Path: blob/main/operations/observability/mixins/meta/rules/login-slo.yaml
3645 views
# Copyright (c) 2022 Gitpod GmbH. All rights reserved.1# Licensed under the GNU Affero General Public License (AGPL).2# See License.AGPL.txt in the project root for license information.34apiVersion: monitoring.coreos.com/v15kind: PrometheusRule6metadata:7labels:8prometheus: k8s9role: alert-rules10name: login-slo-monitoring-rules11spec:12groups:13- name: login-slo-recording-rules14rules:15- record: gitpod_server_login_requests_total:5m_failure_ratio16expr: |17sum(rate(gitpod_server_login_requests_total{status="failed"}[5m]))18/19sum(rate(gitpod_server_login_requests_total[5m]))2021- record: gitpod_server_login_requests_total:30m_failure_ratio22expr: |23sum(rate(gitpod_server_login_requests_total{status="failed"}[30m]))24/25sum(rate(gitpod_server_login_requests_total[30m]))2627- record: gitpod_server_login_requests_total:1h_failure_ratio28expr: |29sum(rate(gitpod_server_login_requests_total{status="failed"}[1h]))30/31sum(rate(gitpod_server_login_requests_total[1h]))3233- record: gitpod_server_login_requests_total:2h_failure_ratio34expr: |35sum(rate(gitpod_server_login_requests_total{status="failed"}[2h]))36/37sum(rate(gitpod_server_login_requests_total[2h]))3839- record: gitpod_server_login_requests_total:6h_failure_ratio40expr: |41sum(rate(gitpod_server_login_requests_total{status="failed"}[6h]))42/43sum(rate(gitpod_server_login_requests_total[6h]))4445- record: gitpod_server_login_requests_total:1d_failure_ratio46expr: |47sum(rate(gitpod_server_login_requests_total{status="failed"}[1d]))48/49sum(rate(gitpod_server_login_requests_total[1d]))5051- record: gitpod_server_login_requests_total:3d_failure_ratio52expr: |53sum(rate(gitpod_server_login_requests_total{status="failed"}[3d]))54/55sum(rate(gitpod_server_login_requests_total[3d]))5657- record: gitpod_server_login_requests_total:30d_failure_ratio58expr: |59sum(rate(gitpod_server_login_requests_total{status="failed"}[30d]))60/61sum(rate(gitpod_server_login_requests_total[30d]))6263- record: gitpod_server_login_requests_total:slo_target64expr: "0.95"6566- record: gitpod_server_login_requests_total:error_budget_remaining67expr: gitpod_server_login_requests_total:monthly_availability - gitpod_server_login_requests_total:slo_target6869- record: gitpod_server_login_requests_total:monthly_availability70expr: 1 - gitpod_server_login_requests_total:30d_failure_ratio7172- name: login-slo-alerts73rules:74- alert: GitpodLoginErrorBudgetBurn75labels:76severity: critical77annotations:78runbook_url: https://github.com/gitpod-com/observability/blob/main/runbooks/GitpodLoginErrorBudgetBurn.md79summary: Error budget is being burn too quickly.80description: Error budget is being burn too quickly. At this rate, the whole monthly budget will be burnt in less than 2 days.81expr: |82(83gitpod_server_login_requests_total:1h_failure_ratio > (14.4 * (1 - gitpod_server_login_requests_total:slo_target))84and85gitpod_server_login_requests_total:5m_failure_ratio > (14.4 * (1 - gitpod_server_login_requests_total:slo_target))86)87or88(89gitpod_server_login_requests_total:6h_failure_ratio > (6 * (1 - gitpod_server_login_requests_total:slo_target))90and91gitpod_server_login_requests_total:30m_failure_ratio > (6 * (1 - gitpod_server_login_requests_total:slo_target))92)9394- alert: GitpodLoginErrorBudgetBurn95labels:96severity: warning97annotations:98runbook_url: https://github.com/gitpod-com/observability/blob/main/runbooks/GitpodLoginErrorBudgetBurn.md99summary: Error budget is being burn quickly.100description: Error budget is being burn quickly. At this rate, the whole monthly budget will be burnt in less than 10 days.101expr: |102(103gitpod_server_login_requests_total:1d_failure_ratio > (3 * (1 - gitpod_server_login_requests_total:slo_target))104and105gitpod_server_login_requests_total:2h_failure_ratio > (3 * (1 - gitpod_server_login_requests_total:slo_target))106)107or108(109gitpod_server_login_requests_total:3d_failure_ratio > (1 * (1 - gitpod_server_login_requests_total:slo_target))110and111gitpod_server_login_requests_total:6h_failure_ratio > (1 * (1 - gitpod_server_login_requests_total:slo_target))112)113114115