Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2023-08-15 13:44:36	2023-08-15 13:45:16	2023-08-15 14:47:39	1:02:23	0:44:25	0:17:58	smithi	main	centos	8.stream	3	pass

Nodes: smithi006 smithi121 smithi174

Description: orch:cephadm/workunits/{0-distro/centos_8.stream_container_tools agent/off mon_election/classic task/test_monitoring_stack_basic}

Log: http://qa-proxy.ceph.com/teuthology/adking-2023-08-15_13:44:09-orch:cephadm-wip-adk-testing-2023-08-14-1902-distro-default-smithi/7368062/teuthology.log

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/adking-2023-08-15_13:44:09-orch:cephadm-wip-adk-testing-2023-08-14-1902-distro-default-smithi/7368062/teuthology.log
archive_path: /home/teuthworker/archive/adking-2023-08-15_13:44:09-orch:cephadm-wip-adk-testing-2023-08-14-1902-distro-default-smithi/7368062
description: orch:cephadm/workunits/{0-distro/centos_8.stream_container_tools agent/off mon_election/classic task/test_monitoring_stack_basic}
duration: 0:44:25
email: adking@redhat.com
failure_reason:
flavor: default
job_id: 7368062
kernel:
- kdb: True
- sha1: distro
last_in_suite: False
machine_type: smithi
name: adking-2023-08-15_13:44:09-orch:cephadm-wip-adk-testing-2023-08-14-1902-distro-default-smithi
nuke_on_error: True
os_type: centos
os_version: 8.stream
overrides:
- admin_socket:
  - branch: wip-adk-testing-2023-08-14-1902
- 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:
    - $MDS_ALL_DOWN$
    - $MDS_UP_LESS_THAN_MAX$
  - sha1: 3e38e80b384fd9a2477eb48b406e2dd38dd365a6
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
      - osd default pool size: 2
- install:
  - ceph:
    - flavor: default
    - sha1: 3e38e80b384fd9a2477eb48b406e2dd38dd365a6
- selinux:
  - whitelist:
    - scontext=system_u:system_r:logrotate_t:s0
- workunit:
  - branch: wip-adk-testing-2023-08-14-1902
  - sha1: 3e38e80b384fd9a2477eb48b406e2dd38dd365a6
owner: scheduled_adking@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: pass
success: True
branch: wip-adk-testing-2023-08-14-1902
seed:
sha1: 3e38e80b384fd9a2477eb48b406e2dd38dd365a6
subset:
suite:
suite_branch: wip-adk-testing-2023-08-14-1902
suite_path:
suite_relpath:
suite_repo:
suite_sha1: 3e38e80b384fd9a2477eb48b406e2dd38dd365a6
targets:
- smithi006.front.sepia.ceph.com: ssh-rsa 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
- smithi121.front.sepia.ceph.com: ssh-rsa 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
- smithi174.front.sepia.ceph.com: ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABgQD6RY3AQ5R04kbshhcFPDp082l2y2glGYoXlTPAzh43sMqkI50v61ejziuouaknlKjs9Onq6VGXcLamWR1fhB0S5lTUNk5omWz+WghsItc+Qz6qGABQt4ad7bp4JP1e27wbicAxVk6THNmb865MSKV8tZqd7JS9MgXBj2qWkPgOUTTS6qoAfJixSh5aIF5H2F5gebfGg0sPqoziybbp9RbR6ECgijbs8V5+JdYZ32w2S/1w52OoLFpsLJhyCntbtGWy9cE62KkuXcKhA+9eoXsjegFBY1oc1ZUaxf1u7dUXhJY1wV+syPEY8wHCtPy+tM5YvvoKuWLcUjC9a00rUHUJ5zBvUAOHTu5jr4fUEyJBbe9vgEMQZZXSTBp6Qv11QUZhpUUFBqubDQAAYX76/GT42GIkx/MfeeVzCXPnmj6fVS3SkNc1ubCC/f6ebZZCrlPhWDDAK7tn3xwZJqmEeyFxrtluA7MbVd7CirsHzwg5OVlAr2x97y77jpnThoJ9Izk=
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 --allowerasing --nobest
    - sudo cp /etc/containers/registries.conf.backup /etc/containers/registries.conf
- 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: False
pcp_grafana_url:
priority:
user:
queue:
posted: 2023-08-15 13:44:36
started: 2023-08-15 13:45:16
updated: 2023-08-15 14:47:39
status_class: success
runtime: 1:02:23
wait_time: 0:17:58