jbourdon/social-media
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add preprod observability foundation

Browse Source
This commit is contained in:
Jonathan Bourdon
2026-05-08 15:45:31 -04:00
parent 1ca6ab7117
commit 8bcff96821
35 changed files with 1627 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

413
deploy/observability/grafana/dashboards/socialize-overview.json Normal file
View File

@@ -0,0 +1,413 @@
{
"annotations": {
"list": []
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": null,
"links": [],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"targets": [
{
"expr": "sum(rate(http_server_request_duration_seconds_count{service_name=\"socialize-api\"}[5m]))",
"legendFormat": "requests/sec"
}
],
"title": "API Requests/sec",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 6,
"y": 0
},
"id": 2,
"options": {
"colorMode": "background",
"graphMode": "area",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"targets": [
{
"expr": "sum(rate(http_server_request_duration_seconds_count{service_name=\"socialize-api\", http_response_status_code=~\"5..\"}[5m])) / clamp_min(sum(rate(http_server_request_duration_seconds_count{service_name=\"socialize-api\"}[5m])), 0.001)",
"legendFormat": "5xx rate"
}
],
"title": "API 5xx Rate",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 12,
"y": 0
},
"id": 3,
"options": {
"colorMode": "background",
"graphMode": "area",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"targets": [
{
"expr": "histogram_quantile(0.95, sum by (le) (rate(http_server_request_duration_seconds_bucket{service_name=\"socialize-api\"}[5m])))",
"legendFormat": "p95"
}
],
"title": "API p95 Latency",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 6,
"x": 18,
"y": 0
},
"id": 4,
"options": {
"colorMode": "background",
"graphMode": "area",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"targets": [
{
"expr": "sum(ALERTS{alertstate=\"firing\"})",
"legendFormat": "firing"
}
],
"title": "Firing Alerts",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 4
},
"id": 5,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"expr": "sum(rate(http_server_request_duration_seconds_count{service_name=\"socialize-api\"}[5m])) by (http_request_method, http_route)",
"legendFormat": "{{http_request_method}} {{http_route}}"
}
],
"title": "Request Rate By Endpoint",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"fieldConfig": {
"defaults": {
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 4
},
"id": 6,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"expr": "histogram_quantile(0.95, sum by (le, http_route) (rate(http_server_request_duration_seconds_bucket{service_name=\"socialize-api\"}[5m])))",
"legendFormat": "{{http_route}}"
}
],
"title": "p95 Latency By Endpoint",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 12
},
"id": 7,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"expr": "sum(increase(socialize_login_attempts_total[24h])) by (outcome)",
"legendFormat": "login {{outcome}}"
},
{
"expr": "sum(increase(socialize_organizations_created_total[24h]))",
"legendFormat": "organizations"
},
{
"expr": "sum(increase(socialize_workspaces_created_total[24h]))",
"legendFormat": "workspaces"
},
{
"expr": "sum(increase(socialize_content_items_created_total[24h]))",
"legendFormat": "content"
},
{
"expr": "sum(increase(socialize_comments_created_total[24h]))",
"legendFormat": "comments"
},
{
"expr": "sum(increase(socialize_approval_decisions_submitted_total[24h]))",
"legendFormat": "approvals"
},
{
"expr": "sum(increase(socialize_feedback_submitted_total[24h]))",
"legendFormat": "feedback"
}
],
"title": "Usage Signals, 24h Rolling",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 12
},
"id": 8,
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom"
},
"tooltip": {
"mode": "multi"
}
},
"targets": [
{
"expr": "sum(increase(socialize_email_delivery_total[1h])) by (outcome, provider)",
"legendFormat": "email {{provider}} {{outcome}}"
},
{
"expr": "sum(increase(socialize_blob_storage_operations_total[1h])) by (operation, outcome)",
"legendFormat": "blob {{operation}} {{outcome}}"
},
{
"expr": "sum(increase(socialize_background_job_runs_total[1h])) by (job, outcome)",
"legendFormat": "job {{job}} {{outcome}}"
}
],
"title": "Operational Events, 1h Rolling",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "Prometheus"
},
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 20
},
"id": 9,
"options": {
"showHeader": true
},
"targets": [
{
"expr": "ALERTS{alertstate=\"firing\"}",
"format": "table",
"instant": true,
"legendFormat": "{{alertname}}"
}
],
"title": "Firing Alerts",
"type": "table"
},
{
"datasource": {
"type": "loki",
"uid": "Loki"
},
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 27
},
"id": 10,
"options": {
"dedupStrategy": "none",
"enableLogDetails": true,
"prettifyLogMessage": false,
"showCommonLabels": false,
"showLabels": false,
"showTime": true,
"sortOrder": "Descending",
"wrapLogMessage": false
},
"targets": [
{
"expr": "{platform=\"docker\", compose_service=\"api\"}",
"refId": "A"
}
],
"title": "API Logs",
"type": "logs"
}
],
"refresh": "30s",
"schemaVersion": 39,
"tags": [
"socialize",
"preprod"
],
"templating": {
"list": []
},
"time": {
"from": "now-6h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "Socialize Overview",
"uid": "socialize-overview",
"version": 2,
"weekStart": ""
}

11
deploy/observability/grafana/provisioning/dashboards/dashboards.yml Normal file
View File

@@ -0,0 +1,11 @@
apiVersion: 1
providers:
- name: Socialize
orgId: 1
folder: Socialize
type: file
disableDeletion: false
updateIntervalSeconds: 30
options:
path: /var/lib/grafana/dashboards

26
deploy/observability/grafana/provisioning/datasources/datasources.yml Normal file
View File

@@ -0,0 +1,26 @@
apiVersion: 1
datasources:
- name: Prometheus
uid: Prometheus
type: prometheus
access: proxy
url: http://prometheus:9090
isDefault: true
- name: Loki
uid: Loki
type: loki
access: proxy
url: http://loki:3100
- name: Tempo
uid: Tempo
type: tempo
access: proxy
url: http://tempo:3200
jsonData:
tracesToLogsV2:
datasourceUid: Loki
serviceMap:
datasourceUid: Prometheus