\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Standby To Active Echo Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ops" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 101 + }, + "id": 38, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_ha_rpc_client_echo_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Standby Echo Rate", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 108 + }, + "id": 39, + "panels": [], + "title": "Storage Latency", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 6, + "x": 0, + "y": 109 + }, + "id": 40, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_barrier_get{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Barrier GET Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 6, + "x": 6, + "y": 109 + }, + "id": 41, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_get{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Raft GET Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 6, + "x": 12, + "y": 109 + }, + "id": 42, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_storage_get{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "Raft Storage GET Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 6, + "x": 18, + "y": 109 + }, + "id": 43, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_raft_storage_fsm_get{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} p{{quantile}}", + "range": true, + "refId": "A" + } + ], + "title": "FSM GET Latency", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "ops" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 116 + }, + "id": 44, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_barrier_get_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}} barrier get", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_raft_get_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}} raft get", + "range": true, + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_raft_storage_get_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}} storage get", + "range": true, + "refId": "C" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(vault_raft_storage_fsm_get_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}} fsm get", + "range": true, + "refId": "D" + } + ], + "title": "Storage Operation Rates", + "type": "timeseries" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 123 + }, + "id": 45, + "panels": [], + "title": "Node Runtime And Resources", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "cores" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 124 + }, + "id": 46, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(process_cpu_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "CPU Usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 124 + }, + "id": 47, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "process_resident_memory_bytes{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Resident Memory", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 124 + }, + "id": 48, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "100 * process_open_fds{job=~\"$job\", instance=~\"$instance\"} / process_max_fds{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Open File Descriptors", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "Bps" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 131 + }, + "id": 49, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(process_network_receive_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}} receive", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "rate(process_network_transmit_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{instance}} transmit", + "range": true, + "refId": "B" + } + ], + "title": "Network Throughput", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 131 + }, + "id": 50, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_runtime_num_goroutines{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} goroutines", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_runtime_heap_objects{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} heap objects", + "range": true, + "refId": "B" + } + ], + "title": "Goroutines And Heap Objects", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 131 + }, + "id": 51, + "options": { + "legend": { + "calcs": [ + "lastNotNull" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "12.0.1+security-01", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_runtime_alloc_bytes{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} alloc", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "vault_runtime_sys_bytes{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{instance}} sys", + "range": true, + "refId": "B" + } + ], + "title": "Runtime Memory", + "type": "timeseries" + } + ], + "preload": false, + "refresh": "30s", + "schemaVersion": 41, + "tags": [ + "openbao", + "vault", + "raft", + "prometheus" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "41eFLCx7k" + }, + "includeAll": false, + "label": "Prometheus datasource", + "name": "DS_PROMETHEUS", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "text": "openbao", + "value": "openbao" + }, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "definition": "label_values(vault_core_active, job)", + "includeAll": false, + "label": "Job", + "name": "job", + "options": [], + "query": "label_values(vault_core_active, job)", + "refresh": 1, + "regex": "", + "sort": 1, + "type": "query" + }, + { + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "definition": "label_values(up{job=~\"$job\"}, instance)", + "includeAll": true, + "label": "Instance", + "multi": true, + "name": "instance", + "options": [], + "query": "label_values(up{job=~\"$job\"}, instance)", + "refresh": 1, + "regex": "", + "sort": 1, + "type": "query" + } + ] + }, + "time": { + "from": "now-3h", + "to": "now" + }, + "timepicker": {}, + "timezone": "", + "title": "OpenBao Overview", + "uid": "openbao-overview", + "version": 2 +} +{% endraw %} diff --git a/etc/kayobe/kolla/config/prometheus/openbao.rules b/etc/kayobe/kolla/config/prometheus/openbao.rules new file mode 100644 index 0000000000..5f104ebf5f --- /dev/null +++ b/etc/kayobe/kolla/config/prometheus/openbao.rules @@ -0,0 +1,27 @@ +{% if stackhpc_enable_openbao_monitoring | bool %} +{% raw %} + +groups: +- name: OpenBao + rules: + + - alert: OpenBaoSealed + expr: vault_core_unsealed{job="openbao"} == 0 + for: 5m + labels: + severity: critical + annotations: + summary: "OpenBao is sealed (instance {{ $labels.instance }})" + description: "OpenBao on {{ $labels.instance }} has been sealed for more than 5 minutes. Unseal the overcloud secret store before generating new certificates." + + - alert: OpenBaoUnhealthy + expr: min by (node_id) (vault_autopilot_node_healthy{job="openbao"}) == 0 + for: 5m + labels: + severity: critical + annotations: + summary: "OpenBao node is unhealthy (node {{ $labels.node_id }})" + description: "OpenBao autopilot has reported {{ $labels.node_id }} as unhealthy for more than 5 minutes." + +{% endraw %} +{% endif %} diff --git a/etc/kayobe/kolla/config/prometheus/prometheus.yml.d/50-openbao.yml b/etc/kayobe/kolla/config/prometheus/prometheus.yml.d/50-openbao.yml new file mode 100644 index 0000000000..178c9e7eb9 --- /dev/null +++ b/etc/kayobe/kolla/config/prometheus/prometheus.yml.d/50-openbao.yml @@ -0,0 +1,17 @@ +# yamllint disable-file +--- +{% if stackhpc_enable_openbao_monitoring | bool %} +scrape_configs: + - job_name: 'openbao' + metrics_path: "/v1/sys/metrics" + params: + format: ['prometheus'] + scheme: https + static_configs: +{% for host in groups['controllers'] %} + - targets: + - '{{ internal_net_name | net_ip(inventory_hostname=host) }}:8200' + labels: + instance: "{{ host }}" +{% endfor %} +{% endif %} diff --git a/etc/kayobe/stackhpc-monitoring.yml b/etc/kayobe/stackhpc-monitoring.yml index d443c12c65..f69cf34d35 100644 --- a/etc/kayobe/stackhpc-monitoring.yml +++ b/etc/kayobe/stackhpc-monitoring.yml @@ -67,6 +67,12 @@ redfish_exporter_target_address: "{{ ipmi_address }}" # How often to scrape OpenStack Exporter in seconds. stackhpc_prometheus_openstack_exporter_interval: 300 +# Whether OpenBao monitoring is enabled. +# Enabling this will add OpenBao scrape targets and alerting rules during +# Prometheus deployment. Defaults to enabled when OpenBao is the configured +# CA secret store. +stackhpc_enable_openbao_monitoring: "{{ stackhpc_ca_secret_store == 'openbao' }}" + ############################################################################### # Whether the RADOS gateway usage exporter is enabled. diff --git a/releasenotes/notes/add-openbao-monitoring-alerts-1c0837df41c80459.yaml b/releasenotes/notes/add-openbao-monitoring-alerts-1c0837df41c80459.yaml new file mode 100644 index 0000000000..c4b53c5fa6 --- /dev/null +++ b/releasenotes/notes/add-openbao-monitoring-alerts-1c0837df41c80459.yaml @@ -0,0 +1,13 @@ +--- +features: + - | + Adds OpenBao monitoring support, including Prometheus scrape configuration, + Prometheus alerts for sealed and unhealthy overcloud OpenBao nodes, and an + OpenBao Grafana dashboard. OpenBao monitoring can be disabled by setting + ``stackhpc_enable_openbao_monitoring`` to ``false``. +upgrade: + - | + Existing OpenBao deployments should rerun + ``ansible/secret-store/secret-store-deploy-overcloud.yml`` to enable + unauthenticated metrics access,and then reconfigure Prometheus and Grafana + to apply the new scrape configuration, alerting rules, and dashboard.