Pulpito

teuthology-2024-04-21_20:00:14-rados-main-distro-default-smithi/7666930

Posted Started Updated
Runtime
Duration
In Waiting
 Machine Teuthology Branch OS Type OS Version Nodes Status
2024-04-21 20:03:49 2024-04-21 20:31:49 2024-04-21 21:10:24 0:38:35 0:24:31 0:14:04 smithi main ubuntu 22.04 3 fail

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

Log: http://qa-proxy.ceph.com/teuthology/teuthology-2024-04-21_20:00:14-rados-main-distro-default-smithi/7666930/teuthology.log

Failure Reason:

"2024-04-21T21:01:03.014875+0000 mon.a (mon.0) 639 : cluster [WRN] Health check failed: 1 stray daemon(s) not managed by cephadm (CEPHADM_STRAY_DAEMON)" in cluster log

All Details...

  • log_href: http://qa-proxy.ceph.com/teuthology/teuthology-2024-04-21_20:00:14-rados-main-distro-default-smithi/7666930/teuthology.log
  • archive_path: /home/teuthworker/archive/teuthology-2024-04-21_20:00:14-rados-main-distro-default-smithi/7666930
  • description: rados/cephadm/workunits/{0-distro/ubuntu_22.04 agent/on mon_election/connectivity task/test_host_drain}
  • duration: 0:24:31
  • email: ceph-qa@ceph.com
  • failure_reason: "2024-04-21T21:01:03.014875+0000 mon.a (mon.0) 639 : cluster [WRN] Health check failed: 1 stray daemon(s) not managed by cephadm (CEPHADM_STRAY_DAEMON)" in cluster log
  • flavor: default
  • job_id: 7666930
  • kernel:
    • kdb: 1
    • sha1: distro
  • last_in_suite: False
  • machine_type: smithi
  • name: teuthology-2024-04-21_20:00:14-rados-main-distro-default-smithi
  • nuke_on_error: True
  • 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: True
        • mon:
          • debug mon: 20
          • debug ms: 1
          • debug paxos: 20
        • osd:
          • debug ms: 1
          • debug osd: 20
      • flavor: default
      • log-ignorelist:
        • \(MDS_ALL_DOWN\)
        • \(MDS_UP_LESS_THAN_MAX\)
        • MON_DOWN
        • mons down
        • mon down
        • out of quorum
      • log-only-match:
        • CEPHADM_
      • sha1: d5c8530042f7705c6e8ec83a32e0ea1be9cbad40
    • ceph-deploy:
      • conf:
        • client:
          • log file: /var/log/ceph/ceph-$name.$pid.log
        • mon:
      • install:
        • ceph:
          • flavor: default
          • sha1: d5c8530042f7705c6e8ec83a32e0ea1be9cbad40
      • workunit:
        • branch: main
        • sha1: 226cba1c5219f5bb8d0cd056721711c87d9bf2fd
    • owner: scheduled_teuthology@teuthology
    • pid:
    • roles:
      • ['host.a', 'mon.a', 'mgr.a', 'osd.0', 'osd.1']
      • ['host.b', 'mon.b', 'mgr.b', 'osd.2', 'osd.3']
      • ['host.c', 'mon.c', 'osd.4', 'osd.5']
    • sentry_event:
    • status: fail
    • success: False
    • branch: main
    • seed: 8858
    • sha1: d5c8530042f7705c6e8ec83a32e0ea1be9cbad40
    • subset: 15139/100000
    • suite: rados
    • suite_branch: main
    • suite_path: /home/teuthworker/src/git.ceph.com_ceph_226cba1c5219f5bb8d0cd056721711c87d9bf2fd/qa
    • suite_relpath: qa
    • suite_repo: https://git.ceph.com/ceph.git
    • suite_sha1: 226cba1c5219f5bb8d0cd056721711c87d9bf2fd
    • targets:
      • smithi090.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBL1zFEuzNMJAhWToY8wDHSaHWsNXpTAdq3vWhe46eVhgn94VDpgtK6ucZ4Zwu60myOmDUouksrW4xlGnm/5gso8=
      • smithi119.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBDgzUKoaweWJDpk9u5k8fhEc5sbw/vKoRFMlIM7MVK7GM8nWo9df7I3Z/isA1Nrp2PSVohexeRXINNGkg2HoJLs=
      • smithi178.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBImVKtFA0Ra6r4ubkCF2MEa26anv3VyU/tgnPJRpiIQOFJ7NWVo5tiUes8gcteWJ/aeqOvyTjG89mus5cMqG+Cg=
    • 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:
      • install:
      • cephadm:
      • cephadm.shell:
        • host.a:
          • set -ex HOSTNAMES=$(ceph orch host ls --format json | jq -r '.[] | .hostname') for host in $HOSTNAMES; do # find the hostname for "host.c" which will have no mgr HAS_MGRS=$(ceph orch ps --hostname ${host} --format json | jq 'any(.daemon_type == "mgr")') if [ "$HAS_MGRS" == "false" ]; then HOST_C="${host}" fi done # One last thing to worry about before draining the host # is that the teuthology test tends to put the explicit # hostnames in the placement for the mon service. # We want to make sure we can drain without providing # --force and there is a check for the host being removed # being listed explicitly in the placements. Therefore, # we should remove it from the mon placement. ceph orch ls mon --export > mon.yaml sed /"$HOST_C"/d mon.yaml > mon_adjusted.yaml ceph orch apply -i mon_adjusted.yaml # now drain that host ceph orch host drain $HOST_C --zap-osd-devices # wait for drain to complete HOST_C_DAEMONS=$(ceph orch ps --hostname $HOST_C) while [ "$HOST_C_DAEMONS" != "No daemons reported" ]; do sleep 15 HOST_C_DAEMONS=$(ceph orch ps --hostname $HOST_C) done # we want to check the ability to remove the host from # the CRUSH map, so we should first verify the host is in # the CRUSH map. ceph osd getcrushmap -o compiled-crushmap crushtool -d compiled-crushmap -o crushmap.txt CRUSH_MAP=$(cat crushmap.txt) if ! grep -q "$HOST_C" <<< "$CRUSH_MAP"; then printf "Expected to see $HOST_C in CRUSH map. Saw:\n\n$CRUSH_MAP" exit 1 fi # If the drain was successful, we should be able to remove the # host without force with no issues. If there are still daemons # we will get a response telling us to drain the host and a # non-zero return code ceph orch host rm $HOST_C --rm-crush-entry # verify we've successfully removed the host from the CRUSH map sleep 30 ceph osd getcrushmap -o compiled-crushmap crushtool -d compiled-crushmap -o crushmap.txt CRUSH_MAP=$(cat crushmap.txt) if grep -q "$HOST_C" <<< "$CRUSH_MAP"; then printf "Saw $HOST_C in CRUSH map after it should have been removed.\n\n$CRUSH_MAP" exit 1 fi
    • teuthology_branch: main
    • verbose: False
    • pcp_grafana_url:
    • priority: 951
    • user: teuthology
    • queue:
    • posted: 2024-04-21 20:03:49
    • started: 2024-04-21 20:31:49
    • updated: 2024-04-21 21:10:24
    • status_class: danger
    • runtime: 0:38:35
    • wait_time: 0:14:04