Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2024-03-01 20:53:49	2024-03-02 02:04:46	2024-03-02 03:08:12	1:03:26			smithi	main	centos	9.stream	3	dead

Nodes: smithi006 smithi007 smithi087

Description: rados/cephadm/workunits/{0-distro/centos_9.stream_runc agent/off mon_election/classic task/test_monitoring_stack_basic}

Log: http://qa-proxy.ceph.com/teuthology/yuriw-2024-03-01_20:50:47-rados-squid-distro-default-smithi/7578400/teuthology.log

Failure Reason:

Error reimaging machines: reached maximum tries (241) after waiting for 3600 seconds

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/yuriw-2024-03-01_20:50:47-rados-squid-distro-default-smithi/7578400/teuthology.log
archive_path: /home/teuthworker/archive/yuriw-2024-03-01_20:50:47-rados-squid-distro-default-smithi/7578400
description: rados/cephadm/workunits/{0-distro/centos_9.stream_runc agent/off mon_election/classic task/test_monitoring_stack_basic}
duration:
email: yweinste@redhat.com
failure_reason: Error reimaging machines: reached maximum tries (241) after waiting for 3600 seconds
flavor:
job_id: 7578400
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: centos
os_version: 9.stream
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
- selinux:
  - whitelist:
    - scontext=system_u:system_r:logrotate_t:s0
- workunit:
  - branch: squid
  - sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
owner: scheduled_yuriw@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: squid
seed:
sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
subset:
suite:
suite_branch: squid
suite_path:
suite_relpath:
suite_repo:
suite_sha1: 4c76c50a73f63ba48ccdf0adccce03b00d1d80c7
targets:
- smithi006.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBAbizU8/g+DqtePDJq71XLXETGmL0JXxY1EUaNFeNWPRIdxJVJe/ce1bfLoNbMT+G1WTHgUa60n3ZJbaBoB3P9s=
- smithi007.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBI6dMqL31uF2wbz9bBWEzZ3Z0+WBNqaVfKlqrTqz9j+KpUzkYs5/jFjwZQIwVQ9A9f3eFg/9pJ1O2iz1bf0K2BQ=
- smithi087.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBLQR3YJB/3K7ioEpJIrEgoexFWZL32wjON8attsCVL4eKAsB7axZYAoyFKthhvyzPsVEJlSnBOi61UbEFRT+fDc=
tasks:
- pexec:
  - all:
    - sudo dnf install runc -y
    - sudo sed -i 's/^#runtime = "crun"/runtime = "runc"/g' /usr/share/containers/containers.conf
    - sudo sed -i 's/runtime = "crun"/#runtime = "crun"/g' /usr/share/containers/containers.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: True
pcp_grafana_url:
priority:
user:
queue:
posted: 2024-03-01 20:53:49
started: 2024-03-02 02:04:46
updated: 2024-03-02 03:08:12
status_class: danger
runtime: 1:03:26