Pulpito

gabrioux-2024-07-03_14:50:01-orch:cephadm-squid-release-distro-default-smithi/7785901

Posted Started Updated
Runtime
Duration
In Waiting
 Machine Teuthology Branch OS Type OS Version Nodes Status
2024-07-03 14:52:10 2024-07-03 16:06:33 2024-07-03 16:36:03 0:29:30 0:19:08 0:10:22 smithi main centos 9.stream 3 pass

Description: orch:cephadm/workunits/{0-distro/centos_9.stream_runc agent/off mon_election/classic task/test_monitoring_stack_basic}

Log: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-07-03_14:50:01-orch:cephadm-squid-release-distro-default-smithi/7785901/teuthology.log

All Details...

  • log_href: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-07-03_14:50:01-orch:cephadm-squid-release-distro-default-smithi/7785901/teuthology.log
  • archive_path: /home/teuthworker/archive/gabrioux-2024-07-03_14:50:01-orch:cephadm-squid-release-distro-default-smithi/7785901
  • description: orch:cephadm/workunits/{0-distro/centos_9.stream_runc agent/off mon_election/classic task/test_monitoring_stack_basic}
  • duration: 0:19:08
  • email: gabrioux@ibm.com
  • failure_reason:
  • flavor: default
  • job_id: 7785901
  • kernel:
    • kdb: 1
    • sha1: distro
  • last_in_suite: False
  • machine_type: smithi
  • name: gabrioux-2024-07-03_14:50:01-orch:cephadm-squid-release-distro-default-smithi
  • nuke_on_error:
  • os_type: centos
  • os_version: 9.stream
  • overrides:
    • admin_socket:
      • branch: squid-release
    • ceph:
      • conf:
        • global:
          • mon election default strategy: 1
        • 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: c00506dc10003928f8cb40769168571f611cbd67
    • ceph-deploy:
      • conf:
        • client:
          • log file: /var/log/ceph/ceph-$name.$pid.log
        • mon:
      • install:
        • ceph:
          • flavor: default
          • sha1: c00506dc10003928f8cb40769168571f611cbd67
      • selinux:
        • allowlist:
          • scontext=system_u:system_r:logrotate_t:s0
      • workunit:
        • branch: squid-release
        • sha1: 47d23ed6cd9bd552d37bff09d8392220d7ba7b11
    • owner: scheduled_gabrioux@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: pass
    • success: True
    • branch: squid-release
    • seed: 3319
    • sha1: c00506dc10003928f8cb40769168571f611cbd67
    • subset: 1/8
    • suite: orch:cephadm
    • suite_branch: squid-release
    • suite_path: /home/teuthworker/src/github.com_guits_ceph_47d23ed6cd9bd552d37bff09d8392220d7ba7b11/qa
    • suite_relpath: qa
    • suite_repo: https://github.com/guits/ceph
    • suite_sha1: 47d23ed6cd9bd552d37bff09d8392220d7ba7b11
    • targets:
      • smithi045.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBNfQLdIfSdEBDD8qIufWdT0sxBE3QIjpwiSEKpu/Iiw146Ket7CCYAx1bGpP6gKQtb7BgA/1WIthY6gnX5RVNv4=
      • smithi053.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBCcl2ekeukZDj8zVQ4S4ZVZAiYdXqSQjWE9uxQ9a4aOxeKN7uuhIFNYGAG81r59rFyu6S3kZk5PGGJWT6gu/0Dg=
      • smithi178.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBAI0BuThZPpprVtyTyBJl+tzKqkAH7ABn4aYwRgiDq8hijLCF7v6Dxf2TPRBFDJtpLGfQbYKjqIyocgzUWF9Quw=
    • tasks:
      • internal.check_packages:
      • internal.buildpackages_prep:
      • internal.save_config:
      • internal.check_lock:
      • internal.add_remotes:
      • console_log:
      • internal.connect:
      • internal.push_inventory:
      • internal.serialize_remote_roles:
      • internal.check_conflict:
      • internal.check_ceph_data:
      • internal.vm_setup:
      • kernel:
        • kdb: 1
        • sha1: distro
      • internal.base:
      • internal.archive_upload:
      • internal.archive:
      • internal.coredump:
      • internal.sudo:
      • internal.syslog:
      • internal.timer:
      • pcp:
      • selinux:
      • ansible.cephlab:
      • clock:
      • pexec:
        • all:
          • sudo dnf install runc nvmetcli nvme-cli -y
          • sudo sed -i 's/^#runtime = "crun"/runtime = "runc"/g' /usr/share/containers/containers.conf
          • sudo sed -i 's/runtime = "crun"/#runtime = "crun"/g' /usr/share/containers/containers.conf
      • 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: True
    • pcp_grafana_url:
    • priority: 30
    • user: gabrioux
    • queue:
    • posted: 2024-07-03 14:52:10
    • started: 2024-07-03 16:06:33
    • updated: 2024-07-03 16:36:03
    • status_class: success
    • runtime: 0:29:30
    • wait_time: 0:10:22