Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2024-06-13 14:13:45	2024-06-16 20:22:18	2024-06-16 20:23:52	0:01:34			smithi	main	centos	9.stream	3	dead

Nodes: smithi113 smithi138 smithi167

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

Log: http://qa-proxy.ceph.com/teuthology/pdiazbou-2024-06-13_14:12:47-rados-wip-pereman2-buffer-space-distro-default-smithi/7754002/teuthology.log

Failure Reason:

Error reimaging machines: Failed to power on smithi138

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/pdiazbou-2024-06-13_14:12:47-rados-wip-pereman2-buffer-space-distro-default-smithi/7754002/teuthology.log
archive_path: /home/teuthworker/archive/pdiazbou-2024-06-13_14:12:47-rados-wip-pereman2-buffer-space-distro-default-smithi/7754002
description: rados/cephadm/workunits/{0-distro/centos_9.stream agent/on mon_election/connectivity task/test_monitoring_stack_basic}
duration:
email: pdiazbou@redhat.com
failure_reason: Error reimaging machines: Failed to power on smithi138
flavor:
job_id: 7754002
kernel:
- kdb: 1
- sha1: distro
last_in_suite: False
machine_type: smithi
name: pdiazbou-2024-06-13_14:12:47-rados-wip-pereman2-buffer-space-distro-default-smithi
nuke_on_error:
os_type: centos
os_version: 9.stream
overrides:
- admin_socket:
  - branch: wip-pereman2-buffer-space
- 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: a7c6e10036e71ba3043677c46639ba98d34a4237
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
- install:
  - ceph:
    - flavor: default
    - sha1: a7c6e10036e71ba3043677c46639ba98d34a4237
- selinux:
  - allowlist:
    - scontext=system_u:system_r:logrotate_t:s0
- workunit:
  - branch: wip-pereman2-buffer-space
  - sha1: a7c6e10036e71ba3043677c46639ba98d34a4237
owner: scheduled_pdiazbou@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-pereman2-buffer-space
seed: 6874
sha1: a7c6e10036e71ba3043677c46639ba98d34a4237
subset: 512/20000
suite: rados
suite_branch: wip-pereman2-buffer-space
suite_path: /home/teuthworker/src/git.ceph.com_ceph-c_a7c6e10036e71ba3043677c46639ba98d34a4237/qa
suite_relpath: qa
suite_repo: https://git.ceph.com/ceph-ci.git
suite_sha1: a7c6e10036e71ba3043677c46639ba98d34a4237
targets:
- smithi113.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBLMtrU/x5nW4Lz54bZZxipzjLJeH71aRxvU6RMzUHArWZ9IkJPDkDYzkBUxbeuwjw6sE45T/4bx+nB8bboy7mQU=
- smithi138.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBOgoY+SJlqboxDtFqqnbSRVtcojfse5Ze0KX0F8AwfStEQ42gtD8c71hlxyhFTNW+pQR4cYPF7r5qHyda4wgReQ=
- smithi167.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBM6r3/kfV1WliCJr9pLSk9+5lZb1oSjkz2EymQ0iAsdeaUF8hrGqDWJo0LSm+KjWBaluZ3hKyx/EIpRnKxbm6nw=
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: False
pcp_grafana_url:
priority: 200
user: pdiazbou
queue:
posted: 2024-06-13 14:13:45
started: 2024-06-16 20:22:18
updated: 2024-06-16 20:23:52
status_class: danger
runtime: 0:01:34