feat: add preprod observability foundation

2026-05-08 15:45:31 -04:00
parent 1ca6ab7117
commit 8bcff96821
35 changed files with 1627 additions and 56 deletions
--- a/deploy/observability/alloy/config.alloy
+++ b/deploy/observability/alloy/config.alloy
@@ -0,0 +1,95 @@
+logging {
+  level  = "info"
+  format = "logfmt"
+}
+
+otelcol.receiver.otlp "api" {
+  grpc {
+    endpoint = "0.0.0.0:4317"
+  }
+
+  http {
+    endpoint = "0.0.0.0:4318"
+  }
+
+  output {
+    metrics = [otelcol.processor.transform.metric_labels.input]
+    traces  = [otelcol.processor.batch.default.input]
+  }
+}
+
+otelcol.processor.transform "metric_labels" {
+  error_mode = "ignore"
+
+  metric_statements {
+    context = "datapoint"
+    statements = [
+      `set(attributes["service.name"], resource.attributes["service.name"])`,
+      `set(attributes["deployment.environment"], resource.attributes["deployment.environment"])`,
+    ]
+  }
+
+  output {
+    metrics = [otelcol.processor.batch.default.input]
+  }
+}
+
+otelcol.processor.batch "default" {
+  output {
+    metrics = [otelcol.exporter.prometheus.local.input]
+    traces  = [otelcol.exporter.otlp.tempo.input]
+  }
+}
+
+otelcol.exporter.prometheus "local" {
+  forward_to = [prometheus.remote_write.local.receiver]
+}
+
+prometheus.remote_write "local" {
+  endpoint {
+    url = "http://prometheus:9090/api/v1/write"
+  }
+}
+
+otelcol.exporter.otlp "tempo" {
+  client {
+    endpoint = "tempo:4317"
+
+    tls {
+      insecure = true
+    }
+  }
+}
+
+discovery.docker "linux" {
+  host = "unix:///var/run/docker.sock"
+}
+
+discovery.relabel "docker_logs" {
+  targets = []
+
+  rule {
+    source_labels = ["__meta_docker_container_name"]
+    regex         = "/(.*)"
+    target_label  = "service_name"
+  }
+
+  rule {
+    source_labels = ["__meta_docker_container_label_com_docker_compose_service"]
+    target_label  = "compose_service"
+  }
+}
+
+loki.source.docker "default" {
+  host          = "unix:///var/run/docker.sock"
+  targets       = discovery.docker.linux.targets
+  labels        = {"platform" = "docker"}
+  relabel_rules = discovery.relabel.docker_logs.rules
+  forward_to    = [loki.write.local.receiver]
+}
+
+loki.write "local" {
+  endpoint {
+    url = "http://loki:3100/loki/api/v1/push"
+  }
+}
--- a/deploy/observability/compose.observability.yml
+++ b/deploy/observability/compose.observability.yml
@@ -0,0 +1,94 @@
+services:
+  api:
+    environment:
+      OTEL_SERVICE_NAME: socialize-api
+      OTEL_EXPORTER_OTLP_ENDPOINT: http://alloy:4317
+      OTEL_EXPORTER_OTLP_PROTOCOL: grpc
+      OTEL_RESOURCE_ATTRIBUTES: deployment.environment=preprod
+    depends_on:
+      alloy:
+        condition: service_started
+
+  grafana:
+    image: grafana/grafana:13.0.1
+    restart: unless-stopped
+    environment:
+      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
+      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-admin}
+      GF_USERS_ALLOW_SIGN_UP: "false"
+    volumes:
+      - grafana-data:/var/lib/grafana
+      - ./observability/grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./observability/grafana/dashboards:/var/lib/grafana/dashboards:ro
+    ports:
+      - "${GRAFANA_HTTP_BIND:-127.0.0.1}:3000:3000"
+    depends_on:
+      - prometheus
+      - loki
+      - tempo
+    networks:
+      - internal
+
+  prometheus:
+    image: prom/prometheus:v3.11.3
+    restart: unless-stopped
+    command:
+      - --config.file=/etc/prometheus/prometheus.yml
+      - --storage.tsdb.path=/prometheus
+      - --storage.tsdb.retention.time=${PROMETHEUS_RETENTION:-15d}
+      - --web.enable-remote-write-receiver
+    volumes:
+      - prometheus-data:/prometheus
+      - ./observability/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./observability/prometheus/rules:/etc/prometheus/rules:ro
+    networks:
+      - internal
+
+  loki:
+    image: grafana/loki:3.7.1
+    restart: unless-stopped
+    command: -config.file=/etc/loki/local-config.yml
+    volumes:
+      - loki-data:/loki
+      - ./observability/loki/local-config.yml:/etc/loki/local-config.yml:ro
+    networks:
+      - internal
+
+  tempo:
+    image: grafana/tempo:2.10.3
+    restart: unless-stopped
+    command: -config.file=/etc/tempo.yml
+    volumes:
+      - tempo-data:/var/tempo
+      - ./observability/tempo/tempo.yml:/etc/tempo.yml:ro
+    networks:
+      - internal
+
+  alloy:
+    image: grafana/alloy:v1.16.0
+    restart: unless-stopped
+    command:
+      - run
+      - --server.http.listen-addr=0.0.0.0:12345
+      - --storage.path=/var/lib/alloy/data
+      - /etc/alloy/config.alloy
+    volumes:
+      - alloy-data:/var/lib/alloy/data
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - ./observability/alloy/config.alloy:/etc/alloy/config.alloy:ro
+    expose:
+      - "4317"
+      - "4318"
+      - "12345"
+    networks:
+      - internal
+
+volumes:
+  grafana-data:
+  prometheus-data:
+  loki-data:
+  tempo-data:
+  alloy-data:
+
+networks:
+  internal:
--- a/deploy/observability/grafana/dashboards/socialize-overview.json
+++ b/deploy/observability/grafana/dashboards/socialize-overview.json
@@ -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": ""
+}
--- a/deploy/observability/grafana/provisioning/dashboards/dashboards.yml
+++ b/deploy/observability/grafana/provisioning/dashboards/dashboards.yml
@@ -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
--- a/deploy/observability/grafana/provisioning/datasources/datasources.yml
+++ b/deploy/observability/grafana/provisioning/datasources/datasources.yml
@@ -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
--- a/deploy/observability/loki/local-config.yml
+++ b/deploy/observability/loki/local-config.yml
@@ -0,0 +1,32 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+
+common:
+  path_prefix: /loki
+  replication_factor: 1
+  ring:
+    kvstore:
+      store: inmemory
+
+schema_config:
+  configs:
+    - from: 2024-01-01
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+storage_config:
+  filesystem:
+    directory: /loki/chunks
+
+limits_config:
+  allow_structured_metadata: true
+  volume_enabled: true
+
+analytics:
+  reporting_enabled: false
--- a/deploy/observability/prometheus/prometheus.yml
+++ b/deploy/observability/prometheus/prometheus.yml
@@ -0,0 +1,17 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+rule_files:
+  - /etc/prometheus/rules/*.yml
+
+scrape_configs:
+  - job_name: prometheus
+    static_configs:
+      - targets:
+          - prometheus:9090
+
+  - job_name: alloy
+    static_configs:
+      - targets:
+          - alloy:12345
--- a/deploy/observability/prometheus/rules/socialize-alerts.yml
+++ b/deploy/observability/prometheus/rules/socialize-alerts.yml
@@ -0,0 +1,97 @@
+groups:
+  - name: socialize-preprod
+    rules:
+      - alert: SocializeApiTelemetryMissing
+        expr: absent(http_server_request_duration_seconds_count{service_name="socialize-api"})
+        for: 5m
+        labels:
+          severity: critical
+          service: socialize-api
+        annotations:
+          summary: Socialize API telemetry is missing
+          description: No API request telemetry has been received for 5 minutes. The API or telemetry pipeline may be down.
+
+      - alert: SocializeApiHighErrorRate
+        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)
+          ) > 0.05
+        for: 5m
+        labels:
+          severity: critical
+          service: socialize-api
+        annotations:
+          summary: Socialize API 5xx rate is high
+          description: More than 5% of API requests are returning 5xx responses over 5 minutes.
+
+      - alert: SocializeApiHighLatency
+        expr: |
+          histogram_quantile(
+            0.95,
+            sum by (le) (rate(http_server_request_duration_seconds_bucket{service_name="socialize-api"}[5m]))
+          ) > 2
+        for: 10m
+        labels:
+          severity: warning
+          service: socialize-api
+        annotations:
+          summary: Socialize API p95 latency is high
+          description: API p95 latency has been above 2 seconds for 10 minutes.
+
+      - alert: SocializeCoreUsageQuiet
+        expr: |
+          (
+            sum(increase(socialize_content_items_created_total[12h]))
+            + sum(increase(socialize_comments_created_total[12h]))
+            + sum(increase(socialize_approval_decisions_submitted_total[12h]))
+            + sum(increase(socialize_feedback_submitted_total[12h]))
+          ) < 1
+        for: 30m
+        labels:
+          severity: warning
+          service: socialize-api
+        annotations:
+          summary: Socialize core usage is quiet
+          description: No content, comment, approval, or feedback activity has been observed over the last 12 hours.
+
+      - alert: SocializeFeedbackBugSubmitted
+        expr: sum(increase(socialize_feedback_submitted_total{feedback_type="Bug"}[15m])) > 0
+        for: 0m
+        labels:
+          severity: info
+          service: socialize-api
+        annotations:
+          summary: New bug feedback submitted
+          description: A user submitted bug feedback in the last 15 minutes.
+
+      - alert: SocializeEmailDeliveryFailures
+        expr: sum(increase(socialize_email_delivery_total{outcome="failure"}[15m])) > 0
+        for: 0m
+        labels:
+          severity: warning
+          service: socialize-api
+        annotations:
+          summary: Email delivery failures detected
+          description: One or more email delivery attempts failed in the last 15 minutes.
+
+      - alert: SocializeBlobStorageFailures
+        expr: sum(increase(socialize_blob_storage_operations_total{outcome="failure"}[15m])) > 0
+        for: 0m
+        labels:
+          severity: warning
+          service: socialize-api
+        annotations:
+          summary: Blob storage failures detected
+          description: One or more blob storage operations failed in the last 15 minutes.
+
+      - alert: SocializeBackgroundJobFailures
+        expr: sum(increase(socialize_background_job_runs_total{outcome="failure"}[30m])) > 0
+        for: 0m
+        labels:
+          severity: warning
+          service: socialize-api
+        annotations:
+          summary: Background job failures detected
+          description: One or more background jobs failed in the last 30 minutes.
--- a/deploy/observability/tempo/tempo.yml
+++ b/deploy/observability/tempo/tempo.yml
@@ -0,0 +1,25 @@
+server:
+  http_listen_port: 3200
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+        http:
+          endpoint: 0.0.0.0:4318
+
+storage:
+  trace:
+    backend: local
+    local:
+      path: /var/tempo/traces
+
+compactor:
+  compaction:
+    block_retention: 168h
+
+metrics_generator:
+  storage:
+    path: /var/tempo/generator/wal