groups: - name: ReplayGroup interval: 1m concurrency: 1 rules: - record: type:vm_cache_entries:rate5m expr: sum(rate(vm_cache_entries[5m])) by (type) labels: recording: true - record: go_cgo_calls_count:rate5m expr: rate(go_cgo_calls_count{job="vmdb"}[5m]) labels: recording: true - name: vmsingleReplay interval: 30s concurrency: 2 rules: - alert: RequestErrorsToAPI expr: increase(vm_http_request_errors_total[5m]) > 0 for: 15m labels: severity: warning annotations: dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=35&var-instance={{ $labels.instance }}" summary: "Too many errors served for path {{ $labels.path }} (instance {{ $labels.instance }})" description: "Requests to path {{ $labels.path }} are receiving errors. Please verify if clients are sending correct requests." - alert: TooManyLogs expr: sum(increase(vm_log_messages_total{level!="info"}[5m])) by (job, instance) > 0 for: 15m labels: severity: warning annotations: dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=67&var-instance={{ $labels.instance }}" summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})" description: "Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.\n Worth to check logs for specific error messages."