Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2024-05-03 06:32:49	2024-05-03 09:03:58	2024-05-03 09:12:30	0:08:32			smithi	main	ubuntu	22.04	3	dead

Nodes: smithi066 smithi098 smithi103

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

Log: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-05-03_06:31:58-orch:cephadm-wip-guits-testing-2024-05-02-0628-distro-default-smithi/7687235/teuthology.log

Failure Reason:

Error reimaging machines: Expected smithi098's OS to be ubuntu 22.04 but found centos 9

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-05-03_06:31:58-orch:cephadm-wip-guits-testing-2024-05-02-0628-distro-default-smithi/7687235/teuthology.log
archive_path: /home/teuthworker/archive/gabrioux-2024-05-03_06:31:58-orch:cephadm-wip-guits-testing-2024-05-02-0628-distro-default-smithi/7687235
description: orch:cephadm/workunits/{0-distro/ubuntu_22.04 agent/on mon_election/connectivity task/test_monitoring_stack_basic}
duration:
email: gabrioux@ibm.com
failure_reason: Error reimaging machines: Expected smithi098's OS to be ubuntu 22.04 but found centos 9
flavor:
job_id: 7687235
kernel:
- kdb: 1
- sha1: distro
last_in_suite: False
machine_type: smithi
name: gabrioux-2024-05-03_06:31:58-orch:cephadm-wip-guits-testing-2024-05-02-0628-distro-default-smithi
nuke_on_error: True
os_type: ubuntu
os_version: 22.04
overrides:
- admin_socket:
  - branch: wip-guits-testing-2024-05-02-0628
- 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: f8e6d2d721bc96a93915917c59bc3d287d57263d
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
- install:
  - ceph:
    - flavor: default
    - sha1: f8e6d2d721bc96a93915917c59bc3d287d57263d
- workunit:
  - branch: wip-guits-testing-2024-05-02-0628
  - sha1: f8e6d2d721bc96a93915917c59bc3d287d57263d
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: dead
success:
branch: wip-guits-testing-2024-05-02-0628
seed: 2184
sha1: f8e6d2d721bc96a93915917c59bc3d287d57263d
subset: 1/8
suite: orch:cephadm
suite_branch: wip-guits-testing-2024-05-02-0628
suite_path: /home/teuthworker/src/git.ceph.com_ceph-c_f8e6d2d721bc96a93915917c59bc3d287d57263d/qa
suite_relpath: qa
suite_repo: https://git.ceph.com/ceph-ci.git
suite_sha1: f8e6d2d721bc96a93915917c59bc3d287d57263d
targets:
- smithi066.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBE/X85XoZpinYNrs0ZLT5EcFLrmuWd4IxQi+JCybFFEgxF+8KD1f8cNB/3ujooXWW31jy3BB2HA8OtJBZPmHZVY=
- smithi098.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBK97ph1G97RYZLWvxsoC67/rw4VYgFc4AZsM3OMAWxAQuLQ7nu8fsD0FTQT5Oqn59zsjYW900o9BI+5KsMk8t1E=
- smithi103.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBHHlqlv7ojU5zPyOgn3P2TSmgzjAeFxb0iIjJjYU+rePmOAqCosi/WnJEtP+OlgKnpiSDtv7WTvuYWuqrh+Mw5I=
tasks:
- 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: 70
user: gabrioux
queue:
posted: 2024-05-03 06:32:49
started: 2024-05-03 09:03:58
updated: 2024-05-03 09:12:30
status_class: danger
runtime: 0:08:32