Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2024-03-01 20:53:29	2024-03-02 01:26:35	2024-03-02 02:02:50	0:36:15	0:23:11	0:13:04	smithi	main	ubuntu	22.04	3	fail

Nodes: smithi039 smithi067 smithi176

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

Log: http://qa-proxy.ceph.com/teuthology/yuriw-2024-03-01_20:50:47-rados-squid-distro-default-smithi/7578332/teuthology.log

Failure Reason:

"2024-03-02T02:00:00.000218+0000 mon.a (mon.0) 655 : cluster 3 [WRN] OSD_DOWN: 1 osds down" in cluster log

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/yuriw-2024-03-01_20:50:47-rados-squid-distro-default-smithi/7578332/teuthology.log
archive_path: /home/teuthworker/archive/yuriw-2024-03-01_20:50:47-rados-squid-distro-default-smithi/7578332
description: rados/cephadm/workunits/{0-distro/ubuntu_22.04 agent/off mon_election/classic task/test_host_drain}
duration: 0:23:11
email: yweinste@redhat.com
failure_reason: "2024-03-02T02:00:00.000218+0000 mon.a (mon.0) 655 : cluster 3 [WRN] OSD_DOWN: 1 osds down" in cluster log
flavor: default
job_id: 7578332
kernel:
- kdb: True
- sha1: distro
last_in_suite: False
machine_type: smithi
name: yuriw-2024-03-01_20:50:47-rados-squid-distro-default-smithi
nuke_on_error: True
os_type: ubuntu
os_version: 22.04
overrides:
- admin_socket:
  - branch: squid
- 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
  - sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
- install:
  - ceph:
    - flavor: default
    - sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
- workunit:
  - branch: squid
  - sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
owner: scheduled_yuriw@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: squid
seed:
sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
subset:
suite:
suite_branch: squid
suite_path:
suite_relpath:
suite_repo:
suite_sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
targets:
- smithi039.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBDz4w7/rVK5pQAqvsrz/rqfWi9GsoLmWf8vXxNWh4lZLjPiivJ0pSZnkNwGmA35ICZCLJucCinDuN/8k4TlwsuE=
- smithi067.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBAZPxju/OcjE6iJYT1cYru8CCDRsPdxWKoMULmBMyQwSt3T6fmAwOVhKAKLXeTFfplhC1d7Yju7ABvWqjNcTsWQ=
- smithi176.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBI9PSiiaT4B/F9dgqaqZEYUeqKGBWaQds4Xre7nHXam4tXvUd90xIOee4F+3SbAn4U/F8sGDHd/ADOUKpct+HI8=
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:
user:
queue:
posted: 2024-03-01 20:53:29
started: 2024-03-02 01:26:35
updated: 2024-03-02 02:02:50
status_class: danger
runtime: 0:36:15
wait_time: 0:13:04