{ "annotations": { "list": [ { "builtIn": 1, "datasource": { "type": "grafana", "uid": "-- Grafana --" }, "enable": true, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", "name": "Annotations & Alerts", "type": "dashboard" } ] }, "description": "Cross-domain platform-wide request rate, latency percentiles, error rate, and resource utilization for Oshun services.", "editable": true, "fiscalYearStartMonth": 0, "graphTooltip": 1, "id": null, "liveNow": false, "panels": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Request rate (RPS) across all domain services, grouped by domain label.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 15, "gradientMode": "opacity", "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "scaleDistribution": { "type": "linear" }, "showPoints": "never", "spanNulls": true, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "off" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] }, "unit": "reqps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 }, "id": 1, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "sum by (domain) (rate(http_requests_total{domain=~\"$domain\"}[5m]))", "legendFormat": "{{domain}}", "range": true, "refId": "A" } ], "title": "HTTP Request Rate by Domain", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Error rate (percentage of 5xx responses) by domain.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "axisCenteredZero": false, "axisColorMode": "text", "axisPlacement": "auto", "drawStyle": "line", "fillOpacity": 25, "gradientMode": "opacity", "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true, "stacking": { "group": "A", "mode": "none" }, "thresholdsStyle": { "mode": "line" } }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "yellow", "value": 0.5 }, { "color": "red", "value": 1 } ] }, "unit": "percent" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 }, "id": 2, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "100 * sum by (domain) (rate(http_requests_total{domain=~\"$domain\",status=~\"5..\"}[5m])) / clamp_min(sum by (domain) (rate(http_requests_total{domain=~\"$domain\"}[5m])), 1)", "legendFormat": "{{domain}}", "range": true, "refId": "A" } ], "title": "HTTP 5xx Error Rate by Domain", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Latency percentiles (p50, p95, p99) computed from http_request_duration_seconds histogram.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "line", "fillOpacity": 10, "gradientMode": "opacity", "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 0.25 }, { "color": "red", "value": 0.5 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 9, "w": 24, "x": 0, "y": 8 }, "id": 3, "options": { "legend": { "calcs": ["mean", "max", "lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "histogram_quantile(0.50, sum by (domain, le) (rate(http_request_duration_seconds_bucket{domain=~\"$domain\"}[5m])))", "legendFormat": "{{domain}} p50", "range": true, "refId": "A" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "histogram_quantile(0.95, sum by (domain, le) (rate(http_request_duration_seconds_bucket{domain=~\"$domain\"}[5m])))", "legendFormat": "{{domain}} p95", "range": true, "refId": "B" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "histogram_quantile(0.99, sum by (domain, le) (rate(http_request_duration_seconds_bucket{domain=~\"$domain\"}[5m])))", "legendFormat": "{{domain}} p99", "range": true, "refId": "C" } ], "title": "HTTP Request Duration Percentiles by Domain", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Current p95 latency across all selected domains.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 0.25 }, { "color": "red", "value": 0.5 } ] }, "unit": "s" }, "overrides": [] }, "gridPos": { "h": 6, "w": 6, "x": 0, "y": 17 }, "id": 4, "options": { "colorMode": "background", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false }, "textMode": "auto" }, "pluginVersion": "10.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "histogram_quantile(0.95, sum by (le) (rate(http_request_duration_seconds_bucket{domain=~\"$domain\"}[5m])))", "legendFormat": "p95", "range": true, "refId": "A" } ], "title": "Platform p95 Latency", "type": "stat" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "CPU utilization (percentage) for service pods/containers by domain.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "line", "fillOpacity": 15, "gradientMode": "opacity", "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "orange", "value": 70 }, { "color": "red", "value": 90 } ] }, "unit": "percent" }, "overrides": [] }, "gridPos": { "h": 6, "w": 9, "x": 6, "y": 17 }, "id": 5, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "100 * avg by (domain) (rate(process_cpu_seconds_total{domain=~\"$domain\"}[5m]))", "legendFormat": "{{domain}}", "range": true, "refId": "A" } ], "title": "Process CPU Utilization by Domain", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Resident memory in bytes for services, grouped by domain.", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "drawStyle": "line", "fillOpacity": 15, "gradientMode": "opacity", "lineInterpolation": "smooth", "lineWidth": 2, "pointSize": 5, "showPoints": "never", "spanNulls": true }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] }, "unit": "bytes" }, "overrides": [] }, "gridPos": { "h": 6, "w": 9, "x": 15, "y": 17 }, "id": 6, "options": { "legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "right", "showLegend": true }, "tooltip": { "mode": "multi", "sort": "desc" } }, "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "sum by (domain) (process_resident_memory_bytes{domain=~\"$domain\"})", "legendFormat": "{{domain}}", "range": true, "refId": "A" } ], "title": "Resident Memory by Domain", "type": "timeseries" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Top services by request rate across all domains.", "fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "custom": { "align": "auto", "cellOptions": { "type": "auto" }, "inspect": false }, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null } ] }, "unit": "reqps" }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 23 }, "id": 7, "options": { "cellHeight": "sm", "footer": { "countRows": false, "fields": "", "reducer": ["sum"], "show": false }, "showHeader": true, "sortBy": [ { "desc": true, "displayName": "Value" } ] }, "pluginVersion": "10.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "topk(10, sum by (domain, service) (rate(http_requests_total{domain=~\"$domain\"}[5m])))", "format": "table", "instant": true, "refId": "A" } ], "title": "Top 10 Services by Request Rate", "type": "table" }, { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "description": "Heatmap of p95 request duration by domain over time.", "fieldConfig": { "defaults": { "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false }, "scaleDistribution": { "type": "linear" } } }, "overrides": [] }, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 23 }, "id": 8, "options": { "calculate": false, "cellGap": 1, "color": { "exponent": 0.5, "fill": "dark-orange", "mode": "scheme", "reverse": false, "scale": "exponential", "scheme": "Turbo", "steps": 64 }, "exemplars": { "color": "rgba(255,0,255,0.7)" }, "filterValues": { "le": 1e-9 }, "legend": { "show": true }, "rowsFrame": { "layout": "auto" }, "tooltip": { "show": true, "yHistogram": true }, "yAxis": { "axisPlacement": "left", "reverse": false, "unit": "s" } }, "pluginVersion": "10.2.0", "targets": [ { "datasource": { "type": "prometheus", "uid": "${datasource}" }, "editorMode": "code", "expr": "sum by (le) (rate(http_request_duration_seconds_bucket{domain=~\"$domain\"}[1m]))", "format": "heatmap", "legendFormat": "{{le}}", "range": true, "refId": "A" } ], "title": "Request Duration Heatmap", "type": "heatmap" } ], "refresh": "30s", "schemaVersion": 39, "tags": ["oshun", "platform", "overview"], "templating": { "list": [ { "current": { "selected": false, "text": "Prometheus", "value": "prometheus" }, "hide": 0, "includeAll": false, "label": "Datasource", "multi": false, "name": "datasource", "options": [], "query": "prometheus", "refresh": 1, "regex": "", "skipUrlSync": false, "type": "datasource" }, { "allValue": ".+", "current": { "selected": true, "text": ["All"], "value": ["$__all"] }, "datasource": { "type": "prometheus", "uid": "${datasource}" }, "definition": "label_values(http_requests_total, domain)", "hide": 0, "includeAll": true, "label": "Domain", "multi": true, "name": "domain", "options": [], "query": { "query": "label_values(http_requests_total, domain)", "refId": "StandardVariableQuery" }, "refresh": 2, "regex": "", "skipUrlSync": false, "sort": 1, "type": "query" } ] }, "time": { "from": "now-6h", "to": "now" }, "timepicker": {}, "timezone": "", "title": "Oshun Platform Overview", "uid": "oshun-platform-overview", "version": 1, "weekStart": "" }