Pulpito

gabrioux-2024-03-26_20:31:35-orch:cephadm-wip-guits-testing-2024-03-26-0925-distro-default-smithi/7624077

Posted Started Updated
Runtime
Duration
In Waiting
 Machine Teuthology Branch OS Type OS Version Nodes Status
2024-03-26 20:31:49 2024-03-26 20:32:07 2024-03-26 20:58:05 0:25:58 0:16:00 0:09:58 smithi main centos 9.stream 3 fail

Description: orch:cephadm/workunits/{0-distro/centos_9.stream agent/on mon_election/connectivity task/test_host_drain}

Log: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-03-26_20:31:35-orch:cephadm-wip-guits-testing-2024-03-26-0925-distro-default-smithi/7624077/teuthology.log

Failure Reason:

"2024-03-26T20:52:16.917505+0000 mon.a (mon.0) 394 : cluster [WRN] Health check failed: 1 failed cephadm daemon(s) (CEPHADM_FAILED_DAEMON)" in cluster log

All Details...

  • log_href: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-03-26_20:31:35-orch:cephadm-wip-guits-testing-2024-03-26-0925-distro-default-smithi/7624077/teuthology.log
  • archive_path: /home/teuthworker/archive/gabrioux-2024-03-26_20:31:35-orch:cephadm-wip-guits-testing-2024-03-26-0925-distro-default-smithi/7624077
  • description: orch:cephadm/workunits/{0-distro/centos_9.stream agent/on mon_election/connectivity task/test_host_drain}
  • duration: 0:16:00
  • email: gabrioux@ibm.com
  • failure_reason: "2024-03-26T20:52:16.917505+0000 mon.a (mon.0) 394 : cluster [WRN] Health check failed: 1 failed cephadm daemon(s) (CEPHADM_FAILED_DAEMON)" in cluster log
  • flavor: default
  • job_id: 7624077
  • kernel:
    • kdb: True
    • sha1: distro
  • last_in_suite: False
  • machine_type: smithi
  • name: gabrioux-2024-03-26_20:31:35-orch:cephadm-wip-guits-testing-2024-03-26-0925-distro-default-smithi
  • nuke_on_error: True
  • os_type: centos
  • os_version: 9.stream
  • overrides:
    • admin_socket:
      • branch: wip-guits-testing-2024-03-26-0925
    • 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
      • sha1: 42fc52b86b14d4f88c40d75eb7102e0ab3918f55
    • ceph-deploy:
      • conf:
        • client:
          • log file: /var/log/ceph/ceph-$name.$pid.log
        • mon:
      • install:
        • ceph:
          • flavor: default
          • sha1: 42fc52b86b14d4f88c40d75eb7102e0ab3918f55
      • selinux:
        • allowlist:
          • scontext=system_u:system_r:logrotate_t:s0
      • workunit:
        • branch: wip-guits-testing-2024-03-26-0925
        • sha1: 42fc52b86b14d4f88c40d75eb7102e0ab3918f55
    • owner: scheduled_gabrioux@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: wip-guits-testing-2024-03-26-0925
    • seed: 832
    • sha1: 42fc52b86b14d4f88c40d75eb7102e0ab3918f55
    • subset: 1/8
    • suite: orch:cephadm
    • suite_branch: wip-guits-testing-2024-03-26-0925
    • suite_path: /home/teuthworker/src/git.ceph.com_ceph-c_42fc52b86b14d4f88c40d75eb7102e0ab3918f55/qa
    • suite_relpath: qa
    • suite_repo: https://git.ceph.com/ceph-ci.git
    • suite_sha1: 42fc52b86b14d4f88c40d75eb7102e0ab3918f55
    • targets:
      • smithi115.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBCDM5h2QARePYD4WdbbPVVqp2FfQhU/Ct0NyVGjEhLjH//n0SwlMdkmgvUwfCMfhsdB0b6OE2YvIUDhQQEhbdbI=
      • smithi152.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBD4UjXWaKRitKnM1ruiyi9NU6SUbST5w138N0+/fClu21DbqY2lahFWbfkyok8a1L6uK3YshJP8TC7qxE2GrZ/E=
      • smithi179.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBJVmxz6DkNV7HwmbmX9sIr6nkNoxTfKPG6AUy+DVGkqiENY34VvCmZnY4MKNNmS7jANtFYUz78ISk0ZV9hLxFFM=
    • 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:
      • 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: True
    • pcp_grafana_url:
    • priority: 70
    • user: gabrioux
    • queue:
    • posted: 2024-03-26 20:31:49
    • started: 2024-03-26 20:32:07
    • updated: 2024-03-26 20:58:05
    • status_class: danger
    • runtime: 0:25:58
    • wait_time: 0:09:58