Pulpito

teuthology-2024-07-21_20:00:15-rados-main-distro-default-smithi/7811406

Posted Started Updated
Runtime
Duration
In Waiting
 Machine Teuthology Branch OS Type OS Version Nodes Status
2024-07-21 20:04:49 2024-09-07 13:29:47 smithi main ubuntu 22.04 — dead

Description: rados/cephadm/workunits/{0-distro/ubuntu_22.04 agent/off mon_election/connectivity task/test_monitoring_stack_basic}

Log: http://qa-proxy.ceph.com/teuthology/teuthology-2024-07-21_20:00:15-rados-main-distro-default-smithi/7811406/teuthology.log

All Details...

  • log_href: http://qa-proxy.ceph.com/teuthology/teuthology-2024-07-21_20:00:15-rados-main-distro-default-smithi/7811406/teuthology.log
  • archive_path:
  • description: rados/cephadm/workunits/{0-distro/ubuntu_22.04 agent/off mon_election/connectivity task/test_monitoring_stack_basic}
  • duration:
  • email: ceph-qa@ceph.com
  • failure_reason:
  • flavor:
  • job_id: 7811406
  • kernel:
    • kdb: 1
    • sha1: distro
  • last_in_suite: False
  • machine_type: smithi
  • name: teuthology-2024-07-21_20:00:15-rados-main-distro-default-smithi
  • nuke_on_error:
  • os_type: ubuntu
  • os_version: 22.04
  • overrides:
    • admin_socket:
      • branch: main
    • ceph:
      • conf:
        • global:
          • mon election default strategy: 3
        • mgr:
          • debug mgr: 20
          • debug ms: 1
          • mgr/cephadm/use_agent: False
        • mon:
          • debug mon: 20
          • debug ms: 1
          • debug paxos: 20
        • osd:
          • debug ms: 1
          • debug osd: 20
      • flavor: default
      • log-ignorelist:
        • \(MDS_ALL_DOWN\)
        • \(MDS_UP_LESS_THAN_MAX\)
        • MON_DOWN
        • mons down
        • mon down
        • out of quorum
        • CEPHADM_STRAY_DAEMON
        • CEPHADM_FAILED_DAEMON
      • log-only-match:
        • CEPHADM_
      • sha1: d557013a4f70b9d8a6a2e6c5e73c6fee3106dc2a
    • ceph-deploy:
      • conf:
        • client:
          • log file: /var/log/ceph/ceph-$name.$pid.log
        • mon:
      • install:
        • ceph:
          • flavor: default
          • sha1: d557013a4f70b9d8a6a2e6c5e73c6fee3106dc2a
      • workunit:
        • branch: main
        • sha1: d557013a4f70b9d8a6a2e6c5e73c6fee3106dc2a
    • owner: scheduled_teuthology@teuthology
    • pid:
    • roles:
      • ['host.a', 'mon.a', 'mgr.a', 'osd.0']
      • ['host.b', 'mon.b', 'mgr.b', 'osd.1']
      • ['host.c', 'mon.c', 'osd.2']
    • sentry_event:
    • status: dead
    • success:
    • branch: main
    • seed: 7590
    • sha1: d557013a4f70b9d8a6a2e6c5e73c6fee3106dc2a
    • subset: 6350/100000
    • suite: rados
    • suite_branch: main
    • suite_path:
    • suite_relpath: qa
    • suite_repo: https://git.ceph.com/ceph.git
    • suite_sha1: d557013a4f70b9d8a6a2e6c5e73c6fee3106dc2a
    • targets:
    • tasks:
      • install:
      • cephadm:
      • cephadm.shell:
        • host.a:
          • set -e set -x ceph orch apply node-exporter ceph orch apply grafana ceph orch apply alertmanager ceph orch apply prometheus sleep 240 ceph orch ls ceph orch ps ceph orch host ls MON_DAEMON=$(ceph orch ps --daemon-type mon -f json | jq -r 'last | .daemon_name') GRAFANA_HOST=$(ceph orch ps --daemon-type grafana -f json | jq -e '.[]' | jq -r '.hostname') PROM_HOST=$(ceph orch ps --daemon-type prometheus -f json | jq -e '.[]' | jq -r '.hostname') ALERTM_HOST=$(ceph orch ps --daemon-type alertmanager -f json | jq -e '.[]' | jq -r '.hostname') GRAFANA_IP=$(ceph orch host ls -f json | jq -r --arg GRAFANA_HOST "$GRAFANA_HOST" '.[] | select(.hostname==$GRAFANA_HOST) | .addr') PROM_IP=$(ceph orch host ls -f json | jq -r --arg PROM_HOST "$PROM_HOST" '.[] | select(.hostname==$PROM_HOST) | .addr') ALERTM_IP=$(ceph orch host ls -f json | jq -r --arg ALERTM_HOST "$ALERTM_HOST" '.[] | select(.hostname==$ALERTM_HOST) | .addr') # check each host node-exporter metrics endpoint is responsive ALL_HOST_IPS=$(ceph orch host ls -f json | jq -r '.[] | .addr') for ip in $ALL_HOST_IPS; do curl -s http://${ip}:9100/metric done # check grafana endpoints are responsive and database health is okay curl -k -s https://${GRAFANA_IP}:3000/api/health curl -k -s https://${GRAFANA_IP}:3000/api/health | jq -e '.database == "ok"' # stop mon daemon in order to trigger an alert ceph orch daemon stop $MON_DAEMON sleep 120 # check prometheus endpoints are responsive and mon down alert is firing curl -s http://${PROM_IP}:9095/api/v1/status/config curl -s http://${PROM_IP}:9095/api/v1/status/config | jq -e '.status == "success"' curl -s http://${PROM_IP}:9095/api/v1/alerts curl -s http://${PROM_IP}:9095/api/v1/alerts | jq -e '.data | .alerts | .[] | select(.labels | .alertname == "CephMonDown") | .state == "firing"' # check alertmanager endpoints are responsive and mon down alert is active curl -s http://${ALERTM_IP}:9093/api/v1/status curl -s http://${ALERTM_IP}:9093/api/v1/alerts curl -s http://${ALERTM_IP}:9093/api/v1/alerts | jq -e '.data | .[] | select(.labels | .alertname == "CephMonDown") | .status | .state == "active"'
    • teuthology_branch: main
    • verbose: False
    • pcp_grafana_url:
    • priority: 951
    • user: teuthology
    • queue:
    • posted: 2024-07-21 20:04:49
    • started:
    • updated: 2024-09-07 13:29:47
    • status_class: danger