Imporve monitoring 4

This commit is contained in:
Urtzi Alfaro
2026-01-09 14:48:44 +01:00
parent 7ef85c1188
commit 22dab143ba
21 changed files with 1911 additions and 202 deletions

View File

@@ -0,0 +1,213 @@
{
"name": "Bakery IA Dashboard Collection",
"description": "Complete set of SigNoz dashboards for Bakery IA monitoring",
"version": "1.0.0",
"author": "Bakery IA Team",
"license": "MIT",
"dashboards": [
{
"id": "infrastructure-monitoring",
"name": "Infrastructure Monitoring",
"description": "Kubernetes infrastructure and resource monitoring",
"file": "infrastructure-monitoring.json",
"tags": ["infrastructure", "kubernetes", "system"],
"category": "infrastructure"
},
{
"id": "application-performance",
"name": "Application Performance",
"description": "Microservice performance and API metrics",
"file": "application-performance.json",
"tags": ["application", "performance", "apm"],
"category": "performance"
},
{
"id": "database-performance",
"name": "Database Performance",
"description": "PostgreSQL and Redis database monitoring",
"file": "database-performance.json",
"tags": ["database", "postgresql", "redis"],
"category": "database"
},
{
"id": "api-performance",
"name": "API Performance",
"description": "REST and GraphQL API performance monitoring",
"file": "api-performance.json",
"tags": ["api", "rest", "graphql"],
"category": "api"
},
{
"id": "error-tracking",
"name": "Error Tracking",
"description": "System error tracking and analysis",
"file": "error-tracking.json",
"tags": ["errors", "exceptions", "tracking"],
"category": "monitoring"
},
{
"id": "user-activity",
"name": "User Activity",
"description": "User behavior and activity monitoring",
"file": "user-activity.json",
"tags": ["user", "activity", "behavior"],
"category": "user"
},
{
"id": "system-health",
"name": "System Health",
"description": "Overall system health monitoring",
"file": "system-health.json",
"tags": ["system", "health", "overview"],
"category": "overview"
},
{
"id": "alert-management",
"name": "Alert Management",
"description": "Alert monitoring and management",
"file": "alert-management.json",
"tags": ["alerts", "notifications", "management"],
"category": "alerts"
},
{
"id": "log-analysis",
"name": "Log Analysis",
"description": "Log search and analysis",
"file": "log-analysis.json",
"tags": ["logs", "search", "analysis"],
"category": "logs"
}
],
"categories": [
{
"id": "infrastructure",
"name": "Infrastructure",
"description": "Kubernetes and system infrastructure monitoring"
},
{
"id": "performance",
"name": "Performance",
"description": "Application and service performance monitoring"
},
{
"id": "database",
"name": "Database",
"description": "Database performance and health monitoring"
},
{
"id": "api",
"name": "API",
"description": "API performance and usage monitoring"
},
{
"id": "monitoring",
"name": "Monitoring",
"description": "Error tracking and system monitoring"
},
{
"id": "user",
"name": "User",
"description": "User activity and behavior monitoring"
},
{
"id": "overview",
"name": "Overview",
"description": "System-wide overview and health dashboards"
},
{
"id": "alerts",
"name": "Alerts",
"description": "Alert management and monitoring"
},
{
"id": "logs",
"name": "Logs",
"description": "Log analysis and search"
}
],
"usage": {
"import_methods": [
"ui_import",
"api_import",
"kubernetes_configmap"
],
"recommended_import_order": [
"infrastructure-monitoring",
"system-health",
"application-performance",
"api-performance",
"database-performance",
"error-tracking",
"alert-management",
"log-analysis",
"user-activity"
]
},
"requirements": {
"signoz_version": ">= 0.10.0",
"opentelemetry_collector": ">= 0.45.0",
"metrics": [
"container_cpu_usage_seconds_total",
"container_memory_working_set_bytes",
"http_server_requests_seconds_count",
"http_server_requests_seconds_sum",
"pg_stat_activity_count",
"pg_stat_statements_total_time",
"error_total",
"alerts_total",
"kube_pod_status_phase",
"container_network_receive_bytes_total",
"kube_pod_container_status_restarts_total",
"kube_pod_container_status_ready",
"container_fs_reads_total",
"kube_pod_status_phase",
"kube_pod_container_status_restarts_total",
"kube_pod_container_status_ready",
"container_fs_reads_total",
"kubernetes_events",
"http_server_requests_seconds_bucket",
"http_server_active_requests",
"http_server_up",
"db_query_duration_seconds_sum",
"db_connections_active",
"http_client_request_duration_seconds_count",
"http_client_request_duration_seconds_sum",
"graphql_execution_time_seconds",
"graphql_errors_total",
"pg_stat_database_blks_hit",
"pg_stat_database_xact_commit",
"pg_locks_count",
"pg_table_size_bytes",
"pg_stat_user_tables_seq_scan",
"redis_memory_used_bytes",
"redis_commands_processed_total",
"redis_keyspace_hits",
"pg_stat_database_deadlocks",
"pg_stat_database_conn_errors",
"pg_replication_lag_bytes",
"pg_replication_is_replica",
"active_users",
"user_sessions_total",
"api_calls_per_user",
"session_duration_seconds",
"system_availability",
"service_health_score",
"system_cpu_usage",
"system_memory_usage",
"service_availability",
"alerts_active",
"alerts_total",
"log_lines_total"
]
},
"support": {
"documentation": "https://signoz.io/docs/",
"bakery_ia_docs": "../SIGNOZ_COMPLETE_CONFIGURATION_GUIDE.md",
"issues": "https://github.com/your-repo/issues"
},
"notes": {
"format_fix": "All dashboards have been updated to use the correct SigNoz JSON schema with proper filter arrays to resolve the 'e.filter is not a function' error.",
"compatibility": "Tested with SigNoz v0.10.0+ and OpenTelemetry Collector v0.45.0+",
"customization": "You can customize these dashboards by editing the JSON files or cloning them in the SigNoz UI"
}
}