stella-ops.org/git.stella-ops.org
1
0
Fork 0
Code Issues Pull Requests Actions 2 Releases Wiki Activity

devops folders consolidate

Browse Source
This commit is contained in:
master
2026-01-25 23:27:41 +02:00
parent 6e687b523a
commit a743bb9a1d
613 changed files with 8611 additions and 41846 deletions
Download Patch File Download Diff File Expand all files Collapse all files

536
devops/telemetry/dashboards/stella-ops-error-tracking.json Normal file
View File

@@ -0,0 +1,536 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
},
{
"datasource": "${datasource}",
"enable": true,
"expr": "increase(stella_error_total[1m]) > 0",
"iconColor": "red",
"name": "Error Spikes",
"tagKeys": "error_type",
"titleFormat": "Error: {{error_type}}"
}
]
},
"description": "Stella Ops Release Orchestrator - Error Tracking",
"editable": true,
"gnetId": null,
"graphTooltip": 1,
"id": null,
"iteration": 1737158400000,
"links": [],
"panels": [
{
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
"id": 1,
"panels": [],
"title": "Error Summary",
"type": "row"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 1 },
{ "color": "red", "value": 10 }
]
}
},
"overrides": []
},
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
"id": 2,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": { "calcs": ["sum"], "fields": "", "values": false },
"textMode": "auto"
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "sum(increase(stella_error_total[1h]))",
"legendFormat": "",
"refId": "A"
}
],
"title": "Errors (1h)",
"type": "stat"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 0.01 },
{ "color": "red", "value": 0.05 }
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 1 },
"id": 3,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
"textMode": "auto"
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "sum(rate(stella_error_total[5m])) / sum(rate(stella_api_requests_total[5m]))",
"legendFormat": "",
"refId": "A"
}
],
"title": "Error Rate",
"type": "stat"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 1 },
{ "color": "red", "value": 5 }
]
}
},
"overrides": []
},
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 1 },
"id": 4,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": { "calcs": ["sum"], "fields": "", "values": false },
"textMode": "auto"
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "sum(increase(stella_release_failed_total[1h]))",
"legendFormat": "",
"refId": "A"
}
],
"title": "Failed Releases (1h)",
"type": "stat"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "yellow", "value": 1 },
{ "color": "red", "value": 3 }
]
}
},
"overrides": []
},
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 1 },
"id": 5,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": { "calcs": ["sum"], "fields": "", "values": false },
"textMode": "auto"
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "sum(increase(stella_gate_failed_total[1h]))",
"legendFormat": "",
"refId": "A"
}
],
"title": "Gate Failures (1h)",
"type": "stat"
},
{
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
"id": 6,
"panels": [],
"title": "Error Trends",
"type": "row"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 20,
"gradientMode": "none",
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
"lineInterpolation": "smooth",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": { "type": "linear" },
"showPoints": "never",
"spanNulls": false,
"stacking": { "group": "A", "mode": "normal" },
"thresholdsStyle": { "mode": "off" }
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
},
"unit": "short"
},
"overrides": []
},
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
"id": 7,
"options": {
"legend": { "calcs": ["sum"], "displayMode": "table", "placement": "bottom" },
"tooltip": { "mode": "multi", "sort": "desc" }
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "sum(rate(stella_error_total[5m])) by (error_type)",
"legendFormat": "{{error_type}}",
"refId": "A"
}
],
"title": "Errors by Type",
"type": "timeseries"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 20,
"gradientMode": "none",
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
"lineInterpolation": "smooth",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": { "type": "linear" },
"showPoints": "never",
"spanNulls": false,
"stacking": { "group": "A", "mode": "normal" },
"thresholdsStyle": { "mode": "off" }
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
},
"unit": "short"
},
"overrides": []
},
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
"id": 8,
"options": {
"legend": { "calcs": ["sum"], "displayMode": "table", "placement": "bottom" },
"tooltip": { "mode": "multi", "sort": "desc" }
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "sum(rate(stella_error_total{environment=~\"$environment\"}[5m])) by (component)",
"legendFormat": "{{component}}",
"refId": "A"
}
],
"title": "Errors by Component",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 14 },
"id": 9,
"panels": [],
"title": "Release Failures",
"type": "row"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"fillOpacity": 80,
"gradientMode": "none",
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
"lineWidth": 1,
"scaleDistribution": { "type": "linear" },
"thresholdsStyle": { "mode": "off" }
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
}
},
"overrides": []
},
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 15 },
"id": 10,
"options": {
"barRadius": 0.1,
"barWidth": 0.8,
"groupWidth": 0.7,
"legend": { "calcs": [], "displayMode": "list", "placement": "bottom" },
"orientation": "horizontal",
"showValue": "auto",
"stacking": "none",
"tooltip": { "mode": "single", "sort": "none" },
"xTickLabelRotation": 0,
"xTickLabelSpacing": 0
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "topk(10, sum(increase(stella_release_failed_total[24h])) by (failure_reason))",
"format": "table",
"instant": true,
"legendFormat": "{{failure_reason}}",
"refId": "A"
}
],
"title": "Top Failure Reasons (24h)",
"transformations": [
{
"id": "organize",
"options": {
"excludeByName": { "Time": true },
"indexByName": {},
"renameByName": { "Value": "Count", "failure_reason": "Reason" }
}
}
],
"type": "barchart"
},
{
"datasource": "${datasource}",
"fieldConfig": {
"defaults": {
"color": { "mode": "palette-classic" },
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "bars",
"fillOpacity": 80,
"gradientMode": "none",
"hideFrom": { "legend": false, "tooltip": false, "viz": false },
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": { "type": "linear" },
"showPoints": "never",
"spanNulls": false,
"stacking": { "group": "A", "mode": "normal" },
"thresholdsStyle": { "mode": "off" }
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [{ "color": "green", "value": null }]
},
"unit": "short"
},
"overrides": [
{
"matcher": { "id": "byName", "options": "Failures" },
"properties": [{ "id": "color", "value": { "fixedColor": "red", "mode": "fixed" } }]
},
{
"matcher": { "id": "byName", "options": "Rollbacks" },
"properties": [{ "id": "color", "value": { "fixedColor": "orange", "mode": "fixed" } }]
}
]
},
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 15 },
"id": 11,
"options": {
"legend": { "calcs": ["sum"], "displayMode": "table", "placement": "bottom" },
"tooltip": { "mode": "multi", "sort": "none" }
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "sum(increase(stella_release_failed_total{environment=~\"$environment\"}[1h])) by (environment)",
"legendFormat": "{{environment}} Failures",
"refId": "A"
},
{
"expr": "sum(increase(stella_rollback_total{environment=~\"$environment\"}[1h])) by (environment)",
"legendFormat": "{{environment}} Rollbacks",
"refId": "B"
}
],
"title": "Failures & Rollbacks by Environment",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 23 },
"id": 12,
"panels": [],
"title": "Recent Errors",
"type": "row"
},
{
"datasource": "${loki_datasource}",
"fieldConfig": {
"defaults": {},
"overrides": []
},
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 24 },
"id": 13,
"options": {
"dedupStrategy": "none",
"enableLogDetails": true,
"prettifyLogMessage": false,
"showCommonLabels": false,
"showLabels": true,
"showTime": true,
"sortOrder": "Descending",
"wrapLogMessage": true
},
"pluginVersion": "9.0.0",
"targets": [
{
"expr": "{app=\"stella-ops\"} |= \"error\" | json | level=~\"error|fatal\"",
"legendFormat": "",
"refId": "A"
}
],
"title": "Error Logs",
"type": "logs"
}
],
"refresh": "30s",
"schemaVersion": 36,
"style": "dark",
"tags": ["stella-ops", "errors"],
"templating": {
"list": [
{
"current": { "selected": false, "text": "Prometheus", "value": "Prometheus" },
"hide": 0,
"includeAll": false,
"label": "Metrics",
"multi": false,
"name": "datasource",
"options": [],
"query": "prometheus",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"current": { "selected": false, "text": "Loki", "value": "Loki" },
"hide": 0,
"includeAll": false,
"label": "Logs",
"multi": false,
"name": "loki_datasource",
"options": [],
"query": "loki",
"queryValue": "",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"allValue": ".*",
"current": { "selected": true, "text": "All", "value": "$__all" },
"datasource": "${datasource}",
"definition": "label_values(stella_error_total, environment)",
"hide": 0,
"includeAll": true,
"label": "Environment",
"multi": true,
"name": "environment",
"options": [],
"query": { "query": "label_values(stella_error_total, environment)", "refId": "StandardVariableQuery" },
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
}
]
},
"time": { "from": "now-6h", "to": "now" },
"timepicker": {},
"timezone": "",
"title": "Stella Ops - Error Tracking",
"uid": "stella-ops-errors",
"version": 1,
"weekStart": ""
}