all: children: cephs: hosts: instance: null computes: hosts: instance: null controllers: hosts: instance: null zuul_unreachable: hosts: {} hosts: instance: ansible_connection: ssh ansible_host: 162.253.55.218 ansible_port: 22 ansible_python_interpreter: auto ansible_user: zuul ceph_conf_overrides: - option: mon allow pool size one section: global value: true - option: osd crush chooseleaf type section: global value: 0 - option: auth allow insecure global id reclaim section: mon value: false ceph_csi_rbd_helm_values: provisioner: replicaCount: 1 ceph_fsid: 4837cbf8-4f90-4300-b3f6-726c9b9f89b4 ceph_osd_devices: - /dev/ceph-{{ inventory_hostname_short }}-osd0/data - /dev/ceph-{{ inventory_hostname_short }}-osd1/data - /dev/ceph-{{ inventory_hostname_short }}-osd2/data cilium_helm_values: operator: replicas: 1 cilium_ipv4_cidr: 172.24.0.0/16 csi_driver: rbd kube_vip_address: 172.17.0.100 kube_vip_interface: '{{ ansible_facts[''default_ipv4''].interface }}' kubernetes_hostname: '{{ ansible_facts[''default_ipv4''].address }}' molecule_scenario: csi nodepool: az: nova cloud: public external_id: 667e20aa-06e2-4f89-ab48-dc3149112364 host_id: c9670958829e9c96e47d452d2c9c4ce9edaac336d3dbc4a3c4ec531c interface_ip: 162.253.55.218 label: ubuntu-jammy node_properties: {} private_ipv4: 162.253.55.218 private_ipv6: null provider: yul1 public_ipv4: 162.253.55.218 public_ipv6: 2604:e100:1:0:f816:3eff:fe0e:ca7f region: ca-ymq-1 slot: null zuul_node: az: nova cloud: public external_id: 667e20aa-06e2-4f89-ab48-dc3149112364 host_id: c9670958829e9c96e47d452d2c9c4ce9edaac336d3dbc4a3c4ec531c interface_ip: 162.253.55.218 label: ubuntu-jammy node_properties: {} private_ipv4: 162.253.55.218 private_ipv6: null provider: yul1 public_ipv4: 162.253.55.218 public_ipv6: 2604:e100:1:0:f816:3eff:fe0e:ca7f region: ca-ymq-1 slot: null uuid: null vars: ceph_conf_overrides: - option: mon allow pool size one section: global value: true - option: osd crush chooseleaf type section: global value: 0 - option: auth allow insecure global id reclaim section: mon value: false ceph_csi_rbd_helm_values: provisioner: replicaCount: 1 ceph_fsid: 4837cbf8-4f90-4300-b3f6-726c9b9f89b4 ceph_osd_devices: - /dev/ceph-{{ inventory_hostname_short }}-osd0/data - /dev/ceph-{{ inventory_hostname_short }}-osd1/data - /dev/ceph-{{ inventory_hostname_short }}-osd2/data cilium_helm_values: operator: replicas: 1 cilium_ipv4_cidr: 172.24.0.0/16 csi_driver: rbd kube_vip_address: 172.17.0.100 kube_vip_interface: '{{ ansible_facts[''default_ipv4''].interface }}' kubernetes_hostname: '{{ ansible_facts[''default_ipv4''].address }}' molecule_scenario: csi zuul: _inheritance_path: - '' - '' - '' - '' - '' - '' ansible_version: '9' attempts: 1 branch: main build: a8d2cc95158e44408d7f2e797486faf1 build_refs: - branch: main change: '3564' change_message: "feat(kube_prometheus_stack): replace HighInternalServerErrors with SLO-based NGINX Ingress alerts\n\nReplaces the basic `HighInternalServerErrors` alert with two granular SLO-based alerts following the pattern established in #3542.\n\n## Changes\n\n- **New alerts** (`nginx.libsonnet`):\n - `NginxIngressHighErrorRate` (P3): 5% threshold, 15min duration\n - `NginxIngressCriticalErrorRate` (P2): 20% threshold, 5min duration\n \n- **Removed** `HighInternalServerErrors` from `openstack.libsonnet`\n\n- **Alert structure**:\n ```jsonnet\n {\n \ alert: 'NginxIngressHighErrorRate',\n expr: |||\n (\n sum by (service) (rate(nginx_ingress_controller_requests{status=~\"5[0-9]{2}\"}[5m]))\n \ /\n sum by (service) (rate(nginx_ingress_controller_requests[5m]))\n \ ) > 0.05\n |||,\n 'for': '15m',\n annotations: {\n summary: 'NGINX Ingress: elevated error rate affecting service',\n description: 'The service {{ $labels.service }} is returning 5xx errors at {{ $value | humanizePercentage }}...',\n runbook_url: 'https://vexxhost.github.io/atmosphere/admin/monitoring.html#nginxingresshigherrorrate',\n \ },\n }\n ```\n\n- **Documentation**: Added runbook entries with root cause analysis and diagnostic procedures\n\n- **Tests**: 4 unit tests covering threshold boundaries and duration requirements\n\n## Breaking Change\n\nAlert name changed from `HighInternalServerErrors` to `NginxIngressHighErrorRate` / `NginxIngressCriticalErrorRate`. Update routing rules and silences accordingly.\n\n\n---\n\n\U0001F4AC We'd love your input! Share your thoughts on Copilot coding agent in our [2 minute survey](https://gh.io/copilot-coding-agent-survey).\n" change_url: https://github.com/vexxhost/atmosphere/pull/3564 commit_id: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b patchset: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b project: canonical_hostname: github.com canonical_name: github.com/vexxhost/atmosphere name: vexxhost/atmosphere short_name: atmosphere src_dir: src/github.com/vexxhost/atmosphere topic: null buildset: 5bcbf90e8c8b4e328062a3a332539905 buildset_refs: - branch: main change: '3564' change_message: "feat(kube_prometheus_stack): replace HighInternalServerErrors with SLO-based NGINX Ingress alerts\n\nReplaces the basic `HighInternalServerErrors` alert with two granular SLO-based alerts following the pattern established in #3542.\n\n## Changes\n\n- **New alerts** (`nginx.libsonnet`):\n - `NginxIngressHighErrorRate` (P3): 5% threshold, 15min duration\n - `NginxIngressCriticalErrorRate` (P2): 20% threshold, 5min duration\n \n- **Removed** `HighInternalServerErrors` from `openstack.libsonnet`\n\n- **Alert structure**:\n ```jsonnet\n {\n \ alert: 'NginxIngressHighErrorRate',\n expr: |||\n (\n sum by (service) (rate(nginx_ingress_controller_requests{status=~\"5[0-9]{2}\"}[5m]))\n \ /\n sum by (service) (rate(nginx_ingress_controller_requests[5m]))\n \ ) > 0.05\n |||,\n 'for': '15m',\n annotations: {\n summary: 'NGINX Ingress: elevated error rate affecting service',\n description: 'The service {{ $labels.service }} is returning 5xx errors at {{ $value | humanizePercentage }}...',\n runbook_url: 'https://vexxhost.github.io/atmosphere/admin/monitoring.html#nginxingresshigherrorrate',\n \ },\n }\n ```\n\n- **Documentation**: Added runbook entries with root cause analysis and diagnostic procedures\n\n- **Tests**: 4 unit tests covering threshold boundaries and duration requirements\n\n## Breaking Change\n\nAlert name changed from `HighInternalServerErrors` to `NginxIngressHighErrorRate` / `NginxIngressCriticalErrorRate`. Update routing rules and silences accordingly.\n\n\n---\n\n\U0001F4AC We'd love your input! Share your thoughts on Copilot coding agent in our [2 minute survey](https://gh.io/copilot-coding-agent-survey).\n" change_url: https://github.com/vexxhost/atmosphere/pull/3564 commit_id: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b patchset: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b project: canonical_hostname: github.com canonical_name: github.com/vexxhost/atmosphere name: vexxhost/atmosphere short_name: atmosphere src_dir: src/github.com/vexxhost/atmosphere topic: null change: '3564' change_message: "feat(kube_prometheus_stack): replace HighInternalServerErrors with SLO-based NGINX Ingress alerts\n\nReplaces the basic `HighInternalServerErrors` alert with two granular SLO-based alerts following the pattern established in #3542.\n\n## Changes\n\n- **New alerts** (`nginx.libsonnet`):\n - `NginxIngressHighErrorRate` (P3): 5% threshold, 15min duration\n - `NginxIngressCriticalErrorRate` (P2): 20% threshold, 5min duration\n \n- **Removed** `HighInternalServerErrors` from `openstack.libsonnet`\n\n- **Alert structure**:\n ```jsonnet\n {\n \ alert: 'NginxIngressHighErrorRate',\n expr: |||\n (\n sum by (service) (rate(nginx_ingress_controller_requests{status=~\"5[0-9]{2}\"}[5m]))\n \ /\n sum by (service) (rate(nginx_ingress_controller_requests[5m]))\n \ ) > 0.05\n |||,\n 'for': '15m',\n annotations: {\n summary: 'NGINX Ingress: elevated error rate affecting service',\n description: 'The service {{ $labels.service }} is returning 5xx errors at {{ $value | humanizePercentage }}...',\n runbook_url: 'https://vexxhost.github.io/atmosphere/admin/monitoring.html#nginxingresshigherrorrate',\n \ },\n }\n ```\n\n- **Documentation**: Added runbook entries with root cause analysis and diagnostic procedures\n\n- **Tests**: 4 unit tests covering threshold boundaries and duration requirements\n\n## Breaking Change\n\nAlert name changed from `HighInternalServerErrors` to `NginxIngressHighErrorRate` / `NginxIngressCriticalErrorRate`. Update routing rules and silences accordingly.\n\n\n---\n\n\U0001F4AC We'd love your input! Share your thoughts on Copilot coding agent in our [2 minute survey](https://gh.io/copilot-coding-agent-survey).\n" change_url: https://github.com/vexxhost/atmosphere/pull/3564 child_jobs: [] commit_id: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b event_id: ebbc4350-0512-11f1-95ec-a0a25d578c28 executor: hostname: 3a2793d2bd32 inventory_file: /var/lib/zuul/builds/a8d2cc95158e44408d7f2e797486faf1/ansible/inventory.yaml log_root: /var/lib/zuul/builds/a8d2cc95158e44408d7f2e797486faf1/work/logs result_data_file: /var/lib/zuul/builds/a8d2cc95158e44408d7f2e797486faf1/work/results.json src_root: /var/lib/zuul/builds/a8d2cc95158e44408d7f2e797486faf1/work/src work_root: /var/lib/zuul/builds/a8d2cc95158e44408d7f2e797486faf1/work include_vars: [] items: - branch: main change: '3564' change_message: "feat(kube_prometheus_stack): replace HighInternalServerErrors with SLO-based NGINX Ingress alerts\n\nReplaces the basic `HighInternalServerErrors` alert with two granular SLO-based alerts following the pattern established in #3542.\n\n## Changes\n\n- **New alerts** (`nginx.libsonnet`):\n - `NginxIngressHighErrorRate` (P3): 5% threshold, 15min duration\n - `NginxIngressCriticalErrorRate` (P2): 20% threshold, 5min duration\n \n- **Removed** `HighInternalServerErrors` from `openstack.libsonnet`\n\n- **Alert structure**:\n ```jsonnet\n {\n \ alert: 'NginxIngressHighErrorRate',\n expr: |||\n (\n sum by (service) (rate(nginx_ingress_controller_requests{status=~\"5[0-9]{2}\"}[5m]))\n \ /\n sum by (service) (rate(nginx_ingress_controller_requests[5m]))\n \ ) > 0.05\n |||,\n 'for': '15m',\n annotations: {\n summary: 'NGINX Ingress: elevated error rate affecting service',\n description: 'The service {{ $labels.service }} is returning 5xx errors at {{ $value | humanizePercentage }}...',\n runbook_url: 'https://vexxhost.github.io/atmosphere/admin/monitoring.html#nginxingresshigherrorrate',\n \ },\n }\n ```\n\n- **Documentation**: Added runbook entries with root cause analysis and diagnostic procedures\n\n- **Tests**: 4 unit tests covering threshold boundaries and duration requirements\n\n## Breaking Change\n\nAlert name changed from `HighInternalServerErrors` to `NginxIngressHighErrorRate` / `NginxIngressCriticalErrorRate`. Update routing rules and silences accordingly.\n\n\n---\n\n\U0001F4AC We'd love your input! Share your thoughts on Copilot coding agent in our [2 minute survey](https://gh.io/copilot-coding-agent-survey).\n" change_url: https://github.com/vexxhost/atmosphere/pull/3564 commit_id: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b patchset: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b project: canonical_hostname: github.com canonical_name: github.com/vexxhost/atmosphere name: vexxhost/atmosphere short_name: atmosphere src_dir: src/github.com/vexxhost/atmosphere topic: null job: atmosphere-molecule-csi-rbd jobtags: [] max_attempts: 3 message: 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 patchset: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b pipeline: check playbook_context: playbook_projects: trusted/project_0/vexxhost.dev/zuul-config: canonical_name: vexxhost.dev/zuul-config checkout: main commit: 9052b5a7781b3346e4cffd452a54448cbff54d8b trusted/project_1/opendev.org/zuul/zuul-jobs: canonical_name: opendev.org/zuul/zuul-jobs checkout: master commit: d73b78cc624f363c6b7fcfe833f2db4571e4e979 trusted/project_2/github.com/vexxhost/zuul-jobs: canonical_name: github.com/vexxhost/zuul-jobs checkout: main commit: a6e68243e02ef030ce5e75f8b67630880c475f33 untrusted/project_0/github.com/vexxhost/zuul-jobs: canonical_name: github.com/vexxhost/zuul-jobs checkout: main commit: a6e68243e02ef030ce5e75f8b67630880c475f33 untrusted/project_1/vexxhost.dev/zuul-config: canonical_name: vexxhost.dev/zuul-config checkout: main commit: 9052b5a7781b3346e4cffd452a54448cbff54d8b untrusted/project_2/opendev.org/zuul/zuul-jobs: canonical_name: opendev.org/zuul/zuul-jobs checkout: master commit: d73b78cc624f363c6b7fcfe833f2db4571e4e979 untrusted/project_3/github.com/vexxhost/atmosphere: canonical_name: github.com/vexxhost/atmosphere checkout: main commit: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b untrusted/project_4/opendev.org/openstack/openstack-helm: canonical_name: opendev.org/openstack/openstack-helm checkout: master commit: 3a57ef7049b4b76a5a29f8331975931464a14d51 playbooks: - path: untrusted/project_0/github.com/vexxhost/zuul-jobs/playbooks/molecule/run.yaml roles: - checkout: master checkout_description: project default branch link_name: ansible/playbook_0/role_1/zuul-jobs link_target: untrusted/project_2/opendev.org/zuul/zuul-jobs role_path: ansible/playbook_0/role_1/zuul-jobs/roles - checkout: main checkout_description: playbook branch link_name: ansible/playbook_0/role_2/zuul-jobs link_target: untrusted/project_0/github.com/vexxhost/zuul-jobs role_path: ansible/playbook_0/role_2/zuul-jobs/roles post_review: false post_timeout: null pre_timeout: null project: canonical_hostname: github.com canonical_name: github.com/vexxhost/atmosphere name: vexxhost/atmosphere short_name: atmosphere src_dir: src/github.com/vexxhost/atmosphere projects: github.com/vexxhost/atmosphere: canonical_hostname: github.com canonical_name: github.com/vexxhost/atmosphere checkout: main checkout_description: zuul branch commit: 28eb61b7ed30e8ec0331e5588abd4b4e6f5d775b name: vexxhost/atmosphere required: false short_name: atmosphere src_dir: src/github.com/vexxhost/atmosphere ref: refs/pull/3564/head resources: {} tenant: oss timeout: 1800 topic: null voting: true