Pulpito

gabrioux-2024-01-27_07:25:23-orch:cephadm-wip-guits-testing-2024-01-27-0056-distro-default-smithi/7535376

Posted Started Updated
Runtime
Duration
In Waiting
 Machine Teuthology Branch OS Type OS Version Nodes Status
2024-01-27 07:26:25 2024-01-27 08:45:08 2024-01-27 09:24:07 0:38:59 0:29:45 0:09:14 smithi main rhel 8.6 3 pass

Description: orch:cephadm/workunits/{0-distro/rhel_8.6_container_tools_3.0 agent/on mon_election/connectivity task/test_monitoring_stack_basic}

Log: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-01-27_07:25:23-orch:cephadm-wip-guits-testing-2024-01-27-0056-distro-default-smithi/7535376/teuthology.log

All Details...

  • log_href: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-01-27_07:25:23-orch:cephadm-wip-guits-testing-2024-01-27-0056-distro-default-smithi/7535376/teuthology.log
  • archive_path: /home/teuthworker/archive/gabrioux-2024-01-27_07:25:23-orch:cephadm-wip-guits-testing-2024-01-27-0056-distro-default-smithi/7535376
  • description: orch:cephadm/workunits/{0-distro/rhel_8.6_container_tools_3.0 agent/on mon_election/connectivity task/test_monitoring_stack_basic}
  • duration: 0:29:45
  • email: gabrioux@ibm.com
  • failure_reason:
  • flavor: default
  • job_id: 7535376
  • kernel:
    • kdb: True
    • sha1: distro
  • last_in_suite: False
  • machine_type: smithi
  • name: gabrioux-2024-01-27_07:25:23-orch:cephadm-wip-guits-testing-2024-01-27-0056-distro-default-smithi
  • nuke_on_error: True
  • os_type: rhel
  • os_version: 8.6
  • overrides:
    • admin_socket:
      • branch: wip-guits-testing-2024-01-27-0056
    • ceph:
      • conf:
        • global:
          • mon election default strategy: 3
        • mgr:
          • debug mgr: 20
          • debug ms: 1
          • mgr/cephadm/use_agent: True
        • mon:
          • debug mon: 20
          • debug ms: 1
          • debug paxos: 20
        • osd:
          • debug ms: 1
          • debug osd: 20
      • flavor: default
      • log-ignorelist:
        • \(MDS_ALL_DOWN\)
        • \(MDS_UP_LESS_THAN_MAX\)
      • sha1: 994126d01a889b75062bb3ee87e6fbcc61a5f31d
    • ceph-deploy:
      • conf:
        • client:
          • log file: /var/log/ceph/ceph-$name.$pid.log
        • mon:
      • install:
        • ceph:
          • flavor: default
          • sha1: 994126d01a889b75062bb3ee87e6fbcc61a5f31d
      • selinux:
        • whitelist:
          • scontext=system_u:system_r:logrotate_t:s0
      • workunit:
        • branch: wip-guits-testing-2024-01-27-0056
        • sha1: 994126d01a889b75062bb3ee87e6fbcc61a5f31d
    • 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: wip-guits-testing-2024-01-27-0056
    • seed:
    • sha1: 994126d01a889b75062bb3ee87e6fbcc61a5f31d
    • subset:
    • suite:
    • suite_branch: wip-guits-testing-2024-01-27-0056
    • suite_path:
    • suite_relpath:
    • suite_repo:
    • suite_sha1: 994126d01a889b75062bb3ee87e6fbcc61a5f31d
    • targets:
      • smithi089.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBJ2Bc7KO4NYdziMKOmdFjfbQGNGIIZNZ0sGQsBRAXPHle+wuUkXTlQMI8YEVMBjde5skWKbXSvNTnlLf++ltFUw=
      • smithi184.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBACQzI6akeD3istCQpeU20X6fq8ksyB/4L6OZybMHX8QO5bMqW2kQ25gGtlsChsUeeiOvqAcXcEAOdiwEh00gS8=
      • smithi196.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBBJz31I/2HXdmxphF6/vTqCG9/l3dhMIBRNeXVQvwj9ZxKdY1vwJmsQGVFWhUEQw67S2b3SSVoE4rFNqr5QDciE=
    • 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: True
        • 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 cp /etc/containers/registries.conf /etc/containers/registries.conf.backup
          • sudo dnf -y module reset container-tools
          • sudo dnf -y module install container-tools:3.0 --allowerasing --nobest
          • sudo cp /etc/containers/registries.conf.backup /etc/containers/registries.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:
    • user:
    • queue:
    • posted: 2024-01-27 07:26:25
    • started: 2024-01-27 08:45:08
    • updated: 2024-01-27 09:24:07
    • status_class: success
    • runtime: 0:38:59
    • wait_time: 0:09:14