Files
git.stella-ops.org/ops/devops/orchestrator/alerts.yaml
StellaOps Bot 9f6e6f7fb3
Some checks failed
Docs CI / lint-and-preview (push) Has been cancelled
Signals CI & Image / signals-ci (push) Has been cancelled
Policy Lint & Smoke / policy-lint (push) Has been cancelled
Policy Simulation / policy-simulate (push) Has been cancelled
SDK Publish & Sign / sdk-publish (push) Has been cancelled
AOC Guard CI / aoc-guard (push) Has been cancelled
AOC Guard CI / aoc-verify (push) Has been cancelled
Concelier Attestation Tests / attestation-tests (push) Has been cancelled
devportal-offline / build-offline (push) Has been cancelled
up
2025-11-25 22:09:44 +02:00

70 lines
2.4 KiB
YAML

groups:
- name: orchestrator-core
rules:
- alert: OrchestratorQueueDepthHigh
expr: job_queue_depth > 500
for: 10m
labels:
severity: warning
service: orchestrator
annotations:
summary: "Queue depth high"
description: "job_queue_depth exceeded 500 for 10m"
- alert: OrchestratorFailuresHigh
expr: rate(job_failures_total[5m]) > 5
for: 5m
labels:
severity: critical
service: orchestrator
annotations:
summary: "Job failures elevated"
description: "Failure rate above 5/min in last 5m"
- alert: OrchestratorLeaseStall
expr: rate(lease_extensions_total[5m]) == 0 and job_queue_depth > 0
for: 5m
labels:
severity: critical
service: orchestrator
annotations:
summary: "Leases stalled"
description: "No lease renewals while queue has items"
- alert: OrchestratorDLQDepthHigh
expr: job_dlq_depth > 10
for: 10m
labels:
severity: warning
service: orchestrator
annotations:
summary: "DLQ depth high"
description: "Dead-letter queue depth above 10 for 10m"
- alert: OrchestratorBackpressure
expr: avg_over_time(rate_limiter_backpressure_ratio[5m]) > 0.5
for: 5m
labels:
severity: warning
service: orchestrator
annotations:
summary: "Backpressure elevated"
description: "Rate limiter backpressure >50% over 5m"
- alert: OrchestratorErrorCluster
expr: sum by(jobType) (rate(job_failures_total[5m])) > 3
for: 5m
labels:
severity: critical
service: orchestrator
annotations:
summary: "Error cluster detected"
description: "Failure rate >3/min for a job type"
- alert: OrchestratorFailureBurnRateHigh
expr: |
(rate(job_failures_total[5m]) / clamp_min(rate(job_processed_total[5m]), 1)) > 0.02
and
(rate(job_failures_total[30m]) / clamp_min(rate(job_processed_total[30m]), 1)) > 0.01
for: 10m
labels:
severity: critical
service: orchestrator
annotations:
summary: "Failure burn rate breaching SLO"
description: "5m/30m failure burn rate above 2%/1% SLO; investigate upstream jobs and dependencies."