Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2023-03-29 11:58:28	2023-03-29 16:15:54	2023-03-29 16:48:15	0:32:21	0:21:39	0:10:42	smithi	main	centos	8.stream	2	fail

Nodes: smithi006 smithi135

Description: orch:cephadm/upgrade/{1-start-distro/1-start-centos_8.stream_container-tools 2-repo_digest/defaut 3-upgrade/staggered 4-wait 5-upgrade-ls agent/on mon_election/classic}

Log: http://qa-proxy.ceph.com/teuthology/adking-2023-03-29_11:57:55-orch:cephadm-wip-adk-testing-2023-03-28-1716-distro-default-smithi/7225323/teuthology.log

Sentry event: https://sentry.ceph.com/organizations/ceph/?query=8868d6340fba45279145d0c9972cdad7

Failure Reason:

Command failed on smithi006 with status 2: 'sudo /home/ubuntu/cephtest/cephadm --image quay.io/ceph/ceph:v16.2.0 shell -c /etc/ceph/ceph.conf -k /etc/ceph/ceph.client.admin.keyring --fsid 8a786de6-ce4f-11ed-9afe-001a4aab830c -e sha1=0d827ca1c6ef996567b7f5bc9aca774dc70bce60 -- bash -c \'ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e \'"\'"\'.[] | select(.daemon_type=="mgr") | select(.container_image_id==$TARGET_ID)\'"\'"\' | jq -s > out.json\''

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/adking-2023-03-29_11:57:55-orch:cephadm-wip-adk-testing-2023-03-28-1716-distro-default-smithi/7225323/teuthology.log
archive_path: /home/teuthworker/archive/adking-2023-03-29_11:57:55-orch:cephadm-wip-adk-testing-2023-03-28-1716-distro-default-smithi/7225323
description: orch:cephadm/upgrade/{1-start-distro/1-start-centos_8.stream_container-tools 2-repo_digest/defaut 3-upgrade/staggered 4-wait 5-upgrade-ls agent/on mon_election/classic}
duration: 0:21:39
email: adking@redhat.com
failure_reason: Command failed on smithi006 with status 2: 'sudo /home/ubuntu/cephtest/cephadm --image quay.io/ceph/ceph:v16.2.0 shell -c /etc/ceph/ceph.conf -k /etc/ceph/ceph.client.admin.keyring --fsid 8a786de6-ce4f-11ed-9afe-001a4aab830c -e sha1=0d827ca1c6ef996567b7f5bc9aca774dc70bce60 -- bash -c \'ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e \'"\'"\'.[] | select(.daemon_type=="mgr") | select(.container_image_id==$TARGET_ID)\'"\'"\' | jq -s > out.json\''
flavor:
job_id: 7225323
kernel:
- kdb: True
- sha1: distro
last_in_suite: False
machine_type: smithi
name: adking-2023-03-29_11:57:55-orch:cephadm-wip-adk-testing-2023-03-28-1716-distro-default-smithi
nuke_on_error: True
os_type: centos
os_version: 8.stream
overrides:
- admin_socket:
  - branch: wip-adk-testing-2023-03-28-1716
- ceph:
  - conf:
    - global:
      - mon election default strategy: 1
    - 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: 0d827ca1c6ef996567b7f5bc9aca774dc70bce60
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
      - osd default pool size: 2
- install:
  - ceph:
    - flavor: default
    - sha1: 0d827ca1c6ef996567b7f5bc9aca774dc70bce60
- workunit:
  - branch: wip-adk-testing-2023-03-28-1716
  - sha1: 0d827ca1c6ef996567b7f5bc9aca774dc70bce60
owner: scheduled_adking@teuthology
pid:
roles:
- ['mon.a', 'mon.c', 'mgr.y', 'osd.0', 'osd.1', 'osd.2', 'osd.3', 'client.0', 'node-exporter.a', 'alertmanager.a']
- ['mon.b', 'mgr.x', 'osd.4', 'osd.5', 'osd.6', 'osd.7', 'client.1', 'prometheus.a', 'grafana.a', 'node-exporter.b']
sentry_event: https://sentry.ceph.com/organizations/ceph/?query=8868d6340fba45279145d0c9972cdad7
status: fail
success: False
branch: wip-adk-testing-2023-03-28-1716
seed:
sha1: 0d827ca1c6ef996567b7f5bc9aca774dc70bce60
subset:
suite:
suite_branch: wip-adk-testing-2023-03-28-1716
suite_path:
suite_relpath:
suite_repo:
suite_sha1: 0d827ca1c6ef996567b7f5bc9aca774dc70bce60
targets:
- smithi006.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBLYZVPja1qxhE3Qpxj3fAutdO1amgaRe3RJHhMgqEUtYeuISqYX1A9rIRy1QfA8sZpvLW0XthCFpyuED0rWZLuQ=
- smithi135.front.sepia.ceph.com: ssh-rsa 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
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
    - sudo cp /etc/containers/registries.conf.backup /etc/containers/registries.conf
- cephadm:
  - allow_ptrace: False
  - avoid_pacific_features: True
  - cephadm_branch: v16.2.0
  - cephadm_git_url: https://github.com/ceph/ceph
  - image: quay.io/ceph/ceph:v16.2.0
  - conf:
    - global:
      - mon election default strategy: 1
    - 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: 0d827ca1c6ef996567b7f5bc9aca774dc70bce60
  - cluster: ceph
  - cephadm_mode: root
- cephadm.shell:
  - mon.a:
    - radosgw-admin realm create --rgw-realm=r --default
    - radosgw-admin zonegroup create --rgw-zonegroup=default --master --default
    - radosgw-admin zone create --rgw-zonegroup=default --rgw-zone=z --master --default
    - radosgw-admin period update --rgw-realm=r --commit
    - ceph orch apply rgw foo --realm r --zone z --placement=2 --port=8000
    - ceph osd pool create foo
    - rbd pool init foo
    - ceph orch apply iscsi foo u p
    - sleep 180
    - ceph config set mon mon_warn_on_insecure_global_id_reclaim false --force
    - ceph config set mon mon_warn_on_insecure_global_id_reclaim_allowed false --force
    - ceph config set global log_to_journald false --force
    - ceph orch ps
    - ceph versions
    - ceph -s
    - ceph orch ls
    - export TARGET_ID="$(ceph orch upgrade check --image quay.ceph.io/ceph-ci/ceph:$sha1 | jq -r '.target_id')"
    - echo $TARGET_ID
    - ceph orch daemon redeploy "mgr.$(ceph mgr dump -f json | jq .standbys | jq .[] | jq -r .name)" --image quay.ceph.io/ceph-ci/ceph:$sha1
    - ceph orch ps --refresh
    - sleep 180
    - ceph orch ps
    - ceph versions
    - ceph -s
    - ceph health detail
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="mgr") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==1'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="mgr") | select(.container_image_id!=$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==1'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - ceph mgr fail
    - sleep 180
    - ceph orch daemon redeploy "mgr.$(ceph mgr dump -f json | jq .standbys | jq .[] | jq -r .name)" --image quay.ceph.io/ceph-ci/ceph:$sha1
    - ceph orch ps --refresh
    - sleep 180
    - ceph orch ps
    - ceph versions
    - ceph health detail
    - ceph -s
    - ceph mgr fail
    - sleep 180
    - ceph orch ps
    - ceph versions
    - ceph -s
    - ceph health detail
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="mgr") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==2'
    - ceph mgr fail
    - sleep 180
    - ceph orch ps
    - ceph orch ls
    - ceph versions
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types mgr
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="mgr") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==2'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - cat out.json | jq -e '.[] | .container_image_id' | grep -v $TARGET_ID
    - ceph orch ps --format json | jq -e '.[] | select(.daemon_type!="mgr") | .container_image_id' | grep $TARGET_ID
    - ceph orch upgrade check quay.ceph.io/ceph-ci/ceph:$sha1 | jq -e '.up_to_date | length == 2'
    - ceph orch upgrade status
    - ceph health detail
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types mon --hosts $(ceph orch ps | grep mgr.x | awk '{print $2}')
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
    - ceph orch ps
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="mon") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==1'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="mon") | select(.container_image_id!=$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==1'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - ceph orch upgrade status
    - ceph health detail
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types mon --hosts $(ceph orch ps | grep mgr.y | awk '{print $2}')
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
    - ceph orch ps
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="mon") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==2'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - cat out.json | jq -e '.[] | .container_image_id' | grep -v $TARGET_ID
    - ceph orch upgrade check quay.ceph.io/ceph-ci/ceph:$sha1 | jq -e '.up_to_date | length == 5'
    - ceph orch upgrade status
    - ceph health detail
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types osd --limit 2
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
    - ceph orch ps
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="osd") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==2'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - ceph orch upgrade check quay.ceph.io/ceph-ci/ceph:$sha1 | jq -e '.up_to_date | length == 7'
    - ceph orch upgrade status
    - ceph health detail
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types crash,osd --limit 1
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
    - ceph orch ps
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="osd") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==3'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - ceph orch upgrade check quay.ceph.io/ceph-ci/ceph:$sha1 | jq -e '.up_to_date | length == 8'
    - ceph orch upgrade status
    - ceph health detail
    - ceph config get mgr mgr/cephadm/upgrade_osd_flags | grep noout
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --daemon-types crash,osd
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do if ceph osd dump -f json | jq '.flags_set' | grep noout; then touch saw_noout.txt; break; else echo "no noout yet"; fi; sleep 1; done
    - ls | grep saw_noout
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
    - ceph orch ps
    - if ceph osd dump -f json | jq '.flags_set' | grep noout; then (exit 1); else (exit 0); fi
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="osd") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==8'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - cat out.json | jq -e '.[] | .container_image_id' | grep -v $TARGET_ID
    - ceph orch upgrade status
    - ceph health detail
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1 --services rgw.foo
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; sleep 30 ; done
    - ceph orch ps
    - ceph orch ps --format json | jq --arg TARGET_ID "$TARGET_ID" -e '.[] | select(.daemon_type=="rgw") | select(.container_image_id==$TARGET_ID)' | jq -s > out.json
    - cat out.json | jq -e 'length==2'
    - cat out.json | jq -e '.[] | .container_image_id' | grep $TARGET_ID
    - cat out.json | jq -e '.[] | .container_image_id' | grep -v $TARGET_ID
    - ceph orch upgrade status
    - ceph health detail
    - ceph orch upgrade start --image quay.ceph.io/ceph-ci/ceph:$sha1
- cephadm.shell:
  - env:
    - sha1
  - mon.a:
    - while ceph orch upgrade status | jq '.in_progress' | grep true && ! ceph orch upgrade status | jq '.message' | grep Error ; do ceph orch ps ; ceph versions ; ceph orch upgrade status ; ceph health detail ; sleep 30 ; done
    - ceph orch ps
    - ceph versions
    - echo "wait for servicemap items w/ changing names to refresh"
    - sleep 60
    - ceph orch ps
    - ceph versions
    - ceph orch upgrade status
    - ceph health detail
    - ceph versions | jq -e '.overall | length == 1'
    - ceph versions | jq -e '.overall | keys' | grep $sha1
    - ceph orch ls | grep '^osd '
- cephadm.shell:
  - mon.a:
    - ceph orch upgrade ls
    - ceph orch upgrade ls --image quay.io/ceph/ceph --show-all-versions | grep 16.2.0
    - ceph orch upgrade ls --image quay.io/ceph/ceph --tags | grep v16.2.2
teuthology_branch: main
verbose: False
pcp_grafana_url:
priority:
user:
queue:
posted: 2023-03-29 11:58:28
started: 2023-03-29 16:15:54
updated: 2023-03-29 16:48:15
status_class: danger
runtime: 0:32:21
wait_time: 0:10:42